Study of artificial neural networks for broadband antenna based on a parametric frequency model

Abstract

In this paper neural network (ANN) is proposed to predict the input impedance of a broadband antenna as a function of its geometric parameters. The input resistance of the antenna is first parameterized by a Gaussian model, and the ANN is constructed to approximate the nonlinear relationship between the antenna geometry and the model parameters. A hybrid gradient descent and particle swarm optimization method is used to train the neural network. The antenna structure is then optimized for broadband operation via a genetic algorithm that uses input impedance estimates provided by the trained ANN in place of brute-force electromagnetic computations. It is found that the required number of electromagnetic computations in training the ANN is ten times lower than that needed during the antenna optimization process.