A novel method for journal bearing degradation evaluation and remaining useful life prediction under different working conditions

Abstract Accurate bearing degradation performance analysis and remaining useful life (RUL) prediction are significant to prevent major accidents and economic losses in industry. Data-driven methods have emerged as reliable algorithms for RUL prediction. These existing approaches assume that the training (source) and testing (target) samples have the same probability distribution. However, the obtained run-to-failure datasets with different work conditions are usually from different domains. The distribution discrepancy between the source and target domain will reduce the accuracy of RUL prediction models when only source domain data in one working condition is trained. To solve the problem, this paper proposes a novel transfer learning method for journal bearing RUL prediction under different work conditions based on the LSTM-DNN network with domain adaptation. The multi-sensor run-to-failure datasets of journal bearings are collected and the extracted multi-sensor features are used for degradation assessment through the fuzzy c-means (FCM) clustering algorithm and the determination of degradation occurrence time (DOT). The multi-sensor feature representations and RUL values after DOT are used to validate the effectiveness of the proposed model. The results show that the proposed method has higher accuracy in journal bearing RUL prediction under different work conditions and outperforms other transfer learning approaches.

[1]  Wentao Mao,et al.  Predicting Remaining Useful Life of Rolling Bearings Based on Deep Feature Representation and Transfer Learning , 2020, IEEE Transactions on Instrumentation and Measurement.

[2]  Michael I. Jordan,et al.  Learning with Mixtures of Trees , 2001, J. Mach. Learn. Res..

[3]  J. C. Dunn,et al.  A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters , 1973 .

[4]  Sanjay H Upadhyay,et al.  Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering , 2017 .

[5]  M. A. Djeziri,et al.  Hybrid method for remaining useful life prediction in wind turbine systems , 2018 .

[6]  Cheng Han,et al.  Transferable convolutional neural network based remaining useful life prediction of bearing under multiple failure behaviors , 2021, Measurement.

[7]  Jie Chen,et al.  Degradation evaluation of slewing bearing using HMM and improved GRU , 2019, Measurement.

[8]  N. Tandon,et al.  Detection of particle contamination in journal bearing using acoustic emission and vibration monitoring techniques , 2019, Tribology International.

[9]  M. S. Safizadeh,et al.  Prediction of oil whirl initiation in journal bearings using multi-sensors data fusion , 2020 .

[10]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[11]  Wang Heng,et al.  Research on rolling bearing state health monitoring and life prediction based on PCA and Internet of things with multi-sensor , 2020, Measurement.

[12]  Mohamed Tkiouat,et al.  Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network , 2018 .

[13]  Jin Cui,et al.  Multi-bearing remaining useful life collaborative prediction: A deep learning approach , 2017 .

[15]  Cong Wang,et al.  A diagnosis framework based on domain adaptation for bearing fault diagnosis across diverse domains. , 2020, ISA transactions.

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

[17]  Z. Yin,et al.  Simulation and experimental verification of fatigue strength evaluation of journal bearing bush , 2020 .

[18]  Lei Ren,et al.  Bearing remaining useful life prediction based on deep autoencoder and deep neural networks , 2018, Journal of Manufacturing Systems.

[19]  Hui Li,et al.  A prediction method for the real-time remaining useful life of wind turbine bearings based on the Wiener process , 2018, Renewable Energy.

[20]  Yu Wang,et al.  Hybrid adversarial network for unsupervised domain adaptation , 2020, Inf. Sci..

[21]  Ke Zhao,et al.  An adaptive deep transfer learning method for bearing fault diagnosis , 2020 .

[22]  Ning Ding,et al.  Journal bearing seizure degradation assessment and remaining useful life prediction based on long short-term memory neural network , 2020 .

[23]  Brigitte Chebel-Morello,et al.  Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network , 2015 .

[24]  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.

[25]  Xu Li,et al.  Deep learning-based adversarial multi-classifier optimization for cross-domain machinery fault diagnostics , 2020 .

[26]  Liang Guo,et al.  A recurrent neural network based health indicator for remaining useful life prediction of bearings , 2017, Neurocomputing.

[27]  Jun Zhu,et al.  A new data-driven transferable remaining useful life prediction approach for bearing under different working conditions , 2020 .

[28]  Jinrui Wang,et al.  A novel bearing intelligent fault diagnosis framework under time-varying working conditions using recurrent neural network. , 2019, ISA transactions.

[29]  Junsheng Cheng,et al.  An improved deep convolutional neural network with multi-scale information for bearing fault diagnosis , 2019, Neurocomputing.

[30]  Rongjing Hong,et al.  HYGP-MSAM based model for slewing bearing residual useful life prediction , 2019, Measurement.

[31]  Peng Wang,et al.  Long short-term memory for machine remaining life prediction , 2018, Journal of Manufacturing Systems.

[32]  Rongjing Hong,et al.  Reliability-based residual life prediction of large-size low-speed slewing bearings , 2014 .

[33]  Uzay Kaymak,et al.  Remaining Useful Lifetime Prediction via Deep Domain Adaptation , 2019, Reliab. Eng. Syst. Saf..

[34]  Yuxin Cui,et al.  Transfer Learning with Deep Recurrent Neural Networks for Remaining Useful Life Estimation , 2018, Applied Sciences.

[35]  Fulei Chu,et al.  Deep convolutional neural network based planet bearing fault classification , 2019, Comput. Ind..

[36]  Brigitte Chebel-Morello,et al.  PRONOSTIA : An experimental platform for bearings accelerated degradation tests. , 2012 .

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

[38]  Ruqiang Yan,et al.  A sparse auto-encoder-based deep neural network approach for induction motor faults classification , 2016 .

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

[40]  Mengchen Shan,et al.  A new wind turbine health condition monitoring method based on VMD-MPE and feature-based transfer learning , 2019 .

[41]  Fan Xu,et al.  An unsupervised and enhanced deep belief network for bearing performance degradation assessment , 2020 .

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

[43]  Bing Wang,et al.  Rolling bearing performance degradation condition recognition based on mathematical morphological fractal dimension and fuzzy C-means , 2017 .

[44]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[45]  Koby Crammer,et al.  A theory of learning from different domains , 2010, Machine Learning.

[46]  Zhibin Zhao,et al.  Deep Transfer Learning Based on Sparse Autoencoder for Remaining Useful Life Prediction of Tool in Manufacturing , 2019, IEEE Transactions on Industrial Informatics.

[47]  Yang Yang,et al.  Fault diagnosis of rolling bearing of wind turbines based on the Variational Mode Decomposition and Deep Convolutional Neural Networks , 2020, Appl. Soft Comput..

[48]  Jingjing Li,et al.  Joint metric and feature representation learning for unsupervised domain adaptation , 2020, Knowl. Based Syst..

[49]  S. M. Jafari,et al.  Bearing remaining useful life prediction under starved lubricating condition using time domain acoustic emission signal processing , 2021, Expert Syst. Appl..