Simulation strategies to identify the failure parameters of repairable systems under the influence of general repair

With repairable systems, it is suspected than many of the post‐failure repairs have the effect of partially resetting the failure rate of the system. Consequently, identifying the correct failure model and its associated parameters is confounded by the impact of these repair effects. The purpose of this paper is to compare the use of several simulation strategies involving mimicking experiments, to assist in this identification process. Data collected from a hydrelectric turbine unit is used to illustrate the approach.