模具设计知识表示方法  

Representation method on mold design knowledge

作　　者：李宝清 王运平 曹立林 李西宁[2] 叶园园 Li Baoqing;Wang Yunping;Cao Lilin;Li Xining;Ye Yuanyuan(AECC Xi′an Power Control Technology Co.,Ltd.,Xi′an 710000,China;School of Mechanical Engineering,Northwestern Polytechnical University,Xi′an 710072,China)

机构地区：[1]中国航发西安动力控制科技有限公司,陕西西安710000 [2]西北工业大学机电学院,陕西西安710072

出　　处：《锻压技术》2023年第6期176-184,共9页Forging & Stamping Technology

基　　金：中国航发自主创新专项资金项目(ZZCX-2019-026)。

摘　　要：设计知识有效表示是模具智能化设计的前提和基础,对提高模具设计质量和效率具有重要的作用和意义。首先,对传统知识表示方法如谓词逻辑、产生式、框架、语义网络、面向对象和基于本体表示法的基本原理以及研究现状进行了总结。然后,对比分析了不同知识表示方法的优缺点,分析了知识表示的发展趋势并介绍了知识图谱的基本概况。最后,结合知识特点,将模具知识分为3类,即事实类知识、规则类知识和实例类知识。阐述了基于知识图谱进行知识表示的基本流程,主要包括:信息抽取、知识融合和知识加工,并以凸模结构形式(部分)知识为例,完成了相关知识图谱的构建。Effective representation of design knowledge is a prerequisite and foundation for intelligent design of mold,which plays an important role and significance in improving the quality and efficiency of mold design.Firstly,the basic principles and research status of traditional knowledge representation methods such as predicate logic,production,framework,semantic network,object-oriented and representation of ontology were summarized.Then,the advantages and disadvantages of different knowledge representation methods were compared,the development trends of knowledge representation were analyzed,and the basic overview of knowledge graph was introduced.Finally,based on the characteristics of knowledge,the mold knowledge was divided into three categories:practical knowledge,rule knowledge and instance knowledge,and the basic process of knowledge representation through knowledge graph was elaborated,mainly including information extraction,knowledge fusion and knowledge processing.In addition,taking the punch structure form(partial)knowledge as an example,the relevant knowledge graph construction was completed.

关 键 词：知识表示 知识分类 知识图谱 模具设计 智能制造 

分 类 号：TG385.2[金属学及工艺—金属压力加工]