基于小波包分析的滚动轴承故障诊断  

The Rolling Bearing Fault Diagnosis Based on Wavelet Packet Decomposition

作　　者：张国新[1] 刘祚时[1] 

机构地区：[1]江西理工大学机电工程学院,江西赣州341000

出　　处：《江西理工大学学报》2007年第1期17-20,共4页Journal of Jiangxi University of Science and Technology

摘　　要：应用小波包分析方法构造滚动轴承故障信号的能量特征向量,再以此作为神经网络的输入,对滚动轴承故障进行分类,实践表明,能量特征向量较显著的表达了故障,有较好的诊断效果．The feature parameter vectors are extracted to represent the working state of rolling bearing by wavelet packet decomposition.Then the BP neural network is taken as the output of the working state of rolling bearing when the feature parameter vectors is taken as input.The experimental results prove that this method is efficient and feasible in rolling bearing fault diagnosis.

关 键 词：滚动轴承 小波包分析 能量特征向量 BP神经网络 

分 类 号：TH133.3[机械工程—机械制造及自动化]