Dynamic Work Planning by Using Simulation-based Optimization in Consideration of Workers’ Skill and Training∗

High-skill tasks such as aircraft maintenance procedures generally require considerable on-the-job training (OJT). Because OJT requires a considerable amount of time, longterm scheduling of OJT by considering both working efficiency and skill development is required. The authors have proposed education coefficient (EC) as a parameter that adjusts the frequency of OJT and have proposed a scheduling support system for longterm scheduling of OJT considering working efficiency and skill education. Users of the proposed scheduling support system can easily adjust the balance between working efficiency and skill education by changing EC. However, it is difficult for them to find effective values of EC that realize a good balance between working efficiency and skill education to maintain a certain number of skilled workers. In this paper, we propose a simulation-based scheduling optimization system using a simple genetic algorithm (GA). The purpose of this study is to adjust the value of EC automatically by considering the balance between working efficiency and skill education and to find effective rules for adjusting the value of EC. The experimental results show that the proposed system computes solutions that are better than those computed by using a constant EC.