The invention provides a turnout point switch abnormity diagnosis method based on machine learning. The method comprises the steps: collecting a plurality of types of working characteristic curves during the operation of a turnout point switch for many times, building a plurality of working characteristic curve groups, and generating corresponding curve data for each group of working characteristic curves based on the selected reference working characteristic curve groups; putting the curve data into a normal data pool or a fault data pool based on a label set for the curve data; sampling curve data in normal and fault data pools to establish a training data set and a test data set; pre-training a convolutional neural network model through the training data set and the test data set, wherein the model is used for recognizing whether a fault occurs or not and recognizing a fault type when the turnout point switch acts; and processing the working characteristic curve group to be diagnosed to obtain curve data of the working characteristic curve group, and inputting the curve data into the trained convolutional neural network model to obtain a corresponding turnout point switch fault judgment result. The invention further provides a turnout point switch abnormity diagnosis system based on machine learning.

    本发明提供一种基于机器学习的道岔转辙机异常诊断方法,包含步骤:多次采集道岔转辙机动作时的多类工作特性曲线建立多个工作特性曲线组,基于选取的参考工作特性曲线组为每组工作特性曲线生成对应的曲线数据;基于为曲线数据设置的标签将曲线数据放入正常数据池或故障数据池;采样正常、故障数据池中的曲线数据建立训练数据集和测试数据集;通过训练数据集、测试数据集预训练卷积神经网络模型,该模型用于识别道岔转辙机动作时是否出现故障及故障类型;处理需要诊断的工作特性曲线组获取其曲线数据,将该曲线数据输入至训练好的卷积神经网络模型中,得到对应的道岔转辙机故障判断结果。本发明还提供一种基于机器学习的道岔转辙机异常诊断系统。


    Access

    Download


    Export, share and cite



    Title :

    Turnout point switch abnormity diagnosis method and system based on machine learning


    Additional title:

    一种基于机器学习的道岔转辙机异常诊断方法及系统


    Contributors:
    ZHU CUNREN (author) / HU ENHUA (author) / TU PENGFEI (author) / WEI SHENGXIN (author)

    Publication date :

    2021-04-16


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

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



    Turnout switch machine fault diagnosis method and device based on ensemble learning

    HE DEQIANG / LAO ZHENPENG / JIN ZHENZHEN et al. | European Patent Office | 2023

    Free access

    Intelligent turnout point switch system

    GANG JIANLEI / DUAN WU / PAN MING et al. | European Patent Office | 2015

    Free access

    Locking device and locking method for turnout switch machine and turnout switch machine

    HILLEBRECHT FRANK / PETRICK ROBERT / WALTER NADINE | European Patent Office | 2023

    Free access

    Railway turnout switch machine

    XU YAN | European Patent Office | 2021

    Free access

    Railway turnout fault diagnosis method and system based on machine learning

    CHENG MENGMENG | European Patent Office | 2024

    Free access