计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (13): 1-3.

• 博士论坛 • 上一篇    下一篇

基于群智能SOM算法的特征造型搜索技术

李 峰,孙立镌   

  1. 哈尔滨理工大学 计算机科学与技术学院,哈尔滨 150080
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-05-01 发布日期:2011-05-01

Searching technology for feature module based on self-organizing clustering

LI Feng,SUN Lijuan   

  1. Computer Science & Technology College,Harbin University of Science and Technology,Harbin 150080,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-05-01 Published:2011-05-01

摘要: 为解决语义特征化后复杂造型协同设计中造型共享库中的造型检索问题,提出了一种基于群智能自组织聚类算法。该算法首先将语义特征造型信息向量化,通过语义造型特征树得到语义特征造型特征集,以蚁群算法做为自组织准则,并以粒子群算法做为蚁群移动模型,将特征语义群分布在一个平面上进行聚类,递归收集聚类结果。试验证明,采用此种方法,可以对特征造型完成准确率很高的聚类,使特征库组织性得到了很大提高。

关键词: 特征语义造型, 自组织聚类, 蚁群算法, 粒子群

Abstract: To solve the problem of searching complex feature model in the shared module library for collaborative design,this paper proposes a self-organizing clustering algorithm to re-arrange the structure of modules.Firstly,the module tree information is converted to vector represented.Then ant colony is used as the rule of self-organizing,and particle swarm optimization algorithm is used to calculate the next position.Finally,the objects are clustered and the result is collected by a recursive algorithm.After the self-organizing cluster,the structure of module library becomes better arranged.

Key words: feature model, self-organizing clustering, ant colony, particle swarm