C. Nussbaum et al., A NEURAL-NETWORK FOR THE PREDICTION OF PERFORMANCE PARAMETERS OF TRANSFORMER CORES, Journal of magnetism and magnetic materials, 160, 1996, pp. 81-83
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
.