• RELIABILITY •

### Remaining useful life prediction based on nonlinear random coefficient regression model with fusing failure time data

Fengfei WANG(), Shengjin TANG(), Xiaoyan SUN(), Liang LI(), Chuanqiang YU(), Xiaosheng SI

1. 1 Department of Mechanical Engineering, Rocket Force University of Engineering, Xi’an 710025, China
• Received:2021-03-10 Online:2023-02-18 Published:2023-03-03
• Contact: Shengjin TANG E-mail:18755187114@163.com;tangshengjin27@126.com;sunxiaoyantsj@126.com;xzj_921@163.com;fishychq@163.com
• About author:
WANG Fengfei was born in 1997. He received his B.S. degree from Hefei University of Technology in 2019 and he is currently pursuing his M.S. degree in Rocket Force University of Engineering. His main research interests are prognostics and health management, remaining useful life prediction, and reliability assessment. E-mail: 18755187114@163.com

TANG Shengjin was born in 1985. He received his B.S., M.S., and Ph.D. degrees in 2007, 2010, and 2015 from Rocket Force University of Engineering, Xi ’an, China. He is currently an associate professor with the Rocket Force University of Engineering, Xi ’an, China. His main research interests include prognostics and health management, reliability assessment, predictive maintenance, and image processing. E-mail: tangshengjin27@126.com

SUN Xiaoyan was born in 1987. She received her B.S. degree in 2010 from Southeast University Chengxian College, Nanjing, China, and M.S. degree in 2013 from Xi’an Technological University, Xi’an, China. She is currently a lecturer with the Rocket Force University of Engineering, Xi’an, China. Her main research interests include prognostics and health management, image processing, and machine learning E-mail: sunxiaoyantsj@126.com

LI Liang was born in 1984. He received his B.S., M.S. and Ph.D. degrees from the Rocket Force University of Engineering, Xi’an, China. He is currently a lecturer with the Rocket Force University of Engineering, Xi’an, China. His main research interests include fault diagnosis of hydraulic system, hydraulic control theory and engineering. E-mail: xzj_921@163.com

YU Chuanqiang was born in 1975. He received his B.S., M.S., and Ph.D. degrees from Xi ’an Institute of High-Technology, Xi ’an, China, in 2000, 2003, and 2007, respectively. He is currently a professor with the Rocket Force University of Engineering, Xi ’an, China. His main research interests are reliability assessment, driverless cars, and image processing. E-mail: fishychq@163.com

SI Xiaosheng was born in 1984. He received his B.S., M.S., and Ph.D. degrees from the Rocket Force University of Engineering, Xi’an, China, in 2006, 2009, and 2014, respectively. He is currently a professor with the Department of Mechanical Engineering. His research interests include evidence theory, expert system, prognostics and health management, reliability assessment, predictive maintenance, and lifetime estimation. E-mail: sixiaosheng@gmail.com
• Supported by:
This work was supported by National Natural Science Foundation of China (61703410;61873175;62073336;61873273;61773386;61922089)

Abstract:

Remaining useful life (RUL) prediction is one of the most crucial elements in prognostics and health management (PHM). Aiming at the imperfect prior information, this paper proposes an RUL prediction method based on a nonlinear random coefficient regression (RCR) model with fusing failure time data. Firstly, some interesting natures of parameters estimation based on the nonlinear RCR model are given. Based on these natures, the failure time data can be fused as the prior information reasonably. Specifically, the fixed parameters are calculated by the field degradation data of the evaluated equipment and the prior information of random coefficient is estimated with fusing the failure time data of congeneric equipment. Then, the prior information of the random coefficient is updated online under the Bayesian framework, the probability density function (PDF) of the RUL with considering the limitation of the failure threshold is performed. Finally, two case studies are used for experimental verification. Compared with the traditional Bayesian method, the proposed method can effectively reduce the influence of imperfect prior information and improve the accuracy of RUL prediction.