深度学习在射频干扰抑制中的应用研究  

Research on the Application of Deep Learning in Radio Frequency Interference Suppression

作　　者：郭一鸣 GUO Yiming(Zhengzhou University of Industrial Technology,Zhengzhou 451100,China)

机构地区：[1]郑州工业应用技术学院,河南郑州451100

出　　处：《通信电源技术》2023年第16期136-138,共3页Telecom Power Technology

摘　　要：研究深度学习在射频干扰抑制中的应用,设计了一种基于深度学习的射频干扰抑制架构。该架构包括数据预处理、基于循环神经网络的射频干扰识别以及自适应滤波器。其中:数据预处理部分用于预处理原始射频信号;基于循环神经网络的射频干扰识别模块能够准确分类与识别射频信号;自适应滤波器模块能够抑制射频干扰信号。为验证所提架构的有效性,设计了一个射频干扰数据集进行实验和测试。结果表明,该架构在射频干扰抑制方面具有出色的性能,能够显著提高通信系统的稳定性和可靠性。Application of deep learning in radio frequency interference suppression was researched and a radio frequency interference suppression architecture based on deep learning was designed.The architecture includes data preprocessing,radio frequency interference identification based on recurrent neural network and adaptive filter.The data preprocessing part was used to preprocess the original radio frequency signal;The radio frequency interference identification module based on recurrent neural network can accurately classify and identify radio frequency signals;The adaptive filter module can suppress radio frequency interference signals.To verify the effectiveness of the proposed architecture,a radio frequency interference dataset was designed,and experiments and tests were conducted.The results indicate that the architecture has excellent performance in radio frequency interference suppression and can significantly improve the stability and reliability of communication systems.

关 键 词：深度学习 射频干扰 循环神经网络 自适应滤波 

分 类 号：TN975[电子电信—信号与信息处理] TP18[电子电信—信息与通信工程]