An effective CNN-MHSA method for the fault diagnosis of ZPW-2000A track circuit

被引:2
作者
Ke, Ting [1 ]
Zhang, Yajiang [1 ]
Hu, Qizheng [2 ]
Zhang, Chuanlei [1 ]
机构
[1] Tianjin Univ Sci & Technol, Coll Artificial Intelligence, Tianjin 300457, Peoples R China
[2] China Acad Railway Sci Corp Ltd, Signal & Commun Res Inst, Beijing, Peoples R China
关键词
ZPW-2000A track circuit; fault diagnosis; feature extraction; CNN; multi-head self-attention mechanism; HEAD SELF-ATTENTION;
D O I
10.1177/01423312241273855
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The mainstream methods for fault diagnosis of ZPW-2000A track circuits are overly complex in extracting features from sequence data, and their feature extraction capability is relatively limited, thus impacting the performance of fault diagnosis. To address this issue, we propose a fault diagnosis model for track circuits, named as convolutional neural network incorporating multi-head self-attention mechanism (CNN-MHSA). On one hand, the local features of sequence data are locally sensed and extracted by the convolutional layer; on the other hand, the global features of sequence data are captured by establishing long-distance dependency relationships through the multi-head self-attention layer. The dual extraction of local and global features enables accurate diagnosis of faults. Finally, we collect 27 fault modes and 2 normal operation modes in the simulation system and conduct a large number of numerical experiments. The experimental results show that the fault diagnosis accuracy of the CNN-MHSA model in this paper can reach 97.45%, which is an improvement of 0.64%, 0.44%, 0.44%, 0.44%, 0.33%, 0.22%, and 0.11% compared with models such as Decision Tree, Random Forest, CatBoost, long short-term memory (LSTM), convolutional neural network (CNN), and CNN-LSTM. It also has obvious advantages in evaluation metrics such as precision, recall, Macro-F1, and Micro-F1, as well as other evaluation metrics. Therefore, the model significantly improves the comprehensive performance of ZPW-2000A track circuit fault diagnosis and can be used as a more effective fault diagnosis method.
引用
收藏
页数:13
相关论文
共 50 条
  • [31] A New Intelligent Bearing Fault Diagnosis Method Using SDP Representation and SE-CNN
    Wang, Hui
    Xu, Jiawen
    Yan, Ruqiang
    Gao, Robert X.
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2020, 69 (05) : 2377 - 2389
  • [32] A Fault Diagnosis Method for Rotating Machinery Based on CNN With Mixed Information
    Zhao, Zhiqian
    Jiao, Yinghou
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (08) : 9091 - 9101
  • [33] A Fault Diagnosis Method for Planetary Gearbox Based on GAF-CNN
    Pang X.-Y.
    Tong Y.
    Wei Z.-H.
    Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 2020, 40 (11): : 1161 - 1167
  • [34] Rolling bearing fault diagnosis method based on MTF-CNN
    Lei C.
    Xia B.
    Xue L.
    Jiao M.
    Zhang H.
    Zhendong yu Chongji/Journal of Vibration and Shock, 2022, 41 (09): : 151 - 158
  • [35] MT-ConvFormer: A Multitask Bearing Fault Diagnosis Method Using a Combination of CNN and Transformer
    Han, Yufei
    Zhang, Fan
    Li, Zhaoqi
    Wang, Qichen
    Li, Chaofan
    Lai, Pei
    Li, Tianrui
    Teng, Fei
    Jin, Zhenzhen
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2025, 74
  • [36] Fault Diagnosis for Railway Track Circuit Based on Wavelet Packet Power Spectrum and ELM
    Wang, Zicheng
    Guo, Jin
    Zhang, Yadong
    Luo, Rong
    PROCEEDINGS OF 2016 11TH INTERNATIONAL CONFERENCE ON RELIABILITY, MAINTAINABILITY AND SAFETY (ICRMS'2016): INTEGRATING BIG DATA, IMPROVING RELIABILITY & SERVING PERSONALIZATION, 2016,
  • [37] A Comprehensive Fault Detection Method for Jointless Track Circuit Based on SA Algorithm
    Zhang Y.
    Chang G.
    Zhao B.
    1600, Science Press (39): : 68 - 72
  • [38] Fault diagnosis method for aeroengine bearings based on PIRD-CNN
    Zhang, Bowen
    Pang, Xinyu
    Cheng, Baoan
    Li, Feng
    Su, Shenzheng
    Zhendong yu Chongji/Journal of Vibration and Shock, 43 (18): : 201 - 207and231
  • [39] Diagnosis Method for Multiple Compensation Capacitor Faults of Jointless Track Circuit
    Qianqian W.
    Weili L.
    Minan T.
    Kaiyue Z.
    EEA - Electrotehnica, Electronica, Automatica, 2022, 70 (03): : 12 - 21
  • [40] AutoVMDPgram: An Effective Method for Fault Diagnosis of Rolling Bearing
    Li, Hua
    Wang, Tianyang
    Zhang, Feibin
    Chu, Fulei
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,