Real-time Diagnosis of Gear Slack Fault in Electric Locomotive Based on System Signal Time-series Feature Recognition

被引：0

作者：

Li X. ^{[1
]}

Ni Q. ^{[2
]}

Liu K. ^{[1
]}

Xu S. ^{[3
]}

Huang Q. ^{[3
]}

机构：

[1] College of Mechanical and Vehicle Engineering, Hunan University, Hunan Province, Changsha

[2] School of Automation, Guangdong University of Technology, Guangdong Province, Guangzhou

[3] CRRC Zhuzhou Electric Locomotive Research Institute, Hunan Province, Zhuzhou

来源：

Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2023年 / 43卷 / 03期

基金：

中国国家自然科学基金;

关键词：

CUSUM; dynamic time warping; gear transmission system; real-time diagnosis; slack fault; time-series feature mode;

D O I：

10.13334/j.0258-8013.pcsee.212215

中图分类号：

学科分类号：

摘要：

The traction control unit is the only control device of the train power system. Its comprehensive capacity of information acquisition and processing are fully utilized to make real-time and accurate diagnosis of the running parts associated with the traction drive system to achieve more timely protection, which is very important to prevent the expansion of faults and improve the reliability and safety of the train. The existing gear slack fault diagnosis methods only consider the traction motor speed information, which has the problems of false alarm or missing alarm. Therefore, a real-time slack fault diagnosis method based on system signal time-series feature recognition is proposed. Firstly, starting with the analysis of slack fault mechanism of gear transmission system, combined with the historical fault case data, the feature indexes that can effectively characterize the fault are extracted from the relevant system signals. Secondly, the change law of feature indexes under different working conditions of the train is revealed, and a multi-variable time-series feature mode library strongly related to slack fault is established. Then, based on the dynamic time warping algorithm, the real-time similarity matching with the time-series features related to the feature mode library is realized, and the CUSUM algorithm is used for diagnosis decision-making to realize the effective recognition of slack fault. Finally, the actual train operation data are used to verifythe fault diagnosis model proposed. The test results show that compared with the existing methods, the proposed method significantly improves the slack fault detection rate, and no slack fault false alarm will be activated in case of speed sensor fault and wheel set idling, which has good practical value. ©2023 Chin.Soc.for Elec.Eng.

引用

页码：1200 / 1209

页数：9

共 29 条

[1]

GE Xinglai, Dong XIE, DENG Qingli, Overview of fault diagnosis and fault-tolerant control methods for vehicular traction converter system[J], Journal of Power Supply, 18, 1, pp. 28-44, (2020)

[2]

XU Shaolong, NI Qiang, LI Xueming, Optimization strategy of IGBT life loss in traction converter of autonomous driving electric locomotive[J], Proceedings of the CSEE, 41, 18, pp. 6381-6389, (2021)

[3]

CHEN Zhiwen, Xueming LI, YANG Chao, A data-driven ground fault detection and isolation method for main circuit in railway electrical traction system[J], ISA Transactions, 87, pp. 264-271, (2019)

[4]

Xueming LI, Jiamin XU, CHEN Zhiwen, Real-time fault diagnosis of pulse rectifier in traction system based on structural model[J], IEEE Transactions on Intelligent Transportation Systems, 23, 3, pp. 2130-2143, (2022)

[5]

CHEN Hongtian, JIANG Bin, A review of fault detection and diagnosis for the traction system in high-speed trains[J], IEEE Transactions on Intelligent Transportation Systems, 21, 2, pp. 450-465, (2020)

[6]

CHEN Hongtian, JIANG Bin, DING S X, Data-driven fault diagnosis for traction systems in high-speed trains ： a survey ， challenges ， and perspectives[J], IEEE Transactions on Intelligent Transportation Systems, 23, 3, pp. 1700-1716, (2022)

[7]

Chao YANG, Weihua GUI, CHEN Zhiwen, Voltage difference residual-based open-circuit fault diagnosis approach for three-level converters in electric traction systems[J], IEEE Transactions on Power Electronics, 35, 3, pp. 3012-3028, (2020)

[8]

Yang XIA, Yan XU, Bin GOU, A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification[J], IEEE Transactions on Industrial Informatics, 16, 8, pp. 5223-5233, (2020)

[9]

Bin GOU, Yan XU, Yang XIA, An intelligent time-adaptive data-driven method for sensor fault diagnosis in induction motor drive system[J], IEEE Transactions on Industrial Electronics, 66, 12, pp. 9817-9827, (2019)

[10]

LIU Xiaofeng, SHU Renjie, BO Lin, A novel sparse classification fusion method and its application in locomotive bearing fault diagnosis[J], Proceedings of the CSEE, 40, 17, pp. 5675-5681, (2020)

← 1 2 3 →