基于典型面匹配的机械零件检索方法

Mechanical Parts Retrieval Based on Typical Face Matching

为了检索具有相似局部特征的机械零件,以支持设计的早期复用,提出一种基于典型面匹配的机械零件检索方法.该方法以零件的IGES标准表示作为输入,在离线处理阶段对模型库中的局部面进行训练,标识局部面相对于功能分类的区分度,并过滤非典型面以提高检索效率;在线检索阶段,通过离线处理的结果估算用户输入面的区分度,并根据区分度对输入面进行排序,最后采用贪心算法与数据库模型中的面进行匹配和相似度排序.在原型系统中的实验结果表明,由于避免了网格化造成的精度损失,且加入了对局部面区分度的离线计算过程,与通用三维模型检索算法相比,采用文中方法可检索出更多具有共同局部特征和相似功能的模型,从而更好地支持设计复用.

This paper presents a typical face-based retrieval method to search mechanical parts with similar local features. The method takes the IGES standard representation as input. In the training phase, all the faces in the database are tested and assigned with a value indicating their distinction. Trivial faces and atypical ones with small areas are removed in this phase to improve online retrieval efficiency. In the query phase, we evaluate the distinction of the input faces by aligning them with faces in the database. The similarity between input faces and those in the database is achieved by applying a greedy algorithm. Our method avoids the information lost caused by mesh diseretization and introduces the training phase for local features. Experimental results from the prototype system show that the method can provide a favorable performance when applied to retrieve models with common local features or similar functionalities, and hence can support design reuse better than some other mesh-based methods.