Independently recurrent neural network for remaining useful life estimation

doi:10.19682/j.cnki.1005-8885.2020.0034

中国邮电高校学报(英文) ›› 2020, Vol. 27 ›› Issue (4): 26-33.doi: 10.19682/j.cnki.1005-8885.2020.0034

• Artificial Intelligence • 上一篇下一篇

Independently recurrent neural network for remaining useful life estimation

王锴烨崔绍华许方敏赵成林

1. 北京邮电大学
2. 中国石油技术开发公司
3. 北京市海淀区西土城路10号北京邮电大学科研楼618

收稿日期:2018-06-04 修回日期:2020-08-18 出版日期:2020-08-31 发布日期:2020-08-31
通讯作者: 王锴烨 E-mail:wangky@bupt.edu.cn

Independently recurrent neural network for remaining useful life estimation

Wang Kaiye, Cui Shaohua, Xu Fangmin, Zhao Chenglin

Received:2018-06-04 Revised:2020-08-18 Online:2020-08-31 Published:2020-08-31
Contact: Wang Kaiye E-mail:wangky@bupt.edu.cn

摘要/Abstract

摘要：

In the industrial fields, the mechanical equipment will inevitably wear out in the process of operation. With the accumulation of losses, the probability of equipment failure is increasing. Therefore, if the remaining useful life (RUL) of the equipment can be accurately predicted, the equipment can be maintained in time to avoid the downtime caused by equipment failure and greatly improve the production efficiency of enterprises. This paper aims to use independently recurrent neural network (IndRNN) to learn health degradation of turbofan engine and make accurate predictions of its RUL, which not only effectively solves the problem of gradient explosion and vanishing, but also increases the interpretability of neural networks. IndRNN can be used to process longer time series which matches the scene with high frequency sampling sensor in industrial practical applications. The results demonstrate that IndRNN for RUL estimation significantly outperforms traditional approaches, as well as convolutional neural network (CNN) and long short-term memory network (LSTM) for RUL estimation.

关键词:

multivariate time series analysis, independent recurrent neural network, remaining useful life estimation, prognostic and health management

Abstract: In the industrial fields, the mechanical equipment will inevitably wear out in the process of operation. With the accumulation of losses, the probability of equipment failure is increasing. Therefore, if the remaining useful life (RUL) of the equipment can be accurately predicted, the equipment can be maintained in time to avoid the downtime caused by equipment failure and greatly improve the production efficiency of enterprises. This paper aims to use independently recurrent neural network (IndRNN) to learn health degradation of turbofan engine and make accurate predictions of its RUL, which not only effectively solves the problem of gradient explosion and vanishing, but also increases the interpretability of neural networks. IndRNN can be used to process longer time series which matches the scene with high frequency sampling sensor in industrial practical applications. The results demonstrate that IndRNN for RUL estimation significantly outperforms traditional approaches, as well as convolutional neural network (CNN) and long short-term memory network (LSTM) for RUL estimation.

Key words: multivariate time series analysis, independent recurrent neural network, remaining useful life estimation, prognostic and health management

Wang Kaiye, Cui Shaohua, Xu Fangmin, Zhao Chenglin. Independently recurrent neural network for remaining useful life estimation[J]. The Journal of China Universities of Posts and Telecommunications, 2020, 27(4): 26-33.

参考文献

1. Si X S, Wang W B, Hu C H, et al. Remaining useful life estimation -- A review on the statistical data driven approaches. European Journal of Operational Research, 2011, 213(1): 1-14.

2. Pecht M G. Prognostics and health management of electronics: Fundamentals, machine learning, and the Internet of things. New York, NY, USA: John Wiley & Sons, 2009: 222-229.

of Posts and Telecommunications, 2007 14(3): 28–33

3. Pawar P M, Ganguli R. Fuzzy-logic-based health monitoring and residual-life prediction for composite helicopter rotor. Journal of Aircraft, 2007, 44(3): 981-995.

4. Eker Ö F, Camci F, Jennions I K. Major challenges in prognostics: Study on benchmarking prognostic datasets. Proceedings of the 1st European Conference of the Prognostics and Health Management (PHM’12): Vol 3, 2012, Jul 3-5, Dresden, Germany. 2012: 8p.

5. Xu J P, Wang Y S, Xu L. PHM-oriented integrated fusion prognostics for aircraft engines based on sensor data. IEEE Sensors Journal, 2014, 14(4): 1124-1132.

6. Peel L. Data driven prognostics using a Kalman filter ensemble of neural network models. Proceedings of the 2008 International Conference on Prognostics and Health Management, 2008, Oct 6-9, Denver, CO, USA. Piscataway, NJ, USA: IEEE, 2008: 6p.

7. Tobon-Mejia D A, Medjaher K, Zerhouni N, et al. A data-driven failure prognostics method based on mixture of Gaussians hidden Markov models. IEEE Transactions on Reliability, 2012, 61(2): 491-503.

8. Gers F A, Schraudolph N N, Schmidhuber J. Learning precise timing with LSTM recurrent networks. Journal of Machine Learning Research, 2002, 3: 115-143.

9. Babu G S, Zhao P L, Li X L. Deep convolutional neural network based regression approach for estimation of remaining useful life. Proceedings of the 21st International Conference on Database Systems for Advanced Applications (DASFAA’16), 2016, Apr 16-19, Dallas, TA, USA. Berlin, Germany: Springer, 2016: 214-228.

10. Zheng S, Ristovski K, Farahat A, et al. Long short-term memory network for remaining useful life estimation. Proceedings of the 2017 IEEE International Conference on Prognostics and Health Management (ICPHM'17), 2017, Jun 19-21, Dallas, TX, USA. Piscataway, NJ, USA: IEEE, 2017: 88-95.

11. He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16), 2016, Jun 27-30, Las Vegas, NV, USA. Piscataway, NJ, USA: IEEE, 2016: 770-778.

12. Wu Y H, Schuster M, Chen Z F, et al. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv:1609.08144, 2016.

13. Zhang Y Z, Xiong R, He H W, et al. Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries. IEEE Transactions on Vehicular Technology, 2018, 67(7): 5695-5705.

14. Li S, Li W Q, Cook C, et al. Independently recurrent neural network (IndRNN): Building a longer and deeper RNN. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’18), 2018, Jun 18-23, Salt Lake City, UT, USA. Piscataway, NJ, USA: IEEE, 2018: 5457-5466.

15. Pascanu R, Mikolov T, Bengio Y. On the difficulty of training recurrent neural networks. Proceedings of the 30th International Conference on International Conference on Machine Learning (ICML'13): Vol 3, 2013, Jun 16-21, Atlanta, GA, USA. Red Hook, NY, USA: Curran Associates, 2013: 1310-1318.

16. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521: 436-444.

17. Le Q V, Jaitly N, Hinton G E. A simple way to initialize recurrent networks of rectified linear units. arXiv:1504.00941, 2015.

18. Ramasso E, Saxena A. Performance benchmarking and analysis of prognostic methods for CMAPSS datasets. International Journal of Prognostics and Health Management, 2014, 5(2): 1-15.

19. Sutharssan T. Prognostics and health management of light emitting diodes. Ph D Thesis. London, UK: University of Greenwich, 2012.

20. Heimes F O. Recurrent neural networks for remaining useful life estimation. Proceedings of the 2008 International Conference on Prognostics and Health Management, 2008, Oct 6-9, Denver, CO, USA. Piscataway, NJ, USA: IEEE, 2008: 6p.

Independently recurrent neural network for remaining useful life estimation

Independently recurrent neural network for remaining useful life estimation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价