基于多重分形谱智能分析的卫星信号调制识别研究
Modulation Recognition of Satellite Communication Signal Based on Intelligent Analysis of Multi-Fractal Spectrum
查看参考文献22篇
|
文摘
|
调制方式识别是电磁频谱战中的关键技术之一,已有星上识别方法智能化程度低、适应性差.针对此类问题,提出了一种基于多重分形谱和深度学习相结合的智能识别方法.首先分析了常见卫星通信信号的多重分形特性,构建了多重分形特征域矩阵.在此基础上,将该特征矩阵与深度学习残差网络相结合,并根据多尺度思想对残差网络结构进行了优化改进,改进后残差网络的多层自主细节特征提取优势完美契合了多重分形谱多尺度特征刻画能力,最终实现了卫星通信信号调制方式的有效识别.仿真结果表明,该方法具有较好的识别性能,当信噪比不低于1 dB时,平均识别率大于89%. |
|
其他语种文摘
|
Modulation recognition is one of the key technologies in satellite communication anti-interference and interference analysis. The existing on-board recognition methods have low intelligence degree and poor adaptability. In order to solve these problems, an intelligent recognition method based on multi-fractal spectrum and deep learning is proposed. Firstly, the multi-fractal spectrum characteristics of common satellite communication signals are analyzed, a multi-fractal eigendomain matrix is constructed. On this basis, the eigendomain matrix is combined with the deep learning residual network, and the structure of the residual network is optimized and improved according to the multi-scale idea, and the multilayer autonomous detail feature extraction advantage of the improved residual network perfectly corresponds to the multiscale feature characterization capability of the multi-fractal spectrum. Finally, the modulation of satellite communication signal is effectively recognized. The simulation results show that this method has good recognition performance, when the SNR is not lower than 1 dB, the average recognition rate is greater than 89%. |
|
来源
|
电子学报
,2022,50(6):1336-1343 【核心库】
|
|
DOI
|
10.12263/DZXB.20210882
|
|
关键词
|
卫星通信
;
深度学习
;
调制识别
;
多重分形谱
|
|
地址
|
中国空间技术研究院西安分院, 陕西, 西安, 710100
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
0372-2112 |
|
学科
|
电子技术、通信技术 |
|
基金
|
军委科技委基础加强计划(军173)重点基础研究项目
|
|
文献收藏号
|
CSCD:7240123
|
参考文献 共
22
共2页
|
|
1.
Abdel-Moneim M A. A survey of traditional and advanced automatic modulation classification techniques, challenges, and some novel trends.
International Journal of Communication Systems,2021,34(10):e4762-e4798
|
CSCD被引
1
次
|
|
|
|
|
2.
李正权. 基于判别式受限玻尔兹曼机的数字调制识别.
通信学报,2021,42(2):81-91
|
CSCD被引
6
次
|
|
|
|
|
3.
Simic M. Automatic modulation classification of real signals in AWGN channel based on sixth-order cumulants.
Radioengineering,2021,30(1):204-214
|
CSCD被引
1
次
|
|
|
|
|
4.
Shi Q H. Automatic modulation identification based on the probability density function of signal phase.
IEEE Transactions on Communications,2012,60(4):1033-1044
|
CSCD被引
7
次
|
|
|
|
|
5.
孙姝君. 基于深度学习的调制识别综述.
电信科学,2021,37(5):82-90
|
CSCD被引
3
次
|
|
|
|
|
6.
Peng S L. Modulation classification based on signal constellation diagrams and deep learning.
IEEE Transactions on Neural Networks and Learning Systems,2019,30(3):718-727
|
CSCD被引
22
次
|
|
|
|
|
7.
陈昌美. 基于卷积神经网络的调制样式识别研究.
信息技术,2020,44(1):101-106
|
CSCD被引
3
次
|
|
|
|
|
8.
许华. 适用于样本分布差异的迁移学习调制识别算法.
华中科技大学学报(自然科学版),2021,49(4):127-132
|
CSCD被引
2
次
|
|
|
|
|
9.
Liu K. Automatic modulation recognition based on a DCN-BiLSTM network.
Sensors,2021,21(5):1577-1584
|
CSCD被引
3
次
|
|
|
|
|
10.
Al-Nuaimi D H. AMC2N: automatic modulation classification using feature clustering-based two-lane capsule networks.
Electronics,2021,10(1):76-108
|
CSCD被引
2
次
|
|
|
|
|
11.
李东瑾. 基于栈式稀疏降噪自编码网络的辐射源调制识别.
电子学报,2020,48(6):1198-1204
|
CSCD被引
6
次
|
|
|
|
|
12.
陈红. 基于多重分形特征的通信调制方式识别研究.
电子与信息学报,2016,38(4):863-869
|
CSCD被引
8
次
|
|
|
|
|
13.
Zhao C H. Modulation recognition of MFSK signals based on multifractal spectrum.
Wireless Personal Communications,2013,72(4):1903-1914
|
CSCD被引
1
次
|
|
|
|
|
14.
杨伟超.
Alpha稳定分布噪声下通信信号调制识别研究,2012
|
CSCD被引
3
次
|
|
|
|
|
15.
Zhang D M. Multi-fractal detrended fluctuation half-spectrum analysis of HRV.
The Journal of Engineering,2019,2019(22):8315-8318
|
CSCD被引
1
次
|
|
|
|
|
16.
王书豪. 基于切片双谱多重分形特征的雷达信号识别算法.
探测与控制学报,2019,41(5):66-70
|
CSCD被引
2
次
|
|
|
|
|
17.
钟明寿. 基于分形盒维数和多重分形的爆破地震波信号分析.
振动与冲击,2010,29(1):7-11,233
|
CSCD被引
32
次
|
|
|
|
|
18.
He K M. Deep residual learning for image recognition.
2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778
|
CSCD被引
447
次
|
|
|
|
|
19.
He F X. Why ResNet works? Rresiduals generalize.
IEEE Transactions on Neural Networks and Learning Systems,2020,31(12):5349-5362
|
CSCD被引
2
次
|
|
|
|
|
20.
Bi N. The handwritten Chinese character recognition uses convolutional neural networks with the GoogLeNet.
International Journal of Pattern Recognition and Artificial Intelligence,2019,33(11):1940016
|
CSCD被引
2
次
|
|
|
|
|
了解气象卫星更多信息，请访问