Remaining useful life prediction for non-stationary degradation processes with shocks

Xiaojie Ke, Zhengguo Xu, Wenhai Wang and Youxian Sun

Journal of Risk and Reliability, 2017, vol. 231, issue 5, 469-480

Abstract: Predict the remaining useful life of devices in real time is important to maintenance management. This article addresses a remaining useful life predictive problem where the considered device suffers from non-stationary degradation with shocks. A novel degradation-shock system model subjected to a hidden degradation state is proposed to characterize the degradation process. To estimate the hidden system state, the Kalman filter is modified with optimal estimation. Then, based on Bayes’ theorem, a recursive algorithm is presented to estimate the unknown parameters of the model. With the proposed approach, the hidden state and unknown parameters can be updated at each sampling instant. Subsequently, the analytical solution for the remaining useful life is obtained, while the characteristics of the shocks as well as the uncertainties of the estimated system state are taken into account. Furthermore, the effectiveness of the proposed model is verified by a numerical simulation and a practical case study on a milling machine.

Keywords: Non-stationary degradation; remaining useful life prediction; shock model; Wiener process (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/1748006X17706654 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:risrel:v:231:y:2017:i:5:p:469-480

DOI: 10.1177/1748006X17706654

Access Statistics for this article

More articles in Journal of Risk and Reliability
Bibliographic data for series maintained by SAGE Publications ().