A stochastic hybrid systems based framework for modeling dependent failure processes

Mengfei Fan, Zhiguo Zeng, Enrico Zio, Rui Kang and Ying Chen

PLOS ONE, 2017, vol. 12, issue 2, 1-22

Abstract: In this paper, we develop a framework to model and analyze systems that are subject to dependent, competing degradation processes and random shocks. The degradation processes are described by stochastic differential equations, whereas transitions between the system discrete states are triggered by random shocks. The modeling is, then, based on Stochastic Hybrid Systems (SHS), whose state space is comprised of a continuous state determined by stochastic differential equations and a discrete state driven by stochastic transitions and reset maps. A set of differential equations are derived to characterize the conditional moments of the state variables. System reliability and its lower bounds are estimated from these conditional moments, using the First Order Second Moment (FOSM) method and Markov inequality, respectively. The developed framework is applied to model three dependent failure processes from literature and a comparison is made to Monte Carlo simulations. The results demonstrate that the developed framework is able to yield an accurate estimation of reliability with less computational costs compared to traditional Monte Carlo-based methods.

Date: 2017
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0172680 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 72680&type=printable (application/pdf)

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:plo:pone00:0172680

DOI: 10.1371/journal.pone.0172680

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone (plosone@plos.org).