Search

Multi-state systems, which widely exist in the industrial and military field, are usually required to execute a series of missions with a finite break between two adjacent missions. To improve the system reliability and guarantee the success of the next mission, selective maintenance strategy is proposed to identify a subset of feasible maintenance actions under limited maintenance resources. In this paper, a novel selective maintenance model for a series-parallel multi-state system consisting of multi-state components is developed to minimize the overall maintenance cost. The validity of the selective maintenance model is demonstrated via an illustrative example of an aircraft gas turbine engine system. A comparative analysis between perfect maintenance strategy and imperfect maintenance strategy is conducted, and the result indicates that the imperfect maintenance is more cost-effective than perfect maintenance.

Many industrial systems such as aircrafts, ships, manufacturing systems, etc. are required to perform several missions with finite breaks between missions. Maintenance is only available within the breaks. Due to the limitation of resources, all components in the system may not be maintained as desired. The selective maintenance problem helps the decision makers figure out what critical components to select and how to perform maintenance on these components. This paper studies the selective maintenance for multi-state series-parallel systems with the benefit of repairing multiple components simultaneously. Both time and cost savings can be acquired when several components are simultaneously repaired in a selective maintenance strategy. As the number of repaired components increases, the saved time and cost will also increase due to the share of setting up between components and another additional reduction amount from the repair of multiple identical components. A non-linear optimization model is developed to find the most reliable system subjected to time and cost constraints. Genetic algorithm is used to solve the optimization model. An illustrative example will be provided.