基于二级嵌套阵列的宽频段欠定波达方向估计  

Broadband underdetermined direction of arrival estimation based on two level nested array

作　　者：吴晨曦[1] 张旻[1] 王可人[1] WU Chen-xi ZHANG Min WANG Ke-ren(Electronic Engineering Institute of PLA, Hefei, 230037, Chin)

机构地区：[1]解放军电子工程学院,安徽合肥230037

出　　处：《浙江大学学报（工学版）》2017年第5期1016-1023,共8页Journal of Zhejiang University：Engineering Science

基　　金：国家自然科学基金资助项目(61171170);安徽省自然科学基金资助项目(1408085QF115)

摘　　要：针对宽频段欠定波达方向(DOA)估计问题,提出基于二级嵌套阵列的DOA估计方法.利用空间频率对阵列接收数据进行降维处理;利用空间频率的空域稀疏性建立空间频率连续稀疏模型,利用原始对偶方法以及多项式求根得到空间频率的高分辨估计;构建频域协方差矩阵并进行特征分解,利用大特征矢量之和来建立配对函数实现信号频率与空间频率准确配对得到DOA估计.结果表明,该方法可估计的信号数远大于实际阵元数,同时能够有效避免传统稀疏重构方法中由于角度域离散化所导致的模型不匹配对估计性能的影响,提高了估计精度与分辨力.A novel broadband direction of arrival （DOA） estimation algorithm based on two level nestedarray was proposed to achieve broadband underdetermined DOA estimation. The dimension of the arrayreceived data was reduced by using spatial frequencies. Spatial frequencies continuous sparse recoverymodel was constructed by using the spatial sparseness of the spatial frequency. The high resolutionestimation of spatial frequencies was achieved with primal dual approach and root finding. The frequencydomain covariance matrix was constructed. The spatial frequencies and frequencies were matched by usingthe sparse recovery of the sum of larger eigenvectors, which are coming from the frequency domaincovariance matrixes eigen value decomposition（ED）. Then DOA estimation can be obtained. Results showthat the number of sources by the proposed algorithm is larger than the number of actual sensors. Off-grideffects caused by discretizing this range onto a grid in traditional sparse recovery can be neglected, thusimproving precision and resolution of DOA estimation.

关 键 词：阵列信号处理 波达方向估计 嵌套阵列 宽频段 连续稀疏重构 

分 类 号：TN911.23[电子电信—通信与信息系统]