We present a two-step technique for learning reusable design procedures from observations of a designer in action. This technique is intended for the domain of parametric design problems in which the designer iteratively adjusts the parameters of a design so as to satisfy the design requirements. In the first step of the two-step learning process, decision tree learning is used to infer rules that predict which design parameter the designer is likely to change for any particular state of an evolving design. In the second step, decision tree learning is again used, but this time to learn explicit termination conditions for the rules learned in the first step. The termination conditions are used to predict how large of a parameter change should be made when a rule is applied. The learned rules and termination conditions can be used to automatically solve new design problems with a minimum of human intervention. Experiments with this technique suggest that it can reproduce the decision making process observed from the designer, and it is considerably more efficient than the previous technique, which was incapable of learning explicit rule termination conditions. In particular, the rule termination conditions allow the new program to automatically solve design problems with far fewer iterations than previously required.
Skip Nav Destination
e-mail: Kevin.Rawson@ngc.com
e-mail: stahov@engr.ucr.edu
Article navigation
March 2009
Research Papers
Learning Design Rules With Explicit Termination Conditions to Enable Efficient Automated Design
Kevin Rawson,
Kevin Rawson
Department of Mechanical Engineering,
e-mail: Kevin.Rawson@ngc.com
University of California
, Riverside, CA 92521
Search for other works by this author on:
Thomas F. Stahovich
Thomas F. Stahovich
Department of Mechanical Engineering,
e-mail: stahov@engr.ucr.edu
University of California
, Riverside, CA 92521
Search for other works by this author on:
Kevin Rawson
Department of Mechanical Engineering,
University of California
, Riverside, CA 92521e-mail: Kevin.Rawson@ngc.com
Thomas F. Stahovich
Department of Mechanical Engineering,
University of California
, Riverside, CA 92521e-mail: stahov@engr.ucr.edu
J. Mech. Des. Mar 2009, 131(3): 031011 (11 pages)
Published Online: March 9, 2009
Article history
Received:
February 16, 2008
Revised:
October 28, 2008
Published:
March 9, 2009
Citation
Rawson, K., and Stahovich, T. F. (March 9, 2009). "Learning Design Rules With Explicit Termination Conditions to Enable Efficient Automated Design." ASME. J. Mech. Des. March 2009; 131(3): 031011. https://doi.org/10.1115/1.3066681
Download citation file:
Get Email Alerts
Cited By
Related Articles
Special Issue on Computing Technologies to Support Geometric Dimensioning & Tolerancing (GD&T)
J. Comput. Inf. Sci. Eng (March,2003)
A Study to Understand Perceptual Discrepancies Using Visual Illusions and Data Envelopment Analysis (DEA)
J. Mech. Des (July,2007)
Data-Driven Decision Tree Classification for Product Portfolio Design Optimization
J. Comput. Inf. Sci. Eng (December,2009)
Intelligent Support for Product Design: Looking Backward, Looking
Forward
J. Comput. Inf. Sci. Eng (June,2011)
Related Proceedings Papers
Related Chapters
Introduction
Marketing of Engineering Consultancy Services: A Global Perspective
Concurrent Design Model for Variant Product Design
International Conference on Mechanical Engineering and Technology (ICMET-London 2011)
Processing Free Form Objects within a Product Development Process Framework
Advances in Computers and Information in Engineering Research, Volume 1