Fuzzy logic for scaling finite element solutions of electromagnetic fields

Artificial intelligence (AI) has been used to determine the quasi-stationary two-dimensional electromagnetic fields within rectangular boundaries. Amplitude and phase of magnetic vector potential have been calculated in an iron slot with an embedded current carrying conductor. A suitable fuzzy neural network (FNN) for scaling finite elements electromagnetic field calculations has been developed. FNN has been trained, using finite elements calculations within rectangular boundaries. Then, FNN has been used to calculate the field in a new geometry differing significantly from the geometries used for training. It was concluded that FNN may be used to scale results from one geometry to another with negligible errors.