基于VMD和特征融合的辐射源信号识别

doi:10.3969/j.issn.1001-506X.2020.07.10

摘要/Abstract

摘要：

在日趋复杂的电子对抗中,如何提高雷达辐射源信号(radar emitter signal, RES)识别率和抗噪性能是亟待解决的问题。为此提出了一种变分模态分解(variational mode decomposition, VMD)和特征融合相结合的RES识别方法。首先利用VMD算法对各雷达信号进行分解得到3个本征模态函数(intrinsic mode function, IMF);然后,对这3个IMF分量提取排列熵(permutation entropy, PE)和样本熵(sample entropy, SE)特征进行特征融合，构成六维特征向量；最后利用支持向量机对辐射源信号进行识别。利用6种不同的辐射源信号对该方法进行了验证,仿真实验结果表明,该方法在低信噪比(signal to noise ratio, SNR)下能取得较好的识别率,当SNR不低于0 dB时,六维特征向量的识别率达到100%,具有较强的抗噪性能。

关键词: 雷达辐射源信号识别, 变分模态分解, 特征融合, 支持向量机

Abstract:

In the increasingly complex electronic warfare, how to improve the radar emitter signal (RES) recognition rate and anti-noise performance is an urgent problem to be solved. For this reason, a RES recognition method based on a combination of variational mode decomposition (VMD) and feature fusion is proposed. Firstly, the VMD algorithm is used to decompose the radar signals to obtain three intrinsic mode functions (IMF). Then the permutation entropy (PE)and sample entropy(SE) features of the three IMF components are extracted to form a 6-dimensional feature vector. The support vector machine is used to identify the radar emitter signals. The method is validated by six different radar emitter signals. The simulation results show that the proposed method can achieve the better recognition rate under low signal to noise ratio (SNR). When the SNR is not lower than 0 dB, the recognition rate of the 6-dimensional feature vector reaches 100%, and it has strong anti-noise performance.

Key words: radar emitter signal (RES) recognition, variational mode decomposition (VMD), feature fusion, support vector machine (SVM)

中图分类号:

TN973

李亚兰, 金炜东, 葛鹏. 基于VMD和特征融合的辐射源信号识别[J]. 系统工程与电子技术, 2020, 42(7): 1499-1503.

Yalan LI, Weidong JIN, Peng GE. Radiation emitter signal recognition based on VMD and feature fusion[J]. Systems Engineering and Electronics, 2020, 42(7): 1499-1503.

图/表 7

表1

图1

表2

表3

图2

表4

图3

参考文献 30

1	何明浩, 韩俊. 现代雷达辐射源信号分选与识别[M]. 北京: 科学出版社, 2016.
	HE M H , HAN J . Signal sorting and identification of modern radar emitters[M]. Beijing: Science Press, 2016.
2	KAWALEC A, OWCZAREK R. Specific emitter identification using intrapulse data[C]//Proc.of the European Radar Conference, 2005: 249-252.
3	ZHANG G, RONG H, JIN W, et al. Radar emitter signal recognition based on resemblance coefficient features[C]//Proc.of the International Conference Rough Sets &Current Trends in Computing, 2004: 665-670.
4	ZHANG G X , JIN W D , HU L Z . Radar emitter signal recognition based on complexity features[J]. Journal of Southwest Jiaotong University, 2004, 12 (2): 116- 122.
5	ZHANG G X , RONG H N , JIN W D . Application of support vector machine to radaremitter signal recognition[J]. Journal of Southwest Jiaotong University, 2006, 41 (1): 25- 30.
6	ZHANG X L, YOU W T, GUO Q, et al. Recognition method studies for radar and communication signals based on spectral correlation[C]//Proc.of the International Symposium on Systems & Control in Aeronautics & Astronautics, 2010: 363-366.
7	韩俊, 何明浩, 朱振波, 等. 基于复杂度特征的未知雷达辐射源信号分选[J]. 电子与信息学报, 2009, 31 (11): 2552- 2556.
	HAN J , HE M H , ZHU Z B , et al. Sorting unknown radar emitter signal based on complexity characteristics[J]. Journal of Electronics and Information, 2009, 31 (11): 2552- 2556.
8	LI J, YING Y. Radar signal recognition algorithm based on entropy theory[C]//Proc.of the International Conference on Systems & Informatics, 2015: 718-723.
9	KANG N X, HE M H, HAN J, et al. Radar emitter fingerprint recognition based on bispectrum and SURF feature[C]//Proc.of the CIE International Conference on Radar (RADAR), 2016.
10	CHEN T W , JIN W D , LI J . Individual feature extraction from radar emitter signals based on surrounding-line integral bispectrum[J]. Computer Engineering and Applications, 2013, 49 (8): 209- 212.
11	LIU L, MCLERNON D, GHOGHO M, et al. Micro-Doppler extraction from ballistic missile radar returns using time-frequency analysis[C]//Proc.of the International Symposium on Wireless Communication Systems, 2010: 780-784.
12	HAN J, HE M H, ZHU Y Q, et al. A novel method for sorting radar radiating-source signal based on ambiguity function[M]. IEEE Computer Society, 2009: 820-823.
13	JIN W , ZHANG G , HU L . Radar emitter signal recognition using wavelet packet transform and support vector machines[J]. Journal of Modern Transportation, 2006, 14 (1): 15- 22.
14	WANG X, HUANG G, ZHOU Z, et al. Radar emitter recognition based on the short timefourier transform and convolutional neural networks[C]//Proc.of the International Congress on Image & Signal Processing, 2018.
15	LI L, JI H, WANG L. Specific radar emitter recognition based on wavelet packet transform and probabilistic SVM[C]//Proc.of the International Conference on Information & Automation, 2009: 1308-1313.
16	LI Y B , GE J , LIN Y , et al. Radar emitter signal recognition based on multi-scale wavelet entropy and feature weighting[J]. Journal of Central South University, 2014, 21 (11): 4254- 4260. doi: 10.1007/s11771-014-2422-5
17	CHEN T W, JIN W D, CHEN Z X. Feature extraction using wavelet transform for radar emitter signals[C]//Proc.of the WRI International Conference on Communications and Mobile Computing, 2009.
18	戚晓利, 叶绪丹, 蔡江林, 等. 基于变分模态分解与流形学习的滚动轴承故障特征提取方法[J]. 振动与冲击, 2018, 37 (23): 133- 140.
	QI X L , YE X D , CAI J L , et al. Fault feature extraction method of rolling bearing based on VMD and manifold learning[J]. Journal of Vibration and Shock, 2018, 37 (23): 133- 140.
19	李华, 伍星, 刘韬, 等. 基于信息熵优化变分模态分解的滚动轴承故障特征提取[J]. 振动与冲击, 2018, 37 (23): 219- 225.
	LI H , WU X , LIU T , et al. Bearing fault feature extraction based on VMD with information entropy[J]. Journal of Vibration and Shock, 2018, 37 (23): 219- 225.
20	任学平, 李攀, 王朝阁, 等. 基于改进VMD与包络导数能量算子的滚动轴承早期故障诊断[J]. 振动与冲击, 2018, 37 (15): 6- 13.
	REN X P , LI P , WANG C G , et al. Early fault diagnosis of rolling bearing based on improved VMD and envelope derivative energy operator[J]. Journal of Vibration and Shock, 2018, 37 (15): 6- 13.
21	DRAGOMIRETSKIY K , ZOSSO D . Variational mode decomposition[J]. IEEE Trans.on Signal Processing, 2017, 62 (3): 531- 544.
22	郑近德, 程军圣, 杨宇. 多尺度排列熵及其在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2013, (19): 2641- 2646. doi: 10.3969/j.issn.1004-132X.2013.19.017
	ZHEN J D , CHENG J S , YANG Y . Multi-scale permutation entropy and its application in fault diagnosis of rolling bearings[J]. China Mechanical Engineering, 2013, (19): 2641- 2646. doi: 10.3969/j.issn.1004-132X.2013.19.017
23	OLOFSEN E , SLEIGH J W , DAHAN A . Permutation entropy of the electroencephalogram: ameasure of anaesthetic drug effect[J]. British Journal of Anaesthesia, 2008, 101 (6): 810- 821. doi: 10.1093/bja/aen290
24	BANDT C , POMPE B . Permutation entropy: a natural complexity measure for time series[J]. Physical Review Letters, 2002, 88 (17): 174102. doi: 10.1103/PhysRevLett.88.174102
25	YAN R , GAO R X . Approximate entropy as a diagnostic tool for machine health mon itoring[J]. Mechanical Systems & Signal Processing, 2007, 21 (2): 824- 839.
26	ALCARAZ R , RIETA J J . A review on sample entropy applications for the non-invasive analysis of atrial fibrillation electrocardiograms[J]. Biomedical Signal Processing and Control, 2010, 5 (1): 1- 14. doi: 10.1016/j.bspc.2009.11.001
27	PINCUS S M . Approximate entropy as a measure of system complexity[J]. Proceedings of the National Academy of Sciences, 1991, 88 (6): 2297- 2301. doi: 10.1073/pnas.88.6.2297
28	张葛祥, 胡来招, 金炜东. 基于熵特征的雷达辐射源信号识别[J]. 电波科学学报, 2005, (4): 30- 35.
	ZHANG G X , HU L Z , JIN W D . Rader emitter signal recognition based on entropy features[J]. Chinese Journal of Radio Science, 2005, (4): 30- 35.
29	张葛祥.雷达辐射源信号智能识别方法研究[D].成都:西南交通大学, 2005.
	ZHANG G X. Research on intelligent recognition method of radar emitter signal[D]. Chengdu: Southwest Jiaotong University, 2005.
30	VAPNIK V. The nature of statistical learning theory[M]. Springer, 1995: 1-188.

SNR/dB	识别率/%
SNR/dB	m=3	m=4	m=5	m=6
-6	69.58	62.92	52.50	50.00
-4	84.17	80.83	67.50	66.67
-2	89.17	81.67	71.25	70.42
0	100	89.58	80.83	78.75
2	100	91.25	86.67	83.33
4	100	96.25	89.17	85.42
6	100	98.75	92.50	87.92

SNR/dB	识别率/%
SNR/dB	r=0.1std	r=0.15std	r=0.2std	r=0.25std
-6	56.67	60.00	60.42	61.25
-4	74.58	77.50	77.92	80.00
-2	76.25	79.16	80.00	81.67
0	91.67	94.58	93.75	95.83
2	92.08	95.00	94.17	97.50
4	92.50	95.42	95.42	97.92
6	91.25	97.08	96.67	99.17

SNR/ dB	识别率/%
SNR/ dB	CW	LFM	BPSK	P1	Costas	SNLFM	总体
-6	100	82.5	87.5	72.5	92.5	97.5	88.75
-4	100	100.0	100.0	95.0	95.0	100.0	98.33
-2	100	95.0	100.0	100.0	97.5	100.0	98.75
0	100	100.0	100.0	100.0	100.0	100.0	100.00
2	100	100.0	100.0	100.0	100.0	100.0	100.00
4	100	100.0	100.0	100.0	100.0	100.0	100.00
6	100	100.0	100.0	100.0	100.0	100.0	100.00

[1]	赵晓枫, 吴飞, 徐叶斌, 牛家辉, 蔡伟, 张志利. 基于背景还原的红外伪装效果评价方法[J]. 系统工程与电子技术, 2022, 44(8): 2554-2561.
[2]	薛春岭, 曹菲, 孙庆, 秦建强, 冯晓伟. 基于多特征信息融合的海面微弱目标检测[J]. 系统工程与电子技术, 2022, 44(11): 3338-3345.
[3]	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.
[4]	朱峰, 蒋倩倩, 林川, 杨啸. 基于支持向量机的典型宽带电磁干扰源识别[J]. 系统工程与电子技术, 2021, 43(9): 2400-2406.
[5]	崔邦彦, 田润澜, 王东风, 崔钢, 石静苑. 基于注意力机制和改进CLDNN的雷达辐射源识别[J]. 系统工程与电子技术, 2021, 43(5): 1224-1231.
[6]	李昂, 聂党民, 温祥西, 王泽坤, 杨诚修. 基于相依网络和SVM的管制系统运行态势评估[J]. 系统工程与电子技术, 2021, 43(5): 1287-1294.
[7]	王坤, 侯树贤, 王力. 基于自适应变异PSO-SVM的APU性能参数预测模型[J]. 系统工程与电子技术, 2021, 43(2): 526-536.
[8]	彭正红, 杨德贵, 王行, 王浩, 朱政亮. 基于趋势估计的微多普勒分离与特征提取算法[J]. 系统工程与电子技术, 2021, 43(12): 3452-3461.
[9]	李晨瑄, 钱坤, 胥辉旗. 基于深浅层特征融合的舰船要害关键点检测算法[J]. 系统工程与电子技术, 2021, 43(11): 3239-3249.
[10]	马愈昭, 王强强, 王瑞松, 熊兴隆. 基于SVD和MPSO-SVM的光纤周界[J]. 系统工程与电子技术, 2020, 42(8): 1652-1661.
[11]	李红光, 郭英, 眭萍, 齐子森, 苏令华. 基于高维特征选择的跳频电台细微特征识别[J]. 系统工程与电子技术, 2020, 42(2): 445-451.
[12]	方章闻, 张金艺, 李科, 姜玉稀. 小样本条件下的通信辐射源半监督特征提取[J]. 系统工程与电子技术, 2020, 42(10): 2381-2389.
[13]	王强, 贾希胜, 程中华, 王双川, 马云飞. 基于改进的局部保持投影的战时备件分类[J]. 系统工程与电子技术, 2020, 42(1): 133-140.
[14]	吴青, 臧博研, 祁宗仙, 张昱. 基于压缩感知的多核稀疏最小二乘支持向量机[J]. 系统工程与电子技术, 2019, 41(9): 1930-1936.
[15]	王彩云, 黄盼盼, 李晓飞, 王佳宁, 赵焕玥. 基于AEPSO-SVM算法的雷达HRRP目标识别[J]. 系统工程与电子技术, 2019, 41(9): 1984-1989.