KFF-LSTM high temperature fault prediction method using in high-speed rail train converter based on known future features

被引：0

作者：

Liu D. ^{[1
,2
,3
]}

Qin Y. ^{[1
]}

Yang W. ^{[2
]}

Zhou W. ^{[4
,5
]}

Hu H. ^{[2
]}

Yang N. ^{[2
]}

Liu B. ^{[2
]}

Zhao P. ^{[3
]}

Dong G. ^{[3
]}

机构：

[1] The State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing

[2] Locomotive & Car Research Institute, China Academy of Railway Sciences Group Co. Ltd., Beijing

[3] Beijing Zongheng Electro-Mechanical Technology Co. Ltd., Beijing

[4] School of Traffic & Transportation Engineering, Central South University, Changsha

[5] Key Laboratory of Traffic Safety on Track of Ministry of Education, Changsha

来源：

Zhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (Science and Technology) | 2023年 / 54卷 / 08期

关键词：

data-driven; fault warning; future predictable features; long time series; LSTM;

D O I：

10.11817/j.issn.1672-7207.2023.08.037

中图分类号：

学科分类号：

摘要：

A long sequence fault prediction model was proposed based on known future feature LSTM method (KFF-LSTM), which utilizes predictable future features including dynamic, gradual/static and constant state for model training. At the same time, the output gate, state updating unit and hidden variable in the classical LSTM model were coordinated to optimize its prediction accuracy and time delay. Finally, the model was verified by the stator temperature data of traction converter motor on high-speed EMU site. Ablation test was conducted and visually compared by KFF-LSTM, RNN, GRU and LSTM models in terms of the mean absolute error(MAE), root mean square error(RMSE), and R2-score to demonstrate the evaluation accuracy, and delay steps to represent timeliness. The results show that compared with the other three models, the MAE and RMSE error reduction of the proposed KFF-LSTM best prediction can reach 18.0% and 10.8%, respectively, the R2-score increasing can reach 26.5% in 1-step to 16-step ahead. The time delay is also optimized by 40.0% in 16-step prediction. It has a good application and promotion prospect in the high-speed railway long-sequence data fault early warning scene. © 2023 Central South University of Technology. All rights reserved.

引用

页码：3370 / 3378

页数：8

共 23 条

[1] WANG Jun, Development and practice of PHM oriented high-speed train pedigree product technology platform[J], China Railway Science, 42, 1, (2021)
[2] WEN RUOFENG, TORKKOLA K, NARAYANASWAMY B, Et al., A multi-horizon quantile recurrent forecaster [EB/OL], (2017)
[3] LEI WANG M., Advanced multivariate time series forecasting models[J], Journal of Mathematics and Statistics, 14, 1, (2018)
[4] SUN Zhiqiang, LI Dongyang, Prediction model of photovoltaic power generation based on time-frequency entropy and neural network, Journal of Central South University(Science and Technology), 51, 1, (2020)
[5] MCCALL B., COVID-19 and artificial intelligence: protecting health-care workers and curbing the spread[J], The Lancet Digital Health, 2, 4, pp. e166-e167, (2020)
[6] GE Wanying, PATINO J, TODISCO M, Et al., Explaining deep learning models for spoofing and deepfake detection with shapley additive explanations, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6387-6391, (2022)
[7] ZHOU Haoyi, ZHANG Shanghang, PENG Jieqi, Et al., Informer: beyond efficient transformer for long sequence time-series forecasting[J], Proceedings of the AAAI Conference on Artificial Intelligence, 35, 12, pp. 11106-11115, (2021)
[8] ZHANG Chuxu, SONG Dongjin, CHEN Yuncong, Et al., A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data[J], Proceedings of the AAAI Conference on Artificial Intelligence, 33, 1, (2019)
[9] HUANG Zhi, WANG Jun, PI Lei, Et al., LSTM based trajectory prediction model for cyclist utilizing multiple interactions with environment, Pattern Recognition, 112, (2021)
[10] LI Wan, FENG Fenling, JIANG Qiwei, Prediction for railway passenger volume based on modified PSO optimized LSTM neural network, Journal of Railway Science and Engineering, 15, 12, (2018)

← 1 2 3 →