Optimization of Joint Replacement Policies for Multipart Systems by a Rollout Framework

Abstract

Abstract-Maintaining an asset with life-limited parts, e.g., a jet engine or an electric generator, may be costly. Certain costs, e.g., setup cost, can be shared if some parts of the asset are replaced jointly. Reducing the maintenance cost by good joint replacement policies is difficult in view of complicate asset dynamics, large problem sizes and the irregular optimal policy structures. This paper addresses these difficulties by using a rollout optimization framework. Based on a novel application of time-aggregated Markov decision processes, the "One-Stage Analysis" method is first developed. The policies obtained from the method are investigated and their effectiveness is demonstrated by examples. This method and the existing threshold method are then improved by the "rollout algorithm" for the total cost case and the average cost case. Based on ordinal optimization, it is shown that excessive simulations are not necessary for the rollout algorithm. Numerical testing demonstrates that the policies obtained by the rollout algorithms with either the "One-Stage Analysis" or the threshold method significantly outperform traditional threshold policies.Note to Practitioners-Maintaining an asset with life-limited parts, e.g., a jet engine or an electric generator, over its lifetime may be costly. Optimizing maintenance policies, however, is difficult because of complicated asset dynamics, large problem sizes, and irregular optimal policy structures. This paper addresses the problem by a rollout optimization framework. In this framework, the "One-Stage Analysis" method, which minimizes the expected average cost over one maintenance period, is first developed and investigated. The policies, obtained by either the "One-Stage Analysis" method or the existing threshold method, are used in simulation to evaluate and select good actions. Similar to those learning approaches, this simulation-based framework is flexible for variant performance criteria, e.g., total cost or average cost, and is applicable to problems without explicit mathematical models. Numerical results demonstrate that effective policies can be obtained by the rollout framework in a computationally efficient way and they significantly outperform traditional threshold policies.