TY - JOUR
T1 - Joint Modeling of Degradation and Lifetime Data for RUL Prediction of Deteriorating Products
AU - Hu, Jiawen
AU - Sun, Qiuzhuang
AU - Ye, Zhi Sheng
AU - Zhou, Qiang
N1 - Funding Information:
Manuscript received March 5, 2020; revised May 8, 2020 and July 29, 2020; accepted August 17, 2020. Date of publication September 3, 2020; date of current version April 2, 2021. This work was supported in part by the Natural Science Foundation of China under Grant 71801168 and in part by Singapore MOE Tier 2 under Grant R-266-000-125-112. Paper no. TII-20-1166. (Corresponding author: Qiuzhuang Sun.) Jiawen Hu is with the School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu 611731, China, and also with the Aircraft Swarm Intelligent Sensing and Co-operative Control Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, China (e-mail: hdl@sjtu.edu.cn).
Publisher Copyright:
© 2005-2012 IEEE.
PY - 2021/7
Y1 - 2021/7
N2 - Degradation is one of the major root causes of system failure. In some applications, the degradation levels are different upon failure, in which the fixed failure threshold assumption commonly adopted in the degradation literature may not hold. This article tackles the difficulty by jointly analyzing the system degradation and the lifetime data, which enables the corresponding remaining useful life (RUL) prediction. We treat the degradation level as a multiplicative time-varying covariate of the system hazard rate, where a random-effects Wiener process is adopted to model the degradation process. The model parameters are estimated under a Bayesian framework, and we also develop a particle filter method to update the estimates when new data are available. This makes the proposed model be able to realize online RUL prediction based on the in-situ system health state signals. Through case studies on lead-acid batteries and digital communication systems, the proposed model is shown to outperform existing methods in terms of the RUL prediction accuracy.
AB - Degradation is one of the major root causes of system failure. In some applications, the degradation levels are different upon failure, in which the fixed failure threshold assumption commonly adopted in the degradation literature may not hold. This article tackles the difficulty by jointly analyzing the system degradation and the lifetime data, which enables the corresponding remaining useful life (RUL) prediction. We treat the degradation level as a multiplicative time-varying covariate of the system hazard rate, where a random-effects Wiener process is adopted to model the degradation process. The model parameters are estimated under a Bayesian framework, and we also develop a particle filter method to update the estimates when new data are available. This makes the proposed model be able to realize online RUL prediction based on the in-situ system health state signals. Through case studies on lead-acid batteries and digital communication systems, the proposed model is shown to outperform existing methods in terms of the RUL prediction accuracy.
KW - Proportional hazards model
KW - particle filter
KW - random-effects Wiener process
KW - remaining useful life (RUL)
UR - http://www.scopus.com/inward/record.url?scp=85104174675&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85104174675&partnerID=8YFLogxK
U2 - 10.1109/TII.2020.3021054
DO - 10.1109/TII.2020.3021054
M3 - Article
AN - SCOPUS:85104174675
SN - 1551-3203
VL - 17
SP - 4521
EP - 4531
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
IS - 7
M1 - 9186315
ER -