基于模式识别的计算机辅助零件分类系统设计  

The Design of Computer-aided Part Classification System Based on the Pattern Recognition

作　　者：迟彦孝[1] 王守城[1] 王益强[2] 赵海霞[1] 

机构地区：[1]青岛科技大学机电工程学院 [2]莱阳农学院,山东莱阳265000

出　　处：《青岛科技大学学报（自然科学版）》2003年第3期244-247,共4页Journal of Qingdao University of Science and Technology:Natural Science Edition

摘　　要：基于模式识别的计算机辅助零件分类系统 ,可以对零件进行迅速、准确地分类。这种分类方法不需要进行人工编码 ,故使分类过程更加简单 ,同时也避免了人的主观因素对分类的影响。系统中所用的参考模式起着一个聚类核心的作用 ,使分类更加准确 ,并可由一个空间向量来表示。该参考模式应用模糊聚类分析法进行运算 ,它虽然不代表任何零件 ,但却能反映零件组中诸特征的分布。作者交替运用聚类分析与模式识别法 ,并结合工厂的实际情况 ,取得了很好的分类效果。The computer-aided part classification system based on the pattern recognition can speedily classify parts correctly. Because it is unnecessary to do manual coding work in this classification system, it becomes simpler to perform the classifying process, and further more the effects caused by man's subjective factors on the part classification are avoided. The reference pattern used in the system, which functions as a cluster center and makes the part classification more accurate, can be represented with a multidimensional vector. Although the reference pattern doesn't represent any part, yet it is able to show the distribution of characteristics of the part group, using the method of fuzzy cluster analysis for calculating. We have achieved excellent effect in part classification according to the actual conditions of factories, alternately using the method of cluster analysis and pattern recognition technique.

关 键 词：模式识别 计算机辅助设计 零件分类 参考模式 模糊聚类分析 

分 类 号：TH13[机械工程—机械制造及自动化] TP391.7[自动化与计算机技术—计算机应用技术]