基于DBO-DAOD的未知雷达调制方式识别算法

doi:10.12305/j.issn.1001-506X.2025.06.12

摘要/Abstract

摘要：

随着各种新型雷达的出现或战时预留模式的采用, 真实的战场电磁环境将越加复杂, 大概率会出现种类未知且参数突变的雷达调制信号, 对现有的调制方式识别算法带来严峻挑战。对此，分析雷达调制方式“未知”对识别结果的影响机理, 将开集差分分布对齐(distribution alignment with open set difference, DAOD)算法引入雷达调制方式识别领域, 设计具体应用的技术方案, 并针对DAOD算法所需参数依靠先验知识或者试探选取问题, 利用蜣螂优化(dung beetle optimizer, DBO)算法进行参数优化。仿真结果表明: 在单个雷达调制方式未知情形下, 精确度Accuracy和F-measure分值的平均值分别可达91.34%和95.11%;在多个雷达调制方式未知情形下, Accuracy和F-measure的平均值分别可达91.37%、93.69%;与DAOD算法相比, 上述结果分别提升了3.77%、1.83%、21.17%和12.06%。因此，DBO-DAOD算法可有效提升未知雷达调制方式的识别率。

关键词: 开集差分分布对齐, 蜣螂优化算法, 未知调制方式识别, 影响机理

Abstract:

With the emergence of various new radars and the use of wartime reservation mode, the actual battlefield electromagnetic environment is becoming more and more complex. Radar modulation signals with unknown types and sudden changes in parameters likely appear, which bring great challenges to the existing modulation mode recognition algorithms. In this regard, the influence mechanism of radar modulation "unknown" on the recognition results is analyzed, and the distribution alignment with open set difference (DAOD) algorithm is introduced into the field of radar modulation mode recognition, and a specific application scheme is designed. The dung beetle optimizer (DBO) algorithm is used to optimize the parameters of DAOD algorithm to solve the problem of prior knowledge and heuristic selection needed by DAOD algorithm. The simulation results show that the Accuracy and F-measure can reach 91.34% and 95.11% in the case of single unknown radar modulation mode. The Accuracy and F-measure are 91.37% and 93.69% in the case of multiple unknown radar modulation mode. Compared with DAOD algorithm, the above results increase by 3.77%, 1.83%, 21.17% and 12.06%, respectively. Therefore, DBO-DAOD algorithm can effectively improve the recognition rate of unknown radar modulation modes.

Key words: distribution alignment with open set difference (DAOD), dung beetle optimizer (DBO) algorithm, unknown modulation mode recognition, influence mechanism

中图分类号:

TN973

张本辉, 刘松涛, 晁玉龙. 基于DBO-DAOD的未知雷达调制方式识别算法[J]. 系统工程与电子技术, 2025, 47(6): 1833-1842.

Benhui ZHANG, Songtao LIU, Yulong CHAO. Unknown radar modulation mode recognition algorithm based on DBO-DAOD[J]. Systems Engineering and Electronics, 2025, 47(6): 1833-1842.

图/表 7

图1

图2

表1

表2

图3

表3

表4

参考文献 30

1	张琴, 田宝玉. 通信信号调制模式的自动识别技术及发展前景[J]. 电讯技术, 2008, 48 (2): 6- 10. doi: 10.3969/j.issn.1001-893X.2008.02.002
	ZHANG Q , TIAN B Y . Automatic recognition technology for communication modulation signals and its prospects[J]. Telecommunication Engineering, 2008, 48 (2): 6- 10. doi: 10.3969/j.issn.1001-893X.2008.02.002
2	何正日. 雷达辐射源信号识别技术研究[D]. 西安: 西安电子科技大学, 2015.
	HE Z R. Research on radar emitter signal recognition technology[D]. Xi'an: Xidian University, 2015.
3	王海英, 张群英, 成文海, 等. LPI雷达信号调制识别及参数估计研究进展[J]. 系统工程与电子技术, 2024, 46 (6): 1908- 1924. doi: 10.12305/j.issn.1001-506X.2024.06.09
	WANG H Y , ZHANG Q Y , CHENG W H , et al. Progress in LPI radar signal modulation recognition and parameter estimation[J]. Systems Engineering and Electronics, 2024, 46 (6): 1908- 1924. doi: 10.12305/j.issn.1001-506X.2024.06.09
4	吴斌, 袁亚博, 汪勃. 基于记忆因子的连续相位调制信号最大似然调制识别[J]. 电子与信息学报, 2016, 38 (10): 2546- 2552.
	WU B , YUAN Y B , WANG B . Maximum likelihood modulation recognition for continuous phase modulation signals using memory factor[J]. Journal of Electronics & Information Technology, 2016, 38 (10): 2546- 2552.
5	WANG X , XU G , YAN H , et al. LPI radar signals modulation recognition based on ACDCA-ResNet[J]. IEEE Access, 2023, 11, 45168- 45180. doi: 10.1109/ACCESS.2023.3270231
6	杨静雅, 齐彦丽, 周一青, 等. CNN-Transformer轻量级智能调制识别算法[J]. 西安电子科技大学学报(自然科学版), 2023, 50 (3): 40- 49.
	YANG J Y , QI Y L , ZHOU Y Q , et al. Algorithm for recognition of lightweight intelligent modulation based on the CNN-transformer networks[J]. Journal of Xidian University(Natural Science), 2023, 50 (3): 40- 49.
7	邵凯, 朱苗苗. 一种信号调制识别网络的轻量化设计[J]. 电讯技术, 2023, 63 (5): 626- 632.
	SHAO K , ZHU M M . Lightweight design of a signal modulation identification neural network[J]. Telecommunication Engineering, 2023, 63 (5): 626- 632.
8	孙会楠. 基于深度学习的多进制相移键控信号调制识别研究[J]. 太原学院学报(自然科学版), 2024, 42 (1): 54- 64.
	SUN H N . Research on modulation MPSK signal based on reco-gnition of deep learning[J]. Journal of Taiyuan University(Natural Sciences), 2024, 42 (1): 54- 64.
9	张茜茜, 王禹, 林云, 等. 基于深度学习的自动调制识别方法综述[J]. 无线电通信技术, 2022, 48 (4): 697- 710. doi: 10.3969/j.issn.1003-3114.2022.04.017
	ZHANG X X , WANG Y , LIN Y , et al. A comprehensive survey of deep learning-based automatic modulation recognition methods[J]. Radio Communications Technology, 2022, 48 (4): 697- 710. doi: 10.3969/j.issn.1003-3114.2022.04.017
10	刘松涛, 赵帅, 汪慧阳. 雷达辐射源识别技术新进展[J]. 中国电子科学研究院学报, 2022, 17 (6): 523- 533. doi: 10.3969/j.issn.1673-5692.2022.06.002
	LIU S T , ZHAO S , WANG H Y . New development on the technology of radar emitter identification[J]. Journal of China Academy of Electronics and Information Technology, 2022, 17 (6): 523- 533. doi: 10.3969/j.issn.1673-5692.2022.06.002
11	ZHEN Y , JUN Y , PEDRAM G , et al. Open set recognition in real world[J]. International Journal of Computer Vision, 2024, 132 (3): 3208- 3231.
12	LI J J , YU Z Q , DU Z K , et al. A comprehensive survey on source-free domain adaptation[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2024, 46 (8): 5743- 5762. doi: 10.1109/TPAMI.2024.3370978
13	郝云飞, 刘章孟, 郭福成, 等. 基于生成对抗网络的信号调制方式的开集识别[J]. 系统工程与电子技术, 2019, 41 (11): 2619- 2624.
	HAO Y F , LIU Z M , GUO F C , et al. Open set recognition of signal modulation based on generative adversarial networks[J]. Systems Engineering and Electronics, 2019, 41 (11): 2619- 2624.
14	肖易寒, 李航, 于祥祯, 等. 基于MobileNetV3-SVDD的雷达信号调制方式开集识别[J]. 哈尔滨工程大学学报, 2022, 43 (8): 1178- 1185.
	XIAO Y H , LI H , YU X Z , et al. Open set recognition of radar signal modulation based on MobileNetV3-SVDD[J]. Jour nal of Harbin Engineering University, 2022, 43 (8): 1178- 1185.
15	秦博伟, 蒋磊, 许华, 等. 基于RE-GAN的调制信号开集识别算法[J]. 系统工程与电子技术, 2023, 45 (10): 3321- 3328.
	QIN B W , JIANG L , XU H , et al. A open-set recognition algorithm for modulation signal based on RE-GAN[J]. Systems Engineering and Electronics, 2023, 45 (10): 3321- 3328.
16	卜可. 基于迁移学习的自动调制识别研究[D]. 北京: 北京邮电大学, 2021.
	BU K. Research on transfer learning based automatic modulation classification[D]. Beijing: Beijing University of Posts and Telecommunications, 2021.
17	徐强. 基于迁移学习的调制识别技术研究[D]. 长沙: 国防科技大学, 2021.
	XU Q. Research on modulation recognition technology based on transfer learning[D]. Changsha: National University of Defense Technology, 2021.
18	FAN Z , LU J , LIU F , et al. Open set domain adaptation: theoretical bound and algorithm[J]. IEEE Trans.on Neural Networks and Learning Systems, 2021, 32 (10): 4309- 4322. doi: 10.1109/TNNLS.2020.3017213
19	XUE J K , SHEN B . Dung beetle optimizer: a new metaheuristic algorithm for global optimization[J]. The Journal of Supercomputing, 2022, 27 (10): 7305- 7336.
20	张本辉, 刘松涛. 未知辐射源识别技术研究进展[J]. 中国电子科学研究院学报, 2023, 18 (9): 864- 872. doi: 10.3969/j.issn.1673-5692.2023.09.012
	ZHANG B H , LIU S T . Research progress on unknown radiation source identification technology[J]. Journal of China Academy of Electronics and Information Technology, 2023, 18 (9): 864- 872. doi: 10.3969/j.issn.1673-5692.2023.09.012
21	刘星宏, 周毅, 周涛, 等. 基于自步学习的开放集领域自适应[J]. 计算机研究与发展, 2023, 60 (8): 1711- 1726.
	LIU X H , ZHOU Y , ZHOU T , et al. Self-paced learning for open-set domain adaptation[J]. Journal of Computer Research and Development, 2023, 60 (8): 1711- 1726.
22	BUSTO P P, GALL J. Open set domain adaptation[C]//Proc. of the International Conference on Computer Vision, 2017: 754- 763.
23	SAITO K, YAMAOTO S, USHIKU Y, et al. Open set domain adaptation by back propagation[C]//Proc. of the 15th European Conference on Computer Vision, 2018: 156-171.
24	WANG J D, FENG W J, CHEN Y Q, et al. Visual domain adaptation with manifold embedded distribution alignment[C]//Proc. of the 26th ACM International Conference on Multimedia, 2018: 402-410.
25	DENNIS H , DUNANT H , GETHIN W R . Gear fault diagnosis using an improved reassigned smoothed pseudo Wigner-Ville distribution[J]. Cogent Engineering, 2018, 5 (1): 1436928. doi: 10.1080/23311916.2018.1436928
26	赵小川, 何灏. 深度学习理论及实践(MATLAB版)[M]. 北京: 清华大学出版社, 2021.
	ZHAO X C , HE H . Deep learning theory and practice(MATLAB edition)[M]. Beijing: Tsinghua University Press, 2021.
27	赵帅, 刘松涛, 汪慧阳. 基于PSO-CNN的LPI雷达波形调制识别算法[J]. 系统工程与电子技术, 2021, 43 (12): 3552- 3563. doi: 10.12305/j.issn.1001-506X.2021.12.17
	ZHAO S , LIU S T , WANG H Y . LPI radar waveform recognition algorithm based on PSO-CNN[J]. Systems Engineering and Electronics, 2021, 43 (12): 3552- 3563. doi: 10.12305/j.issn.1001-506X.2021.12.17
28	WANG Q, BU P H, TOBY P B. Unifying unsupervised domain adaptation and zero-shot visual recognition[C]//Proc. of the International Joint Conference on Neural Networks, 2019.
29	GENG C X , CHEN S C . Collective decision for open set recognition[J]. IEEE Trans.on Knowledge and Data Engineering, 2020, 34 (3): 192- 204.
30	高菲, 杨柳, 李晖. 开放集识别研究综述[J]. 南京大学学报(自然科学), 2022, 58 (1): 115- 134.
	GAO F , YANG L , LI H . A survey on open set recognition[J]. Journal of Nanjing University(Natural Sciences), 2022, 58 (1): 115- 134.

雷达调制波形	参数	取值范围
Rect	f_c N	U(f_s/6, f_s/5) U[500, 1 920]
LFM FMCW	f_c BN	U(f_s/6, f_s/5) U(f_s/20, f_s/16) U[500, 1 920]
Barker	L_Bc f_c N_cc	{7, 11, 13} U(f_s/6, f_s/5) U[11, 14]
Frank P1	f_c N_cc M	U(f_s/6, f_s/5) {4, 5, 6} {6, 7, 8}
P2	f_c N_cc M	U(f_s/6, f_s/5) {4, 5, 6} {6, 8}
P3 P4 PX Zadoff-Chu	f_c N_cc m	U(f_s/6, f_s/5) {4, 5, 6} {39, 49, 64}
MFSK	f_c B L_Bc N	U(f_s/6, f_s/5) U(f_s/20, f_s/16) {6, 10, 12} U[500, 1 920]

信道参数	取值
采样频率/MHz	F_s=100
多径衰减/s	{0.1, 1.8, 3.4}/F_s
平均路径增益/dB	{0, －2, －10}
K-factor	4
最大多普勒频移/Hz	4
AWGN/dB	SNR=[-6∶6∶30]

波形名称	DAOD(验证集)		DBO-DAOD(训练集)		DBO-DAOD(验证集)
波形名称	Accuracy	F-measure	Accuracy	F-measure	Accuracy	F-measure
Zadoff-Chu	85.428 6	92.141 8	99.91±0.09	99.95±0.05	85.3±7.79	91.68±4.55
Rect	85.571 4	92.224 8	100±0	100±0	96.66±6.34	98.16±3.49
Px	85.285 7	92.058 6	91.83±2.37	95.09±1.29	95.12±3.13	97.15±1.66
P4	85.285 7	92.058 6	92.31±2.69	95.56±1.53	87.25±4.13	92.91±2.14
P3	85	91.891 9	91.50±6.81	95.41±3.67	86.46±7.24	92.40±4.20
P2	98.857 1	99.328 9	99.85±0.02	99.91±0.01	97.25±2.81	98.34±1.73
平均值	87.57	93.28	95.90±5.10	97.65±2.86	91.34	95.11

开放度	KNN		CAPLS		CD-OSR		DAOD		DBO-DAOD
开放度	Accuracy	F-measure	Accuracy	F-measure	Accuracy	F-measure	Accuracy	F-measure	Accuracy	F-measure
0	86.17	91.01	93.83	96.35	0	NaN	99.83	99.90	100±0.0	100±0
0.039 2	73.86	84.96	82.00	90.11	14.29	NaN	85.43	92.14	87.31±6.97	92.91±3.98
0.074 2	64.62	78.51	72.62	84.14	25	NaN	74.88.	85.63	86.52±7.17	91.55±4.42
0.105 6	57.44	72.97	64.78	78.62	33.33	NaN	66.33	79.76	96.52±4.42	97.41±3.29
0.134 0	51.70	68.16	57.70	73.18	40	NaN	59.70	74.77	92.15±6.50	93.85±3.28
0.159 8	47.00	63.95	51.64	68.11	45.45	NaN	53.91	70.05	88.42±6.87	90.37±4.56
0.183 5	43.08	60.22	47.67	64.56	50	NaN	56.00	69.19	88.68±5.05	89.74±3.90
平均值	60.55	74.25	67.18	79.30	29.72	NaN	70.2	81.63	91.37	93.69