Neural network based beamforming using a Cylindrical Patch Array

A Neural Network algorithm is implemented for beamforming problem. The cylindrical array with M directive MPA elements has a full coverage of 360°. Considering the total angular coverage of 360° in terms of 12 sectors of 30° each and activating only some MPA elements in the related sector reduces the training set and increases the performance of the beamformer. Increasing the number of targets in different sectors has no effect on the performance of the beamformer.