Bayes reliability modeling of a multistate consecutive K-out-of-n: F system

A description is given of Bayes reliability modeling of a multistate consecutive K-out-of-n: F system, comprising independent identical multistate units, with P/sub c/, a unit state probabilities vector. The mathematical expression for the conditional system unreliability (CSU) is derived by Markov chain. A Bayesian approach is adopted in order to reflect uncertainty in P/sub c/. It is modeled by a Dirichlet distribution and propagated into CSU. The proposed model provides Bayes prediction tools for the mean values and confidence bounds of the system failure states probabilities.<
>