Artificial Neural Network Model for HEMTs Constructed from Large-Signal Time-Domain Measurements

Published

June 7, 2002

Author(s)

Dominique Schreurs, Jeffrey Jargon, Kate Remley, Donald C. DeGroot, Kuldip Gupta

Abstract

We develop a methodology to construct behavioral models for microwave devices from time-domain large-signal measurements. The behavioural model for the considered class of devices (microwave transistors) is defined by expressing the terminal currents as functions of the state variables, being the embedded voltages. In this work, we show that artificial neural networks (ANNs) are veluable candidates to represent these relationships. They outperform models based on multivariate polynomials, because they can better represent the typical physical characteristics of the considered devices. Experimental results are quantitatively confirmed by comparison metrics.

Conference Dates

June 6-7, 2002

Conference Location

Seattle, WA

Conference Title

59th Auto. RF Tech. Group Conference

Pub Type

Conferences

Download Paper

https://doi.org/10.1109/ARFTGS.2002.1214677

Local Download

Keywords

artificial neural network, large-signal, measurment, model, nonlinear, time-domain

Wireless (RF)

Citation

Schreurs, D. , Jargon, J. , Remley, K. , DeGroot, D. and Gupta, K. (2002), Artificial Neural Network Model for HEMTs Constructed from Large-Signal Time-Domain Measurements, 59th Auto. RF Tech. Group Conference, Seattle, WA, [online], https://doi.org/10.1109/ARFTGS.2002.1214677, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=33097 (Accessed May 16, 2022)