卷积神经网络的被动测向通道相位校正方法  

A Phase Calibration Method of Passive Direction-Finding Channel Based on Convolutional Neural Network

作　　者：蒋伊琳[1] 张伟 陈涛[1] 张玉欣 JIANG Yilin;ZHANG Wei;CHEN Tao;ZHANG Yuxin(College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China;Luoyang Electro-optical Equipment Research Institute of Aviation Industry Corporation of China,Luoyang 471001,Henan,China)

机构地区：[1]哈尔滨工程大学信息与通信工程学院,哈尔滨150001 [2]中国航空工业集团洛阳电光设备研究所,河南洛阳471001

出　　处：《实验室研究与探索》2023年第7期54-57,共4页Research and Exploration In Laboratory

基　　金：哈尔滨工程大学本科教学改革研究项目(JG2019B76)。

摘　　要：为提高被动测向的准确度,学者们提出多种相位补偿方法,并将其应用于各种接收机中,提出一种更实用的通道失配模型和一种基于卷积神经网络的被动测向通道相位校正方法(PDFCPC-CNN)。它可充分利用先验信息,实现射频信号通道的全相位和频率校正。为提高实际应用,使用通用软件无线电外设(USRP)接收的实验数据进行进一步验证。仿真结果表明,该方法可很好地应用于实践中。Recently,many phase compensation methods have been studied and applied to various receivers in order to improve the accuracy of direction-finding.This paper proposes a more practical channel mismatch model and a passive direction-finding channel phase calibration method based on convolutional neural network(PDFCPC-CNN).It can make full use of prior information to achieve full phase and frequency correction of radio frequency signal channel.In order to improve the practical application,the experimental data received from Universal Software Radio Peripheral(USRP)are used for validation.According to the simulation results,this method can be applied well in simulation and practice.

关 键 词：卷积神经网络 相位误差 通道校正 通道失配 无线电外设 

分 类 号：TN974[电子电信—信号与信息处理]