Power Equipment Fault Traceability Method Based on Graph Data-Driven

With the continuous development of digital construction of power systems, the operating status of power equipment is directly related to the safe and stable operation of the power system. Therefore, accurate traceability of the causes of power equipment failures is of great significance to ensure the safe and stable operation of the power grid. In view of the problems of traditional power equipment fault traceability methods such as low accuracy and over-reliance on expert experience, a graph data-driven power equipment fault traceability method is proposed, which can comprehensively analyze the cause and location of faults based on equipment operating information and improve the accuracy of fault traceability. First, a power equipment fault knowledge graph is constructed and stored in the form of graph data; second, a node classification task based on a graph convolution network is used to realize power equipment fault traceability; finally, an example is constructed to verify that the proposed method can accurately predict power equipment faults. Tracing the causes of equipment failures has good application prospects.