Semi-supervised Fault Identification Based on Laplacian Eigenmap and Deep Belief Networks

doi:10.3901/JME.2020.01.069

Abstract

Abstract: Aiming at solving the problem of insufficient labeled samples in mechanical equipment fault diagnosis, a semi-supervised fault recognition model based on Laplace Eigenmap (LE) and Deep Belief Network (DBN) is presented by combining the idea of manifold learning and deep learning. The model utilizes LE algorithm to directly extract the features from the raw high-dimensional vibration signal, and inputs the low-dimensional manifold features into DBN. By using a few expensive labeled samples and lots of cheap unlabeled samples, it excavates fault features for a second time, and finally constructs the Soft-max classification to identify the fault mode of the mechanical equipment. The semi-supervised model is applied to the identification of bearing faults and gear cracks. The test results show that LE algorithm can effectively reduce the time complexity of the model, enhance the intelligence of feature extraction and improve the diagnostic efficiency. DBN network can fully mine fault characteristics, get better feature representation, and improve diagnostic accuracy. In addition, the model also achieves a good diagnosis effect with unbalanced training label, and is applicable to the diagnosis of multi-sensor feature fusion, which has practical application value.

Key words: Laplacian eigenmap, deep belief networks, semi-supervise, fault diagnosis

CLC Number:

TH133

ZHANG Xin, GUO Shunsheng, LI Yibing, JIANG Li. Semi-supervised Fault Identification Based on Laplacian Eigenmap and Deep Belief Networks[J]. Journal of Mechanical Engineering, 2020, 56(1): 69-81.

References

[1] EL-THALJI I,JANTUNEN E. A summary of fault modelling and predictive health monitoring of rolling element bearings[J]. Mechanical Systems & Signal Processing,2015,60-61(1):252-272.
[2] BIN Guangfu,GAO Jinji,LI Xuejun,et al. Early fault diagnosis of rotating machinery based on wavelet packets-Empirical mode decomposition feature extraction and neural network[J]. Mechanical Systems & Signal Processing,2012,27(1):696-711.
[3] 孙斌,薛广鑫. 基于等距特征映射和支持矢量机的转子故障诊断方法[J]. 机械工程学报,2012,48(9):129-135. SUN Bin,XUE Guangxin. Method of rotor fault diagnosis based on isometric feature mapping and support vector machine[J]. Journal of Mechanical Engineering,2012,48(9):129-135.
[4] ZHANG Xinhai,LEI Yong. Application of bp neural network in mechanical fault diagnosis[J]. Noise & Vibration Control,2008,23(23):182-184.
[5] 李巍华,史铁林,杨叔子. 基于核函数估计的转子故障诊断方法[J]. 机械工程学报,2006,42(9):76-82. LI Weihua,SHI Tielin,YANG Shuzi. Rotor fault diagnosis method based on kernel function estimation[J]. Chinese Journal of Mechanical Engineering,2006,42(9):76-82.
[6] JIANG Li,XUAN Jianping,SHI Tielin. Feature extraction based on semi-supervised kernel Marginal Fisher analysis and its application in bearing fault diagnosis[J]. Mechanical Systems & Signal Processing,2013,41(1-2):113-126.
[7] WANG Sheng,LU Jianfeng,GU Xingjian,et al. Semi-supervised linear discriminant analysis for dimension reduction and classification[J]. Pattern Recognition,2016,57(C):179-189.
[8] HINTON G,SALAKHUTDINOV R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.
[9] 雷亚国,贾峰,孔德同,等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报,2018,54(5):94-104. LEI Yaguo,JIA Feng,KONG Detong,et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering,2018,54(5):94-104.
[10] CHEN Zhiqiang,DENG Shengcai,CHEN Xudong,et al. Deep neural networks-based rolling bearing fault diagnosis[J]. Microelectronics Reliability,2017,75:327-333.
[11] SHAO Haidong,JIANG Hongkai,ZHANG Haizhou,et al. Electric locomotive bearing fault diagnosis using a novel convolutional deep belief Network[J]. IEEE Transactions on Industrial Electronics,2017,65(3):2727-2736.
[12] LIU Jie,HU Youmin,WANG Yan,et al. An integrated multi-sensor fusion-based deep feature learning approach for rotating machinery diagnosis[J]. Measurement Science & Technology,2018,29(5).
[13] SHAO Haidong,JIANG Hongkai,LI Xingqiu,et al. Intelligent fault diagnosis of rolling bearing using deep wavelet auto-encoder with extreme learning machine[J]. Knowledge-based Systems,2018,140:1-14.
[14] HINTON G. Deep belief networks[J]. Scholarpedia,2009,4(6):5947.
[15] 赵光权,葛强强,刘小勇,等. 基于DBN的故障特征提取及诊断方法研究[J]. 仪器仪表学报,2016,37(9):1946-1953. ZHAO Guangquan,GE Qiangqiang,LIU Xiaoyong,et al. Fault feature extraction and diagnosis method based on deep belief network[J]. Chinese Journal of Scientific Instrument,2016,37(9):1946-1953.
[16] 张淑清,胡永涛,姜安琦,等. 基于双树复小波和深度信念网络的轴承故障诊断[J]. 中国机械工程,2017,28(5):532-536. ZHANG Shuqing,HU Yongtao,JIANG Anqi,et al. Bearing fault diagnosis based on DTCWT and DBN[J]. China Mechanical Engineering,2017,28(5):532-536.
[17] JIANG QuanSheng,JIA Minping,HU Jianzhong,et al. Machinery fault diagnosis using supervised manifold learning[J]. Mechanical Systems & Signal Processing,2009,23(7):2301-2311.
[18] RADUCANU B,DORNAIKA F. A supervised non-linear dimensionality reduction approach for manifold learning[J]. Pattern Recognition,2012,45(6):2432-2444.
[19] ZHANG Yun,LI Benwei,WANG Wen,et al. Supervised locally tangent space alignment for machine fault diagnosis[J]. Journal of Mechanical Science & Technology,2014,28(8):2971-2977.
[20] LUNGA D,PRASAD S,CRAWFORD M,et al. Manifold learning based feature extraction for classification of hyperspectral data[J]. IEEE Signal Processing Magazine,2014,31(1):55-66.
[21] NICOLAS L R,YOSHUA B. Representational power of restricted boltzmann machines and deep belief networks[J]. Neural Computation,2008,20(6):1631-1649.
[22] 陶洁,刘义伦,杨大炼,等. 基于细菌觅食决策和深度置信网络的滚动轴承故障诊断[J]. 振动与冲击,2017,36(23):68-74. TAO Jie,LIU Yilun,YANG Dalian,et al. Rolling bearing fault diagnosis based on bacterial foraging algorithm and deep belief network[J]. Journal of Vibration and Shock,2017,36(23):68-74.
[23] HINTON G. Training products of experts by minimizing contrastive divergence[J]. Neural Computation,2002,14(8):1771-1800.
[24] LOPARO K A. Bearings vibration data set[DB/OL]. Cleveland,Ohio:Case Western Reserve University.[2014-10-28].http://csegroups.case.edu/bearingdatacenter/home.
[25] 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,2016,27(14):1911-1916. JIANG Li,GUO Shunsheng. Fault diagnosis based on semi-supervised laplacian eigenmaps[J]. China Mechanical Engineering,2016,27(14):1911-1916.
[26] HE Qingbo. Time-frequency manifold for nonlinear feature extraction in machinery fault diagnosis[J]. Mechanical Systems & Signal Processing,2013,35(1-2):200-218.
[27] 李巍华,单外平,曾雪琼. 基于深度信念网络的轴承故障分类识别[J]. 振动工程学报,2016,29(2):340-347. LI Weihua,SHAN Waiping,ZENG Xueqiong. Bearing fault classification and identification based on deep belief networks[J]. Journal of Vibration Engineering,2016,29(2):340-347.
[28] GUO Liang,LEI Yaguo,LI Naipeng,et al. Machinery health indicator construction based on convolutional neural networks considering trend burr[J]. Neurocomputing,2018,292:142-150.