The invention discloses a 1DCNN-LSTM-based turnout fault diagnosis method and system, and relates to the field of fault diagnosis, and the method comprises the steps: carrying out the decomposition of different frequencies of a to-be-diagnosed motion power signal through employing an empirical mode decomposition algorithm, and obtaining a plurality of intrinsic mode function signals; selecting a multi-channel input signal from the plurality of intrinsic mode function signals; inputting the multi-channel input signal into a turnout switch machine fault diagnosis model, and outputting a fault diagnosis identification result; the turnout switch machine fault diagnosis model is determined by training a deep learning neural network through an action power data set; the deep learning neural network comprises a one-dimensional convolutional neural network and a long short-term memory network which are connected in sequence; the sample data in the action power data set comprises a multi-channel input signal and a state type corresponding to the multi-channel input signal, the state type comprises a normal operation state and a fault state, and the fault diagnosis efficiency of the turnout switch machine is improved.

    本发明公开基于1DCNN‑LSTM的道岔故障诊断方法及系统,涉及故障诊断领域,该方法包括:采用经验模态分解算法对待诊断动作功率信号进行不同频率分解,获得多个固有模态函数信号;从多个所述固有模态函数信号中选取出多通道输入信号;将所述多通道输入信号输入道岔转辙机故障诊断模型,输出故障诊断识别结果;所述道岔转辙机故障诊断模型是通过动作功率数据集对深度学习神经网络进行训练确定的;所述深度学习神经网络包括依次连接的一维卷积神经网络和长短期记忆网络;所述动作功率数据集中样本数据包括多通道输入信号和多通道输入信号对应的状态类型,所述状态类型包括正常运行状态和故障状态,本发明提高了道岔转辙机故障诊断效率。


    Access

    Download


    Export, share and cite



    Title :

    Turnout fault diagnosis method and system based on 1DCNN-LSTM


    Additional title:

    基于1DCNN-LSTM的道岔故障诊断方法及系统


    Contributors:
    FU YATING (author) / WEN SHIMING (author) / YANG HUI (author) / LI ZHONGQI (author) / TAN CHANG (author) / ZHOU YANLI (author)

    Publication date :

    2023-03-28


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B61L Leiten des Eisenbahnverkehrs , GUIDING RAILWAY TRAFFIC / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Milling Tool Wear Prediction Based on 1DCNN-LSTM

    Xia, Wanliang / Zhou, Jin / Jia, Wenju et al. | Springer Verlag | 2023


    Turnout control circuit fault diagnosis system

    FENG GUIPING / WANG ZHIXIN / SHI LONG et al. | European Patent Office | 2023

    Free access

    Fault diagnosis system and method for turnout collection representation

    CHEN XINFU / HU ZHENHUA / ZHANG TAO et al. | European Patent Office | 2023

    Free access

    Railway turnout fault diagnosis method and system based on machine learning

    CHENG MENGMENG | European Patent Office | 2024

    Free access

    Fault Diagnosis of Railway Turnout Based on Random Forests

    Zhang, Huiyue / Wang, Zhipeng / Wang, Ning et al. | TIBKAT | 2020