Research on Recommended Technology of Power Transformer Disposal Case based on Knowledge Graph

When the transformer is in a critical state, it is difficult to adapt to the increasing time-variability and complexity of the power grid operation mode in the era of big data by relying only on the traditional way of manually handling faults based on dispatching management procedures. The application of knowledge graph in transformer fault handling can help break through the restrictions of manual decision-making. Based on the manual experience accumulated for many years in the maintenance and operation of transformers in the power grid and the text data such as maintenance records, defect records and power grid operation procedures, this paper extracts the valuable information from the above data into knowledge elements, and proposes a knowledge graph for transformer fault disposal. The recommendation algorithm based on knowledge graph is adopted in this paper, and introduces the five-dimensional characteristic quantity of transformer state into the calculation of case similarity. Under the condition that the transformer state and fault information are highly similar when the fault occurs, the push function of transformer fault solution is realized, which provides business support for the intelligent decision-making requirements of equipment monitoring.