A Knowledge Graph-Based Information Retrieval Method for Substation Safety Hazards

With the rapid development of smart grid, the number of substation equipment has increased significantly, and its safety hazard information has also increased explosively. The traditional safety hazard information retrieval methods have been difficult to meet the needs of high efficiency and accuracy, especially when dealing with complex and massive data. To address the above problems, this paper proposesa new retrieval methods. Firstly, a joint extraction model based on RPATT is proposed, which solves the problem of gradient vanishing in deep network training by introducing residual connections through RP, and at the same time, ATT is introduced to enhance the model's ability to capture key information and complete the identification of hidden danger triad. Secondly, a multi-dimensional substation safety hidden danger map containing hidden danger causes, hidden danger locations, and management measures is constructed. Finally, a retrieval method based on the similarity of graph structure features is proposed. At the same time, the similarity of hidden dangers is measured from the aspects of structure and features, and the association relationship in the knowledge graph is utilized to realize the comprehensive query across equipment and hidden danger types, so as to improve the comprehensiveness and accuracy of the retrieval results. The experimental results show that the accuracy rate of the knowledge graph-based information retrieval method for substation safety hazards reaches 90.9%, which significantly improves the retrieval efficiency and accuracy, and effectively solves the deficiencies of the traditional method in dealing with complex and massive data.