基于IPSO-MCKD的汽车变速箱轴承故障诊断

Fault diagnosis of automotive gearbox bearings based on MCKD with IPSO

针对车辆在城区运行过程中频繁启停造成变速箱滚动轴承故障易发的问题,在轴承故障诊断中引入最大相关峭度反卷积(Maximum Correlation Kurtosis Deconvolution,MCKD)的方法,为了避免过于依赖人工选择MCKD算法中滤波器系数和移位数,提出了一种参数自适应的最大相关峭度反卷积的故障诊断方法。该方法以输入信号的包络谱中最大相关峭度为目标函数,采用改进后的粒子群优化(Improved Particle Swarm Optimization,IPSO)算法优化MCKD中的滤波器系数和位移数,最后通过对故障信号的包络谱进行分析,提取轴承的故障特征。仿真和试验的结果表明,该方法可以有效降低环境中的噪声干扰,准确从强噪声中提取故障特征,实现故障诊断。

In order to solve the problem of gearbox rolling bearing failure caused by frequent start-stop of hybrid electric vehicles in urban operation,the Maximum Correlation Kurtosis Deconvolution(MCKD)method was applied to the early fault diagnosis of gearbox bearing.In order to solve the problem that the filter order and shift number need to be selected manually in MCKD,a fault diagnosis method of maximum correlation kurtosis deconvolution with adaptive parameters was proposed.In this method,the maxi-mum correlation kurtosis in the signal envelope spectrum was taken as the objective function,and the filter coefficient L and shift number M were optimized by the Improved Particle Swarm Optimization(IPSO)algorithm.Finally,the bearing fault characteristics were extracted by the envelope spectrum.Simulation and experimental results show that this method can effectively reduce environmental interference,accurately extract fault features from strong noise,and realize fault diagnosis.