基于K近邻算法的来波方向估计方法  

A DOA Estimation Method Based on K-nearest Neighbor

作　　者：陈中 王杰贵 唐希雯 杨航 CHEN Zhong;WANG Jiegui;TANG Xiwen;YANG Hang(Institute of Electronic Countermeasure, National University of Defence Technology, Hefei 230031, China)

机构地区：[1]国防科技大学电子对抗学院,安徽合肥230031

出　　处：《探测与控制学报》2022年第1期24-28,共5页Journal of Detection & Control

摘　　要：针对传统波达角估计方法只适用于特定天线阵列,计算量过大和实时性差的问题,提出采用K近邻算法(KNN)对任意天线阵列实现高精度来波方向估计的方法。该方法提取来波信号的相位和幅度信息作为输入数据,利用K近邻算法构建来波方向估计模型,实现了高精度、实时化的来波方向估计。仿真实验结果表明,该方法能够实现高精度的来波方向估计,和干涉仪测向方法进行对比,证明该方法对频率估计误差和信号入射范围有更好的鲁棒性,进一步体现了该方法的优越性和可行性。Aiming at the problems that the traditional DOA estimation method was only suitable for specific antenna array,the amount of calculation was too large and the real-time performance was poor,a high-precision DOA estimation method for any antenna array using k-nearest neighbor algorithm(KNN)was proposed.The phase and amplitude information of the incoming signal between the antenna elements were extracted as the input data of the model.By building direction estimation model with K-nearest neighbor algorithm,the high estimation accuracy could be obtained.At the same time,it was of good adaptability for incoming signals with wide frequency range,different signal-to-noise ratio and large signal incidence range.The results of simulation experiments verified the superiority and feasibility of the method.

关 键 词：波达角估计 机器学习 K近邻算法 

分 类 号：TN974[电子电信—信号与信息处理]