Fault Detection in Three-Phase Transformer Using Machine Learning Methods
In this paper, the study of ABC (artificial bee colony algorithm) and decision tree machine learning has been explored for internal fault detection in a three-phase transformer using a differential protection scheme. The half-cycle window of differential current has been sampled at 1 kHz sampling frequency for classification of five operating conditions i.e. normal, magnetizing inrush, over-excitation, internal and external fault condition. 420 samples have been generated by modeling the differential protection scheme of Y-Y transformer and simulating under different operating conditions in the sim power system of MATLAB/SIMULINK. The k-fold cross-validation is used for measuring the accuracy and sensitivity of the decision tree classification model. The result shows that the decision tree method as compared with the linear model is best in the classification of fault prediction with a sensitivity of 0.88 and an accuracy of 0.91 on the testing data set.