S. Bila et al., An accurate wavelet neural-network-based model for electromagnetic optimization of microwave circuits, INT J RF MI, 9(3), 1999, pp. 297-306
Citations number
20
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
INTERNATIONAL JOURNAL OF RF AND MICROWAVE COMPUTER-AIDED ENGINEERING
In this paper, a relevant automated electromagnetic (EM) optimization metho
d and a novel, fast, and accurate artificial neural network are proposed fo
r the efficient CAD modeling of microwave circuits. We lay the groundwork f
or our investigation of radial wavelet neural networks WNNs trained by BFGS
(Broyden-Fletcher-Goldfarb-Shanno) and LBFGS (limited memory BFGS) algorit
hms and their application to determine the scattering parameters of the cir
cuit under study. Wavelet theory may be exploited in deriving a good initia
lization for the neural network, and thus improved convergence of the learn
ing algorithm. The optimization method combines a rigorous and accurate glo
bal EM analysis of the device performed with a finite-element method (FEM)
and a fast neural model deduced from its segmented EM analysis. Finally, ex
perimental results, which confirm the validity of the WNN model, and good a
greement between theoretical optimization results and experimental ones are
reported. (C) 1999 John Wiley & Sons, Inc.