| Nowadays, a great number of researchers have been focus to find an approach to solve effectively manufacturing scheduling problems. The interest for this kind of problems is due to their complexity and variety. This research presents an approach for optimizing job shop scheduling problems. The main objective of our research was to find a method capable of producing a more realistic model where the produced schedule would be more robust and less sensitive to the variations in the data. Techniques that have been used to solve scheduling problems individually will be used collectively to solve the proposed problem.; In the first stage of the approach, the job shop problem is structured in the way that a genetic algorithm can be applied to find optimal or near to optimal solutions. Genetic algorithms are stochastic search algorithms based on the mechanics of genetics and natural selection. Because of genetic inheritance, the characteristics of the survivors after several generations should be similar. In using a genetic algorithm for job shop scheduling, the solution is an operational sequence for resource allocation. Among these optimal or near optimal solutions, similar relationships may exist between the characteristics of operations and sequential order. Therefore, an artificial neural network is employed to explore the patterns in the data generated by a genetic algorithm performing a scheduling operation and to develop a model, which approximates the genetic algorithm's scheduler. Since more general knowledge about the system is often available in linguistic form, fuzzy rules created from the genetic algorithm's results are introduced to incorporate knowledge into the neural networks.; As result of this research work a new approach to the job shop scheduling was obtained. This approach included a combination of genetic algorithms, fuzzy logic and neural network creating all together a flexible and a real time response system that can be used by manufacturing plants with the need of applying real time systems in their production area. |
