High-speed train bogies are the critical components of high-speed trains, which can play the role of traction, braking, and buffering. In long-term train service, bogies are prone to wear and aging. Currently, most studies on fault diagnosis methods are aimed at single equipment identification. It is challenging to accurately diagnose the faults of such coupled multi-equipment combination systems as bogies. Multiple devices on the bogie have implied correlations in space, and fully exploiting their spatial features enhances the fault diagnosis accuracy. This paper proposes a new bogie fault diagnosis method based on the directional graph of train bogie: RS-GAT model. The model uses the Residual-Squeeze Network (RS-Net) to construct the framework of the model and use the Graph Attention Network (GAT) for spatial information fusion and feature extraction to identify bogie faults. Using six datasets collected under the operation of high-speed trains, experimental results demonstrate that the proposed approach has better effectiveness than the RS-Net class model and single-layer graph class model, with diagnosis accuracy near 96%. Ablation experiments and comparisons between RS-GAT and RS-GCN verify the effectiveness of RS-Net framework and GAT model in fault classification. In addition, the RS-GAT model is found to have strong robustness when different models are analyzed using small-scale data sets.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An Adaptive Multisensor Fault Diagnosis Method for High-Speed Train Bogie


    Contributors:
    Man, Jie (author) / Dong, Honghui (author) / Jia, Limin (author) / Qin, Yong (author) / Zhang, Jun (author)


    Publication date :

    2023-06-01


    Size :

    16926592 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    HIGH-SPEED TRAIN BOGIE

    ZONG HAN / ZHU YONG / LI KAI | European Patent Office | 2020

    Free access

    AttGGCN Model: A Novel Multi-Sensor Fault Diagnosis Method for High-Speed Train Bogie

    Man, Jie / Dong, Honghui / Jia, Limin et al. | IEEE | 2022


    Bogie for high-speed train and frame of bogie

    ZHANG ZHENXIAN / LI XIAOYAN / ZHOU PINGYU et al. | European Patent Office | 2015

    Free access

    High-speed railway bullet train bogie

    LI ZE / ZHANG HUIYING / YANG CHANGXIU et al. | European Patent Office | 2021

    Free access