This PDF file contains the front matter associated with SPIE Proceedings Volume 12331, including the Title Page, Copyright information, Table of Contents and Conference Committee lists.

Remote sensing satellite system has many advantages, such as wide observation range and no geographical limitation, and has played a great role in agricultural exploration, ocean current monitoring, geological exploration and disaster investigation. In view of the fact that the traditional quality function deployment (QFD) method fails to consider the fuzziness of evaluation information and the allocation of experts' weights, an improved QFD method based on triangular fuzzy number and ideal point method is proposed, which can provide reference for the construction, optimization and upgrading of remote sensing satellite system.

In order to solve the noise pollution problem of off-road vehicle in the city, a high-duty dual exhaust silencer system was designed to reduce exhaust noise. Considering the flow characteristics of air and the nature of vibration, one front silencer and two rear silencers were adopted for exhaust system. The resistance silencer is used as front silencer to eliminate the high frequency noise while reactive silencer as rear silencer to eliminate the low frequency noise. Acoustics and hydrodynamics analyses of exhaust system were carried out based on Sysnoise combined with Fluent to obtain transmission loss, velocity, turbulent energy, pressure loss and so on. Based on these information, the acoustic and aerodynamic properties of the silencer are analyzed and evaluated. The analysis results show that the insert-pipe structure can broaden frequency bandwidth of noise reduction, and the silencer performance of different silencer units can be superposition after series.

Z-source inverters are able to use their unique impedance network to achieve the boost function, which can be better suited for applications with a wide range of input voltage variations. However, the conventional Z-source inverter has limited boosting capability and cannot meet the user's demand. And it suffers from the defects of high capacitive voltage stress and high start-up inrush current. In this paper, an enhanced quasi-Z-source inverter is introduced. Compared with the existing quasi-Z-source inverter topology, the enhanced quasi-Z-source inverter has the feature of continuous input current, a larger boosting capacity with the same boost factor and modulation mode, and improved the stability and reliability of the Z-source network.

The massive multiple-input multiple-output (MIMO) system is one of the most important key technologies in 5G era and will play an important role in the future telecommunication development. In massive MIMO signal detection, a huge number of matrix calculations need to be completed, especially matrix inversion. This makes the massive MIMO detection algorithm computationally complex and consumes lots of resources. Firstly, this paper briefly introduces and analyzes a variety of traditional iterative algorithms. Based on simplifying the inversion of MMSE matrix by solving linear equations, an improved algorithm is proposed to reduce the number of iterations by optimizing the initial solution to achieve the same detection performance as the traditional algorithms. The computational complexity of the proposed algorithm keep consistently at 𝑂(K²), which is one order of magnitude lower than the traditional ones.

China is a big country in aquaculture, but not a strong country, and the need for transformation and upgrading is urgent. The rapid development of intensive and large-scale aquaculture has put forward new requirements for online monitoring of water quality and automatic control of equipment. The current water quality monitoring IoT system has multiple brands of dissolved oxygen sensor equipment is not compatible, the application cost of replacing the dissolved oxygen sensor is high. In this research, an integrated A/D converter device for dissolved oxygen sensor interface is designed, without changing the premise of water quality monitoring IOT system architecture, to achieve different brands of dissolved oxygen sensor "plug and play". This research analyzes the mainstream brand dissolved oxygen sensors and designs the system architecture of the integrated A/D converter device. The integrated A/D converter device takes STM32F103C8T6 as the control core, is composed of power module, processing chip module, data storage module, signal acquisition module and data transmission module, and introduces the function and structure of each module in detail. Then a prototype was built, and the testing of the prototype was completed by building a test platform. The test result shows that the prototype can operate normally. Finally, areas for improvement and next works for the article are given.

Because the impact duration of a projectile is very short (microsecond level), it is difficult to observe stress evolution of iron matrix under the impact in an industrial field and a laboratory. For the purpose of conducting an in-depth analysis on the residual stress on iron matrix surface after impact, a finite element model was established and simulated on a computer. The results show that: (1) the projectile rebounds after imposing an impact force, and the oxide layer in a certain area on the surface of hot rolled steel is broken and stripped; (2) when the impact velocity is small, along with the increase of which, the maximum Mises stress of iron matrix increases; when the impact velocity is high, along with the increase of which, the maximum Mises stress decreases slowly; when the impact velocity value is 35 m/s, the maximum Mises stress value is the biggest, which is 641.1 MPa; (3) under the impact force, a plastic tunnel is formed on the surface of hot rolled iron matrix, and the tunnel depth increases with the increase of impact velocity, forming a roughly linear relationship between them.

In order to improve the accuracy and robustness of the small target detection for SSD (Single Shot Multi-Box Detector) algorithm, this paper proposes an improved SSD algorithm. Firstly, the Mish activation function is introduced in the backbone network to provide more linear relationships. Secondly, a copy-reduce-paste data enhancement method is proposed to ensure a more balanced train. In the multi-scale detection stage, feature enhancement module and feature fusion strategy guided by channel attention mechanism are used to improve the feature information. At the same time, modify the loss function to improve the model training effect. Experiments on the VOC2007+2012 dataset show that the detection performance of the proposed algorithm is better than that of the SSD algorithm.

Load forecasting is the basis of power network planning and power market transaction. Aiming at the characteristics of load driven by multi-dimensional factors and strong uncertainty, a long-term load probability prediction model based on non-parametric combined regression was proposed. Through Granger causality analysis, the multi-dimensional variables driving the long-term development of load are preliminarily screened. In order to improve the prediction accuracy, nonparametric combination regression modeling was carried out for the selected variable set based on the stepwise average combination to realize the optimal combination model and integrate the dynamic driving of each variable to the long-term load. Based on the random rate of change, the uncertainty modeling of multi-dimensional variables contained in the optimal combination model was carried out and applied to the probability prediction of long-term load to obtain the loci values of 10%, 50% and 90% of long-term load. Non-parametric combined regression model not only has high accuracy, but also can realize long-term load probability prediction combined with multi-dimensional variable uncertainty modeling.

Traditional WSNs clustering routing cluster head task is heavy, resulting in excessive network energy consumption. In order to reduce energy consumption and prolong the network life cycle, a non-uniform clustering routing algorithm based on Meanshift in SDWSN (SD-MNCR) is proposed. The controller uses the Meanshift clustering algorithm to campaign for cluster heads, and performs non-uniform clustering to reduce hot spots, and periodically refreshes the network. In the routing stage, the branch and bound method is used to realize the optimal path between cluster heads, and then the flow table is generated and sent to the sensor nodes to realize data transmission. Simulation experiments show that compared with LEACH, UCR and SDN-based ESR-W algorithms, SD-MNCR cluster heads have relatively low energy consumption and a relatively large number of cluster heads to survive, thereby prolonging the network life cycle.

With the development of carbon fiber composites with the extensive use of Carbon Fiber Reinforced Plastic (CFRP) and Aluminum alloy in car body, the traditional connection mode between carbon fiber and light metal cannot meet the development requirements of plate connection, and the Flow Drilling Screw process has well enriched the connection mode of heterogeneous materials. This paper takes CFRP plate with thickness of 1.5mm and Al5052 aluminum alloy plate with thickness of 1.5mm as the research object DEFORM-3D software simulates and analyzes the flow drilling screw process connection of CFRP-Al5052 dissimilar plates. According to the simulation results, the influence laws of the first stage screw speed, the second stage screw speed and pressing speed on the inter plate clearance, sleeve length and wall thickness of the formed joint are explored by using the range method, the influence weights of different process parameters on the joint forming are obtained, and the optimal combination of process parameters is obtained according to the analysis results.

As a hotspot for image processing and information fusion, image fusion technology can effectively integrate several source images from different sensors of the same scene or from the same sensor in different states, eliminating the redundancy among the source images while enhancing the complementarity. In this paper, an infrared and weak visible fusion algorithm based on detail-approximation decomposition is proposed. First, the visibility of brightness difference details in visible images is enhanced by using an adaptive image enhancement method based on high dynamic range compression of a rolling guide filter. Then an image decomposition method based on the fourth order partial differential equations is introduced to decompose the images into approximation images and detail images. Next, detail images are fused by principal component analysis and approximation images are fused by Visual Saliency Map. The final fused image is obtained by combining the detail fusion and approximation fusion results. This fusion method can transfer the important information of infrared images to the fusion image well, while retain the details and background scenery of the input visible images. Experimental comparisons with existed methods show that this algorithm can achieve better fusion performance under poor illumination conditions.

The internal combustion engine is a power generating device. For the machine, the internal combustion engine is its "heart", and the connecting rod plays a role of transmitting force in the internal combustion engine and is one of the most important components in the internal combustion engine. In this paper, the three-dimensional solid model of the crank-link mechanism of single-cylinder four-stroke internal combustion engine is established. It is imported for kinematic simulation analysis. The kinematic and dynamic characteristics of piston and connecting rod in internal combustion engine are observed by post-processing of results. At the same time, a finite element model is established to check the safety factor of static strength and fatigue strength of connecting rod. According to the theory and method of mechanical reliability design, the reliability of connecting rod is analyzed.

At present, the point clouds-based 3D target detection technology has many researches and applications in the field of car automatic driving, but there is no 3D target detection technology for ships. Ship navigation is different from car driving. There will be waves in the channel, undulations occur when the ship is sailing, and there is often fog above the channel, which affects the quality of lidar imaging. These will bring many difficulties to the detection of 3D targets of the ship. In order to deal with the complex noise in the point clouds in the waterway scene, we fused a variety of filtering algorithms to preprocess the point clouds, and in view of the ups and downs of the ship during the sailing process, a point clouds fusion sampling algorithm is introduced on the basis of the PointRCNN algorithm, and established lidar standard coordinate system. The experimental results show that the improved algorithm is more suitable for ship detection than the PointRCNN algorithm, and has higher detection accuracy for ship targets. This research expands the scope of application of 3D target detection, and provides a theoretical basis for subsequent applications such as ship gate risk warning.

One of the main challenges in Tokomak fusion reactor is the design of the breeding blanket since it is the first wall to the plasma. It can be seriously damaged due to the high heat flux and particle impact. However, liquid blankets could be a perfect solution to resist structural damage on the breeding blankets. On this basis, we designed a preliminary liquid blanket structure, using porous tungsten as frames and producing liquid film on frames’ surface, and investigated the thermo-mechanical properties of a porous medium unit based on COMSOL Multiphysics. According to the analysis, under compressive pressure load, the unit structure was stable mechanically. Besides, as for thermal analysis, the porous medium was great for injecting slow fuels and temperature can drop dramatically through the width. Hence, it verifies the stability and feasibility of such a structure. Nevertheless, both simulations could be further improved by revising the model and updating the initial conditions. Overall, these results shed light on future breeding blanket design.

To meet the more demanding requirements of the modeling and simulation technology in various fields, more diverse modeling languages and methods are emerging, which in turn makes it more challenging to integrate and reuse heterogeneous models for field applications. Therefore, it is necessary to extract a constructional frameset of heterogeneous models based on a unified modeling language. This paper presents a method of constructional frameset extraction and feature quantization to address the issues of matching, classification, and composition of multi-domain heterogeneous models. Firstly, heterogeneous models are converted into unified models, which are described by X language. Then, the structural features of each X model are extracted to be incorporated into a predefined template. Then the template can be quantified in the form of a binary tree. The sequence obtained by inorder transversal of the binary tree can be a quantified feature of the template. All the model templates make up the constructional frameset of multi-domain heterogeneous models. The results show that the proposed method can abstract the features of multi-domain heterogeneous models and support a constructional frameset library to rapid modeling, integration, and reuse.

The high energetic particle generated from nuclear fusion will severely change material structures and properties of the reactor, where the surface of the steering gear would become fluffy. On this basis, the SRIM software is introduced in this paper, aiming to investigate the impact of different ions with different masses and energies on material structures in order to observe the damage on the material caused by the radiation. According to our simulation, a drop in 13% elastic property has been observed. The bombardment can produce a considerable amount of damage, which should be taken into consideration during the design. Thus, the tungsten shield can’t be used as weight supporting element. Besides, regarding the above discussion, a wider margin should be taken into consider when designing the fusion reactor. We hope to figure out some uncontrollable error and imperfection still existing in the simulation. These results offer a guideline for better observation of the damage on the material caused by the radiation.

In order to improve the accuracy of structured light measurement, this paper proposes a color surface structured light three-dimensional reconstruction method based on DB sequence. In the encoding stage, according to the principle that the greater the Euclidean distance between two points in the RGB space model, the greater the color difference, the color of adjacent stripes in the stripe pattern is constrained; in the decoding stage, in order to eliminate the influence of ambient light on the edge color of the stripes, Based on the threshold method, an improved algorithm is proposed. First, the color of the main area of the stripe is corrected by setting the RGB three-channel threshold. For the point where noise is generated by the crosstalk on the stripe boundary, a single-channel threshold and the other two-channel color are proposed. The method of co-constraining the size of the components. The experimental results show that for the measurement of achromatic objects, this method has high measurement accuracy and can be used for actual measurement.

Substituting plastic for steel in automotive piping is an important indicator for achieving lightweight vehicle. Research on high-precision and high-quality plastic piping has become a hot spot now. In the production process of plastic pipes, the extrusion production process is the most complicated, with the most influencing factors, and the most difficult to establish an accurate mathematical model. Therefore, establishing an accurate prediction model of the extrusion system is the key to improving its control accuracy. Based on this, this paper studies a back-propagation neural network (SSA-BP) optimized based on the Sparrow search algorithm, which takes the melt temperature, melt pressure, screw speed and traction speed of the production line as input variables, and pipe wall thickness as output variables. The prediction result uses the average absolute error, the mean square error and the average absolute percentage error as evaluation indicators. By comparing the prediction results of the SSA-BP algorithm and the BP algorithm, it is finally concluded that the SSA-BP algorithm has a higher prediction accuracy.

Simplifying the complex vibration reduction design process makes sense and helps engineering to improve efficiency. The passive vibration reduction system of electronic equipment is simplified and equivalent to a single degree of freedom damped forced vibration system, and based on reasonable simplification, equivalence and approximation, a complete theoretical analysis model and mathematical calculation model of vibration damping of electronic equipment are established by replacing the complex nonlinear vibration theory with simple linear vibration theory. The vibration reduction characteristics of vibration damping and the factors affecting the vibration reduction effect are studied and analyzed, the influence of damping on resonant frequency and resonant vibration transmission rate is given, and the mathematical model for evaluating the vibration reduction effect of random vibration excitation is established. Combined with engineering experience and empirical formula, the general process and key design process of vibration reduction design suitable for engineering application are given. Taking the vibration reduction design of an electronic equipment as an example, the complete process of vibration damping system design is demonstrated, which provides an example reference for engineering design.

Railway switch machine circuit action Curve feature is essential for railway turnout control system fault diagnosis research. In recent research, manual extraction of curve features or supervised learning based on data sets with fault labels to construct diagnostic models has been most adopted, which requires enormous energy and time. Therefore, a method based on one-dimensional residual convolutional Auto-encoder is proposed for curve features extraction in this paper, which can decrease the workload of manual annotation of data sets and lower the influence of the minor duration difference of the switch curves data on code over-fitting through the flexibility of unsupervised learning auto-encoder and convolutional neural network. According to the experiments, the proposed model can effectively extract key switch machine curve features and can featuring strong adaptability.

The application scope of UAV in the power field is gradually expanding, which puts forward higher requirements for the accurate landing of UAV. At this stage, the fixed-point landing of UAV mainly depends on RTK, but RTK is easy to be disturbed by the external environment, so it can not meet the requirements of fine landing. This paper proposes an improved yolov4-tiny algorithm, which adds the convolutional attention module to the yolov4-tiny network structure feature pyramid to reduce the interference of complex backgrounds on target recognition. In this system, the UAV is guided to fly above the nest by RTK in the first, and then the landing code is recognized by improved yolov4 tiny algorithm, so as to realize the accurate landing of UAV. Through the field fine landing test of UAV, it is found that the landing accuracy of the proposed technology is high and meets the landing requirements.

Hydraulic expander adopts the principle of force-increasing mechanism, which has the most powerful functions of expanding, pulling and tearing in emergency rescue, and can still carry out emergency rescue work under high load. In this paper, based on a certain type of hydraulic expander, the kinematic closed-loop vector model is established, and the simplified simulation model of the expander is established in the virtual prototype ADAMS. The virtual experiment results show that the motion acceleration of the dilator is small and changes smoothly, and it has good dynamic performance.

In this paper, the study of sliding mode control for nonlinear aero-engine distributed control system with time delay and packet loss is carried out. First, the system is modeled as a kind of Markov jump system with unmatched disturbance. Then, a linear sliding mode surface is proposed which is robust to unmatched disturbance. Linear matrix inequality method is used to solve the sliding surface parameter which makes the system mean square asymptotically stable. The RBF neural network is combined with sliding mode control theory in controller designing where the RBF neural network is used to solve the control input that satisfies the sliding mode reaching condition. Simulation results show that the designed controller can make the system stable in a fast time under the conditions of time delay and packet loss.

The detected temperature in the chassis is converted into voltage signal by thermistor, and then the voltage signal is converted into digital signal by analog digital converter inside single chip microcomputer STM32. The temperature sensor is also used to convert the detected temperature into IIC bus, which is connected with the internal IIC interface of STM32, so STM32 can read and write data directly. PID algorithm is used to control the speed of DC fan through PWM. Finally, the test results show that the control module can well control the fan speed and adjust it according to the temperature in the chassis.

Using computational fluid dynamics method, numerical simulation is carried out on the typical two-dimensional multi-segment wing with the deflection hinged flap configuration of spoiler, and the influence of the down-deflection of the spoiler on the Reynold number effect of the multi-segment wing is studied. the result show that: Within the scope of this article, 1) The camber effect produced by the deflection of spoiler can increase lift at small angles of attack but has a limited effect on the C_L-MAX; 2) The spoiler down-deflection configuration has a limited affection of Reynold number in linear segment, which is more affected near stall, the slope of C_L is affected by Reynold number.

The development of social information technology provides technical support for the arrival of the big data era. Big data and its related technologies have been gradually integrated into people's lives. Conducting big data technology and data mining technology, this paper adopts the vehicle networking scheme in vehicle driving, that is, each vehicle is connected to a data center, and analyzes the driving safety on the basis of a large number of vehicle driving data. The algorithm can be subdivided into three steps: data acquisition, using time series analysis method to obtain driving indicators, and classification and processing of various indicators by clustering algorithm. Through data mining technology and driving safety algorithm, the risk factors in the process of vehicle driving can be found in time, so as to ensure vehicle driving safety.

Wearable health monitoring system can realize human health monitoring without relying on fixed medical places and complex equipment, which has important research value and application value. In this paper, a wearable health monitoring system based on walking exercise is studied, and the built-in sensors in smart phones are used for health monitoring based on walking exercise. This article first analyzes the overall architecture of the wearable health detection system. Use the built-in sensors in the smartphone to perform health monitoring based on walking motion, study the differences in gait parameters of pedestrians between different age groups and the same age group, and analyze the correlation between basic physical information and gait parameters of pedestrians sex. According to the experimental data, it is concluded that parameters such as stride length, stride speed, stride frequency, and thigh swing angle peak are closely related to the movement function of the human lower limbs, which are used as indicators for human health monitoring.

A precise and accurate dynamic model of the lower limb exoskeleton is particularly important for the optimization of the exoskeleton mechanical structure parameters and the design of the control system. Different scholars choose different ways of modeling, which can be generally based on absolute coordinates and relative coordinates. In order to analyze the correctness of the two modeling methods, the dynamic model of the lower limb exoskeleton with 2 degrees of freedom in absolute coordinates and relative coordinates is established by using Lagrange equation. The contribution of this paper is that by comparing the torque expressions of hip and knee joint under the two modeling methods and combining with the derivation process, the correctness of the dynamic model under the two coordinate systems is qualitatively analyzed. This provides a reference for researchers to accurately model the lower limb exoskeleton.

In this paper, a method for controlling the parachute opening device of a small sounding rocket through a multi-sensor fusion algorithm is proposed. This method uses IMU, airspeed tube and GNSS to obtain acceleration, velocity and position information respectively. After processing the three sets of data, the corresponding speed data is obtained, and the more accurate speed data is obtained through the Kalman filter algorithm. The vertical speed is used as the basis for the parachute-opening judgment condition and the timing of parachute-opening. Through simulation and experimental results, this method of parachute control of the sounding rocket proved to be very effective. This method can significantly reduce the accuracy requirements for the sounding rocket sensors, and obtain relatively high-precision results through the fusion processing of data collected by multiple low-precision sensors. This method can be used in the parachute control system of low-cost sounding rockets, which is of great significance for reducing the cost of small sounding rockets and promoting commercial applications.

For the requirements of high efficiency of communications satellite on solid state power amplifier in the broadband. In this paper, a power amplifier works in 3.7-4.2GHz using gallium nitride (GaN) based high electron mobility transistor (HEMT) for satellite application was presented. The test results show that in the 3. 7-4. 2 GHz frequency range, under the conditions of the drain voltage of 28 V, the gate voltage of -2.8 V and continuous wave, the saturated output power and drain efficiency of the designed amplifier in this paper are above 40.02 dBm and 59.6% respectively.

As a modern means of transportation, automated guided vehicle (AGV) has been widely used in production workshops, warehouses and logistics transportation. In the production workshop, the order change and machine failure in the actual production process have a great impact on the transportation of AGV. This paper studies an AGV rescheduling model, which can effectively improve the transportation efficiency of AGV transportation system. Based on the above model, a discrete invasive weed optimization (DIWO) algorithm is proposed. In order to verify the effectiveness of the model, this paper takes a Foxconn workshop as a comparative case.

At present, the commonly used Angular Rate Gyro components on aircraft are mostly Liquid Floating Gyroscopes, but the disadvantages of locked rotor caused by the wear of its bearings and rotors are gradually exposed in long flight. In contrast, Fiber Optic Gyroscope (FOG) has the advantages of wide dynamic range, wide measurement range, less affected by vibration and impact, fast start-up and long service life. In order to realize the use of fog components in aircraft, this paper analyzes the main error sources affecting the accuracy of fog by modeling the fog components. Finally, according to the main characteristics of fog changing with temperature, it is proposed that the error can be reduced by Least Squares - Support Vector Machine method.

Aviation electro-mechanical system development process with a large number of experimental data, the use of traditional data processing algorithm is difficult to effectively utilize contains information to data modeling of system operating mode, in order to solve this problem using the intelligent fault diagnosis of intelligent data mining algorithm driven architecture, dig deeper into the historical experimental data modeling, data driven fault discrimination and trend prediction. As a sample to use machine learning algorithm for fault diagnosis of mechanical and electrical hydraulic subsystem process, using the offline to deep mining, hydraulic test data collected fault condition data model is set up and use the validation data verification, analysis of test data of abnormal trend, finally according to the actual task plan for different maintenance support decision making to ensure the safe and stable operation of aircraft electromechanical system, realize the application of data mining and PHM technology in aircraft electromechanical system, and put forward a new idea for future research work.

In order to improve the heat dissipation performance of the rectangular cooling channel of the shearer electric control box, this paper proposes to add arc spoilers on the left and right walls of the rectangular channel. The heat transfer characteristics and flow characteristics of the spoiler block are explored through numerical calculation methods, and the influence of the ratio of the structural parameters of the spoiler (height h, radius R) to the channel width D on the fluid flow characteristics and heat transfer characteristics is studied by the control variable method. The research shows that when the spoiler radius ratio R/H=1, D/H =0.12, the comprehensive heat transfer efficiency of the rectangular flow channel is the highest.

Electric vehicle load forecasting is the basis for the safe and stable operation of the distribution network, and it is also a prerequisite for the planning and layout of electric vehicle infrastructure. Firstly, considering the characteristics of electric vehicles as participants in the transportation network and the characteristics and mobile load characteristics of electric vehicles as vehicles, a method for forecasting the temporal and spatial distribution of electric vehicle charging load considering traffic flow is proposed. This method first establishes a road network model that considers the flow-density-speed model and the road section impedance and node impedance based on the traffic flow of the road section based on the characteristics of the urban road network multiple intersections and the traffic flow of each section. Secondly, introduce the time function of charging probability and Freud's path search algorithm to assign start and end nodes and plan the driving path for electric vehicles to simulate its dynamic driving process and charging behavior. Finally, a simulation experiment of charging load prediction is carried out with a typical regional road network. The result shows that the distribution of electric vehicle charging load in different functional areas is different and the time distribution is uneven, which verifies the effectiveness and feasibility of the proposed method.

This paper describes a new wear prediction model for a three-dimensional fractal friction surface considering scale dependence. The analytical formulas for critical microcontact area and critical level are derived. According to the truncated area distribution function of asperities at multiple-scale levels, the total real contact area of different deformation stages on the rough surface is obtained respectively. Based on the traditional adhesion theory and fractal theory, and introducing the concept of multi-scale, the wear fractal model of rough friction surface is established. The effects of fractal roughness, fractal dimension, and total contact load on the wear rate are analyzed by numerical simulation. The numerical results show that as the fractal dimension increases, the wear rate decreases first and then increases. There is an optimal fractal dimension to make the wear rate reach the lowest value. With the increase of the fractal roughness, the wear rate will increase. For the fixed surface fractal parameters, the wear rate will increase with the increase of the normal load.

This paper introduces a seawater desalination device based on solar energy and wave energy, and analyzes and studies the wave energy utilization part. The designed seawater desalination device uses heat pipe vacuum tubes to collect solar energy, undergoes heats desalination through a multi-effect distillation system, and utilizes duck-like wave energy capture devices to obtain mechanical energy. The device uses wave energy as mechanical power and transmits the mechanical energy to the reciprocating pump through the gear shaft to complete the conversion of wave energy to mechanical energy, thereby realizing the use of non-electric wave energy. According to the actual conditions of China's sea area, the wave energy-based mechanical power system is analyzed and calculated, and the mechanical conversion efficiency of the system is given.

A scheme of global position system (GPS) disciplining Coherent Population Trapping (CPT) atomic clock is studied. The state equation and observation equation of the GPS disciplining CPT atomic clock system are derived. The state noise parameters for the state equation are obtained according to the relationship between the frequency stability of the output signal of the CPT atomic clock and the noise. The relevant noise parameters of the state equation are calculated. A Kalman filter is designed according to the established state equation and the observation equation, and applied to process the output frequency signal of a CPT atomic clock. The experimental results reveal that the frequency stability/day of the GPS disciplining CPT atomic clock using Kalman filter is one order of magnitude better.

Harvesting human motion energy to power intelligent wearable devices is a research hotspot in the field of energy harvesting. Due to the characteristics of ultra-low frequency of the vibration generated by human motion, the conventional piezoelectric energy harvester cannot work efficiently. This paper proposes a magnetic coupled piezoelectric energy harvester which is composed of two piezoelectric cantilever beams, two endmost magnets, a center magnet, and a tube. The ultra-low frequency vibration of human motion is sensed by the center magnet in the tube and coupled to the piezoelectric cantilever beams by the repulsive force between the endmost magnet and the center magnet. The mathematical model of the harvester is established, and the influence of various parameters on energy harvesting efficiency is analyzed in detail. Through simulation analysis, the proposed harvester can effectively harvest ultra-low frequency vibration energy of human motion.

Silicon-based electronic products have gradually been unable to meet environmentally friendly requirements. Flexibility, environmentally friendly, high efficiency and low cost are becoming important directions. The biggest challenge is how to produce environmentally friendly sensors. Here, paper-based materials are selected as the substrate, which can meet the requirements of environmentally friendly. The direct writing technology with low-cost is selected for preparation. We formulated a liquid precursor material for direct writing ink. Ink does not need to synthesize nano materials in advance, as long as it is prepared according to the method mentioned above, and the preparation method is simple and short in time. Combining low-cost direct writing preparation technology, it can realize low-cost and efficient preparation of green and environmentally friendly flexible devices. Using direct writing technology, the ink was directly written onto the surface of the paper substrate, and the influence of direct writing parameters on the preparation structure was studied. The device obtained by direct writing is put into an oven and heated, so that the precursor ink is transformed into a silver micro-nano structure. The influence of different temperatures on the formation of silver structure was studied, and it was concluded that the effect was best when the temperature was 100 degrees Celsius. The prepared paper-based sensor is then used for finger bending signal detection. It can detect the bending of the finger very well. The method is simple, high-efficiency, low-cost, and can prepare a flexible and environmentally friendly force-sensitive sensor. Based on this method, it can also be used for the preparation of other devices.

The missile electrical system is an important part of the weapon system. During the operation of the missile, according to the system required work sequence, it provides time-sharing power supply for the various components on the missile to provide a stable and reliable power supply, stable signal transmission link. The stability of the electrical system and the quality of the power supply play a vital role in the flight mission. Normalization, modularization and standardization design criteria point out the direction for the design of electrical systems.

An interior ballistic model of hydrogen-oxygen combustion of the combustion light gas gun is built to perform numerical calculations by using the Van der Waals equation, the RKS equation and the P-R Equation, respectively. Comparing the calculation results with the experimental results in the literature, it is found that the results obtained through the PR equation are closer to the experimental results. Using the equations of real gases, the influence of different projectile masses, hydrogen-oxygen molar ratios, and initial pressures on the interior ballistic performance are calculated. The results show that the projectile mass will affect the interior ballistic time, the acceleration, and the projectile's initial velocity; the hydrogen-oxygen molar ratio and the initial pressure will affect the interior ballistic time, the maximum bore pressure and the initial velocity.

Oxygen-enriched is the more mentioned technology at thermal engineering in energy saving recently, which is called as ‘resource creation technology’. The paper used oxygen-enriched experimental platform of gas boiler to test the thermal indexes of the boiler under local oxygen-increasing. The conclusion showed: Deceasing unburned heat exhaust of the boiler is the main measure for local oxygen-enriched to improve the boiler efficiency. For local oxygen-enriched, we should make the flow and the combustion inadequacy gas mix fully where the fuel combustion was most inadequately, as to improve burnout rate of fuel and decrease the unburned heat exhaust farthest.

With the deterioration of environmental problems and the energy transformation needs of governments, the consumption of renewable resources has increased sharply. The intermittency of renewable energy is one of the important factors limiting its large-scale application. Air liquid energy storage technology is one of the effective methods to solve the intermittency problem of renewable energy. Air liquid energy storage technology has advantages over other energy storage technologies in system efficiency, energy storage density and geographical selection. This paper introduces the research status of air liquid energy storage technology from four aspects: the principle of circulation technology, the influencing factors of system performance, the system evaluation index and the system integration. The defects and future development direction of air liquid energy storage system are analyzed.

In this paper, the effects of different initial head-on wind speed and heat exchange temperature difference on the frosting and performance of heat exchanger are studied by using wind tunnel experimental device. The results show that with the frost amount under different initial head-on wind speed and different heat exchange temperature difference increases with the frost time, while the growth rate of frost amount gradually increases with the increase of heat exchange temperature difference. And the refrigeration capacity and heat transfer coefficient almost increased first and then decreased.

Generator loss of excitation protection is generally based on the R-X coordinate plane, while the low excitation limit is generally based on the P-Q coordinate plane. Due to the above two are not on the same coordinate plane, the coordination relationship between them cannot be shown intuitively. A0 reduction method suitable for engineering practice is proposed, that is, the setting of loss of excitation protection is mapped from R-X coordinate plane to P-Q coordinate plane. Based on P-Q coordinate plane, generator loss of excitation protection and low excitation limit are calculated, and the correctness of the method is verified with a cooperation of network related protection example of a power plant.

A fast and effective early warning method is proposed in this paper for the possible collision between the large portal crane and gantry crane cross-operation, which are widely used in port, in the same workplace. This method can eliminate the hidden danger through systematic methods before the collision of equipment, so as to effectively avoid the accident caused by the collision of equipment.

The vibration isolation components with viscoelastic and nonlinear characteristics of rubber are simulated by establishing a fractional nonlinear Zener model. The fractional differential terms are treated by Caputo definition, and the dynamic performance of the system is simulated by numerical simulation. The periodic motion stability and motion transition law of the system are studied by establishing Poincaré mapping, and the motion stability is determined by combining the maximum Lyapunov exponent. It is found that the fractional differential term defined by Caputo can not only be equivalent to the linear spring stiffness and linear damping coefficient, but also related to the frequency of external excitation. With the decrease of the external excitation frequency, the nonlinear system with fractional differential produces two different attractors under the induction of fork bifurcation, and the number of attractors doubles under the induction of period-doubling bifurcation. after the system enters the chaotic motion, under the induction of cataclysmic bifurcation, different attractors combine with each other as a whole, and the phase trajectory of the system transforms into a single symmetric chaotic motion.

For the boring bar’s chatter, based on the built-in damping boring bar, a type of magnetorheological semi-active dynamic vibration absorbing boring bar component was proposed. And a nonlinear dynamical model of absorbing boring bar was established. An analytical solution for the system's dynamical response is obtained by the multi-scale method, which is verified by the numerical solution, and the changes in the boring bar system parameters on the effect of dynamic characteristic was explored, the results provide the basis for the monitored control of the boring bar’s cutting chatter.

The centrifugal casting method was introduced to successfully fabricate the SiCp/Al composites electronic packaging components. Three zones including the SiC particle segregation zone, matrix alloy region and inclusion collecting zone were observed on the cross section of the casting due to the SiC particles in the slurry migrating towards the centrifugal force direction while the inclusions segregating to the revolving axis in the centrifugal field. The macro-morphologies and the microstructures of the castings were observed. The results show that the electronic packaging components obtained from the particle segregation zone has a dense structure and a uniform distribution of SiC particles. Especially, the leading-out wire holes on the components were directly formed during the centrifugal casting process. The castings had the most remarkable segregation of SiC particles, the volume fraction of SiC particles in the particle segregation zone can reach the largest value of 61%.

Eight different height-to-length ratio forward-facing steps are investigated in this paper to study the tolerance of steps on leading edge of the main wing of an aircraft during landing. Numerical simulation is applied to simulate the separation and subsequent vortex formation around a multi-element airfoil with various steps. Aerodynamic characteristics of different steps show that steps with H/L ratio less than 1/4 turn out to have less effect on aerodynamic performance of an aircraft. Inclined plane can be applied to the trailing edge of the slat during high lift devices design.

The gap of elevator horizontal sliding door is an important safety index of elevator. When the horizontal sliding door is applied on the most unfavorable point with an external force of 150N in the opening direction, the door gap shall not exceed 30mm. However, the manual measurement has the defect about low efficiency and accuracy. This article designs an instrument for measuring the gap of elevator door leaf in force exertion state. The instrument contains support plates, oil cylinders, scale, drive arm, handle, plunger pumps, ejector rod, positioning hole and spring. While using, the inspector inserts the instrument into the gap of the horizontal sliding door and swings the driving arm. When the second support plate is not aligned with the scale and the ejector rod slides out of the positioning hole, it indicates that the external force of 150N makes the door gap less than 30mm. The operation of the instrument is Optimized, so that single inspector can easily complete the measurement and identify the results directly. The instrument is also convenient to reset after measurement and easy to carry. The instrument has the feature of high accuracy, simple operation and well portability. The horizontal sliding door also can be avoid damaging during the measurement process.

The main purpose of this paper is to build a mathematical model of virtual pallet in tobacco logistics center. We take Beijing Tobacco Sorting System as an example to verify the consistency of the mathematical model. The experiment shows the model is reasonable and when optimal length of virtual pallet is suggested, the sorting efficiency is increased by 7.8%.

In order to solve the problem of trackless transportation of materials and equipment in vertical shaft coal mines, in view of the restricted space where vertical shaft cage dimensions are generally ≤5.0m in length and ≤2.0m in width, and the diversified transportation needs of underground, as well as the harsh working conditions such as slippery and sloping roads, a platform-based R&D model is proposed to first develop a compact articulated main platform of power transmission based on which the development of a series of articulated explosion-proof rubber-tyred vehicles that can enter and exit the vertical shaft cage directly. The key technologies such as the overall design of the vehicle, determination of the main parameters, development of the compact platform, multi-mode design of the driving unit, expanded design of working devices. The articulated trackless rubber-tyred vehicles for vertical shafts applying the above key technologies and design solutions have been verified in Wangcun coal mine of Jinneng Holding Group. The test results show that: the technical performance of vehicle fully meets the needs of the production site, The research on the key technology, design ideas and methods of the compact trackless rubber wheeled vehicle can solve the problems of the trackless vehicles enter and exit the vertical shaft cage directly, diverse transportation needs and poor safety protection in harsh working conditions.

According to the 25% overlap frontal crash procedure formulated by Insurance Institute for Highway Safety, a test was conducted on a prototype vehicle. The test results showed that it’s cross car beam was fallen off from the Body-in-White along the Y axis of the vehicle coordinate system. In order to improve the crash safety of this vehicle type, this paper adopts parametric modeling, carries out finite element analysis on the statics module of Ansys Workbench for the cross car beam, and optimizes the cross car beam from the design standards and material properties. Then the aforementioned static analysis and real vehicle crash test are repeated after the optimization, the results show that the stress at the failure areas is dramatically reduced and the beam doesn’t fall off from the Body-in-White, which verifies the effectiveness of the scheme and provides a reference for the design and optimization of the cross car beam.

In the application practice of robot autonomous navigation, the path tracking algorithm as the control layer is the key technology to realize the intelligence and practicability of robot, which directly determines the bionic level of robot self perception and autonomous action. Path tracking can be regarded as a control problem. In this paper, the control problem of mobile robot path tracking is studied. Firstly, the multi degree of freedom kinematics model of robot mobile mechanism is established, the path tracking control system is decoupled into speed following closed-loop control and steering angle control subsystems, and a path tracking controller based on optimization theory is proposed, The control algorithms are designed for the tasks of robot tracking specific target points and tracking arbitrary path curves, and the tracking performance of the controller based on the optimization theory is verified by simulation analysis. The simulation results show that the control algorithm has the advantages of simple algorithm, good real-time performance and strong autonomous tracking and navigation ability in robot path tracking.

Lightweight structure of a rescue robot for a high voltage transmission line is the key to its practical stage. In this paper, taking the shell of the rescue robot arm of high voltage transmission line as the object, aiming at the minimum mass of the structure and taking stiffness as constraint conditions, the topological optimization design of the structure was carried out, and the three-dimensional topological configuration of the shell structure was obtained. According to the topological optimized configuration, the three-dimensional structure of the manipulator shell is reconstructed and the finite element stress is verified and analyzed. By comparing the stress analysis results before and after reconstruction, it is found that the mass of the reconstructed manipulator shell is reduced by 41.40% under the conditions of satisfying the structural strength and stiffness. The research ideas and results in this paper can provide ideas for the pro-quantitative design of other structures of the transmission line rescue robot.

In this paper, a truss-shell integrated antenna support structure has been proposed to meet the requirements of 5 large-aperture floor antenna layout. By combining the truss configuration optimization and size optimization, the comprehensive optimization of the mass and stiffness of the antenna structure has been realized under the condition of meeting the mechanical constraints, with the weight reduced by more than 1/3, which meets the lightweight and integrated requirements of the antenna support structure, and has a broad application prospect.

A new energy vehicle is a product that combines modern technology with traditional battery technology. It has the advantages of energy saving, environmental protection, and long service life. How to collect and feedback the utilization rate of new energy vehicles is a big problem. This paper designs the car's operation monitoring system by studying the convolutional neural network, the purpose is to extract useful information through the monitoring of the car, and promote the development of new energy vehicles. This paper mainly analyzes the application loss function and IOU of the monitoring system of new energy vehicles through experimental methods, and compares them to highlight the characteristics and functions of the convolutional neural network in the monitoring system. The experimental results show that the loss value is below 0.17 after a hundred trainings, and gradually decreases to 0.01. The application of convolutional neural network in the monitoring of new energy vehicles is feasible.

Vehicles need to accelerate frequently when dealing with road conditions during driving. The meshing impact load generated during acceleration is likely to cause surface and plastic deformation of gear teeth, which affects the balance of transmission power. Therefore, it is very important to clarify the impact of dynamic impact on gears during rapid start-stop driving to improve transmission balance. Based on this, this article establish a multi-field coupling gear acceleration meshing contact model by using ANSYS , and analyzed the value and distribution of the contact stress and shear stress in the gear meshing area under the impact of the acceleration phase, and to analyze the impact of the gear due to internal excitation. Clarify the law of contact stress and shear stress in the meshing zone under impact. On this basis, the power flow open gear test bench is used to test the gear transmission. The results show that during gear acceleration, the number of shocks first increases and then decreases with the increase in speed; the contact stress and shear stress increase first and then decrease, with multiple peaks; the two stress distributions are based on the contact point. The center spreads to the inside of the gear teeth. The loss power measured by the experiment is in the same interval as the numerical simulation, which verifies the accuracy of the model.

The statics analysis of the cantilever screw conveyor under normal working conditions is carried out by means of finite element analysis software. According to the analysis results, the structure is improved, and a stiffener plate is added near the maximum stress. After the static analysis of the improved screw conveyor under different working conditions, it is found that the improved conveyor can operate safely under different working conditions, the maximum stress and displacement of the conveyor can be significantly reduced by adding the stiffening plate. This paper provides a basis for the optimization design of the conveyor, and further studies the influence of the main parameters such as the conveyor speed and the thickness of the spiral blade on the stress and displacement of the cantilever half-shaft spiral conveyor.

The suspension system of EMS medium and low speed maglev train is a self-unstable and nonlinear system. At the same time, it is affected by external disturbance and internal uncertainty during train operation. Thus, it is a challenging work to design its controller. In this article, the coprime decomposition of the suspension system model is carried out firstly, then the polynomial satisfying Bezout identity is obtained by Euclid's algorithm. Next, the suspension controller can be obtained by designing a reasonable filter Q. Finally, the simulation in Matlab/Simulink verifies the effect of the designed controller. This article creatively applies Youla parameterization and coprime decomposition to the controller design of suspension system, which not only broadens the application fields of these algorithms, but also provides a new idea for the controller design of suspension system. So that the degree of freedom of controller design is increased and the parameter adjustment of the controller has more flexible operation space, which promotes the suspension system to better deal with different working conditions when the train runs in different scenarios.

With STM32 as the main controller, the brushless DC motor driving circuit is designed, and the corresponding electronic differential program and control algorithm are designed to control the track car to complete the forward, backward and left and right turns. On this basis, a universal wireless remote controller is used to realize the remote control of tracked vehicle. Through practice verification, the power system and control system can fully meet the design requirements of granary patrol track vehicle, and can walk smoothly on grain surface under the condition of loading certain weight detection equipment.

In many large scientific facilities, equipped with detectors and other electronic equipment in the field of research, such electronic equipment is used to capture high-speed particles, then the response of the electronic equipment needs different trigger signals as a gate signal, in order to obtain a synchronized timestamp. The trigger signal fan out equipment provides gated trigger signals for different node devices. Due to the large number of nodes and varying distances, the trigger signal needs to be synchronized to the node devices through multiple fan outs. White Rabbit technology integrates a variety of mature technologies to improve the time synchronization accuracy to sub-nanosecond level, enabling a large-scale, multi-node time synchronization mechanism. Its distributed timing technology conforms to the distributed fan out architecture.

As a combination of rotor and fixed-wing aircraft, tilt-rotor aircraft can integrate functions such as vertical takeoff and landing, short takeoff and landing, and high-speed cruise, greatly broadening the flight envelope of the aircraft, and significantly increasing the functions of the aircraft. The tilting of the rotor depends on nacelles or tiltable rotors installed on the wing tips. When the tilt angle changes, the configuration of the aircraft and the direction of the pulling force vector change, and the flight dynamics are complex. Accurate analysis of its characteristics is the basis of flight control law design. This paper proposes a control law design method based on the analysis of modal characteristics. Through the distribution of the characteristic roots of the small disturbance equations of different flying mechanism types and the analysis of the influence of different types of feedback signals under multiple configurations, the tilting rotor modal characteristics is explained in detail. Based on the results of modal analysis, the design method and structure of the control law of the all envelope are proposed. This method can not only provide support for the design of the tilt-rotor flight control system, but also has significant theoretical and engineering significance for the design of variable configuration aircraft.

Aiming at the excessive vibration issue of a crane frame, the vibration damping performance of both engine and transmission mounts was evaluated and optimized with experiment and simulation. Firstly, test detection and vibration acceleration spectrum analysis of 20 points were conducted to investigate the cause of excessive frame vibration through modal analysis. Calibration of the simulation process was completed based on the test data. Secondly the vibration damping performance of both engine and transmission mounts were optimized with the simulation process. Finally, the proposed optimization scheme was verified through testing. The results show that the vibration amplification of the frame is caused by the resonance between the mount natural frequency and the excitation frequency of the transmission near 450Hz and 690Hz. Through optimization design of the transmission mounts, the resonance issue of the transmission is effectively improved and vibration transmission rate meets requirement of less than 70%.

In the current installation or maintenance process of large substation equipment, due to the lack of special hoisting equipment to cope with complex substation operation conditions, resulting in sustained power maintenance time, construction personnel safety can not be guaranteed, and other problems. For these issues, this paper proposes a new type of substation special hoisting equipment program and designed a related mechanical structure. The equipment uses the bottom crawler walking mechanism to enter the narrow working space and uses the frog legs to achieve balance and prevent overturning. The three-degree-of-freedom double mechanical arm and the high-altitude manned device carry out the hoisting of the substation equipment and the human intervention of the equipment, to complete the accurate and efficient hoisting operation of substation equipment.

As the most widely used high voltage equipment in power system, the fault monitoring, analysis, prevention, elimination to ensure its safe and reliable operation, have been widely concerned in recent years. In this paper, the high voltage isolation switch type of GW4D-126(G•W) is concerned. Firstly, various modal parameter identification methods in time and frequency domain are studied. The modal parameter identification in frequency domain by complex orthogonal polynomial curve fitting method is analyzed. Secondly, an algorithm for modal parameter identification by orthogonal polynomial method is proposed. Its accuracy and feasibility are verified by MATLAB. Thirdly, the data analysis methods such as signal preprocessing (eliminating trend term, smoothing curve) and filtering are presented. The experimental modal parameters are identified based on orthogonal polynomial method. Then the modal parameters such as natural frequency, damping ratio and vibration shape are obtained. Finally, the test results are compared with the finite element simulation, so as to verify that the vibration analysis method can be applied to the disconnector status diagnosis.

The comparator is essential in analog-to-digital converters (ADC). This paper analyzes different improvements in the designs of comparators. In order to improve the energy efficiency, the dynamic bias comparator was developed, and it also reduces the input-referred noise. A floating reservoir design was then adopted to solve some weaknesses of the dynamic bias comparator and further increases energy efficiency. On-chip inductors and charge pumps were also implemented to perfect the performance of the comparator. These two changes improve delay performance, and the first one reduces power consumption simultaneously. The last update was an energy-efficient ring oscillator collapse-based comparator. It adjusts the performance of the comparator without any external control and then makes the energy consumption achieve a minimum value without energy scaling. At the same time, this comparator has a wider resolution tuning capability.

Aiming at the unbalanced vibration of rotor system, a novel integral squeeze film bearing damper is designed to control the vibration of rotor. In this paper, the stiffness and damping characteristics of tilting pad journal bearing and integral squeeze film bearing damper are calculated based on finite element method. At the same time, the rotor-support system model is established. The energy distribution of rotor system is analyzed, and the vibration control characteristics of integral squeeze film bearing damper are studied. The results indicate that, compared with tilting pad journal bearing, the novel integral squeeze film bearing damper can reduce the bending strain energy of the rotor by 36.5%. It can also reduce the vibration at the critical speed by 46.1%. In the spectrum diagram, it can be found that the amplitude of 1x frequency caused by the unbalanced fault has decreased by 45.2%. The research provides guidance for industrial application.

Sealing effect is the most basic and important performance index in low temperature system. The sealing structure in the low-temperature system is quite different from that in the normal temperature system, mainly because the physical properties of various materials in the low-temperature environment are different from those in the normal temperature, such as thermal expansion and cold contraction, low-temperature brittleness, phase transformation in the material microstructure and so on. Aiming at the sealing problem of low-temperature system, the key factors such as sealing structure, sealing materials (including sealing interface structural materials, sealing ring materials and sealing grease) and sealing stress in low-temperature environment are studied. Through the simulation analysis of determining the compression ratio and sealing stress of the seal, the design method of low temperature seal is summarized. The test results show that the sealing structure can meet the sealing requirements under -40℃ low temperature environment.

The university online college mental health service platform is based on cloud computing technology, so it can effectively conduct data collection and data processing. Using the Internet of Things sensing equipment and sensors, students' psychological test data can be uploaded to the database of the university mental health online service platform. Moreover, using the K-means clustering algorithm. In the results of the simulation experiment, it can be seen that the online mental health service platform of universities has certain effectiveness, and the mental health management system and the online mental health consultation service system have also improved the mental health services of universities to a certain extent.

This paper introduces four different designs of the comparator in recent years. The edge-pursuit comparator (EPC), which is a new energy-efficient ring oscillator collapse-based comparator, can automatically scale comparison energy according to its input difference and eliminating unnecessary energy. To reduce the energy consumption, the pre-amplifier output node of a dynamic bias comparator (DBC) partially discharge by adding a tail capacitor. The novel two-stage dynamic comparator with a transconductance-enhanced latching stage efficiently decreases the delay and energy consumption. Furthermore, an improvement of the traditional comparator for precise application is introduced. The new comparator applies PMOS transistors at the input of the preamplifier and the latch stage, and both are controlled by a special clock generator which lets the new comparator achieve optimum delay and with no excess power consumption. This paper describes each comparator in detail and compares different features of them.

Aiming at the problems existing in the traditional experimental teaching of stepping motor, such as inflexible time arrangement of students, inability to experiment in different places and difficulty in instrument maintenance, a remote experimental platform of stepping motor is designed based on ZigBee. The experimental platform consists of several stepper motor experimental nodes with CC2530 as the core to form a wireless sensor network, which receives the experimental parameters of the stepper motor set by the remote computer through mqtt communication provided by the intelligent gateway, and feeds back the real-time parameters of the stepper motor uploaded by the obtained experimental nodes to observe the experimental process and record the experimental data. The test shows that the laboratory platform has the advantages of simple operation, low cost and flexible arrangement of experimental time.

In order to control the wear of mechanical seal within the allowable range of leakage, it is very necessary to accurately collect the end friction torque.Through three groups of main bearing torque calibration tests, this paper analyzes and compares the relationship between the friction torque (or both fluid stirring friction torque) of the main bearing of the mechanical seal and the motor speed under different test conditions, and calibrates the friction torque of the main bearing in order to accurately obtain the friction power of the end face of the mechanical seal. The results show that the total power consumption is relatively small and changes little when the mechanical seal is running without load. The test results of noload operation test considering fluid mixing power consumption eliminate the influence of fluid mixing power consumption, which is more favorable and accurate for the subsequent measurement of mechanical seal performance test.

Manned winch is an essential transportation equipment for coal mine production. Handbrake and crossbeam as the main load-bearing parts and braking parts, its reliability directly determines the working performance, working efficiency and safety performance of the equipment. This paper establishes the mechanical model of the brake belt, calculates the minimum braking force required by the handbrake, establishes the model of the handbrake adjusting rod and beam with the help of three-dimensional modeling software, and carries on the structural analysis in the finite element analysis software. The simulation results show that the safety factor of the handbrake adjustment lever is 3.66 under the maximum braking force, and the safety factor of the winch beam is greater than 2 when pulling and braking, which meets the strength requirements. The calculation verifies the safety and reliability of the design and provides engineering reference for the calculation and analysis of the winch brake system in the future.

The dynamic modeling of the propulsion system is of great significance to the overall optimization and vibration control of the airship. Based on the finite element method and the energy equivalence method, this paper proposed an equivalent model of the propulsion stent structure considering the flexible constraints of the capsule. Firstly, the finite element method was used to derive a set of six-degree-of-freedom capsule constraint stiffness coefficients, and an equivalent model of the propulsion stent was established. Secondly, the verification of the equivalent stent model was carried out. Then an accurate dynamic model of the propulsion stent considering the flexible constraints of the capsule was established. The vibration characteristics of the equivalent model are in good agreement with the finite element model, which indicates that the equivalent model has good accuracy.

In order to improve the overall operation efficiency of the ball mill and reduce the production and operation costs, the low-speed and high torque permanent magnet synchronous motor is applied to realize direct drive of the ball mill. Based on the stress analysis of the original drive end cover and discharge port of the mill, the stiffener structure is adopted to increase the strength of the drive end. Through a large number of finite element analysis and comparison of simulation models, the appropriate structural design is obtained, and the corresponding conclusions are summarized The influence law between the strength and structural parameters of the driving parts in the new direct drive mode is analyzed, and the relevant design experience is summarized, which provides the necessary basis for the design and production of the new permanent magnet direct drive ball mill.

Test cases are the key to software testing, and it is particularly important to generate and select test cases that detect faults more quickly. This paper first analyses the characteristics and applicability of typical ART, then combines the isolation forest algorithm with ART, proposes a test case generation technique for IForest-ART, and compares the fault detection effects of typical distance-based ART and IForest-ART in low to high dimensions. The experimental results show that the test validity of IForest-ART in high-dimensional input domain space is significantly higher than that of FSCS-ART, which effectively alleviates the problem of decreasing test validity of typical ART in high-dimensional input domain space and provides a new idea for ART.

Aiming at the vibration control problem, this paper put forward an optical platform for vibration control using two-layer vibration isolation technology. The theoretical analysis model of double-layer vibration isolation system for optical platform is established, the influence of key design parameters of double-layer vibration isolation technology on the vibration transmission characteristics of the system is studied, and the design optimization idea is proposed. Taking an optical platform as an example, the optimization of two-layer vibration isolation design is carried out. The results show that the two-layer vibration isolation technology is applied to the optical platform, and the vibration isolation capability of the system is significantly improved in the middle and high frequency bands above the second-order natural frequency. The design optimization ideas proposed in this study provide important theoretical reference for the engineering design of optical platform.

Spherical mechanism has simple structure and reliable control. Aiming at the problem of insufficient workspace of spherical mechanism, an adjustable spherical four-bar mechanism is proposed to meet the requirements of different working environments and expand the workspace range of actuators, and its multi-task trajectory is optimized and synthesized by improved genetic algorithm. Based on the minimum position error between the actual trajectory and the given trajectory, the objective function is established, and the multi-task optimization model of the adjustable spherical mechanism is established. The global search ability and numerical analysis ability of genetic algorithm are used to optimize the operation, and the global optimal solution is obtained. In order to improve the local search ability of genetic algorithm, the constraint conditions are gradually strengthened in the algorithm, and the mutation operator is used in the mutation operation, which can effectively prevent the premature phenomenon of the population and maintain the diversity of the population. Finally, it is concluded through an example that the adjustable spherical mechanism can effectively increase the workspace of the mechanism and complete the given multi-task well; The analysis results also show the effectiveness and feasibility of the analysis method.

Because of the compact layout of substation electrical equipment, it is difficult to guarantee the safe distance between the equipment and the charged body when the power is cut off or replaced. In order to ensure the safe distance in operation, the special insulation barrier without power cut is developed, and the displacement/stress analysis, vibration mode and stability calculation are carried out for the bearing part, namely the epoxy skeleton. The results show that the displacement/stress response of the middle part of the epoxy skeleton beam is the largest, and the lower the height and the smaller the span, the greater the influence of the higher frequency. The larger the thickness of the epoxy skeleton and the smaller the weight of the single insulating plate, the smaller the stress and displacement response. The results show that the device meets the stability requirements of live working tools, and the research results are helpful to promote the development of uninterrupted operation in substations

In response to increasingly severe environmental problems and energy crises, the microgrid has become an important research topic for distributed power generation through the effective use of renewable energy. This paper comprehensively considers the economy and environmental protection of the microgrid and proposes a demand-side response comprehensive satisfaction evaluation mechanism and an improved particle swarm optimization algorithm based on the Gaussian disturbance mechanism to optimize the source and load sides of the microgrid.

In order to improve the accuracy of speed identification results of traffic accidents, the uncertainty evaluation method of speed model based on tire marks is introduced. Firstly, according to kinematic formula and kinetic energy theorem, the vehicle speed calculation model based on tire marks is established. Secondly, combined with the specific information of an accident site investigation, the vehicle speed model based on tire marks was used to solve the problem, and the method of uncertainty evaluation was applied to obtain the best range of vehicle speed. Finally, the reliability of the model combined with uncertainty evaluation method is verified by MATLAB numerical verification and PC-Crash.

Recently, with the continuous improvement of living standards and the rapid development of civil aviation industry, more and more people choose convenient and efficient aircraft as a means of travel, and the number of flights increases rapidly. However, in the process of flight operation, it is inevitable to encounter complicated weather, other airspace user activities or air resource flow restrictions, which seriously affect the flight normality and passenger satisfaction. In order to solve such problems, people also put forward higher requirements for flight time resource management. In this paper, based on the collaborative decision-making mechanism, this paper carries out flight plan adjustment through the early predictions, assessment analysis, dynamic update and so on, implementation of passengers, airlines and flights running related units and efficient coordination, make the flight security requirements and Air traffic control, integrated airport security ability to achieve the optimal matching, to ensure flight safety, stable, orderly, and maintain flight release order, Improve the normal rate of flight clearance.

As a key component of a diesel engine, the connecting rod will bear the reciprocating stress of tension and compression during operation, and its performance is very important for the safe operation of the diesel engine. This paper uses the finite element analysis software ANSYS to analyze the stress and deformation of the designed connecting rod at the top dead center of the intake stroke and the top dead center of the work stroke. Through the method of multi-objective optimization, the quality, stress and deformation are improved and optimized at the same time. The results show that: 1) The designed connecting rod meets the requirements of strength and deformation; 2) The mass of the optimized connecting rod is reduced by about 20%; 3) The stress and deformation of the top dead center of the intake stroke are respectively reduced by 33.8% and 42.2%; 4) The stress and deformation of the top dead center working condition of the work stroke have been reduced by 29.0% and 45.3%.

The monitoring system of coal mine main ventilation equipment generally has disadvantages such as poor stability, inaccurate fault location, difficult to find problems, incomplete monitoring content, and complementary and compatible communication interface protocols, which have been unable to meet the needs of mine safety production and automated management. This article mainly describes the functions, monitoring content and troubleshooting of the coal mine main ventilation monitoring system, laying the foundation for the unmanned duty of the ventilation monitoring system.

According to the needs of pipeline inspection in power industry, an omni-directional motion robot with a magnetic adsorption is proposed. The robot can not only achieve the stable adsorption and movement of the magnetic conductor wall, but also has a simple structure, and high flexibility. Firstly, combining with the actual performance requirements of the project, the scheme selection of different modules of the robot was determined. Secondly, Maxwell module of ANSYS finite element analysis software was used to study the adsorption device, and an adsorption device with stable adsorption was obtained, which ensured the safe and stable operation of the robot on the vertical wall. Then, the hardware system and control system of the robot are determined, and the construction of the robot system is completed. Then the dynamics of the robot are analyzed, and the simulation is carried out according to the analysis. It is verified that under the control of PID algorithm, the acceleration of the robot can be in a stable state finally, which ensures the robot is stable in the process of motion. Finally, we finished experiments of the robot and verified the robot is stable when it works on walls.

The output of a coal mine in Shanxi province is large, resulting in a large amount of absolute gas emission from the working face. The gas problem in the upper corner of the working face has become the main factor restricting the safe and efficient production of the mine. Therefore, aiming at the existing problems of gas control in the upper corner of the mine, the design and optimization of extraction parameters for high-level boreholes along the roof of the goaf are carried out. Through theoretical calculation and numerical simulation, the strata of the end hole of roof borehole are obtained, and the formula for calculating the number of boreholes is deduced. The field test of extraction effect is carried out at 3103 working face of the mine, and the parameters suitable for the layout of high-level boreholes in the mine are obtained to ensure the safe and efficient production of the mine.

Tension string truss structure is a hybrid prestressed structure system combining hardness and flexibility. It has many advantages, such as self balancing function, large stiffness, beautiful shape, wide applicability. Prestressed cable is the most important source of bearing capacity, and the failure of cable will have a disastrous impact on the structure. In order to study the influence of prestressed cable fracture on the structure of tension string truss structure, based on typical cases, the structural response of cable fracture failure is studied by finite element analysis method. The results show that after cable failure, the remaining structure will reach equilibrium on the new transmission path after internal force redistribution. Initial prestress and broken cable holding time have little effect on it. The restraint form of the support is a fixed support at one end. When one end can slide, the structure is safer.

The traditional magnetic fluid sealing is designed in accordance with the special environment (such as normal temperature), but the safety factor has always been set only through the experience of engineers and technicians, and there is no quantitative theoretical basis. The magnetic-liquid large-diameter, large-gap rotary seal device designed in this paper should be used in high-power motors. Taking into account the variability and complexity of its marine combat working environment, the design will fully consider the factors of the working environment to ensure sealing the parts meet the sealing requirements in a compact structure.

Product tending machine (PTM) is one of the most important equipment in the aluminum electrolysis production process, for the problem of PTM optimization, a queuing system model of aluminum electrolysis PTM is proposed for the first time. According to the actual production situation of the aluminum electrolysis industry, a non-preemptive priority M/G/1 aluminum electrolysis PTM queuing system model is defined, and the general calculation formula of the operating index of the non-preemptive priority PTM queuing system is given, including queuing system length, waiting time, optimal service rate, etc. According to the actual production data of an aluminum factory, the relevant indicators were calculated and analyzed, and the relationship between the operating indicators and the number of electrolysis cells was drawn. Finally, under the conditions of meeting different operating indicators, the optimal matching scheme of PTM and aluminum electrolysis cells was given.

As a substitute of petroleum and natural gas, fuel cell has the advantages of high efficiency and environmental protection. Air compressor is one of the core components of fuel cell system. In commercial bus fuel cell system, twin screw air compressor has unique advantages. In this paper, a pair of meshing rotors, the core component of twin screw air compressor, are studied. The design method of profile and calculation method of equidistance surface of rotor are given.

Bolted connection is a common connection method for FRP structures and it has the advantages of economy, convenience of construction, easy to replace and so on. It is found that the seismic performance of bolted FRP connection depends on the size and form of bolt hole. In order to study the influences of clearance and type for bolt holes on mechanical behavior of bearing-type high-strength fiber-reinforced polymer (FRP) bolted connection, 14 specimens with type of round and slotted hole, and different bolt-hole clearance were studied under monotonic tension loading based on ABAQUS software. The analysis result showed that the connection stiffness decreased when the bolt-hole was enlarged with round hole, while the failure mode and ultimate bearing capacity were changed slightly either by the hole types or bolt-hole clearance and are negligible. This is beneficial and provides a reference for engineers to adopt different connection forms for FRP structures according to the specific situation of seismic requirements in engineering practice.

It is difficult to use traditional bearings for the telescope base in extreme environments, and the use of spliced arc guides can solve this problem. This paper studies the change of the friction force of the arc motion rolling guide under the condition of splicing error. In this paper, simulation methods are used to explore the speed change of the arc guide under different splicing error conditions, the Coulomb model is used to calculate the friction force change, and then the polynomial fitting is used to observe its fluctuation. The research results show that when the splicing error is 0.005 mm and 0.01 mm, the friction force of the arc motion rolling guide is roughly 10-15 N. Moreover, when the splicing error is 0.01 mm, the frictional force changes more discretely.

Crane safety protection is one of the important contents of enterprise safety and equipment safety management. Cranes often have cross operation conditions, and the rotating mechanism and luffing mechanism of portal crane also have a certain compound movement in the operation process, which is easy to cause collision accidents. Taking the large portal crane which is widely used in port as an example, this paper makes a detailed comparative analysis of the current mainstream wireless communication signal processing methods, and puts forward the data signal processing method of crane space anti-collision system.

Aiming at a new type of annular groove PDC bit, the law of scraping rock breaking efficiency of the cutter is studied in this paper. The three-dimensional simulation model of dynamic rock breaking of the cutter under two conditions of flat rock sample and rock ridge rock sample is established by finite element method. The variation laws of rock breaking efficiency, contact pressure and load on the cutter in the process of rock breaking are studied. The rock breaking experiment of the cutter scraping on sandstone ridge is carried out, and the influence trend of load in cutting and the destruction specific energy is analyzed. The results show that the rock breaking efficiency of the cutter is higher than that of flat rock samples, and the side angle has a great influence on the load in cutting and the destruction specific energy of the cutter. With the increase of rake angle, the destruction specific energy of the cutter first decreases and then increases, and there is also an optimal rake angle. With the increase of intrusion depth, the destruction specific energy of the cutter gradually decreases and the load in cutting gradually increases.

The escalator safety brush is used on the escalators at the entrances and exits of major markets, shopping malls or subways and is installed on both sides of the lower part of the escalator to prevent potential safety hazards caused by objects or shoelaces entangled in the gap between the steps and the skirt side plate of the escalator. There is a certain gap between the steps of the escalator, and between the steps and the upper and lower stations and the surrounding skirts. Generally, the gap is no more than 4mm, but such a small gap will also pinch clothes or children's fingers and shoes and cause injury. In order to avoid the passenger's foot extending between the escalator step and the apron, in the prior art, a brush is usually installed on the apron, so that when the passenger's foot extends to the edge, it will touch the brush to remind the passenger. Since the brush is often touched by passengers or other items, it needs to be replaced regularly, and it is best to replace it quickly. In the prior art, conventional bolts are usually used to fix the brush, which will reduce the replacement efficiency of the brush. The purpose of this paper is to provide a detachable escalator brush structure in order to overcome the defects of the prior art. The structure can realize the rapid replacement of the safety brush, and the installation mode of the device is faster and more efficient than the existing screw direct installation mode. When it needs to be replaced, just loosen the jackscrew to remove the whole brush. When the installation is completed, the fixing block can be completely hidden inside the installation slot, and the brush fixing strip supports the escalator apron through the outer edge of the installation slot to make it more beautiful.

The operation of electrical measuring equipment is affected by the local climate. Classifying the climate of each place based on environmental parameters is an important guide to the design and manufacture of electrical measurement equipment. Therefore, a support vector machine classification prediction model based on kernel parameter optimization is proposed. Firstly, linear discriminant analysis is used to extract the features of various environmental parameters. Then, support vector machine classification model is used to train the extracted environmental feature data. Finally, in order to improve the prediction accuracy of the model, particle swarm optimization algorithm was used to optimize the kernel parameters of the model to achieve the classification prediction of the model. The model is verified based on climate data, and the experimental results show that the use of the proposed model can effectively realize the classification and recognition of climate data.

With the rapid development of computer technology, it is comprehensively and deeply applied in the field of music creation. Computer technology plays an important role in the writing, practice and secondary creation of music creation by using its characteristics of rapidity, diversity and efficiency. At the same time, the integration of music software system and the use of multimedia technology can greatly realize the rapid processing of computer and sound data. So as to establish the logical relationship between music and computer software, develop a proprietary music creation system for music creation, and provide overall planning and technical support for the creation structure of music creation system by using image processing technology and multimedia technology. Based on the application of computer technology in music creation, this paper makes computer technology realize the purpose of human-computer interaction in the application process of music creation, so as to promote the good development of music creation.

At present, most oral English tests use manual scoring, which has many drawbacks. In the past English tests, the scores of the subjects often depend on the subjective impression of the rater. Because of the strong subjectivity in the English test, the reliability of the English test is not high. In order to improve this situation, you can use the multi-faceted Rasch The model is improved. The multi-faceted Rasch model can use a rigorous mathematical statistical probability model to standardize test scoring through various data generated in the test, and correct deviations in the scoring, so as to achieve the fairness of the scoring of the spoken English test. The multi-faceted Rasch model can be completed by the analysis software Facets. This software can complete the deviation analysis of examinees, graders, grading standards and other aspects by relatively simple setting of the parameters of the required model.

Based on the measured signals of extremely low frequency underwater magnetic targets, this paper extracts the magnetic anomaly data of sensors at 50Hz for denoising processing, and uses the denoised magnetic anomaly data as the basic data. Random noise is added to the basic data as a simulated noise signal. Based on Stein's unbiased likelihood estimation threshold method, two wavelet family Symlets, Daubechie and soft and hard threshold selection methods commonly used in denoising literature are used to denoise the measured underwater magnetic target signal data. The different de-noising results are calculated and compared. The de-noising signal-to-noise ratio of the data is used as the evaluation index, and the de-noising effect and reliability of different combined methods are objectively analyzed. Research shows that the hard-thresholding of sym7 as the generating wave function has the lowest signal-to-noise ratio and poor denoising effect. The soft threshold processing using db9 as the generating wave function has the highest signal-to-noise ratio, which can achieve the best denoising effect.

This paper proposes a linear variable error extended state observer (VELESO) based on the problem that the output response under linear active disturbance rejection control (LADRC) oscillates by uncertain disturbance. The stability of VELESO is also proved from the perspective of Lyapunov stability principle. Meanwhile, the concept of virtual step length is introduced by the possibility of coupling among the controller’s adjusted parameter. The virtual step length as a bridge which links the adjusted parameter of the controller is used, in theory, to simplify parameter tuning. In the simulation, the observer accuracy is first tested. Comparing with performance index ITAE of observation errors (e1, e2 and e3) of linear extended state observer (LESO), the ITAE corresponding to VELESO increases by 96.51%, 99.78% and 14.64% respectively. Then, the control performance is also verified. Under the index ITAE of LADRC that contains VELESO is better than LADRC by a simulation of coupled system.

Linear regression is widely used as a tool for statistical analysis and is very popular as a technique to build predictive models in data mining field. Due to the fear of leakage of their privacy, data owners are reluctant to share data with others, while they wish to perform statistical analysis cooperatively. To solve the privacy issues, one of most popular approaches is to encrypt user’s data with public keys. However, this technique inevitably leads to another challenge that how to train linear regression based on encrypted data with multiple keys. In this work, we propose a privacy-preserving linear regression scheme base on a public-key cryptosystem with distributed two trapdoors to protect the privacy of the training data. We consider the problem of linear regression where the data are split up and held by different parties. We give details of how this scheme is implemented. Finally, we provide the theoretical analysis of the scheme.

With the development of deep learning, deep neural network can be consumed to many kinds of tasks, such as target detection, super resolution and other image processing applications. However, super resolution for sonar images adopts traditional ways without neural network. Due to the characteristic of sonar sensors, which shoot images in turbid underwater environment and have low resolution, objects taken by sonar sensors are difficult to recognize. This paper proposes an efficient method called Multi-stage Residual Network (MRN) which combines neural network to achieve super resolution for sonar images. Adding pixel shuffle to the medium of the structure, the number of layers and blocks in every part is different. In addition, we trained the network with no modification from underwater sonar images. Experimental results show that low-resolution fuzzy images can acquire a clear super resolution by using our model, and furthermore, PSNR of our resultant images is higher than that of the interpolation algorithms and residual network.

After much research and advancements, GANs have achieved great success but still face many challenges. In this paper, we adopt self-supervised learning based on rotation angles to overcome the catastrophic forgetting of the discriminator. Self-supervision encourages the discriminator to learn meaningful feature representations that are not forgotten during training. Meanwhile, this paper adopts consistent adversarial training to alleviate the mode collapse of the generator. The consistency constraint condition encourages the discriminator to explore more features, which helps the generator achieve more significant improvement space. This deep generative model improves unsupervised image generation tasks by simultaneously alleviating two critical issues in GANs. Experimental results demonstrate that our model achieves competitive scores.

With the emergence of environmental protection, energy crisis and other problems, distributed photovoltaic microgrid has received wide attention from various countries. The traditional distribution grid dispatching system to monitor the microgrid makes most of the distributed power sources out of control, so it is very important to research and innovate the new microgrid operation mode. By interconnecting microgrids with similar geographic areas and related characteristics electrically and communicatively, and interacting with the distribution grid through a unique access point, microgrid clusters are formed, which is a higher level of distributed power structure. For the stability problem of autonomous operation of microgrid clusters, multi-agent microgrid clusters can not only solve the autonomous operation of the grid, but also make the microgrid with higher stability. In this paper, a coordinated autonomous control strategy for microgrid clusters with ring-type multi-agent is proposed. The method uses a ring network structure between agents to control each microgrid. In this approach, Agents communicate with each other and microgrid units are electrically interconnected to form microgrid clusters with stable power output. Finally, the PSCAD platform simulation verifies the stability of autonomous operation of microgrid clusters with multiple Agents.

Axle box bearings for locomotives play a significant role in guaranteeing the service performance of the locomotives. This paper has studied how to extract the weak feature of compound fault under strong interference excitations and proposed a kernel correlated kurtosis of square envelope spectrum. Firstly, simulated compound fault signals were applied to analyze important issue of its demodulation; Three signal processing tools are compared to evaluate their detection performance. Secondly, frequency domain correlated kernel was used to quantitatively compute the amplitude value of signal squared envelope spectrum, settle the failure that conventional time-frequency kurtosis fail identify signals of a strong pulse interference fault; namely, with frequency-domain correlated kernel values, Kurtogram is generated. Which can identify the optimum frequency range and decomposed the single fault feature adaptively. Finally, the proposed method was proved effective and applicable in contrast with experimental results.

Adjusting the traditional PID controller parameters requires the expert’s experience. Sometimes, the traditional linear PID controller can't balance the dynamic and static performance of the system, and it can’t effectively control the object when the object parameters change. We propose a nonlinear PID controller, which uses state transition algorithm (STA) to tune the parameters of nonlinear PID controller, and uses data-driven (DD) to enable the system to identify different object parameters and adopt the corresponding controller. Simulation results show that the proposed controller effectively improves the control effect of the above problems.

At present, the defect detection link is indispensable in industrial production, and for the problem of low accuracy of existing neural networks in steel surface defect detection, a Faster-RCNN-based steel surface defect detection network (P-RCNN) is proposed in this paper. First, a new backbone network (Resnet-P2) is formed by adding feature fusion and attention mechanism to the original Faster-RCNN backbone network Resnet50, which can make the features transfer more effectively in the backbone network; second, a parallel cascade network is introduced, which aims to train a high-quality detector without reducing the number of high-quality samples. The purpose is to train a high quality detector without reducing the number of high quality samples, which makes the detection accuracy better. The experimental results show that the P-RCNN algorithm is used for steel surface defect detection with better detection performance and the accuracy is improved by 7.6% to 83.4% compared with Faster-RCNN, which can be used as a reference for steel surface defect identification applications.

Fingerprint positioning is a common method of indoor positioning. The matching algorithm is an important part of determining the final positioning accuracy. How to choose a better algorithm to improve the positioning accuracy is the focus of this article. The traditional KNN algorithm is a common matching algorithm, but its positioning accuracy is not very high. Therefore, this paper proposes to select the optimal hyperparameter K through cross-validation, align to perform KNN regression, and then pass PF (particle filter) Method to optimize its results, its average positioning accuracy is improved by 23%, which has certain practical significance.

Through the analysis of two-dimensional contour composition and its approximation error, the paper introduces the approximation algorithms of commonly used contour. Using Romberg algorithm to calculate the approximation error of straight line and equal radius curve, it is found that the approximation error of straight line is always 0, and the approximation error rate of curve contour under the same area is 1.57% after three accelerations approximation. The more the number of contour halves, the smaller the approximation error.

With the open sharing of power Internet of things, many IOT applications are in an uncontrollable environment, facing risks such as vulnerabilities/attacks and advanced sustainable threats. Through the software security detection before the application goes online to eliminate vulnerabilities, the resilience of IOT applications to threats can be greatly improved. However, the current software analysis methods have some problems, such as insufficient program coverage, high resource consumption, randomness of analysis results and so on. In view of the above problems, this paper studies the software security analysis method combining static and dynamic. Based on the control flow chart extracted by static analysis and combined with vulnerability potential evaluation, this paper generates the control flow chart with additional vulnerability prediction weight, so as to guide fuzzy testing to carry out dynamic analysis and improve the overall efficiency of fuzzy testing. Finally, a cross platform dynamic analysis architecture is proposed to improve the analysis efficiency by optimizing the intermediate language and code refactoring.

When processing printed circuit board (PCB) defects using an infrared fault diagnostic system, we found that the small dimensionality of the recorded PCB temperature data and the difficulty of extracting some features of the error mode may lead to low fault diagnosis accuracy. To solve this problem, based on the temperature data of PCB components, a PALSTM- FCN(Parall-Attention-LSTM-FCN) board error diagnostic model based on multidimensional temperature data was proposed. First, we use the temperature data acquisition system to collect chip temperature information for different failure modes. Then, a multidimensional chip temperature dataset is created to optimize the diagnostic model input data features. Finally, the PA-LSTM-FCN model is trained to extract the temperature data features to complete the circuit board fault diagnosis. The experiment uses an adjustable regulated power supply circuit board for reliability analysis. The results show that the diagnostic accuracy of the model proposed in this paper reached 97.34%, achieving high accuracy diagnosis of circuit board failure modes.

In order to solve the problems of pool generalization ability of traditional algorithms and high cost of manual inspection for abnormal image detection in remote video surveillance, this paper proposes an algorithm for abnormal image detection in video surveillance based on deep learning. First, the convolutional neural network based on VGG-16 uses the he_normal method to initialize the weights, and then the self-made datasets is preprocessed and input into the convolutional neural network for training, and finally an image for detecting video surveillance is obtained Model of abnormal interference. Experimental results show that this method can detect abnormal interference such as overexposure of brightness, color distortion, and video freezes in video surveillance, with an accuracy rate of 86%.

With the arrival of the Internet age, SQL injection is widely distributed as a web application attack method. It’s with low operating threshold and not easy to be discovered, so it seriously threatens network security, causing a large number of websites to have security risks. When the number of sensitive words and non-sensitive words in the SQL sentence data set is close, the SQL injection attack detection method based on the TFIDF algorithm has the problem of high false alarm rate. This paper proposes a detection method based on the improved TFIDF algorithm. It analyzes and compares a large number of attack statements and normal SQL statements, summarizes the characteristics of SQL statements and vectorizes the text, and adds quantification related to keywords in the formula. parameter. The purpose of this article is to use the improved TFIDF algorithm in the data preprocessing stage, use three different classifiers in the classification stage, combine SVM, KNN and DT three different machine learning algorithms, and finally compare experiments. The results prove that the improved TFIDF algorithm combined with SVM has a higher accuracy rate and a lower false alarm rate.

Resistance spot welding (RSW) is the leading process of automobile body welding, and its quality is related to the reliability and safety of the whole vehicle. The effectively and automatically ultrasonic nondestructive testing is the development direction which can judge the spot welding quality, and then the positioning error of probe has an important impact on the test results. From this, conventional ultrasonic A-scan is adopted. Firstly, this paper presents the nugget diameter mathematic model of two-layer plates with different thickness when the probe positioning error is present. Then, the ultrasonic nondestructive testing simulation models of the spot welds are established, and the influence of the probe positioning error on the calculation result of the nugget diameter is studied. Finally, this paper carries out ultrasonic nondestructive testing of spot welding of two-layer plates with different thickness when the probe has positioning error. The experimental results verify the correctness of the theoretical analysis and simulation.

This article introduces the research process and solution of Flink stream process data and storing parsed data into MySQL, which means that the one-stop process of obtaining, analyzing and storing is realized in the field of vehicle big data. The algorithm obtains real-time information from the target (Kafka) through Flink, then passes the information to parsing program, and finally imports the parsing result into MySQL. Since the MySQL is designed as a storage method of sub-databases and tables, by setting the time period and then landing the data in HBase, we don’t need to worry about the storage performance of MySQL when the amount of data is large.

Surface remeshing is widely used in computer vision and reverse engineering. The vertex normal vectors used in the existing surface remeshing methods are not accurate enough in the characteristic regions such as large curvature change, boundary and sharp edge, which leads to poor remeshing results in these regions. In this paper, the vertex normal vector based on hybrid weight and boundary correction is introduced to our method. We use this normal vector to improve the reprojection step in vertex translation, and combining edge splitting, collapsing, and flipping, propose an improved real-time adaptive remeshing method. Three models are selected for remeshing experiments. Compared with the RAR (real-time adaptive remeshing) method based on Thürrner's vertex normal, the Hausdorff distance is reduced by 4.99%, 8.79% and 6.85% respectively in the uniform length remeshing, and 3.21%, 2.25% and 11.92% respectively in the adaptive length remeshing. The results show that the remeshing effect obtained by our method is smoother and has higher geometric similarity with the original model.

Hyperspectral images (HSIs) contain spatial features and rich spectral features that provide them with great advantages in target classification and make it easy to improve image classification accuracy. Convolutional neural networks (CNNs) have shown good performance in HSI classification. However, blindly increasing the depth of the CNNs may lead to overfitting. A HSI classification method based on a dense multi-scale residual network is proposed to address these two problems. The proposed framework obtains the spectral-spatial characteristics of HSIs through an improved multi-scale residual network. Then, three cascaded multi-scale residual modules form a deep network. The dense connection module is used to stack feature maps from all previous layers to form the concatenate feature map rather than fusing pixels of these feature maps and further achieve the purpose of improving classification accuracy and reducing the time consumption of the network. A series of experiments show that the proposed method achieves good experimental results on three widely used hyperspectral datasets and a new hyperspectral dataset (Farmland distribution dataset, FDD).

At present, there are problems in remote video surveillance that it is difficult to detect image anomalies in complex scenes, and traditional algorithm functions are single (only for a certain specific scene or a certain type of abnormal image). Moreover, the currently commonly used convolutional neural network is deployed on the monitoring device, there are problems such as insufficient device memory and low computing power. In response to the above problems, this paper proposes a recognition method that applies the MobileNet convolutional neural network to the detection of abnormal images in surveillance video. The off-line enhancement method is used to reverse and translate the abnormal images in the surveillance video. The data set can be reasonably expanded, the problem of data imbalance can be solved, and the detection accuracy and generalization performance of abnormal images can be improved. The results show that this method can detect abnormalities such as freeze, overexposure, blur, and colorific distortion in remote video surveillance, with an accuracy rate of 91.75%, and can reduce the amount of model parameters and facilitate model deployment.

In order to ensure the normal operation of power system and improve the recognition accuracy of the substation abnormality, an abnormal recognition method based on improved neural network for power equipment is proposed. Firstly, the abnormal image of the substation is collected and denoised. Then, the features of the abnormal image are extracted and dimensionless processed. Thirdly, the improved neural network is used to establish the image recognition model of the abnormal image. Finally, the simulation experiment of this method is carried out. The experimental results show that the proposed method can not only obtain better recognition results, but also meet the detection requirements of the abnormal image.

Disk failure prediction has become a major concern with the rapid expansion of data centers and the demand for reliable storage systems. Based on extremely unbalanced positive and negative samples in the disk data set, this paper proposes a fast and accurate disk failure prediction model. Target disks are selected from the actual disk data set, and the correlation matrix is used to filter the features with high correlation coefficients, which makes the model easy to fit. Aiming at the imbalance of positive and negative samples, an under-sampling strategy is implemented through Mini Batch K-Means clustering, and the Focal Loss function is introduced into the LightGBM model to reduce the impact of the imbalance data. Compared with several traditional machine learning models, the effectiveness of the proposed prediction model is verified on the public real data set.

For the data streams retrieved from the various sensors in energy cyber physical system, an anomaly detection algorithm based on time series extremum was proposed. Firstly, for a single data stream, the algorithm identifies the extreme points of the data stream in the sliding window, and marks off the abnormal sub-sequences according to these points. Then the eigenvalues of the sub-sequences are calculated to establish the feature space. Several anomaly measures are defined, so the sub-sequences can be sorted by the measures in the feature space. Finally, based on the correlation between the sensors points, the anomaly points on each work section are detected. The algorithm can make up for the limitation of other point anomaly detection algorithms by detecting the abnormal sub-sequences, and reduces the probability of false alarm and missing alarm in data stream analysis. Experiments show that the algorithm is effective and feasible.

The rapid development of vehicle cooperative control technology has greatly accelerated the process of "intelligent city" all over the world. This paper studies string stability control for the nonlinear vehicle platoon via vehicular networks. A nonlinear vehicle cooperative control model is established by considering the influence of cyber-attack. Based on the research of resilient controller ensuring the stability of platoon system under the influence of cyber-attack, the string stability condition of platoon system is proposed, and the string stability of platoon system under this condition is proved. The algorithms are compared and analyzed in Matlab. It is verified that under the influence of cyber-attack, the vehicle spacing error of the platoon system can quickly converge to zero, and the platoon system can drive safely and stably.

It is inevitable for civil aircraft to encounter lightning during flight. The vent of fuel tank is the inlet and outlet for the exchange of gas in the fuel tank with the outside atmosphere. Corona and streamering may be generated at the vent cap when encountering lightning. The vent cover shall be designed reasonably to prevent the corona streamering from igniting fuel vapor in the fuel tank. This paper analyzes the airworthiness requirements of lightning protection of fuel tank vent cap, describes the structural design characteristics of typical vent cover and its layout on the wing, and discusses the corona streamering certification test of fuel tank vent cap, so as to provide reference for airworthiness certification of lightning protection design of fuel tank vent cap.

Graph-based Approximate Nearest Neighbor Search (ANNS) algorithms have attracted more attention due to their better performance. Numerous ANNS optimization methods have been proposed by researchers. However, Current graph-based ANNS algorithms still cannot index billion-scale datasets on a single server with 256GB RAM. Although several researchers have investigated on this problem, we believe there is still an improvement in reducing disk accesses. In this paper, we provide a fast navigation layer to decrease the number of disk accesses by assisting query points in swiftly reaching the range of strongly connected components. Compared with the state-of-the-art ANNS algorithms, NDANN reduces the mean latency by about 20% under the same recall.

Due to the absorption and scattering of light in the water environment, the polymetallic nodule images were of low quality, such as color deviation, uneven illumination and blur, which was negative for the extraction and abundance calculation of polymetallic nodules. An improved image color correction method based on the dual transmission underwater imaging model is proposed. Its key lies in the estimation of direct component transmission (DCT) and backscattering component transmission (BCT) in the model. BCT is estimated in red, green and blue color channels, which are no longer considered equal. The DCT is estimated based on the mean pixel value and BCT of the background light region. In addition, the retinex algorithm is used to eliminate the illumination image and solve the imbalance of illumination and shadows caused by photoshooting with supplementary lighting. The image contrast is enhanced by using the contrast limited adaptive histogram equalization (CLAHE) algorithm. The polymetallic nodule images are used to evaluate the proposed method qualitatively and quantitatively. The results demonstrate that the proposed method has high performance in image visibility enhancement and color restoration. It is beneficial to the extraction and distribution analysis of polymetallic nodules.

This paper considers the problem of cross-modal retrieval, e.g. using a text query to search for images and vice-versa. Existing approaches usually learn a common subspace where the shared parts of different modalities can be directly compared. However, no previous works explicitly show that the learned space contains only the common information but without the modality-specific information. And the division between these two types of information would benefits the task of cross-modal retrieval. In this paper, we present a COordinated and Specific autoEncoder (a.k.a. COSE) that can distinguish the common part from modality-specific part of different modalities. The proposed model COSE consists of two subnetworks, each with two representation layers. The common representation layer learns the common patterns shared within different modalities. And the modality-specific representation layer learns the modality-specific patterns owned by individual modalities. We evaluate our model on three publicly real-world datasets with the task of cross-modal retrieval. The extensive experiments demonstrate the effectiveness of our COSE.

Obfuscation is a method of endogenous security commonly used to thwart software vulnerabilities exploitation and protect important properties such as intellectual property rights, software algorithms and user privacy. Numerous obfuscation techniques and products have been developed after decades of research while it is hard for users to are easy to figure out how to apply these obfuscation rules properly or if a program is obfuscated sufficiently. To solve this problem, this paper proposes a recommendation strategy for code obfuscation based on comprehensive metrics, providing a new scope for obfuscation development and applications. The strategy was implemented and verified on obfuscators and a suit of program benchmarks, demonstrating the strategy could obfuscate programs sufficiently with cost reduced by 30% within five obfuscation rules in average.

At present, the classical semantic segmentation methods can not accurately realize the obstacle instance detection of traffic scene, which makes this method can not be used in driverless system alone. In order to meet the requirements of obstacle detection accuracy in unmanned system, pixel level obstacle detection in complex driving scene is studied in this paper. A pixel level obstacle anomaly detection framework is formed by combining the maximum entropy, maximum distance and perceptual difference of uncertainty mapping with the output of dissimilar model. The framework uses uncertainty map and designs a hollow spatial pyramid pool structure of different receptive field stitching to enhance the correlation between various levels of information to improve the existing re synthesis methods to find the differences between the input image and the generated image. As a general framework, this method focuses on the trained segmentation network to ensure anomaly detection without affecting the accuracy of segmentation. The network is implemented based on pytorch framework. The experimental results on the road scene dataset cityscapes dataset show that the mlou reaches 85.7%.

To reduce equipment maintenance costs and shorten the parts processing cycle in the Electromechanical industry, based on the current situation of equipment maintenance in the Electromechanical industry, the application of FDM screw 3D ceramic matrix composite printing technology in equipment maintenance in the Electromechanical industry is studied, and the selection of process parameters for FDM screw 3D printing technology and its application in electromechanical equipment maintenance are introduced. The results show that when the nozzle diameter is 0.4 mm, the screw speed is 0.6 ~ 1.0 R/min, the pressure is 0.2 ~ 1.0 MPa, the layer height is 0.2 mm and the printing speed is 30 mm/s, both the printing speed and a certain accuracy are guaranteed. At the same time, it can ensure that the processing of electromechanical equipment parts is faster and more convenient, help to reduce the processing cost of parts, and help to shorten the processing cycle.

Aiming at the problem that traditional underwater detection technology has been unable to meet the detection requirements, a new type of power-frequency (50Hz) magnetic field detection method is proposed. The space power frequency magnetic field model of the ferromagnetic cylindrical underwater target is deduced, and the magnetic anomaly of the ferromagnetic cylindrical underwater target rotating 0°, 30°, and 90° along the axis direction under the background of the power frequency magnetic field is simulated. The field distribution is further analyzed for the three-component magnetic anomaly spatial distribution law of ferromagnetic underwater targets. Through experiments on the scaled model, the magnetic induction intensity of the scaled model is measured, and the correctness and consistency of the spatial distribution of the power frequency magnetic anomalies of the ferromagnetic cylinder are verified, which is provided thinking for the design of power frequency electromagnetic detection of underwater targets.

In order to accurately evaluate the residual life of rotating machinery equipment and grasp the health status information of bearings, a residual life prediction method based on SSA-BP was proposed. Firstly, Sparrow Search Algorithm (SSA) is used to optimize the connection weights and thresholds of BP neural network for selective optimization. This can solve the problem that the performance of BP neural network is greatly affected by connection weights and thresholds. At the same time, the life characteristic index is established by the method of eigenvalue extraction. The lifetime characteristic index was used as input neuron of SSA-BP network model. It establishes SSA-BP residual life prediction model. The feasibility of the model was verified by taking the experimental data of bearing life cycle from Xi 'an Jiaotong University as an example. The prediction curve of the remaining life of the bearing is given. Compared with the BP prediction model, the results show that the SSA-BP model can effectively reduce the prediction error of BP model.

Active control of vibration plays a vital role in space mission. This paper proposes a method using Solid Propellant Microthruster Array (SPMA) as actuator to control vibration of solar panels. The characteristic of SPMA is introduced and an application criterion is presented. Thus, an independent modal control algorithm for SPMA is presented by elaborately analyzing the output characteristics of the SPMA. In addition, optimization criterion for reducing energy consumption is drawn, and the stability of SPMA control algorithm is proved by the Lyapunov method. Finally, simulation results demonstrate the feasibility and effectiveness of proposed method, SPMA with independent modal control algorithm can be a promising tool for vibration suppression problems.

In order to protect high-voltage cables from lightning overvoltage and operating overvoltage, lightning arresters should be installed at both ends of the high-voltage cable. According to the resistive component of leakage current, the operating status of the zinc oxide arrester can be effectively judged. A finite element simulation modeling method for zinc oxide arrester is proposed, of which the accuracy is verified through experiments. The simulation analysis of the leakage current characteristics of 220kV arresters under different damp conditions was conducted, which provides a reference for online monitoring and early warning of the arresters.

In order to solve the problem of identification and verification of topological relationship between feeder and distribution transformer in distribution network, an identification method of the feeder-transformer connection relationship in distribution network based on fault outage information inversion is proposed. Firstly, the identification model of feeder-transformer connection relationship is established through the single fault outage information set. Then, through the identification model of feeder-transformer connection relationship, the feeder fault standard outage information set and feeder fault real-time outage information set are established. Finally, the distribution transformer fault connection information set and distribution transformer missing connection information set are determined by the difference set between the feeder fault standard outage information set and feeder fault real-time outage information set. The example analysis shows that this method can identify the feeder-transformer relationship of distribution network based on the topology information and real-time fault alarm information of DMS. The method is simple and reliable, can better meet the actual needs of the site, and has good promotion value.

Radar jamming technology is indispensable in modern warfare. As a consequence, developing effective radar jamming has become the focus of contemporary scientific research. A new jamming strategy using the unique characteristics of frequency diverse array (FDA) antenna is presented in this paper. The suggested jamming technology can generate a high number of false targets quickly, and the number of false targets can be manipulated by the number of array elements and frequency offset (Δf). First, the jamming model is described, followed by a simulated examination of the jamming effect. Then, the FDA prototype, developed independently by the Wang Wenqin team of the UESTC, was used to build the test platform, which is tested. Finally, the test results verify that the proposed radar jamming method can perform a better function in the conventional radar.

In order to improve the stability of distributed drive electric vehicle under extreme conditions, a stable drift control method based on longitudinal force distribution was proposed in this paper. Firstly, A 7-DOF vehicle model, front and rear tire models are established considering the drift motion under extreme conditions. Secondly, the tire longitudinal force was allocated according to the ratio of vertical force, and the drift balance was analyzed. Then, the Linear Quadratic Regulator(LQR) is used to design the stable drift controller. Finally, based on the hardware-in-the-loop experimental platform, the reliability of the algorithm is verified. The experimental results show that the stable drift control algorithm can keep the vehicle stable under the condition of large sideslip angle, improve the stability of the vehicle in the limit conditions, and verify the real-time performance and effectiveness of the algorithm.

In order to reduce the hop size error and improve the location accuracy, a three-dimensional DV-hop location algorithm (3D-HCRL) based on hop size correction and region location is proposed in this paper. Firstly, the RSSI signal strength value is used to calculate the distance value, and the similar path search algorithm is used to correct the one-hop count and multi-hop count distance between the anchor node and the unknown node to reduce the hop size error and algorithm overhead. Secondly, region location is used to reduce the cumulative error caused by location, and the range of each location and the selection of anchor nodes are controlled by setting hop count threshold and node reliability. Finally, the minimum maximum method is introduced to calculate the unknown node location after region location. Experimental results show that the location accuracy of the proposed algorithm is better than 3DDV-hop location algorithm, TDGT location algorithm and 3D-WFLS-DVHOP location algorithm, and can effectively solve the location requirements in practical applications.

Casing threaded joint wear is one of the main reasons that affect the sealing integrity and structural integrity of casing string. Due to the complex structural characteristics of casing threaded joint, there are few studies on mechanical properties of casing threaded joint under wear conditions. In this paper, to simulate the residual strength of casing threaded joint considering wear, a finite element model of BTC casing thread is established. The stress distribution of worn casing threaded joint is analysed under the effect of inner pressure, outer pressure and axial tension. The results indicate that under the effect of inner pressure and outer pressure, the maximum and average Mises stress increases with the increase of casing wear depth; under the effect of axial tension, with the increase of wear depth, the maximum Mises stress has a little change, but the average Mises stress increases significantly. Based on the stress analysis of thread under different wear depths, the decrease rate of bearing capacity of BTC thread is measured by the increase proportion of average stress after wear. Thread residual strength gets lower with the increase of wear depth, when wear depth reaches 4 mm, burst strength, collapse strength and tensile strength decrease by 14.7%, 25.9% and 20.7% respectively. Through the methods and results presented in this paper, the residual strength of casing threaded joint can be quantized, which can provide a theoretical foundation and technical basis for casing residual strength evaluation and casing strength check.

Ventilation system is one of the important systems to ensure the safe production of underground mines. If the fan in the ventilation system fails and is not diagnosed and repaired in time, it will cause damage to the ventilation facilities. According to this view, the retrospective calculation method for fan anomaly diagnosis is deduced by using the air flow theory and the air flow data monitored by the on-line monitoring system. Finally, the accuracy and reliability of the retrospective calculation method are verified by field tests. The results show that the tracing calculation method can uniquely determine the abnormal fan roadway; the calculation method is simple and easy to realize real-time on-line diagnosis.

Compound energy storage has been widely used in practice, but there is no effective method to realize the optimal capacity allocation of multiple compound energy storage. This paper presents a multi-objective compound energy storage optimal allocation model and method based on economy, environmental protection and reliability. Firstly, the life quantitative model of each component of the combined energy storage system is established. Secondly, the distribution network structure and the efficiency index of the energy storage system are proposed. Then, the joint optimal configuration model of the combined energy storage system is established. Finally, the proposed method is verified by an example simulation.

Ultrasonic rangefinder is a measuring instrument in the field of mechanical manufacturing. It is made of the principle of acoustic ranging and is suitable for measuring the distance within 50 meters in the air. The instrument is mainly used in construction engineering, mechanical installation, farmland water conservancy, highway traffic, mine tunnel and garden planning and other occasions. In recent years, ultrasonic rangefinder manufacturing technology and verification technology have been developed by leaps and bounds. At present, the current regulation of ultrasonic rangefinder verification in China is JJG 928-1998 Ultrasonic Rangefinder Verification Regulation. However, due to its compiling year is relatively long, the equipment used has been updated, and some are no longer applicable. Such as counting frequency, ultrasonic emission frequency, temperature compensation, ranging application equation, ranging standard deviation, instrument sensitivity and other items. Therefore, it is imperative to revise the corresponding regulations. , entrusted by the National Surveying, Mapping and Geographic Information Special metrology Testing Technical Committee, China National Institute of Testing Technology is mainly responsible for the revision of JJG 928-1998 "Ultrasonic rangefinder Verification Regulations".

Aiming at the characteristics of high intensity and low efficiency of manual sorting of irregular shaped workpieces, a workpiece sorting system based on visual recognition was studied in this paper. A new sorting system based on ROS robot system in Linux environment is proposed. Machine vision technology and ROS method are used in the intelligent sorting of common shape geometry. Firstly, considering the characteristics of large amount of operation and high flexibility of workpiece sorting, the Baxter dual arm robot was selected as the hardware device, an experimental platform for workpiece sorting was constructed. Secondly, the template matching method based on edge information detection realizes image acquisition and processes the collected image to solve the difficult problem of workpiece recognition caused by large background noise and low image feature contrast, Open cv combined with VC + + was used to realize the design of visual program and the motion control function of actuator. The simulation results show that the workpiece sorting method based on visual recognition technology has the characteristics of fast timeliness, strong flexibility and high stability, and can be applied to the rapid sorting of irregular parts.