A knowledge-based constraints network system for concurrent product design

Author

Peng, Ying-hong ; Wang, Wei-Ming ; Hu, Jie ; Zhang, Kai-Yuan ; Yin, Ji-long

Author_Institution

Sch. of Mech. Eng., Shanghai Jiao Tong Univ., China

Volume

3

fYear

2005

fDate

18-21 Aug. 2005

Firstpage

1943

Abstract

This paper discusses the development of a knowledge-based constraints network system for concurrent product design using a combination of both mathematic methods and knowledge-based engineering (KBE) techniques. Firstly, the model of knowledge-based constraints network system (KCNS) is developed. Secondly, a data-mining algorithm named fuzzy-rough algorithm is developed to acquisition of knowledge level constraints from numerical simulation. Finally, the method integrated CBR and RBR with interval consistency algorithm is adopted to predict the potential conflicts and specify the interval of design parameters. The system is demonstrated by the design of crank connecting link in a V6 engine.

Keywords

computer aided engineering; concurrent engineering; constraint handling; data acquisition; data mining; fuzzy set theory; knowledge based systems; knowledge engineering; mechanical engineering computing; product design; rough set theory; V6 engine; case-based reasoning; concurrent product design; crank connecting link design; data mining; fuzzy-rough algorithm; interval consistency algorithm; knowledge level constraint acquisition; knowledge-based constraint network; knowledge-based engineering; mathematic method; numerical simulation; Algorithm design and analysis; Design engineering; Engines; Joining processes; Knowledge engineering; Mathematics; Numerical simulation; Product design; CBR; Constraints network; RBR; consistency algorithm; fuzzy-rough algorithm; knowledge level constraints;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on

Conference_Location

Guangzhou, China

Print_ISBN

0-7803-9091-1

Type

conf

DOI

10.1109/ICMLC.2005.1527263

Filename

1527263