Application of GAE in incipient fault detection of speed train traction system

doi:10.16265/j.cnki.issn1003-3033.2022.06.2614

Abstract

Abstract:

In order to address problems in incipient fault detection of traction system for high-speed trains, firstly, data collected from the system was processed by GAE. Then, statistics were tested on residual generator carrying fault information, which could effectively enhance fault detection ability. Finally, effectiveness and feasibility of the proposed method were validated on a traction system platform of high-speed trains, where four kinds of faults were studied, including air gap eccentricity, bar breaking, end link and bearing. The results show that the residual generator of GAE has strong applicability and sensitivity, and can adapt to the nonlinear characteristics of traction system. There is no false alarm phenomenon in fault detection, and the missing alarm ratio is less than 6%.

Key words: generalized autoencoder (GAE), high-speed train, traction system, incipient fault detection, neural network

CHENG Chao, JU Yunfei, LIU Ming, CHEN Hongtian, HAN Ling, WEN Tao. Application of GAE in incipient fault detection of speed train traction system[J]. China Safety Science Journal, 2022, 32(6): 73-78.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Tab.1

References 12

[1]	陈志煌, 刘国恒, 王莹莹, 等. 基于动态贝叶斯网络的水下连接器故障诊断[J]. 中国安全科学学报, 2020, 30(5):81-87. doi: 10.16265/j.cnki.issn1003-3033.2020.05.013
	CHEN Zhihuang, LIU Guoheng, WANG Yingying, et al. Fault diagnosis of subsea collet connector based on dynamic bayesian network[J]. China Safety Science Journal, 2020, 30(5):81-87. doi: 10.16265/j.cnki.issn1003-3033.2020.05.013
[2]	李建明. 数据驱动的高速铁路列车掉分相诊断方法[J]. 中国安全科学学报, 2019, 29(增1):192-196.
	LI Jianming. Data-driven failure diagnosis approach of high-speed railway trains stopping in the neutral zone[J]. China Safety Science Journal, 2019, 29(S1):192-196. doi: 10.16265/j.cnki.issn1003-3033.2019.S1.034
[3]	CHEN Hongtian, JIANG Bin, LU Ningyun, et al. Deep PCA based real-time incipient fault detection and diagnosis methodology for electrical drive in high-speed trains[J]. IEEE Transactions on Vehicular Technology, 2018, 67(6):4819-4830. doi: 10.1109/TVT.2018.2818538
[4]	MAO Zehui, TAO Gang, JIANG Bin, et al. Adaptive compensation of traction system actuator failures for high-speed trains[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(11):2950-2963. doi: 10.1109/TITS.2017.2666428
[5]	CHEN Zhiwen, DING Steven, PENG Tao, et al. Fault detection for non-Gaussian processes using generalized canonical correlation analysis and randomized algorithms[J]. IEEE Transactions on Industrial Electronics, 2018, 65(2):1559-1567. doi: 10.1109/TIE.2017.2733501
[6]	CHEN Zhiwen, ZHANG Kai, DING Steven, et al. Improved canonical correlation analysis-based fault detection methods for industrial processes[J]. Journal of Process Control, 2016, 41:26-34. doi: 10.1016/j.jprocont.2016.02.006
[7]	CHEN Hongtian, JIANG Bin, LU Ningyun, et al. Multi-mode kernel principal component analysis—based incipient fault detection for pulse width modulated inverter of China railway high-speed 5[J]. Advances in Mechanical Engineering, 2017, 9(10):1-12.
[8]	HARMOUCHE Jinane, DELPHA Claude, DIALLO Demba. Incipient fault detection and diagnosis based on kullback-leibler divergence using principal component analysis: part I[J]. Signal Processing, 2014, 94: 278-287. doi: 10.1016/j.sigpro.2013.05.018
[9]	GIANTOMASSI Andrea, FERRACUTI Francesco, IARLORI Sabrina, et al. Electric motor fault detection and diagnosis by kernel density estimation and kullback-leibler divergence based on stator current measurements[J]. IEEE Transactions on Industrial Electronics, 2014, 62(3): 1770-1780. doi: 10.1109/TIE.2014.2370936
[10]	SIVLA Vin De, TENENBAUM Joshua. Global versus local methods in nonlinear dimensionality reduction[C]. Advances in Neural Information Processing Systems, 2002:721-728.
[11]	WANG Wei, HUANG Yan, WANG Yizhou, et al. Generalized autoencoder: a neural network framework for dimensionality reduction[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014:490-497.
[12]	YANG Xiaoyue, QIAO Xinyu, CHENG Chao, et al. A tutorial on hardware-implemented fault injection and online fault diagnosis for high-speed trains[J]. Sensors, 2021, 21(17):Doi: 10.3390/s21175957. doi: 10.3390/s21175957

故障状态	f1	f2	f3	f4
误报率	0	0	0	0
漏报率	6.0	4.5	5.0	5.0

[1]	LIN Sen, HAN Xiaohui, LI Gangqing, WANG Peng, ZHAO Cunjin, YANG Zhibin. Research on stress corrosion crack failure of MIG joints on aluminum alloy of high-speed trains [J]. China Safety Science Journal, 2022, 32(6): 115-122.
[2]	SONG Li, GUO Wei, LI Fei, LIU Leyu. Velocity control algorithm of high-speed trains based on RBF-ADRC [J]. China Safety Science Journal, 2022, 32(6): 131-136.
[3]	ZHANG Changfan, HU Xinliang, HE Jing, LIU Jianhua, HOU Na. Defect classification model for high-speed train wheelset treads based on SimAM and SpinalNet [J]. China Safety Science Journal, 2022, 32(6): 38-43.
[4]	HUANG Deqing, NI Chenjia, QIN Na, YU Wei. Research on redundant time reallocation at stations for purpose of minimum delay [J]. China Safety Science Journal, 2022, 32(6): 66-72.
[5]	HE Yongbo, CAO Zhubing. Pressure compensation algorithm of fire gas sensors based on IPSO-BP model [J]. China Safety Science Journal, 2022, 32(2): 107-114.
[6]	SHI Juan, CHANG Dingyi, ZHENG Peng. An early warning model of unsafe behaviors of construction workers based on BP neural network [J]. China Safety Science Journal, 2022, 32(1): 27-33.
[7]	ZHENG Dukui, CHENG Yuanpeng, LI Haoran, HE Tianlong. Application of IAFSA-GRNN in CO₂ corrosion rate prediction of oil gathering and transportation pipelines [J]. China Safety Science Journal, 2022, 32(1): 110-117.
[8]	YUE Rentian, HAN Meng. Diagnosis of safety operation state for ATC position based on four diagnostic methods [J]. China Safety Science Journal, 2021, 31(9): 52-59.
[9]	YANG Lixia, XU Maozeng, CHEN Renxiang. Study on recognition of traffic terrorist attacks with limited data samples [J]. China Safety Science Journal, 2021, 31(8): 30-37.
[10]	ZHAO Jiangping, XU Heng, DANG Yueyue. Research on bolt detection of railway passenger cars based on improved Faster R-CNN [J]. China Safety Science Journal, 2021, 31(7): 82-89.
[11]	ZHANG Kai, ZHANG Ke, LI Kun. Prediction model of rockburst grade based on PCA-neural network [J]. China Safety Science Journal, 2021, 31(3): 96-104.
[12]	WANG Haibiao, CHEN Haichao, LI Rui, YU He, ZHAO Tianyi. Construction and application of management system of urban emergency shelters [J]. China Safety Science Journal, 2021, 31(12): 153-159.
[13]	LYU Wei, QIN Shuangshuang, MU Zhiguo, WANG Jinghui, JIANG Yajuan, LI Jiawei. Simulation study on evacuation of CRH380AL high-speed train and its influencing factors [J]. China Safety Science Journal, 2020, 30(8): 164-170.
[14]	BI Aorui, LUO Zhengshan, SONG Yingying, ZHANG Xinsheng. Residual strength analysis of internally corroded submarine pipeline based on FOA-GRNN model [J]. China Safety Science Journal, 2020, 30(6): 78-83.
[15]	XIAO Peng, XIE Xingjun, SHUANG Haiqing, LIU Chaoyang, WANG Haining, XU Jingcang. Prediction of gas emission quantity based on KPCA-CMGANN algorithm [J]. China Safety Science Journal, 2020, 30(5): 39-47.