Early fault diagnosis strategy for high-speed train suspension systems based on model-agnostic meta-learning

被引:3
作者
Yang, Funing [1 ]
Liu, Jikai [1 ]
Hua, Chunrong [1 ]
Liu, Weiqun [1 ]
Dong, Dawei [1 ]
机构
[1] Southwest Jiaotong Univ, Sch Mech Engn, Chengdu, Peoples R China
基金
中国国家自然科学基金;
关键词
High-speed train; suspension system; fault diagnosis; model-agnostic meta-learning; grouping normalisation; sample reconstruction; RAILWAY VEHICLE SUSPENSION; BOGIE;
D O I
10.1080/00423114.2023.2295935
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Early fault diagnosis of suspension systems is essential for the safe operation of high-speed trains. However, neural network-based fault diagnosis methods have two remaining issues: the fault samples are difficult to obtain in practice and the early fault features are too weak to be extracted directly from the raw vibration signals using neural networks. A novel strategy is proposed for early faults diagnosis in suspension systems (i.e. component performance degradation within 20%) by integrating a new sample reconstruction method, a new grouping normalisation method, and model-agnostic meta-learning (MAML) algorithm. First, the 1D raw vibration signals are converted to 2D feature matrices consisting of artificial features using the sample reconstruction method; meanwhile, the grouping normalisation method is used to enhance the early weak fault features in the feature matrices. Second, MAML specialises in few-shot model training for early fault diagnosis, with the feature matrices as the training samples. Finally, the results are compared with those obtained using other current methods. The numerical results show that the proposed strategy yielded excellent performance in the few-shot early faults diagnosis of suspension systems, achieving a maximum accuracy of 94.75%.
引用
收藏
页码:2510 / 2532
页数:23
相关论文
共 44 条
[1]   Fault Diagnosis of High-Speed Train Bogie Based on Capsule Network [J].
Chen, Lingling ;
Qin, Na ;
Dai, Xi ;
Huang, Deqing .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2020, 69 (09) :6203-6211
[2]  
China Academy of Railway Sciences, 2009, CHINA ACAD RAILWAY S
[3]   Adaptive Sensor Fault Detection for Rail Vehicle Suspension Systems [J].
Dong, Min ;
Tao, Gang ;
Wen, Liyan ;
Jiang, Bin .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2019, 68 (08) :7552-7565
[4]   Fault detection of damper in railway vehicle suspension based on the cross-correlation analysis of bogie accelerations [J].
Dumitriu, Madalina .
MECHANICS & INDUSTRY, 2019, 20 (01)
[5]  
Finn C, 2017, PR MACH LEARN RES, V70
[6]   Data-driven condition-based monitoring of high-speed railway bogies [J].
Gasparetto, Livio ;
Alfi, Stefano ;
Bruni, Stefano .
INTERNATIONAL JOURNAL OF RAIL TRANSPORTATION, 2013, 1 (1-2) :42-56
[7]   Bogie fault diagnosis under variable operating conditions based on fast kurtogram and deep residual learning towards imbalanced data [J].
Geng, Yixuan ;
Wang, Zhipeng ;
Jia, Limin ;
Qin, Yong ;
Chen, Xinan .
MEASUREMENT, 2020, 166
[8]  
Gun XX, 2015, CHIN CONT DECIS CONF, P1676, DOI 10.1109/CCDC.2015.7162189
[9]  
HE KM, 2016, PROC CVPR IEEE, P770, DOI [DOI 10.1109/CVPR.2016.90, 10.1109/CVPR.2016.90]
[10]   High-Speed Rail Suspension System Health Monitoring Using Multi-Location Vibration Data [J].
Hong, Ning ;
Li, Lishuai ;
Yao, Weiran ;
Zhao, Yang ;
Yi, Cai ;
Lin, Jianhui ;
Tsui, Kwok Leung .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2020, 21 (07) :2943-2955