Neural Network Characterization of Microstrip Patches for Reflectarray Optimization

Konferenz: EuCAP 2009 - 3rd European Conference on Antennas and Propagation
23.03.2009 - 27.03.2009 in Berlin, Germany

Tagungsband: EuCAP 2009

Seiten: 3Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Caputo, D.; Pirisi, A.; Mussetta, M.; Zich, R. E. (Politecnico di Milano, Department of Energy, Piazza Leonardo da Vinci 32, 20133 Milano, Italy)
Mussetta, M.; Pirinoli, P. (Politecnico di Torino, Department of Electronics, Corso Duca degli Abruzzi 24, 10129 Torino, Italy)
Freni, A. (University of Florence, Department of Electronics and Telecommunications, Via di S. Marta 3, 50139 Florence, Italy)

The increasing interest among the scientific community of reflectarray antennas in recent years leads to develop effective ad-hoc procedures for the antenna performances optimization, often based on evolutionary iterative algorithms. However, in most of engineering problems such an optimization approach could be very computational expensive, since it could require the computation of a complex fitness function thousands of times. An example of this is for instance the design of a large array or reflectarray, in which the structure to be optimized presents a lot of degrees of freedom and all concur to the performances of the whole antenna. To enhance the speed of the optimization task, in this work the optimization of a broadband reflectarray antenna has been carried out introducing a Neural Network model of the single element of the reflectarray: the artificial neural network (ANN) is used to predict the phase behaviour of patch radiator as a function of its geometric parameters. The characterization of the antenna is first obtained by numerical simulations, and the ANN is constructed to approximate the nonlinear relationship between the antenna geometry and the phase behaviour. Some preliminary results will show the effectiveness of this method in providing a fast interface between the antenna model and the optimisation tool.