基于注意力机制优化的生成对抗网络及其在海杂波模拟中的应用

张苏恺; 陈鹏; 董紫颖; 王威

doi:10.12263/DZXB.20250475

您当前的位置：

首页 >

文章列表页 >

基于注意力机制优化的生成对抗网络及其在海杂波模拟中的应用

学术论文 | 更新时间：2025-12-27

- 基于注意力机制优化的生成对抗网络及其在海杂波模拟中的应用
- Attention Mechanism Optimized Generative Adversarial Networks and Their Application in Sea Clutter Simulation
- 电子学报 2025年53卷第9期页码：3345-3357
- 作者机构：
  
  长安大学信息工程学院，陕西西安 710064
- 作者简介：
  
  [ "张苏恺男，2001年8月出生于广东省深圳市.现为长安大学硕士研究生.主要研究方向为雷达杂波智能生成.E-mail: 2023124114@chd.edu.cn" ]
  [ "陈鹏男，1992年4月出生于安徽省合肥市.博士，硕士生导师.现为长安大学信息工程学院副教授.主要研究方向为多模信道传播与定位技术.E-mail: pchen@chd.edu.cn" ]
  [ "董紫颖女，2002年12月出生于湖北省武汉市.现为长安大学硕士研究生.主要研究方向为基于FMCW毫米波的无人机空对地雷达感知信道测量、分析与建模.E-mail: 2024124026@chd.edu.cn" ]
  [ "王威男，1981年9月出生于湖北省荆门市.博士，博士生导师.现为长安大学信息工程学院教授.主要研究方向为无线电信道传播与建模、通信感知一体化技术.E-mail: wei.wang@chd.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62341133);长安大学青年学者学科交叉团队建设项目(3001042400922);长安大学中央高校基本科研业务费专项资金(300102244203;300102243401)
- DOI：10.12263/DZXB.20250475
  中图分类号： TP391;
- 收稿：2025-06-05，
  
  录用：2025-09-09，
  
  纸质出版：2025-09-25
- 稿件说明：
移动端阅览
张苏恺, 陈鹏, 董紫颖, 等. 基于注意力机制优化的生成对抗网络及其在海杂波模拟中的应用[J]. 电子学报, 2025, 53(09): 3345-3357.

ZHANG Su-kai, CHEN Peng, DONG Zi-ying, et al. Attention Mechanism Optimized Generative Adversarial Networks and Their Application in Sea Clutter Simulation[J]. Acta Electronica Sinica, 2025, 53(09): 3345-3357.
张苏恺, 陈鹏, 董紫颖, 等. 基于注意力机制优化的生成对抗网络及其在海杂波模拟中的应用[J]. 电子学报, 2025, 53(09): 3345-3357. DOI：10.12263/DZXB.20250475

ZHANG Su-kai, CHEN Peng, DONG Zi-ying, et al. Attention Mechanism Optimized Generative Adversarial Networks and Their Application in Sea Clutter Simulation[J]. Acta Electronica Sinica, 2025, 53(09): 3345-3357. DOI：10.12263/DZXB.20250475

摘要

针对在复杂海况下，雷达海杂波模拟所面临的全局特征建模不足、多模态生成能力受限以及评估体系单一等挑战，本文提出了一种基于多头自注意力机制增强的高保真生成对抗网络（Self-Attention HIgh FIdelity Generative Adversarial Network，SA-HIFIGAN）.该模型在生成器与判别器中嵌入了多头自注意力模块，以增强对海杂波长程时空相关性的建模能力，并设计了具有分类功能的多尺度与多周期判别器结构.同时，本文构建了一个融合分布相似性、频谱误差和统计稳定性的混合评估体系，实现了对生成杂波的多维质量控制.通过采用X波段雷达实测数据集进行实验，验证了模型在幅度概率密度、功率谱密度和时空相关性等指标上的有效性.实验结果显示，SA-HIFIGAN在上述指标上与实测数据高度吻合，不仅能根据海况等级生成对应特性的杂波数据，还在综合评分上优于深度卷积生成对抗网络（Deep Convolutional Generative Adversarial Network，DCGAN）和变分自编码器（Variational Auto-Encoder，VAE）等现有的杂波生成方法.

Abstract

To address the challenges in radar sea clutter simulation under complex sea conditions

including insufficient global feature modeling

limited multimodal generation capability

and a simplistic evaluation system

this paper proposes a generative adversarial network enhanced by multi-head self-attention mechanisms self-attention high-fidelity generative adversarial network (SA-HIFIGAN). The model incorporates multi-head self-attention modules in both the generator and discriminator to strengthen the modeling of long-range spatiotemporal correlations in sea clutter. Additionally

a multi-scale and multi-period discriminator structure with classification functionality is designed. Furthermore

this paper constructs a hybrid evaluation system integrating distribution similarity

spectral error

and statistical stability

achieving multidimensional quality control for generated clutter. Experiments conducted using X-band radar field-measured datasets validate the model’s effectiveness in metrics such as amplitude probability density

power spectral density

and spatiotemporal correlation. The results demonstrate that SA-HIFIGAN achieves high consistency with measured data across these metrics. Not only can it generate clutter data with characteristics corresponding to sea state levels

but it also outperforms existing clutter generation methods like deep convolutional generative adversarial network (DCGAN) and variational auto-encoder (VAE) in comprehensive scoring.

关键词

Keywords

references

SKOLNIK M I . Radar Handbook [M ] . New York : McGraw-Hill , 1970 .

GU T C . Detection of small floating targets on the sea surface based on multi-features and principal component analysis [J ] . IEEE Geoscience and Remote Sensing Letters , 2020 , 17 ( 5 ): 809 - 813 .

CAO X W , CHENG Y Q , WU H , et al . Nonstationary moving target detection in spiky sea clutter via time-frequency manifold [J ] . IEEE Geoscience and Remote Sensing Letters , 2022 , 19 : 3510505 .

ZHAO P , WU Z S , ZHANG Y S , et al . Analysis of the influencing factors on S-band sea spikes [J ] . Electronics , 2022 , 11 ( 24 ): 4225 .

HUANG P H , ZOU Z H , XIA X G , et al . Multichannel sea clutter modeling for spaceborne early warning radar and clutter suppression performance analysis [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2021 , 59 ( 10 ): 8349 - 8366 .

ZHANG J P , ZHANG Y S , XU X Y , et al . Estimation of sea clutter inherent Doppler spectrum from shipborne S-band radar sea echo [J ] . Chinese Physics B , 2020 , 29 ( 6 ): 068402 .

GREGERS-HANSEN V , MITAL R . An empirical sea clutter model for low grazing angles [C ] // 2009 IEEE Radar Conference . Piscataway : IEEE , 2009 : 1 - 5 .

RODRIGUEZ E . Beyond the Kirchhoff approximation [J ] . Radio Science , 1989 , 24 ( 5 ): 681 - 693 .

SOTO-CRESPO J M , NIETO-VESPERINAS M , FRIBERG A T . Scattering from slightly rough random surfaces: A detailed study on the validity of the small perturbation method [J ] . Journal of the Optical Society of America A , 1990 , 7 ( 7 ): 1185 - 1201 .

VORONOVICH A . Small-slope approximation for electromagnetic wave scattering at a rough interface of two dielectric half-spaces [J ] . Waves in Random Media , 1994 , 4 ( 3 ): 337 - 367 .

AWADA A , AYARI M Y , KHENCHAF A , et al . Bistatic scattering from an anisotropic sea surface: Numerical comparison between the first-order SSA and the TSM models [J ] . Waves in Random and Complex Media , 2006 , 16 ( 3 ): 383 - 394 .

KERR D E . Propagation of Short Radio Waves [M ] . New York : McGraw-Hill , 1951 .

LI G , YU K B . Modelling and simulation of coherent Weibull clutter [J ] . IEE Proceedings F Radar and Signal Processing , 1989 , 136 ( 1 ): 2 .

JAKEMAN E , PUSEY P . A model for non-Rayleigh sea echo [J ] . IEEE Transactions on Antennas and Propagation , 1976 , 24 ( 6 ): 806 - 814 .

ARNOLD B C . Pareto distribution [EB/OL ] . ( 2015-09-16 )[ 2025-05-25 ] . https://doi.org/10.1002/9781118445112.stat01100.pub2 https://doi.org/10.1002/9781118445112.stat01100.pub2 .

MARIER L J . Correlated K-distributed clutter generation for radar detection and track [J ] . IEEE Transactions on Aerospace and Electronic Systems , 1995 , 31 ( 2 ): 568 - 580 .

VAN DEN OORD A , DIELEMAN S , ZEN H , et al . Wavenet: A generative model for raw audio [EB/OL ] . ( 2016-12 )[ 2025-05-25 ] . https://www.academia.edu/41680066/WAVENET_A_GENERATIVE_MODEL_FOR_RAW_AUDIO https://www.academia.edu/41680066/WAVENET_A_GENERATIVE_MODEL_FOR_RAW_AUDIO .

DONAHUE C , MCAULEY J , PUCKETTE M . Adversarial audio synthesis [EB/OL ] . ( 2019-02-09 )[ 2025-09-02 ] . https://arxiv.org/abs/1802.04208 https://arxiv.org/abs/1802.04208 .

YAMAMOTO R , SONG E , KIM J M . Parallel wavegan: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram [C ] // ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2020 : 6199 - 6203 .

KONG J , KIM J , BAE J . HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis [C ] // The 34th Conference on Neural Information Processing Systems . New York : ACM , 2020 : 17022 - 17033 .

丁斌 , 夏雪 , 梁雪峰 . 基于深度生成对抗网络的海杂波数据增强方法 [J ] . 电子与信息学报 , 2021 , 43 ( 7 ): 1985 - 1991 .

DING B , XIA X , LIANG X F . Sea clutter data augmentation method based on deep generative adversarial network [J ] . Journal of Electronics & Information Technology , 2021 , 43 ( 7 ): 1985 - 1991 . (in Chinese)

施祖帅 . 基于深度学习的雷达杂波模拟技术研究 [D ] . 成都 : 电子科技大学 , 2021 .

SHI Z S . Research on Radar Clutter Simulation Technology Based on Deep Learning [D ] . Chengdu : University of Electronic Science and Technology of China , 2021 . (in Chinese)

马鑫 . 基于深度生成学习的雷达杂波模拟技术研究 [D ] . 成都 : 电子科技大学 , 2022 .

MA X . Radar Clutter Simulation Based on Deep Generative Learning [D ] . Chengdu : University of Electronic Science and Technology of China , 2022 . (in Chinese)

ZHANG X X , WANG Z F , LU K , et al . Data augmentation and classification of sea land clutter for over-the-horizon radar using AC-VAEGAN [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2023 , 61 : 5104416 .

DENG X Y , HUI B W , HAN X , et al . A method for generating sea clutter data based on variational autoencoder [C ] // 2024 9th International Conference on Signal and Image Processing . Piscataway : IEEE , 2024 : 54 - 61 .

SALIMANS T , GOODFELLOW I , ZAREMBA W , et al . Improved techniques for training GANs [C ] // Proceedings of the 30th International Conference on Neural Information Processing Systems . New York : ACM , 2016 : 2234 - 2242 .

CHE T , LI Y R , JACOB A P , et al . Mode regularized generative adversarial networks [EB/OL ] . ( 2017-03-02 )[ 2025-09-01 ] . https://arxiv.org/abs/1612.02136 https://arxiv.org/abs/1612.02136 .

HEUSEL M , RAMSAUER H , UNTERTHINER T , et al . GANs trained by a two time-scale update rule converge to a local Nash equilibrium [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . New York : ACM , 2017 : 6629 - 6640 .

DZIUGAITE G K , ROY D M , GHAHRAMANI Z . Training generative neural networks via maximum mean discrepancy optimization [C ] // Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence . New York : ACM , 2015 : 258 - 267 .

ZHANG H , GOODFELLOW I , METAXAS D , et al . Self-attention generative adversarial networks [C ] // Proceedings of the 36th International Conference on Machine Learning . Cambridge : PMLR , 2019 : 7354 - 7363 .

KUMAR K , KUMAR R , DE BOISSIERE T , et al . MelGAN: Generative adversarial networks for conditional waveform synthesis [C ] // 33rd Conference on Neural Information Processing Systems . New York : ACM , 2019 : 32 .

刘宁波 , 董云龙 , 王国庆 , 等 . X波段雷达对海探测试验与数据获取 [J ] . 雷达学报 , 2019 , 8 ( 5 ): 656 - 667 .

LIU N B , DONG Y L , WANG G Q , et al . X-band radar sea detection test and data acquisition [J ] . Journal of Radars , 2019 , 8 ( 5 ): 656 - 667 . (in Chinese) .

丁昊 , 刘宁波 , 董云龙 , 等 . 雷达海杂波测量试验回顾与展望 [J ] . 雷达学报 , 2019 , 8 ( 3 ): 281 - 302 .

DING H , LIU N B , DONG Y L , et al . Overview and prospects of radar sea clutter measurement experiments [J ] . Journal of Radars , 2019 , 8 ( 3 ): 281 - 302 . (in Chinese)

XIA F , LIU J Y , NIE H S , et al . Random walks: A review of algorithms and applications [J ] . IEEE Transactions on Emerging Topics in Computational Intelligence , 2020 , 4 ( 2 ): 95 - 107 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

应试心理状态增强的学生表现预测模型

天波超视距雷达地海杂波图像增强与检测器设计

基于最小熵准则与生成对抗网络的SAR三维转动舰船目标重聚焦方法

基于方面级情感分析的深度语义挖掘模型