Power distribution companies must establish an optimal maintenance schedule that balances reliability and efficiency of a number of widely scattered facilities. Conventionally, Japanese power utilities divide their distribution areas into multiple inspection areas, and they maintain high reliability by periodically inspecting each area. A time-based maintenance scheme is generally inefficient. This paper proposes a method of optimizing inspection schedules of Japanese distribution facilities. A condition model is presented that predicts the next inspection timing of each facility using past inspection data. Moreover, an algorithm to minimize the inspection cost based on the predicted inspection timing is proposed. The algorithm can efficiently calculate the optimal combination of two inspection schemes, an area inspection scheme and an individual inspection scheme. Simulation results with test data show that the algorithm reduces the inspection cost by 15%. The proposed method results in a more effective inspection schedule.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.