基于熵评价模态分解的雷达信号双谱特征识别

doi:10.12305/j.issn.1001-506X.2021.08.12

摘要/Abstract

摘要：

针对在低信噪比下雷达信号调制识别准确率低、抗噪性差的问题, 提出一种基于熵评价模态分解和双谱特征提取的识别方法。利用双谱可以抑制高斯噪声的特点, 分析了在低信噪比下进行信号调制识别的可行性并引入了噪声项。由于噪声项的干扰, 双谱在0 dB以下时, 噪声抑制效果变差, 提出了基于信息熵评价的经验模态化分解对信号进行预处理, 提高信噪比。最后, 设计了卷积神经网络分类器, 实现对不同调制类型信号的识别。仿真实验结果表明, 本文方法相比传统方法具有良好的抗噪性, 能够在低信噪比下对不同类型信号进行有效识别。

关键词: 双谱, 信息熵, 卷积神经网络, 经验模态化分解

Abstract:

In order to solve the problems of low accuracy and poor anti-noise of radar signal modulation recognition under low signal to noise ratio (SNR), a recognition method based on entropy evaluation modal decomposition and bispectrum feature extraction is proposed. Based on the characteristics of bispectrum which can suppress Gaussian noise, the feasibility of signal modulation recognition in low SNR is analyzed and the noise term is introduced. Due to the interference of noise term, the noise suppression effect of bispectrum below 0 dB becomes worse. An empirical modal decomposition based on information entropy evaluation is proposed to preprocess the signal and improve the SNR. Finally, a convolutional neural network classifier is designed to recognize different modulation signals. Simulation experiment results show that this method has better anti-noise performance than the traditional method, and can effectively identify different types of signals in low SNR.

Key words: bispectrum, information entropy, convolutional neural network, empirical modal decomposition

中图分类号:

TN971

米新平, 陈西宏, 刘赞, 刘永进, 刘强. 基于熵评价模态分解的雷达信号双谱特征识别[J]. 系统工程与电子技术, 2021, 43(8): 2116-2123.

Xinping MI, Xihong CHEN, Zan LIU, Yongjin LIU, Qiang LIU. Bispectrum feature recognition of radar signal based on entropy evaluation and modal decomposition[J]. Systems Engineering and Electronics, 2021, 43(8): 2116-2123.

图/表 12

图1

图2

图3

表1

图4

表2

表3

图5

图6

图7

表4

图8

参考文献 22

1	胡国兵. 雷达信号调制识别相关技术研究[D]. 南京: 南京航空航天大学, 2011.
	HU G P. Research on modulation recognition technology of radar signal[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2011.
2	张永顺, 童宁宁, 赵国庆. 雷达电子战原理[M]. 北京: 国防工业出版社, 2006.
	ZHANG Y S , TONG N N , ZHAO G Q . Principle of radar electronic warfare[M]. Beijing: National Defense Industry Press, 2006.
3	WEI Y J , FANG S L , WANG X Y . Automatic modulation classification of digital communication signals using SVM based on hybrid features, cyclostationary, and information entropy[J]. Entropy, 2019, 21 (8): 745- 753. doi: 10.3390/e21080745
4	ZHU D M , MATHEWS V J , DETIENNE D H . A likelihood-based algorithm for blind Identification of QAM and PSK signals[J]. IEEE Trans.on Wirel Commun, 2018, 17 (5): 3417- 3430. doi: 10.1109/TWC.2018.2811802
5	XU J L , SU W , ZHOU M C . Likelihood-ratio approaches to automatic modulation classification[J]. IEEE Trans.on System Man Cybernetics Part C-Applications Reviews, 2011, 41 (4): 455- 469. doi: 10.1109/TSMCC.2010.2076347
6	SHI Q H , KARASAWA Y . Automatic modulation identification based on the probability density function of signal Phase[J]. IEEE Trans.on Communications, 2012, 60 (4): 1033- 1044. doi: 10.1109/TCOMM.2012.021712.100638
7	郭立民, 陈鑫, 陈涛. 基于AlexNet模型的雷达信号调制类型识别[J]. 吉林大学学报(工学版), 2019, 49 (3): 1000- 1008.
	GUO L M , CHEN X , CHEN T . Radar signal modulation type recognition based on alexnet model[J]. Journal of Jilin University (Engineering Edition), 2019, 49 (3): 1000- 1008.
8	WANG H , GUO L L , DOU Z , et al. A new method of cognitive signal recognition based on hybrid information entropy and D-S evidence theory[J]. Mobile Networks & Applications, 2018, 23 (4): 677- 685.
9	DALDAL N , COMERT Z , POLAT K . Automatic determination of digital modulation types with different noises using convolutional neural network based on time-frequency information[J]. Applied Soft Computing, 2020, 86 (10): 456- 463.
10	ZHANG Y , LIU B , JI X M , et al. Classification of EEG signals based on autoregressive model and wavelet packe t decomposition[J]. Neural Processing Letters, 2017, 45 (2): 365- 378. doi: 10.1007/s11063-016-9530-1
11	陈昌孝, 何明浩, 朱元清, 等. 基于双谱分析的雷达辐射源个体特征提取[J]. 系统工程与电子技术, 2008, 30 (6): 1046- 104. doi: 10.3321/j.issn:1001-506X.2008.06.011
	CHEN C X , HE M H , ZHU Y Q , et al. Feature extraction of radar emitter based on bispectrum analysis[J]. Systems Engineering and Electronics, 2008, 30 (6): 1046- 1049. doi: 10.3321/j.issn:1001-506X.2008.06.011
12	CIUONZO D , ROSSI P S . Noncolocated time-reversal MUSIC: high-SNR distribution of null spectrum[J]. IEEE Signal Processing Letters, 2017, 24 (4): 397- 401. doi: 10.1109/LSP.2017.2661246
13	ALI A K , ERCELEBI E . Automatic modulation recognition of DVB-S2X standard-specific with an APSK-based neural network classifier[J]. Measurement, 2020, 151 (10): 72- 79.
14	蒋鹏. 雷达信号细微特征分析与识别[D]. 哈尔滨: 哈尔滨工程大学, 2012.
	JIANG P. Analysis and recognition of radar signal subtle features[D]. Harbin: Harbin Engineering University, 2012.
15	王世强, 张登福, 毕笃彦, 等. 双谱二次特征在雷达信号识别中的应用[J]. 西安电子科技大学学报, 2012, 39 (2): 127- 132. doi: 10.3969/j.issn.1001-2400.2012.02.021
	WANG S Q , ZHANG D F , BI D Y , et al. Application of bispectrum quadratic feature in radar signal recognition[J]. Journal of Xidian University, 2012, 39 (2): 127- 132. doi: 10.3969/j.issn.1001-2400.2012.02.021
16	LI J F , WANG J , ZHANG X L , et al. Empirical mode decomposition based on instantaneous frequency boundary[J]. Electronics Letters, 2017, 53 (12): 781- 782. doi: 10.1049/el.2016.3866
17	XU Y , LUO M Z , LI T , et al. ECG signal de-noising and baseline wander correction based on CEEMDAN and wavelet threshold[J]. Sensors, 2017, 17 (12): 16- 25.
18	LIM M H , YUEN P C . Entropy measurement for biometric verification systems[J]. IEEE Trans.on Cybernetics, 2016, 46 (5): 1065- 1077. doi: 10.1109/TCYB.2015.2423271
19	LIU Z G , CUI Y , LI W H . A classification method for complex power quality disturbances using EEMD and rank wavelet SVM[J]. IEEE Trans.on Smart Grid, 2015, 6 (4): 1678- 1685. doi: 10.1109/TSG.2015.2397431
20	叶文强, 俞志富, 王虎帮, 等. 基于卷积神经网络辐射源信号识别算法[J]. 计算机仿真, 2019, 36 (9): 33- 37. doi: 10.3969/j.issn.1006-9348.2019.09.009
	YE W Q , YU Z F , WANG H B , et al. Emitter signal recognition algorithm based on convolutional neural network[J]. Computer Simulation, 2019, 36 (9): 33- 37. doi: 10.3969/j.issn.1006-9348.2019.09.009
21	刘赢, 田润澜, 王晓峰. 基于深层卷积神经网络和双谱特征的雷达信号识别方法[J]. 系统工程与电子技术, 2019, 41 (9): 1998- 2005.
	LIU Y , TIAN R L , WANG X F . Radar signal recognition method based on deep convolution neural network and bispectrum feature[J]. Systems Engineering and Electronics, 2019, 41 (9): 1998- 2005.
22	吴灏, 周亮, 李亚星, 等. 基于卷积神经网络和稀疏滤波的调制识别方法[J]. 系统工程与电子技术, 2019, 41 (9): 2114- 2121.
	WU H , ZHOU L , LI Y X , et al. Modulation recognition method based on convolutional neural network and sparse filter[J]. Systems engineering and electronics, 2019, 41 (9): 2114- 2121.

层数	输入尺寸	卷积核	尺寸	步长
卷积层1	227×227×3	96	11/3	4/2
池化层1	27×27×256	256	5/3	1/2
卷积层2	13×13×384	384	3/0	1/1
池化层2	13×13×384	384	3/0	1/1
卷积层3	13×13×384	256	3/3	1/2

类型	SNR/dB
类型	5	0	-5	-10
LFM	16.7	9.3	4.9	2.9
CW	15.2	7.2	4.2	2.5
QPSK	21.6	16.8	9.2	5.3
BPSK	25.6	18.2	10.2	8.1
FSK	18.6	11.0	6.3	4.9
NLFM	16.7	7.4	4.5	3.1

类型	T/s
类型	5	0	-5	-10
LFM	4.8	15.9	54.8	183.8
CW	3.2	13.4	48.2	178.5
QPSK	15.4	28.6	65.2	205.1
BPSK	18.4	32.5	76.2	220.4
FSK	11.8	21.4	56.4	186.3
NLFM	4.1	15.8	61.1	193.9

类型	信号长度
类型	256	512	1 024	2 048
LFM	0.78	0.89	0.91	0.91
CW	0.79	0.90	0.90	0.91
QPSK	0.84	0.91	0.97	0.97
BPSK	0.82	0.93	0.94	0.94
FSK	0.79	0.89	0.93	0.94
NLFM	0.85	0.91	0.94	0.94

[1]	宋爽, 张悦, 张琳娜, 岑翼刚, 李浥东. 基于深度学习的轻量化目标检测算法[J]. 系统工程与电子技术, 2022, 44(9): 2716-2725.
[2]	王彩云, 吴钇达, 王佳宁, 马璐, 赵焕玥. 基于改进的CNN和数据增强的SAR目标识别[J]. 系统工程与电子技术, 2022, 44(8): 2483-2487.
[3]	韦娟, 杨皇卫, 宁方立. 基于NMF与CNN联合优化的声学场景分类[J]. 系统工程与电子技术, 2022, 44(5): 1433-1438.
[4]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[5]	卢盈齐, 范成礼, 付强, 朱晓雯, 李威. 基于改进IFRS相似度和信息熵的反导作战目标威胁评估[J]. 系统工程与电子技术, 2022, 44(4): 1230-1238.
[6]	方伟, 王玉, 闫文君, 林冲. 基于神经网络的符号化飞行动作识别[J]. 系统工程与电子技术, 2022, 44(3): 737-745.
[7]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[8]	刘恒燕, 张立民, 闫文君, 钟兆根, 凌青, 梁晓军. 基于WBP-CNN算法的LDPC译码[J]. 系统工程与电子技术, 2022, 44(3): 1030-1035.
[9]	邵凯, 朱苗苗, 王光宇. 基于生成对抗与卷积神经网络的调制识别方法[J]. 系统工程与电子技术, 2022, 44(3): 1036-1043.
[10]	张玺, 金正猛, 姜亚琴. 融合深度图像先验的全变差图像着色算法[J]. 系统工程与电子技术, 2022, 44(2): 385-393.
[11]	金涛, 王晓峰, 田润澜, 张歆东. 基于改进1DCNN+TCN的雷达辐射源快速识别方法[J]. 系统工程与电子技术, 2022, 44(2): 463-469.
[12]	吕勤哲, 全英汇, 沙明辉, 董淑仙, 邢孟道. 基于集成深度学习的有源干扰智能分类[J]. 系统工程与电子技术, 2022, 44(12): 3595-3602.
[13]	高涌荇, 王旭东, 汪玲, 朱岱寅, 郭军, 孟凡旺. 基于RCNN的双极化气象雷达天气信号检测[J]. 系统工程与电子技术, 2022, 44(11): 3380-3387.
[14]	李永刚, 朱卫纲, 黄琼男, 李云涛, 何永华. 复杂背景下SAR图像近岸舰船目标检测[J]. 系统工程与电子技术, 2022, 44(10): 3096-3103.
[15]	但波, 付哲泉, 高山, 简涛. 基于卷积神经网络的海面目标全极化高分辨距离像识别技术[J]. 系统工程与电子技术, 2022, 44(1): 108-116.