Evolutionary manifold regularized stacked denoising autoencoders for gearbox fault diagnosis

Abstract Vibration signals are widely employed to fulfill gearbox fault diagnosis in real-world cases. However, it is quite challenging to extract effective fault features from noised vibration signals and then to construct an effective defect recognition model. Although deep neural networks (DNNs) have been used for feature extraction from vibration signals, the optimization of parameters and structure of DNNs simultaneously is still a difficult task in many applications. This paper proposes a new stacked denoising autoencoders (SDAE) algorithm, called manifold regularized SDAE (MRSDAE) based on particle swarm optimization (PSO), where manifold regularization and feature selection are embedded in the deep network smoothly. This study puts its emphasis on using PSO to simultaneously learn structure and parameters of MRSDAE based on a specific individual representation and learning scheme. MRSDAE aims to generate discriminant features from vibration signal data by using the integration of these effective techniques, i.e., structure and parameter optimization, manifold regularization and feature selection. MRSDAE-based fault diagnosis is implemented by an unsupervised representation learning followed by a supervised fine-tuning. The effectiveness of the MRSDAE-based fault diagnosis method has been verified by experimental results on vibration signal data from a gearbox defect test rig. The results illustrate that MRSDAE learns effective discriminative features and achieves the better diagnosis accuracy in comparison with that of the regular DNNs. Finding from this study can be used as the effective guidance in feature learning for machinery fault diagnosis based on evolutionary DNNs with manifold regularization and feature selection techniques.

[1]  Young-Joon Lee,et al.  Heath monitoring of a glass transfer robot in the mass production line of liquid crystal display using abnormal operating sounds based on wavelet packet transform and artificial neural network , 2012 .

[2]  Dacheng Tao,et al.  Non-Local Auto-Encoder With Collaborative Stabilization for Image Restoration , 2016, IEEE Transactions on Image Processing.

[3]  Ge Xiurun,et al.  An improved PSO-based ANN with simulated annealing technique , 2005, Neurocomputing.

[4]  Steven Verstockt,et al.  Convolutional Neural Network Based Fault Detection for Rotating Machinery , 2016 .

[5]  Yang Wang,et al.  Unsupervised local deep feature for image recognition , 2016, Inf. Sci..

[6]  Jianbo Yu,et al.  Machinery fault diagnosis using joint global and local/nonlocal discriminant analysis with selective ensemble learning , 2016 .

[7]  Guoqiang Zeng,et al.  Design of PID controller based on a self-adaptive state-space predictive functional control using extremal optimization method , 2018, J. Frankl. Inst..

[8]  Jian Weng,et al.  Adaptive population extremal optimization-based PID neural network for multivariable nonlinear control systems , 2019, Swarm Evol. Comput..

[9]  Enrico Zio,et al.  Feature-based classifier ensembles for diagnosing multiple faults in rotating machinery , 2008, Appl. Soft Comput..

[10]  Jianbo Yu,et al.  Tool condition prognostics using logistic regression with penalization and manifold regularization , 2018, Appl. Soft Comput..

[11]  Haidong Shao,et al.  Rolling bearing fault detection using continuous deep belief network with locally linear embedding , 2018, Comput. Ind..

[12]  Min-Rong Chen,et al.  A novel elitist multiobjective optimization algorithm: Multiobjective extremal optimization , 2008, Eur. J. Oper. Res..

[13]  Cong Wang,et al.  Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings , 2016 .

[14]  Haidong Shao,et al.  Electric Locomotive Bearing Fault Diagnosis Using a Novel Convolutional Deep Belief Network , 2018, IEEE Transactions on Industrial Electronics.

[15]  Xiaoqiang Lu,et al.  Scene Recognition by Manifold Regularized Deep Learning Architecture , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Guoqiang Zeng,et al.  Design of fractional order PID controller for automatic regulator voltage system based on multi-objective extremal optimization , 2015, Neurocomputing.

[17]  Danial Jahed Armaghani,et al.  Prediction of uniaxial compressive strength of rock samples using hybrid particle swarm optimization-based artificial neural networks , 2015 .

[18]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[19]  Haibo He,et al.  Stacked Multilevel-Denoising Autoencoders: A New Representation Learning Approach for Wind Turbine Gearbox Fault Diagnosis , 2017, IEEE Transactions on Instrumentation and Measurement.

[20]  Florian Metze,et al.  Extracting deep bottleneck features using stacked auto-encoders , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[21]  Gaoliang Peng,et al.  A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load , 2018, Mechanical Systems and Signal Processing.

[22]  Qiao Hu,et al.  Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble , 2007 .

[23]  Chin-Hui Lee,et al.  Exploiting deep neural networks for detection-based speech recognition , 2013, Neurocomputing.

[24]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[25]  Jing Lin,et al.  A multivariate encoder information based convolutional neural network for intelligent fault diagnosis of planetary gearboxes , 2018, Knowl. Based Syst..

[26]  R. Eberhart,et al.  Empirical study of particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[27]  Shu Zhan,et al.  Face detection using representation learning , 2016, Neurocomputing.

[28]  Wai Keung Wong,et al.  Deep Learning Regularized Fisher Mappings , 2011, IEEE Transactions on Neural Networks.

[29]  Guifang Liu,et al.  A Stacked Autoencoder-Based Deep Neural Network for Achieving Gearbox Fault Diagnosis , 2018, Mathematical Problems in Engineering.

[30]  Wuneng Zhou,et al.  Constrained population extremal optimization-based robust load frequency control of multi-area interconnected power system , 2019, International Journal of Electrical Power & Energy Systems.

[31]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[32]  Bin Jiang,et al.  Deep forest based multivariate classification for diagnostic health monitoring , 2018, 2018 Chinese Control And Decision Conference (CCDC).

[33]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[34]  Haidong Shao,et al.  A novel deep autoencoder feature learning method for rotating machinery fault diagnosis , 2017 .

[35]  Márcio das Chagas Moura,et al.  Deep variational auto-encoders: A promising tool for dimensionality reduction and ball bearing elements fault diagnosis , 2018, Structural Health Monitoring.

[36]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[37]  J. Salerno,et al.  Using the particle swarm optimization technique to train a recurrent neural model , 1997, Proceedings Ninth IEEE International Conference on Tools with Artificial Intelligence.

[38]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[39]  Chengjiang Li,et al.  Signal fusion-based deep fast random forest method for machine health assessment , 2018 .

[40]  Wei Xiong,et al.  Stacked Convolutional Denoising Auto-Encoders for Feature Representation , 2017, IEEE Transactions on Cybernetics.

[41]  Chia-Feng Juang,et al.  A hybrid of genetic algorithm and particle swarm optimization for recurrent network design , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[42]  Simon J. Doran,et al.  Stacked Autoencoders for Unsupervised Feature Learning and Multiple Organ Detection in a Pilot Study Using 4D Patient Data , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Ming Zhao,et al.  A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox , 2017 .

[44]  Chuang Sun,et al.  Deep Coupling Autoencoder for Fault Diagnosis With Multimodal Sensory Data , 2018, IEEE Transactions on Industrial Informatics.

[45]  Lifeng Xi,et al.  Evolving artificial neural networks using an improved PSO and DPSO , 2008, Neurocomputing.

[46]  Nanning Zheng,et al.  Improving CNN Performance Accuracies With Min–Max Objective , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[47]  Jianbo Yu,et al.  A hybrid feature selection scheme and self-organizing map model for machine health assessment , 2011, Appl. Soft Comput..

[48]  Pingfeng Wang,et al.  Failure diagnosis using deep belief learning based health state classification , 2013, Reliab. Eng. Syst. Saf..

[49]  Jianbo Yu,et al.  Bearing performance degradation assessment using locality preserving projections and Gaussian mixture models , 2011 .

[50]  Prasant Kumar Pattnaik,et al.  Artificial Neural Network trained by Particle Swarm Optimization for non-linear channel equalization , 2014, Expert Syst. Appl..

[51]  Qingbo He,et al.  Energy-Fluctuated Multiscale Feature Learning With Deep ConvNet for Intelligent Spindle Bearing Fault Diagnosis , 2017, IEEE Transactions on Instrumentation and Measurement.

[52]  Saman K. Halgamuge,et al.  Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients , 2004, IEEE Transactions on Evolutionary Computation.

[53]  Mingzhe Liu,et al.  Evolving RBF neural networks for rainfall prediction using hybrid particle swarm optimization and genetic algorithm , 2015, Neurocomputing.

[54]  Jun Yan,et al.  Multiscale Convolutional Neural Networks for Fault Diagnosis of Wind Turbine Gearbox , 2019, IEEE Transactions on Industrial Electronics.

[55]  B. Samanta,et al.  Gear fault detection using artificial neural networks and support vector machines with genetic algorithms , 2004 .

[56]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[57]  Hujun Bao,et al.  Laplacian Regularized Gaussian Mixture Model for Data Clustering , 2011, IEEE Transactions on Knowledge and Data Engineering.

[58]  Haidong Shao,et al.  An enhancement deep feature fusion method for rotating machinery fault diagnosis , 2017, Knowl. Based Syst..

[59]  Jianbo Yu,et al.  Process monitoring through manifold regularization-based GMM with global/local information , 2016 .