基于零件特征关注度的夹具实例相似性检索方法  

Research on Feature Attention-Driven Fixture Case Retrieval

作　　者：刘金山[1] 廖文和[1] 张素敏[2] 郭宇[1] 

机构地区：[1]南京航空航天大学机电学院,南京210016 [2]中国航天科工集团公司第三研究院,北京100013

出　　处：《计算机辅助设计与图形学学报》2007年第10期1303-1307,1314,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家"八六三"高技术研究发展计划(2002AA411030)

摘　　要：针对传统夹具实例检索方法的不足和三维模型检索的局限性,提出一种对于零件几何形状的零件特征关注度模型表示方法及生成该模型的方法,并给出了根据零件特征关注度模型进行夹具实例检索的算法.根据B-rep实体表示方法构造零件属性邻接图,通过特征提取算法获得零件的特征并计算特征关注度,形成关注度模型.在零件特征关注度模型的基础上,利用非精确图匹配算法匹配零件关注度模型,并应用于夹具设计实例检索过程中.应用证明,该算法可以满足工程应用的需求.From an analysis on the case retrieval approaches applied in conventional case-based fixture design and the limitation of 3D-model retrieval method, feature attention-driven model （FADM） to represent CAD models and a new approach to fixture case retrieval based on FADM for case-based design are proposed. The method to generate the FADM and match FADMs is presented to solve the retrieval of fixture design case. Firstly, an attributed adjacent graph （AAG） is created based on the boundary representation （B-rep） of solid geometry of parts. The features of the parts are recognized based on the AAG, and the attention parameter of each feature is quantified to determine the FADM. Then the inexact graph matching approach is applied to match the FADMs. The algorithm is used for the fixture design case retrieval and its effectiveness is proved.

关 键 词：计算机辅助夹具设计 实例检索 特征关注度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]