Proper

Abstract

At present, the transformer fault diagnosis methods are many, because the oil dissolved gas analysis (DGA) technology can be found in the transformer latent failure to prevent catastrophic accidents, According to statistics, the transformer is the most common failure is the temperature rise of the transformer, the damage rate of about 60% -70% of the transformer failure, The correct and effective fault diagnosis of the transformer is very important to the safety and stability of the whole power system. After studying the neural network theory, learning algorithm and its various applications in the transformer fault diagnosis, Based on the characteristics of the oil dissolved gas sample data, the basic trust distribution function model of transformer fault diagnosis based on BP neural network is established. Finally, the simulation model is simulated by MATLAB simulation software, which proves the feasibility of the algorithm and provides a theoretical basis for transformer fault prediction.