应用多分辨SVD和ICA的轴承复合故障诊断研究  

Research of rolling bearing compound fault diagnosis based on multi-resolution SVD and ICA

作　　者：孟智慧[1] 王昌[1] 

机构地区：[1]内蒙古科技大学机械工程学院,包头014010

出　　处：《现代制造工程》2014年第8期127-130,共4页Modern Manufacturing Engineering

基　　金：内蒙古自然基金项目(2010MS0714)

摘　　要：针对滚动轴承复合故障信号中故障特征难以分离的问题,提出了基于多分辨奇异值分解(SVD)和独立分量分析(ICA)的复合故障诊断方法。首先利用多分辨SVD将复合故障振动信号分解为几个分量实现维数的增加;然后将分解得到的分量组合为混合信号,并利用ICA进行欠定盲分离;最后对分离后的独立分量进行Hilbert包络解调,由此实现对复合故障特征信息的分离和故障识别。通过对滚动轴承内外圈复合故障的试验信号分析表明,该方法可以有效地分离和提取轴承复合故障的特征信息。Aiming at the separating fault information from compound rolling bearing fault signal ,a new compound fault diagnosis method is proposed based on multi-resolution Singular Value Decomposition （ SVD ） and Independent Component Analysis （ICA）.Firstly,the signal of compound fault was decomposed into several components through multi -resolution SVD,and the di-mension was increased .Then the mixed signal of components combination was realized blind source separation of under -deter-mined mixtures by ICA .Finally,Hilbert envelope spectrum were got from independent signal components separated ,thus the infor-mation of fault feature can be separated and identified .The results of the experiments show that the fault feature of rolling bearing can be separated effectively and the fault feature information were extracted .

关 键 词：奇异值分解 独立分量分析 欠定 盲分离 复合故障 

分 类 号：TH133.3[机械工程—机械制造及自动化] TH165