Faults of railway suspension units may endanger vehicle operation safety. Therefore, timely fault detection of railway suspension is necessary. The reported fault detection method that uses Bidirectional Long Short-Term Memory (BiLSTM) neural network in a denoising autoencoder fashion suffers from a shortcoming that the condition monitoring data under faulty states needs to be ultilized to determine the added noise level. Such data is not always available in practice. In this paper, we modified the BiLSTM such that the output data point is excluded from the input when predicting this specific output data point. The requirement of using condition monitoring data under faulty states is therefore relaxed, as the modified BiLSTM is free from determining the level of added noise. A case study on railway suspension fault detection was presented. We used the railway vehicle dynamics model to generate car body vibration under healthy, three levels of reduced first suspension stiffness states, and three levels of reduced first suspension damping states. We compared the performance of the modified BiLSTM with the linear autoregression model, LSTM, and BiLSTM-DAE models. The results have shown that the modified BiLSTM-based fault detection method performs the best, having the highest area under the receiver operating curve.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A modified bidirectional long short-term memory neural network for rail vehicle suspension fault detection


    Contributors:
    Chen, Yuejian (author) / Niu, Gang (author) / Li, Yifan (author) / Li, Yongbo (author)

    Published in:

    Vehicle System Dynamics ; 61 , 12 ; 3136-3160


    Publication date :

    2023-12-02


    Size :

    25 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown