The invention discloses a high-speed train traction converter fault diagnosis and prediction method based on a twinning network model, and the method comprises the steps: building a T-Si am model through employing a twinning network model, extracting the hidden time features in multiple sensors through employing a time convolution network TCN model and a one-dimensional convolution network 1D-CNN model, and carrying out the time sequence prediction. The characteristics of the traction converter are extracted by using a branch network of the T-Siam framework, whether the states of the traction converter in two time periods are the same is obtained by using a measurement network module of the T-Siam framework, and the state of the traction converter is obtained through a verification module. After verification by using real fault data of the traction converter of the high-speed train, compared with the prior art, the method disclosed by the invention has a better fault diagnosis effect, and the accuracy rate reaches 99.6%. According to the method, the T-Si am model is used for predicting the fault state of the traction converter after a period of time, and the method is superior to other comparison prediction models.

    本发明公开了一种基于孪生网络模型的高速列车牵引变流器故障诊断与预测方法,使用孪生网络(Si ameseN Network)模型构建T‑Si am模型,使用时间卷积网络TCN模型与一维卷积网络1D‑CNN模型提取多传感器中隐藏的时间特征并进行时序预测。使用T‑Siam框架的分支网络对牵引变流器的特征进行提取,使用T‑Siam框架的度量网络模块得到两时段牵引变流器状态是否相同,通过验证模块得到牵引变流器的状态。使用真实的高速列车牵引变流器故障数据验证后表明,本发明所述方法与现有技术相比,具有更好的故障诊断效果,准确率达到99.6%。本发明使用T‑Si am模型预测了牵引变流器一段时间后的故障状态,优于其他对比预测模型。


    Access

    Download


    Export, share and cite



    Title :

    High-speed train traction converter fault diagnosis and prediction method based on twin network model


    Additional title:

    一种基于孪生网络模型的高速列车牵引变流器故障诊断与预测方法


    Contributors:
    DONG HONGHUI (author) / WANG ZHUO (author) / MAN JIE (author) / YANG ZHIQIANG (author)

    Publication date :

    2024-02-06


    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 / G01D MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE , Anzeigen oder Aufzeichnen in Verbindung mit Messen allgemein / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen




    Tiny fault detection method for high-speed train traction system

    WANG YAN / CHENG CHAO / GAO HONGLIU | European Patent Office | 2022

    Free access

    Fault Diagnosis of High Speed Maglev Train

    Yuan, Jian-Jun / Cui, Wei-Qi / Chen, Jin-Liang et al. | ASCE | 2015



    TRACTION MODULE OF A HIGH-SPEED TRAIN

    DEBO PER / BERA LORAN / LAMPENYA BRYUNO et al. | European Patent Office | 2021

    Free access