DOA Estimation Method Based on Neural Network

Traditional signal direction of arrival (DOA) estimation algorithm has exist some problems, such as a large amount of calculation and slow convergence speed. In this paper, neural network method is used to improve the performance of DOA estimation. Due to the fact that BP neural network is inclined to be trapped in local minimum point, particle swarm optimization (PSO) algorithm is applied to optimization the weights and threshold. The model of DOA estimation based on PSO-BP neural network is constructed and trained. Simulation results show that, compared with classical RBFNN method and traditional MUSIC algorithm, the optimized BP neural network method has higher estimation accuracy and real-time performance.