Neural networks for large- and small-signal modeling of MESFET/HEMT transistors

Author

Làzaro, Marcelino ; Santamaría, Ignacio ; Pantaleón, Carlos

Author_Institution

DICOM, Cantabria Univ., Santander, Spain

Volume

50

Issue

6

fYear

2001

fDate

12/1/2001 12:00:00 AM

Firstpage

1587

Lastpage

1593

Abstract

In this paper, we present a comparative study of three neural networks-based solutions for large- and small-signal modeling of MESFET and HEMT transistors. The first two neural architectures are specific for this modeling problem: the generalized radial basis function (GRBF) network, and the smoothed piecewise linear (SPWL) model. These models are compared with the well-known multilayer perceptron (MLP) network. Results are presented for both the large- and small-signal regimes separately. Finally, a global model is proposed that is able to accurately characterize the whole behavior of the transistors. This model is based on a simple combination of the best models obtained for the two kinds of regimes

Keywords

Schottky gate field effect transistors; electronic engineering computing; equivalent circuits; high electron mobility transistors; intermodulation; microwave field effect transistors; multilayer perceptrons; neural nets; piecewise linear techniques; radial basis function networks; semiconductor device models; GRBF network; HEMT; MESFET; MLP network; generalized radial basis function network; global model; intermodulation; large-signal modeling; microwave transistors; multilayer perceptron network; neural networks-based solutions; nonlinear modeling; small-signal modeling; smoothed PWL model; smoothed piecewise linear model; transistor modeling; HEMTs; MESFETs; Microwave FETs; Microwave circuits; Microwave devices; Microwave transistors; Multilayer perceptrons; Neural networks; Piecewise linear approximation; Piecewise linear techniques;

fLanguage

English

Journal_Title

Instrumentation and Measurement, IEEE Transactions on

Publisher

ieee

ISSN

0018-9456

Type

jour

DOI

10.1109/19.982950

Filename

982950