A large-signal characterization of an HEMT using a multilayered neural network

Author

Shirakawa, Kazuo ; Shimiz, Masahiko ; Okubo, Naofumi ; Daido, Yoshimasa

Author_Institution

Fujitsu Labs. Ltd., Kawasaki, Japan

Volume

45

Issue

9

fYear

1997

fDate

9/1/1997 12:00:00 AM

Firstpage

1630

Lastpage

1633

Abstract

We propose an approach to describe the large-signal behavior of a high electron-mobility transistor (HEMT) by using a multilayered neural network. To conveniently implement this in standard circuit simulators, we extracted the HEMT´s bias dependent behavior in terms of conventional small-signal equivalent-circuit elements. We successfully represented seven intrinsic elements with a five-layered neural network (composed of 28 neurons) whose inputs are the gate-to source bias (V_gs,) and drain-to-source bias (V_ds) A “well-trained” neural network shows excellent accuracy and generates good extrapolations

Keywords

circuit analysis computing; equivalent circuits; extrapolation; high electron mobility transistors; microwave field effect transistors; multilayer perceptrons; semiconductor device models; HEMT; bias dependent behavior; drain-to-source bias; extrapolations; gate-to source bias; large-signal characterization; multilayered neural network; small-signal equivalent-circuit elements; standard circuit simulators; Analytical models; Circuit simulation; Databases; Equations; Extrapolation; HEMTs; MODFETs; Multi-layer neural network; Neural networks; Neurons;

fLanguage

English

Journal_Title

Microwave Theory and Techniques, IEEE Transactions on

Publisher

ieee

ISSN

0018-9480

Type

jour

DOI

10.1109/22.622932

Filename

622932