Neuromodelling of tapered microstrip antennas and frequency selective surfaces

Abstract

The main objective of this work is the application of Artificial Neural Networks (ANN) in the analysis of microwave integrated circuits, such as tapered microstrip antennas and frequency selective surfaces (FSS). The advantages of modeling these devices through neural networks are discussed. The ANN results are presented and validated with those from the method of moments (MoM). The antenna ANN results are presented and validated with measured ones. Furthermore, a good generalization capacity of the ANN analysis was observed.