An Adaptive Approach for Simulation of Inrush Current in Three-phase Transformers Considering Hysteresis Effects

Abstract

This article proposes a novel adaptive approach for accurate simulation of inrush currents in three-phase power transformers. The proposed technique is based on using artificial neural networks to update inverse Jiles–Atherton hysteresis model parameters during inrush current transients. The required parameters for training artificial neural networks are obtained using particle swarm optimization based on measured inrush current waveforms. The results show that the proposed technique can be used for accurate simulation of this phenomenon in three-phase power transformers. Inrush current measurements on a three-phase three-leg transformer are used for artificial neural network training and verification of the results.