Transformer Fault Diagnosis Method Based on Particle Swarm Optimization Neural Network
Aiming at the problems of low processing efficiency and strong subjectivity in diagnosis results of traditional transformer fault diagnosis methods,an improved particle swarm optimization BP neural network transformer fault diagnosis method is proposed,and research is conducted on intelligent transformer fault diagnosis methods.Firstly,using the non coding ratio method,the ratio of various dissolved gases in transformer oil is selected to more accurately distinguish the type of fault.Secondly,based on the gas ratio information of the selected test set,the grey correlation method is used to select information with high similarity to the information features of the test set as the training set,eliminate redundant information,and optimize the sample data.Finally,a PSO-BP transformer fault diagnosis model is constructed,and an improved particle swarm optimization algorithm is used to optimize the weights and thresholds in the BP neural network,enabling the diagnostic model to have faster diagnostic speed and higher accuracy.Train a diagnostic network using dissolved gas information collected from transformer oil,and compare it with the traditional BP neural network method.The results show that the proposed method has significantly improved the accuracy of transformer fault diagnosis.
NETL
NSTL
万方数据
