Characterization of microstrip reflectarray square ring elements by means of an Artificial Neural Network

In this paper an Artificial Neural Network (ANN) is introduced in order to speed up the optimized design procedure of a printed Reflectarray. The ANN is used to model the reflecting behaviour of patch radiator as a function of its geometric parameters, the angle of incidence and the frequency. When used in the RA design process, the reflection coefficient approximated with the ANN produces results that are very close to those obtained with that directly evaluated, proving the accuracy of the ANN model, which, on the other hand, strongly reduces the computational effort and the data memory storage.