Toward a Soft Computing Integrated Intelligent Design Framework

DS 58-6: Proceedings of ICED 09, the 17th International Conference on Engineering Design, Vol. 6, Design Methods and Tools (pt. 2), Palo Alto, CA, USA, 24.-27.08.2009

Year: 2009
Editor: Norell Bergendahl, M.; Grimheden, M.; Leifer, L.; Skogstad, P.; Lindemann, U.
Author: Zha, Xuan F.
Series: ICED
Section: Design Methods and Tools
Page(s): 439-450

Abstract

In this paper, a novel integrated intelligent framework is first proposed for virtual product design and prototyping based upon the hybrid intelligent and soft computing techniques. Then, a comprehensive evolutionary neuro-fuzzy model (EFNN) which is a five-layer fuzzy (rule-based) neural network that combines fuzzy logic, neural networks, and genetic algorithms is developed to support modeling, analysis and evaluation, and optimization tasks in the complex design process. The developed model, framework and system (EFNN-HIDS) provides a unified integrated intelligent environment for virtual prototyping, design and simulation, and customization of complex engineering systems and products. Case studies are provided to illustrate and verify the proposed model and framework.

Keywords: Hybrid intelligent design system (HIDS), soft computing, computational intelligence, evolutionary neuro-fuzzy modeling, evolutionary fuzzy neural network, design pattern, integration, virtual design and prototyping, customization, simulation

Download