基于经验模态分解和主成分分析的滚动轴承故障诊断研究

Research on Fault Diagnosis of Rolling Bearing Based on Empirical Mode Decomposition and Principal Component Analysis

针对传统的振动信号特征提取效率低、诊断时间较长等问题,提出了基于经验模态分解与主成分分析的滚动轴承故障诊断方法。首先利用经验模态分解将振动信号分解为有限个本征模函数和一个残差函数,提取主要的本征模函数能量及其局部平均频率特征,最后将复合特征向量作为主成分分析分类器的输入,完成对故障的识别。实验结果表明:复合特征向量能够有效地反映轴承的运行状态;相比于BP神经网络、支持向量机、K-近邻算法,主成分分析分类法不仅能够准确地识别故障,而且训练时间短、使用方便。

In order to solve the problems of low efficiency and long diagnosis time of traditional vibration signal feature extraction,a rolling bearing fault diagnosis method based on empirical mode decomposition and principal component analysis were proposed.Firstly,the empirical mode decomposition was used to decompose the vibration signal into a finite number of intrinsic mode functions and a residual function to extract the energy of the main intrinsic mode functions and their local average frequency characteristics.Finally,the composite feature vector was used as the input of principal component analysis classifier to complete the fault identification.The experimental results showed that the composite eigenvector can effectively reflect the running state of the bearing.Compared with BP neural network,support vector machine and K-nearest neighbor algorithm,principal component analysis classification not only can accurately identify faults,but also has the advantages of short training time and convenient use.