【摘要】 基于特征空间(ESB)自适应波束形成算法性能优良,但需要进行矩阵特征分解,运算量大。提出了一种基于神经网络的ESB自适应波束形成算法。该算法仅将Toeplitz化后的采样协方差矩阵的第一列元素作为网络输入,从而降低了输入矢量的维数。利用广义回归神经网络逼近权矢量,神经网络的并行计算可提高运算速度。计算机仿真结果表明此方法是有效的。更多还原

【Abstract】 The eigenspace-based (ESB)adaptive beamforming algorithm has good performance,but it is computa- tionally expensive because of eigen-decomposition.An eigenspace-based adaptive beamforming algorithm based on neural network is proposed.The algorithm reduces the dimension of the input vectors by using the Toeplitz technique for the sample correlation matrix and needs only the first column of the processed matrix.The weight vector is approximated by general regression neural network.This algorithm can make the computation rapid because the neural network can operate in parallel. Computer simulation results show that the method is effective.更多还原