基于FSS-kernel BSS方法的机械故障诊断

杨彦龙; 程伟; 常洪振

基于FSS-kernel BSS方法的机械故障诊断

北京航空航天大学航空科学与工程学院, 北京 100191

详细信息

中图分类号: TN911
计量
- 文章访问数: 1910
- HTML全文浏览量: 167
- PDF下载量: 570
- 被引次数: 0
出版历程
- 收稿日期: 2011-07-28
- 网络出版日期: 2012-11-30

Fault diagnosis based on blind source separation using kernel function with finite support samples

School of Aeronautic Science and Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 机械设备发生故障时,故障特征的提取是很重要的.为了从观测信号中分离出不同的故障特征源信号,并根据分离信号准确地进行故障诊断,从观测信号样本出发,提出了基于有限支持样本核函数的盲源分离(FSS-kernel BSS)方法.此方法利用有限的观测样本估计信号的概率分布,得到了评价函数,具有很好的自适应能力.仿真试验结果表明:此方法能成功地分离超、亚高斯混合信号,与其他盲源分离方法相比,此方法具有更好的分离性能.将该方法用于转子不平衡和支座松动的复合故障信号的盲分离,分离出了各复合故障的主要频谱.分离结果表明:此方法应用于机械设备复合故障诊断中是可行的.
- 故障诊断 /
- 盲源分离 /
- 有限支持样本 /
- 核函数
Abstract: It is important to extract fault features when machine would be in fault state. In order to separate different fault vibration signals from measured mixtures and diagnose the fault features of the machine effectively according to the separated signals, a blind source separation (BSS) method using kernel function based on finite support samples was proposed. The method is stronger adaptability for the score functions estimated according to finite support observed signal samples. The simulation results prove that the proposed BSS algorithm is able to separate hybrid mixtures that contain both sub-gaussian and super-gaussian sources. It is shown that the algorithm has better separation performance when compared with other BSS ones. The results of an experiment under the motor’s composite fault states with pedestal looseness fault and rotor unbalance fault show that this method is feasible for fault diagnosis.
- fault diagnose /
- blind source separation /
- finite support samples /
- kernel function

HTML全文

参考文献(15)

[1]	李良敏,温广瑞,王生昌,等.机械故障诊断的遗传-独立分量分析算法[J].农业机械学报,2008,39(11):197-202 Li Liangmin,Wen Guangrui,Wang Shengchang,et al.Genetic algorithm based independent component analysis method in machine fault diagnosis[J].Transactions of the Chinese Society for Agricultural Machinery,2008,39(11):197-202(in Chinese)
[2]	艾延廷,费成巍,张凤玲,等.ICA在航空发动机振动信号盲源分离中的应用[J].振动、测试与诊断,2010,30(6):671-674,711 Ai Yanting,Fei Chengwei,Zhang Fengling,et al.Blind source separation for aero-engines vibration signal by independent component analysis[J].Journal of Vibration,Measurement & Diagnosis,2010,30(6):671-674,711(in Chinese)
[3]	胥永刚,李强,王正英,等.基于独立分量分析的机械故障信息提取[J].天津大学学报,2006,39(9):1066-1071 Xu Yonggang,Li Qiang,Wang Zhengying,et al.Fault information extraction of mechanical equipment based on independent component analysis[J].Journal of Tianjin University,2006,39(9):1066-1071(in Chinese)
[4]	李良敏.基于遗传算法的盲源分离及其在轴承诊断中的应用[J].轴承,2005(9):31-34 Li Liangmin.Application of blind source separation method based genetic algorithm in bearing diagnosis[J].Bearing,2005(9):31-34 (in Chinese)
[5]	吴作伦,杨世锡,冯海涛.基于最小互信息原理的机械振动源分离研究[J].机电工程,2003,20(5):44-46 Wu Zuolun,YangShixi,Feng Haitao.Study on separation of mechanical vibration based on the principle of the minimum mutual information[J].Mechanical & Electrical Engineering Magazine,2003,20(5):44-46(in Chinese)
[6]	张洪渊,史习智.一种任意信号源盲分离的高效算法[J].电子学报,2001,29(10):1392-1396 Zhang Hongyuan,Shi Xizhi.An effective algorithm for blind separation of arbitrary source signals[J].Acta Electronica Sinica 2001,29(10):1392-1396(in Chinese)
[7]	Hyvarinen A,Oja E.A fast fixed point algorithm for independent component analysis[J].Neural Computation,1997,9(7):1483- 1492
[8]	Cardoso J F.High-order contrasts for independent component analysis[J].Neural Computation,1999,11(1):157-192
[9]	Duda R O,Hart P E, Strok D G.模式分类[M].李宏东,等译.2版.北京:机械工业出版社,2009:389-390 Duda R O,Hart P E,Strok D G.Pattern classification[M].Translated by Li Hongdong,et al.2nd ed.Beijing:China Machine Press Edition,2009:389-390(in Chinese)
[10]	Karvanen J,Eriksson J,Koivunen V.Pearson system based method for blind separation [C]//Proceedings of 2nd International Workshop on Independent Component Analysis and Blind Signal Separation.Helsinki:IEEE,2000:585-590
[11]	Barlow H.Unsupervised learning[J].Neural Computation,1989(1):295-311
[12]	Ozertem U,Uysal I,Erdogmus D.Continuously differentiable sample-spacing entropy estimation[J].IEEE Trans Neural Networks,2008,19(11):1978-1984
[13]	Bach F,Jordan M.Kernel independent component analysis[J].Journal of Machine Learning Research,2002(3):1-48
[14]	成孝刚,姜华,刘国庆,等.基于参数Parzen窗估计的独立分量分析[J].信号处理,2009,25(3):485-488 Cheng Xiaogang,Jiang Hua,Liu Guoqing,et al.Independent component analysis based on parametric parzen window estimstion[J].Signal Processing,2009,25(3):485-488(in Chinese)
[15]	Ypma A,Leshem A.Blind separation of machine vibration with bilinear forms [C]//Proceedings of 2nd International Workshop on Independent Component Analysis and Blind Signal Separation.Helsinki:IEEE,2000:109-114