空间同频电子侦察信号的盲分离  

Blind Separation of Space Radio Reconnaissance Signals with Same Frequency

作　　者：周治宇[1] 陈豪[1] 

机构地区：[1]中国空间技术研究院,西安710100

出　　处：《中国空间科学技术》2009年第3期10-15,22,共7页Chinese Space Science and Technology

基　　金：国家重点实验室基金项目(9140C5305020705与9140C5306030707)资助课题

摘　　要：空间电子侦察等应用中,经常会遇到如何分离同频信号的问题,传统的时域和频域处理方法很难解决这一难题。文中提出了利用并行FastICA(快速独立分量分析)盲信号分离技术解决这一难题的方法,该方法利用盲信号分离技术不需要知道信号及信道环境先验信息的特性,符合电子侦察的实际情况,具有广泛的适用范围。通过仿真实验证明,文中介绍的并行FastICA盲分离算法,不仅能分离功率相差十万倍以上的频域混叠信号,而且收敛速度快,分离效果良好,在多个领域具有较好的应用前景。The problem of separating several signals with same frequency is very common in space radio reconnaissance, but it is difficult to deal with it by traditional signal processing. A new blind signal separation method of parallel FastICA to solve the problem was proposed, which didn＇t need any information of the source signals and could correctly separate the signals mixed in the frequency-domain. The method is fit for radio reconnaissance and can be used widely. The simulations demonstrate that the FastICA can separate the signals mixed in the frequency-domain whose power has 10000 times difference. The FastICA not only has a good performance under gauss white noise condition, but also has a fast convergence. The proposed method will have a good application prospect.

关 键 词：同频信号分离 盲信号分离 独立分量分析 空间电子侦察 

分 类 号：TN912.3[电子电信—通信与信息系统] TN957.51[电子电信—信息与通信工程]