智能系统学报2024，Vol.19Issue(6)：1584-1592,9.DOI:10.11992/tis.202305050
联合结构-语义关系图知识推理的输电线路螺栓缺陷识别方法
Bolt defect recognition method for transmission line based on joint struc-ture-semantic relationship graph knowledge reasoning
摘要
Abstract
To tackle the issues of visual inseparability and semantic ambiguity in identifying transmission line bolt de-fects,a new method using joint structure-semantic relationship graph knowledge reasoning is proposed.Initially,a se-mantic expression module extracts feature class mappings that highlight the discriminative attributes of each bolt.Sub-sequently,the structural relationship graph captures contextual bolt information and establishes spatial relationships across different scales.Utilizing a graph convolutional neural network and cooperative learning,the semantic relation graph nodes are updated with structural and semantic knowledge derived from the bolt attributes.Finally,the network employs label co-occurrence information from the bolt training data set to improve the accuracy of defect recognition.In the experimental stage,13 types of bolt properties across 3 types of typical fittings were examined.Comparative experi-ments show that the method proposed in this study outperforms other methods in identifying bolt defects,boosting ac-curacy by 8.12%over the baseline model.关键词
输电线路/螺栓/缺陷识别/知识表达/知识推理/图神经网络/结构关系/语义关系Key words
transmission lines/bolts/defects recognition/knowledge representation/knowledge reasoning/graph neural networks/structural relationships/semantic relationships分类
计算机与自动化引用本文复制引用
赵振兵,王睿,王艺衡,苗思雨,赵文清..联合结构-语义关系图知识推理的输电线路螺栓缺陷识别方法[J].智能系统学报,2024,19(6):1584-1592,9.基金项目
国家自然科学基金项目(61871182,U21A20486) （61871182,U21A20486）
河北省自然科学基金项目(F2020502009,F2021502008,F2021502013). （F2020502009,F2021502008,F2021502013）
