Open AccessJournal Article10.1017/S0890060404040090

Constructing design methodologies using multiagent systems

- 01 Apr 2004

- Ai Edam Artificial Intelligence for Engi...

- Vol. 18, Iss: 2, pp 115-134

TL;DR: An innovative approach has been developed for discovering better design methodologies that is based on simulating the design process using a multiagent system that mimics the behavior of a design team.

Abstract: An innovative approach has been developed for discovering better design methodologies that is based on simulating the design process using a multiagent system that mimics the behavior of a design team. The system implements a knowledge-based model of design in which highly specialized knowledge from expert sources is applied to synthesize a design. The agents activate 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 human design teams through future design projects.

AI Agents for this Paper

Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps

Most frequently asked questions

1. What are the contributions in "Constructing design methodologies using multi-agent systems" ?

In this paper, the same concept is applied to analyzing the design process instead of the design product, in which the design activities that are usually carried out by humans are performed by software agents in a slightly simplified manner.

2. What have the authors stated for future works in "Constructing design methodologies using multi-agent systems" ?

Design methodologies that are biased toward manufacturability, for example, can be another area of further research.. As the authors used the multi-agent design system to discover sensitive parameters as well as their boundaries, more research can be done to convert the system to an optimization tool.. Close the feedback loop around the system in which the methodologies generated by the sys- tem are fed back into it to further refine the methodology.. Simulation of complex systems using agents can be a powerful tool in analyzing why those systems behave in a certain way.

Figure 3. Integration by Breaking up the Knowledge into Smaller Segments.

Figure 9. Correlation between Requirement Space and Trace Space.

Figure 4. The Opportunistic Strategy in Activating Design Methods.

Figure 5. The Architecture of the Multi-agent Design System

Table 6. Traces taken by projects 44, 45, 46.

Citations

Journal Article•10.1115/1.4000449

Multiagent Shape Grammar Implementation: Automatically Generating Form Concepts According to a Preference Function

Seth Orsborn, +1 more

- 01 Dec 2009

- Journal of Mechanical Design

TL;DR: The inaugural multiagent shape grammar implementation (MASGI) is presented to automatically generate product form designs according to a preference function that can represent designer or consumer design preference.

...read moreread less

Book Chapter•10.1007/978-1-84628-061-0_7

Artificial intelligence for design process improvement

David C. Brown

- 01 Jan 2005

•Dissertation

Vers une CAO guidée par la connaissance des fabricants

Mael Hilléreau

- 05 Sep 2008

TL;DR: La solution proposee consiste en une modelisation des connaissances de fabrication par l'intermediaire de regles, and en l'utilisation and the reutilisation of ce savoir-faire au travers de l'approche de modelisation synthetique du projet DIJA.

...read moreread less

•Dissertation

Mnemotechne of design — ontology and design research theories

Frances Joseph

- 01 Jan 2010

TL;DR: A Mnemotechne of Design, envisaged through semantic web technologies, aims to overcome the dualistic thinking that has dominated design discourses in a project that serves design researchers in assaying the plurality of methodological frameworks that have emerged in the discipline’s approaches to research theories.

...read moreread less

•Posted Content

Holistic Complex-Systems Model to Solve Macroeconomics Issues (HC-SMSMI)

Cinthya Ivonne Mota-Hernández, +2 more

- 01 Jan 2014

- Advances in Management and Applied Econo...

TL;DR: In this paper, a new model based on Soft Systems Thinking is proposed to understand the dynamics of global financial market as well as its role in the economic system and to find new ways for analyzing them.

...read moreread less

References

Journal Article•10.1049/IP-SEN:19971026

Agent-based software engineering

Michael Wooldridge

- 01 Jan 1997

TL;DR: The paper considers the problem of building a multi-agent system as a software engineering enterprise and discusses three issues: how agents might be specified; how these specifications might be refined or otherwise transformed into efficient implementations: and how implemented agents and multi- agent systems might subsequently be verified, to show that they are correct with respect to their specifications.

...read moreread less

1.5K

•Book

Introduction To Expert Systems

Peter Jackson

- 01 Apr 1986

TL;DR: The third edition of Peter Jackson's book, Introduction to Expert Systems, updates the technological base of expert systems research and embeds those results in the context of a wide variety of application areas.

...read moreread less

1.5K

Book Chapter•10.1016/B978-1-4832-0773-5.50018-3

The formation and use of abstract concepts in design

Yoram Reich, +1 more

- 01 Sep 1991

TL;DR: The chapter presents BRIDGER, which is a concept formation system that partially automates the acquisition of design knowledge for a class of design domains in which the structure of the artifact is fixed.

...read moreread less

101

Journal Article•10.1177/1063293X9600400407

Modeling for Concurrent Design Using Game Theory Formulations

K. Badhrinath, +1 more

- 01 Dec 1996

- Concurrent Engineering

TL;DR: The solutions in these models show how the final design out come can be predicted based on the different interactions that may occur between the decision makers in concurrent design project.

...read moreread less

Discovery of design methodologies for the integration of multi-disciplinary design problems

Cirrus Shakeri

- 01 Dec 1998

TL;DR: In this paper, an 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, where highly specialized knowledge from expert sources is applied to synthesize a design.

...read moreread less

Constructing design methodologies using multiagent systems

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions in "Constructing design methodologies using multi-agent systems" ?

2. What have the authors stated for future works in "Constructing design methodologies using multi-agent systems" ?

Figures

Citations

Multiagent Shape Grammar Implementation: Automatically Generating Form Concepts According to a Preference Function

Artificial intelligence for design process improvement

Vers une CAO guidée par la connaissance des fabricants

Mnemotechne of design — ontology and design research theories

Holistic Complex-Systems Model to Solve Macroeconomics Issues (HC-SMSMI)

References

Agent-based software engineering

Introduction To Expert Systems

The formation and use of abstract concepts in design

Modeling for Concurrent Design Using Game Theory Formulations

Discovery of design methodologies for the integration of multi-disciplinary design problems

Related Papers (5)

Towards a knowledge-based design support environment for design automation and performance evaluation

Case-based design and learning in telecommunications

Design integrated learning systems for engineering design

ALEX: A Knowledge-Based Architectural Design System

Design and implementation of an agent-based collaborative product design system