精密制造与加工:2017,Vol:36,Issue(9):1402-1407
引用本文:
孟凡磊, 崔伟成, 李伟, 刘林密. LCD、k-means与ICA相结合的滚动轴承故障诊断方法[J]. 机械科学与技术
Meng Fanlei, Cui Weicheng, Li Wei, Liu Linmi. Fault Diagnosis of Rolling Bearing using LCD, k-means and ICA[J]. Journal Of Remote Sensing

LCD、k-means与ICA相结合的滚动轴承故障诊断方法
孟凡磊, 崔伟成, 李伟, 刘林密
海军航空工程学院飞行器工程系, 山东烟台 264001
摘要:
为了准确地进行滚动轴承故障诊断,针对故障振动信号的低信噪比特征,提出了局部特征尺度分解、k均值聚类分析和独立分量分析相结合的故障诊断方法。首先,应用局部特征尺度分解对振动信号进行分解,得到若干个内禀尺度分量;然后,依据分量与原始信号的互相关系数及峭度值,应用k均值聚类方法选取有效的分量组成新的观测信号;最后,对观测信号进行独立分量分析处理,实现信噪分离,依据峭度值选取信号分量,对信号应用希尔伯特包络谱技术实现故障诊断。通过轴承内圈故障数据分析,验证了方法的有效性。
关键词:    局部特征尺度分解    聚类分析    独立分量分析    互相关系数    峭度    轴承故障诊断   
Fault Diagnosis of Rolling Bearing using LCD, k-means and ICA
Meng Fanlei, Cui Weicheng, Li Wei, Liu Linmi
Department of Aircraft Engineering, Naval Aeronautical and Astronautical University, Shandong Yantai 264001, China
Abstract:
The rolling bearing fault vibration signals have low signal-to-noise ratio. Aiming at diagnosing the fault of rolling bearing accurately, a method based on local characteristic-scale decomposition(LCD), k-means cluster analysis and independent component analysis(ICA) was proposed. Firstly, the vibration signal was decomposed into some intrinsic mode components (ISC) by LCD. Then the correlation coefficients of every ISC and the original signal and the kurtosis value of every ISC were calculated, the efficient components were selected by means of k-means cluster analysis. The efficient components were processed by ICA to separate the signal from the noise, and the signal components were selected according to the kurtosis values. Finally, the Hilbert envelope aptitude envelope spectrum was used for fault diagnosis. The analysis of the bearing fault data shows that the method can realize weak signal detection and fault diagnosis effectively.
Key words:    local characteristic-scale decomposition    cluster analysis    independent component analysis    correlation coefficients    kurtosis    fault diagnosis of Rolling Bearing   
收稿日期: 2016-01-20     修回日期:
DOI: 10.13433/j.cnki.1003-8728.2017.0915
基金项目: 国家部委预研基金项目(9140A27020214JB1446)资助
通讯作者:     Email:
作者简介: 孟凡磊(1978-),讲师,硕士,研究方向为装备智能故障诊断方法研究,fl_meng@126.com
相关功能
PDF(1065KB) Free
打印本文
把本文推荐给朋友
作者相关文章
孟凡磊  在本刊中的所有文章
崔伟成  在本刊中的所有文章
李伟  在本刊中的所有文章
刘林密  在本刊中的所有文章

参考文献:
[1] 屈梁生,张西宁,沈玉娣.机械故障诊断理论与方法[M].西安:西安交通大学出版社,2009 Qu L S, Zhang X N, Shen Y D. Mechanical fault diagnosis theory and method[M]. Xi'an:Xi'an Jiaotong University Press, 2009(in Chinese)
[2] 李舜酩.振动信号的盲源分离技术及应用[M].北京:航空工业出版社,2011 Li S M. Vibration signal blind source separation technique and its application[M]. Beijing:Aviation Industry Press, 2011(in Chinese)
[3] Huang N E, Hen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A:Mathematical, Physical and Engineering Sciences, 1998,454(1971):903-995
[4] 陈建国,张志新,郭正刚,等.独立分量分析方法在经验模式分解中的应用[J].振动与冲击,2009,28(1):109-111,130 Chen J G, Zhang Z X, Guo Z G, et al. Application of independent component analysis in empirical mode decomposition[J]. Journal of Vibration and Shock, 2009,28(1):109-111,130(in Chinese)
[5] 唐先广,郭瑜,丁彦春.基于独立分量分析与希尔伯特-黄变换的轴承故障特征提取[J].振动与冲击,2011,30(10):45-49 Tang X G, Guo Y, Ding Y C. Application of Hilbert Huang transition and independent components analysis on rolling element bearing faults features extraction[J]. Journal of Vibration and Shock, 2011,30(10):45-49(in Chinese)
[6] 张俊红,李林洁,马文朋,等.EMD-ICA联合降噪在滚动轴承故障诊断中的应用[J].中国机械工程,2013,24(11):1468-1472 Zhang J H, Li L J, Ma W P, et al. Application of EMD-ICA to fault diagnosis of rolling bearings[J]. China Mechanical Engineering, 2013,24(11):1468-1472(in Chinese)
[7] 赵阳,陈捷,洪荣晶,等.EMD和独立分量分析在转盘轴承故障诊断中的应用[J].轴承,2015(7):54-59 Zhao Y, Chen J, Hong R J, et al. Application of EMD and ICA in fault diagnosis for slewing bearing[J]. Bearing, 2015(7):54-59(in Chinese)
[8] 崔玲丽,吴春光,邬娜.基于EMD与ICA的滚动轴承复合故障诊断[J].北京工业大学学报,2014,40(10):1459-1464 Cui L L, Wu C G, Wu N. Composite fault diagnosis of rolling bearings based on EMD and ICA algorithm[J]. Journal of Beijing University of Technology, 2014,40(10):1459-1464(in Chinese)
[9] 程军圣,郑近德,杨宇.一种新的非平稳信号分析方法-局部特征尺度分解法[J].振动工程学报,2012,25(2):215-220 Cheng J S, Zheng J D, Yang Y. A nonstationary signal analysis approach-the local characteristic-scale decomposition method[J]. Journal of Vibration Engineering, 2012,25(2):215-220(in Chinese)
[10] 杨宇,曾鸣,程军圣.一种新的时频分析方法-局部特征尺度分解[J].湖南大学学报(自然科学版),2012,39(6):35-39 Yang Y, Zeng M, Cheng J S. A new time-frequency analysis method-the local characteristic-scale decomposition[J]. Journal of Hunan University (Natural Sciences), 2012,39(6):35-39(in Chinese)
[11] 杨宇,曾鸣,程军圣.局部特征尺度分解方法及其分解能力研究[J].振动工程学报,2012,25(5):602-609 Yang Y, Zeng M, Cheng J S. Research on local characteristic-scale decomposition and its capacities[J]. Journal of Vibration Engineering, 2012,25(5):602-609(in Chinese)
[12] 李力.机械信号处理及其应用[M].武汉:华中科技大学出版社,2007 Li L. Mechanical signal processing and its application[M]. Wuhan:Huazhong University of Science and Technology Press, 2007(in Chinese)
[13] 张学工.模式识别[M].3版.北京:清华大学出版社,2010 Zhang X G. Pattern recognition[M]. 3rd ed. Beijing:Tsinghua University Press, 2010(in Chinese)
[14] 廖伯瑜.机械故障诊断基础[M].北京:冶金工业出版社,1995 Liao B Y. Mechanical fault detection[M]. Beijing:Metallurgical Industry Press, 1995(in Chinese)
[15] Case Western Reserve University Bearing Data Center[EB/OL]. (2012-11-07)[2012-12-07]. http://csegroups.case.edu/bearingdatacenter
相关文献:
1.张超, 陈建军.基于EMD降噪和谱峭度的轴承故障诊断方法[J]. 机械科学与技术, 2015,34(2): 252-256