Remaining useful life estimation using an inverse Gaussian degradation model

NEUROCOMPUTING

卷:185

Article

Pan, Donghui¹  Liu, Jia-Bao²  Cao, Jinde³ 

[1] Anhui Univ, Sch Math Sci, Hefei 230601, Peoples R China

[2] Anhui Xinhua Univ, Dept Publ Courses, Hefei 230088, Peoples R China

[3] Southeast Univ, Dept Math, Res Ctr Complex Syst & Network Sci, Nanjing 210096, Jiangsu, Peoples R China

关键词: Degradation modeling;    Inverse Gaussian process;    Random effect;    Remaining useful life;   

DOI  :  10.1016/j.neucom.2015.12.041

来源: Elsevier

【 摘 要 】

The use of degradation data to estimate the remaining useful life (RUL) has gained great attention with the widespread use of prognostics and health management on safety critical systems. Accurate RUL estimation can prevent system failure and reduce the running risks since the efficient maintenance service could be scheduled in advance. In this paper, we present a degradation modeling and RUL estimation approach by using available degradation data for a deteriorating system. An inverse Gaussian process with the random effect is firstly used to characterize the degradation process of the system. Expectation maximization algorithm is then adopted to estimate the model parameters, and the random parameters in the degradation model are updated by Bayesian method, which makes the estimated RUL able to be real-time updated in terms of the fresh degradation data. Our proposed method can capture the latest condition of the system by means of updating degradation data continuously, and obtain the explicit expression of RUL distribution. Finally, a numerical example and a practical case study are provided to show that the presented approach can effectively model degradation process for the individual system and obtain better results for RUL estimation. (C) 2015 Elsevier B.V. All rights reserved.

【 授权许可】

Free