DocumentCode :
2781208
Title :
A constraint based evolutionary decision support system for product design
Author :
Guoyan, Yu ; Xiaozhen, Wang ; Peng, Li
Author_Institution :
Eng. Coll., Guangdong Ocean Univ., Zhanjiang, China
fYear :
2009
fDate :
17-19 June 2009
Firstpage :
2585
Lastpage :
2590
Abstract :
At conceptual design stage, designers often tend to be restricted by general stereotypes and by their previous design experiences. Consequently, this paper proposes a constraint-based cooperative interactive design method, in order to combine human intelligence and computer intelligence for product design. The model of constraint based human machine cooperative interactive design system is described, how to realize the human machine cooperative interactive optimal search by genetic algorithm (GA) is discussed in detail. In design process, GA is employed to search for a near-optimal design, and a trained neural network is used as a fitness function. Finally, a mould injection structure design is chosen as the subject of the current investigation.
Keywords :
CAD/CAM; decision support systems; genetic algorithms; injection moulding; learning (artificial intelligence); man-machine systems; moulding equipment; product design; search problems; constraint-based cooperative interactive design method; evolutionary decision support system; genetic algorithm; human intelligence; human machine cooperative interactive optimal search; mould injection structure design; neural network training; product design; Algorithm design and analysis; Competitive intelligence; Decision support systems; Design methodology; Genetic algorithms; Humans; Machine intelligence; Neural networks; Process design; Product design; Constraint based; Cooperative Interactive; Genetic algorithm; Product design;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Decision Conference, 2009. CCDC '09. Chinese
Conference_Location :
Guilin
Print_ISBN :
978-1-4244-2722-2
Electronic_ISBN :
978-1-4244-2723-9
Type :
conf
DOI :
10.1109/CCDC.2009.5191831
Filename :
5191831
Link To Document :
بازگشت