基于RCMDE和GWO-LSSVM的抗蛇行减振器故障诊断  

Fault Diagnosis of Anti-yaw Damper Based on RCMDE and GWO-LSSVM

作　　者：岑潮宇 代亮成[1] 池茂儒[1] 赵明花 CEN Chaoyu;DAI Liangcheng;CHI Maoru;ZHAO Minghua(State Key Laboratory of Rail Transit Vehicle System,Southwest Jiaotong University,Chengdu Sichuan 610031,China)

机构地区：[1]西南交通大学轨道交通运载系统全国重点实验室,四川成都610031

出　　处：《机床与液压》2024年第21期199-205,共7页Machine Tool & Hydraulics

基　　金：国家重点研发计划项目(2022YFB4301303)。

摘　　要：针对高速列车抗蛇行减振器故障振动信号具有非线性、非平稳特征以及特征信号提取相对困难的问题,提出一种基于自适应噪声完备集合模态分解(CEEMDAN)与灰狼算法优化的最小二乘支持向量机(LSSVM)相结合的故障诊断方法。利用CEEMDAN方法分解车辆的振动信号,得到振动信号的各模态分量(IMF),并计算IMF各分量的精细复合多尺度散布熵(RCMDE),组成每个样本下的特征向量,最后输入到利用灰狼优化算法(GWO)对LSSVM的惩罚系数和核函数参数迭代寻优以获得最优分类效果的LSSVM中进行故障诊断。试验结果表明:通过提取CEEMDAN各模态分量IMF的精细复合多尺度散布熵作为特征输入到GWO-LSSVM中具有很好的诊断效果,实现了抗蛇行减振器故障的有效判别,验证了该方法的可行性。Aiming at the problem that the fault vibration signals of anti-yaw damper of high-speed trains have non-linear and non-stationary characteristics and the feature extraction is relatively difficult,a fault diagnosis method based on the combination of complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)and least squares support vector machine(LSSVM)optimized by grey wolf algorithm was proposed.The vibration signal of the vehicle was decomposed by CEEMDAN method,and the intrinsic mode function(IMF)of the vibration signal was obtained,refined composite multiscale dispersion entropy(RCMDE)for each component of IMF was calculated to form the eigenvector under each sample.Finally,the fault diagnosis was carried out in the LSSVM which the penalty coefficient and kernel function parameters were iteratively optimized by using grey wolf optimizer(GWO)to obtain the optimal classification effect.The experimental results show that by extracting the refined composite multiscale dispersion entropy of each modal component IMF of CEEMDAN as the feature and inputing it into GWO-LSSVM,a good diagnostic effect is gotten,and the effective discrimination of damper faults is realized,which verifies the feasibility of the method.

关 键 词：抗蛇行减振器 精细复合多尺度散布熵 故障诊断 灰狼优化 最小二乘支持向量机 

分 类 号：TH707[机械工程—仪器科学与技术] TP206.3[机械工程—精密仪器及机械]