Convolutional Neural Network Algorithm and Application Method for Real-Time Beam Steering in RF System

This paper presents a novel artificial intelligence (AI)-based phase shift system in a beamforming system implemented with field programmable gate array (FPGA)-based hardware by integrating a conventional convolutional neural network (CNN) algorithm. The position of the target can be determined through a phase shifter in a beamforming system using artificial intelligence. In a system that emits a beam from a radio frequency (RF) transmitter and receives a beam from an RF receiver, artificial intelligence can control the phase. It controls the phase of the transmitter for beam scanning and the phase to optimize the signal-to-noise ratio (SNR) of the receiver. The position of the target was detected by learning the signal input data from the receiver. Targets were detected through two-beam scanning processes in a 3D space. The first is a coarse process of detecting the approximate position of the target in the entire space, and the second is a fine process of detecting the area in detail after detecting the first approximate position. The phases of the individual antennae should be controlled for optimal beamforming based on the $5\times 5$ antenna, and the phase is detected at high speed by holding the phase large in the first coarse tuning. The second scan entails a narrow range scan with a small phase to detect it at a high speed accurately. This study shows that with FPGA, AI beamforming can be implemented through two scanning methods without image sensors. Based on the receiver’s $5\times 5$ antenna, the CNN input feature consisted of $35\times 35$ classifies the class with high accuracy.