An end-to-end DOA estimation method based on deep learning for underwater acoustic array

The Direction of arrival (DOA) estimation of signals is a fundamental problem in array signal processing and one of the tasks in many fields such as radar arrays and sonar arrays. In this paper, we propose an end-to-end deep learning-based network structure for DOA estimation task of underwater acoustic arrays, and train the model by extracting array features. We compared the proposed model with traditional methods such as CBF and MVDR, and found that the method proposed in this paper can effectively identify the incoming wave direction of unknown signals in water after training. Compared with various traditional algorithms, the method proposed in this paper significantly improves the effective measurement range of DOA and reduces the angular resolution.