This paper presents a design optimization problem reformulation method based on singular value decomposition, dimensionality reduction, and unsupervised clustering. The method calculates linear approximations of associative patterns of symbol co-occurrences in a design problem representation to induce implicit coupling strengths between variables and constraints. Unsupervised clustering of these approximations is used to heuristically identify useful reformulations. In contrast to knowledge-rich Artificial Intelligence methods, this method derives from a knowledge-lean, unsupervised pattern recognition perspective. We explain the method on an analytically formulated decomposition problem, and apply it to various analytic and nonanalytic problem forms to demonstrate design decomposition and design “case” identification. A single method is used to demonstrate multiple design reformulation tasks. The results show that the method can be used to infer multiple well-formed reformulations starting from a single problem representation in a knowledge-lean manner.
Skip Nav Destination
e-mail: ssar3264@mail.usyd.edu.au
e-mail: andy@arch.usyd.edu.au
Article navigation
August 2009
Research Papers
Design Optimization Problem Reformulation Using Singular Value Decomposition
Somwrita Sarkar,
Somwrita Sarkar
Graduate Student
Faculty of Architecture, Design and Planning,
e-mail: ssar3264@mail.usyd.edu.au
University of Sydney
, Australia
Search for other works by this author on:
Andy Dong,
Andy Dong
Senior Lecturer
Faculty of Architecture, Design and Planning,
e-mail: andy@arch.usyd.edu.au
University of Sydney
, Australia
Search for other works by this author on:
John S. Gero
John S. Gero
Research Professor
Search for other works by this author on:
Somwrita Sarkar
Graduate Student
Faculty of Architecture, Design and Planning,
University of Sydney
, Australiae-mail: ssar3264@mail.usyd.edu.au
Andy Dong
Senior Lecturer
Faculty of Architecture, Design and Planning,
University of Sydney
, Australiae-mail: andy@arch.usyd.edu.au
John S. Gero
Research Professor
J. Mech. Des. Aug 2009, 131(8): 081006 (10 pages)
Published Online: July 20, 2009
Article history
Received:
September 24, 2008
Revised:
May 21, 2009
Published:
July 20, 2009
Citation
Sarkar, S., Dong, A., and Gero, J. S. (July 20, 2009). "Design Optimization Problem Reformulation Using Singular Value Decomposition." ASME. J. Mech. Des. August 2009; 131(8): 081006. https://doi.org/10.1115/1.3179148
Download citation file:
Get Email Alerts
A Visual Representation of Engineering Catalogs Using Variational Autoencoders
J. Mech. Des (April 2025)
Datasets in Engineering Design
J. Mech. Des
Related Articles
10th Anniversary Special Issue: From Fringe to Mainstream—We Have Come a Long Way
J. Comput. Inf. Sci. Eng (June,2011)
Rational Be´zier Line-Symmetric Motions
J. Mech. Des (March,2005)
Special Issue on Computing Technologies to Support Geometric Dimensioning & Tolerancing (GD&T)
J. Comput. Inf. Sci. Eng (March,2003)
Nonlinear Problems in Machine Design
Appl. Mech. Rev (September,2001)
Related Proceedings Papers
Related Chapters
Artificial Intelligence in Wind Energy
Wind Energy Applications
Exchange Helical Shape from a Mechanical CAD System to a Ship CAD System Based on Shape Approximation
International Conference on Instrumentation, Measurement, Circuits and Systems (ICIMCS 2011)
On the Similarity of Test Paper in the Intelligent System of Test Paper Composition
International Symposium on Information Engineering and Electronic Commerce, 3rd (IEEC 2011)