Faculty Advisor or Committee Member

Professor David C. Brown, Advisor

Faculty Advisor or Committee Member

Professor Mohammad N. Noori, Advisor

Faculty Advisor or Committee Member

Professor Michael A. Demetriou, Committee Member

Faculty Advisor or Committee Member

Professor Allen H. Hoffman, Committee Member

Faculty Advisor or Committee Member

Dr. Susan E. Lander, Committee Member

Faculty Advisor or Committee Member

Professor John M. Sullivan, Jr., Committee Member

Identifier

etd-101399-155624

Abstract

"In order to succeed in today’s global, competitive market, manufacturing industries need continuous improvements in their multi-disciplinary design processes. These improvements should result in expending fewer resources on the design process while achieving better quality and more environmentally friendly products. The current approach for improving design processes is mostly based on intuitive observations followed by incremental changes to the existing methodologies. However, today’s fast-paced world needs rapid incorporation of new technologies and methods into design methodologies. Recent advances in the application of Artificial Intelligence to design Multi-agent Design Systems in particular-provide an opportunity to accomplish this goal. The inter-disciplinary collaboration between Computer Science and Engineering Design provides the means to develop systematic and holistic approaches for constructing superior design methodologies. An innovative approach has been developed that is based on simulating the design process using a multi-agent system that mimics the behavior of the design team. The multi-agent system implements a knowledge-based model of design in which highly specialized knowledge from expert sources is applied to synthesize a design. The multi-agent 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 inductive learning techniques to generalize the traces generated. These methodologies then can be used to guide design teams through future design projects."

Publisher

Worcester Polytechnic Institute

Degree Name

PhD

Department

Mechanical Engineering

Project Type

Dissertation

Date Accepted

1999-10-13

Accessibility

Unrestricted

Subjects

interdisciplinary, multi-agent, methodology discovery, design, artificial intelligence, Computer-aided design, Expert systems (Computer science), Engineering design, Data processing

Share

COinS