基于小波分析与EMD的机车轴承故障诊断方法  

A locomotive bearing fault diagnosis method based on wavelet analysis and EMD

作　　者：王嘉浩 罗倩[1] 胡园园 WANG Jiahao;LUO Qian;HU Yuanyuan(School of Information and Communication Engineering,Beijing Information Science&Technology University,Beijing 100192,China)

机构地区：[1]北京信息科技大学信息与通信工程学院,北京100192

出　　处：《北京信息科技大学学报（自然科学版）》2020年第3期31-35,共5页Journal of Beijing Information Science and Technology University

基　　金：国家自然科学基金资助项目(61271198);北京市科技提升计划项目(5211624101)。

摘　　要：机车滚动轴承发生故障时信号是非平稳的,其振动信号各频带的能量发生相应变化。针对故障发生在不同部位时,其振动信号能量分布重叠较少这一问题,将一种相似度度量earth mover’s distance(EMD)引入到故障部位分类中。该方法使用db3小波对轴承震动信号进行3层小波包分解,并计算第三层各结点能量作为该信号的特征向量。对得到的特征向量进行处理,计算特征向量间的EMD,根据EMD大小对特征向量间的相似度进行判断,并依此对故障部位进行定位。仿真结果表明,该方法诊断准确率达到98.75%,相较于传统KNN诊断方法在诊断准确率上提升了5%。该方法能够准确有效地诊断滚动轴承故障,可以应用到工业生产中。When the rolling bearing of the locomotive breaks down,the signal is non-stationary,and the energy of each frequency band of the vibration signal changes accordingly.Aiming at the problem that the energy distribution of vibration signals overlaps less when faults occur in different parts,a similarity measure earth mover’s distance(EMD)is introduced into the classification of fault parts.This method uses db3 wavelet to perform three-layer wavelet packet decomposition on the bearing signal,and calculates the energy of each node in the third layer as the feature vector of the signal.The obtained feature vectors are processed,the EMD between the feature vectors is calculated,the similarity between the feature vectors is judged by the EMD size,and the fault parts are located accordingly.Simulation results show that the diagnostic accuracy of this method reaches 98.75%,which is 5%higher than that of the traditional KNN diagnostic method.This method can accurately and effectively diagnose rolling bearing faults,and can be applied to the industrial production.

关 键 词：轴承故障诊断 小波包分解 能量特征 earth mover’s distance(EMD) 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]