Pattern Synthesis for Linear Phase Arrays using Artificial Neural Network

الملخص

This paper focuses on the antenna synthesis of uniformly spaced linear phase array using artificial neural network (ANN), and describes the basics of artificial neural network. Chebyshev method is used to compare with this approach. Although, Chebyshev method is able to generate perfectly leveled side lobes, ANN does not have the phenomena of up-swing in edges amplitude of the excitation and grating lobes does not appear in ANN when the distances between elements are increased.
The basic rule is to alter the weights (current distributions of elements) such that the error between the output values and the target values (desired values) is minimized.
In this paper, single layer feed forward neural network with supervised learning is used. An adaptive linear element algorithm (ADALINE) is used for training artificial neural network