基于深度学习的多进制相移键控信号调制识别研究  

Research on Modulation Recognition of MPSK Signal Based on Deep Learning

作　　者：孙会楠[1] SUN Huinan(School of Data Science and Information Engineering,Harbin Huade University,Harbin 150025,China)

机构地区：[1]哈尔滨华德学院数据科学与信息工程学院,黑龙江哈尔滨150025

出　　处：《太原学院学报（自然科学版）》2024年第1期54-64,共11页Journal of TaiYuan University:Natural Science Edition

摘　　要：国内外众多的学者针对信号的调制识别做了许多深入的研究,并不断地研究出各种调制识别方法。针对多进制相移键控信号(multiple phase shift keying, MPSK)的识别效果不理想,给出了基于深度学习的识别模型,利用信号的时频图和星座图相关特征进行MPSK调制信号类型的识别,并基于时频图和星座图的识别结果进行决策融合,对比3种方法的识别效果,实现对MPSK信号识别效果的有效提升。Many scholars at home and abroad have done a lot of in-depth research on signal modulation recognition,and devised a variety of modulation recognition methods.However,among these recognition algorithms,the recognition effect of Multiple Phase Shift Keying(MPSK)signals is not ideal.The article will use a deep learning recognition model to identify the type of MPSK modulation signal using the relevant features of the signal’s time-frequency map and constellation map,and make decision fusion based on the recognition results of the time-frequency and constellation graphs.The recognition effects of the three methods are compared to achieve substantial improvement of MPSK signal recognition effect.

关 键 词：深度学习 调制识别 多进制相移键控 决策融合 

分 类 号：TH77[机械工程—仪器科学与技术]