Incipient Fault Recognition of Rolling Bearings Based on Manifold Learning and One-class SVM

Abstract

Abstract:

A method was presented for incipient fault recognition of rolling bearings,which was based on manifold learning and one-class SVM.Firstly,the original feature space was constructed with the domain parameters of bearing signals,and then the LE was used to compress the feature samples and acquire the sensitive fault features,Finally the classification and recognition of all status were implemented with one-class SVM.Besides,with the actual fault data of rolling bearings the method was confirmed and the feasibility was indicated from the comparison of LE and principal component analysis. 

Key words: manifold learning, one-class SVM, rolling bearing, fault recognition, Laplacian eigenmap(LE)

摘要：

提出了一种基于流形学习与一类支持向量机的轴承早期故障识别方法。首先提取轴承信号的时域参数构成原始特征样本空间;然后采用基于拉普拉斯特征映射算法(Laplacian eigenmap,LE）的流形学习方法对特征样本进行特征压缩,提取出敏感的故障特征;最后采用一类支持向量机对各状态实现分类识别。利用实测的滚动轴承故障数据对算法进行了验证,并将LE方法与主成分分析（PCA）方法进行了比较,
结果证明该方法可行。

关键词: 流形学习, 一类支持向量机, 轴承, 故障识别, 拉普拉斯特征映射

CLC Number:

V263.6
TP277

LIU Li-Juan, CHEN Guan, HAO Teng-Fei. Incipient Fault Recognition of Rolling Bearings Based on Manifold Learning and One-class SVM[J]. China Mechanical Engineering, 2013, 24(5): 628-633.

刘丽娟, 陈果, 郝腾飞. 基于流形学习与一类支持向量机的滚动轴承早期故障识别方法[J]. 中国机械工程, 2013, 24(5): 628-633.

References

[1]陈果.滚动轴承早期故障的特征提取与智能诊断[J].航空学报,2009,30(2):362-267.
Chen Guo.Feature Extraction and Intelligent Diagnosis for Ball Bearing Early Faults[J].Acta Aeronautica et Astronautica Sinica,2009,30(2):362-267.
[2]Huang N E,Shen Z,Long S R.The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-Stationary Time Series Analysis[C]//Proceedings of the Royal Society.London,1998:903-995.
[3]Seung H S,Daniel D L.The Manifold Ways of Perception[J].Science,2000,290(5500):2268-2269.
[4]Roweis S,Saul L.Nonlinear Dimensionality Reduction by Locally Linear Embedding[J].Science,2000,290(5500):2323-2326.
[5]Tenenbaum J,Silva D D,Langford J.A Global Geometric Framework for Nonlinear Dimensionality Reduction[J].Science,2000,290(5500):2319-2323.
[6]罗四维,赵连伟.基于谱图理论的流形学习算法[J].计算机研究与发展,2006,43(7):1173-1179.
Luo Siwei,Zhao Lianwei.Manifold Learning Algorithms Based on Spectral Graph Theory[J].Journal of Computer Research and Development,2006,43(7):1173-1179.
[7]栗茂林,王孙安,梁霖.利用非线性流形学习的轴承早期故障特征提取方法[J].西安交通大学学报,2010,44(5):45-49.
Li Maolin,Wang Sun’an,Liang Lin.Feature Extraction for Incipient Fault Diagnosis of Rolling Bearings Based on Nonlinear Manifold Learning[J].Journal of Xi’an Jiaotong University，2010,44(5):45-49.
[8]Juszczak P.Learning to Recognise:a Study on One-class Classification and Active Learning[D].Delft:Delft University of Technology,2006.
[9]谭真臻,陈果,陈立波,等.基于图像分析和野点检测的航空发动机磨损状态识别[J].中国机械工程,2010,21(7):827-831.
Tan Zhenzhen,Chen Guo,Chen Libo,et al.Areo-engine Wear State Recogniton Based on Image Analysis and Novelty Detection[J].China Mechanical Engineering,2010, 21(7):827-831.
[10]杨洁明,田英.基于EMD和球结构SVM的滚动轴承故障诊断[J].振动、测试与诊断,2009,29(2):155-158.
Yang Jieming,Tian Ying.Roller Bearing Fault Diagnosis by Using Empirical Mode Decomposition and Sphere-Structured Support Vector Machine[J].Journal of Vibration,Measurement & Diagnosis,2009,29(2):155-158.
[11]Belkin M, Niyogi P. Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering[C]//Advances in NIPS 14.Cambridge,2001:585-591.
[12]Belkin M,Niyogi P.Laplacian Eigenmaps for Dimensionality Reduction and Data Representation[J].Neural Computation(S0899-7667),2003,15(6):1373-1396.
[13]蒋全胜,贾民平,胡建中,等.基于拉普拉斯特征映射的故障模式识别方法[J].系统仿真学报,2008,20(20):5710-5713.
Jiang Quansheng,Jia Minping,Hu Jianzhong,et al.Method of Fault Pattern Recognition Based on Laplacian Eigenmaps[J].Journal of System Simulation,2008,20(20):5710-5713.
[14]李良敏,屈梁生.遗传编程在无量纲指标构建中的应用[J].西安交通大学学报,2002,36(7):735-739.
Li Liangmin,Qu Liangsheng.Genetic Programming for Dimensionless Parameters Construction[J].Journal of Xi’an Jiaotong University,2002,36(7):735-739.
[15]易良榘.简易振动诊断现场实用技术[M].北京:机械工业出版社,2003.
[16]The Case Western Reserve University Bearing Data Center.Bearing Data Center Fault Test Data.[2009-10-01].http://www.eecs.cwru.edu/laboratory/bearing/．
[17]Tax D,Duin R.Support Vector Data Description[J].Machine Learning,2004,54(1):45-66.