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

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.