In recent years Artificial Neural Networks have been adopted as an alternative modelling approach for the design of microwave circuits. In this work a characterization of circular resonators realized in substrate integrated waveguide (SIW) technology by means of Artificial Neural Networks is presented. SIW resonators are analyzed considering the scattering of the ensemble of metallic vias placed in a parallel plate waveguide. Resonances are efficiently located looking at an estimate of the smallest singular value. Results carried out for circular resonators demonstrate the effectiveness of the method.
Feed forward neural network characterization of circular SIW resonators / Angiulli, G., Arnieri, E., De Carlo, D., Amendola, G.. - (2008), pp. 1-4. (IEEE Antennas and Propagation Society International Symposium, 2008. San Diego, California (Usa) 5-11 July 2008) [10.1109/APS.2008.4619807].
Feed forward neural network characterization of circular SIW resonators
ANGIULLI, Giovanni
;
2008-01-01
Abstract
In recent years Artificial Neural Networks have been adopted as an alternative modelling approach for the design of microwave circuits. In this work a characterization of circular resonators realized in substrate integrated waveguide (SIW) technology by means of Artificial Neural Networks is presented. SIW resonators are analyzed considering the scattering of the ensemble of metallic vias placed in a parallel plate waveguide. Resonances are efficiently located looking at an estimate of the smallest singular value. Results carried out for circular resonators demonstrate the effectiveness of the method.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
