Community Research and Development Information Service - CORDIS


Components operating in NPPs are generally reliable. They experience relatively few failures even for long periods of observation, and estimation procedures for their reliability parameters are Bayesian in character. This paper proposes an empirical Bayes estimator for the failure rate of components on which times operated and times of failure are available. It presents the compound model for population heterogeneity and proposes to estimate the posterior failure rate of components with compound Poisson failures through an implicitly estimated prior. The estimator is applied on a dataset typical of samples drawn from a component event database.

Additional information

Authors: ARSENIS S P, JRC Ispra (IT)
Bibliographic Reference: Paper presented: SMIRT 12 Conference, Stuttgart (DE), August 15-20, 1993
Availability: Available from (1) as Paper EN 37327 ORA
Record Number: 199311425 / Last updated on: 1994-11-28
Original language: en
Available languages: en