Joint Optimization of Maintenance and Production Scheduling for Multi-component Systems

To address the impact of maintenance time during production scheduling processes and the impact of production scheduling on maintenance optimization, a joint modeling of maintenance and scheduling is proposed. Simultaneously, considering the interdependencies within multi-component systems, economic dependency is taken into account in maintenance optimization. For the joint model, a two-stage approach is introduced. In the first stage, deep reinforcement learning is employed for maintenance optimization considering production plans, with production information incorporated into the state space. In the second stage, maintenance strategies obtained from the first stage are utilized. Maintenance time and cost during production are considered in the optimization model, and genetic algorithm is used to solve the optimization problem.