Design and optimization of CPW circuits using EM-ANN models for CPW components

Author

Watson, Paul M. ; Gupta, Kuldip C.

Author_Institution

Colorado Univ., Boulder, CO, USA

Volume

45

Issue

12

fYear

1997

fDate

12/1/1997 12:00:00 AM

Firstpage

2515

Lastpage

2523

Abstract

Accurate and efficient electromagnetically trained artificial neural-network (EM-ANN) models have been developed for coplanar waveguide (CPW) circuit components. Modeled components include: CPW transmission lines (frequency dependent Z₀ and ε_re), 90° bends, short-circuit stubs, open-circuit stubs, step-in-width discontinuities, and symmetric T-junctions. These models allow for circuit design, simulation, and optimization within a commercial microwave circuit simulator environment, while providing the accuracy of electromagnetic (EM) simulation. Design and optimization of a CPW folded double-stub filter and a 50-Ω 3-dB power divider circuit using the developed CPW EM-ANN models are demonstrated

Keywords

MMIC; circuit CAD; circuit analysis computing; circuit optimisation; coplanar waveguides; integrated circuit design; neural nets; power dividers; waveguide discontinuities; waveguide filters; 50 ohm; CPW bends; CPW circuits; CPW components; CPW transmission lines; EM-ANN models; circuit design; electromagnetically trained artificial neural-network; folded double-stub filter; microwave circuit simulator environment; open-circuit stubs; optimization; power divider circuit; short-circuit stubs; simulation; step-in-width discontinuities; symmetric T-junctions; Circuit simulation; Coplanar transmission lines; Coplanar waveguides; Design optimization; Distributed parameter circuits; Electromagnetic modeling; Electromagnetic waveguides; Frequency dependence; Power transmission lines; Waveguide components;

fLanguage

English

Journal_Title

Microwave Theory and Techniques, IEEE Transactions on

Publisher

ieee

ISSN

0018-9480

Type

jour

DOI

10.1109/22.643868

Filename

643868