Job shop scheduling with metaheuristic approaches and artificial neural network application

Since production scheduling is considered as short-term plans for the future in production planning, the advantages of effective scheduling and control and its contribution to the production process are numerous. Efficient use of resources improves productivity and ensures that orders are met on time for customers. Even the simplest scheduling system has a complex solution structure. Long lead times also make it difficult to estimate the demand accurately. It is very important to solve scheduling problems effectively for such difficult-to-manage production processes. Job shop scheduling problems are among the combinatorial problems in the NP-hard problems class. As constraints increase in such problems, the solution space starts to go to infinity and it becomes increasingly difficult to find the exact optimum solution. For this reason, in recent years, meteheuristic algorithms have been used to solve such problems. In this thesis, metaheuristic methods and literature studies used for JSS are explained. In addition, an artificial neural network algorithm has been developed by using the C# programming language for scheduling. Total processing time (i.e. makespan) was calculated by using the ANN method on Taillard Job Shop benchmark instances. The results were compared with the ones reported in the literature.