基于 DLMD 样本熵和模糊聚类的滚动轴承故障诊断

摘要

In view of the problem that the traditional local mean decomposition (LMD)was diffi-cult to effectively extract the weak high frequency signal components,a method of DLMD was put for-ward.A new approach for rolling bearing fault diagnosis based on the combination of DLMD,sample entropy and fuzzy clustering was proposed.Firstly,rolling bearing vibration signals were decomposed with DLMD to obtain a certain number of product function(PF)components which had physical mean-ing.Then the sample entropies of the PF components were calculated and used as the eigenvectors. Finally,the eigenvectors were recognized and classified through the fuzzy clustering.The experimen-tal results show that the method based on the combination of DLMD,sample entropy and fuzzy clus-tering can be used to recognize and classify rolling bearing fault signals accurately and effectively.%针对传统的局部均值分解(LMD)方法不能有效提取微弱高频信号成分的问题，提出了一种基于微分的微分局部均值分解(DLMD)方法，在此基础上，将 DLMD、样本熵和模糊聚类分析相结合，提出了一种基于 DLMD 样本熵和模糊聚类的滚动轴承故障诊断方法。该方法首先对滚动轴承振动信号进行微分局部均值分解，得到若干具有物理意义的乘积函数(PF)分量，然后求取各 PF 分量的样本熵并将其作为特征向量，最后通过模糊聚类对特征向量进行识别分类。实验结果表明，基于 DLMD 样本熵和模糊聚类相结合的方法能够准确、有效地对滚动轴承故障信号进行识别分类。