Hostname: page-component-586b7cd67f-dsjbd Total loading time: 0 Render date: 2024-11-22T23:13:22.670Z Has data issue: false hasContentIssue false

SEED-Config: A case-based reasoning system for conceptual building design

Published online by Cambridge University Press:  07 February 2001

HUGUES RIVARD
Affiliation:
Centre for Building Studies, Department of Building, Civil, and Environmental Engineering, Concordia University, Montreal, QC, H3G 1M8, Canada
STEVEN J. FENVES
Affiliation:
Department of Civil and Environmental Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213, U.S.A.

Abstract

A case-based design functionality is a natural and intuitive addition to a design tool that can augment human capabilities and help designers remember and retrieve appropriate cases. SEED-Config, a design environment for conceptual building design, was developed to incorporate a case-based reasoning functionality to provide designers with initial potential solutions. The case representation in SEED-Config is the BENT information model, which records design knowledge, supports the hierarchical decomposition of design cases, offers multiple views, and encapsulates the outcome of the design in addition to the problem specification and the design solution. The case library was implemented in an object-oriented database management system to accumulate cases automatically and to provide efficient query facilities. The case retrieval aspect of SEED-Config offers three different methods to find the most useful cases stored in the case library: task-based, lineage-based, and customized. Case retrieval responds to the exploratory nature of the design process and supports versatile case retrieval by providing multiple paths to each case. The case adaptation aspect, which adjusts the selected case to the new problem to provide a complete solution, uses an adaptation method called derivational replay. The case-based design capabilities are completely integrated within the design environment from which the cases originate.

Type
Research Article
Copyright
© 2000 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)