| 292 | 5 | 78 |
| 下载次数 | 被引频次 | 阅读次数 |
随着通信环境的日益复杂,信号的调制分类在各种领域中变得越来越重要。在低信噪比下,能准确地识别出信号的调制类型具有极大的挑战。针对这一问题,提出了一种基于多输入网络的调制识别算法,利用信号的熵值特征、高阶累积量和预处理后的IQ数据作为网络的输入,在网络内部对不同输入数据提取到的特征进行融合,实现了在低信噪比下有效地识别2FSK,4FSK,BPSK,QPSK,8PSK,8QAM,16QAM,32QAM,64QAM这9类数字通信信号。实验结果表明,当信噪比为0 d B时,整个集合的平均识别率能达到93%。
Abstract：As the complexity of communication environment increases,signal modulation classification has become very important in various military and civilian applications.Under low signal-to-noise ratio,it is very challenging to accurately identify the modulation type of the signal.To solve this problem,a modulation recognition algorithm based on multi-input networks is proposed.The network uses signal entropy features,high-order cumulants and preprocessed IQ data as the input of the network,and integrates features extracted from different input data within the network.It can effectively identify 9 types of signals including 2 FSK,4 FSK,BPSK,QPSK,8 PSK,8 QAM,16 QAM,32 QAMand 64 QAM under low signal-to-noise ratio.Experiments show that when the signal-to-noise ratio is 0 d B,the average recognition rate of signal samples can reach more than 93%.
[1] LI L Z,FAN X L,CHEN Z P.Recognition of Intra-pulse Modulation Based on Phase Difference[C]∥Proceedings of 2017 IEEE 2nd Advanced Information Technology,Electronic and Automation Control Conference(IAEAC2017). Chongqing:Institute of Electrical and Electonics Engineers,2017:477-481.
[2]范真真，朱立忠，张笑宇，等．一种小波变换的数字信号调制方式识别方法研究[J]．沈阳理工大学学报，2015,34(3):10-15.
[3] YANG Y Q,JIANG S Q,ZHOU Z. Research on Signal Models and Recognition Method for Digital Modulation[C]∥2019 IEEE 7th International Conference on Computer Science and Network Technology(ICCSNT).Dalian:IEEE,2019:508-512.
[4]郭蕴欣，张越，马宏．基于CNN的数字信号调制识别研究[J]．电子测量技术，2019,42(14):112-116.
[5]李一兵，葛娟，林云．基于熵特征和支持向量机的调制识别方法[J]．系统工程与电子技术，2012,34(8):1691-1695.
[6] LI J C,GUO J,SWIERNIAK A.A New Feature Extraction Algorithm Based on Entropy Cloud Characteristics of Communication Signals[J].Mathematical Problems in Engineering,2015(5):1-8.
[7]郭有为，蒋鸿宇，周劼，等．分离通道联合卷积神经网络的自动调制识别[J]．电讯技术，2018,58(6):702-707.
[8]杨洁，夏卉．基于卷积神经网络的通信信号调制识别研究[J]．计算机测量与控制，2020,28(7):220-224.
[9] WEI S J,QU Q Z,SU H,et al.Intra-pulse Modulation Radar Signal Recognition Based on CLDN Network[J]. IET Radar,Sonar&Navigation,2020,14(6):803-810.
[10]唐作栋，龚晓峰，雒瑞森．一种小波特征与深度神经网络结合的信号制式识别算法[J]．计算机工程与科学，2020,42(5):902-909.
[11] XIE B,XIONG Z Q,WANG Z J,et al.Gamma Spectrum Denoising Method Based on Improved Wavelet Threshold[J].Nuclear Engineering and Technology,2020,52(8):1771-1776.
[12]李晨，杨俊安，刘辉．基于信息熵和GA-ELM的调制识别算法[J]．系统工程与电子技术，2020,42(1):223-229.
[13] ORLIC V D,DUKIC M L.Automatic Modulation Classification:Sixth-order Cumulant Features as a Solution for Real-world Challenges[C]∥2012 20th Telecommunications Forum(Telfor). Belgrade:IEEE,2012:392-399.
[14]杨丽，吴雨茜，王俊丽，等．循环神经网络研究综述[J]．计算机应用，2018,38(S2):1-6.
[15] DALDAL N,YILDIRIMO，POLAT K. Deep Long Shortterm Memory Networks-based Automatic Recognition of Six Different Digital Modulation Types Under Varying Noise Conditions[J].Neural Computing and Applications,2019,31(6):1967-1981.
[16]石荣，吴聪．信噪比的不同定义及对调制识别性能评估的影响[J]．通信技术，2019,52(7):1556-1562.
基本信息:
中图分类号:TN911.3;TP183
引用信息:
[1]熊一谦,高勇.一种多输入神经网络的调制识别方法[J].无线电工程,2021,51(04):277-282.