The invention belongs to the technical field of rail transit turnout fault diagnosis, and particularly relates to a railway turnout fault diagnosis method and system based on machine learning, and the method comprises the steps: sampling a power characteristic curve of a switch machine for multiple times, carrying out the normalization processing and analysis of the collected power characteristic curve, and obtaining a power characteristic curve of the switch machine; the method comprises the following steps: acquiring power characteristic curve slope data of the action of the switch machine in each process, and calculating the power characteristic curve slope data of the action of the switch machine based on the power characteristic curve mean value slope data; training set data and test set data are selected according to the concentration degree of power characteristic curve mean slope data to train and test the deep belief network model DBN, and power curves corresponding to various actions in different processes when the switch machine works in real time are input into the trained deep belief network model DBN. The deep belief network model DBN carries out comparative analysis on the slope of the real-time power characteristic curve of the switch machine, and whether the switch machine breaks down or not and the fault type are judged.

    本发明属于轨道交通道岔故障诊断技术领域,具体的说是一种基于机器学习的铁路道岔故障诊断方法及系统,包括多次采样转辙机的功率特性曲线,对所采集的功率特性曲线进行归一化处理并分析,获得每个过程中转辙机动作的功率特性曲线斜率数据,基于功率特性曲线均值斜率数据在转辙机正常工作以及故障情况下,按照功率特性曲线均值斜率数据的集中程度选取训练集数据以及测试集数据对深度置信网络模型DBN进行训练和测试,将转辙机实时工作时不同过程中各种动作对应的功率曲线输入至训练完成的深度置信网络模型DBN中,深度置信网络模型DBN对转辙机实时功率特性曲线斜率进行比较分析,判定转辙机是否故障以及故障类型。


    Access

    Download


    Export, share and cite



    Title :

    Railway turnout fault diagnosis method and system based on machine learning


    Additional title:

    一种基于机器学习的铁路道岔故障诊断方法及系统


    Contributors:

    Publication date :

    2024-02-20


    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 / G01R Messen elektrischer Größen , MEASURING ELECTRIC VARIABLES / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Railway Turnout Fault Diagnosis Based on Support Vector Machine

    He, You Min ;Zhao, Hui Bing ;Tian, Jian | Trans Tech Publications | 2014


    Fault Diagnosis of Railway Turnout Based on Random Forests

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


    Fault Diagnosis of Railway Turnout Based on Random Forests

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


    Fault Diagnosis of Railway Turnout Based on Random Forests

    Zhang, Huiyue / Wang, Zhipeng / Wang, Ning et al. | British Library Conference Proceedings | 2020


    Fault Diagnosis of Railway Turnout Based on Fuzzy Cognitive Map

    Liang, Yao / Dai, Shenghua / Zheng, Ziyuan | IEEE | 2019