基于导向矢量特征的多源DOA降维估计

翁晓君; 张旻; 李鹏飞

doi:10.15892/j.cnki.djzdxb.2011.04.026

2011 , Vol. 31 >Issue 4: 176 - 179

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2011.04.026

摘要

针对利用智能学习方法进行多信号源方向估计模型难以构建的难题,文中提出了一种有效的降维构建方法。该方法首先对构造的DOA矩阵进行特征分解,获取各个信号源的DOA矩阵导向矢量,这样就可以用单信号样本来训练RBF神经网络模型,然后利用训练好的模型分别对分离出来的信号导向矢量进行映射估计,从而达到了对多信号源来波方向进行降维估计的目的,仿真结果也证明了文中方法的有效性和可行性。

关键词： 多源方向估计; DOA矩阵; 导向矢量; 特征分离; RBF神经网络

本文引用格式

翁晓君 , 张旻 , 李鹏飞 . 基于导向矢量特征的多源DOA降维估计[J]. 弹箭与制导学报, 2011 , 31(4) : 176 -179 . DOI: 10.15892/j.cnki.djzdxb.2011.04.026

Abstract

To solve the modeling problem of multi-source direction estimation based on smart learning method, an effective dimension-degraded modeling approach was proposed in this paper. This approach based on decomposing the DOA matrix could result in the steering-vector of each signal source, then they were taken as the input vector to train the radial basis function neural networks (RBFNN) model with the training sets of single source, the trained model could approximate the nonlinear mapping from the separating input vectors of multi-source to direction-of-arrival. The simulation results showed the effectiveness and feasibility of this method.

Key words： multi-source direction estimation; DOA matrix; steering-vector; separated character; RBFNN

[an error occurred while processing this directive]

参考文献

[1]	季飞, 余华, 谢泽明,等. 基于DOA矩阵法的矢量传感器阵列二维波达方向估计[J]. 电子与信息学报, 2008, 30(8): 1886-1889.
[2]	夏铁骑, 汪学刚, 郑毅,等. 联合对角化-DoA 矩阵方法[J]. 中国科学E辑:信息科学, 2008, 38(4): 599-606.
[3]	Guo XS, Wan Q, Yang W L, et al. Low-complexity 2D coherently distributed sources decoupled DOAs estimation method[J]. SciChina Ser F-Inf Sci, 2009, 52(5): 835-842.
[4]	S Vigneshwaran, Narasimhan Sundararajan. Direction of arrival estimation under array sensor failures using a minimal resource allocation neural network[J]. IEEE Transactions on Antennas and Propagation, 2007, 55(2): 334-343.
[5]	Wang M, Yang S, Wu S, et al. A RBFNN approach for DOA estimation of ultra wideband antenna array[J]. Neurocomputing, 2008, 71(4/6): 631-640.
[6]	Nelson Jorge G Fonseca, Michael Coudyser, Jean-Jacques Laurin, et al. On the design of a compact neural network-based DOA estimation system[J]. IEEE Transactions on Antennas and Propagation, 2010, 58(2): 357-366.
[7]	严颂华, 吴世才, 吴雄斌. 基于神经网络的高频地波雷达目标到达角估计[J]. 电子与信息学报, 2008, 30(2): 339-342.
[8]	安冬, 王守觉. 基于仿生模式识别的DOA估计方法[J]. 电子与信息学报, 2004, 26(9): 1468-1472.
[9]	Ching-Sung Shieh, Chin-Teng Lin. Direction of arrival estimation based on phase differences using neural fuzzy network[J]. IEEE Transactions on Antennas and Propagation, 2000, 48(7): 1115-1124.
[10]	张旻, 李鹏飞. 基于互相关函数相角特征的RBF神经网络来波方向估计[J]. 电子与信息学报, 2009, 31(12): 2926-2930.
[11]	Simon Haykin. Neural networks: A comprehensive foundation[M]. 2nd ed. 北京: 清华大学出版社, 2001.
[12]	殷勤业. 高分辨率波达方向估计[D]. 西安: 西安交通大学, 1989.

Options

文章导航