基于PELCD样本熵的抗蛇行减振器故障诊断  

Fault diagnosis of anti-yaw damper based on PELCD sample entropy

作　　者：郑航 李刚[1,2,3] 李德仓 ZHENG Hang;LI Gang;LI Decang(Mechatronics T&R Institute,Lanzhou Jiaotong University,Lanzhou 730070,China;Gansu Provincial Engineering Technology Center for Informatization of Logistics&Transport Equipment,Lanzhou 730070,China;Gansu Provincial Industry Technology Center of Logistics&Transport Equipment,Lanzhou 730070,China)

机构地区：[1]兰州交通大学机电技术研究所,甘肃兰州730070 [2]甘肃省物流及运输装备信息化工程技术研究中心,甘肃兰州730070 [3]甘肃省物流与运输装备行业技术中心,甘肃兰州730070

出　　处：《电力机车与城轨车辆》2023年第6期34-41,共8页Electric Locomotives & Mass Transit Vehicles

基　　金：国家自然科学基金(62063013)。

摘　　要：长期高速运行的服役状态会造成列车转向架关键部件性能蜕化甚至故障等情况,导致的安全事件将造成严重的经济损失甚至人员伤亡。文章针对列车振动信号非线性、非平稳的特点,以部分集成局部特征尺度分解(PELCD)方法对高速列车抗蛇行减振器失效的故障振动信号进行分解,并且对相关性较强的前6个分量进行样本熵特征提取,将互补集合经验模态分解(CEEMD)方法与样本熵结合的结果进行对比,最后将CEEMD样本熵与PELCD样本熵两种方法下所得到的特征向量作为支持向量机的样本进行故障训练与故障预测。对比二者的结果表明PELCD与样本熵的结合能够有效地识别出列车的故障类别。High speed running state of serving for a long time can cause the train bogie key component performance such as reduced or even failure,leading to safety events that can cause serious economic losses and even casualties.According to the nonlinear and non-stationary characteristics of train vibration signals,the partly ensemble local characteristic-scale decomposition(PELCD)method is used to decompose the fault vibration signals of anti-yaw damper failure of high-speed trains.In addition,sample entropy features are extracted for the first 6 components with strong correlation,and the results of the combination of complementary ensemble empirical mode decomposition(CEEMD)method and sample entropy are compared.Finally,feature vectors obtained by CEEMD sample entropy and PELCD sample entropy methods are used as samples of support vector machines for fault training and fault prediction.The comparison of the two results shows that the combination of PELCD and sample entropy can effectively identify the fault categories of trains.

关 键 词：部分集成局部特征尺度分解(PELCD) 样本熵 故障诊断 抗蛇行减振器 

分 类 号：U260.331.5[机械工程—车辆工程]