基于本体引导的注塑知识图谱构建及缺陷溯因应用  

Injection Molding Knowledge Graph Based on Ontology Guidance and its Application to Quality Diagnosis

作　　者：王雅琳[1] 邹江枫 王凯[1] 袁小锋 谢胜利[2] WANG Yalin;ZOU Jiangfeng;WANG Kai;YUAN Xiaofeng;XIE Shengli(School of Automation,Central South University,Changsha 410083,China;School of Automation,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]中南大学自动化学院,长沙410083 [2]广东工业大学,广州510006

出　　处：《电子与信息学报》2022年第5期1521-1529,共9页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(U1911401);国家重点研发计划(2020YFB1713800);湖南省科技创新计划(2021RC4054);中南大学中央高校基本科研业务费专项资金(2021zzts0711)。

摘　　要：针对大型注塑图谱缺失、成熟标注语料匮乏等导致的工业知识图谱构建代价高昂、质量不高等问题,该文提出一种基于本体引导的注塑知识图谱构建方法。首先,设计以缺陷-表观-原因-方案为导向的注塑本体,指导注塑网页的搜集;其次将本体信息融入至触发词中,以提升对半结构化网页的知识抽取性能;然后,结合本体中的属性相似度进行两级实体对齐,综合提高冗余知识的发现率。最后与已有方法对比,图谱知识正确率高于95%,可快速实现缺陷溯因。Due to the lack of mature labeled corpus and large-scale injection molding knowledge graphs for defection diagnosis,industrial knowledge graphs are constructed with high cost and low quality.A framework for constructing industrial knowledge graph based on ontology guidance is developed in this paper.Firstly,the injection molding ontology guided by defect-appearance-cause-scheme chain is designed to limit the collection of web pages.Then,the ontology information is sequentially integrated into the trigger thesaurus to improve the knowledge extraction performance of unstructured web text.Finally,the two-level entity merging method is carried out by combining with the attribute similarity in ontology,which realized the fusion of redundant knowledge.Compared with the existing methods,the accuracy of domain knowledge is higher than 95%,which can be used for tracing the defect quickly.

关 键 词：注塑成型 知识图谱 本体工程 实体对齐 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]