Artificial neural networks for accurate microwave CAD applications

Author

Creech, G.L. ; Paul, B. ; Lesniak, C. ; Jenkins, T. ; Lee, R. ; Calcatera, M.

Author_Institution

Wright Lab., Solid State Electron. Directorate, Wright-Patterson AFB, OH, USA

Volume

2

fYear

1996

fDate

17-21 June 1996

Firstpage

733

Abstract

A unique approach for applying neurocomputing technology for accurate CAD of microwave circuits is described. In our proposed method, a multilayer perceptron neural network (MLPNN) is trained to predict the scattering parameters of MMIC passive elements based on the element´s physical dimensions. The s-parameters were obtained by performing a full-wave electromagnetic (EM) analysis of these elements. An X-band MLPNN spiral inductor model is developed. The MLPNN computed s-parameter values are in excellent agreement with those obtained from EM simulations with correlations greater than 0.99 for all modelled parameters.

Keywords

MMIC; S-parameters; circuit CAD; integrated circuit design; integrated circuit modelling; multilayer perceptrons; CAD; EM simulation; MMIC passive elements; X-band spiral inductor model; artificial neural network; full-wave electromagnetic analysis; microwave circuit; multilayer perceptron neural network; neurocomputing technology; scattering parameters; Artificial neural networks; Electromagnetic analysis; MMICs; Microwave circuits; Microwave technology; Multi-layer neural network; Multilayer perceptrons; Neural networks; Performance analysis; Scattering parameters;

fLanguage

English

Publisher

ieee

Conference_Titel

Microwave Symposium Digest, 1996., IEEE MTT-S International

Conference_Location

San Francisco, CA, USA

ISSN

0149-645X

Print_ISBN

0-7803-3246-6

Type

conf

DOI

10.1109/MWSYM.1996.511043

Filename

511043