Use of copula functions for the reliability of series systems
International Journal of Quality & Reliability Management
ISSN: 0265-671X
Article publication date: 1 June 2015
Abstract
Purpose
The purpose of this paper is to provide a new method to estimate the reliability of series system by using copula functions. This problem is of great interest in industrial and engineering applications.
Design/methodology/approach
The authors introduce copula functions and consider a Bayesian analysis for the proposed models with application to the simulated data.
Findings
The use of copula functions for modeling the bivariate distribution could be a good alternative to estimate the reliability of a two components series system. From the results of this study, the authors observe that they get accurate Bayesian inferences for the reliability function considering large samples sizes. The Bayesian parametric models proposed also allow the assessment of system reliability for multicomponent systems simultaneously.
Originality/value
Usually, the studies of systems reliability engineering assume independence among the component lifetimes. In the approach the authors consider a dependence structure. Using standard classical inference methods based on asymptotical normality of the maximum likelihood estimators for the parameters the authors could have great computational difficulties and possibly, not accurate inference results, which there is not found in the approach.
Keywords
Citation
Achcar, J.A. and Moala, F.A. (2015), "Use of copula functions for the reliability of series systems", International Journal of Quality & Reliability Management, Vol. 32 No. 6, pp. 617-634. https://doi.org/10.1108/IJQRM-10-2013-0161
Publisher
:Emerald Group Publishing Limited
Copyright © 2015, Emerald Group Publishing Limited