工件加工变形知识图谱的构建

打开文本图片集

中图分类号：TH166 文献标识码：A

The Constructing Knowledge Graph for Workpiece Machining Distortion

QI Hao1 LI Xiaoyue1 SUN Zhaoze¹ GUO Yue² TAO Qiang1

Abstract： To address the issues fragmented knowledge limited information sharing in the field workpiece machining distortion，this paper proposes a knowledge graph framework tailored for this domain. A dataset comprising 1 O85 long-text records related to machining distortion was constructed， an ontology model was developed to define the relevant entities relationships. A BERT + BiLSTM + CRF-based entity extraction model a BERT-based relation extraction model were employed to enable automated knowledge extraction. Knowledge fusion was performed through a combination cosine similarity-based matching manual verification. A knowledge graph containing 4 330 entities 5 509 relationships was then built using the Neo4j graph database，with support for data insertion，deletion，updating， querying implemented via Cypher language. Experimental results demonstrate that the proposed knowledge graph can effectively support decision-making research analysis in workpiece machining processes.

Keywords： workpiece machining distortion； knowledge extraction; knowledge fusion； knowledge graph

在现代制造业中，工件加工变形是影响产品质量和生产效率的关键问题之一。（剩余7787字）