集中式多输入多输出雷达信号盲分离算法研究  

Blind Source Separation Algorithm for Colocated MIMO Radar Signals

作　　者：汤小为[1] 唐波[2] 汤俊[1] 

机构地区：[1]清华大学电子工程系,北京100084 [2]电子工程学院,合肥230037

出　　处：《宇航学报》2013年第5期679-685,共7页Journal of Astronautics

基　　金：国家自然科学基金(61171120;61201379);安徽省自然科学基金(1208085QF103);信息综合控制国家重点实验室基金

摘　　要：在电子对抗领域,对集中式多输入多输出(Multiple-Input Multiple-Output,MIMO)雷达的信号侦察和分选是一个难点。提出采用盲分离(Blind Source Separation,BSS)算法中的非圆复信号快速独立分量分析(NoncircularComplex Fast ICA,NC-FastICA)对MIMO雷达进行信号分选。为了满足盲分离算法的应用条件,提出一种在多视角观测位置采集雷达信号的侦察方法来构建可分离的满秩混合矩阵。仿真结果表明,对相位编码、离散频率编码等典型正交波形进行等角度间隔采样和盲分离时,无论是否存在幅度起伏,在信噪比为10dB时均可以达到低于-14dB的正交波形分离度,对分离后的波形进行相关性对比和时频分析的结果也验证了本文方法的有效性。In electronic countermeasure,reconnaissance and signal sorting of colocated MIMO radar is a difficult point.The blind source separation algorithm based on noncircular complex fast ICA（NC-Fast ICA） is utilized to sort MIMO radar signals.In order to satisfy the application conditions of the BSS algorithm,a reconnaissance method for collecting radar signals in multiple positions with different angles of view is proposed to obtain and a separable full-rank mixing matrix.Several typical orthogonal waveforms such as phase-coded signals and discrete frequency coded waveforms are used for separation.Simulation results show that a separation performance of-14dB can be achieved under the condition of evenly angle spaced sampling and a signal to noise ratio of 10dB regardless of the amplitude fluctuations.The correlation comparison and time-frequency analysis of separated waveforms also demonstrate the validity of proposed method.

关 键 词：MIMO雷达 电子侦察 信号分选 盲分离 正交波形 独立分量分析 

分 类 号：TN957.51[电子电信—信号与信息处理]