基于深度神经网络的高环境适应性水声通信系统研究

付晓梅　贾碧群　王思宁

摘   要：深度神经网络中的自动编码器（Autoencoder，AE）通过收发端两个神经网络模块进行全局优化，利用端到端的训练方式以提高通信系统的可靠性. 然而，现有对AE的研究未针对信道进行特殊设计，尤其对于时变的水声信道的多径效应，难以进行灵活调整，降低了该方法的实用性. 本文提出一种提高水声通信系统信道环境适应性的Attention-Autoencoder网络模型，基于Attention网络可以高效地从大量信息中筛选出关键信息的特点，设计了一种针对水声信道的Attention机制，该机制能够增加网络提取水声信道特征的能力，使系统的适应性大大提高. 仿真验证和湖试实验结果表明，基于Attention-Autoencoder网络模型的通信系统与基于文献中AE模型和没有引入神经网络的水声通信系统相比，具有更高的信道环境适应性.

关键词： OFDM;水声通信;注意力网络（Attention）;自动编码器（Autoencoder，AE）

中图分类号：TN  929.3                      文献标志码：A

Research on Underwater Acoustic Communication System with

High Environmental Adaptability Based on Deep Neural Network

FU Xiaomei JIA Biqun WANG Sining

（School of Marine Science and Technology，Tianjin University，Tianjin 300072，China）

Abstract：The Autoencoder（AE） in the deep neural network is globally optimized through two neural network modules at the transmitter and receiver，and uses end-to-end training to improve the reliability of the communication system. However，the existing research on the AE does not have a special design for the channel，especially for the multipath effect of the time-varying underwater acoustic channel，and thus it is difficult to make flexible adjustments，which reduces the practicability of the method. This paper proposes an Attention-Autoencoder network model to improve the adaptability of the underwater acoustic communication system channel environment. Based on the Attention network's characteristic that it can efficiently filter out key information from a large amount of information，an Attention mechanism for the underwater acoustic channel is designed. The mechanism can increase the ability of the network to extract the characteristics of the underwater acoustic channel and greatly improve the adaptability of the system. Simulation verification and lake test results show that the communication system based on a comparision of. Attention-Autoencoder network model with the AE model in the literature and the underwater acoustic communication system without the introduction of neural networks，has a higher channel environment adaptability.

Key words：orthogonal frequency division multiplexing（OFDM）; underwater acoustic communication;attention;autoencoder（AE）

水声通信在海洋信息数据采集、环境监测、沿海石油勘探等方面发挥着重要的作用. 水声信道由于具有快时变、窄带宽、显著的多径效应和多普勒频移等特性，是最复杂的信道之一[1]，在水聲通信系统中需要准确估计和跟踪信道状态信息（CSI）.

近年来，将深度神经网络（Deep Neural Net-work， DNN）引入水声通信的接收端，取得了一些积极进展，文献[2]利用深度神经网络代替信道估计模块，与最小二乘（LS）算法相比提高了信道估计的精度;文献[3]利用深度神经网络直接代替信道估计与均衡，提高了系统的可靠性;文献[4]使用深度……