Machine Learning of Design Rules: Methodology and Case Study
Authors:
- 1 July 1994
- journal article
- Published by American Society of Civil Engineers (ASCE) in Journal of Computing in Civil Engineering
- Vol. 8 (3) , 286-308
Abstract
This paper describes a methodology for applying machine learning to problems of conceptual design, and presents a case study of learning design rules for wind bracings in tall buildings. Design rules are generated by induction from examples of minimum weight designs. This study investigates the applicability of machine learning methods that are capable of constructive induction, that is of automatically searching for and generating problem‐relevant attributes beyond those originally provided. The decision rules generated by machine learning programs specify design configurations that are recommended, typical, infeasible, or those that are to be avoided. The learned rules captured some of the essential expert's understanding of the design characteristics involved in selecting wind bracings for tall buildings. These results are promising and demonstrate a potential practical usefulness of the proposed methodology for automated generating of design rules.Keywords
This publication has 18 references indexed in Scilit:
- A neural network-based machine learning approach for supporting synthesisArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 1994
- Optimal sizing, geometrical and topological design using a genetic algorithmStructural and Multidisciplinary Optimization, 1993
- Automatically Learning Preliminary Design Knowledge from Design ExamplesComputer-Aided Civil and Infrastructure Engineering, 1992
- Design knowledge acquisition: task analysis and a partial implementationKnowledge Acquisition, 1991
- Microcomputer‐Based Optimization of Steel Structures in Professional PracticeComputer-Aided Civil and Infrastructure Engineering, 1989
- Perceptron Learning in Engineering DesignComputer-Aided Civil and Infrastructure Engineering, 1989
- A methodology of design knowledge acquisition for use in learning expert systemsInternational Journal of Man-Machine Studies, 1987
- A machine learning approach to the automatic synthesis of mechanistic knowledge for engineering decision-makingArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 1987
- Acquiring expert knowledge from characterized designsArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 1987
- A theory and methodology of inductive learningArtificial Intelligence, 1983