基于神经网络的高频地波雷达目标到达角估计

严颂华; 吴世才; 吴雄斌

doi:10.3724/SP.J.1146.2006.01096

基于神经网络的高频地波雷达目标到达角估计

doi: 10.3724/SP.J.1146.2006.01096

基金项目:

国家自然科学基金(60571065)和国家863计划(20001AA631050)持续资助课题

计量
- 文章访问数: 3530
- HTML全文浏览量: 106
- PDF下载量: 1613
- 被引次数: 0
出版历程
- 收稿日期: 2006-07-28
- 修回日期: 2007-03-23
- 刊出日期: 2008-02-19

DOA Estimation Based on Neural Network for HFGWR

摘要

摘要: 该文利用神经网络进行高频地波雷达目标到达角估计。论文分别采用RBFN和GRNN构造了基于函数逼近和模式编码的到达角估计网络，介绍了网络结构、数据仿真的过程和应用于高频地波雷达目标定向的实际效果。数据仿真和现场实验的分析结果表明基于模式编码的GRNN网络到达角估计方法鲁棒性较好，在低信噪比时能够给出正确估计。
- 神经网络; 到达角估计; 模式分类; 高频地波雷达
Abstract: Direction of Arrival (DOA) technology based on neural network is discussed. In the paper, the DOA method based on function approach and model classification with coding is presented and it employs two kinds of neural networks: Radial Basis Function Network(RBFN) and General Regression Neural Net (GRNN). The paper introduces the network structure, simulation and the application to High Frequency Ground Wave Radar(HFGWR). The simulation and real data processing verifies that the model classification method based on GRNN offers better performance than others, its performance is good even the signal-to-noise of the signal is low until 4 dB.

HTML全文

参考文献(1)

Barrick D, Teague C, Lilleboe P, Cheng R, and Gartner J.Profiling river surface velocities and volume flow estimationwith bistatic UHF RiverSonde radar. Proceedings of theIEEE/OES Seventh Working Conference on CurrentMeasurement Technology, SanDiego, United States, 2003:55-59.[2]Xie Junhao, Yuan Yeshu, and Liu Yongtan. Super-resolutionprocessing for HF surface wave radar based on pre-whitenedMUSIC[J].IEEE Journal of Oceanic Engineering.1998, 23(4):313-321[3]Schmidt R O. Multiple emitter location and signal parameterestimation[J].IEEE Trans. on Antennas Propagation.1986,34(3):276-280[4]黄佑勇, 王激扬, 陈天麒. 一种基于高阶累积量的信号频率和到达角联合估计算法[J].电子与信息学报.2001, 23(2):140-146浏览[5]王兰美, 廖桂生, 王洪洋. 矢量传感器误差校正与补偿[J].电子与信息学报.2006, 28(1):92-95浏览[6]王哲, 李衍达, 罗发龙. 一种用于PCA与MCA的神经网络学习算法. 电子学报, 1996, 24(4): 12-16.Wang Zhe, Li Yan-da, and Luo Fa-long. A neural networklearning algorithm for PCA and MCA. Acta ELectronicaSinica, 1996，24(4): 12-16.[7]罗发龙, 李衍达. 神经网络信号处理.北京: 电子工业出版社,1993: 88-93.[8]Southall L, Simmers A, and ODonnell H. Directionfinding in phased arrays with a neural network beamformer[J].IEEE Trans. on Antennas Propagation.1995,43(12):1369-1374[9]Zooghby A H El, Christodoulou C G, and Georgiopoulos M.A neural network-based smart antenna for multiple sourcetracking[J].IEEE. Trans. on Antennas Propagation.2000, 48(5):768-775[10]阎平凡，张长水. 人工神经网络与模拟进化计算.北京: 清华大学出版社, 2000: 15-17.[11]胡守仁. 神经网络应用技术. 长沙: 国防科技大学出版社,1993: 77-78.[12]Moody J and Darken C. Fast learning in networks of locallytuned processing units[J].Neural Computation.1989, 1(1):281-294[13]Stoica P and Nehorai A. MUSIC, maximum likelihood, andCramer-Rao bound[J].IEEE Trans. on Acoust. Speech andSignal Processing.1989, 37(5):720-741

施引文献

资源附件(0)

访问统计