基于深度神经网络的无线通信信号抗干扰识别研究  

Study on Anti-Interference Recognition of Wireless Communication Signal Based on Deep Neural Network

作　　者：李姗姗 刘新新 LI Shanshan;LIU Xinxin(School of Information and Electronic Engineering,Shangqiu Institute of Technology,Shangqiu 476000,China)

机构地区：[1]商丘工学院信息与电子工程学院,河南商丘476000

出　　处：《通信电源技术》2025年第6期29-31,共3页Telecom Power Technology

摘　　要：无线通信信号抗干扰识别主要依赖于信号的表层特征,如频率、带宽等,这些特征仅能反映部分信号的内部特性和干扰环境,导致识别精度差,为此研究基于深度神经网络的无线通信信号抗干扰识别。从无线通信环境中采集干扰信号样本并进行预处理,应用短时傅里叶变换(Short Time Fourier Transform,STFT)将信号从时域转换到时频域,全面提取与干扰信号相关的特征。利用深度神经网络建立信号抗干扰识别模型,通过卷化等积、池操作自动学习干扰信号特征,并输出信号抗干扰识别结果。实验结果表明,基于深度神经网络的无线通信信号抗干扰识别方法在5种方法的对比中展现出最优的识别率和抗干扰识别性能,识别精度较好,具有实际应用价值。Anti-jamming identification of wireless communication signals mainly depends on the surface characteristics of signals,such as frequency and bandwidth,which can only reflect the internal characteristics and interference environment of some signals,resulting in poor identification accuracy.Therefore,anti-jamming identification of wireless communication signals based on deep neural network is studied.The interference signal samples are collected from wireless communication environment and preprocessed.The signal is transformed from time domain to time domain by using Short Time Fourier Transform(STFT),and the characteristics related to the interference signal are comprehensively extracted.The model of signal anti-jamming identification is established by using deep neural network,and the characteristics of interference signal are automatically learned by convolution equal product and pool operation,and the results of signal anti-jamming identification are output.The experimental results show that the anti-jamming identification method of wireless communication signal based on deep neural network shows the best identification rate and anti-jamming identification performance in the comparison of five methods,and the identification accuracy is good,which has practical application value.

关 键 词：深度神经网络 无线通信信号 信号抗干扰 信号识别 抗干扰识别 

分 类 号：TN9[电子电信—信息与通信工程]