基于EMD和FastICA的轴承故障诊断  

Bearing Fault Diagnosis Based on EMD and FastICA

作　　者：高云峰 张金萍[1] GAO Yun-feng;ZHANG Jin-ping(School of Mechanical and Power Engineering,Shenyang University of Chemical Technology,Liaoning Shenyang 110142,China)

机构地区：[1]沈阳化工大学机械与动力工程学院,辽宁沈阳110142

出　　处：《机械设计与制造》2024年第6期48-52,共5页Machinery Design & Manufacture

摘　　要：针对滚动轴承振动信号之间的影响并且易受到噪声干扰的问题,提出了一种基于快速独立分类分析(FastICA)与经验模态分解(EMD)相结合的故障提取特征方法。通过经验模态分解将振动信号分解成若干个模态分量。继而,根据计算相关性系数选取有效的模态分量构建噪声通道,最后通过快速独立分类分析将源信号与噪声信号分离,进而得到独立的源信号。通过对西储大学轴承数据的仿真与实验结果表明,该方法可以有效的抑制噪声干扰,清晰的看出轴承的故障频率,实现了对轴承的故障诊断。A fault feature extraction method based on the combination of Fast Independent Classification Analysis(FastiCA)and empirical mode decomposition(EMD)is proposed to solve the problem that the vibration signals of rolling bearings are affected by noise.The vibration signal is decomposed into several modal components by empirical mode decomposition.Then,according to the Correlation Coefficient,the effective modal components are selected to construct the noise channel.Finally,the source signal is sep-arated from the noise signal by fast independent classification analysis.The simulation and experimental results of bearing data in Xchu University show that this method can effectively suppress noise interference,clearly see the fault frequency of bearing,and realize the fault diagnosis of bearing.

关 键 词：振动信号 特征提取 经验模态分解 快速独立分类分析 

分 类 号：TH16[机械工程—机械制造及自动化] TH133.33