A novel deep learning method based on attention mechanism for bearing remaining useful life prediction

Abstract Rolling bearing is a key component in rotation machine, whose remaining useful life (RUL) prediction is an essential issue of constructing condition-based maintenance (CBM) system. However, recent data-driven approaches for bearing RUL prediction still require prior knowledge to extract features, construct health indicate (HI) and set up threshold, which is inefficient in the big data era. In this paper, a pure data-driven method for bearing RUL prediction with little prior knowledge is proposed. This method includes three steps, i.e., features extraction, HI prediction and RUL calculation. In the first step, five band-pass energy values of frequency spectrum are extracted as features. Then, a recurrent neural network based on encoder–decoder framework with attention mechanism is proposed to predict HI values, which are designed closely related with the RUL values in this paper. Finally, the final RUL value can be obtained via linear regression. Experiments carried out on the dataset from PRONOSTIA and comparison with other novel approaches demonstrate that the proposed method achieves a better performance.

[1]  Donghua Zhou,et al.  Remaining useful life estimation - A review on the statistical data driven approaches , 2011, Eur. J. Oper. Res..

[2]  Yaguo Lei,et al.  Condition monitoring and fault diagnosis of planetary gearboxes: A review , 2014 .

[3]  Yoshua Bengio,et al.  On Using Very Large Target Vocabulary for Neural Machine Translation , 2014, ACL.

[4]  Ruqiang Yan,et al.  Machine health monitoring with LSTM networks , 2016, 2016 10th International Conference on Sensing Technology (ICST).

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

[6]  Huijun Gao,et al.  A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis , 2019, Neurocomputing.

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

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

[9]  Lifeng Xi,et al.  Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods , 2007 .

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  Dong Yu,et al.  Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[12]  Li Lin,et al.  Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network , 2016, 2016 IEEE International Conference on Aircraft Utility Systems (AUS).

[13]  Theodoros H. Loutas,et al.  Remaining Useful Life Estimation in Rolling Bearings Utilizing Data-Driven Probabilistic E-Support Vectors Regression , 2013, IEEE Transactions on Reliability.

[14]  Zhu Huijie,et al.  Fault diagnosis of hydraulic pump based on stacked autoencoders , 2015, 2015 12th IEEE International Conference on Electronic Measurement & Instruments (ICEMI).

[15]  Yoshua Bengio,et al.  Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription , 2012, ICML.

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

[17]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[18]  Wei Zhang,et al.  ACDIN: Bridging the gap between artificial and real bearing damages for bearing fault diagnosis , 2018, Neurocomputing.

[19]  Yaguo Lei,et al.  Machinery health prognostics: A systematic review from data acquisition to RUL prediction , 2018 .

[20]  Yann LeCun,et al.  Recurrent Orthogonal Networks and Long-Memory Tasks , 2016, ICML.

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

[23]  Yaguo Lei,et al.  A Model-Based Method for Remaining Useful Life Prediction of Machinery , 2016, IEEE Transactions on Reliability.

[24]  Bin Zhang,et al.  Machine Condition Prediction Based on Adaptive Neuro–Fuzzy and High-Order Particle Filtering , 2011, IEEE Transactions on Industrial Electronics.

[25]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[26]  Jie Liu,et al.  An Enhanced Diagnostic Scheme for Bearing Condition Monitoring , 2010, IEEE Transactions on Instrumentation and Measurement.

[27]  Liang Guo,et al.  Multifeatures Fusion and Nonlinear Dimension Reduction for Intelligent Bearing Condition Monitoring , 2016 .

[28]  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.

[29]  Noureddine Zerhouni,et al.  Particle filter-based prognostics: Review, discussion and perspectives , 2016 .

[30]  Robert X. Gao,et al.  Prognosis of Defect Propagation Based on Recurrent Neural Networks , 2011, IEEE Transactions on Instrumentation and Measurement.

[31]  Hong-Hee Lee,et al.  Probabilistic frequency-domain discrete wavelet transform for better detection of bearing faults in induction motors , 2016, Neurocomputing.

[32]  Nishchal K. Verma,et al.  Intelligent condition based monitoring of rotating machines using sparse auto-encoders , 2013, 2013 IEEE Conference on Prognostics and Health Management (PHM).

[33]  M. Pecht,et al.  Estimation of remaining useful life of ball bearings using data driven methodologies , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[34]  Shaohui Liu,et al.  Bearing Fault Diagnosis Using Fully-Connected Winner-Take-All Autoencoder , 2018, IEEE Access.

[35]  Enrico Zio,et al.  Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method , 2014, Digit. Signal Process..

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

[37]  Noureddine Zerhouni,et al.  Degradations analysis and aging modeling for health assessment and prognostics of PEMFC , 2016, Reliab. Eng. Syst. Saf..

[38]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[39]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[40]  Guanghua Xu,et al.  Rotating speed isolation and its application to rolling element bearing fault diagnosis under large speed variation conditions , 2015 .

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

[42]  Weiwen Peng,et al.  Estimation of Bearing Remaining Useful Life Based on Multiscale Convolutional Neural Network , 2019, IEEE Transactions on Industrial Electronics.

[43]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.