An X-band GaN HEMT power amplifier design using an artificial neural network modeling technique

Author

Lee, Sang Yun ; Cetiner, Bedri Artug ; TORPI, Hamid ; Cai, S.J. ; Li, Jiang ; Alt, K. ; Chen, Y.L. ; Wen, Cheng P. ; Wang, Kang L. ; Itoh, Tatsuo

Author_Institution

Dept. of Comput. & Electr. Eng., California Univ., Los Angeles, CA, USA

Volume

48

Issue

3

fYear

2001

fDate

3/1/2001 12:00:00 AM

Firstpage

495

Lastpage

501

Abstract

In this paper, the first gallium nitride (GaN) based high electron mobility transistor (HEMT) power amplifier design using an artificial neural network (ANN) modeling technique is presented. The ANN technique was used to model the small signal behavior of a device with a gate periphery of 1 mm and a gate length of 1 μm over the broad frequency range from 1 GHz to 26 GHz with multiple bias points, based on fitting calculated S-parameters to measured S-parameters. A single stage amplifier constructed using these parameters showed a gain of about 7 dB and an output power of 1.2 W at 8 GHz when biased at V_ds = 20 V and I_ds 220 mA in class AB mode. The good agreement between measured and simulated results was shown in both S-parameter modeling and in amplifier design

Keywords

HEMT integrated circuits; III-V semiconductors; MMIC power amplifiers; S-parameters; circuit CAD; field effect MMIC; gallium compounds; integrated circuit modelling; neural nets; 1 micron; 1 to 26 GHz; 1.2 W; 20 V; 220 mA; 7 dB; GaN; HEMT power amplifier; III-V semiconductors; X-band; artificial neural network modeling technique; calculated S-parameter fitting; class AB mode; gate length; gate periphery; multiple bias points; output power; power amplifier design; single stage amplifier; small signal behavior; Artificial neural networks; Frequency measurement; Gallium nitride; HEMTs; High power amplifiers; III-V semiconductor materials; Length measurement; MODFETs; Power amplifiers; Scattering parameters;

fLanguage

English

Journal_Title

Electron Devices, IEEE Transactions on

Publisher

ieee

ISSN

0018-9383

Type

jour

DOI

10.1109/16.906442

Filename

906442