Fault Diagnosis of Transformer Windings Based on Decision Tree and Fully Connected Neural Network

While frequency response analysis (FRA) is a well matured technique widely used by current industry practice to detect the mechanical integrity of power transformers, interpretation FRA signatures still challenging, regardless research efforts in this area. This paper presents method for reliable quantitative and qualitative transformer based on decision tree classification model fully connected neural network. Several levels different six fault types are obtained using lumped parameter-based model. Results show that proposed performs training validation stages, good generalization ability.