Prediction for geometric degradation of track on machine learning

Junjie Hao; Rengkui Liu

doi:10.1117/12.2689517

7 September 2023 Prediction for geometric degradation of track on machine learning

Junjie Hao, Rengkui Liu

Proceedings Volume 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023); 127903U (2023) https://doi.org/10.1117/12.2689517
Event: 8th International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 2023, Hangzhou, China

Abstract

High track quality is the basis of ensuring the safe and comfortable operation of trains, and it is of great significance to accurately grasp the degradation law of track geometry to ensure track quality. Long Short-Term Memory (LSTM) network in machine learning has the function of remembering historical information, which can better predict the development trend of nonlinear time series, a prediction model of orbital geometric degradation based on LSTM is constructed by using historical data of track quality index (TQI). In order to verify the validity of the model, the test data of Lanzhou-Urumqi High-speed Railway Track Inspection Vehicle are selected. The results show that the prediction model of track geometric degradation based on LSTM established in this paper is effective and has high prediction accuracy.

Citation Download Citation

Junjie Hao and Rengkui Liu "Prediction for geometric degradation of track on machine learning", Proc. SPIE 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 127903U (7 September 2023); https://doi.org/10.1117/12.2689517

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Machine learning

Inspection

Artificial neural networks

Matrices

Process modeling

Stochastic processes

RELATED CONTENT

Prediction of used car prices using back propagation neural network...
Proceedings of SPIE (January 12 2023)

Variable input structure user load forecasting method based on user...
Proceedings of SPIE (February 06 2024)

Personalised federated learning based on probabilistic knowledge transfer
Proceedings of SPIE (July 19 2024)

A new stroke prediction model combined algorithm based on artificial...
Proceedings of SPIE (October 20 2022)

Comparison of different machine learning models on feature extraction for...
Proceedings of SPIE (March 15 2019)

Two-dimensional boundary inspection using autoregressive model
Proceedings of SPIE (February 01 1991)

A federated learning scheme based on personalized differential privacy and...
Proceedings of SPIE (March 27 2024)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years