Approximation of Dispatching Rules in Manufacturing Control Using Artificial Neural Networks

Automatic generation of simulation models has been a recurring topic in scientific papers for years. A common problem of all known model generation approaches is the generation of dynamic behavior, e.g. buffering or control strategies. This paper introduces a novel methodology for generation of dynamic behavior, based on artificial neural networks, which is usable directly in the simulation. We also test the approach in a manageable scenario; all results are illustrated via small simulation experiments.