Design of Transformer Fault Intelligent Diagnosis System

Abstract

Transformer is an important equipment of power system, and its working condition can affect the safety of the power system. Therefore, the adoption of advanced technology to monitor the working condition of transformers is of great significance to the safe operation of the power system. The traditional manual empirical methods have low accuracy. This paper proposes an intelligent diagnosis method for transformer faults, which effectively combines the advantages of sparrow search algorithm (SSA) and support vector machine (SVM). The gas composition ratio in transformer oil is used as the system input of the diagnostic system, and the parameters of SVM are optimized by SSA. The experiments show that the intelligent diagnosis model proposed in this paper, with 100% accuracy and 35% improvement in accuracy, is an effective method that can be used for intelligent diagnosis of transformer faults with good application results.