Remaining Useful Life Prediction Algorithm for Rolling Bearing in the Early Stage

doi:10.19678/j.issn.1000-3428.0068624

Abstract

Abstract:

Traditional useful life prediction algorithms have achieved good results in predicting the useful life of rolling bearings containing degradation stage data. However, as data just running are similar to data running for a period of time, accurate prediction using only normal-working-stage data is difficult. The Reservoir Computer (RC) can predict future data after multiple time steps based on previous time data, raising the possibility of converting predictions in the early stage into traditional predictions by supplementing the degraded data through data simulation. An Echo State Network (ESN) can output the relevant dimensions of the current moment while fully utilizing the temporal information. In this study, a Recursive Reconstructible Neural (RRN) network algorithm based on RC and ESN is proposed for bearing useful life prediction in the early stage. First, an RC-based feature simulation network is designed to simulate the entire lifecycle of data containing degraded data based on early features. Subsequently, a useful life prediction network based on ESN, which outputs the Remaining Useful Life (RUL) based on the simulated features of the input, is proposed. The effectiveness of the algorithm is validated on the PHM 2012 dataset, and the experimental results showed that compared with current algorithms with good performance, the proposed algorithm reduced the average error of the RUL prediction in the original test data and early stage experiments by 61.35% and 53.14%, respectively, demonstrating superior prediction performance.

Key words: Remaining Useful Life (RUL) prediction in the early stage, rolling bearing, data simulation, Reservoir Computer (RC), Echo State Network (ESN), Recursive Reconstructible Neural(RRN) network

摘要：

传统寿命预测算法在包含退化阶段数据的滚动轴承寿命预测方面已取得不错的效果, 但是由于刚运行和运行一段时间数据相似, 因此在只有正常工作阶段数据的情况下难以准确预测。储备池计算(RC)可根据之前时刻数据预测多个时间步长之后的数据, 通过数据模拟补充退化数据, 提高了将早期预测转化为传统预测的可能性。回声状态网络(ESN)可在充分利用时序信息的基础上输出当前时刻的相关维度。针对早期阶段轴承寿命预测, 提出一个基于RC和ESN的递归可重构神经(RRN)网络的算法。首先设计一个基于RC的特征模拟网络, 根据早期特征模拟包含退化数据的全寿命周期数据; 然后提出一个基于ESN的寿命预测网络, 根据输入的模拟特征输出剩余寿命。在PHM 2012数据集上验证了该算法的有效性, 实验结果表明, 与目前效果较好的算法相比, 该算法在原测试数据实验与早期阶段剩余寿命预测的实验平均误差分别降低了61.35%和53.14%, 具有较优的预测性能。

关键词: 早期剩余寿命预测, 滚动轴承, 数据模拟, 储备池计算, 回声状态网络, 递归可重构神经网络

HAO Jinxiao, WANG Yan, GUO Qianyu, ZHANG Wenqiang. Remaining Useful Life Prediction Algorithm for Rolling Bearing in the Early Stage[J]. Computer Engineering, 2024, 50(12): 48-58.

郝金骁, 王龑, 郭倩宇, 张文强. 早期工作阶段滚动轴承剩余寿命预测算法[J]. 计算机工程, 2024, 50(12): 48-58.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0068624

https://www.ecice06.com/EN/Y2024/V50/I12/48

Figures/Tables 18

Fig.1 Basic architecture of reservoir computing

Fig.2 The framework of the RFSN

Fig.3 The framework of ESRULPN

Fig.4 The framework of RRN

Fig.5 The framework of constructed method

Fig.6 The framework of RUL prediction

Fig.7 Procedure of RUL prediction on degradation stage

Fig.8 The original results before linear fitting and the final results after linear fitting

Fig.9 Peak to peak values of horizontal vibration signals for bearings

Fig.10 Procedure of RUL prediction in the early stage

Fig.11 Characteristic simulation results of bearings 1-5 with 10% input data

Fig.12 Prediction results of bearing 1-3 with 10%, 20%, 30%, and 40% input data

Fig.13 Comparison results of experimental errors

References 26

1	张龙, 张号, 王朝兵, 等. 显式动力学驱动的轴承变工况故障诊断方法. 中国机械工程, 2023, 34 (8): 982- 992. doi: 10.3969/j.issn.1004-132X.2023.08.013
	ZHANG L , ZHANG H , WANG C B , et al. Explicit dynamics driving fault diagnosis method for bearing variable conditions. China Mechanical Engineering, 2023, 34 (8): 982- 992. doi: 10.3969/j.issn.1004-132X.2023.08.013
2	VRIGNAT P , KRATZ F , AVILA M . Sustainable manufacturing, maintenance policies, prognostics and health management: a literature review. Reliability Engineering & System Safety, 2022, 218, 108140. doi: 10.1016/j.ress.2021.108140
3	LI X C , DUAN F , MBA D , et al. Multidimensional prognostics for rotating machinery: a review. Advances in Mechanical Engineering, 2017, 9 (2): 11- 16. doi: 10.1177/1687814016685004
4	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. doi: 10.1016/j.ejor.2010.11.018
5	CUI L L , WANG X , XU Y G , et al. A novel switching unscented Kalman filter method for remaining useful life prediction of rolling bearing. Measurement, 2019, 135, 678- 684. doi: 10.1016/j.measurement.2018.12.028
6	KEDADOUCHE M , THOMAS M , TAHAN A . A comparative study between Empirical wavelet transforms and Empirical mode decomposition methods: application to bearing defect diagnosis. Mechanical Systems and Signal Processing, 2016, 81, 88- 107. doi: 10.1016/j.ymssp.2016.02.049
7	BARUAH P , CHINNAM R B . HMMs for diagnostics and prognostics in machining processes. International Journal of Production Research, 2005, 43 (6): 1275- 1293. doi: 10.1080/00207540412331327727
8	SUN F Q , WANG N , LI X Y , et al. Remaining useful life prediction for a machine with multiple dependent features based on Bayesian dynamic linear model and copulas. IEEE Access, 2017, 5, 16277- 16287. doi: 10.1109/ACCESS.2017.2735966
9	PANDIYAN V , CAESARENDRA W , TJAHJOWIDODO T , et al. In-process tool condition monitoring in compliant abrasive belt grinding process using support vector machine and genetic algorithm. Journal of Manufacturing Processes, 2018, 31, 199- 213. doi: 10.1016/j.jmapro.2017.11.014
10	CHEN F F , CHENG M T , TANG B P , et al. A novel optimized multi-kernel relevance vector machine with selected sensitive features and its application in early fault diagnosis for rolling bearings. Measurement, 2020, 156, 107583. doi: 10.1016/j.measurement.2020.107583
11	金柱璋, 方旭源, 黄彦慧, 等. 基于深度度量学习的卫星云图检索. 光电工程, 2022, 49 (4): 210307. doi: 10.12086/oee.2022.210307
	JIN Z Z , FANG X Y , HUANG Y H , et al. Satellite cloud image retrieval based on deep metric learning. Opto-Electronic Engineering, 2022, 49 (4): 210307. doi: 10.12086/oee.2022.210307
12	姚德臣, 李博阳, 刘恒畅, 等. 基于注意力GRU算法的滚动轴承剩余寿命预测. 振动与冲击, 2021, 40 (17): 116- 123. doi: 10.13465/j.cnki.jvs.2021.17.016
	YAO D C , LI B Y , LIU H C , et al. Residual life prediction of rolling bearing based on attention GRU algorithm. Journal of Vibration and Shock, 2021, 40 (17): 116- 123. doi: 10.13465/j.cnki.jvs.2021.17.016
13	ZHAO R , YAN R Q , WANG J J , et al. Learning to monitor machine health with convolutional bi-directional LSTM networks. Sensors, 2017, 17 (2): 273. doi: 10.3390/s17020273
14	QIN Y , XIANG S , CHAI Y , et al. Macroscopic-microscopic attention in LSTM networks based on fusion features for gear remaining life prediction. IEEE Transactions on Industrial Electronics, 2020, 67 (12): 10865- 10875. doi: 10.1109/TIE.2019.2959492
15	WANG B , LEI Y G , YAN T , et al. Recurrent convolutional neural network: a new framework for remaining useful life prediction of machinery. Neurocomputing, 2020, 379, 117- 129. doi: 10.1016/j.neucom.2019.10.064
16	董绍江, 朱朋, 朱孙科, 等. 基于仿真数据驱动和领域自适应的滚动轴承故障诊断方法. 中国机械工程, 2023, 34 (6): 694- 702. doi: 10.3969/j.issn.1004-132X.2023.06.008
	DONG S J , ZHU P , ZHU S K , et al. Fault diagnosis method of rolling bearings based on simulation data drive and domain adaptation. China Mechanical Engineering, 2023, 34 (6): 694- 702. doi: 10.3969/j.issn.1004-132X.2023.06.008
17	BENJAMIN S, DAVID V, CAMPENHOUT V, et al. An overview of reservoir com-puting: theory, applications and implementations[C]//Proceedings of the 15th European Symposium on Artificial Neural Networks. Berlin, Germany: Springer, 2007: 471-482.
18	GALLICCHIO C , MICHELI A . Tree echo state networks. Neurocomputing, 2013, 101, 319- 337. doi: 10.1016/j.neucom.2012.08.017
19	NECTOUX P, GOURIVEAU R, MEDIAHER K, et al. PRONOSTIA: an experimental platform for bearingac-celerated degradation tests[C]//Proceedings of IEEE International Conference on Prognostics and Health Management. Washington D. C., USA: IEEE Press, 2012: 11-17.
20	HINCHI A Z , TKIOUAT M . Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network. Procedia Computer Science, 2018, 127, 123- 132. doi: 10.1016/j.procs.2018.01.106
21	LEI Y G , LI N P , GONTARZ S , et al. A model-based method for remaining useful life prediction of machinery. IEEE Transactions on Reliability, 2016, 65 (3): 1314- 1326. doi: 10.1109/TR.2016.2570568
22	HONG S , ZHOU Z , ZIO E , et al. Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method. Digital Signal Processing, 2014, 27, 159- 166. doi: 10.1016/j.dsp.2013.12.010
23	CHEN Y H , PENG G L , ZHU Z Y , et al. A novel deep learning method based on attention mechanism for bearing remaining useful life prediction. Applied Soft Computing, 2020, 86, 105919. doi: 10.1016/j.asoc.2019.105919
24	WANG B , LEI Y G , LI N P , et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Transactions on Reliability, 2020, 69 (1): 401- 412. doi: 10.1109/TR.2018.2882682
25	张龙, 胡燕青, 赵丽娟, 等. 多通道信息融合与深度迁移学习的旋转机械故障诊断. 中国机械工程, 2023, 34 (8): 966- 975. doi: 10.3969/j.issn.1004-132X.2023.08.011
	ZHANG L , HU Y Q , ZHAO L J , et al. Multichannel information fusion and deep transfer learning for rotating machinery fault diagnosis. China Mechanical Engineering, 2023, 34 (8): 966- 975. doi: 10.3969/j.issn.1004-132X.2023.08.011
26	赵靖, 杨绍普, 李强, 等. 一种残差注意力迁移学习方法及其在滚动轴承故障诊断中的应用. 中国机械工程, 2023, 34 (3): 332- 343. doi: 10.3969/j.issn.1004-132X.2023.03.010
	ZHAO J , YANG S P , LI Q , et al. A new transfer learning method with residual attention and its applications on rolling bearing fault diagnosis. China Mechanical Engineering, 2023, 34 (3): 332- 343. doi: 10.3969/j.issn.1004-132X.2023.03.010

Please choose a citation manager

Content to export