A genetically trained neural network application for fault finding in antenna arrays

Abstract

In this work, an extension of the previous approach on the Genetic Algorithm based Backpropagation Network (GA/BPN) is presented for finding the positions of defective elements in antenna arrays. The backpropagation network (BPN) takes samples of radiation pattern of the array with fault elements and maps it to the location of the faulty element in that array. The weights were extracted and optimized using GA. The result of the conventional ANN procedure is compared with genetically trained neural network approach. The developed methodology is tested for a linear array. The developed network can be used at the base stations to find out the number and location of the fault elements in the array in space platforms.