Research into Expert Systems to Aid Simulation Model Formulation

The widespread availability of inexpensive computing power and recent developments in machine intelligence now makes it possible to consider computer assistance in the formulation phase of a discrete-event simulation model. The goal is to speed up this process. With this in mind, a series of prototype expert systems (written in LISP and run on an APPLE II) have been produced. The first prototype system was built using the ‘MYCIN’ approach. In the second prototype system a more informal approach was used, and the resulting computer-aided system is a natural-language understanding system. This paper outlines the need for such research and discusses the system development by describing the two main models and explaining why the natural-language approach was adopted.