1 星载SAR信号数据仿真
1.1 星载SAR信号数据仿真流程
k[t-τ(t)]2}}·exp{j2πfD(t)[t-τ(t)]}·exp{jϕ[t-τ(t)]}
1.2 星载SAR信号数据仿真结果
2 CGRU-SVM网络模型设计
2.1 卷积神经网络
2.2 门控循环神经网络
2.3 CGRU-SVM网络模型搭建
3 实验验证与结果分析
3.1 CGRU-SVM模型训练
3.2 CGRU-SVM模型对比验证
表1 不同识别方法性能对比结果 |
表2 不同深度学习模型的训练对比结果 |
Command Control and Simulation >
Operating Modes of Space-borne SAR Recognition Method Based on CGRU-SVM
Received date: 2021-11-01
Revised date: 2021-11-12
Online published: 2022-06-17
An operating modes of space-borne SAR recognition method based on CGRU-SVM is proposed to solve the problem of the low recognition accuracy and bad timeliness of traditional space-borne SAR operating modes inversion methods. The method takes the impulse peak I/Q data of the SAR signal as input, extracts the good feature vector of the space-borne SAR signal for classification by using adaptive learning ability of the deep learning network, and finally realizes the "end-to-end" fast and effective identification from original SAR signal to the operating modes of space-borne SAR which reducing the influence of human factors and the complexity of the recognition process. CGRU-SVM model has better training efficiency and recognition accuracy compared with the traditional inversion method and other network models by contrast experiments, and its average recognition accuracy can reach above 91%.
Key words: SAR; operating modes; convolutional neural network; gated recurrent unit
HE Jun , ZHANG Ya-sheng , YIN Can-bin , FANG Yu-qiang . Operating Modes of Space-borne SAR Recognition Method Based on CGRU-SVM[J]. Command Control and Simulation, 2022 , 44(3) : 99 -105 . DOI: 10.3969/j.issn.1673-3819.2022.03.017
表1 不同识别方法性能对比结果 |
表2 不同深度学习模型的训练对比结果 |
| [1] |
王振力, 钟海. 国外先进星载SAR卫星的发展现状及应用[J]. 国防科技, 2016, 37(1): 19-24.
|
| [2] |
梁泽浩, 王晋, 李广雪. 星载SAR技术的发展及应用浅析[J]. 测绘与空间地理信息, 2021, 44(2): 29-32.
|
| [3] |
刘正堂, 胡振震, 孙健. 对星载SAR分布式干扰掩护区建模与仿真[J]. 指挥控制与仿真, 2019, 41(2): 88-93.
|
| [4] |
夏周越, 钟华, 陈维, 等. 侦察模式下星载合成孔径雷达工作模式鉴别[J]. 杭州电子科技大学学报(自然科学版), 2017, 37(4): 36-40.
|
| [5] |
唐小明, 立春升, 孙兵. 基于遗传算法的星载SAR工作模式反演方法[J]. 空间电子技术, 2013, 10(2): 90-94.
|
| [6] |
|
| [7] |
单连平, 窦强. 基于深度学习的海战场图像目标识别[J]. 指挥控制与仿真, 2019, 41(1): 1-5.
|
| [8] |
曲卫, 吴彦鸿, 贾鑫. 对SAR卫星天线旁瓣信号侦察研究[J]. 装备指挥技术学院学报, 2004(2): 103-107.
|
| [9] |
熊小莉. 星载侦察接收技术[J]. 电讯技术, 2010, 50(8): 18-21.
|
| [10] |
陈杰, 杨威, 王鹏波, 等. 多方位角观测星载SAR技术研究[J]. 雷达学报, 2020, 9(2): 205-220.
|
| [11] |
|
| [12] |
|
| [13] |
张盛涛, 方纪村. 基于深度学习算法的道路旅行时间预测[J]. 指挥控制与仿真, 2019, 41(2): 53-56.
|
| [14] |
|
| [15] |
朱元富, 贺文武, 李建兴, 等. 基于Bi-LSTM/Bi-GRU循环神经网络的锂电池SOC估计[J]. 储能科学与技术, 2021, 10(3): 1163-1176.
|
| [16] |
李洋, 王官云, 王彦平, 等. 多角度极化SAR图像散射特征分解及SVM分类[J]. 电波科学学报, 2019, 34(6): 771-777.
|
| [17] |
|
| [18] |
|
| [19] |
|
/
| 〈 |
|
〉 |