Solution of the non-uniformly spaced array problem using neural networks

Abstract

A neural network algorithm used in a non-conventional way to solve the non-uniformly spaced array problem is demonstrated. Using this algorithm, the problem of uniformly spaced and non-uniformly excited arrays was solved. Comparison between this method and the Dolph-Chebyshev method demonstrated its capability of producing lower sidelobe levels for same beamwidth and number of elements. Moreover, using this algorithm to synthesize non-uniformly spaced and non-uniformly excited arrays improved its performance remarkably and enabled it to compete with other synthesis methods such as Redlich and the iterative optimization.