Predicting Remaining Useful Life of Rolling Bearings Based on Reliable Degradation Indicator and Temporal Convolution Network with the Quantile Regression
Abstract
:1. Introduction
- (1)
- The original features are compressed and reconstructed based on the SDAE compression method to obtain low-dimensional representative features and retain sufficient information on the premise of not increasing the size of the neural network.
- (2)
- The redundancy, correlation, and monotonicity measures were incorporated into the DI selection criteria. The sensitivity standard of DI is redefined to further reduce the dimension of input feature variables on the premise of ensuring the efficiency of DI set.
- (3)
- Combining TCN with QR, a probability density prediction method based on TCNQR is proposed to obtain the predicted value of bearings RUL probability density, obtain more comprehensive and effective information of bearings degradation state, and further reflect the uncertainty of bearings RUL, so as to guide the equipment maintenance decision of actual production and manufacturing activities and avoid large errors and economic losses.
2. Basic Theory
2.1. Basic Theory of SAE
- (1)
- Let
- (2)
- Calculate
- (3)
- (4)
- (5)
- , where is the learning rate.
2.2. Basic Theory of Quantile Regression
3. Methodology
- (1)
- bearing operation state data acquisition;
- (2)
- Representative feature extraction of bearing running state information;
- (3)
- Predictive modeling;
- (4)
- RUL prediction.
3.1. Feature Extraction
3.2. Feature Compression
3.3. Feature Fusion
Optimal DI Set Construction
Algorithm 1 Optimal DI construction method. |
Input: The de-redundant feature subset , feature subset , real RUL value R, m is the number of features in the subset . Output: optimal DI set .
|
3.4. Quantile Regression of Temporal Convolution Network (TCNQR)
3.5. Kernel Density Estimation (KDE)
3.6. Prediction Accuracy Measures
- (1)
- Mean absolute error (MAE)
- (2)
- Root mean square error (RMSE)n is the number of prediction points, is the real RUL of the sample, is the predicted value.
- (3)
- ReliabilityPrediction interval coverage probability (PICP) is usually used to evaluate the accuracy of prediction interval. It is composed of upper bound and lower bound of coverage target value.A larger value means that more target values fall within the constructed prediction interval. n is the number of prediction points, is the coverage of the prediction interval, , if . and are the upper and lower bounds of the target value respectively, and the optimal value of PICP is 100%, which means that all the target values fall within the prediction interval, that is, the coverage rate is 100%.
- (4)
- ClarityMean prediction interval width (MPIW) shows the average width of prediction interval [39].
4. Experiment and Analysis
4.1. Data Description
4.2. Experiment
4.2.1. Data Preprocessing
4.2.2. Construction of Bearing Optimal Degradation Indicator Set
4.2.3. Train Prediction Model
4.3. Results and Analysis
4.3.1. Comparison of Point Prediction Results
4.3.2. Comparison of KDE Prediction Results
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Son, K.L.; Fouladirad, M.; Barros, A.; Levrat, E.; Lung, B. Remaining useful life estimation based on stochastic deterioration models: A comparative study. Reliab. Eng. Syst. Saf. 2013, 112, 165–175. [Google Scholar] [CrossRef]
- Si, X.S.; Wang, B.; Hu, C.H.; Zhou, D.H. Remaining useful life estimation–A review on the statistical data driven approaches. Eur. J. Oper. Res. 2011, 213, 1–14. [Google Scholar] [CrossRef]
- Li, X.; Ding, Q.; Sun, J.Q. Remaining useful life estimation in prognostics using deep convolution neural networks. Reliab. Eng. Syst. Saf. 2018, 172, 1–11. [Google Scholar] [CrossRef] [Green Version]
- Lei, Y.; Li, N.; Jia, F.; Lin, J.; Xing, S. A Nonlinear Degradation Model Based Method for Remaining Useful Life Prediction of Rolling Element Bearings. In Proceedings of the 2015 Prognostics and System Health Management Conference, Beijing, China, 21–23 October 2015; pp. 1–8. [Google Scholar] [CrossRef]
- Lei, Y.; Li, N.; Gontarz, S.; Lin, J.; Radkowski, S.; Dybala, J. A Model-Based Method for Remaining Useful Life Prediction of Machinery. IEEE Trans. Reliab. 2017, 65, 1314–1326. [Google Scholar] [CrossRef]
- Qian, Y.; Yan, R. Remaining Useful Life Prediction of Rolling Bearings Using an Enhanced Particle Filter. IEEE Trans. Instrum. Meas. 2015, 64, 2696–2707. [Google Scholar] [CrossRef]
- Li, H.; Liu, T.; Wu, X.; Chen, Q. Enhanced Frequency Band Entropy Method for Fault Feature Extraction of Rolling Element Bearings. IEEE Trans. Ind. Inform. 2020, 16, 5780–5791. [Google Scholar] [CrossRef]
- Yen, G.G.; Lin, K.C. Wavelet packet feature extraction for vibration monitoring. IEEE Trans. Ind. Electr. 2000, 47, 650–667. [Google Scholar] [CrossRef] [Green Version]
- Liu, H.; Zhou, J.; Zheng, Y.; Wei, J.; Zhang, Y. Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders. ISA Trans. 2018, 77, 167–178. [Google Scholar] [CrossRef] [PubMed]
- Deng, Z.; Li, Y.; Zhu, H.; Huang, K.; Tang, Z.; Wang, Z. Sparse stacked autoencoder network for complex system monitoring with industrial applications. Chaos Solitons Fractals 2020, 137. [Google Scholar] [CrossRef]
- Yu, W.; Kim, I.Y.; Mechefske, C. An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme. Reliab. Eng. Syst. Saf. 2020. [Google Scholar] [CrossRef]
- Chen, R.X.; Chen, S.Y.; He, M.; He, D.; Tang, B.P. Rolling bearing fault severity identification using deep sparse auto-encoder network with noise added sample expansion. J. Risk Reliab. 2017, 231. [Google Scholar] [CrossRef]
- Vincent, P.; Larochelle, H.; Bengio, Y.; Manzagol, P.A. Extracting and Composing Robust Features with Denoising Autoencoders. In Proceedings of the Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, 5–9 June 2008. [Google Scholar]
- Vincent, P.; Larochelle, H.; Lajoie, I.; Bengio, Y.; Manzagol, P.A. Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion. J. Mach. Learn. Res. 2010, 11, 3371–3408. [Google Scholar]
- Kaji, M.; Parvizian, J.; Venn, H. Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform. Appl. Sci. 2020, 10, 8948. [Google Scholar] [CrossRef]
- Malhotra, P.; Vishnu, T.V.; Ramakrishnan, A.; Anand, G.; Vig, L.; Agarwal, P.; Shroff, G. Multi-sensor prognostics using an unsupervised health index based on LSTM encoder-decoder. arXiv 2016, arXiv:1608.06154. [Google Scholar]
- Yoo, Y.J.; Baek, J.G. A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network. Appl. Sci. 2018, 8, 1102. [Google Scholar] [CrossRef] [Green Version]
- Ren, L.; Sun, Y.; Wang, H.; Zhang, L. Prediction of Bearing Remaining Useful Life With Deep Convolution Neural Network. IEEE Access 2018, 13041–13049. [Google Scholar] [CrossRef]
- Kong, Z.; Cui, Y.; Xia, Z.; lv, H. Convolution and Long Short-Term Memory Hybrid Deep Neural Networks for Remaining Useful Life Prognostics. Appl. Sci. 2019, 9, 4156. [Google Scholar] [CrossRef] [Green Version]
- Yu, J.; Xu, Y.; Liu, K. Planetary gear fault diagnosis using stacked denoising autoencoder and gated recurrent unit neural network under noisy environment and time-varying rotational speed conditions. Meas. Sci. Technol. 2019, 30. [Google Scholar] [CrossRef]
- Wang, B.; Lei, Y.; Yan, T.; Li, N.; Guo, L. Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery. Neurocomputing 2020, 379, 117–129. [Google Scholar] [CrossRef]
- Ren, L.; Sun, Y.; Cui, J.; Zhang, L. Bearing remaining useful life prediction based on deep autoencoder and deep neural networks. J. Manuf. Syst. 2018, 48, 71–77. [Google Scholar] [CrossRef]
- Koenker, R.; Bassett, J.G. Regression quantiles. Econometrica 1978, 46, 33–50. [Google Scholar] [CrossRef]
- Lv, P.; Yu, Y.W.; Fan, Y.Y.; Tang, X.F.; Tong, X.R. Layer-constrained variational autoencoding kernel density estimation model for anomaly detection. Knowl.-Based Syst. 2020, 196. [Google Scholar] [CrossRef]
- Taylor, J.W. A quantile regression neural network approach to estimating the conditional density of multi-period returns. J. Forecast. 2000, 19, 299–311. [Google Scholar] [CrossRef]
- Tian, C.; Ma, J.; Zhang, C.H.; Zhan, P.P. A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network. Energies 2018, 11, 3493. [Google Scholar] [CrossRef] [Green Version]
- Bai, S.; Kolter, J.Z.; Koltun, V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv 2018, arXiv:1803.01271. [Google Scholar]
- Varon, C.; Alzate, C.; Suykens, J.A.K. Noise Level Estimation for Model Selection in Kernel PCA Denoising. IEEE Trans. Neural Netw. Learn. Syst. 2015, 26, 2650–2663. [Google Scholar] [CrossRef]
- Hinton, G.; Salakhutdinov, R.R. Reducing the Dimensionality of data with neural networks. Science 2006, 313, 504–507. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Hallock, K.F.; Koenker, R.W. Quantile Regression. J. Econ. Perspect. 2001, 15, 143–156. [Google Scholar]
- Mao, W.; He, J.; Zuo, M.J. Predicting Remaining Useful Life of Rolling Bearings Based on Deep Feature Representation and Transfer Learning. IEEE Trans. Instrum. Meas. 2020, 69, 1594–1608. [Google Scholar] [CrossRef]
- Li, X.; Zhang, W.; Ding, Q. Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction. Reliab. Eng. Syst. Saf. 2019, 182, 208–218. [Google Scholar] [CrossRef]
- Reshef, D.N.; Reshef, Y.A.; Finuca, H.K.; Grossman, S.R. Detecting Novel Associations in Large Data Sets. Science 2011, 334, 1518–1524. [Google Scholar] [CrossRef] [Green Version]
- Tang, X.H.; Wang, J.C.; Lu, J.G.; Liu, G.K. Improving bearing fault diagnosis using maximum information coefficient based feature selection. Appl. Sci. 2018, 8, 2143. [Google Scholar] [CrossRef] [Green Version]
- Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014, 15, 1929–1958. [Google Scholar]
- Epanechnikov, V.A. Nonparametric estimation of a multidimensional probability density. Theory Probab. Appl. 1969, 14, 153–158. [Google Scholar] [CrossRef]
- Sheather, S.J.; Jones, M.C. A Reliable Data-Based Bandwidth Selection Method for Kernel Density Estimation. J. R. Stat. Soc. Series B Method. 1991, 53, 683–690. [Google Scholar] [CrossRef]
- Wan, C.; Xu, Z.; Pinson, P.; Dong, Z.Y.; Wong, K.P. Optimal Prediction Intervals of Wind Power Generation. IEEE Trans. Power Syst. 2014, 39, 1166–1174. [Google Scholar] [CrossRef] [Green Version]
- Khosravi, A.; Nahavandi, S.; Creighton, D.; Atiya, A.F. Comprehensive Review of Neural Network-Based Prediction Intervals and New Advances. IEEE Trans. Neural Netw. 2011, 22, 1341–1356. [Google Scholar] [CrossRef]
- Wang, B.; Lei, Y.; Li, N.; Li, N. A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings. IEEE Trans. Reliab. 2020, 69, 401–412. [Google Scholar] [CrossRef]
- Lei, Y.G.; He, Z.J.; Zi, Y.Y. A new approach to intelligent fault diagnosis of rotating machinery. Expert Syst. Appl. 2008, 35, 1593–1600. [Google Scholar] [CrossRef]
Operating Condition | Rotating Speed (rpm) | Radial Force (kN) | Bearings Dataset |
---|---|---|---|
Condition A | 2100 | 12 | BearingA_1 BearingA_2 BearingA_3 BearingA_4 BearingA_5 |
Condition B | 2250 | 11 | BearingB_1 BearingB_2 BearingB_3 BearingB_4 BearingB_5 |
Condition C | 2400 | 10 | BearingC_1 BearingC_2 BearingC_3 BearingC_4 BearingC_5 |
Feature (Horizontal) | Feature (Vertical) | Time-Domain Feature Parameters | Feature (Horizontal) | Feature (Vertical) | Frequency-Domain Feature Parameters |
---|---|---|---|---|---|
where is the time-domain signal series, for , N is the number of each sample points. | where is the frequency-domain signal series, for , K is the number of spectral lines. is the frequency value of the k-th spectral line. |
Working Condition | DI Set | The Prediction Results | |||
---|---|---|---|---|---|
MAE (LSTMQR) | RMSE (LSTMQR) | MAE (TCNQR) | RMSE (TCNQR) | ||
Condition A 2100 rpm | Initial feature set PCA feature set | 2.928 2.407 1.706 1.411 0.729 | 3.207 2.683 1.976 1.694 0.903 | 2.801 2.473 1.391 1.317 0.584 | 3.034 2.650 1.589 1.533 0.783 |
Condition B 2250 rpm | Initial feature set PCA feature set | 2.643 2.296 1.781 1.803 0.657 | 2.916 2.602 1.940 2.117 0.851 | 2.509 2.217 1.445 1.283 0.579 | 2.733 2.406 1.690 1.466 0.747 |
Condition C 2400 rpm | Initial feature set PCA feature set | 2.727 2.279 1.502 1.412 0.701 | 2.985 2.549 1.737 1.689 0.884 | 2.648 2.335 1.277 1.182 0.458 | 2.811 2.560 1.492 1.369 0.619 |
Moment | Evaluation Indexes | DI Construction Method | |||||
---|---|---|---|---|---|---|---|
PCA-DI Set | PCA-DI Set | - DI Set | -DI Set | -DI Set | -DI Set | ||
(LSTMQR) | (TCNQR) | (LSTMQR) | (TCNQR) | (LSTMQR) | (TCNQR) | ||
30 min | PICP MPIW | 84.93% 64.22% | 87.17% 63.98% | 90.71% 63.06% | 91.49% 60.72% | 93.43% 60.17% | 95.16% 58.44% |
60 min | PICP MPIW | 87.12% 62.91% | 89.74% 62.13% | 90.13% 59.28% | 92.35% 58.90% | 93.39% 56.13% | 95.02% 53.06% |
100 min | PICP MPIW | 87.03% 62.15% | 90.19% 59.74% | 89.28% 59.87% | 93.04% 55.39% | 95.87% 58.62% | 96.25% 41.06% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Tian, Q.; Wang, H. Predicting Remaining Useful Life of Rolling Bearings Based on Reliable Degradation Indicator and Temporal Convolution Network with the Quantile Regression. Appl. Sci. 2021, 11, 4773. https://doi.org/10.3390/app11114773
Tian Q, Wang H. Predicting Remaining Useful Life of Rolling Bearings Based on Reliable Degradation Indicator and Temporal Convolution Network with the Quantile Regression. Applied Sciences. 2021; 11(11):4773. https://doi.org/10.3390/app11114773
Chicago/Turabian StyleTian, Qiaoping, and Honglei Wang. 2021. "Predicting Remaining Useful Life of Rolling Bearings Based on Reliable Degradation Indicator and Temporal Convolution Network with the Quantile Regression" Applied Sciences 11, no. 11: 4773. https://doi.org/10.3390/app11114773