Intelligent Recognition of Underwater Acoustic Target Noise on Underwater Glider Platform

Abstract

The underwater acoustic target detection system based on the underwater glider platform requires the platform itself to have the ability of target automatic tracking, identification and evaluation, but the traditional methods of underwater target noise identification have strong human-computer interaction characteristics. It can not meet the needs of automatic target recognition. In order to solve this problem, the feature extraction method, automatic recognition model had been studied with the combination of the characteristics of underwater glider in this paper. An intelligent recognition model of underwater target noise based on long-short terms memory network is established. The model is tested in the laboratory, and it is verified by the underwater acoustic signal obtained on the sea. The results show that the intelligent identification model of underwater acoustic target noise can identify underwater acoustic target noise without artificial participation, and meet the requirements of underwater acoustic target detection and identification of the underwater glider platform.