Underwater acoustic communication system adaptive selection method based on deep neural network

Abstract

The invention discloses an underwater acoustic communication system adaptive selection method based on a deep neural network, and the method comprises the steps: carrying out the quantitative scoring of each feature of underwater acoustic communication; performing performance division on each feature of each underwater acoustic communication system based on the quantitative score table to construct an underwater acoustic communication system performance division table; constructing an underwater acoustic communication system selection deep neural network and an underwater acoustic communication system sample set based on the quantitative score table and the underwater acoustic communication system performance division table; selecting a deep neural network for the underwater acoustic communication system based on the underwater acoustic communication system sample set for training; and selecting the underwater acoustic communication system by using the trained underwater acoustic communication system selection deep neural network. According to the method, quantitative modeling is carried out on selection of a communication system based on different dimensions, the deep neural network is trained through actual test data, communication system selection is carried out, the neural network can be further perfected through a selection result, and data reusability is improved while a blind area is reduced.

Description

technical field [0001] The invention belongs to the field of underwater acoustic communication networks, and in particular relates to an adaptive selection method of an underwater acoustic communication system based on a deep neural network. Background technique [0002] Underwater acoustic communication is one of the effective means of underwater long-distance wireless communication, and it is widely used in ocean observation, warning detection, security defense and other fields. At present, the modulation and demodulation methods commonly used in underwater acoustic communication mainly include direct sequence spread spectrum (DSSS) communication, orthogonal frequency division multiplexing (OFDM) communication, single carrier coherent phase shift keying (PSK) communication and multi-ary frequency shift Keying (MFSK) communication, etc. These underwater acoustic communication systems have their own advantages in terms of communication capability, reliability, concealment, ...

AI Technical Summary

Problems solved by technology

[0011] One of the purposes of the present invention is to provide a method for adaptively selecting an underwater acoustic communication system based on a deep neural network, so as to solve the problem that the selection of an existing underwater acoustic communication system in the background technology needs to rely on the rich experience of technicians, and the existing The selection of the underwater acoustic communication system has not considered and explored issues such as Doppler expansion and signal-to-noise ratio.

Images