Nonlinear HEMT modeling using artificial neural network technique

Author

Jianjun Gao ; Lei Zhang ; Jianjun Xu ; Qi-Jun Zhang

Author_Institution

Dept. of Electron., Carleton Univ., Ottawa, Ont., Canada

fYear

2005

fDate

12-17 June 2005

Abstract

An improved nonlinear modeling technique for high electron mobility transistors (HEMT) based on the combination of the conventional equivalent circuit and artificial neural network (ANN) modeling techniques is presented. Effective initial values of the artificial neural network for each nonlinear element in HEMT model are evaluated from a semi-analytical parameter extraction technique. A multi-goal DC, S-parameter, and harmonic (DC/S/HB) training process has been formulated. Good agreement is obtained between the model and data of the DC, S-parameter, and harmonic performance for a 200μm gate width 0.25μm PHEMT (FHX04LG) over a wide range of bias points.

Keywords

S-parameters; electronic engineering computing; equivalent circuits; high electron mobility transistors; neural nets; semiconductor device models; 0.25 micron; 200 micron; DC performance; PHEMT modeling; S-parameter performance; artificial neural networks; equivalent circuits; harmonic performance; high electron mobility transistors; nonlinear HEMT modeling; semi-analytical parameter extraction; Artificial neural networks; Equivalent circuits; HEMTs; MODFETs; Neural networks; Neurons; Nonlinear equations; Parameter extraction; Scattering parameters; Table lookup;

fLanguage

English

Publisher

ieee

Conference_Titel

Microwave Symposium Digest, 2005 IEEE MTT-S International

ISSN

01490-645X

Print_ISBN

0-7803-8845-3

Type

conf

DOI

10.1109/MWSYM.2005.1516631

Filename

1516631