Power losses analysis in a three-phase distribution transformer using artificial neural networks

Abstract

This research article presents the analysis of power losses in a three-phase distribution transformer, 100 kVA 22 kV-400/230 V by using artificial neural networks that can analyze the power losses in distribution transformers faster and use fewer variables than the original method. The measurement data were collected for 100,000 sets at the transformer manufacturer factory by setting the current flow from 1% to 100% at temperatures: 30◦C, 35◦C, 40◦C, 45◦C, 50◦C, 55◦C, 60◦C, 65◦C, 70◦C, and 75◦C to calculate the power losses in a distribution transformer. The collected data were divided into 80,000 sets to use for training in order to find the parameters of the artificial neural networks, and 20,000 sets were used for the artificial neural network input in order to calculate power losses in a distribution transformer. From comparing the power losses in the distribution transformer of artificial neural networks compared with the calculated values from the measurement, the percentage error was at a satisfactory level and can be applied to design a test of power losses in the distribution transformer in the future.