Domain adaptive deep belief network for rolling bearing fault diagnosis

Abstract As the essential components of rotating machines, rolling bearings always operate in variable working conditions and suffer from different failure modes. To address the issue of lacking substantial labeled samples in new working conditions, a domain adaptive deep belief network (DA-DBN) is proposed for rolling bearing fault diagnosis. Firstly, the DBN model is pre-trained by the labeled samples which are composed of raw vibration signals and their corresponding time domain and frequency domain indicators. Secondly, the domain adaption method in transfer learning is applied to calculate the multi-kernel maximum mean discrepancies (MK-MMD) between the known working condition data and new working condition data in multiple layers. Thus, the loss function composed of MK-MMD and classification error can be obtained, and back propagation algorithm is used to fine-tune model parameters. Finally, the datasets with five fault patterns are collected to evaluate the performance of the DA-DBN. The results demonstrate that the proposed DA-DBN can achieve more than 92% fault classification accuracy under three noise levels; the average accuracy of fault classification under variable working conditions is 93.5%, which is the highest compared with other models.

[1]  Loris Nanni,et al.  Deep learning and transfer learning features for plankton classification , 2019, Ecol. Informatics.

[2]  Yang Zhang,et al.  Novel chaotic bat algorithm for forecasting complex motion of floating platforms , 2019, Applied Mathematical Modelling.

[3]  Jin Li,et al.  Differentially private Naive Bayes learning over multiple data sources , 2018, Inf. Sci..

[4]  Xiao‐Bi Xie,et al.  Frequency-domain full waveform inversion with an angle-domain wavenumber filter , 2017 .

[5]  Liu Zheng,et al.  MMDF-LDA: An improved Multi-Modal Latent Dirichlet Allocation model for social image annotation , 2018, Expert Syst. Appl..

[6]  Xipeng Shen,et al.  LCD: A Fast Contrastive Divergence Based Algorithm for Restricted Boltzmann Machine. , 2018, Neural networks : the official journal of the International Neural Network Society.

[7]  Dong-Joo Kim,et al.  Automated artifact elimination of physiological signals using a deep belief network: An application for continuously measured arterial blood pressure waveforms , 2018, Inf. Sci..

[8]  Teng Li,et al.  Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder , 2017 .

[9]  Jefersson Alex dos Santos,et al.  Towards better exploiting convolutional neural networks for remote sensing scene classification , 2016, Pattern Recognit..

[10]  Huawei Wang,et al.  Civil aviation safety evaluation based on deep belief network and principal component analysis , 2019, Safety Science.

[11]  Yan Zhang,et al.  Deep domain similarity Adaptation Networks for across domain classification , 2018, Pattern Recognit. Lett..

[12]  MengChu Zhou,et al.  TL-GDBN: Growing Deep Belief Network With Transfer Learning , 2019, IEEE Transactions on Automation Science and Engineering.

[13]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[14]  Nadir Durrani,et al.  Domain adaptation using neural network joint model , 2017, Comput. Speech Lang..

[15]  Zichen Zhang,et al.  Electric load forecasting by complete ensemble empirical mode decomposition adaptive noise and support vector regression with quantum-based dragonfly algorithm , 2019, Nonlinear Dynamics.

[16]  B. Piwakowski,et al.  Time domain model and experimental validation of non‐contact surface wave scanner , 2019, Ultrasonics.

[17]  A. Terry Bahill,et al.  Preprocessing methods in the computation of the fast Fourier transform , 1991 .

[18]  K. Loparo,et al.  HMM-Based Fault Detection and Diagnosis Scheme for Rolling Element Bearings , 2005 .

[19]  Hee-Jun Kang,et al.  A survey on Deep Learning based bearing fault diagnosis , 2019, Neurocomputing.

[20]  Zhiqiang Chen,et al.  Deep neural networks-based rolling bearing fault diagnosis , 2017, Microelectron. Reliab..

[21]  Haiyang Pan,et al.  Sigmoid-based refined composite multiscale fuzzy entropy and t-SNE based fault diagnosis approach for rolling bearing , 2018, Measurement.

[22]  Faisal Mahmood,et al.  Deep learning and conditional random fields‐based depth estimation and topographical reconstruction from conventional endoscopy , 2017, Medical Image Anal..

[23]  Nacer Hamzaoui,et al.  Semi-automated diagnosis of bearing faults based on a hidden Markov model of the vibration signals , 2018, Measurement.

[24]  Oral Büyüköztürk,et al.  Conditional classifiers and boosted conditional Gaussian mixture model for novelty detection , 2018, Pattern Recognit..

[25]  Dan Guo,et al.  Research on intelligent fault diagnosis method for nuclear power plant based on correlation analysis and deep belief network , 2018, Progress in Nuclear Energy.

[26]  Victor Fernando Gómez Comendador,et al.  Energy Efficient GNSS Signal Acquisition Using Singular Value Decomposition (SVD) , 2018, Sensors.

[27]  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 .

[28]  Xuelong Li,et al.  Deep neural networks with Elastic Rectified Linear Units for object recognition , 2018, Neurocomputing.

[29]  Kunikazu Kobayashi,et al.  Time series forecasting using a deep belief network with restricted Boltzmann machines , 2014, Neurocomputing.

[30]  Hee-Jun Kang,et al.  Rolling element bearing fault diagnosis using convolutional neural network and vibration image , 2019, Cognitive Systems Research.

[31]  Lunke Fei,et al.  Robust Sparse Linear Discriminant Analysis , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[32]  Cheng Wang,et al.  Accelerated stochastic gradient descent with step size selection rules , 2019, Signal Process..

[33]  Gao Lin,et al.  Fault Diagnosis and Location Method for Active Distribution Network Based on Artificial Neural Network , 2018 .

[34]  W. Sandberg,et al.  Implementation and Evaluation of the Z-Score System for Normalizing Residency Evaluations , 2018, Anesthesiology.

[35]  Xiang Li,et al.  Cross-Domain Fault Diagnosis of Rolling Element Bearings Using Deep Generative Neural Networks , 2019, IEEE Transactions on Industrial Electronics.

[36]  Wei Zhang,et al.  Multi-Layer domain adaptation method for rolling bearing fault diagnosis , 2019, Signal Process..

[37]  Jie Lin,et al.  Analysis and Simulation of Capacitor-Less ReRAM-Based Stochastic Neurons for the in-Memory Spiking Neural Network , 2018, IEEE Transactions on Biomedical Circuits and Systems.

[38]  Jun He,et al.  Unsupervised Fault Diagnosis of a Gear Transmission Chain Using a Deep Belief Network , 2017, Sensors.

[39]  Fan Xu,et al.  Roller bearing fault diagnosis using stacked denoising autoencoder in deep learning and Gath-Geva clustering algorithm without principal component analysis and data label , 2018, Appl. Soft Comput..

[40]  Kaixiang Peng,et al.  A Deep Belief Network-based Fault Detection Method for Nonlinear Processes , 2018 .

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

[42]  Muhammad A. Rushdi,et al.  Classification of scaled texture patterns with transfer learning , 2019, Expert Syst. Appl..

[43]  Giancarlo Fortino,et al.  Human emotion recognition using deep belief network architecture , 2019, Inf. Fusion.

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

[45]  Stéphane Marchand-Maillet,et al.  Inductive t-SNE via deep learning to visualize multi-label images , 2019, Eng. Appl. Artif. Intell..

[46]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

[47]  Xiaoxia Qi,et al.  Deep belief network based k-means cluster approach for short-term wind power forecasting , 2018, Energy.