基于BP神经网络水声通信调制模式识别的研究  

Modulation Recognition of Underwater Acoustic Communication Signals Based on BP Neural Networks

作　　者：尹航[1] 田甜[1] 冯师军 禹润田 YIN Hang;TIAN Tian;FENG Shijun;YU Runtian(The Third Institute of China Electronics Technology Group Corporation,Beijing 100015,China)

机构地区：[1]中国电子科技集团公司第三研究所,北京100015

出　　处：《电声技术》2020年第9期28-32,46,共6页Audio Engineering

摘　　要：介绍一种水声通信模式识别的方法,利用水声通信信号的特征参数,构建基于BP神经网络的水声通信信号调制识别系统,实现水声通信信号的调制识别。在不同信噪比条件下,仿真水声通信信号,建立训练和测试样本。仿真实验结果表明,在一定仿真条件下,该方法的识别正确率可以达到90%以上。This paper introduces a method of modulation recognition of underwater acoustic communication,using the signal characteristic parameters,constructs the modulation recognition system based on BP neural network.Under different SNR conditions,simulating signal characteristic parameters,training and test BP neural network.Comparative experimental results have shown that the modulation recognition of underwater acoustic communication signals can be achieved by using BP neural network,and the recognition accuracy can reach more than 90%under simulation conditions.

关 键 词：水声通信 信号调制模式识别 信号特征参数 BP神经网络 

分 类 号：TN929.3[电子电信—通信与信息系统]