A CAD neural model for shielded and conductor backed CPW

Author

Selvan, P. Thiruvalar ; Raghavan, S. ; Suganthi, S.

Author_Institution

Dept. of ECE, Nat. Inst. of Technol., Trichirapalli

fYear

2007

fDate

19-20 Dec. 2007

Firstpage

1

Lastpage

4

Abstract

In this paper a CAD approach based on ANNs was successfully introduced to determine the parasitic effects occurred in (effective dielectric and characteristics impedance) Coplanar Wave guide (CPW) with upper shielding and conductor backing. ANNs were trained with three learning algorithms to obtain better performance and faster convergence with simpler structure. The best results were obtained with Levenberg-marquardt algorithms. The quasi-static parameters of two different CPW configurations can be calculated using the neural model proposed in this work very accurately.

Keywords

MMIC; circuit CAD; coplanar waveguides; electromagnetic shielding; neural nets; ANN; CAD neural model; CPW; Levenberg-marquardt algorithm; MMIC applications; conductor backing; coplanar waveguide; learning algorithm; upper shielding; Capacitance; Conductors; Conformal mapping; Coplanar waveguides; Dielectric substrates; Erbium; Gallium arsenide; Impedance; Microwave integrated circuits; Strips; Artificial neural networks; Characteristics impedance; Effective Permitivity; Learning Algorithms; Shielded Coplanar wave-guides;

fLanguage

English

Publisher

ieee

Conference_Titel

Applied Electromagnetics Conference, 2007. AEMC 2007. IEEE

Conference_Location

Kolkata

Print_ISBN

978-1-4244-1863-3

Electronic_ISBN

978-1-4244-1864-0

Type

conf

DOI

10.1109/AEMC.2007.4638026

Filename

4638026