Flexible Job-Shop Problem with Predictive Maintenance Planning Using Genetic Algorithm

The most common disruptions and emerging challenges that manufacturing systems frequently encounter include the arrival of new orders, last-minute order cancellations, unforeseen machine breakdowns, and alterations in due dates. To effectively respond to these challenges, production schedules are continually adjusted by implementing real-time rescheduling mechanisms that rely on up-to-the-minute data from the shop floor. In this paper we propose a dynamic process for simultaneous planing of production and predictive maintenance planning in a flexible job-shop environment using genetic algorithm. The proposes model leverages real-time information from Prognostics and Health Management modules to assess the health status of machines. The integration of predictive maintenance significantly reduces both the risk of machine breakdowns and maintenance cost, enhancing the robustness and efficiency of job shop scheduling in dynamic manufacturing environments.