A NEURAL-NETWORK FOR THE PREDICTION OF PERFORMANCE PARAMETERS OF TRANSFORMER CORES

The paper shows that Artificial Neural Networks (ANNs) may offer new p ossibilities for the prediction of transformer core performance parame ters, i.e. no-lend power losses and excitation. Basically this techniq ue enables simulations with respect to different construction paramete rs most notably the characteristics of corner designs, i.e. the overla p length, the air gap length, and the number of steps. However, withou t additional physical knowledge incorporated into the ANN extrapolatio n beyond the training data limits restricts the predictive performance .