Published in WPI-CS-TR-99-28, Computer Science Department, WPI, Worcester, MA, September 28, 1999. 19 pages.
NOTE: At the time of publication, the author Mohammad N. Noori was affiliated with Worcester Polytechnic Institute. Currently, August 2008, he is the Dean of the College of Engineering at California Polytechnic State University - San Luis Obispo.
In this paper we present an AI-based approach for the discovery of design methodologies for multi-disciplinary design situations. The approach is based on simulating the design process using a multi-agent system that mimics the behavior of the design team. The system activates the pieces of design knowledge when they become applicable. The use of knowledge by agents is recorded by tracing the steps that the agents have taken during a design project. Many traces are generated by solving a large number of design projects that differ in their requirements. A set of design methodologies is constructed by using clustering techniques to generalize the traces. These methodologies can be used to guide design teams through design projects.