基于1D-2D-GRU-ResNet的辐射源个体识别方法

doi:10.12305/j.issn.1001-506X.2026.02.33

系统工程与电子技术 ›› 2026, Vol. 48 ›› Issue (2): 727-735.doi: 10.12305/j.issn.1001-506X.2026.02.33

• 通信与网络 • 上一篇

基于1D-2D-GRU-ResNet的辐射源个体识别方法

刘恒燕(), 方君, 凌青, 闫文君, 于柯远, 张立民

海军航空大学，山东烟台 264001

收稿日期:2024-11-04 修回日期:2025-02-03 出版日期:2025-05-23 发布日期:2025-05-23
通讯作者: 方君 E-mail:2290319679@qq.com
作者简介:刘恒燕（1994—），女，讲师，博士，主要研究方向为信号智能处理
凌　青（1987—），女，副教授，博士，主要研究方向为通信信号智能处理
闫文君（1986—），男，副教授，博士，主要研究方向为空时分组码检测、智能信号处理
于柯远（1992—），男，讲师，博士，主要研究方向为空时分组码检测、智能信号处理
张立民（1966—），男，教授，博士，主要研究方向为卫星信号处理及应用
基金资助:
国家自然科学基金(62371465) ；山东省泰山学者专项人才工程（TS201511020）；山东省高等学校青创团队计划（2022kj084）资助课题

Emitter individual identification method based on 1D-2D-GRU-ResNet

Hengyan LIU(), Jun FANG, Qing LING, Wenjun YAN, Keyuan YU, Limin ZHANG

Naval Aviation University，Yantai 264001，China

Received:2024-11-04 Revised:2025-02-03 Online:2025-05-23 Published:2025-05-23
Contact: Jun FANG E-mail:2290319679@qq.com

摘要/Abstract

摘要：

针对现有辐射源个体识别算法对特征提取不够充分，导致分类准确率提升受限的问题，提出了一种基于一维、二维特征融合的特定辐射源分类方法。该方法通过格拉姆角场将一维序列直接转换为二维数据，分别采用门控循环单元（gated recurrent unit，GRU）及改进的深度残差网络（residual networks，ResNet）提取一维、二维特征，充分利用原始序列特征及机器学习处理二维数据的优势进行互补。仿真结果表明，GRU-ResNet具有更好的特征提取能力，大大提升了辐射源个体识别准确率，迭代次数为50次时，识别准确率较其他网络提升了10%以上，为特定辐射源识别问题提供了新思路。

关键词: 特定辐射源识别, 门控循环单元, 深度残差网络, 特征融合

Abstract:

In existing radar emitter individual identification algorithms, insufficient feature extraction limits the improvement of classification accuracy. To address the issue, a classification method for specific emitter based on one-dimensional and two-dimensional feature fusion is proposed. This method directly converts one-dimensional sequence into two-dimensional data through Gramian angular field. Then gated recurrent unit （GRU） and improved deep residual networks （ResNet） are used to extract one-dimensional and two-dimensional features respectively. The method leverages the advantages of both raw sequence features and the machine learning capabilities for processing two-dimensional data. The simulation results show that the GRU-ResNet has better feature extraction ability and greatly improves the accuracy of individual emitter recognition. When the number of iterations is 50 times, the recognition accuracy is improved by more than 10 % compared with other networks. The method provides a new idea for specific emitter recognition.

Key words: specific emitter identification, gated recurrent unit（GRU）, deep residual network（ResNet）, feature fusion

中图分类号:

TN 911.7

刘恒燕, 方君, 凌青, 闫文君, 于柯远, 张立民. 基于1D-2D-GRU-ResNet的辐射源个体识别方法[J]. 系统工程与电子技术, 2026, 48(2): 727-735.

Hengyan LIU, Jun FANG, Qing LING, Wenjun YAN, Keyuan YU, Limin ZHANG. Emitter individual identification method based on 1D-2D-GRU-ResNet[J]. Systems Engineering and Electronics, 2026, 48(2): 727-735.

图/表 10

图1

图2

图3

表1

图4

图5

表2

图6

图7

图8

参考文献 21

22	LI Y J, YANG H L, WU K X, et al. A Gramian angular field for constructing graph-based GNNs and its applications in rolling bearing defect detection[J]. IEEE Sensors Journal, 2024, 24 (21): 35141- 35155. doi: 10.1109/JSEN.2024.3458409
23	张国栋, 尹强, 羊柳. 基于格拉姆角场和PSO-CNN的滚动轴承故障诊断方法[J]. 兵器装备工程学报, 2024, 45 (4): 301- 308. doi: 10.11809/bqzbgcxb2024.04.039
	ZHANG G D, YIN Q, YANG L. Rolling bearing fault diagnosis method on Gramian angle field and PSO-CNN[J]. Journal of Ordnance Equipment Engineering, 2024, 45 (4): 301- 308. doi: 10.11809/bqzbgcxb2024.04.039
24	IWANA B K, FRINKEN V, Uchida S. DTW-NN: a novel neural network for time series recognition using dynamic alignment between inputs and weights[J]. Knowledge-Based Systems, 2020, 188, 104971. doi: 10.1016/j.knosys.2019.104971
25	PRIYADHARSHINI G, DOLLY D R J. Comparative investigations on tomato leaf disease detection and classification using CNN, R-CNN, fast R-CNN and faster R-CNN[C]// Proc. of the 9th International Conference on Advanced Computing and Communication Systems, 2023: 1540−1545.
26	ZAEED M, ISLAM T Z, INDIC V. Characterize and compare the performance of deep learning optimizers in recurrent neural network architectures[C]// Proc. of the IEEE 48th Annual Computers, Software, and Applications Conference, 2024: 39−44.
27	YUAN Y, XUN G X, MA F L, et al. A novel channel-aware attention framework for multi-channel EEG seizure detection via multi-view deep learning[C]// Proc. of the IEEE EMBS International Conference on Biomedical & Health Informatics, 2018: 206–209.
28	CHEN L P. Multi-view subspace clustering algorithm based on spatiotemporal attention[C]// Proc. of the 6th International Conference on Electronics and Communication, Network and Computer Technology, 2024: 142−145.
29	CHO K, MERRIENBOER V, BAHDANAU D, et al. On the properties of neural machine translation: encoder-decoder approaches [EB/OL]. [2024-09-04]. https://arxiv.org/abs/1409.1259.2014.
30	LIU Y, YU L J. Deep learning with gated recurrent unit recurrent neural networks and multi-objective optimisation for portfolio management[C]// Proc. of the 7th International Conference on Pattern Recognition and Artificial Intelligence, 2024: 1037−1042.
31	XIAO X W, YAN J. A transfer learning based CSI indoor localization using GASF image construction[C]// Proc. of the International Conference on Computer, Information and Telecommunication Systems, 2023.
32	周思益, 张江梅, 刘灏霖, 等. 基于GASF与MSVM的放射性核素识别方法[J]. 西南科技大学学报, 2023, 38 (2): 78- 84.
	ZHOU S Y, ZHANG J M, LIU H L, et al. Radionuclide recognition method based on GASF and MSVM[J]. Journal of Southwest University of Science and Technology, 2023, 38 (2): 78- 84.
33	MENG L H, XIE J Y, ZHOU Z W, et al. A fault diagnosis method for power electronic circuits based on GADF coding and channel split residual network[C]// Proc. of the IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, 2024: 360−368.
34	WU Y, CHEN Y Y, LIU Y Y, et al. A novel rust damage diagnosis method for reinforced concrete based on WAESN and GADF-AlexNet-Multihead-Attention[J]. IEEE Sensors Journal, 2025, 25 (1): 1579- 1592. doi: 10.1109/JSEN.2024.3489663
35	郭庆梅, 于恒力, 王中训, 等. 基于卷积神经网络的图像分类模型综述[J]. 电子技术应用, 2023, 49 (9): 31- 38.
	GUO Q M, YU H L, WANG Z X, et al. Review of image classification models based on convolutional neural networks[J]. Application of Electronic Technique, 2023, 49 (9): 31- 38.
36	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770−778.
37	任利强, 贾舒宜, 王海鹏, 等. 基于深度学习的时间序列分类研究综述[J]. 电子与信息学报, 2024, 46 (8): 3094- 3116. doi: 10.11999/JEIT231140
	REN L Q, JIA S Y, WANG H P, et al. A review of research on time series classification based on deep learning[J]. Journal of Electronics & Information Technology, 2024, 46 (8): 3094- 3116. doi: 10.11999/JEIT231140
1	XING Y X, HU A Q, ZHANG J Q, et al. Design of a robust radio-frequency fingerprint identification scheme for multimode LFM radar[J]. IEEE Internet of Things Journal, 2020, 7 (10): 10581- 10593. doi: 10.1109/JIOT.2020.3003692
2	KONG M X, ZHANG J, LIU W F, et al. Radar emitter identification based on deep convolutional neural network[C]// Proc. of the International Conference on Control and Automation, 2018: 309−314.
3	YE W Q, PENG C. Recognition algorithm of emitter signals based on PCA+CNN[C]// Proc. of the IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference, 2018: 2410−2414.
4	ZHANG J W, WANG F G, DOBRE O A, et al. Specific emitter identification via Hilbert-Huang transform in single-hop and relaying scenarios[J]. IEEE Trans. on Information Forensics and Security, 2016, 11 (6): 1192- 1205. doi: 10.1109/TIFS.2016.2520908
5	YUAN Y J, HUANG Z T, WU H, et al. Specific emitter identification based on Hilbert-Huang transform based time-frequency-energy distribution features[J]. IET Communications, 2014, 8 (13): 2404- 2412. doi: 10.1049/iet-com.2013.0865
6	PAN Y W, YANG S H, PENG H, et al. Specific emitter identification based on deep residual networks[J]. IEEE Access, 2019, 7, 54425- 54434. doi: 10.1109/ACCESS.2019.2913759
7	GONG J L, XU X D, LEI Y K. Unsupervised specific emitter identification method using radio-frequency fingerprint embedded InfoGAN[J]. IEEE Trans. on Information Forensics and Security, 2020, 15, 2898- 2913. doi: 10.1109/TIFS.2020.2978620
8	YAO Y Y, YU L, CHEN Y M. Specific emitter identification based on square integral bispectrum features[C]// Proc. of the IEEE 20th International Conference on Communication Technology, 2020: 1311–1314.
9	MERCHANT K, REVAY S, STANTCHEV G, et al. Deep learning for RF device fingerprinting in cognitive communication networks[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12 (1): 160- 167. doi: 10.1109/JSTSP.2018.2796446
10	QIAN Y H, QI J, KUAI X Y, et al. Specific emitter identification based on multi-level sparse representation in automatic identification system[J]. IEEE Trans. on Information Forensics and Security, 2021, 16, 2872- 2884. doi: 10.1109/TIFS.2021.3068010
11	WU Q Y, FERES C, KUZMENKO D, et al. Deep learning based RF fingerprinting for device identification and wireless security[J]. Electronics Letters, 2018, 54 (24): 1405- 1407. doi: 10.1049/el.2018.6404
12	WANG X B, HUANG G M, MA C S, et al. Convolutional neural network applied to specific emitter identification based on pulse waveform images[J]. IET Radar, Sonar & Navigation, 2020, 14(5): 728–735.
13	何遵文, 侯帅, 张万成, 等. 通信特定辐射源识别的多特征融合分类方法[J]. 通信学报, 2021, 42 (2): 103- 112. doi: 10.11959/j.issn.1000-436x.2021028
	HE Z W, HOU S, ZHANG W C, et al. Multifeature fusion classification method for communication specific emitter identification[J]. Journal on Communications, 2021, 42 (2): 103- 112. doi: 10.11959/j.issn.1000-436x.2021028
14	ZHOU H J, JIAO L C, ZHENG S L, et al. Generative adversarial network-based electromagnetic signal classification: a semi-supervised learning framework[J]. China Communications, 2020, 17 (10): 157- 169. doi: 10.23919/JCC.2020.10.011
15	PAN J F, GUO L Q, CHEN Q J. Specific radar emitter identification using 1D-CBAM-ResNet[C]// Proc. of the IEEE 14th International Conference on Wireless Communications and Signal Processing, 2022: 483−488.
16	WANG B, GAO N, WANG F. Specific emitter identification based on CNN and transformer[C]// Proc. of the 5th International Academic Exchange Conference on Science and Technology Innovation, 2023: 571−575.
17	LI W, ZHU W G, PANG H F, et al. Radar emitter identification based on fully connected spiking neural network[J]. Journal of Physics: Conference Series, 2021, 1914, 012036.
18	SHI Y, YUAN M D, REN J, et al. Specific radar emitter identification based on two stage multiple kernel extreme learning machine[J]. Electronics Letters, 2021, 57 (18): 699- 701. doi: 10.1049/ell2.12231
19	普运伟, 余永鹏, 姜萤, 等. 基于模糊函数多域特征融合与集成学习的雷达辐射源信号识别[J]. 控制与决策, 2024, 39 (1): 39- 48.
	PU Y W, YU Y P, JIANG Y, et al. Radar emitter signal recognition based on ambiguity function multi-domain feature fusion and ensemble learning[J]. Control and Decision, 2024, 39 (1): 39- 48.
20	郭瑞鹏. 基于深度学习的雷达辐射源个体识别技术研究[D]. 西安: 西安电子科技大学, 2022.
	GUO R P. Research on individual identification technology of radar emitter based on deep learning[D]. Xi’an: Xidian University, 2022.
21	张虎成, 李雷孝, 刘东江. 多模态数据融合研究综述[J]. 计算机科学与探索, 2024, 18 (10): 2501.
	ZHANG H C, LI L X, LIU D J. A survey of multimodal data fusion research[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18 (10): 2501.

层（阶段）	网络结构
阶段0	Cov2d（1, 7, 64）, BN, ReLU, MaxPool2d
阶段1	1个卷积模块，2个识别模块
阶段2	1个卷积模块，3个识别模块
阶段3	1个卷积模块，5个识别模块
阶段4	1个卷积模块，2个识别模块
池化层	AdaptiveAvgPool2d（1, 1）
降维层	squeeze（）
Pro1	Linear（2048, 128）, BN, ReLU, （Linear Block） Linear （128, 128） , BN, ReLU，（Linear Block） Linear （128, 64） , BN
Pro2	Linear （64, 64） , BN, ReLU Linear （64, 32） , BN

模型	时间复杂度	Num
GRU	$ O(N \cdot ({n_{{\mathrm{input}}}} \cdot {n_{{\mathrm{hidden}}}} + n_{{\mathrm{hidden}}}^2)) $	−
改进ResNet	$ O\left( \displaystyle\sum\nolimits_{l = 1}^{55} {{F_l} \cdot {C_l} \cdot {K_l} \cdot } {H_l} \cdot {W_l}\right) $	96
GRU-ResNet	$ O\left(\displaystyle \sum\nolimits_{l = 1}^{55} {{F_l} \cdot {C_l} \cdot {K_l} \cdot } {H_l} \cdot {W_l} \right) $	18
Linformer-ResNet	$ O\left( \displaystyle \sum\nolimits_{l = 1}^{55} {{F_l} \cdot {C_l} \cdot {K_l} \cdot } {H_l} \cdot {W_l}\right) $	50

[1]	王瑶, 胥辉旗, 曹司磊, 王磊. 基于深度学习的舰船关键部位检测算法[J]. 系统工程与电子技术, 2026, 48(2): 410-421.
[2]	包玉刚, 贾皓翔, 赵旦峰. 基于高阶递归网络的单幅图像去雨滴模型[J]. 系统工程与电子技术, 2026, 48(1): 12-21.
[3]	石文强, 雷迎科, 金虎, 滕飞. 基于自适应小波分解和轻量化网络架构的特定辐射源识别算法[J]. 系统工程与电子技术, 2025, 47(9): 2785-2796.
[4]	季策, 马相宇, 牟晓宇, 赵家毅. TS-GRU-VTA：基于深度学习的车辆信道估计方案[J]. 系统工程与电子技术, 2025, 47(9): 3093-3098.
[5]	付卫红, 彭文洪, 刘乃安. 混合注意力优化的SAR图像小目标检测方法[J]. 系统工程与电子技术, 2025, 47(8): 2519-2526.
[6]	周东平, 阮航, 沙明辉, 王崇宇, 崔念强, 鲁耀兵. 基于特征融合的Fast-CNN的复杂波形调制识别[J]. 系统工程与电子技术, 2025, 47(7): 2165-2175.
[7]	张琬滢, 高由兵, 李泽一, 李鹏飞, 张伟. 基于双路径特征融合网络的背景信号抑制算法[J]. 系统工程与电子技术, 2025, 47(7): 2406-2413.
[8]	王彩云, 贾一帆, 李晓飞, 王佳宁, 吴钇达. 基于改进鲸鱼算法和BiGRU的弹道目标HRRP识别方法[J]. 系统工程与电子技术, 2025, 47(6): 1824-1832.
[9]	姜杰, 凌青, 闫文君, 刘凯. 基于MFFDet-R的多源舰船图像融合检测方法[J]. 系统工程与电子技术, 2025, 47(2): 390-397.
[10]	王勇, 张博雅. 基于特征融合和定位增强的SAR图像舰船目标检测方法[J]. 系统工程与电子技术, 2025, 47(11): 3586-3597.
[11]	韦娟, 何德华, 宁方立. 基于自适应多分支卷积的声学场景分类[J]. 系统工程与电子技术, 2025, 47(10): 3148-3154.
[12]	韩子硕, 范喜全, 付强, 马传焱, 张冬冬. 面向无人机视角的多源信息融合目标检测[J]. 系统工程与电子技术, 2025, 47(1): 52-61.
[13]	于蕾, 邓秋月, 郑丽颖, 吴昊宇. 二阶逐层特征融合网络的图像超分辨重建[J]. 系统工程与电子技术, 2024, 46(2): 391-400.
[14]	薛峰涛, 孙天宇, 杨益民, 杨健. 基于全局特征融合的SAR图像旋转舰船目标检测算法[J]. 系统工程与电子技术, 2024, 46(12): 4044-4053.
[15]	罗佳奕, 李煊鹏, 李江浩, 薛启凡, 杨凤, 张为公. 基于PDW多特征融合的辐射源信号分选方法[J]. 系统工程与电子技术, 2024, 46(1): 80-87.

基于1D-2D-GRU-ResNet的辐射源个体识别方法

Emitter individual identification method based on 1D-2D-GRU-ResNet

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价