Residual Convolution Long Short-Term Memory Network for Machines Remaining Useful Life Prediction and Uncertainty Quantification

Authors

  • Wenting Wang Key Laboratory of Education Ministry for Modern Design & Rotor-Bearing System, Xi'an Jiaotong University, Xi'an, China
  • Yaguo Lei Key Laboratory of Education Ministry for Modern Design & Rotor-Bearing System, Xi'an Jiaotong University, Xi'an, China https://orcid.org/0000-0002-5167-1459
  • Tao Yan Key Laboratory of Education Ministry for Modern Design & Rotor-Bearing System, Xi'an Jiaotong University, Xi'an, China https://orcid.org/0000-0002-3328-2118
  • Naipeng Li Key Laboratory of Education Ministry for Modern Design & Rotor-Bearing System, Xi'an Jiaotong University, Xi'an, China
  • Asoke Nandi Department of Electronic and Electrical Engineering, Brunel University London, Uxbridge, United Kingdom https://orcid.org/0000-0001-6248-2875

DOI:

https://doi.org/10.37965/jdmd.v2i2.43

Keywords:

deep learning, residual convolution LSTM network, remaining useful life prediction, uncertainty quantification

Abstract

Recently, deep learning is widely used in the field of remaining useful life (RUL) prediction. Among various deep learning technologies, recurrent neural network (RNN) and its variant, e.g., long short-term memory (LSTM) network, are gaining more attention because of their capability of capturing temporal dependence. Although the existing RNN-based approaches have demonstrated their RUL prediction effectiveness, they still suffer from the following two limitations: 1) it is difficult for RNN to extract directly degradation features from original monitoring data, and 2) most of the RNN-based prognostics methods are unable to quantify the uncertainty of prediction results. To address the above limitations, this paper proposes a new method named Residual convolution LSTM (RC-LSTM) network. In RC-LSTM, a new ResNet-based convolution LSTM (Res-ConvLSTM) layer is stacked with convolution LSTM (ConvLSTM) layer to extract degradation representations from monitoring data. Then, predicated on the RUL following a normal distribution, an appropriate output layer is constructed to quantify the uncertainty of the forecast result. Finally, the effectiveness and superiority of RC-LSTM is verified using monitoring data from accelerated degradation tests of rolling element bearings.

Conflict of Interest Statement
The authors declare no conflicts of interest.

Metrics

PDF views
976
Dec 22 '21Dec 25 '21Dec 28 '21Dec 31 '21Jan 01 '22Jan 04 '22Jan 07 '22Jan 10 '22Jan 13 '22Jan 16 '22Jan 19 '2231
| |
HTML views
94
Jan 2022Jul 2022Jan 2023Jul 2023Jan 2024Jul 2024Jan 2025Jul 2025Jan 202618
|

Downloads

Published

2021-12-21

How to Cite

Wang, W., Lei, Y., Yan, T., Li, N., & Nandi, A. (2021). Residual Convolution Long Short-Term Memory Network for Machines Remaining Useful Life Prediction and Uncertainty Quantification. Journal of Dynamics, Monitoring and Diagnostics, 1(1), 2–8. https://doi.org/10.37965/jdmd.v2i2.43

Issue

Section

Invited Article