基于小波包能量特征的滚动轴承故障监测方法  

The Method of Roller Bearing Fault Monitoring Based on Wavelet Packet Engergy Feature

作　　者：李世玲[1] 李治[2] 李合生[1] 

机构地区：[1]四川绵阳919信箱510分箱中国工程物理研究院电子工程研究所,四川绵阳621900 [2]西南交通大学电气工程学院,成都610031

出　　处：《系统仿真学报》2003年第1期76-80,83,共6页Journal of System Simulation

摘　　要：对滚动轴承的故障特点进行分析,根据小波包变换能将信号按任意时频分辨率分解到不同频段的特性,提出了小波包能量特征的概念及算法,并给出两个仿真算例,然后将小波包能量特征与径向基函数网络相结合,提出了一种新的滚动轴承故障诊断方法,数字仿真实验证实了该方法的正确性和有效性。This paper analyzes fault characteristics of roller bearing. Based on wavelet packet analysis theory, the concept of wavelet packet energy feature and the algorithm of wavelet packet energy feature extraction is presented. Two simulating examples about wavelet packet energy feature are provided. By combining wavelet packet energy feature (WPEF) with radial basis function networks (RBFN), a new fault diagnosis method of roller bearing is proposed. The validity of fault diagnosis method has been demonstrated by a numerical simulation.

关 键 词：小波包 能量特征 滚动轴承 故障监测 径向基函数网络 

分 类 号：TH133.33[机械工程—机械制造及自动化]