Developing a trustworthy framework for intelligent fault diagnosis (IFD) of machines has two major challenges: confidently recognizing known faults and precisely detecting novel faults. However, current IFD frameworks are typically based on the closed-world assumption and tackle the two issues independently, making it hard to meet the expectations of reliable diagnosis in complicated working situations. In this paper, a Pro babilistic framework for ${M}$ echanical fault diagn ${o}$ sis (ProMo) is proposed to integrate misidentification and out-of-distribution (OOD) detection for high-speed train bogie. ProMo uses variational parameters to capture uncertainties at both the feature and prediction levels, in this way the misclassified and OOD samples with high predictive uncertainty are differentiated. To begin, a Bayesian deep neural network with a hierarchical classifier is built, offering diverse predictions and enabling ensemble uncertainty estimate. Then, a probabilistic null space analysis technique for post hoc OOD detection is presented, in which the magnitude of feature projections indicates the OOD-ness. Additionally, a novel metric assessing classification correctness and prediction reliability simultaneously is proposed. Extensive experiments revealed that ProMo outperforms state-of-the-art methods and achieves reliable fault diagnosis, even in the presence of covariate shift in monitoring data.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Integrating Misidentification and OOD Detection for Reliable Fault Diagnosis of High-Speed Train Bogie


    Beteiligte:
    Feng, Yong (Autor:in) / Chen, Jinglong (Autor:in) / Xie, Zongliang (Autor:in) / Xie, Jingsong (Autor:in) / Pan, Tongyang (Autor:in) / Li, Chao (Autor:in) / Zhao, Qing (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.09.2024


    Format / Umfang :

    10107714 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



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

    Man, Jie / Dong, Honghui / Jia, Limin et al. | IEEE | 2023


    HIGH-SPEED TRAIN BOGIE

    ZONG HAN / ZHU YONG / LI KAI | Europäisches Patentamt | 2020

    Freier Zugriff

    Bogie for high-speed train and frame of bogie

    ZHANG ZHENXIAN / LI XIAOYAN / ZHOU PINGYU et al. | Europäisches Patentamt | 2015

    Freier Zugriff

    High-speed railway bullet train bogie

    LI ZE / ZHANG HUIYING / YANG CHANGXIU et al. | Europäisches Patentamt | 2021

    Freier Zugriff

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

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