Research on DOA Estimation Method of Vector Hydrophone Array in Low SNR Based on CNN

This paper presents a direction of arrival (DOA) estimation method for vector sensor arrays based on convolutional neural networks (CNN) to improve the estimation accuracy. The model consists of four convolutional layers and three fully connected layers. The network input is a three-channel data consisting of real part, imaginary part, and phase from the signal covariance matrix received by the array. Each node of the output stands for a presented directional grid, and the output value on that node indicates the probability of a signal locating in the neighborhood of the grid. The experimental results show that the neural network model can achieve 360-degree unambiguous estimation and is capable of acquiring precise and accurate estimation of DOA, especially in the cases of low signal-to-noise ratio (SNR).