• 목록

Improving quality and reducing product completion time in a multistage manufacturing process is a critical challenge. This paper proposes a method to solve the multistage manufacturing process scheduling problem identifying process paths that yield high quality using reinforcement learning. Environment module and products agent module are constructed. For quality, we estimated main and interaction effects of machines on the quality and used them as rewards. For productivity, product agent makes actions for each product by interacting with environment module that consists machines status and machines queue. This dual-focus strategy aims to optimize path selections to maximize productivity and ensure high quality, offering solution for effective scheduling in complex, large-scale multistage manufacturing environments.