基于通信域和雷达域融合特征的无人机集群类型识别算法

doi:10.12305/j.issn.1001-506X.2023.12.03

摘要/Abstract

摘要：

目前已有无人机类型识别算法仅通过通信域或雷达域的信号特征实现单个无人机类型的识别, 存在识别准确率低等问题。提出了一种基于通信信号和雷达信号融合特征的无人机集群类型识别算法。首先, 提取集群通信信号的高阶累积量和瞬时特征统计量, 并融合雷达航迹特征构建无人机集群特征矩阵。其次, 提出一种改进的特征选择算法—二次筛选的近邻成分分析, 对融合特征矩阵进行降维。最后, 利用稀疏自编码器网络进行集群类型的识别。仿真结果表明, 该算法显著降低了集群特征矩阵的维度(仅为原始矩阵维度的27%)，同时在信噪比为0 dB时, 对5种集群类型识别的正确率可达88%。

关键词: 无人机集群类型识别, 特征选择, 高阶累积量, 瞬时特征统计量, 雷达航迹

Abstract:

At present, the unmanned aerial vehicle (UAV) type recognition algorithms only realize the identification of a single UAV type through the signal characteristics of the communication domain or radar domain, and there are problems such as low recognition accuracy. This paper proposes a UAV swarm type recognition algorithm based on the fusion characteristics of communication signals and radar signals. Firstly, the high-order cumulant and instantaneous feature statistics of the swarm communication signal are extracted, and the radar track features are fused to construct the UAV swarm feature matrix. Secondly, an improved feature selection algorithm-secondary screening of neighbourhood components analysis (SSNCA) is proposed to reduce the dimensionality of the fusion feature matrix. Finally, a sparse autoencoder network is used for swarm type identification. The simulation results show that the algorithm significantly reduces the dimension of the swarm feature matrix (only 27% of the original matrix dimension). At the same time, when the signal-to-noise ratio is 0 dB, the correct rate of identifying five swarm types can reach 88%.

Key words: unmanned aerial vehicle (UAV) swarm type identification, feature selection, high-order cumulant, instantaneous feature statistics, radar trajectory

中图分类号:

TN911

张书衡, 翟茹萍, 刘永凯. 基于通信域和雷达域融合特征的无人机集群类型识别算法[J]. 系统工程与电子技术, 2023, 45(12): 3734-3742.

Shuheng ZHANG, Ruping ZHAI, Yongkai LIU. Identification of UAV swarm type based on fusion features of communication and radar domain[J]. Systems Engineering and Electronics, 2023, 45(12): 3734-3742.

图/表 13

图1

图2

图3

表1

图4

图5

表2

表3

表4

图6

图7

图8

图9

参考文献 21

1	董超, 陶婷, 冯斯梦, 等. 面向无人机自组网和车联网的媒体接入控制协议研究综述[J]. 电子与信息学报, 2022, 44 (3): 790- 802.
	DONG C , TAO T , FENG S M , et al. Overview on medium access control protocol in flying ad-hoc networks and vehicular ad-hoc networks[J]. Journal of Electronics and Information Technology, 2022, 44 (3): 790- 802.
2	CHOU S F , PANG A C , YU Y J . Energy-aware 3D unmanned aerial vehicle deployment for network throughput optimization[J]. IEEE Trans.on Wireless Communications, 2019, 19 (1): 563- 578.
3	贾永楠, 田似营, 李擎. 无人机集群研究进展综述[J]. 航空学报, 2020, 41 (S1): 4- 14.
	JIA Y N , TIAN S Y , LI Q . Recent development of unmanned aerial vehicle swarms[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41 (S1): 4- 14.
4	刘雷, 刘大为, 王晓光, 等. 无人机集群与反无人机集群发展现状分析[J]. 航空学报, 2022, 43 (S1): 526908.
	LIU L , LIU D W , WANG X G , et al. Analysis of the development status of unmanned clusters and anti-unmanned clusters[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43 (S1): 526908.
5	NOH D I , JEONG S G , HOANG H T , et al. Signal preprocessing technique with noise-tolerant for RF-based UAV signal classification[J]. IEEE Access, 2022, 10, 134785- 134798. doi: 10.1109/ACCESS.2022.3232036
6	NIE W , HAN Z C , ZHOU M , et al. UAV detection and identification based on WiFi signal and RF fingerprint[J]. IEEE Sensors Journal, 2021, 21 (12): 13540- 13550. doi: 10.1109/JSEN.2021.3068444
7	ZENG Y , ZHANG M , HAN F , et al. Spectrum analysis and convolutional neural network for automatic modulation recognition[J]. IEEE Wireless Communications Letters, 2019, 8 (3): 929- 932. doi: 10.1109/LWC.2019.2900247
8	BYEOUNGDO K, JAEKYUM K, HYUNMIN C, et al. Deep neural network-based automatic modulation classification technique[C]//Proc. of the International Conference on Information and Communication Technology Convergence, 2016: 579-582.
9	XIAO Y, ZHANG X J. Micro-UAV detection and identification based on radio frequency signature[C]//Proc. of the 6th Interna-tional Conference on Systems and Informatics, 2019: 1056-1062.
10	狄佳颖. 基于雷达低分辨率航迹信息的目标分类方法研究[D]. 南京: 南京航空航天大学, 2019.
	DI J Y. Research on target classification method based on radar low resolution track information[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2019.
11	SUTTHIPHONG S, KIM H C, DENZEL M D L, et al. Drone versus bird flights: classification by trajectories characterization[C]// Proc. of the 59th Annual Conference of the Society of Instrument and Control Engineers of Japan, 2020: 343-348.
12	LIU J , XU Q Y , CHEN W S . Classification of bird and drone tar-gets based on motion characteristics and random forest model using surveillance radar data[J]. IEEE Access, 2021, 9, 160135- 160144. doi: 10.1109/ACCESS.2021.3130231
13	PAVLO M, KAREN E, JAAKKO A, et al. Classification of small UAVs and birds by micro-Doppler signatures[C]//Proc. of the European Radar Conference, 2013: 172-175.
14	BEOM-SEOK O , GUO X , WAN F Y , et al. Micro-Doppler mini-UAV classification using empirical-mode decomposition features[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (2): 227- 231. doi: 10.1109/LGRS.2017.2781711
15	PAVLO M , KAREN E , JAAKKO A , et al. Classification of aircraft using micro-Doppler bicoherence-based features[J]. IEEE Trans.on Aerospace and Electronic Systems, 2014, 50 (2): 1455- 1467.
16	LARS F, OLIVER B, JENS K, et al. Micro-Doppler analysis and classification of UAVs at Ka band[C]//Proc. of the 18th International Radar Symposium, 2017.
17	ZHAO X D, ZHOU X H, XIONG J, et al. Automatic modulation recognition based on multi-dimensional feature extraction[C]// Proc. of the International Conference on Wireless Communications and Signal Processing, 2020: 823-828.
18	SHAH M H , DANG X Y . A robust approach for AMC in frequency selective fading scenarios using unsupervised sparse autoencoder based deep neural network (SAE-DNN)[J]. IET Communications, 2018, 13 (4): 423- 432.
19	杨杰. 通信信号调制识别: 原理与算法[M]. 北京: 人民邮电出版社, 2014.
	YANG J . Modulation recognition for communication signals: principles and algorithms[M]. Beijing: Posts & Telecom Press, 2014.
20	SONG F X, GUO Z W, MEI D Y. Feature selection using principal component Analysis[C]//Proc. of the International Conference on System Science, Engineering Design and Manufacturing Informatization, 2010: 27-30.
21	JACOB G, SAM R, GEOFF H, et al. Neighbourhood components analysis[C] //Proc. of the 17th International Conference on Neural Information Processing Systems, 2004: 513-520.

结构或参数	设置
输入层	14/46/51
隐藏层	(10, 8)/(30, 20)
输出层	5
激活函数	Sigmoid, Softmax
优化算法	L-BFGS
稀疏系数(ρ)	0.1
惩罚系数(β)	3

集群类型	集群内通信用户数量	通信信号调制方式	集群航迹类型
A	2	BPSK	航迹类型1
B	2	QPSK	航迹类型2
C	2	8PSK	航迹类型3
D	2	16QAM	航迹类型4
E	2	64QAM	航迹类型5

雷达参数	变量符号	数值
频率/GHz	f₀	10
带宽/MHz	B₀	15
脉冲重复周期/μs	PRP	120
快时间点数	N₁	256
慢时间点数	N₂	128

维度	变量符号	数值
距离/m	d	[200, 1 200]
方位/(°)	α	[0, 30]
速度/(m·s^-1)	v	[10, 30]
高度/m	h	[30, 100]

[1]	李庚松, 刘艺, 郑奇斌, 秦伟, 李红梅, 任小广, 宋明武. 基于蚁狮算法的元特征选择方法[J]. 系统工程与电子技术, 2023, 45(9): 2831-2842.
[2]	刘丹阳, 吴堃, 朱永锋, 张永杰, 周剑雄. 地面目标HRRP识别的稳健性特征选择方法[J]. 系统工程与电子技术, 2023, 45(12): 3726-3733.
[3]	吴梦蝶, 程龙生, 陈闻鹤. 基于自适应马氏空间与深度学习的滚动轴承退化趋势预测[J]. 系统工程与电子技术, 2023, 45(10): 3338-3349.
[4]	李波, 周家豪, 刘民岷, 朱品朝. 基于改进NSGA3的焊接缺陷评估特征选择[J]. 系统工程与电子技术, 2022, 44(7): 2211-2218.
[5]	曹浪财, 林晓昌, 苏思行. 基于矩阵分解和自适应图的无监督特征选择[J]. 系统工程与电子技术, 2021, 43(8): 2197-2208.
[6]	李睿峰, 许爱强, 孙伟超, 王树友. 基于元学习的航空电子设备特征选择算法推荐方法[J]. 系统工程与电子技术, 2021, 43(7): 2011-2020.
[7]	史蕴豪, 许华, 郑万泽, 刘英辉. 基于集成学习与特征降维的小样本调制识别方法[J]. 系统工程与电子技术, 2021, 43(4): 1099-1109.
[8]	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.
[9]	袁莉芬, 宁暑光, 何怡刚, 吕密, 路健. 基于高阶累积量特征学习的调制识别方法[J]. 系统工程与电子技术, 2019, 41(9): 2122-2131.
[10]	张妍, 王村松, 陆宁云, 姜斌. 基于退化特征相似性的航空发动机寿命预测[J]. 系统工程与电子技术, 2019, 41(6): 1414-1421.
[11]	魏存伟, 段发阶, 刘先康. 基于宽带雷达HRRP舰船目标长度估计算法[J]. 系统工程与电子技术, 2018, 40(9): 1960-1965.
[12]	谭晓衡, 褚国星, 张雪静, 杨扬. 基于高阶累积量和小波变换的调制识别算法[J]. 系统工程与电子技术, 2018, 40(1): 171-177.
[13]	李岸达, 何桢, 何曙光. 基于GSA的复杂产品关键质量特性识别[J]. 系统工程与电子技术, 2015, 37(9): 2073-2079.
[14]	司伟建, 李晓林, 蒋伊琳. 基于特殊阵列的近场源参数估计新算法[J]. 系统工程与电子技术, 2015, 37(7): 1476-1482.
[15]	范广伟，蔚保国，晁磊，邓志鑫. 卫星导航电磁干扰识别分类器设计[J]. 系统工程与电子技术, 2014, 36(2): 234-238.