基于半监督拉普拉斯特征映射的故障诊断

摘要/Abstract

摘要： 针对有标记故障样本不足和故障数据高维非线性的问题，提出了基于半监督拉普拉斯特征映射（LE）算法的故障诊断模型。该模型运用LE算法，直接从原始高维振动信号中提取低维流形特征，并将其输入到基于LE的半监督分类器，从而识别出机械设备的运行状态。与传统方法相比，该模型能明显提高滚动轴承和齿轮的故障识别性能。

关键词: 故障诊断, 特征提取, 流形学习, 半监督拉普拉斯特征映射

Abstract: Aiming at solving the problems of insufficient labeled fault samples and high-dimensional nonlinear fault data, a fault diagnosis model was proposed based on semi-supervised LE algorithm. The model directly extracted the low-dimensional manifold features from the raw high-dimensional vibration signals, by implementing LE algorithm. The features were fed into semi-supervised classifier based on LE algorithm. Thereby, the operating conditions of mechanical equipment were recognized. Compared with the traditional methods, the model is able to obviously improve fault recognition performance of rolling bearings and gears.

Key words: fault diagnosis, feature extraction, manifold learning, semi-supervised Laplacian eigenmap(LE)

中图分类号:

江丽, 郭顺生. 基于半监督拉普拉斯特征映射的故障诊断[J]. 中国机械工程.

Jiang Li, Guo Shunsheng. Fault Diagnosis Based on Semi-supervised Laplacian Eigenmaps[J]. China Mechanical Engineering.

参考文献

[1]He Qingbo. Time–frequency Manifold for Nonlinear Feature Extraction in Machinery Fault Diagnosis[J]. Mechanical Systems and Signal Processing，2013, 35（1/2):200-218.

[2]Lu Wenbo, Jiang Weikang, Wu Haijun, et al. A Fault Diagnosis Scheme of Rolling Element Bearing Based on Near-field Acoustic Holography and Gray Level Co-occurrence Matrix[J]. Journal of Sound and Vibration，2012, 331（15): 3663-3674.

[3]黄宏臣, 韩振南, 张倩倩，等. 基于拉普拉斯特征映射的滚动轴承故障识别[J]. 振动与冲击，2015，34(5): 128-134.

Huang Hongchen, Han Zhennan, Zhang Qianqian, et al. Method of Fault Diagnosis for Rolling Bearings Based on Laplacian Eigenmap[J]. Journal of Vibration and Shock，2015, 34（5): 128-134.

[4]孙斌, 刘立远, 牛翀，等. 基于局部切空间排列和K-最近邻分类器的转子故障诊断方法[J]. 中国机械工程，2015，26（1): 74-78.

Sun Bin, Liu Liyuan, Niu Chong, et al. Rotor Fault Diagnosis Methods Based on Local Tangent Space Alignment and K-nearest Neighbor Classifier[J]. China Mechanical Engineering，2015, 26（1): 74-78.

[5]Schlkopf B, Smola A, Muller K R. Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J]. Neural Computation， 1998, 10（5): 1299-1319.

[6]Mika S, Rtsch G, Weston J, et al. Fisher Discriminant Analysis with Kernels[C]//Proceedings of the 1999 IEEE Signal Processing Society Workshop. New York，1999: 41-48.

[7]Owsley L M D, Atlas L E, Bernard G D. Self-organizing Feature Maps and Hidden Markov Models for Machine-tool Monitoring[J]. IEEE Transactions on Signal Processing， 1997, 45（11): 2787-2798.

[8]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.

Liu Lijuan, Chen Guo, Hao Tengfei. Incipient Fault Recognition of Rolling Bearings Based on Manifold Learning and One-class SVM[J]. China Mechanical Engineering，2013, 24（5): 628-633.

[9]欧璐, 于德介. 基于拉普拉斯分值和模糊c均值聚类的滚动轴承故障诊断[J]. 中国机械工程，2014，25(10): 1352-1357.

Ou Lu, Yu Dejie. Rolling Bearing Fault DiagnosisBased on Laplacian Score and Fuzzy C-means Clustering[J]. China Mechanical Engineering，2014, 25（10): 1352-1357.

[10]苏祖强, 汤宝平, 刘自然，等. 基于正交半监督局部fisher判别分析的故障诊断[J]. 机械工程学报，2014，50（18): 7-13.

Su Zuqiang, Tang Baoping, Liu Ziran. Fault Diagnosis Method Based on Orthogonal Semi-supervised Local Fisher Discriminant Analysis[J]. Journal of Mechanical Engineering，2014, 50（18): 7-13.

[11]Su Zuqiang, Tang Baoping, Ma Jinghua, et al. Fault Diagnosis Method Based on Incremental Enhanced Supervised Locally Linear Embedding and Adaptive Nearest Neighbor Classifier[J]. Measurement，2014, 48: 136-148.

[12]Wang Yi, Xu Guanghua, Liang Lin, et al. Detection of Weak Transient Signals Based on Wavelet Packet Transform and Manifold Learning for Rolling Element Bearing Fault Diagnosis[J]. Mechanical Systems and Signal Processing，2015, 54: 259-276.

[13]Belkin M, Niyogi P. Laplacian Eigenmaps for Dimensionality Reduction and Data Representation[J]. Neural Computation， 2003, 15（6): 1373-1396.

[14]Belkin M, Niyogi Pi. Semi-supervised Learning on Riemannian Manifolds[J]. Machine Learning，2004, 56（1/3): 209-239.

[15]Kouropteva O, Okun O, Hadid A, et al. Beyond Locally Linear Embedding Algorithm, MVG-01-2002[R].Oulu，Finland：University of Oulu, 2002.

[16]He Qingbo. Time–frequency Manifold for Nonlinear Feature Extraction in Machinery Fault Diagnosis[J]. Mechanical Systems and Signal Processing, 2013, 35（1/2): 200-218.

[17]Loparo K A. Bearings Vibration Data Set[DB/OL]. Cleveland, Ohio：Case Western Reserve University. [2014-10-28]. http://Csegroups.Case.Edu/Bearingdatacenter/Home.

[18]Vibroacoustic Gear Signatures with Time-Frequency Spectrograms[DB/OL]. [2015-05-09]. http://www.ulb.ac.be/polytech/laborulb/gearvi/gearjtfa.htm.