小波神经网络技术在减速器轴承故障诊断中的应用  

Application of Wavelet Neural Network Technique to Reducer Bearing Fault Diagnosis

作　　者：郜立焕[1] 雷萍[1] 杨阳[1] 刘世亮[1] 孙俊伟[1] 张福志 

机构地区：[1]兰州理工大学流体动力与控制学院,甘肃兰州730050 [2]上海东昊测试技术有限公司

出　　处：《矿山机械》2008年第20期28-31,共4页Mining & Processing Equipment

基　　金：甘肃省教育厅科研项目(0503B-07)

摘　　要：针对滚动轴承振动信号复杂,故障类型难以识别的问题,提出基于小波神经网络技术的滚动轴承诊断的一种新方法。该方法根据滚动轴承振动信号的频域变化特征,采用小波包分析对其建立频域能量特征向量,利用径向基函数神经网络完成滚动轴承故障模式的识别。通过仿真和试验数据对比,证明了该方法是有效的。According to the problems that the vibration signal is complex and fault mode recognition is difficult, a new method for fault diagnosis of rolling bearing based on the wavelet neural network is proposed. Based on the frequency domain characteristics of the vibration signals of rolling bearing, the characteristic vector of frequency domain energy is established using the wavelet packet analysis, and the recognition of the rolling bearing fault modes is completed by radial basis function neural network. The simulation and experimental data comparison show that the method is effective.

关 键 词：滚动轴承 小波包分析 径向基函数神经网络 模式识别 

分 类 号：TH133.33[机械工程—机械制造及自动化]