Application of neural networks in microwave circuit modelling

Author

Peik, S.F. ; Coutts, G. ; Mansour, R.R.

Author_Institution

COM DEV, Cambridge, Ont., Canada

Volume

2

fYear

1998

fDate

24-28 May 1998

Firstpage

928

Abstract

Multi-layer perceptron neural networks have been developed for resonant microwave structures with highly non-linear responses. The network training data is compiled by an accurate electromagnetic simulation of the circuits. Two numerical examples are given: a microstrip patch antenna and a planar 3-pole filter. Utilizing the trained networks the circuits have been also optimized to certain specifications

Keywords

circuit analysis computing; circuit optimisation; learning (artificial intelligence); microstrip antennas; microwave antennas; microwave filters; multilayer perceptrons; nonlinear network analysis; poles and zeros; resonance; circuit optimization; electromagnetic simulation; microstrip patch antenna; microwave circuit modelling; multi-layer perceptron; network training data; neural networks; nonlinear responses; planar 3-pole filter; resonant microwave structures; trained networks; Circuit simulation; Microstrip antennas; Microstrip filters; Microwave circuits; Multi-layer neural network; Multilayer perceptrons; Neural networks; Patch antennas; Resonance; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 1998. IEEE Canadian Conference on

Conference_Location

Waterloo, Ont.

ISSN

0840-7789

Print_ISBN

0-7803-4314-X

Type

conf

DOI

10.1109/CCECE.1998.685651

Filename

685651