基于TC-CNN网络的残缺TACAN空/地信号识别方法  

Incomplete TACAN Air/Ground Signal Recognition Method Based on TC-CNN Network

作　　者：郝彦超 侯进[1,2] 杨宗源 王祥宇 李天宇 文志龙 HAO Yanchao;HOU Jin;YANG Zongyuan;WANG Xiangyu;LI Tianyu;WEN Zhilong(IPSOM Lab,School of Information Science and Technology,Southwest Jiaotong University,Chengdu 611756,China;National Engineering Laboratory of Integrated Transportation Big Data Application Technology,Southwest Jiaotong University,Chengdu 611756,China;Tangshan Institute,Southwest Jiaotong University,Tangshan 063000,China)

机构地区：[1]西南交通大学信息科学与技术学院智能感知智慧运维实验室,四川成都611756 [2]西南交通大学综合交通大数据应用技术国家工程实验室,四川成都611756 [3]西南交通大学唐山研究院,河北唐山063000

出　　处：《无线电工程》2022年第9期1513-1518,共6页Radio Engineering

基　　金：国家重点基础研究发展计划(2014CB845800);四川省科技计划项目(2020SYSY0016)。

摘　　要：TACAN空/地信号是一种基于脉冲调制技术的短程通信信号,主要应用于方位测量和距离测量,当使用接收器捕获TACAN空/地信号时,由于信噪比、信号完整度等差异,导致信号识别率较低。针对传统模板匹配算法无法有效对残缺的TACAN空/地信号进行识别的问题,提出了一种新型卷积神经网络(Convolutional Neural Network,CNN)模型,该模型以传统CNN模型为基础,同时加入了长短期记忆(Long Short-Term Memory,LSTM)人工神经网络结构以提高模型对信号时序特征的识别能力,实验结果表明,当数据丢失率低于30%时,该模型可以达到84%以上的识别率。TACAN air/ground signal is a short-range communication signal based on pulse modulation technology.It is mainly used for azimuth measurement and distance measurement.When the receiver is used to capture TACAN air/ground signal,the signal recognition rate is low due to differences in signal-to-noise ratio and signal integrity.To solve the problem that traditional template matching algorithms cannot effectively identify incomplete TACAN air/ground signals,a new type of convolutional neural network model is proposed.The model is based on the traditional Convolutional Neural Network(CNN)model.The artificial neural network structure of Long Short-Term Memory(LSTM)is added to improve the model’s ability to recognize signal timing characteristics.The experimental results show that when the data loss rate is less than 30%,the recognition rate of this model can reach more than 84%.

关 键 词：电子侦察 TACAN 残缺信号识别 神经网络 

分 类 号：TN911[电子电信—通信与信息系统] TN965[电子电信—信息与通信工程]