An Oil-Immersed Transformer Fault Diagnosis Method Based on Data Preprocessing and Gradient Boosting

Abstract

In view of traditional transformer fault diagnosis methods' drawbacks including sensibility to noise, low diagnostic accuracy and difficulty to determine model parameters, a transformer fault diagnosis method based on four-stage data preprocessing and Gradient Boosting is proposed. Firstly, the 14-dimensional features are obtained based on data of dissolved gas in the oil. Secondly, four-stage data preprocessing method (Local Outlier Factor, Canopy, K-Means, SMOTE) is used to identify and replace outliers to obtain de-noising samples. Finally, a fault diagnosis model based on GBDT is constructed, which is optimized by Particle Swarm Optimization (PSO) algorithm. The example verifies that compared with Linear Discriminant Analysis (LDA), K Nearest Neighbor (KNN), Back-Propagation Neural Network (BPNN), Support Vector Machine (SVM) and Random Forest (RF), this method improves the fault diagnosis accuracy significantly, which shows its effectiveness and practicality.