Unsupervised machine fault diagnosis for noisy domain adaptation using marginal denoising autoencoder based on acoustic signals

Abstract Recently, with the desperate demand for data-driven deep learning methods in practical industrial applications, increasing popularity of deep learning methods for machine fault diagnosis under noisy environments has been observed. However, the existing studies have encountered two limitations: 1) the domain shift problem has not been researched enough to ensure a functional adaptation model across different noisy domains; 2) those deep learning frameworks are generally complicated and require massive computational space. To address those problems, we propose a Noisy Domain Adaptive marginal Stacking Denoising Auto-encoder (NDAmSDA) based on acoustic signals for domain adaptation between different noise levels. Specifically, a modified mSDA, integrated with a dimensionality reduction method based on Transfer Component Analysis (TCA), not only facilitates the training acceleration by replacing the traditional gradient descent method of backpropagation with a forward closed-form solution, but also promotes gapping the discrepancy between various noise levels and transferring the classifier built from one noisy domain to others. This enables us to extend diagnostic models’ capability to real-world scenarios because of the unavoidable background noise in the collected signals. To validate the effectiveness of our proposed approach, datasets mixed with additive white Gaussian noise (AWGN) and binary masking noise (BMN) from the gear tests and motor tests are constructed for validation. Comparisons with representative and popular fault diagnosis approaches confirm the superiority of the proposed method.

[1]  Chen Lu,et al.  Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification , 2017, Signal Process..

[2]  Xu Li,et al.  A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning , 2021 .

[3]  Jianyu Long,et al.  Attitude data-based deep hybrid learning architecture for intelligent fault diagnosis of multi-joint industrial robots , 2020 .

[4]  Biao Wang,et al.  LiftingNet: A Novel Deep Learning Network With Layerwise Feature Learning From Noisy Mechanical Data for Fault Classification , 2018, IEEE Transactions on Industrial Electronics.

[5]  Jiawei Xiang,et al.  Latest developments in gear defect diagnosis and prognosis: A review , 2020 .

[6]  Haidong Shao,et al.  Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing , 2018 .

[7]  Dong Wang,et al.  Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis , 2018, Neurocomputing.

[8]  Yixiang Huang,et al.  Unsupervised deep representation learning for motor fault diagnosis by mutual information maximization , 2020, Journal of Intelligent Manufacturing.

[9]  Yixiang Huang,et al.  Domain Adaptive Motor Fault Diagnosis Using Deep Transfer Learning , 2019, IEEE Access.

[10]  Yanrui Jin,et al.  Precise cutterhead torque prediction for shield tunneling machines using a novel hybrid deep neural network , 2021 .

[11]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[12]  Shunming Li,et al.  General normalized sparse filtering: A novel unsupervised learning method for rotating machinery fault diagnosis , 2019, Mechanical Systems and Signal Processing.

[13]  Cong Wang,et al.  A novel bearing fault diagnosis method based on 2D image representation and transfer learning-convolutional neural network , 2019, Measurement Science and Technology.

[14]  Yixiang Huang,et al.  Actual bearing compound fault diagnosis based on active learning and decoupling attentional residual network , 2020 .

[15]  Feng Jia,et al.  An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data , 2016, IEEE Transactions on Industrial Electronics.

[16]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

[17]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[18]  Zepeng Liu,et al.  A review of failure modes, condition monitoring and fault diagnosis methods for large-scale wind turbine bearings , 2020 .

[19]  Yaguo Lei,et al.  Applications of machine learning to machine fault diagnosis: A review and roadmap , 2020 .

[20]  Qi Jin,et al.  Planetary gearbox fault feature learning using conditional variational neural networks under noise environment , 2019, Knowl. Based Syst..

[21]  Bin Yang,et al.  An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings , 2019, Mechanical Systems and Signal Processing.

[22]  Chengjin Qin,et al.  A novel Chebyshev-wavelet-based approach for accurate and fast prediction of milling stability , 2020 .

[23]  Sung-Jin Song,et al.  Convolutional neural network for ultrasonic weldment flaw classification in noisy conditions. , 2019, Ultrasonics.

[24]  Wei Zhang,et al.  A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals , 2017, Sensors.

[25]  Hans-Peter Kriegel,et al.  Integrating structured biological data by Kernel Maximum Mean Discrepancy , 2006, ISMB.

[26]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[27]  Jianjun Hu,et al.  End-To-End Convolutional Neural Network Model for Gear Fault Diagnosis Based on Sound Signals , 2018, Applied Sciences.

[28]  Philip S. Yu,et al.  Transfer Feature Learning with Joint Distribution Adaptation , 2013, 2013 IEEE International Conference on Computer Vision.

[29]  Ming J. Zuo,et al.  Atomic decomposition and sparse representation for complex signal analysis in machinery fault diagnosis: A review with examples , 2017 .

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

[31]  Chengjin Qin,et al.  Timely chatter identification for robotic drilling using a local maximum synchrosqueezing-based method , 2019, J. Intell. Manuf..

[32]  Jiayu Jiang,et al.  Multisensor bearing fault diagnosis based on one-dimensional convolutional long short-term memory networks , 2020 .

[33]  Chengjin Qin,et al.  A pre-generated matrix-based method for real-time robotic drilling chatter monitoring , 2019 .

[34]  Chao Liu,et al.  Learning transferable features in deep convolutional neural networks for diagnosing unseen machine conditions. , 2019, ISA transactions.

[35]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[36]  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.

[37]  Yaguo Lei,et al.  Deep Convolutional Transfer Learning Network: A New Method for Intelligent Fault Diagnosis of Machines With Unlabeled Data , 2019, IEEE Transactions on Industrial Electronics.

[38]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[39]  Yide Wang,et al.  A Sparse Autoencoder and Softmax Regression Based Diagnosis Method for the Attachment on the Blades of Marine Current Turbine , 2018, Sensors.

[40]  Chengjin Qin,et al.  Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN , 2019, Shock and Vibration.

[41]  Tian Ran Lin,et al.  A consistency regularization based semi-supervised learning approach for intelligent fault diagnosis of rolling bearing , 2020 .

[42]  Robert X. Gao,et al.  Deep learning and its applications to machine health monitoring , 2019, Mechanical Systems and Signal Processing.

[43]  Qicai Zhou,et al.  Fault Diagnosis of Rotating Machinery under Noisy Environment Conditions Based on a 1-D Convolutional Autoencoder and 1-D Convolutional Neural Network , 2019, Sensors.

[44]  Jian Sun,et al.  Convolutional neural networks at constrained time cost , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  T. Lin,et al.  Simulation data driven weakly supervised adversarial domain adaptation approach for intelligent cross-machine fault diagnosis , 2020 .

[46]  Jing Li,et al.  An enhancement denoising autoencoder for rolling bearing fault diagnosis , 2018, Measurement.

[47]  Ying Zhang,et al.  Fault diagnosis of reciprocating compressor using a novel ensemble empirical mode decomposition-convolutional deep belief network , 2020 .

[48]  Zhengjia He,et al.  A novel intelligent gear fault diagnosis model based on EMD and multi-class TSVM , 2012 .

[49]  Peng Fan,et al.  A sparse stacked denoising autoencoder with optimized transfer learning applied to the fault diagnosis of rolling bearings , 2019, Measurement.

[50]  Zhiyu Liu,et al.  Transfer learning with convolutional neural networks for small sample size problem in machinery fault diagnosis , 2019, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science.

[51]  Jianyu Long,et al.  Evolving Deep Echo State Networks for Intelligent Fault Diagnosis , 2020, IEEE Transactions on Industrial Informatics.