Chinese Journal of Mechanical Engineering >

2021 , Vol. 34 >Issue 3: 62 - 62

DOI: https://doi.org/10.1186/s10033-021-00576-1

Special Issue on AI-Enabled Monitoring Diagnosis & Prognosis

Deep Spatiotemporal Convolutional-Neural-Network-Based Remaining Useful Life Estimation of Bearings

  • Xu Wang ,
  • Tianyang Wang ,
  • Anbo Ming ,
  • Qinkai Han ,
  • Fulei Chu ,
  • Wei Zhang ,
  • Aihua Li
展开
  • 1. State Key Laboratory of Tribology, Tsinghua University, Beijing 100084, China;
    2. High-Tech Research Institute of Xi'an, Xi'an 710025, China

收稿日期: 2020-11-05

  修回日期: 2021-04-29

  网络出版日期: 2021-12-21

基金资助

Supported by National Key Research and Development Project of China (Grant No. 2020YFB2007700), State Key Laboratory of Tribology Initiative Research Program (Grant No. SKLT2020D21), National Natural Science Foundation of China (Grant No. 51975309), Shaanxi Provincial Natural Science Foundation of China (Grant No. 2019JQ-712), and Young Talent Fund of University Association for Science and Technology in Shaanxi (Grant No. 20170511)

收起

Deep Spatiotemporal Convolutional-Neural-Network-Based Remaining Useful Life Estimation of Bearings

  • Xu Wang ,
  • Tianyang Wang ,
  • Anbo Ming ,
  • Qinkai Han ,
  • Fulei Chu ,
  • Wei Zhang ,
  • Aihua Li
Expand
  • 1. State Key Laboratory of Tribology, Tsinghua University, Beijing 100084, China;
    2. High-Tech Research Institute of Xi'an, Xi'an 710025, China

Received date: 2020-11-05

  Revised date: 2021-04-29

  Online published: 2021-12-21

Supported by

Supported by National Key Research and Development Project of China (Grant No. 2020YFB2007700), State Key Laboratory of Tribology Initiative Research Program (Grant No. SKLT2020D21), National Natural Science Foundation of China (Grant No. 51975309), Shaanxi Provincial Natural Science Foundation of China (Grant No. 2019JQ-712), and Young Talent Fund of University Association for Science and Technology in Shaanxi (Grant No. 20170511)

Fold

摘要

The remaining useful life (RUL) estimation of bearings is critical for ensuring the reliability of mechanical systems. Owing to the rapid development of deep learning methods, a multitude of data-driven RUL estimation approaches have been proposed recently. However, the following problems remain in existing methods: 1) Most network models use raw data or statistical features as input, which renders it difficult to extract complex fault-related information hidden in signals; 2) for current observations, the dependence between current states is emphasized, but their complex dependence on previous states is often disregarded; 3) the output of neural networks is directly used as the estimated RUL in most studies, resulting in extremely volatile prediction results that lack robustness. Hence, a novel prognostics approach is proposed based on a time-frequency representation (TFR) subsequence, three-dimensional convolutional neural network (3DCNN), and Gaussian process regression (GPR). The approach primarily comprises two aspects: construction of a health indicator (HI) using the TFR-subsequence-3DCNN model, and RUL estimation based on the GPR model. The raw signals of the bearings are converted into TFR-subsequences by continuous wavelet transform and a dislocated overlapping strategy. Subsequently, the 3DCNN is applied to extract the hidden spatiotemporal features from the TFR-subsequences and construct HIs. Finally, the RUL of the bearings is estimated using the GPR model, which can also define the probability distribution of the potential function and prediction confidence. Experiments on the PRONOSTIA platform demonstrate the superiority of the proposed TFR-subsequence-3DCNN-GPR approach. The use of degradation-related spatiotemporal features in signals is proposed herein to achieve a highly accurate bearing RUL prediction with uncertainty quantification.

关键词： Bearing; Remaining useful life; Continuous wavelet transform; Convolution neural network; Gaussian process regression

本文引用格式

Xu Wang , Tianyang Wang , Anbo Ming , Qinkai Han , Fulei Chu , Wei Zhang , Aihua Li . Deep Spatiotemporal Convolutional-Neural-Network-Based Remaining Useful Life Estimation of Bearings[J]. Chinese Journal of Mechanical Engineering, 2021 , 34(3) : 62 -62 . DOI: 10.1186/s10033-021-00576-1

Abstract

The remaining useful life (RUL) estimation of bearings is critical for ensuring the reliability of mechanical systems. Owing to the rapid development of deep learning methods, a multitude of data-driven RUL estimation approaches have been proposed recently. However, the following problems remain in existing methods: 1) Most network models use raw data or statistical features as input, which renders it difficult to extract complex fault-related information hidden in signals; 2) for current observations, the dependence between current states is emphasized, but their complex dependence on previous states is often disregarded; 3) the output of neural networks is directly used as the estimated RUL in most studies, resulting in extremely volatile prediction results that lack robustness. Hence, a novel prognostics approach is proposed based on a time-frequency representation (TFR) subsequence, three-dimensional convolutional neural network (3DCNN), and Gaussian process regression (GPR). The approach primarily comprises two aspects: construction of a health indicator (HI) using the TFR-subsequence-3DCNN model, and RUL estimation based on the GPR model. The raw signals of the bearings are converted into TFR-subsequences by continuous wavelet transform and a dislocated overlapping strategy. Subsequently, the 3DCNN is applied to extract the hidden spatiotemporal features from the TFR-subsequences and construct HIs. Finally, the RUL of the bearings is estimated using the GPR model, which can also define the probability distribution of the potential function and prediction confidence. Experiments on the PRONOSTIA platform demonstrate the superiority of the proposed TFR-subsequence-3DCNN-GPR approach. The use of degradation-related spatiotemporal features in signals is proposed herein to achieve a highly accurate bearing RUL prediction with uncertainty quantification.

Key words： Bearing; Remaining useful life; Continuous wavelet transform; Convolution neural network; Gaussian process regression

参考文献

[1] M F Li, T Y Wang, F L Chu, et al. Component matching Chirplet transform via frequency-dependent chirp rate for wind turbine planetary gearbox fault diagnostics under variable speed condition. Mechanical Systems and Signal Processing, 2021, 161: 107997.
[2] T Han, C Liu, L J Wu, et al. An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems. Mechanical Systems and Signal Processing, 2019, 117: 170-187.
[3] F B Zhang, J F Huang, F L Chu, et al. Mechanism and method for the full-scale quantitative diagnosis of ball bearings with an inner race fault. Journal of Sound and Vibration, 2020, 488: 115641.
[4] J Lee, F J Wu, W Y Zhao, et al. Prognostics and health management design for rotary machinery systems - Reviews, methodology and applications. Mechanical Systems and Signal Processing, 2014, 42: 314-334.
[5] Y F Li, M J Zuo, K Feng, et al. Detection of bearing faults using a novel adaptive morphological update lifting wavelet. Chinese Journal of Mechanical Engineering, 2017, 30: 1305-1313.
[6] Y G Lei, N P Li, L Guo, et al. Machinery health prognostics: A systematic review from data acquisition to RUL prediction. Mechanical Systems and Signal Processing, 2018, 104: 799-834.
[7] K S Singleton, E G Strangas, S Aviyente. The use of bearing currents and vibrations in lifetime estimation of bearings. IEEE Transactions on Industrial Informatics, 2017, 13: 1301-1309.
[8] S Kerst, B Shyrokau, E Holweg. A model-based approach for the estimation of bearing forces and moments using outer ring deformation. IEEE Transactions on Industrial Electronics, 2020, 67: 461-470.
[9] M Cerrada, R V Sánchez, C Li, et al. A review on data-driven fault severity assessment in rolling bearings. Mechanical Systems and Signal Processing, 2018, 99: 169-196.
[10] T S Liu, K P Zhu, L C Zeng. Diagnosis and prognosis of degradation process via hidden semi-Markov model. IEEE/ASME Transactions on Mechatronics, 2018, 23: 1456-1466.
[11] L L Cui, X Wang, Y G Xu, et al. A novel switching unscented Kalman filter method for remaining useful life prediction of rolling bearing. Measurement, 2019, 135: 678-684.
[12] X S Si, W B Wang, C H Hu, et al. A Wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation. Mechanical Systems and Signal Processing, 2013, 35: 219-237.
[13] Y G Lei, N P Li, S Gontarz, et al. A model-based method for remaining useful life prediction of machinery. IEEE Transaction on Reliability, 2016, 65: 1314-1326.
[14] D Wang, K L Tsui, Q Miao. Prognostics and health management: A review of vibration based bearing and gear health indicators. IEEE Access, 2017, 6: 665-676.
[15] D Z Zhao, L Y Li, W D Cheng, et al. Generalized demodulation transform for bearing fault diagnosis under nonstationary conditions and gear noise interferences. Chinese Journal of Mechanical Engineering, 2019, 32: 7.
[16] R N Liu, B Y Yang, E Zio, et al. Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 2018, 108: 33-47.
[17] L Liu, X Song, K Chen, et al. An enhanced encoder-decoder framework for bearing remaining useful life prediction. Measurement, 2021, 170: 108753.
[18] C H Hu, H Pei, X S Si, et al. A prognostic model based on DBN and diffusion process for degrading bearing. IEEE Transactions on Industrial Electronics, 2020, 67 (10): 8767-8777.
[19] H Wang, M J Peng, Z Miao, et al. Remaining useful life prediction techniques for electric valves based on convolution auto encoder and long short term memory. ISA Transactions, 2021, 108: 3333-3342.
[20] Y H Chen, G L Peng, Z Y Zhu, et al. A novel deep learning method based on attention mechanism for bearing remaining useful life prediction. Applied Soft Computing Journal, 2020, 86: 105919.
[21] B Zhang, S H Zhang, W H Li. Bearing performance degradation assessment using long short-term memory recurrent network. Computers in Industry, 2019, 106: 14-29.
[22] J Zhu, N Chen, W Peng. Estimation of bearing remaining useful life based on multiscale convolutional neural network. IEEE Transactions on Industrial Electronics, 2019, 66: 3208-3216.
[23] M F Li, T Y Wang, F L Chu, et al. Scaling-basis Chirplet transform. IEEE Transactions on Industrial Electronics, 2021, doi: https://doi.org/10.1109/TIE.2020.3013537.
[24] H Huang, N Baddour, M Liang. Bearing fault diagnosis under unknown time-varying rotational speed conditions via multiple time-frequency curve extraction. Journal of Sound and Vibration, 2018, 414: 43-60.
[25] R Klein, E Masad, E Rudyk, et al. Bearing diagnostics using image processing methods. Mechanical Systems and Signal Processing, 2014, 45: 105-113.
[26] J J Shi, M Liang, D S Necsulescu, et al. Generalized stepwise demodulation transform and synchrosqueezing for time - frequency analysis and bearing fault diagnosis. Journal of Sound and Vibration, 2016, 368: 202-222.
[27] B Wang, Y G Lei, T Yan, et al. Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery. Neurocomputing, 2020, 379: 117-129.
[28] Z S Chen, X T Tu, Y Hu, et al. Real-time bearing remaining useful life estimation based on the frozen convolutional and activated memory neural network. IEEE Access, 7, 2019: 96583-96593.
[29] B Wang, Y G Lei, N P Li, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Transactions on Reliability, 2020, 69(1): 401-412.
[30] D Wang, P W Tse. Prognostics of slurry pumps based on a moving-average wear degradation index and a general sequential Monte Carlo method. Mechanical Systems and Signal Processing, 2015, 56: 213-229.
[31] K P Zhu, T S Liu. Online tool wear monitoring via hidden semi-Markov model with dependent durations. IEEE Transactions on Industrial Informatics, 2018, 14: 69-78.
[32] S W Ji, W Xu, M Yang, et al. 3D Convolutional neural networks for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35: 221-231.
[33] Ł Jedlińki, J Jonak. Early fault detection in gearboxes based on support vector machines and multilayer perceptron with a continuous wavelet transform. Applied Soft Computing Journal, 2015, 30: 636-641.
[34] S Qian, H Liu, C Liu, et al. Adaptive activation functions in convolutional neural networks. Neurocomputing, 2018, 272: 204-212.
[35] F Kang, S X Han, S Salgado, et al. System probabilistic stability analysis of soil slopes using Gaussian process regression with Latin hypercube sampling. Computers and Geotechnics, 2015, 63: 13-25.
[36] L L Kang, R S Chen, N X Xiong, et al. Selecting hyper-parameters of Gaussian process regression based on non-inertial particle swarm optimization in Internet of Things. IEEE Access, 7, 2019: 59504-59513.
[37] P Nectoux, R Gouriveau, K Medjaher, et al. PRONOSTIA: An experimental platform for bearings accelerated degradation tests. PHM'12, United States: Denver, Colorado, 2012, 1-8.
[38] T P Le. Use of the Morlet mother wavelet in the frequency-scale domain decomposition technique for the modal identification of ambient vibration responses. Mechanical Systems and Signal Processing, 2017, 95, 488-505.
[39] M Mastyło. Bilinear interpolation theorems and applications. Journal of Functional Analysis, 2013, 265: 185-207.
[40] J J Wang, J X Yan, C Li, et al. Deep heterogeneous GRU model for predictive analytics in smart manufacturing: Application to tool wear prediction. Computers in Industry, 2019, 111: 1-14.
[41] K J Ashok, S Abirami. Aspect-based opinion ranking framework for product reviews using a Spearman's rank correlation coefficient method. Information Sciences, 2018, 460-461: 23-41.
[42] J Coble, J W Hines. Identifying optimal prognostic parameters from data: A genetic algorithms approach. Annual Conference of the Prognostics and Health Management Society, San Diego, CA, 2009, 1-11.
Options
文章导航

/

〈 〉

版权所有 © 《Chinese Journal of Mechanical Engineering》编辑部

技术支持：北京玛格泰克科技发展有限公司