Learning Symbolic Formulations in Design Optimization

This paper presents a learning and inference mechanism for unsupervised learning of semantic concepts from purely syntactical examples of design optimization formulation data. Symbolic design formulation is a tough problem from computational and cognitive perspectives, requiring domain and mathematical expertise. By conceptualizing the learning problem as a statistical pattern extraction problem, the algorithm uses previous design experiences to learn design concepts. It then extracts this learnt knowledge for use with new problems. The algorithm is knowledge-lean, needing only the mathematical syntax of the problem as input, and generalizes quickly over a very small training data set. We demonstrate and evaluate the method on a class of hydraulic cylinder design problems.

[1]  Shuang Song,et al.  IDENTIFYING SHARED UNDERSTANDING IN DESIGN USING DOCUMENT ANALYSIS , 2001 .

[2]  Andrew Gelsey,et al.  Using Modeling Knowledge to Guide Design Space Search , 1998, Artif. Intell..

[3]  Jonathan Cagan,et al.  Cognitive Investigations into Knowledge Representation in Engineering Design , 2004 .

[4]  John S. Gero,et al.  Learning while designing , 2004, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[5]  Jonathan Cagan,et al.  The A-Design approach to managing automated design synthesis , 2003 .

[6]  Takahiro Murata,et al.  A transformation system for interactive reformulation of design optimization strategies , 1995, Proceedings 1995 10th Knowledge-Based Software Engineering Conference.

[7]  Masaki Suwa,et al.  Unexpected discoveries and S-invention of design requirements , 2000 .

[8]  John S. Gero,et al.  A KNOWLEDGE-BASED APPROACH TO MATHEMATICAL DESIGN MODELING AND OPTIMIZATION , 1987 .

[9]  Haym Hirsh,et al.  Learning to set up numerical optimizations of engineering designs , 1998, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[10]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[11]  Panos Y. Papalambros,et al.  Principles of Optimal Design: Author Index , 2000 .

[12]  D. Kalman.  A Singularly Valuable Decomposition: The SVD of a Matrix , 1996 .

[13]  Alice M. Agogino,et al.  Text analysis for constructing design representations , 1997, Artif. Intell. Eng..

[14]  G. Strang.  Introduction to Linear Algebra , 1993 .

[15]  John S. Gero,et al.  Learning design rules from decisions and performances , 1987, Artif. Intell. Eng..

[16]  Jonathan Cagan,et al.  Learning from design experience in an agent-based design system , 2004 .

[17]  Janet K. Allen,et al.  13th International Conference on Design Theory and Methodology , 2001 .

[18]  Alice M. Agogino,et al.  Multiobjective Hydraulic Cylinder Design , 1988 .

[19]  Haym Hirsh,et al.  Learning to set up numerical optimizations of engineering designs , 1998 .