基于小波域对数正态模型的滚动轴承故障诊断

中国机械工程 ›› 2012, Vol. 23 ›› Issue (4): 443-448.

基于小波域对数正态模型的滚动轴承故障诊断

姜海燕1;彭涛2

1.湖南铁道职业技术学院,株洲,412001

2.中南大学,长沙,410083

出版日期:2012-02-25 发布日期:2012-03-02
基金资助:
国家自然科学基金资助项目（60774069）;中国博士后科学基金资助项目（20070410462）
National Natural Science Foundation of China（No. 60774069）;
Supported by China Postdoctoral Science Foundation（No. 20070410462）

Fault Diagnosis of Rolling Bearings Based on Wavelet-domain Lognormal Model

Jiang Haiyan1;Peng Tao2

1.Hunan Railway Professional Technology College,Zhuzhou,Hunan,412001

2.Central South University,Changsha,410083

Online:2012-02-25 Published:2012-03-02
Supported by:

National Natural Science Foundation of China（No. 60774069）;
Supported by China Postdoctoral Science Foundation（No. 20070410462）

摘要/Abstract

摘要：

针对小波分析无法全面准确描述滚动轴承振动信号的非高斯问题,提出一种结合小波变换与对数正态分布模型的故障特征提取方法,以提取能准确反映滚动轴承运行状态的特征信息。首先,通过小波变换对滚动轴承运行时产生的非平稳、非高斯振动信号进行分解重构,得到不同尺度下的重构信号;然后对重构信号建立对数正态分布模型,提取模型的对数均值和对数标准差作为表征滚动轴承运行状态的统计特征;最后采用支持向量机分类器对提取的特征进行故障分类与识别。实验结果表明,该方法可以有效、准确地识别滚动轴承的运行状态。

关键词:

小波变换, 对数正态模型, 特征提取, 滚动轴承

Abstract:

Since the non-Gaussian of rolling bearing vibration signals can not be fully described by the wavelet analysis,a feature extraction approach based on wavelet transformation and lognormal model was

proposed,so as to that the feature vectors were extracted to reflect accurately the running state of rolling bearings.First of all,the non-stationary and non-Gaussion signals generated by rolling bearing vibrations were decomposed into some coefficients by wavelet transformation.Then the signals of single reconstruction were modeled as lognormal models and its log mean and log variance were extracted.Finally, fault patterns were recognized by the feature vectors using support vector machine(SVM) classifier.The experimental results show the effectiveness and accuracy of the proposed approach for recognizing the states of rolling bearings.

Key words: wavelet transform, lognormal model, feature extraction, rolling bearing

中图分类号:

TP206.3

姜海燕1, 彭涛2.

基于小波域对数正态模型的滚动轴承故障诊断

[J]. 中国机械工程, 2012, 23(4): 443-448.

JIANG Hai-Yan-1, BANG Chao-2.

Fault Diagnosis of Rolling Bearings Based on Wavelet-domain Lognormal Model

[J]. China Mechanical Engineering, 2012, 23(4): 443-448.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.cmemo.org.cn/CN/

http://www.cmemo.org.cn/CN/Y2012/V23/I4/443

参考文献

[1]钟秉林,黄仁.机械故障诊断学[M].北京:机械工业出版社,2007.119-131.
[2]Lin J, Qu L S. Feature Extraction Based on Morlet Wavelet and Its Application for Mechanical Fault Diagnosis[J]. Journal of Sound and Vibration, 2000, 234(1) : 135-148.
[3]He Y, Shen S, Ying H, et al. Application of Wavelet Packet Decomposition and Its Energy Spectrum on the Fault Diagnosis of Reciprocation Machinery.[J].Journal of vibration Engineering, 2001, 14 ( 1):72-7&.
[4]Hao Rujiang,Chu Fulei. Morphological Undeeimat- ed Wavelet Decomposition for Fault Diagnostics of Rolling Element Bearings[J].Journal of Sound and Vibration, 2009,320 (4) :1164-1177.
[5]张邦基[1],于德介[1],杨胜[1].基于小波变换与粗集理论的滚动轴承故障诊断[J].中国机械工程,2008,19(15):1793-1795.
[6]Rubini R, Meneghetti U. Application of the Envelope and Wavelet Transform AnalYses for the Diagnosis of Incipient Faults in Ball Baarings[J]. Mechanical Sys- tems and Signal Processing,2001,15(2):287-302.
[7]陆爽 [1],杨斌 [2],李萌 [1],张子达 [2].基于小波和径向基函数神经网络的滚动轴承故障模式识别[J].农业工程学报,2004,20(6):102-105.
[8]杨国安,钟秉林,黄仁,贾民平,许云飞.机械故障信号小波包分解的时域特征提取方法研究[J].振动与冲击,2001,20(2):25-28.
[9]Guillermo A J, Alfredo O M, Manuel A D M. Fault Detection in Induction Motors Using Hilbert and Wavelet Transforms[J].Electrical Engineering, 2007,89(3) : 205-220.
[10]陈琨[1],于雷[2,3].基于对数正态和分布的路径行程时间可靠性模型[J].北京交通大学学报：自然科学版,2009,33(3):35-39.
[11]飞思科技产品研发中心.小波分析理论与MAT-LAB7实现[M].北京:电子工业出版社,2005.238-241.
[12]McAlister D. The Law of the Geometric Mean[J]. Proceeding of the Royal Society of London, 1879, 29(3) :367-376.
[13]于洋[1],孙月静[1].对数正态分布参数的最大似然估计[J].九江学院学报：哲学社会科学版,2007,26(6):55-57.
[14]杨正友[1],彭涛[1].基于振动信号分析和支持向量机的滚动轴承故障诊断[J].湖南工业大学学报,2009,23(1):96-99.
[15]Case Western Reserve University Bearing Data Center. Bearing Data Center Fault Test Data. [EB/OL]. [2009-10-01]. http..//www, eecs. case. edu/laboratory/bearing.