基于双通道复数卷积神经网络的DOA估计算法

针对低信噪比下基于实数卷积神经网络(RV-CNN)的阵列波达方向(DOA)估计方法对接收信号幅相特征提取不充分的问题,引入复数卷积神经网络(CV-CNN)进行DOA估计。为进一步提高分类准确率,构建了一种基于复数卷积神经网络的非对称双通道DOA估计模型(CV-DCNN)。该模型以阵列接收信号的复数协方差矩阵作为输入,分别输入由空洞卷积层组成的第一通道和由标准卷积层组成的第二通道中,其中空洞卷积在不损失角度信息的情况下,增大特征图的感受野。通过复数卷积神经网络(CV-CNN)独有的复数卷积方式提取和融合信号的幅值和相位特征,将双通道提取的特征融合后通过全连接层和sigmoid函数实现角度分类结果输出。实验结果表明,CV-CNN比RV-CNN有更快的收敛速度,在低信噪比和少快拍条件下,CV-CNN比RV-CNN有更高的估计精度,而CV-DCNN比CV-CNN在收敛速度和估计精度上又有了进一步的提升。

Blind Joint DOA and Polarization Estimation for Polarization Sensitive Coprime Planar Arrays via a Fast-Convergence Quadrilinear Decomposition Approach

The problem of joint direction of arrival(DOA)and polarization estimation for polarization sensitive coprime planar arrays(PS-CPAs)is investigated,and a fast-convergence quadrilinear decomposition approach is proposed.Specifically,we first decompose the PS-CPA into two sparse polarization sensitive uniform planar subarrays and employ propagator method(PM)to construct the initial steering matrices separately.Then we arrange the received signals into two quadrilinear models so that the potential DOA and polarization estimates can be attained via quadrilinear alternating least square(QALS).Subsequently,we distinguish the true DOA estimates from the approximate intersecting estimations of the two subarrays in view of the coprime feature.Finally,the polarization estimates paired with DOA can be obtained.In contrast to the conventional QALS algorithm,the proposed approach can remarkably reduce the computational complexity without degrading the estimation performance.Simulations demonstrate the superiority of the proposed fast-convergence approach for PS-CPAs.

Two-dimensional DOA estimation based on thin array towed by a small autonomous platform

The small autonomous platform with a thin line array is an important tool for underwater acoustic mobile surveillance.Generally,only one-dimensional(1-D)direction-of-arrival(DOA)of the source signal can be estimated using a thin towed line array.In this work,the two-dimensional(2-D)DOA estimation is achieved by the thin line array towed by a small autonomous platform due to its flexible maneuver.Two perpendicular tow paths are formed through the fast turning of this array.An L-shaped array is formed by the same towed array on these two tow paths at different times.Using the array on these two straight paths,two 1-D DOAs of the source signal are obtained respectively,and then the 2-D DOA based on the formed L-shaped array can be estimated.The effectiveness of proposed approach is verified by numerical simulations and its theoretical error is analyzed.