The invention discloses a heavy-load locomotive coupler force identification method based on data driving, and relates to the technical field of heavy-load locomotive coupler state monitoring, and the method comprises the steps: collecting a longitudinal relative displacement signal of a heavy-load train coupler body; smoothing the longitudinal relative displacement signal of the coupler body; intercepting the filtered and smoothed longitudinal relative displacement signals of the car coupler and the car body by adopting a sliding window, extracting relative speed characteristics in each section of relative displacement signal, and constructing a data set; performing normalization processing on the data set; establishing a DBO-ELM model, taking the number of neurons of an ELM hidden layer, a penalty parameter and an activation function parameter as optimization parameters, taking a mean square error of a verification set recognition result as a fitness function, and utilizing the verification set to perform iterative optimization on DBO-ELM model parameters; after optimal parameters of the model are obtained, the model is trained through the training set; inputting a test set sample into the trained model, and determining the accuracy of the training model according to the error of the coupler force identification result; the method has the advantages of low cost and high efficiency.

    本发明公开了一种基于数据驱动的重载机车车钩力识别方法,涉及重载机车车钩状态监测技术领域,包括:采集重载列车车钩车体纵向相对位移信号;平滑处理车钩车体纵向相对位移信号;采用滑动窗口截取滤波和平滑后的车钩车体纵向相对位移信号,提取每段相对位移信号内相对速度特征,构建数据集;对数据集进行归一化处理;建立DBO‑ELM模型,将ELM隐藏层神经元个数、惩罚参数和激活函数参数作为优化参数,以验证集识别结果的均方误差为适应度函数,利用验证集对DBO‑ELM模型参数进行迭代寻优;得到模型最优参数后利用训练集对模型开展训练;将测试集样本输入训练后的模型中,根据车钩力识别结果的误差确定训练模型的准确性;本发明具有低成本、高效率的优点。


    Access

    Download


    Export, share and cite



    Title :

    Heavy-duty locomotive coupler force identification method based on data driving


    Additional title:

    基于数据驱动的重载机车车钩力识别方法


    Contributors:
    WANG KAIYUN (author) / RAN XIANGRUI (author) / CHEN SHIQIAN (author) / XIE BO (author) / CHEN QINGHUA (author) / ZHAI WANMING (author) / LING LIANG (author)

    Publication date :

    2024-04-12


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B61G Kupplungen besonders ausgebildet für Eisenbahnfahrzeuge , COUPLINGS SPECIALLY ADAPTED FOR RAILWAY VEHICLES / B61L Leiten des Eisenbahnverkehrs , GUIDING RAILWAY TRAFFIC / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Heavy duty adjustable gooseneck coupler

    RABSKA KEVIN / DRAKE FRANK / ALANKO ERIK | European Patent Office | 2017

    Free access

    HEAVY DUTY ADJUSTABLE GOOSENECK COUPLER

    RABSKA KEVIN / DRAKE FRANK / ALANKO ERIK | European Patent Office | 2022

    Free access

    HEAVY DUTY ADJUSTABLE GOOSENECK COUPLER

    RABSKA KEVIN / DRAKE FRANK / ALANKO ERIK | European Patent Office | 2015

    Free access

    Locomotive coupler installation device

    WANG DEDUO / QIAN JUNHUI / WANG FENG | European Patent Office | 2015

    Free access

    Locomotive coupler opening device

    YUAN YUAN / XU QI / WU XIAOQIANG et al. | European Patent Office | 2022

    Free access