A study in applying case-based reasoning to engineering design: Mechanical bearing design
- 1 August 2003
- journal article
- research article
- Published by Cambridge University Press (CUP) in Artificial Intelligence for Engineering Design, Analysis and Manufacturing
- Vol. 17 (3) , 235-252
Abstract
Case-based reasoning (CBR) is a promising methodology for solving many complex engineering design problems. CBR employs past problem-solving experiences when solving new problems. This paper presents a case study of how to apply CBR to a specific engineering problem: mechanical bearing design. A system is developed that retrieves previous design cases from a case repository and uses adaptation techniques to modify them to satisfy the current problem requirements. The approach combines both parametric and constraint satisfaction adaptations. Parametric adaptation considers not only parameter substitution but also the interrelationships between the problem definition and its solution. Constraint satisfaction provides a method to globally check the design requirements to assess case adaptability. Currently, our system has been implemented and tested in the domain of rolling bearings. This work serves as a template for application of CBR techniques to realistic engineering problems.Keywords
This publication has 27 references indexed in Scilit:
- Design rationale systems: understanding the issuesIEEE Expert, 1997
- Functional reasoning in designIEEE Expert, 1997
- Developing case-based reasoning for structural designIEEE Expert, 1996
- Variant design for mechanical artifacts: A state-of-the-art surveyEngineering with Computers, 1996
- Discovery of physical principles from design experiencesArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 1994
- Exploring case-Based building design—CADREArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 1993
- Introduction: Issues in case-based design systemsArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 1993
- Case-based reasoning and learning in manufacturing with the TOLTEC plannerIEEE Transactions on Systems, Man, and Cybernetics, 1993
- Innovative design systems: where are we, and where do we go from here? Part II: Design by explorationThe Knowledge Engineering Review, 1992
- Innovative design Systems, where are we and where do we go from here? Part I: Design by associationThe Knowledge Engineering Review, 1992