基于形态滤波和独立分量分析的轴承故障盲分离  

Blind separation for bearing faults based on morphological filters and ICA

作　　者：李豫川[1] 伍星[1] 柳小勤[1] 贺玮[1] 

机构地区：[1]昆明理工大学机电工程学院,昆明650093

出　　处：《电子测量技术》2010年第9期101-103,113,共4页Electronic Measurement Technology

基　　金：国家自然科学基金资助项目(50805071);云南省教育厅科学研究基金资助项目(08J0009)

摘　　要：针对独立分量分析(ICA)对噪声较为敏感及滚动轴承故障信号的调制特性,提出一种基于形态滤波与ICA相结合的方法。该方法首先对观测信号进行形态滤波以突出故障特征同时消除其他干扰源,然后应用ICA分离形态滤波后信号。对滚动轴承外圈内圈复合故障信号进行实验研究,结果表明该方法能够有效识别分离滚动轴承故障特征。A method based on morphological filtering and independent component analysis（ICA）was proposed to deal with the problem that ICA is sensitive to noise.The morphological filtering technique was used to extract modulation features embedded in the observed signals and remove the sources of disturbance,and then ICA was used to separate source signals from filtered observed signals.The method was applied to analyze the combined failure of out ring and inner ring of rolling bearing.Analysis results show that this method can identify the rolling bearing＇s fault characteristic efficiently.

关 键 词：形态滤波 独立分量分析 故障诊断 滚动轴承 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]