Development of a optimization model and solution approach for scheduling parallel machines used in production of composite material

We tackle a scheduling problem encountered in a real production department that produces composite parts in an aircraft manufacturing plant. Two main steps in the production process of composite parts are mounting the composite parts on molds and then heat treatment of the parts in pressurized parallel ovens, called autoclaves. Parts have different process requirements in terms of heating level, pressure, and time. Only the compatible parts can go into the same autoclaves together in a batch. The scheduling problem is about the second step of the process and it involves batching the parts together and then scheduling batches into the autoclaves. The problem has several different types of constraints, such as the capacity of autoclave in terms of space and thermocouple, the number of molds available for the process, due dates, the earliest and latest processing time for parts, and the sequence status of parts. The objective is taken as the minimization of the energy consumption since the autoclaves consume high levels of electricity. Closest problem to our problem in the literature is called batch scheduling with incompatible job families. In this study we introduced a mathematical model of the problem and preliminary solutions were obtained under different scenarios. Since the problem is in the NP-hard category, solutions cannot be obtained in a reasonable time for complex problems. For this reason, the K-means algorithm is developed for the problem, which divides the works into batches then schedules the batches to the furnaces, obtains the first feasible solution, and improves the schedules by the variable neighbor search (DKA) algorithm. In this way parameter sensitivity analysis of the mathematical model and the performance of the developed heuristic tested. As a result of the tests, it was observed that the heuristic algorithm deviated from the optimal by 5,12732% on average. Keywords: Batch scheduling, Incompatible job families, Mathematical modeling, Heuristic algorithm