Accuracy of Perceptron Based Beamforming for Embedded Smart and MIMO Antennas

Abstract

Array antennas have a nonlinear, complex relationship between the antenna beams generated and the array input functions that generate the steerable beams. In this paper we demonstrate the use of a simple, computationally less intensive Perceptron Neural Network with non-linear sigmoid activation function to do the synthesis of the desired antenna beam. The single neuron is used, where its optimized weights will yield the beam shape required. This paper presents a successfully implemented Perceptron and discusses the error between the desired and Perceptron generated beams The successful beam control gives high accuracy in the maximum radiation direction of the desired beam, as well as optimization in the direction of null points. Moreover, a comparison between the array antenna beams obtained using the Perceptron Single Neuron Weight Optimization method (SNWOM) and the optimized beams obtained using the Least Mean Square (LMS) method, further demonstrates the reliability and accuracy of the Perceptron based beamformer. The tests were performed for two different desired antenna beams: one braod side beam and the other with the antenna radiating in four different desired directions. The Perceptron based antenna may be embedded in the Arduino microcontroller used. It is also shown why it is not possible to get a single beam, linear array antenna with the Perceptron based array reported herein.