Linear maximum margin tensor classification based on flexible convex hulls for fault diagnosis of rolling bearings

Abstract The fault diagnosis of rolling bearings methods based on machine learning have been developed in the past years, such as neutral network (NN), support vector machine (SVM) and convolutional neural networks (CNN). The first two methods just can be used for the classification of the vector space in which the feature data extracted from raw signals are input in vector form, so they lose their functions when the input feature data are high order tensors which can contain rich feature information of rolling bearing vibration signals. Moreover, a large number of data are needed in CNN, but it is hard to get large numbers of fault samples of rolling bearings under different conditions. Recently, a kind of tensor classifier called support tensor machines (STM) can solve the problems in the above methods. These classifiers can be regarded as maximum margin tensor classification based on convex hulls methods. But convex hull is typically a substantial under-approximation to the class region. Therefore, in this paper, a novel linear maximum margin tensor classification based on flexible convex hulls(MMTC-FCH) is proposed and applied to the fault diagnosis of rolling bearings. In this method, firstly, for binary classification problems, MMTC-FCH is aimed at finding an optimal separating hyperplane that generates the maximum margin between flexible convex hulls of two tensor sample sets. Subsequently, for linearly inseparable cases, the reduction factor is used to improve the robustness of MMTC-FCH when there are outliers in the training samples. Finally, MMTC-FCH is extended to deal with the multi-class classification problems by using the strategies in SVM. To train a MMTC-FCH classifier, wavelet time–frequency grayscale images as second-order tensors input are constructed from raw vibration signals by continuous wavelet transform (CWT). The experimental results show that the proposed method not only recognizes different rolling bearing faults but also can achieve the best results when the classifier is lack of severe fault training samples and there are outliers in the training sample.

[1]  Wei Jiang,et al.  Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders. , 2018, ISA transactions.

[2]  Peng Chen,et al.  Step-by-Step Fuzzy Diagnosis Method for Equipment Based on Symptom Extraction and Trivalent Logic Fuzzy Diagnosis Theory , 2018, IEEE Transactions on Fuzzy Systems.

[3]  Qiang Miao,et al.  Bearing fault diagnosis using a whale optimization algorithm-optimized orthogonal matching pursuit with a combined time–frequency atom dictionary , 2018, Mechanical Systems and Signal Processing.

[4]  Yaguo Lei,et al.  Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization , 2018, Mechanical Systems and Signal Processing.

[5]  Ming Zeng,et al.  Maximum margin classification based on flexible convex hulls , 2015, Neurocomputing.

[6]  Lingli Cui,et al.  Quantitative and Localization Diagnosis of a Defective Ball Bearing Based on Vertical–Horizontal Synchronization Signal Analysis , 2017, IEEE Transactions on Industrial Electronics.

[7]  Yonghua Zhou,et al.  Parallel computing method of deep belief networks and its application to traffic flow prediction , 2019, Knowl. Based Syst..

[8]  Xiaofeng Liu,et al.  Bearing faults diagnostics based on hybrid LS-SVM and EMD method , 2015 .

[9]  Caroline Fossati,et al.  Improvement of Classification for Hyperspectral Images Based on Tensor Modeling , 2010, IEEE Geoscience and Remote Sensing Letters.

[10]  Dong Xu,et al.  Multilinear Discriminant Analysis for Face Recognition , 2007, IEEE Transactions on Image Processing.

[11]  Tamir Hazan,et al.  Sparse image coding using a 3D non-negative tensor factorization , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[12]  Xiaowei Yang,et al.  A Linear Support Higher-Order Tensor Machine for Classification , 2013, IEEE Transactions on Image Processing.

[13]  Fernando Moreu,et al.  Low-cost, efficient wireless intelligent sensors (LEWIS) measuring real-time reference-free dynamic displacements , 2018, Mechanical Systems and Signal Processing.

[14]  Satish C. Sharma,et al.  Fault diagnosis of ball bearings using continuous wavelet transform , 2011, Appl. Soft Comput..

[15]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[16]  Florian Roemer,et al.  A semi-algebraic framework for approximate CP decompositions via simultaneous matrix diagonalizations (SECSI) , 2013, Signal Process..

[17]  Gérard Dreyfus,et al.  Single-layer learning revisited: a stepwise procedure for building and training a neural network , 1989, NATO Neurocomputing.

[18]  Yu Yang,et al.  A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM , 2007 .

[19]  Qu Yi,et al.  Fault detection and diagnosis for non-Gaussian stochastic distribution systems with time delays via RBF neural networks. , 2012, ISA transactions.

[20]  Ming Zeng,et al.  Maximum margin classification based on flexible convex hulls for fault diagnosis of roller bearings , 2016 .

[21]  Haiping Lu,et al.  MPCA: Multilinear Principal Component Analysis of Tensor Objects , 2008, IEEE Transactions on Neural Networks.

[22]  Xin Zhou,et al.  Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data , 2016 .

[23]  Ming Shao,et al.  Sparse Canonical Temporal Alignment With Deep Tensor Decomposition for Action Recognition , 2017, IEEE Transactions on Image Processing.

[24]  Saïd Rechak,et al.  On the extraction of rules in the identification of bearing defects in rotating machinery using decision tree , 2010, Expert Syst. Appl..

[25]  Xuelong Li,et al.  Supervised Tensor Learning , 2005, ICDM.

[26]  Souleymen Sahnoun,et al.  Tensor decomposition exploiting diversity of propagation velocities: Application to localization of icequake events , 2016, Signal Process..

[27]  Jirí Vomlel,et al.  Exploiting tensor rank-one decomposition in probabilistic inference , 2007, Kybernetika.

[28]  Haidong Shao,et al.  Intelligent fault diagnosis of rolling bearing using deep wavelet auto-encoder with extreme learning machine , 2018, Knowl. Based Syst..

[29]  Hongxia Zhang,et al.  Research on mud pulse signal detection based on adaptive stochastic resonance , 2017 .

[30]  Irene Kotsia,et al.  Support tucker machines , 2011, CVPR 2011.

[31]  Junsheng Cheng,et al.  One-class classification based on the convex hull for bearing fault detection , 2016 .

[32]  Minho Lee,et al.  Deep learning of support vector machines with class probability output networks , 2015, Neural Networks.

[33]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[34]  Sunil Tyagi,et al.  An improved envelope detection method using particle swarm optimisation for rolling element bearing fault diagnosis , 2017, J. Comput. Des. Eng..

[35]  Yang Yu,et al.  The application of energy operator demodulation approach based on EMD in machinery fault diagnosis , 2007 .

[36]  Yudong Zhang,et al.  Binary PSO with mutation operator for feature selection using decision tree applied to spam detection , 2014, Knowl. Based Syst..

[37]  Jin Chen,et al.  Decision tree and PCA-based fault diagnosis of rotating machinery , 2007 .

[38]  Lin Mi,et al.  Multi-steps degradation process prediction for bearing based on improved back propagation neural network , 2013 .

[39]  Xiaoyuan Zhang,et al.  Multi-fault diagnosis for rolling element bearings based on ensemble empirical mode decomposition and optimized support vector machines , 2013 .

[40]  Liang Gao,et al.  A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method , 2018, IEEE Transactions on Industrial Electronics.