基于改进FastICA的雷达信号分离方法  

An Improved FastICA Radar Signal Sorting Method

作　　者：王国涛 姜秋喜 刘方正 WANG Guotao;JIANG Qiuxi;LIU Fangzheng(Institute of Electronic Countermeasure,National University of Defense Technology,Hefei 230037,China)

机构地区：[1]国防科技大学电子对抗学院,安徽合肥230037

出　　处：《探测与控制学报》2021年第6期43-49,共7页Journal of Detection & Control

摘　　要：针对基于辐射源描述字的传统信号分选方法难以适应当前复杂电磁环境的问题,提出基于改进FastICA算法的雷达信号分离方法。该方法利用PCA方法对数据进行降维预处理,采用改进算法循环迭代,得到分离矩阵,再根据分离矩阵提取出独立的雷达信号成分。仿真实验结果表明,该方法所采用的算法能够在复杂电磁环境下分离出源信号,而且较传统FastICA算法具有更快的收敛速度。In order to solve the problem that the traditional signal sorting method based on emitter description words was difficult to adapt to the current complex electromagnetic environment,a radar signal separation method based on improved FastICA algorithm was proposed.In this method,the PCA method was used to reduce the dimensionality of the data,and the improved algorithm was used to iterate in a loop to get the separation matrix,and then the independent radar signal components were extracted according to the separation matrix.Simulation results showed that the proposed algorithm used in this method could separate the source signal in the complex electromagnetic environment,and had a faster convergence speed than the traditional FastICA algorithm.

关 键 词：复杂电磁环境 雷达信号分选 主成分分析 FASTICA算法 

分 类 号：TN971.1[电子电信—信号与信息处理]