Research on arc fault identification method based on improved backpropagation neural network

Li Pengbo; Cunxu Wang

doi:10.1117/12.2635029

25 April 2022 Research on arc fault identification method based on improved backpropagation neural network

Li Pengbo, Cunxu Wang

Proceedings Volume 12244, 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022); 122444F (2022) https://doi.org/10.1117/12.2635029
Event: 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022), 2022, Guilin, China

Abstract

Arc fault is a common fault type in power system, but arc fault is not easy to be found. In order to improve the accuracy of arc fault identification of power system, this paper first uses MATLAB /Simulink to build an arc fault model. The experimental verification shows that the model is in line with the characteristics of arc fault of power system. Then, aiming at the shortcomings of BP neural network, particle swarm optimization algorithm is applied to overcome the characteristics of slow recognition speed and low accuracy of BP neural network. Finally, in order to verify the effectiveness of the proposed method, simulation verification is made on the MATLAB software platform. Experimental results show that the improved identification method has a certain degree of improvement in the accuracy and speed of identification.

Citation Download Citation

Li Pengbo and Cunxu Wang "Research on arc fault identification method based on improved backpropagation neural network", Proc. SPIE 12244, 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022), 122444F (25 April 2022); https://doi.org/10.1117/12.2635029

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available