基于图二次分解的加工特征识别算法  

Machining Feature Recognition Based on Graph Twice Decomposition

作　　者：郭付龙[1] 孙根正[1] 周竞涛[1] 邵立[1] 

机构地区：[1]西北工业大学现代设计与集成制造技术教育部重点实验室,陕西西安710072

出　　处：《机械设计与制造》2013年第5期56-59,共4页Machinery Design & Manufacture

摘　　要：从零件的CAD模型中获取工艺设计所需的加工特征信息是CAPP的基础,也是实现CAPP与CAD集成的关键。针对基于图的特征识别方法中子图搜索算法时间复杂度高且难以识别相交特征的问题,提出了一种基于图二次分解的加工特征识别方法。首先,通过提CAD取模型的B-Rep信息,将CAD模型用属性邻接图表示;然后通过对属性邻接图进行二次分解,最大限度的分离出特征子图,利用图的同构实现了对凸出类和凹陷类特征的识别。最后,通过一个实例验证了该方法的可行性和有效性。It is very important to obtain machining characteristic information from CAD model in order to design techniques and realize CAD and CAPP integration.To solve the problem of high time complexity and difficulty to recognize Inter-acting feature of subgraph isomorphism of the feature recognition method based on graph,a machining feature recognition algorithm based on graph twice decomposition is proposed.Firstly,the CAD model is showed by an attribute adjacent graph of extracting the model＇s B-Rep information.Then,the model＇s attribute adjacent graph is twice decomposed into a set of feature subgraphs,and both protrusion features and depression features are successfully recognized by graph isomorphism.Finally,the correctness and validity of the algorithm is demonstrated by an example.

关 键 词：属性邻接图 图分解 图同构 特征识别 

分 类 号：TH16[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]