| 基于深度神经网络模型的雷达目标识别 |
| |
| 引用本文： | 詹武平,郑永煌,王金霞.基于深度神经网络模型的雷达目标识别[J].现代雷达,2018,40(1):16-19. |
| |
| 作者姓名： | 詹武平 郑永煌 王金霞 |
| |
| 作者单位： | 解放军63620 部队,兰州732750,解放军63620 部队,兰州732750,解放军63620 部队,兰州732750 |
| |
| 摘 要： | 根据雷达测量的目标电磁散射面积(RCS)序列,采用深度神经网络模型识别空间飞行目标。首先,阐述了提取RCS时间序列特征的方法,包括均值、均方差及周期特性等特征;然后,给出了深度神经网络模型识别RCS目标的算法;最后,用仿真数据验证该识别方法,数值实验结果表明该方法能较准确识别雷达跟踪目标。
|
| 关 键 词： | 雷达 RCS特征 深度神经网络 目标识别 |
Radar Target Recogintion Based on Deep Neural Network |
| |
| ZHAN Wuping,ZHENG Yonghuang and WANG Jinxia.Radar Target Recogintion Based on Deep Neural Network[J].Modern Radar,2018,40(1):16-19. |
| |
| Authors: | ZHAN Wuping ZHENG Yonghuang and WANG Jinxia |
| |
| Institution: | The Unit 63620 of PLA,Lanzhou 732750, China,The Unit 63620 of PLA,Lanzhou 732750, China and The Unit 63620 of PLA,Lanzhou 732750, China |
| |
| Abstract: | The deep neural network for space flying target recognition is provided using radar cross section( RCS) . Firstly, the method of extracting RCS time series characteristics is described, including the average, mean variance and periodicity characteristics. Then, a deep neural network model is presented to identify RCS targets. Finally, the identification method is verified by simulation data, and the numerical results show that the method can accurately identify radar tracking targets. |
| |
| Keywords: | radar RCS character deep neural network target recognition |
|
| 点击此处可从《现代雷达》浏览原始摘要信息 |
| 点击此处可从《现代雷达》下载免费的PDF全文 |
|
