Estimating Far-Field Emissions From Simulated Near-Field Data With Artificial Neural Networks

In this paper, a procedure for estimating the electromagnetic fields radiated far from their source based on near-field (NF) simulation is considered. The NFs radiated from the sources are modeled with the transmission-line matrix method. The so-called far fields are estimated with the help of different artificial neural networks. Comparison with results based on theoretical equations and software simulations substantiate the validity of the proposed method association.