摘要
为识别当前卫星通信系统所采用的主要调制方式,提出了一种基于多端卷积神经网络的通信信号调制识别算法。利用信号的先验信息以及对网络拓扑结构的认知,将信号时域波形转化为眼图和矢量图,作为信号的浅层特征表达,并由此设计了基于多端卷积神经网络的调制识别模型。通过训练所搭建的网络,对浅层特征进行深度提取和映射,最终完成了目标信号的调制识别。仿真实验表明,所提算法相对于传统调制识别算法以及目前基于波形和星座图的深度学习识别算法识别效果更好,当信噪比为5 dB时,识别性能可达95%。
In order to identify the main modulation modes adopted in current satellite communication systems, a signal modulation recognition algorithm based on multi-inputs convolution neural network was proposed. With the prior information of the signals and knowledge of the network topological structure, the time-domain signal waveforms were converted into eye diagrams and vector diagrams to represent the shallow features of the signals. Meanwhile, the modulation recognition model based on multi-inputs convolution neural network was designed. Through the training of the network, the shallow features were deeply extracted and mapped. Finally, the signal modulation recognition task was completed. The simulation results show that compared with the traditional algorithms and deep learning algorithms, the proposed method has a better anti-noise performance, and the overall recognition rate of this algorithm can reach 95% when the signal-to-noise ratio is 5 dB.
作者
查雄
彭华
秦鑫
李广
李天昀
ZHA Xiong;PENG Hua;QIN Xin;LI Guang;LI Tianyun(School of Information Systems Engineering,Information Engineering University,Zhengzhou 450001,China)
出处
《通信学报》
EI
CSCD
北大核心
2019年第11期30-37,共8页
Journal on Communications
基金
国家自然科学基金资助项目(No.61401511)
关键词
调制识别
多端卷积神经网络
眼图
矢量图
modulation recognition
multi-inputs convolution neural network
eye diagram
vector diagram
