论文部分内容阅读
为了获取较高的宽带信号的DOA(direction-of-arrival)估计精度,提出了基于改进的广义回归神经网络(IGRNN,improved generalized regression neural network)和主成分分析(PCA,principalcomponent analysis)的宽带DOA估计算法。选用PCA方法对训练样本进行降维,以降低神经网络的复杂度;利用粒子群算法优化GRNN的参数;根据选取不同的聚焦角度确定粗估计、精估计的训练模型,通过粗估计得出目标的大致方位后,利用精估计模型得出最终的估计结果,避免了聚焦角度对估计精度的影响。仿真结果表明,本文提出的算法具有较好的估计精度和较高的工作效率。
In order to obtain high DOA (direction-of-arrival) estimation accuracy of wideband signals, a wideband DOA based on improved generalized regression neural network (IGRNN) and principal component analysis (PCA) Estimation algorithm. The PCA method is used to reduce the training samples to reduce the complexity of the neural network. Particle swarm optimization is used to optimize the parameters of GRNN. The rough and sperm estimation training models are determined according to different focusing angles. After the approximate location, the final estimation result is obtained by using the refined estimation model, which avoids the influence of the focusing angle on the estimation accuracy. Simulation results show that the proposed algorithm has better estimation accuracy and higher working efficiency.