Radar Interference Recognition Based on Improved Lightweight Convolutional Neural Networks

doi:10.3969/j.issn.1009-086x.2025.02.010

Abstract

Abstract:

Considering a large number of radar interference signals could be built within a short period on the battlefield. Traditional convolutional neural networks face issues due to their large scale. It’s a challenge to deploy jamming recognition system on small-scale equipment. This paper proposes an improved lightweight convolutional neural network to solve the problem by adopting adaptive kernel and batch normalization technology to improve recognition efficiency. By extracting time-frequency character to construct training and testing database for neural network training. Experiment shows that the network achieves over 96% identification accuracy for six kinds of interference signals under -8dB JNR. Compared with other networks， it has a superior accuracy efficiency ratio.

Key words: radar active jamming, convolutional neural network, lightweight, adaptive kernel, feature extraction

摘要：

针对战场实战电磁对抗作战中，大量雷达干扰信号可以被简单迅速地生成，使用传统卷积神经网络对雷达干扰进行识别存在规模大，难以在小型化装备上搭载的问题。提出一种改进的轻量化卷积神经网络，通过在传统神经网络中使用动态卷积核尺寸技术并添加批量归一化层技术，提高网络的识别效能。通过提取干扰信号时频特征，构建训练集与测试集对网络进行训练。仿真实验表明，该网络对6种干扰信号在-8 dB干噪比条件下识别准确率达到96 %以上，对比其他网络具有更好的识别准确效能。

关键词: 雷达有源干扰, 卷积神经网络, 轻量化, 动态卷积核, 特征提取

CLC Number:

TN972

Yifan FU, Hang RUAN, Dongping ZHOU, Heqiang MU. Radar Interference Recognition Based on Improved Lightweight Convolutional Neural Networks[J]. Modern Defense Technology, 2025, 53(2): 91-98.

付亦凡, 阮航, 周东平, 穆贺强. 基于改进轻量化神经网络的干扰识别方法[J]. 现代防御技术, 2025, 53(2): 91-98.

Figures/Tables 13

Fig. 1 Radar interference types

Fig. 2 Plot of six jamming signals

Fig. 3 Frequency plot of six jamming signals

Fig. 4 Time-frequency plot of six jamming signals

Fig. 5 Lightweight network interference recognition model

Fig. 6 Traditional CNN structure

Table 1 Structure of LRJRNet

层结构	输出图像尺寸
输入层	128×64×1
卷积层1	64×32×16
归一化层1	64×32×16
最大池化层1	32×16×16
卷积层2	30×14×50
归一化层2	30×14×50
最大池化层2	15×7×50
卷积层3	13×5×100
归一化层3	13×5×100
最大池化层3	6×2×100
平均池化层	1×1×100
全连接层1	1×1×64
丢弃层	1×1×64
全连接层2	1×1×6
归一化指数层	1×1×6
输出层	1×1×6

Fig. 7 LRJRNet structure

Fig. 8 LRJRNet accuracy with the increase of iteration

Fig. 9 LRJRNet loss function with the increase of iteration

Fig. 10 Confusion matrix of LRJRNet

Table 2 Parameters comparison of different networks

网络	参数量
LeNet	9.92×10⁴
VGG	1.07×10⁵
LRJRNet	5.96×10⁴
大核LRJR	1.52×10⁵

Fig. 11 Accuracy of different networks

References 17

1	赵国庆. 雷达对抗原理［M］. 2版. 西安：西安电子科技大学出版社， 2015.
	ZHAO Guoqing. Principle of Radar Countermeasure［M］. 2nd ed. Xi'an： Xidian University Press， 2015.
2	刘春生，郝治理，王伟. 人工智能技术在雷达对抗中的应用［J］. 科技导报， 2019， 37（4）： 63-68.
	LIU Chunsheng， HAO Zhili， WANG Wei. Application of Artificial Intelligence Technology in Radar Countermeasures［J］. Science & Technology Review， 2019， 37（4）： 63-68.
3	YANG Boyang， LI Kang， Bo JIU， et al. An Intelligent Jamming Strategy Design Method Against Frequency Agility Radar［C］∥2023 IEEE International Radar Conference （RADAR）. Piscataway： IEEE， 2023： 1-6.
4	刘慧敏. 基于深度学习的有源欺骗干扰特征级识别方法研究［D］. 西安：西安电子科技大学， 2019.
	LIU Huimin. A Study on Feature-Level Identification of Active Deception Jamming Based on Deep Learning［D］. Xi'an： Xidian University， 2019.
5	王冠，王晖，王金宇，等. 联合分形维数和奇异值熵的雷达干扰信号识别方法［J］. 电子信息对抗技术， 2023， 38（2）： 14-20.
	WANG Guan， WANG Hui， WANG Jinyu， et al. Radar Jamming Signal Recognition Method Combining Fractal Dimension and Singular Value Entropy［J］. Electronic Information Warfare Technology， 2023， 38（2）： 14-20.
6	张忠民，王雨鑫. 基于自适应的SSD算法和1.5维谱的新型雷达干扰识别［J］. 应用科技， 2021， 48（5）： 54-59.
	ZHANG Zhongmin， WANG Yuxin. New Radar Jamming Recognition Based on Adaptive SSD Algorithm and 1.5-Dimensional Spectrum［J］. Applied Science and Technology， 2021， 48（5）： 54-59.
7	XU Chang， YU Lei， WEI Yinsheng， et al. Research on Active Jamming Recognition in Complex Electromagnetic Environment［C］∥2019 IEEE International Conference on Signal， Information and Data Processing （ICSIDP）. Piscataway： IEEE， 2019： 1-5.
8	YU Junfei， LI Jingwen， SUN Bing， et al. Barrage Jamming Detection and Classification Based on Convolutional Neural Network for Synthetic Aperture Radar［C］∥IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium. Piscataway： IEEE， 2018： 4583-4586.
9	李东霞，师亚辉. 基于深度学习的雷达干扰识别方法研究［J］. 遥测遥控， 2023， 44（4）： 102-108.
	LI Dongxia， SHI Yahui. Research on Radar Jamming Recognition Method Based on Deep Learning［J］. Journal of Telemetry， Tracking and Command， 2023， 44（4）： 102-108.
10	QIAN J， TENG X， QIU Z. Recognition of Radar Deception Jamming Based on Convolutional Neural Network［C］∥IET International Radar Conference （IET IRC 2020）. Piscataway： IEEE， 2020： 913-918.
11	刘强. 基于深度学习的雷达干扰识别技术［D］. 成都：电子科技大学， 2020.
	LIU Qiang. Radar Interference Recognition Based on Deep Learning［D］. Chengdu： University of Electronic Science and Technology of China， 2020.
12	LI Hao， FANG Xueli， ZHANG Lei， et al. Semi-Supervised Open-SET Recognition of Radar Active Jamming［C］∥2021 CIE International Conference on Radar （Radar）. Piscataway： IEEE， 2021： 2168-2171.
13	宋星. 复杂电磁环境下的雷达干扰智能感知方法研究［D］. 西安：西安电子科技大学， 2022.
	SONG Xing. Research on Intelligent Perception Method of Radar Jamming in Complex Electromagnetic Environment［D］. Xi'an： Xidian University， 2022.
14	Qinzhe LÜ， QUAN Yinghui， FENG Wei， et al. Radar Deception Jamming Recognition Based on Weighted Ensemble CNN with Transfer Learning［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022， 60： 1-11.
15	GOLDMAN E， GOLDBERGER J. Factorized CRF with Batch Normalization Based on the Entire Training Data［C］∥ICASSP 2021-2021 IEEE International Conference on Acoustics， Speech and Signal Processing （ICASSP）. Piscataway： IEEE， 2021： 2780-2784.
16	FENG Xi， HU Jianwen， WU Wanneng， et al. Dynamic Large-Small Kernel Convolutional Neural Network for Pansharpening［J］. IEEE Geoscience and Remote Sensing Letters， 2023， 20： 1-5.
17	韩丰，高嵩，薛峰，等. 基于CUDA的并行雷达拼图算法研究［J］. 气象， 2023， 49（10）： 1246-1253.
	HAN Feng， GAO Song， XUE Feng， et al. Study of Algorithms for Radar Networking Based on CUDA［J］. Meteorological Monthly， 2023， 49（10）： 1246-1253.

[1]	Jiakuan LI, Bo FENG, Lunhao SHEN, Chunmao YE, Jizhou YU. Aerodynamic Target Recognition Method Based on Incidence Angle-Guided Radar Image Feature Fusion [J]. Modern Defense Technology, 2025, 53(2): 129-140.
[2]	Henglei XU, Shuaiqi CHEN, Xun SONG, Mingjie ZHU. Blade Stitching Technology Based on Image Semantic Segmentation and Structure Preservation Constraints [J]. Modern Defense Technology, 2024, 52(4): 123-129.
[3]	Ming HE, Zihan ZHU, Xulong ZHAI, Zheng ZHAI, Chengpeng HAO. Air-to-Ground Target Detection Algorithm Based on Multi-branch Context Fusion [J]. Modern Defense Technology, 2023, 51(3): 91-98.
[4]	NIU Hao-nan, WANG Wen-can, LIU Qing-bo. Radar Radiation Source Identification Based on Convolution Neural Network [J]. Modern Defense Technology, 2021, 49(3): 130-136.
[5]	HUANG Xiang, XU Jing, DU Chen, GUO Zhao-yi, WU Tao. A Modulation Recognition Algorithm for UAV Emitter [J]. Modern Defense Technology, 2021, 49(3): 98-104.
[6]	ZHAO Yu-meng, FAN Shou-tao, HAN Yu, WANG Chuan. Design of Ku-Band Power Division Amplification 3D-MCM [J]. Modern Defense Technology, 2021, 49(2): 106-110.
[7]	LIANG Fu-tai, LI Hong-quan, MENG Qing-wen, CAI Li. An Aerial Target Track Clustering Method [J]. Modern Defense Technology, 2020, 48(1): 19-25.
[8]	MA Xin-xing, TENG Ke-nan, HOU Xue-long. Forecast Model of Main Air Attack Direction Based on CNN [J]. Modern Defense Technology, 2018, 46(5): 6-12.