基于可视图图谱幅值熵的滚动轴承故障诊断方法

Fault diagnosis of rolling bearings based on graph spectrum amplitude entropy of visibility graph

为了准确有效地提取滚动轴承振动信号的非平稳、非线性故障特征,将复杂网络与图信号处理技术(graph signal processing,GSP)引入机械故障诊断领域,提出了基于可视图图谱幅值熵(graph spectrum amplitude entropy of visibility graph,GSAE VG)的滚动轴承故障诊断方法。该方法先将滚动轴承振动信号转换为可视图,获得可视图信号;再通过图傅里叶变换(graph Fourier transform,GFT)将可视图信号从顶点域变换到图谱域,并将计算得到的图谱幅值熵(graph spectrum amplitude entropy,GSAE)作为故障特征参数;利用马氏距离(Mahalanobis distance,MD)判别函数作为分类器对不同类型故障进行模式识别。实际滚动轴承振动信号的分析结果表明,基于可视图图谱幅值熵的故障诊断方法能对滚动轴承故障进行准确有效地识别。

In order to extract the non-stationary and non-linear fault features of rolling bearing vibration signals more accurately and effectively,complex network and graph signal processing(GSP)techniques were introduced into the field of mechanical fault diagnosis,and a method of rolling bearing fault diagnosis based on the graph spectrum amplitude entropy of visibility graph(GSAE VG)was proposed.Firstly,the vibration signal of rolling bearing was transformed into visibility graph signal;then,the visibility graph signal was transformed from vertex domain to graph spectrum domain by graph Fourier transform(GFT),and graph spectrum amplitude entropy(GSAE)was calculated as the fault characteristic parameter;finally,Mahalanobis distance(MD)discriminant function was used as a classifier to recognize different types of faults.From the analysis results of actual rolling bearing vibration signals,it can be seen that the fault diagnosis method based on the graph spectrum amplitude entropy of visibility graph can be used to identify rolling bearing faults accurately and effectively.