Nonlinear HEMT modeling using artificial neural network technique

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

doi:10.1109/MWSYM.2005.1516631

Nonlinear HEMT modeling using artificial neural network technique

Jianjun Gao^*, Lei Zhang, Jianjun Xu, Qi Jun Zhang

^*Corresponding author for this work

Carleton University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

21 Scopus citations

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 200um gate width 0.2Sμm PHEMT (FHX04LG) over a wide range of bias points.

Original language	English
Title of host publication	2005 IEEE MTT-S International Microwave Symposium Digest
Pages	469-472
Number of pages	4
DOIs	https://doi.org/10.1109/MWSYM.2005.1516631
State	Published - 2005
Externally published	Yes
Event	2005 IEEE MTT-S International Microwave Symposium - Long Beach, CA, United States Duration: 12 Jun 2005 → 17 Jun 2005

Publication series

Name	IEEE MTT-S International Microwave Symposium Digest
Volume	2005
ISSN (Print)	0149-645X

Conference

Conference	2005 IEEE MTT-S International Microwave Symposium
Country/Territory	United States
City	Long Beach, CA
Period	12/06/05 → 17/06/05

Keywords

HEMT
Neural networks
Nonlinear modeling

Access to Document

10.1109/MWSYM.2005.1516631

Cite this

@inproceedings{6ae5f34c7f4745258358a9ad80fc41e4,

title = "Nonlinear HEMT modeling using artificial neural network technique",

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 200um gate width 0.2Sμm PHEMT (FHX04LG) over a wide range of bias points.",

keywords = "HEMT, Neural networks, Nonlinear modeling",

author = "Jianjun Gao and Lei Zhang and Jianjun Xu and Zhang, \{Qi Jun\}",

year = "2005",

doi = "10.1109/MWSYM.2005.1516631",

language = "英语",

isbn = "0780388461",

series = "IEEE MTT-S International Microwave Symposium Digest",

pages = "469--472",

booktitle = "2005 IEEE MTT-S International Microwave Symposium Digest",

note = "2005 IEEE MTT-S International Microwave Symposium ; Conference date: 12-06-2005 Through 17-06-2005",

}

Gao, J, Zhang, L, Xu, J & Zhang, QJ 2005, Nonlinear HEMT modeling using artificial neural network technique. in 2005 IEEE MTT-S International Microwave Symposium Digest., 1516631, IEEE MTT-S International Microwave Symposium Digest, vol. 2005, pp. 469-472, 2005 IEEE MTT-S International Microwave Symposium, Long Beach, CA, United States, 12/06/05. https://doi.org/10.1109/MWSYM.2005.1516631

TY - GEN

T1 - Nonlinear HEMT modeling using artificial neural network technique

AU - Gao, Jianjun

AU - Zhang, Lei

AU - Xu, Jianjun

AU - Zhang, Qi Jun

PY - 2005

Y1 - 2005

N2 - 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 200um gate width 0.2Sμm PHEMT (FHX04LG) over a wide range of bias points.

AB - 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 200um gate width 0.2Sμm PHEMT (FHX04LG) over a wide range of bias points.

KW - HEMT

KW - Neural networks

KW - Nonlinear modeling

UR - https://www.scopus.com/pages/publications/33745239682

U2 - 10.1109/MWSYM.2005.1516631

DO - 10.1109/MWSYM.2005.1516631

M3 - 会议稿件

AN - SCOPUS:33745239682

SN - 0780388461

SN - 9780780388468

T3 - IEEE MTT-S International Microwave Symposium Digest

SP - 469

EP - 472

BT - 2005 IEEE MTT-S International Microwave Symposium Digest

T2 - 2005 IEEE MTT-S International Microwave Symposium

Y2 - 12 June 2005 through 17 June 2005

ER -

Nonlinear HEMT modeling using artificial neural network technique

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this