论文部分内容阅读
针对阵列信号处理的特点,提出了一种基于广义回归神经网络的 DOA 估计方法。仿真结果表明,GRNN 对多源信号 DOA 估计精度较好,对信道噪声不敏感,而且无信源数少于天线阵元数的限制。
Aiming at the characteristics of array signal processing, a DOA estimation method based on generalized regression neural network is proposed. Simulation results show that GRNN has better estimation accuracy for DOA of multi-source signal and is insensitive to channel noise. Moreover, no source number is less than the number of antenna elements.