Production Scheduling with Artificial Neural Networks



ERIM Research Lunch Seminar
Artificial Neural Networks (ANNs) have emerged as efficient approaches in a variety of engineering applications where problems are difficult to formulate or hardly defined. They are computational structures that implement simplified models of biological processes, and are preferred for their robustness, massive parallelism and ability to learn. In metaheuristics literature, neural networks are put into local-search based metaheuristics category. The reason is their iterative master process characteristic, that is, they guide and modify the operations of subordinate heuristics to efficiently produce high quality solutions, and provide decision makers with fast and robust tools for obtaining high quality solutions in reasonable computation times to many real life problems. In the literature, although a large number of approaches such as mathematical programming, dispatching rules, expert systems, and neighborhood search to the modeling and solution of scheduling problems have been reported, over the last decades, there has been an explosion of interest in using ANNs. Certainly, as the ANNs evolve, solutions of scheduling problems will make progress. In this study, we give an overview on ANN approaches for the solution of production scheduling problems. The reviewed articles are examined under four main categories- Hopfield type networks, multilayer perceptrons, competition based networks and hybrid approaches- according to the architectures they used. Finally, recommendations for future research are suggested and the the entire procedure of employing Hopfield type dynamical neural networks to solve a scheduling problem is explained with an example.
Contact information:
Prof.dr. M.B.M. de Koster