Non-linear modeling of parabolic reflector: Neural network approach

Yilmaz A., Saka B.

ELECTROMAGNETICS, vol.19, no.2, pp.187-200, 1999 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 19 Issue: 2
  • Publication Date: 1999
  • Doi Number: 10.1080/02726349908908634
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.187-200
  • Hacettepe University Affiliated: Yes


In this paper, we present artifical neural network (ANN) models for the calculation of the focal region fields of a parabolic reflector and the estimation of the direction of arrival. We choose a feedforward NN architecture (specifically multilayer perceptrons (MLPs)) for their robust and massively interconnected structure. Simulated results achieved with these models show that the neural network approach is a promising alternative to the conventional methods for focal region calculations of the parabolic reflectors. This paper also represents the results obtained from a NN model trained for the estimation of the direction of arrival for the array-fed parabolic reflector.