Beamforming against main lobe interference based on radial basis function neural network

Abstract

Aiming at the problem that the performance of traditional beamforming algorithm deteriorates sharply in the presence of main lobe interference, a beamforming algorithm based on radial basis function (RBF) neural network is proposed. Firstly, the minimum variance distortionless response (MVDR) is used to solve the optimal beam pattern in the presence of side lobe interference. Then, the training set of RBF neural network is constructed according to the optimal beam pattern and the direction information of main lobe interference to train the network, so that the trained RBF neural network can suppress the main lobe interference while maintaining the ability of optimal beamforming. The simulation results show that the method can overcome the limitations of traditional beamforming algorithm, suppress the main lobe interference and side lobe interference, and form the correct beam direction. At the same time, the algorithm also has good real-time performance.