Bivariate degradation analysis of products based on Wiener processes and copulas
Authors:
- 1 July 2013
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 83 (7) , 1316-1329
Abstract
Modern highly reliable products usually have complex structure and many functions. This means that they may have two or more performance characteristics. All the performance characteristics can reflect the product's performance degradation over time, and they may be independent or dependent. If the performance characteristics are independent, they can be modelled separately. But if they are not independent, it is very important to find the joint distribution function of the performance characteristics for estimating the reliability of the product as accurately as possible. Here, we suppose that a product has two performance characteristics and the degradation paths of these two performance characteristics can be governed by a Wiener process with a time-scale transformation, and that the dependency of the performance characteristics can be described by a copula function. The parameters of the two performance characteristics and the copula function can be estimated jointly. The model in such a situation is very complicated and analytically intractable and becomes cumbersome from a computational viewpoint. For this reason, the Bayesian Markov chain Monte Carlo method is developed for this problem that allows the maximum-likelihood estimates of the parameters to be determined in an efficient manner. For an illustration of the proposed model, a numerical example about fatigue cracks is presented.Keywords
This publication has 17 references indexed in Scilit:
- Bivariate constant stress degradation model: LED lighting system reliability estimation with two‐stage modellingQuality and Reliability Engineering International, 2009
- Analysis of joint multiple failure mode and linear degradation data with renewalsJournal of Statistical Planning and Inference, 2007
- A Review of Accelerated Test ModelsStatistical Science, 2006
- Stochastic Degradation Models With Several Accelerating VariablesIEEE Transactions on Reliability, 2006
- Optimal Design for Step-Stress Accelerated Degradation TestsIEEE Transactions on Reliability, 2006
- Gauss–Poisson Joint Distribution Model for Degradation FailureIEEE Transactions on Plasma Science, 2004
- Reliability analysis of electronic devices with multiple competing failure modes involving performance aging degradationQuality and Reliability Engineering International, 2003
- Accelerated test models with the inverse Gaussian distributionJournal of Statistical Planning and Inference, 2000
- Analyzing accelerated degradation data by nonparametric regressionIEEE Transactions on Reliability, 1999
- Reliability assessment based on accelerated degradation: a case studyIEEE Transactions on Reliability, 1991