Neural network modeling of active devices for use in MMIC design

Gunes F. , Torpi H. , Cetiner B.

ARTIFICIAL INTELLIGENCE IN ENGINEERING, vol.13, no.4, pp.385-392, 1999 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 13 Issue: 4
  • Publication Date: 1999
  • Doi Number: 10.1016/s0954-1810(99)00011-4
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.385-392
  • Keywords: modeling, active device, microwave, neural network
  • Yıldız Technical University Affiliated: Yes


This work can be classified into three parts: The first part is a multidimensional signal-noise neural network model for a microwave small-signal transistor. Here the device is modeled by a black box, whose small signal and noise parameters are evaluated through a neural network, based upon the fitting of both these parameters for multiple bias and configuration with their target values. The second part is the computer simulation of the possible performance (F, V-i, G(max)) triplets. In the final part, which is the combination of the first two parts, the performance curves are obtained using the relationships among operation conditions f, V-CE, and I-CE; the noise figure, input VSWR and maximum stable transducer gain. (C) 1999 Elsevier Science Ltd. All rights reserved.