射频掩护脉冲对抗场景下的分选技术

doi:10.12305/j.issn.1001-506X.2026.11.11

系统工程与电子技术 ›› 2026, Vol. 48 ›› Issue (11): 3792-3798.doi: 10.12305/j.issn.1001-506X.2026.11.11

射频掩护脉冲对抗场景下的分选技术

董阳阳(), 尹卓新(), 王贤铧(), 常诚()

西安电子科技大学电子工程学院，陕西西安 710071

收稿日期:2025-08-27 修回日期:2025-11-11 接受日期:2025-11-27 出版日期:2026-10-25 发布日期:2026-01-19
通讯作者: 董阳阳 E-mail:yydong@xidian.edu.cn;yinzhuoxin@stu.xidian.edu.cn;wangxianhua@xidian.edu.cn;2215070954@qq.com
作者简介:董阳阳（1991—），男，副教授，博士，主要研究方向为电磁频谱感知、辐射源智能对抗
尹卓新（2001—），女，硕士研究生，主要研究方向为电子侦察、雷达干扰
王贤铧（1986—），男，助理研究员，硕士，主要研究方向为电子对抗信号处理与仿真
常　诚（1999—），男，硕士研究生，主要研究方向为侦察信号处理、干扰优化

Sorting technology in radio frequency-masking pulses confrontations scene

Yangyang Dong(), Zhuoxin Yin(), Xianhua Wang(), Cheng Chang()

School of Electronic Engineering，Xidian University，Xi’an 710071，China

Received:2025-08-27 Revised:2025-11-11 Accepted:2025-11-27 Online:2026-10-25 Published:2026-01-19
Contact: Yangyang Dong E-mail:yydong@xidian.edu.cn;yinzhuoxin@stu.xidian.edu.cn;wangxianhua@xidian.edu.cn;2215070954@qq.com

摘要/Abstract

摘要：

射频掩护脉冲分选反侦察手段的应用显著增加了雷达信号分选的难度。针对此问题，提出一种双阶段聚类分选算法。利用自组织映射（self-organizing map, SOM）神经网络对含射频掩护脉冲背景数据初聚类，滤除射频掩护脉冲，得到真实雷达信号聚类中心数量和质心位置，作为K-Means聚类的关键特征参数。通过引入K维树解决K-Means算法处理高密度数据和大量最邻近计算时间复杂度较高的问题。实验结果表明，所提聚类算法不仅将分选结果准确率提升至96.09%，还可降低K-Means聚类算法的时间复杂度，使雷达侦察系统在射频掩护脉冲对抗场景下能更高效准确地完成信号分选任务。

关键词: 雷达信号分选, 对抗场景, 射频掩护脉冲, 双阶段聚类, K维树

Abstract:

The application of radio frequency-masking pulses sorting anti-reconnaissance measures significantly increased the difficulty of radar signals sorting. To solve this problem, a two-stage clustering sorting algorithm is proposed. Self-organizing map （SOM） is used to preliminarily cluster the background data containing radio frequency-masking pulses, filter the radio frequency-masking pulses, and obtain the number of cluster centers and centroid positions of real radar signals, which are used as the key feature parameters of K-Means clustering. The problem of high time complexity of the K-Means algorithm when processing high-density data and a large number of nearest neighbor computations is solved by introducing the K-dimensional tree. The experimental results show that the accuracy rate of the sorting results of the proposed clustering algorithm is increased to 96.09%, the time complexity of K-Means clustering algorithm is reduced, so that the radar reconnaissance system can complete the signal sorting task more efficiently and accurately in the radio frequency-masking pulses confrontation scene.

Key words: radar signals sorting, confrontation scene, radio frequency-masking pulse, two-stage clustering, K-dimensional (K-D) tree

中图分类号:

TN 971

董阳阳, 尹卓新, 王贤铧, 常诚. 射频掩护脉冲对抗场景下的分选技术[J]. 系统工程与电子技术, 2026, 48(11): 3792-3798.

Yangyang Dong, Zhuoxin Yin, Xianhua Wang, Cheng Chang. Sorting technology in radio frequency-masking pulses confrontations scene[J]. Systems Engineering and Electronics, 2026, 48(11): 3792-3798.

图/表 12

图1

图2

图3

图4

表1

图5

表2

图6

表3

表4

图7

图8

参考文献 33

1	赵贵喜, 刘永波, 王岩, 等. 数据场和K-Means算法融合的雷达信号分选[J]. 雷达科学与技术, 2016, 14 (5): 517. doi: 10.3969/j.issn.1672-2337.2016.05.012
2	Chen T, Guo X Q, Li J X. Radar signal sorting method with mimetic image mapping based on antenna scan pattern via SOLOv2 network[J]. Remote Sensing, 2024, 16 (24): 4639. doi: 10.3390/rs16244639
3	Wang Q S, Hu P G, Zhang L Q, et al. The background and significance of radar signal sorting research in modern warfare[J]. Procedia Computer Science, 2019, 154 (C): 519.
4	Jiang Y, Shi S, Zhang F, et al. Radar pre-sorting algorithm based on autoencoder and LSTM[J]. AEUE-International Journal of Electronics and Communications, 2024, 187, 155535.
5	Zhang Y, You S X, Yan Y B, et al. Multi-target cognitive electronic reconnaissance for unmanned aerial vehicles based on scene reconstruction[J]. IET Radar, Sonar & Navigation, 2024, 18(12): 2667.
6	Qi L G, Chen H Z, Guo Q, et al. GLS: a hybrid deep learning model for radar emitter signal sorting[J]. Digital Signal Processing, 2025, 161, 105117. doi: 10.1016/j.dsp.2025.105117
7	路征, 龚燕. 雷达辐射源识别技术面临的主要挑战及对策[J]. 国防科技, 2017, 38 (2): 24. doi: 10.13943/j.issn1671-4547.2017.02.06
8	李辰梓, 马若飞, 余建宇. 基于间歇采样的射频掩护波形干扰效能分析[J]. 火控雷达技术, 2022, 51 (1): 81. doi: 10.19472/j.cnki.1008-8652.2022.01.016
9	Wang B, Gao B, Wang L, et al. Radar signal sorting algorithm based on PRI for large jitter[C]//IOP Conference Series: Materials Science and Engineering, 2018, 466: 2042.
10	Chong B. K-means clustering algorithm: a brief review[J]. Academic Journal of Computing & Information Science, 2021, 4 (5): 142.
11	牟皓, 高由兵, 郑坤. 复杂电磁环境下同型雷达信号的分选方法[J]. 电子信息对抗技术, 2018, 33(5): 12.
12	Hussein A A, Abdulrazzak N H, ALI S A. MANET highly efficient clustering technique based on coverage k-means algorithm[J]. Egyptian Informatics Journal, 2025, 30, 100672. doi: 10.1016/j.eij.2025.100672
13	Ikotun A M, Ezugwu E A, Abualigah L M, et al. K-means clustering algorithms: a comprehensive review, variants analysis, and advances in the era of big data[J]. Information Sciences, 2022, 622, 178.
14	Nie F P, Li Z H, Wang R, et al. An effective and efficient algorithm for K-means clustering with new formulation[J]. IEEE Trans. on Knowledge and Data Engineering, 2023, 35, 3433. doi: 10.1109/TKDE.2022.3155450
15	He Y D. Semi-supervised equilibrium K-means for imbalanced data clustering[J]. Knowledge-Based Systems, 2025, 326, 113990. doi: 10.1016/j.knosys.2025.113990
16	Zhan M L. Intelligent power communication network model based on improved SOM algorithm[C]//16th International Conference on Intelligent Computing Technology and Automation, 2024: 1124.
17	Zhang Y Y, Liu M, Luo H J, et al. Clustering analysis of ancient celadon based on SOM neural network[J]. Science in China Series E: Technological Sciences, 2008, 51 (7): 999.
18	Huo L T, Jia R T, Wei S, et al. Comprehensive evaluation of surface water quality based on SOM and PCA: a case study in Luan River Basin[J]. Journal of Physics: Conference Series, 2025, 3004 (1): 012021. doi: 10.1088/1742-6596/3004/1/012021
19	Lin H Q, Ji Z Z. Breast cancer prediction based on K-Means and SOM hybrid algorithm[C]//2nd International Conference on Computer Modeling, Simulation and Algorithm, 2020: 999.
20	Zhang W Y, Liu X, Wen Y L, et al. User classification based on SOM+K-means cluster analysis[C]//International Conference on Applied Physics and Computing, 2023: 391.
21	Zheng J H, Xiang Y, Li S Y. Research on energy saving scene of 5G base stations based on SOM + K-means two-stage clustering algorithm[C]//2nd International Conference on Artificial Intelligence, Robotics, and Communication, 2023: 271.
22	Chi S C, Yang C C. Integration of ant colony SOM and K-means for clustering analysis[C]//Knowledge-based Intelligent Information and Engineering Systems, 2006.
23	Dogan Y, Birant D, Kut A. SOM++: integration of self-organizing map and K-means++ algorithms[C]//9th International Conference on Machine Learning and Data Mining in Pattern Recognition, 2013: 246.
24	Tao B Y, Wu J, Dou X Y, et al. Memorial K-means clustering for cooperative spectrum sensing in cognitive wireless sensor networks at low SNR regimes[J]. Sensor Review, 2025, 45 (3): 443. doi: 10.1108/SR-10-2024-0883
25	Vardakas G, Papakostas I, Likas A. Efficient error minimization in kernel k-means clustering[J]. Pattern Analysis and Applications, 2025, 28 (2): 107. doi: 10.1007/s10044-025-01463-4
26	沈义龙, 王坤, 靳浩, 等. 一种对雷达射频掩护的干扰方法研究[J]. 现代防御技术, 2020, 48 (1): 62. doi: 10.3969/j.issn.1009-086x.2020.01.010
27	Aarti G S, Renu D. Grey relational classification algorithm for software fault proneness with SOM clustering[J]. International Journal of Data Mining, Modelling and Management, 2020, 12 (1): 28. doi: 10.1504/IJDMMM.2020.105599
28	Xiao E. Comprehensive K-means clustering[J]. Journal of Computer and Communications, 2024, 12 (3): 146. doi: 10.4236/jcc.2024.123009
29	Xue M F, Han L, Peng D L. A combined algorithm of K-means and MTRL for multi-class classification[J]. Journal of Systems Engineering and Electronics, 2019, 30 (5): 875. doi: 10.21629/JSEE.2019.05.06
30	Kalpitha N, Murali S. Object classification using SVM and KD-Tree[J]. International Journal of Recent Technology and Engineering, 2020, 8 (6): 1717.
31	Yuan Y C, Li J Y, Cheng Y H, et al. Efficient reversible data hiding in encrypted point clouds via KD tree-based path planning and dual-model design[J]. Mathematics, 2025, 13 (16): 2593. doi: 10.3390/math13162593
32	Xu D Y, Lv J M, Zhang X Y, et al. Improved data stream clustering method: incorporating KD-tree for typicality and eccentricity-based approach[J]. Computers, Materials & Continua, 2024, 78(2): 2557.
33	Peng N N, Gao S J S, Yin X Z, et al. An improved K-means algorithm based on persistent homology[J]. Journal of Computational Science, 2025, 91 (4): 102680.

工作模式	参数	真实雷达信号	前掩护脉冲	后掩护脉冲
TAS	脉冲载频/MHz	3 100	3 103	3 090
	脉冲宽度/μs	350	30	30
	脉冲重复周期/μs	4 000	3 980	4 050
	到达方向/（°）	80	80	80
TWS	脉冲载频/MHz	3 100	3 103	3 090
	脉冲宽度/μs	150	25	25
	脉冲重复周期/μs	2 000	1 980	2 050
	到达方向/（°）	80	80	80
STT	脉冲载频/MHz	3 100	3 103	3 090
	脉冲宽度/μs	45	20	20
	脉冲重复周期/μs	450	430	500
	到达方向/（°）	80	80	80
MTT	脉冲载频/MHz	3 100	3 103	3 090
	脉冲宽度/μs	35	15	15
	脉冲重复周期/μs	400	380	450
	到达方向/（°）	80	80	80

分选算法	脉冲载频/MHz	脉宽/$\text{μ} {\mathrm{s}}$	到达方向/(°)	幅度范围/dB
传统K-Means 分选算法	3 100.19	149.76	80	75.29~84.6
	3 100.25	351.07	81	76.15~83.85
	3 100、3 090、3 103	14.96~45.42	80	71.13~91.35
所提算法	3 100.56	35.10~350.51	82	71.10~91.39

分选算法	分选正确数量	准确率/%	增批率/%
传统直方图分选算法	0	0	0
SOM算法	112	33.63	333
传统K-Means分选算法	173	51.95	200
所提算法	320	96.09	0

数据量	K-Means	SOM+K-Means
1 000	50.83	95.62
2 000	40.7	96.13
5 000	66.41	95.16
10 000	66.39	96.71

[1]	张华卿, 张晓飞, 郝明瑞, 姜吉祥, 李闪. 鲁棒多智能体协同对抗策略离线强化学习[J]. 系统工程与电子技术, 2026, 48(5): 1670-1681.
[2]	苏显康, 张大维, 叶方. 基于层次聚类和谱适应的雷达信号分选方法[J]. 系统工程与电子技术, 2025, 47(1): 101-108.
[3]	陈柯宇, 杨健, 张伟, 孙国敏, 邵怀宗. 基于极大似然估计的非理想场景雷达信号分选算法[J]. 系统工程与电子技术, 2024, 46(7): 2276-2284.
[4]	陈涛, 刘福悦, 李金鑫, 雷宇. 基于深度分割的端到端雷达信号分选[J]. 系统工程与电子技术, 2023, 45(5): 1351-1358.
[5]	王磊, 张志勇, 曾维贵, 曹司磊, 张天赫. 基于数据场联合决策图改进的GMM聚类[J]. 系统工程与电子技术, 2022, 44(9): 2743-2751.
[6]	张怡霄, 郭文普, 康凯, 姚云龙, 张林科, 张薇. 基于数据场联合PRI变换与聚类的雷达信号分选[J]. 系统工程与电子技术, 2019, 41(7): 1509-1515.
[7]	刘旭波，司锡才. 雷达信号分选实现的新方法[J]. Journal of Systems Engineering and Electronics, 2010, 32(1): 53-56.

射频掩护脉冲对抗场景下的分选技术

Sorting technology in radio frequency-masking pulses confrontations scene

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 33

相关文章 7

编辑推荐

Metrics

本文评价