Bayesian Modeling of Time Trends in Component Reliability Data Vai Markov Chain Monte Carlo Simulation. 2007 ESREL Safety and Reliability Conference.

Kelly, D. L.

Technical Information Center Oak Ridge Tennessee

关键词: Simulation;    Bayesian methods;    Reliability;    Trends;    Monte carlo method;   

RP-ID  :  DE2007911890

学科分类：工程和技术（综合）

美国|英语

来源: National Technical Reports Library

【 摘 要 】

Markov chain Monte Carlo (MCMC) techniques represent an extremely flexible and powerful approach to Bayesian modeling. This work illustrates the application of such techniques to time-dependent reliability of components with repair. The WinBUGS package is used to illustrate, via examples, how Bayesian techniques can be used for parametric statistical modeling of time-dependent component reliability. Additionally, the crucial, but often overlooked subject of model validation is discussed, and summary statistics for judging the models ability to replicate the observed data are developed, based on the posterior predictive distribution for the parameters of interest.