基于知识图谱的复杂薄壁零件机械加工工艺知识建模研究  

Study on Machining Knowledge Modeling of Complex Thin-Walled Parts Based on Knowledge Graph

作　　者：肖彪 徐宝德 彭仕鑫 尉渊 丁国智 王萌 赵正彩[1] XIAO Biao;XU Baode;PENG Shixin;YU Yuan;DING Guozhi;WANG Meng;ZHAO Zhengcai(Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China;Beijing Xinghang Electro-Mechnical Equipment Co.,Ltd.,Beijing 100074,China)

机构地区：[1]南京航空航天大学,南京210016 [2]北京星航机电装备有限公司,北京100074

出　　处：《航空制造技术》2024年第11期76-86,共11页Aeronautical Manufacturing Technology

摘　　要：智能工艺设计是数字孪生环境下工艺设计的核心,零件工艺知识建模是实现基于数字孪生的智能工艺设计的前提。为此,针对航空航天领域复杂薄壁零件机械加工工艺数据结构化程度低、难以重用的问题,提出了典型复杂薄壁零件机械加工工艺知识图谱的构建和质量评估方法。首先,对机械加工工艺知识组成和结构进行分析。其次,通过本体建模、知识抽取、知识储存等相关技术实现了工艺知识的可视化表征,并基于Neo4j图数据库实现机械加工工艺知识检索。最后,利用层次分析法对构建完成的知识图谱进行评估,并以框段类零件的机械加工工艺知识为验证对象,得到子图谱的综合准确度为92.28%。试验结果表明,基于知识图谱的工艺知识建模方法切实可行,有助于实现工艺知识的有效组织和重用,为数字孪生的智能工艺设计奠定基础。Intelligent process design is the core of process design in the digital twin environment,and part process knowledge modeling is a prerequisite for achieving intelligent process design based on digital twins.To address the issues of low structured and difficult to reuse machining process data for complex thin-walled parts in the aerospace field,a construction and quality evaluation method for a typical knowledge graph of machining process for complex thin-walled parts is proposed.Firstly,the composition and structure of machining process knowledge are analyzed.Secondly,the visualization of process knowledge was realized through ontology modeling,knowledge extraction,knowledge storage,and other related technologies,and the knowledge retrieval of machining process was realized based on Neo4j database.Finally,the analytic hierarchy process is used to evaluate the constructed knowledge map,and the machining process knowledge of frame and segment parts is taken as the verification object,the comprehensive accuracy of the sub-map is 92.28%.The experimental results show that the process knowledge modeling method based on knowledge map is feasible,which can help to realize the effective organization and reuse of process knowledge,and lay the foundation for digital twin intelligent process design.

关 键 词：复杂薄壁零件 知识图谱 工艺知识建模 数据抽取 图谱质量评估 数字孪生 

分 类 号：TH161.1[机械工程—机械制造及自动化]