Deep Learning-based Optimization of Fault Early Warning and Maintenance Decision Making for Critical Equipment in Railway Transportation

DOI

10.2991/978-94-6463-793-9_78How to use a DOI?

Keywords

smart transportation; real-time decision-making; industrial IoT

Abstract

With the rapid development of urban rail transit, the early warning of equipment failure and maintenance decision-making is particularly important. Based on deep learning algorithm, this paper proposes a method for the optimization of early warning and maintenance decision-making of key equipment failure in rail transit. Firstly, the data of key equipment's operation status, fault records, environmental factors and maintenance records are collected through the rail transportation monitoring system, and the equipment fault data set is established. Then, We adopt the Morlet wavelet as the basis function due to its optimal time-frequency localization properties, which enhances the extraction of transient fault features in non-stationary signals. In this paper, LSTM is chosen due to its proven capability in capturing long-term dependencies in time series data. Compared to traditional RNNs, LSTM’s gated mechanisms effectively mitigate gradient vanishing issues, making it suitable for modeling the complex temporal evolution of equipment faults. The experimental results show that the method in this paper performs well in the mean absolute percentage error (MAPE) index, and the prediction accuracy is significantly improved compared with the traditional method, which verifies the effectiveness of the optimization of fault early warning and maintenance decision-making based on deep learning.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zhenyao Yin
AU  - Yongjian Liu
AU  - Weiwei Sun
PY  - 2025
DA  - 2025/07/28
TI  - Deep Learning-based Optimization of Fault Early Warning and Maintenance Decision Making for Critical Equipment in Railway Transportation
BT  - Proceedings of the 2025 8th International Conference on Traffic Transportation and Civil Architecture (ICTTCA 2025)
PB  - Atlantis Press
SP  - 932
EP  - 939
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-793-9_78
DO  - 10.2991/978-94-6463-793-9_78
ID  - Yin2025
ER  -