基于局域均值分解包络谱和SVM的滚动轴承故障诊断方法研究

Fault diagnosis method of rolling bearing based on local mean decomposition envelope spectrum and support vector machine(SVM)

论述了局域均值分解(Local mean decomposition,LMD)的定义和算法。结合局域均值分解、包络分析和支持向量机(Support vector machine,SVM)的各自特点,提出了一种基于LMD包络谱和SVM的滚动轴承故障诊断方法,该方法先对滚动轴承振动信号进行分解,得到一系列的生产函数分量,然后,再对前面几个生产函数分量进行包络分析,从包络谱中提取特征幅值比作为特征向量输入到SVM分类器中进行识别。实验结果验证了提出的方法的有效性,可以有效地识别滚动轴承的不同故障。

The definition and algorithm of Local mean decomposition（LMD）is introduced.Combining Local mean decomposition（LMD）,envelope analysis and support vector machine（SVM）,a new fault diagnosis method for rolling bearing based on LMD envelope spectrum and SVM is proposed,in which the signal of rolling bearings is decomposed into a series of product functions（PF）components by the LMD method.Then the envelopespectrum of first few PF components containing the most fault information,features,is obtained through envelopement analysis.Finally,the ratios of amplitudes in different characteristic frequencies,which are extracted from the envelopespectrum,are used as the feature vectors and input into the SVM classifier for recognization.The experiment result shows that the proposed method is effective.