An availability-based system with general repair via Bayesian aspect.

We study the Bayesian inferences of an availability system with reboot delay and standby switching failures, in which the system consists of one active component and one warm standby. The system is studied under the assumption that the time-to-failure and the time-to-repair are assumed to follow an exponential and a general distribution. The reboot time is assumed to be exponentially distributed with parameter β. There is always the failure possibility c during the switching process from standby-component state to the active-component state. To implement the simulation inference for the system availability, two repair-time distributions, namely, the lognormal and Erlang distributions characterized by their shape parameters are considered. Finally, all simulation results are displayed by appropriate tables and curves to analyze the performance of the statistical inference procedures.