摘要： 提出了支持复杂产品并行协同设计的广义动态约束网络(GDCN)概念和模型；然后，提出了模糊－粗糙集算法，对仿真结果进行数据挖掘，实现知识级约束获取；最后，开发了基于仿真的知识级约束获取系统，并以某型号V6发动机曲柄连杆机构设计为例，说明了方法的准确性和有效性。

关键词: 约束网络, 仿真, 知识级约束, 模糊-粗糙集

Abstract: The concept and model of GDCN (generalized dynamic constraints network) supporting for concurrent and collaborative design is presented. Then, a data-mining algorithm named fuzzy-rough algorithm is developed, and it is used to mining the knowledge constraint from the numerical simulation data. Finally, the crank and connecting rod design of one V6 engine are given to show the validity of these modeling methods.

Key words: Constraints network, Simulation, Knowledge level constraint, Fuzzy-rough algorithm

中图分类号: 

• wangweiming@sjtu.edu.cn