计算机科学 ›› 2015, Vol. 42 ›› Issue (Z11): 131-134.

• 模式识别与图像处理 • 上一篇    下一篇

基于有理双树复小波和SVM的滚动轴承故诊断方法

孙珊珊,何光辉,崔建   

  1. 重庆大学数学与统计学院 重庆401331,重庆大学数学与统计学院 重庆401331,重庆大学数学与统计学院 重庆401331
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金项目(61173030)资助

Fault Diagnosis Method of Rolling Bearing Based on Dual-tree Rational-dilation Complex Wavelet Packet Transform and SVM

SUN Shan-shan, HE Guang-hui and CUI Jian   

  • Online:2018-11-14 Published:2018-11-14

摘要: 滚动轴承故障类型被支持向量机(SVM)智能识别的关键是故障特征的提取。为了提取最优的故障特征,提高SVM的分类识别精度,提出了基于有理双树复小波和SVM的滚动轴承故障诊断方法。首先通过双树复小波包变换将非平稳的振动信号分解得到不同频带的分量,然后对每个分量求能量并作归一化处理,最后将从各个频带分量中提取的能量特征参数作为支持向量机的输入来识别滚动轴承的故障类型。研究结果表明该方法可以有效、准确地识别轴承的故障模式。

关键词: 有理双树复小波变换,特征提取,支持向量机,滚动轴承,故障分类

Abstract: In order to improve the recognition accuracy of SVM classification,a fault diagnosis method was proposed based on dual-tree rational-dilation complex wavelet transform and support vector machine(SVM),according to the characteristics of rolling bearing fault vibration signal.Firstly,the fault signal is decomposed into several different frequency band components through dual-tree rational-dilation complex wavelet transform.Secondly,normalization processing is made from the energy of each component.Finally,the energy characteristics parameters of each frequency band component are taken as input of the SVM to identify the fault type of rolling bearing.The experimental results prove that the proposed method can identify the fault type accurately and effectively.

Key words: Dual-tree rational-dilation complex wavelet transform,Feature extraction,SVM,Rolling bearing,Fault identification

[1] 何正嘉,袁静,訾艳阳.机械故障诊断的内积变换原理与应用[M].北京:科学出版社,2012:407-470
[2] 王国彪,何正嘉,陈雪峰.机械故障诊断基础研究 “何去何从”[J].机械工程学报,2013,49(1):63-72
[3] Yan R,Gao R X,Chen X.Wavelets for fault diagnosis of rotary machines:A review with applications[J].Signal Processing,2014,96:1-15
[4] 艾树峰.基于双树复小波变换的轴承故障诊断研究[J].中国机械工程,2011,22(20):2446-2451
[5] Bayram I,Selesnick I W.A dual-tree rational-dilation complexwavelet transform[J].IEEE Transactions on Signal Processing,2011,59(12):6251-6256
[6] Kingsbury N G.The dual-tree complex wavelet transform:Anew efficient tool for image restoration and enhancement[C]∥Proc.European Signal Processing Conf..Rhodes,1998:319-322
[7] Vapnik V N.The Nature of Statistical Learning Theory[M].NewYork:SpringVerag,1995:21-22
[8] Akben S B,Subasi A.Comparison of artificial neural networkand support vector machine classification methods in diagnosis of migraine by using EEG[C]∥2010 IEEE 18th Signal Proces-sing and Communications Applications Conference(SIU).2010:637-640
[9] Bayram I,Selesnick I.Overcomplete discrete wavelet transforms with rational dilation factors[J].IEEE Trans on Signal Process,2009,7(1):131-145
[10] 毛永芳,秦毅,汤宝平.过完备有理小波变换在轴承故障诊断中的应用[J].振动,测试与诊断,2011,1(5):626-630
[11] Bayram I,Selesnick I W.Frequency-domain design of overcomplete rational-dilation wavelet transforms[J].IEEE Trans.Signal Process,2009,7(8):2957-2972
[12] 余辉,赵晖.支持向量机多类分类算法新研究[J].计算机工程与应用,2008,4(7):185-189
[13] 李永龙,邵忍平,曹精明.基于小波包与支持向量机结合的齿轮故障分类研究[J].西北工业大学学报,2010,28(4):530-535
[14] 胥永刚,孟志鹏,陆明.基于双树复小波包变换和SVM 的滚动轴承故障诊断方法[J].航空动力学报,2014,29(1):67-73

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!