.
高文杰1，王建国1，高立新2，张文兴1
(1.内蒙古科技大学机械工程学院，内蒙古包头014010;2． 北京工业大学机械工程学院，北京100124)
关键词:滚动轴承;故障诊断;特征提取;小波－ BP 神经网络;模式识别
中图分类号:TP183 文献标识码:A
摘要:鉴于小波分析与BP 神经网络在故障诊断中各自存在的局限性，提出基于小波－ BP 神经网络的轴承故障模式识别技术． 采用具有良好时频局部特性的小波基函数替代传统BP 网络的激励函数，从而构造小波－ BP 神经网络，并且对其进行训练，获得模式识别网络，再用新数据进行网络检验，仿真结果表明该方法实用有效．
Ｒesearch of bearing fault diagnosis based on integration of wavelet analysis and neural network
GAO Wen-jie1，WANG Jian-guo1，GAO Li-xin2，ZHANG Wen-xing1
(1． Mechanical Engineering School，Inner Mongolia University of Science and Technology，Baotou 014010，China;
2． College of Mechanical Engineering，Beijing University of Technology，Beijing 100124，China)
Key words:rolling bearing; fault diagnosis;feature extraction; wavelet-BP neural network; pattern recognition
Abstract:In view of the limitations of wavelet analysis and BP neural network in fault diagnosis,a bearing failure pattern recognition technology was proposed based on wavelet-BP neural network． The traditional BP network activation function was replaced by wavelet basis function with good time-frequency localization properties． By constructing and training the wavelet-BP neural network，a pattern recognition network was obtained，and then the network was tested with new data． The simulation results show that the method is practical and effective．