首页 | 本学科首页   官方微博 | 高级检索  
     

基于小波包和支持向量机的滚动轴承故障模式识别
引用本文:田野,陆爽. 基于小波包和支持向量机的滚动轴承故障模式识别[J]. 机床与液压, 2006, 0(6): 236-240
作者姓名:田野  陆爽
作者单位:1. 长春工业大学机电工程学院,长春,130012
2. 浙江师范大学高等技术学院,浙江金华,321019
摘    要:为了解决对故障轴承的特征提取和故障特征准确分类问题,提出了应用小波包变换和支持向量机相结合进行滚动轴承故障诊断的方法.小波包变换具有良好的时-频局部化特征,非常适于对瞬态或时变信号进行特征提取.而支持向量机可完成模式识别和非线性回归.利用上述原理根据轴承振动信号的频域变化特征,采用小波包变换对其提取频域能量特征向量,然后利用建立的支持向量机多故障分类器完成滚动轴承故障模式的识别.试验结果表明,支持向量机可以有效、准确地识别轴承的故障模式,为轴承故障诊断向智能化发展提供了新的途径.

关 键 词:滚动轴承  故障诊断  小波包  支持向量机  模式识别
文章编号:1001-3881(2006)6-236-5
收稿时间:2005-03-30
修稿时间:2005-03-30

Fault Pattern Recognition of Rolling Bearing Based on Wavelet Packet and Support Vector Machine
TIAN Ye,LU Shuang. Fault Pattern Recognition of Rolling Bearing Based on Wavelet Packet and Support Vector Machine[J]. Machine Tool & Hydraulics, 2006, 0(6): 236-240
Authors:TIAN Ye  LU Shuang
Affiliation:1. Changchun University of Technology, Changchun 130012, China; 2. Zhejiang Normal University, Jinhua Zhejiang 321019, China
Abstract:The method of fault recognition of rolling bearings based on wavelet packet transform and support vector machine was presented, in order to solve the feature extracting and feature classifying of fault bearings diagnosis. Wavelet packet transform, as a new technique of signal processing, possesses excellent characteristic of time -frequency localization and is suitable for analyzing the time -varying or transient signals. Support vector machine is capable of pattern recognition and nonlinear regression. According to the frequency domain feature of vibration signal of ball bearing, energy eigenvector of frequency domain was extracted using wavelet packet transform method. Fault pattern of rolling bearing was recognized using support vector machine multiple fault classifier. Theory and experiment shows that this method is available to recognize the fault pattern accurately and provides a new approach to intelligent fault diagnosis.
Keywords:Rolling bearing   Fault diagnosis    Wavelet packet    Support vector machine    Pattern recognition
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号