Remaining Useful Life Prediction of Rolling Bearings Based on Attention Mechanism and CNN-BiLSTM

Fu Guozhong; Du Hua; Zhang Zhiqiang; Li Qingzhao; Huang Siyu; Liu Yanting

doi:10.13832/j.jnpe.2023.S2.0033

Volume 44 Issue S2

Dec. 2023

Turn off MathJax

Article Contents

Article Navigation > Nuclear Power Engineering > 2023 > 44(S2): 33-38

Fu Guozhong, Du Hua, Zhang Zhiqiang, Li Qingzhao, Huang Siyu, Liu Yanting. Remaining Useful Life Prediction of Rolling Bearings Based on Attention Mechanism and CNN-BiLSTM[J]. Nuclear Power Engineering, 2023, 44(S2): 33-38. doi: 10.13832/j.jnpe.2023.S2.0033

Citation:

Fu Guozhong, Du Hua, Zhang Zhiqiang, Li Qingzhao, Huang Siyu, Liu Yanting. Remaining Useful Life Prediction of Rolling Bearings Based on Attention Mechanism and CNN-BiLSTM[J]. Nuclear Power Engineering, 2023, 44(S2): 33-38. doi: 10.13832/j.jnpe.2023.S2.0033

Citation:

Fu Guozhong, Du Hua, Zhang Zhiqiang, Li Qingzhao, Huang Siyu, Liu Yanting. Remaining Useful Life Prediction of Rolling Bearings Based on Attention Mechanism and CNN-BiLSTM[J]. Nuclear Power Engineering, 2023, 44(S2): 33-38. doi: 10.13832/j.jnpe.2023.S2.0033

PDF( 4155 KB)

Remaining Useful Life Prediction of Rolling Bearings Based on Attention Mechanism and CNN-BiLSTM

doi: 10.13832/j.jnpe.2023.S2.0033

Science and Technology on Reactor System Design Technology Laboratory, Nuclear Power Institute of China, Chengdu , 610213, China

Received Date: 2023-07-11
Rev Recd Date: 2023-07-31
Publish Date: 2023-12-30

Abstract

Abstract

Aiming at the problem that traditional deep learning methods do not have high accuracy in predicting the remaining useful life (RUL) of rolling bearings, a hybrid RUL model (CNN-BiLSTM-AM) based on attention mechanism convolutional neural network and bidirectional long short-term memory network is proposed, and the model is used to predict the RUL of rolling bearings. Firstly, the bearing first prediction time (FPT) is determined by the steepness characteristics of the bearing’s original vibration signal. Secondly, the noise reduction and normalization of the original vibration signal after FPT are carried out, and the RUL of rolling bearings under two different conditions is predicted by the hybrid model CNN-BiLSTM-AM. Finally, the hybrid model CNN-BiLSTM-AM is compared with several traditional models. The results show that the hybrid model CNN-BiLSTM-AM is more effective for the RUL of rolling bearings and has generalization performance.
- Rolling bearings,
- Remaining useful life (RUL),
- Attention mechanism,
- Convolutional neural network,
- Bidirectional long-short term memory network

FullText(HTML)

References(19)

References

[1]	WANG B, LEI Y G, LI N P, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J]. IEEE Transactions on Reliability, 2020, 69(1): 401-412. doi: 10.1109/TR.2018.2882682
[2]	ZHAO H M, LIU H D, JIN Y, et al. Feature extraction for data-driven remaining useful life prediction of rolling bearings[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3511910.
[3]	WANG Y W, DENG L, ZHENG L Y, et al. Temporal convolutional network with soft thresholding and attention mechanism for machinery prognostics[J]. Journal of Manufacturing Systems, 2021, 60: 512-526. doi: 10.1016/j.jmsy.2021.07.008
[4]	LI W X, SHANG Z W, GAO M S, et al. Remaining useful life prediction based on transfer multi-stage shrinkage attention temporal convolutional network under variable working conditions[J]. Reliability Engineering & System Safety, 2022, 226: 108722.
[5]	LI X, ZHANG W, DING Q. Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction[J]. Reliability Engineering & System Safety, 2019, 182: 208-218.
[6]	鲍霁星. 一维CNN模型在车轴疲劳裂纹声发射信号中的应用研究[D]. 大连: 大连交通大学,2020.
[7]	ZHAO C Y, HUANG X Z, LIU H Z, et al. A novel bootstrap ensemble learning convolutional simple recurrent unit method for remaining useful life interval prediction of turbofan engines[J]. Measurement Science and Technology, 2022, 33(12): 125004. doi: 10.1088/1361-6501/ac84f6
[8]	刘会永,张松,李剑峰,等. 采用改进CNN-BiLSTM模型的刀具磨损状态监测[J]. 中国机械工程,2022, 33(16): 1940-1947,1956. doi: 10.3969/j.issn.1004-132X.2022.16.007
[9]	蔡薇薇,徐彦伟,颉潭成. 基于CNN-LSTM的轴承剩余使用寿命预测[J]. 机械传动,2022, 46(10): 17-23. doi: 10.16578/j.issn.1004.2539.2022.10.003
[10]	CHENG Y W, HU K, WU J, et al. A convolutional neural network based degradation indicator construction and health prognosis using bidirectional long short-term memory network for rolling bearings[J]. Advanced Engineering Informatics, 2021, 48: 101247. doi: 10.1016/j.aei.2021.101247
[11]	LECUN Y, BOSER B, DENKER J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551. doi: 10.1162/neco.1989.1.4.541
[12]	李少鹏. 结合CNN和LSTM的滚动轴承剩余使用寿命预测方法研究[D]. 哈尔滨: 哈尔滨理工大学,2019.
[13]	ZHENG S, RISTOVSKI K, FARAHAT A, et al. Long short-term memory network for remaining useful life estimation[C]//Proceedings of 2017 IEEE International Conference on Prognostics and Health Management. Dallas: IEEE, 2017.
[14]	WANG F T, LIU X F, DENG G, et al. Remaining life prediction method for rolling bearing based on the long short-term memory network[J]. Neural Processing Letters, 2019, 50(3): 2437-2454. doi: 10.1007/s11063-019-10016-w
[15]	LIU H, LIU Z Y, JIA W Q, et al. Remaining useful life prediction using a novel feature-attention-based end-to-end approach[J]. IEEE Transactions on Industrial Informatics, 2021, 17(2): 1197-1207. doi: 10.1109/TII.2020.2983760
[16]	雷亚国,韩天宇,王彪,等. XJTU-SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报,2019, 55(16): 1-6.
[17]	WANG P, LONG Z Q, WANG G. A hybrid prognostics approach for estimating remaining useful life of wind turbine bearings[J]. Energy Reports, 2020, 6 Suppl 9: 173-182.
[18]	LI N P, LEI Y G, LIN J, et al. An improved exponential model for predicting remaining useful life of rolling element bearings[J]. IEEE Transactions on Industrial Electronics, 2015, 62(12): 7762-7773. doi: 10.1109/TIE.2015.2455055
[19]	LI K, WU J J, ZHANG Q J, et al. New particle filter based on GA for equipment remaining useful life prediction[J]. Sensors, 2017, 17(4): 696. doi: 10.3390/s17040696