基于高阶累积量和BP神经网络的数字调制识别  

Digital Modulation Recognition Based on High Order Cumulant and BP Neural Network

作　　者：陈震峰 吴明 孙卫华 CHEN Zhenfeng;WU Ming;SUN Weihua(No.722 Research Institute of China State Shipbuilding Corporation Limited,Wuhan 430205)

机构地区：[1]中国船舶集团有限公司第七二二研究所,武汉430205

出　　处：《舰船电子工程》2024年第1期60-62,共3页Ship Electronic Engineering

摘　　要：针对非合作通信下低信噪比数字调制识别率低的问题,论文提出了一种基于高阶累积量和BP神经网络的调制识别方法。此方法借助二、四、六、八阶累积量构造出T1、T2两种特征值,这两种特征值可以在较低的信噪比下有效地识别2ASK、4ASK、2FSK、4FSK、2PSK、4PSK六种数字调制信号。经过Matlab仿真实验可以得出,当信噪比大于等于-3dB时,六种信号的识别率都可达到100%。To solve the problem of low recognition rate of digital modulation with low signal-to-noise ratio in non-cooperative communication,a modulation recognition method based on high-order cumulant and BP neural network is proposed in this paper.In this method,T1 and T2 are constructed by means of the second,fourth,sixth and eighth order cumulants.These two eigenvalues can effectively identify the six digital modulated signals of 2ASK,4ASK,2FSK,4FSK,2PSK and 4PSK under low signal-to-noise ratio.Through Matlab simulation experiment,it can be concluded that when the signal-to-noise ratio is greater than or equal to-3dB,the recognition rate of six kinds of signals can reach 100%.

关 键 词：调制识别 高阶累积量 神经网络 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]