An Evo-Devo Framework for Computational Design Synthesis Based on a Regulation Process

Evolutionary design synthesis has been used in solving many engineering design problems due to the reliability, robustness and domain-independence of evolutionary algorithms . However, little has been done to explore the role of design knowledge in evolutionary design synthesis. In this paper, inspired by recent advances in evolutionary developmental biology (Evo-Devo), we propose an Evo-Devo framework for computational design synthesis that utilizes design knowledge to guide an evolutionary search processes. The framework embodies a new regulation process to derive feasible phenotypes from the synthesis of genotypes and design knowledge. A multi -agent system (MAS) is implemented to perform the regulation needed to enforce the constraint satisfaction of phenotypes. The practical applicability of the Evo-Devo framework is validated through a meal design problem to be solved as a case study. The results indicate that the Evo-Devo framework and its regulation process outperform traditional processes in terms of effectiveness, efficiency and reliability in searching a constrained design space. The proposed framework and the MAS-based implementation of t he regulation process can be applied to improve the performance of evolutionary design synthesis in different domains and tasks in general.

[1]  Jonathan Cagan,et al.  A Framework for Computational Design Synthesis: Model and Applications , 2005, J. Comput. Inf. Sci. Eng..

[2]  Peter J. Bentley,et al.  Evolutionary Design by Computers with CDrom , 1999 .

[3]  Jonathan Cagan,et al.  Formal Engineering Design Synthesis , 2005 .

[4]  William E. Hart,et al.  The Role of Development in Genetic Algorithms , 1994, FOGA.

[5]  Risto Miikkulainen,et al.  A Taxonomy for Artificial Embryogeny , 2003, Artificial Life.

[6]  Lawrence Davis,et al.  Using a genetic algorithm to optimize problems with feasibility constraints , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[7]  Anikó Ekárt,et al.  Genetic algorithms in computer aided design , 2003, Comput. Aided Des..

[8]  J. Jiao,et al.  Product portfolio planning with customer-engineering interaction , 2005 .

[9]  Makoto Yokoo,et al.  The Distributed Constraint Satisfaction Problem: Formalization and Algorithms , 1998, IEEE Trans. Knowl. Data Eng..

[10]  B. Lieberman,et al.  Evolutionary Developmental Biology , 1993 .

[11]  Peter J. Bentley,et al.  Evolutionary Design By Computers , 1999 .

[12]  Susan Carlson-Skalak,et al.  Using an evolutionary algorithm for catalog design , 1998 .

[13]  John S. Gero,et al.  A Genetic Engineering Approach to Genetic Algorithms , 2001, Evolutionary Computation.

[14]  J. Gero,et al.  Evolving designs by generating useful complex gene structures , 1999 .

[15]  Timothy W. Simpson,et al.  A genetic algorithm based method for product family design optimization , 2003 .

[16]  Robert F. Woodbury,et al.  Whither design space? , 2006, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[17]  Peter J. Bentley,et al.  Three Ways to Grow Designs: A Comparison of Embryogenies for an Evolutionary Design Problem , 1999, GECCO.

[18]  Peter J. Bentley,et al.  Computational Embryology: Past, Present and Future , 2000 .

[19]  Andrew Y. C. Nee,et al.  An Adaptive Machining Fixture Design System for Automatically Dealing With Design Changes , 2007, J. Comput. Inf. Sci. Eng..

[20]  Andrés Gómez de Silva Garza,et al.  A Process Model for Evolutionary Design Case Adaptation , 2000, AID.

[21]  John R. Koza,et al.  Automated Design of Both the Topology and Sizing of Analog Electrical Circuits Using Genetic Programming , 1996 .

[22]  M. West-Eberhard.  Developmental plasticity and evolution , 2003 .