Applying Case-Based Reasoning to Mechanical Bearing Design

Published

September 1, 2000

Author(s)

Xiaoli Qin, William Regli

Abstract

Case-Based Reasoning (CBR) provides a promising methodology for solving many complex engineering design problems. CBR is based on the idea that past problem-solving experiences can be reused and learned from in solving new problems. This paper presents an overview of a CBR design system to assist human engineers in performing mechanical bearing design. It retrieves previously designed cases from a case-base and uses adaptation techniques to adapt them to satisfy the current problem requirements. Our approach combines parametric adaptations and constraint satisfaction adaptations. The technique of parametric adaptation considers not only parameter substitution, but also the interrelationships between the problem definition and its solution. The technique of constraint satisfaction adaptation provides a method to globally check the design requirements to assess case adaptability. Currently, our system has been tested in the rolling bearing domain.

Proceedings Title

Proceedings of the 2000 ASME Design Engineering Technical Conferences, Code:DETC2000/DFM-14011

Conference Dates

September 10-13, 2000

Conference Location

Baltimore, MD, USA

Pub Type

Conferences

Download Paper

Local Download

Keywords

Case-Based Reasoning (CBR), engineering design, manufacturing

Citation

Qin, X. and Regli, W. (2000), Applying Case-Based Reasoning to Mechanical Bearing Design, Proceedings of the 2000 ASME Design Engineering Technical Conferences, Code:DETC2000/DFM-14011, Baltimore, MD, USA, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=821994 (Accessed July 26, 2024)