基于GAN的直扩信号生成算法

doi:10.12305/j.issn.1001-506X.2023.05.32

摘要/Abstract

摘要：

将深度学习模型应用至电子干扰技术来生成干扰信号具有重要的现实意义。将生成对抗网络(generative adversarial network, GAN)应用于信号生成领域, 对电磁扩频信号频谱数据的分布进行深度学习, 并生成与其相干的干扰信号。在实验中GAN的生成器和判别器互相博弈训练, 通过自适应矩估计(adaptive moment estimation, Adam)进行优化, 最终训练出良好的模型, 可以生成所需信号。实验结果表明, 基于GAN的信号生成算法生成的数据分布已基本具备真实数据分布普遍具有的特点, 对同一信噪比的电磁频谱数据进行深度学习后, 生成数据能够较为准确地学习到不同信噪比电磁频谱数据的不同特点。

关键词: 扩频信号, 频谱数据, 生成对抗网络, 电子干扰

Abstract:

It is of great practical significance to apply deep learning model to electronic jamming technology to generate jamming signals. The generative adversarial network (GAN) is applied to signal generation, and the electromagnetic spread spectrum signal is deeply learned by using the model, and the coherent interference signal is generated by learning the distribution of spectrum data of electromagnetic spread spectrum signal. In the experiment, the generator and discriminator of GAN are trained with each other and optimized by adaptive moment estimation (Adam). Finally, a good model can be trained and the required signals can be generated. Experimental results show that the generated data distribution based on the GAN signal generation algorithm basically has the characteristics of the real data distribution, and the generated data can accurately learn the different characteristics of the electromagnetic spectrum data with different signal to noise ratio (SNR) after deep learning of the same SNR data.

Key words: spread spectrum signal, spectrum data, generative adversarial network (GAN), electronic jamming

中图分类号:

TP391.41

陈丽, 方梓涵, 梅立泉. 基于GAN的直扩信号生成算法[J]. 系统工程与电子技术, 2023, 45(5): 1544-1552.

Li CHEN, Zihan FANG, Liquan MEI. DSS signal generation algorithm based on GAN[J]. Systems Engineering and Electronics, 2023, 45(5): 1544-1552.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

参考文献 32

1	贾鑫, 朱卫纲, 曲卫, 等. 认知电子战概念及关键技术[J]. 装备学院学报, 2015, 26 (4): 96- 100.
	JIA X , ZHU W G , QU W , et al. Concept of cognitive electronic warfare and it's key technology[J]. Journal of Equipment Aca-demy, 2015, 26 (4): 96- 100.
2	李瑞. DJS欺骗干扰波形的快速生成技术研究[D]. 西安: 西安电子科技大学, 2014.
	LI R. Research on fast synthesizing the deception jamming based on DJS[D]. Xi'an: Xidian University, 2014.
3	AMURU S, BUEHRER R M. Optimal jamming using delayed learning[C]//Proc. of the IEEE Military Communications Conference, 2014: 1528-1533.
4	陶海红, 廖桂生, 王伶. 基于混合遗传算法的m序列波形优化设计[J]. 电波科学学报, 2004, 19 (3): 253- 257.
	TAO H H , LIAO G S , WANG L . Novel m-sequences waveform design using the hybrid genetic algorithm[J]. Chinese Journal of Radio Science, 2004, 19 (3): 253- 257.
5	刘永贵, 胡国平. 基于DRFM的遗传算法干扰技术研究[J]. 无线电工程, 2009, 39 (6): 31- 33.
	LIU Y G , HU G P . Research on DRFM jamming rechnology based on genetic algorithm[J]. Radio Engineering, 2009, 39 (6): 31- 33.
6	GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al. Generative adversarial nets[J]. Communications of the ACM, 2020, 63 (11): 139- 144. doi: 10.1145/3422622
7	王坤峰, 苟超, 段艳杰, 等. 生成式对抗网络GAN的研究进展与展望[J]. 自动化学报, 2017, 43 (3): 321- 332.
	WANG K F , GOU C , DUAN Y J , et al. Generative adversarial networks: the state of the art and beyond[J]. Acta Automatica Sinica, 2017, 43 (3): 321- 332.
8	梁俊杰, 韦舰晶, 蒋正锋. 生成对抗网络GAN综述[J]. 计算机科学与探索, 2020, 14 (1): 1- 17.
	LIANG J J , WEI J J , JIANG Z F . Generative adversarial networks GAN overview[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14 (1): 1- 17.
9	RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[C]//Proc. of the 4th International Conference on Learning Representations, 2016.
10	MIRZA M, OSINDERO S. Conditional generative adversarial nets[EB/OL]. [2022-02-01]. https://arxiv.org/abs/1411.1784.
11	CHEN X , DUAN Y , HOUTHOOFT R , et al. InfoGAN: interpretable representation learning by information maximizing generative adversarial nets[J]. Advances in Neural Information Processing Systems, 2016, 29 (1): 2180- 2188.
12	ODENA A, OLAH C, SHLENS J. Conditional image synthesis with auxiliary classifier GANs[C]//Proc. of the International Conference on Machine Learning, 2017: 2642-2651.
13	ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein generative adversarial networks[C]//Proc. of the International Conference on Machine Learning, 2017: 214-223.
14	PETZKA H, FISCHER A, LUKOVNICOV D. On the regularization of Wasserstein GANs[C]//Proc. of the 6th International Conference on Learning Representations, 2018.
15	KARRAS T, AILA T, LAINE S, et al. Progressive growing of GANs for improved quality, stability, and variation[C]//Proc. of the 6th International Conference on Learning Representations, 2018.
16	KARRAS T, LAINE S, AILA T. A style-based generator architecture for generative adversarial networks[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 4401-4410.
17	KARRAS T, LAINE S, AITTALA M, et al. Analyzing and improving the image quality of styleGAN[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 8110-8119.
18	CHOI Y, CHOI M, KIM M, et al. StarGAN: unified generative adversarial networks for multi-domain image-to-image translation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8789-8797.
19	CHOI Y, UH Y, YOO J, et al. StarGAN v2: diverse image synthesis for multiple domains[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 8188-8197.
20	DAUPHIN Y N , PASCANU R , GULCEHRE C , et al. Identifying and attacking the saddle point problem in high-dimensional non-convex optimization[J]. Advances in Neural Information Processing Systems, 2014, 27 (2): 2933- 2941.
21	QIAN N . On the momentum term in gradient descent learning algorithms[J]. Neural Networks, 1999, 12 (1): 145- 151.
22	NESTEROV Y . A method for unconstrained convex minimization problem with the rate of convergence O (1/k.2)[J]. Doklady an USSR, 1983, 269, 543- 547.
23	BENGIO Y, BOULANGER-LEWANDOWSKI N, PASCANU R. Advances in optimizing recurrent networks[C]//Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2013: 8624-8628.
24	KINGMA D P, BA J. Adam: a method for stochastic optimization[C]//Proc. of the 3rd International Conference for Learning Representations, 2015.
25	DUCHI J , HAZAN E , SINGER Y . Adaptive subgradient methods for online learning and stochastic optimization[J]. Journal of Machine Learning Research, 2011, 12 (7): 2121- 2159.
26	DEAN J , CORRADO G , MONGA R , et al. Large scale distributed deep networks[J]. Advances in Neural Information Processing Systems, 2012, 25 (1): 1- 11.
27	ZEILER M D. Adadelta: an adaptive learning rate method[EB/OL]. [2022-02-01]. https://arxiv.org/abs/1212.5701.
28	DOZAT T. Incorporating nesterov momentum into Adam[EB/OL]. [2022-02-01]. https://cs229.stanford.edu/proj2015/054_report.pdf.
29	REDDI S J, KALE S, KUMAR S. On the convergence of Adam and beyond[C]//Proc. of the International Conference on Learning Representations, 2018.
30	LOSHCHILOV I, HUTTER F. Decoupled weight decay regu-larization[C]//Proc. of the International Conference on Learning Representations, 2018.
31	MA J, YARATS D. Quasi-hyperbolic momentum and Adam for deep learning[C]//Proc. of the 7th International Conference on Learning Representations, 2019.
32	LUCAS J, SUN S Y, ZEMEL R, et al. Aggregated momentum: stability through passive damping[C]//Proc. of the 8th International Conference on Learning Representations, 2018.

[1]	刘戎翔, 吴琳, 谢智歌, 刘虹麟. 基于生成对抗网络的防空体系态势辅助分析[J]. 系统工程与电子技术, 2022, 44(8): 2522-2529.
[2]	徐平亮, 崔亚奇, 熊伟, 熊振宇, 顾祥岐. 生成式中断航迹接续关联方法[J]. 系统工程与电子技术, 2022, 44(5): 1543-1552.
[3]	王峰毅, 肖志斌, 李蓬蓬, 张可, 倪少杰. 基于载波相位的接收机群时延测量技术[J]. 系统工程与电子技术, 2022, 44(4): 1078-1084.
[4]	曹鹏宇, 杨承志, 石礼盟, 吴宏超. 基于PSO-DBSCAN和SCGAN的未知雷达信号处理方法[J]. 系统工程与电子技术, 2022, 44(4): 1158-1165.
[5]	邵凯, 朱苗苗, 王光宇. 基于生成对抗与卷积神经网络的调制识别方法[J]. 系统工程与电子技术, 2022, 44(3): 1036-1043.
[6]	曹鹏宇, 杨承志, 石礼盟, 吴宏超. 基于DAE-GAN网络的LPI雷达信号增强[J]. 系统工程与电子技术, 2021, 43(9): 2493-2500.
[7]	赵凡, 金虎. 基于GAN的通信干扰波形生成技术[J]. 系统工程与电子技术, 2021, 43(4): 1080-1088.
[8]	田相轩, 石志强. 基于改进型生成对抗网络的指挥信息系统模拟数据生成算法[J]. 系统工程与电子技术, 2021, 43(1): 163-170.
[9]	向南, 张雄涛, 豆亚杰, 徐向前, 杨克巍, 谭跃进. 基于生成对抗网络的高端装备研制数据脱敏方法[J]. 系统工程与电子技术, 2020, 42(6): 1310-1316.
[10]	张丹娜, 钱锋, 冯辉, 闻年成. Walsh码软扩频信号降噪算法[J]. 系统工程与电子技术, 2020, 42(4): 773-780.
[11]	殷小静, 胡晓峰, 刘戎翔, 谢智歌, 马骏. 基于GAN的体系能力图谱生成方法[J]. 系统工程与电子技术, 2020, 42(10): 2257-2264.
[12]	朱克凡, 王杰贵. 小样本条件下SCGAN+CNN低分辨雷达目标一步识别算法[J]. 系统工程与电子技术, 2020, 42(1): 67-75.
[13]	郝云飞, 刘章孟, 郭福成, 张敏. 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.
[14]	沙志超，吴海斌，任啸天，黄知涛，周一宇. 非合作直扩信号检测中的相关函数二阶矩方法[J]. Journal of Systems Engineering and Electronics, 2013, 35(8): 1602-1606.
[15]	付昭旺, 于雷, 寇英信, 徐安. 混合编队协同空战电子支援干扰功率分配方法[J]. Journal of Systems Engineering and Electronics, 2012, 34(6): 1171-1175.