基于小波包与自适应SVM的滚动轴承故障诊断方法研究

Fault Diagnosis of Rolling Bearing Based on Wavelet Packet and Adaptive SVM

近年来,诸多学者针对滚动轴承故障问题进行了大量研究。本文利用基于小波包分解的时频域特征提取方法获取各频段能量谱。同时,为提高故障诊断模型的诊断精度,利用差分进化灰狼优化算法(Differential Evolution Grey Wolf Optimizer,DEGWO)实现支持向量机(Support Vector Machine,SVM)模型参数自适应。最后,通过具体实验完成故障特征提取与自适应故障诊断模型的构建,从而实现机械设备滚动轴承的状态监测与故障诊断。

In recent years,many scholars have conducted a lot of research on the problem of rolling bearing failure.This paper used the time-frequency domain feature extraction method based on wavelet packet decomposition to ob⁃tain the energy spectrum of each frequency band.At the same time,in order to improve the diagnostic accuracy of the fault diagnosis model,the Differential Evolution Grey Wolf Optimizer(DEGWO)was used to realize the support vec⁃tor machine(SVM)model parameter adaptation.At last,the model of fault feature extraction and self-adaptive fault diagnosis was constructed through specific experiments,so as to realize the condition monitoring and fault diagnosis of rolling bearing of mechanical equipment.