To schedule a job shop, the first task is to select an appropriate scheduling algorithm or rules. Because of the complexity of scheduling problems, no general algorithmic approach sufficient for solving all scheduling problems has been developed yet. Most scheduling systems offer multiple alternative algorithms to various circumstances, and experienced human schedulers are needed to select the appropriate dispatching rules in these systems.

To automate scheduling process, this paper discusses the use of neural networks for scheduling decision making. For a given workshop, various situations are simulated to identify the best dispatching rule. The inputs and outputs of the simulation model are used to train an artificial neural network. The trained neural network then will be used to automatically selecting an appropriate dispatching rule for a given situation.

Research results have shown great potential in using a neural network to replace human schedulers in selecting an appropriate approach for real time scheduling. This research is a part of an ongoing project of developing a real-time planning and scheduling system.

This content is only available via PDF.
You do not currently have access to this content.