基于独立分量分析的混合信号盲分离技术  

Blind Separation of Mixing Signals based on Independent Component Analysis

作　　者：王雁涛[1] 吉磊[2] WANG Yan-tao;JI Lei(Military Representative Bureau of Naval Equipment Department in Chongqing Region, Chongqing 400042, China;No.30 Institute of CETC, Chengdu Sichuan 610041, China)

机构地区：[1]海军装备部驻重庆地区军事代表局,重庆400042 [2]中国电子科技集团公司第三十研究所,四川成都610041

出　　处：《通信技术》2018年第5期1041-1044,共4页Communications Technology

摘　　要：针对信号接收端接收多路信号引起线性瞬时混叠的情形,提出基于独立分量分析的混合信号盲分离方法。首先,建立信号混合数学模型,并根据源信号之间的统计独立特性构建目标函数;其次,采用固定点算法优化目标函数,寻找极值点,得到信号分离矩阵;最后,利用分离矩阵和观测信号分离出各路源信号。仿真实验的结果表明,在多路通信信号和其他信号线性瞬时混合的情况下,提出的方法能够有效地分离出各个源信号。For the problem of linear instantaneous mixing signal at the receiver, the mixing signal blind separation method based on independent component analysis is proposed. Firstly, a signal mixing mathematical model is established, and based on the statistical independence characteristics of the source signals, an objective function constructed. Then the fixed point algorithm is used to optimize the objective function, find the extreme points, and acquire the signal separation matrix. Finally, the source signals are separated by using the separation matrix and observation signals. The simulation experiments indicate that the proposed method can effectively separate the source signals when the multipath communication signals are mixed with other signals in a linear and instantaneous manner.

关 键 词：独立分量分析 统计独立 信号分离 线性瞬时混合 

分 类 号：TN911.72[电子电信—通信与信息系统]