计算机应用与软件2026，Vol.43Issue(6)：98-105,8.DOI:10.3969/j.issn.1000-386x.2026.06.014
面向远程监督关系抽取的故障诊断知识图谱构建方法
A FAULT DIAGNOSIS KNOWLEDGE GRAPH CONSTRUCTION FOR DISTANCE SUPERVISED RELATIONSHIP EXTRACTION
摘要
Abstract
To address the issues of insufficient labeling of multi-source corpora and the impact of noisy statements on relationship extraction,we propose a fault diagnosis knowledge graph construction for distance supervised relationship extraction.It designed a fault diagnosis knowledge ontology and defined a conceptual knowledge model.It presented a relation-aware-based attention enhanced piecewise convolutional neural network with reinforcement learning algorithm to extract relationships of entity pairs.As an example of fault diagnosis events for island photovoltaic power plants,the experiments show that the proposed method can effectively predict the relationship for unlabeled data,and has a higher accuracy compare to baseline methods that can provide engineers with effective fault diagnosis decisions.关键词
故障诊断/远程监督关系抽取/知识图谱/分段图卷积网络/注意力增强/强化学习Key words
Fault diagnosis/Distant supervision relation extraction(DSRE)/Knowledge graph/Piecewise convolu-tional neural network(PCNN)/Attention enhance/Reinforcement learning(RL)分类
信息技术与安全科学引用本文复制引用
甘纯,张引贤,张展耀,冯仰光,何宇巍..面向远程监督关系抽取的故障诊断知识图谱构建方法[J].计算机应用与软件,2026,43(6):98-105,8.基金项目
科技部重点研发项目(2022ZD0119400) （2022ZD0119400）
国家自然科学基金项目(78865567) （78865567）
国网浙江省电力有限公司科技项目(B311ZS230002). （B311ZS230002）
