基于改进YOLOv3的OFDM信号中常见干扰的识别  

Identification of Common Jamming in OFDM Signal Based on Improved YOLOv3

作　　者：郑雄 杨晶晶[1] 张彬 吴季达 黄铭[1] ZHENG Xiong;YANG Jingjing;ZHANG Bin;WU Jida;HUANG Ming(School of Information,Yunnan University,Kunming 650091,China;Radio Monitoring Center of Yunnan Province,Kunming 650228,China)

机构地区：[1]云南大学信息学院,昆明650091 [2]云南省无线电监测中心,昆明650228

出　　处：《电子信息对抗技术》2023年第6期9-16,共8页Electronic Information Warfare Technology

基　　金：国家自然科学基金资助项目(62261059,61963037,61863035)。

摘　　要：干扰识别是无线电监测和通信抗干扰的关键环节。针对正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)宽带传输系统中潜在的干扰问题,提出了一种基于目标检测网络的干扰识别方法。核心思想是将传输频带中的多干扰识别问题转化为时频谱图中的多目标检测问题,进而利用改进的目标检测算法进行识别。实验结果表明,该方法能有效识别传输频带内音调干扰、噪声干扰、扫频干扰、脉冲噪声干扰和锯齿波扫频干扰的类型、数量、干扰频率和时间范围,同时相比改进前的YOLOv3算法,平均精度提高了7.6%,权值文件、参数量和计算量分别降低了82.5%,82.6%,90%,对能耗受限场景下的实时检测具有潜在应用价值。Jamming identification is a key aspect of radio monitoring and communication anti-jamming.For the potential jamming problem in orthogonal frequency division multiplexing(OFDM)bandwidth transmission system,an jamming identification method based on target detection network is proposed.The core idea is to transform the multiple jamming identification problem in the transmission band into a multiple target detection problem in the time-frequency spectrogram.Then the improved target detection algorithm for identification is used.The experimental results show that the method can effectively identify the type,quantity,jamming frequency and time range of tone jamming,noise jamming,sweep jamming,impulse noise jamming and sawtooth wave sweep jamming in the transmission band.The average accuracy is improved by 7.6%,and the weight file,number of parameters and computation volume are reduced by 82.5%,82.6%and 90%,respectively,compared with the YOLOv3 algorithm before improvement.It has potential application value for real-time detection in energy-constrained scenarios.

关 键 词：OFDM信号 干扰识别 轻量化模型 图形目标检测 

分 类 号：TN911.4[电子电信—通信与信息系统]