基于DiffBIR模型宽带信号盲检测性能优化

曹文强; 陈雅蓉; 朱锐; 张红; 韩丁

doi:10.13756/j.gtxyj.2026.240104

您当前的位置：

首页 >

文章列表页 >

基于DiffBIR模型宽带信号盲检测性能优化

光通信系统与网络技术 | 更新时间：2026-03-03

- 基于DiffBIR模型宽带信号盲检测性能优化
- Broadband Signal Blind Detection Performance Optimization based on DiffBIR Model
- 光通信研究 2026年第1期
- 作者机构：
  
  1.西京学院　电子信息学院，西安　 710123
  2.联勤保障部队第五工程代建管理办公室，武汉　 430000
- 作者简介：
  
  曹文强，助教。E-mail：2234134078@qq.com
- 基金信息：
  
  西京学院科研基金(200105)
- DOI：10.13756/j.gtxyj.2026.240104
  中图分类号： TN929
- 收稿：2024-05-30，
  
  修回：2024-07-22，
  
  纸质出版：2026-02-10
- 稿件说明：
移动端阅览
曹文强，陈雅蓉，朱锐，等. 基于DiffBIR模型宽带信号盲检测性能优化[J]. 光通信研究，2026(1): 240104.

Cao W Q, Chen Y R, Zhu R, et al. Broadband Signal Blind Detection Performance Optimization based on DiffBIR Model[J]. Study on Optical Communications, 2026(1): 240104.
曹文强，陈雅蓉，朱锐，等. 基于DiffBIR模型宽带信号盲检测性能优化[J]. 光通信研究，2026(1): 240104. DOI： 10.13756/j.gtxyj.2026.240104.

Cao W Q, Chen Y R, Zhu R, et al. Broadband Signal Blind Detection Performance Optimization based on DiffBIR Model[J]. Study on Optical Communications, 2026(1): 240104. DOI： 10.13756/j.gtxyj.2026.240104.

摘要

目的

针对低信噪比（SNR）环境下非合作通信宽带信号盲检测效果不佳的问题，文章旨在通过创新预处理策略提升信号检测性能，确保复杂电磁环境中通信的可靠性与稳定性。

方法

文章提出了一种新颖的信号预处理与检测框架，其核心在于运用生成扩散先验的图像盲恢复（DiffBIR）模型。DiffBIR模型是一种集成了去噪、去模糊及超分辨率技术的先进图像处理方法，经文献检索确认，该模型在宽带接收信号时频图优化中的应用尚未见公开报道，具有创新性。具体实施中，先借助Diff-BIR模型处理增强信号时频特征，随后利用Matlab平台集成的连通组件分析算法进行精细化信号检测，以期在低SNR场景下实现更精准的信号识别。

结果

实验结果显示，该方案在-15~-25 dB的低SNR测试条件下，相较于传统未优化方法，检测精确率提升了133%，召回率增加了32%，且综合评价指标F1分数也实现了139%的增长。这些数据明确反映出，经过DiffBIR模型预处理后的信号在保持高召回的同时，显著提高了检测的精确性。

结论

文章成功构建了一套基于DiffBIR模型的宽带信号盲检测技术体系，有效克服了低SNR环境下信号检测的挑战。该技术不仅极大增强了信号的可检测性和识别精度，还在实践中展示了其应用于复杂电磁环境的潜力，为军事及民用通信系统的信号处理提供了新的理论基础和技术途径，具有重要的理论价值和实践意义。

Abstract

Objective

Aiming at the problem of poor blind detection effect of non-cooperative broadband signal in low Signal-to-Noise Ratio (SNR) environment

this study aims to improve signal detection performance through innovative preprocessing strategies to ensure communication reliability and stability in complex electromagnetic environment.

Methods

A novel signal preprocessing and detection framework is proposed

the core of which is the Blind Image Restoration with Generative Diffusion Prior (DiffBIR) model. DiffBIR model is an advanced image processing method which integrates de-noising

de-blurring and super-resolution techniques.A literature review confirms that the application of this model in the optimization of time-frequency graphs for wideband received signals has not been publicly reported

making it innovative. In the specific implementation

DiffBIR processing is first used to enhance the signal time-frequency characteristics. Then the connected component analysis algorithm integrated with Matlab platform is used to fine signal detection

in order to achieve more accurate signal recognition in the low SNR scenario.

Results

Experimental verification showed that under the low SNR test conditions of-15~-25 dB

compared with the traditional non-optimized method

the detection accuracy rate was increased by 133%

the recall rate was increased by 32%

and the F1 score of the comprehensive evaluation index was also increased by 139%. These data clearly reflect that DiffBIR pretreated signals can significantly improve detection accuracy while maintaining high recall.

Conclusion

In this study

a set of broadband signal blind detection technology system based on DiffBIR model is successfully constructed

which effectively overcomes the challenge of signal detection in low SNR environment. This technology not only greatly enhances the detectability and identification accuracy of signals

but also shows its potential application in complex electromagnetic environment in practice. It provides a new theoretical basis and technical approach for signal processing of military and civil communication systems

and has important theoretical value and practical significance.

关键词

Keywords

references

苏志刚 , 晏翔 , 韩冰 , 等 . 低信噪比条件下无人机射频信号实时检测方法 [J ] . 信号处理 , 2023 , 39 ( 5 ): 919 - 928 .

Su Z G , Yan X , Han B , et al . A Real Time Drone RF Signal Detection Method under Low SNR Condition [J ] . Journal of Signal Processing , 2023 , 39 ( 5 ): 919 - 928 .

云超 , 郑腾 , 蒋攀攀 , 等 . 军事通信抗干扰能力现状及发展建议 [J ] . 中国电子科学研究院学报 , 2022 , 17 ( 8 ): 801 - 808 .

Yun C , Zheng T , Jiang P P , et al . Construction Status and Development Trend of Military Communications Anti-Jamming Technology [J ] . Journal of China Academy of Electronics and Information Technology , 2022 , 17 ( 8 ): 801 - 808 .

张凯 , 刘义 , 李运宏 , 等 . 分布式接收宽带多目标信号盲检测迭代处理方法 [J ] . 海军航空大学学报 , 2024 , 39 ( 1 ): 173 - 181 .

Zhang K , Liu Y , Li Y H , et al . Iterative Blind Detection Algorithm for Wideband Multi-Target Signals in Distributed Receiving Systems [J ] . Journal of Naval Aviation University , 2024 , 39 ( 1 ): 173 - 181 .

樊峰菊 , 张建勇 , 宋义梅 , 等 . 大规模检测算法在光通信系统中的研究 [J ] . 光通信研究 , 2022 ( 5 ): 12 - 17 .

Fan F J , Zhang J Y , Song Y M , et al . The Research of Massive Multiple Input Multiple Output Detection Algorithms in Optical Fiber Communication System [J ] . Study on Optical Communications , 2022 ( 5 ): 12 - 17 .

石磊 , 涂兴华 , 单正友 , 等 . 基于边缘滤波法检测的光纤光栅声波传感研究 [J ] . 光通信研究 , 2023 ( 2 ): 40 - 44 .

Shi L , Tu X H , Shan Z Y , et al . Research on Acoustic Sensing of Fiber Bragg Grating based on Edge Filter Detection [J ] . Study on Optical Communications , 2023 ( 2 ): 40 - 44 .

刘正平 . 基于噪声分布特性的脉冲信号自适应门限检测 [J ] . 电讯技术 , 2018 , 58 ( 10 ): 1212 - 1216 .

Liu Z P . Adaptive Threshold Detection of Pulse Signal based on Noise Distribution Characteristics [J ] . Telecommunication Engineering , 2018 , 58 ( 10 ): 1212 - 1216 .

张晓华 , 彭小 , 黄龙 . 大规模MIMO系统混合线性迭代信号检测算法 [J ] . 光通信研究 , 2022 ( 2 ): 56 - 60 .

Zhang X H , Peng X , Huang L . Hybrid Linear Iterative Signal Detection Algorithm for Massive MIMO Systems [J ] . Study on Optical Communications , 2022 ( 2 ): 56 - 60 .

安宁 . 全光通信网络非线性突变频率干扰检测算法 [J ] . 光通信研究 , 2024 ( 3 ): 56 - 60 .

An N . Nonlinear Mutation Frequency Interference Detection Algorithm for all Optical Communication Networks [J ] . Study on Optical Communications , 2024 ( 3 ): 56 - 60 .

孙思燕 , 张伟雄 , 唐娉 , 等 . 基于小波阈值去噪与时频图像检测的信号调制识别技术 [J ] . 无线电工程 , 2024 , 54 ( 1 ): 78 - 88 .

Sun S Y , Zhang W X , Tang P , et al . Signal Modulation Recognition based on Wavelet Threshold Denoising and Time-Frequency Image Detection [J ] . Radio Engineering , 2024 , 54 ( 1 ): 78 - 88 .

靳瑞哲 , 迟楠 . 基于机器学习的调制格式识别算法研究 [J ] . 光通信研究 , 2022 ( 6 ): 9 - 15 .

Jin R Z , Chi N . Research on Modulation Format Recognition Algorithm based on Machine Learning [J ] . Study on Optical Communications , 2022 ( 6 ): 9 - 15 .

Keawin C , Innok A , Uthansakul P . Optimization of Signal Detection Using Deep CNN in Ultra-Massive MIMO [J ] . Telecom , 2024 , 5 ( 2 ): 280 - 295 .

Ahammed M F , Molla A A , Kadir R , et al . Deep Bidirectional LSTM for the Signal Detection of Universal Filtered Multicarrier Systems [J ] . Machine Learning with Applications , 2022 , 10 : 100425 .

Cheng W , Zhang Q , Lu W , et al . An Efficient Digital Channelized Receiver for Low SNR and Wideband Chirp Signals Detection [J ] . Applied Sciences , 2023 , 13 ( 5 ): 3080 .

刘泽润 , 尹宇飞 , 薛文灏 , 等 . 基于扩散模型的条件引导图像生成综述 [J ] . 浙江大学学报(理学版) , 2023 , 50 ( 6 ): 651 - 667 .

Liu Z R , Yin Y F , Xue W H , et al . A Review of Conditional Image Generation based on Diffusion Models [J ] . Journal of Zhejiang University (Science Edition) , 2023 , 50 ( 6 ): 651 - 667 .

Lin X , He J , Chen Z , et al . DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior [EB/OL ] . ( 2024-04-12 ) [ 2024-06-15 ] . https://arxiv.org/html/2308.15070v3 https://arxiv.org/html/2308.15070v3 .

马飞 , 王梓璇 , 刘思雨 . 基于深度图像先验的高光谱图像去噪方法 [J ] . 激光技术 , 2024 , 48 ( 3 ): 379 - 386 .

Ma F , Wang Z X , Liu S Y . Hyperspectral Image Denoising Method based on Depth Image Prior [J ] . Laser Technology , 2024 , 48 ( 3 ): 379 - 386 .

张伟 , 张俊杰 , 宋杰 , 等 . 基于改进SwinIR的条纹图去噪方法 [J ] . 电子测量技术 , 2023 , 46 ( 23 ): 105 - 111 .

Zhang W , Zhang J J , Song J , et al . Fringe Pattern Denoising Method based on Improved SwinIR [J ] . Electronic Measurement Technology , 2023 , 46 ( 23 ): 105 - 111 .

董章华 , 赵士杰 , 赖莉 . 一种基于Swin Transformer神经网络的低截获概率雷达信号调制类型的识别方法 [J ] . 四川大学学报(自然科学版) , 2023 , 60 ( 2 ): 42 - 48 .

Dong Z H , Zhao S J , Lai L . A Radar Signal Modulation Type Recognition Method based on Swin Transformer Neural Network [J ] . Journal of Sichuan University (Natural Science Edition) , 2023 , 60 ( 2 ): 42 - 48 .

Chai W . AI Animation: Principle and Creative Practice of the Stable Diffusion Model [C ] // ICIDC 2023: Proceedings of the 2nd International Conference on Information Economy, Data Modeling and Cloud Computing . Nanchang, China : European Alliance for Innovation , 2023 : 2334612 .

张文雪 , 罗一涵 , 刘雅卿 , 等 . 基于主动位移成像的图像超分辨率重建 [J ] . 光电工程 , 2024 , 51 ( 1 ): 73 - 92 .

Zhang W X , Luo Y H , Liu Y Q , et al . Image Super-resolution Reconstruction based on Active Displacement Imaging [J ] . Opto-Electronic Engineering , 2024 , 51 ( 1 ): 73 - 92 .

龚智贞 , 贾克斌 , 孙中华 , 等 . 宽带环境下Morse信号自动检测 [J ] . 信号处理 , 2017 , 33 ( 8 ): 1097 - 1103 .

Gong Z Z , Jia K B , Sun Z H , et al . Automatic Detection of Morse Signals in Wide Band Environment [J ] . Journal of Signal Processing , 2017 , 33 ( 8 ): 1097 - 1103 .

贺锋涛 , 王乐莹 , 王晓波 , 等 . 基于改进的AdaBoost无线光通信信号检测算法 [J ] . 激光技术 , 2023 , 47 ( 5 ): 659 - 665 .

He F T , Wang L Y , Wang X B , et al . Signal Detection Algorithm of Wireless Optical Communication based on the Improved AdaBoost [J ] . Laser Technology , 2023 , 47 ( 5 ): 659 - 665 .

孟凡杰 , 唐宏 , 王义哲 , 等 . 基于时频图像纹理特征的雷达辐射源信号识别 [J ] . 弹箭与制导学报 , 2017 , 37 ( 3 ): 152 - 156 .

Meng F J , Tang H , Wang Y Z , et al . Radar Emitter Signal Recognition based on Texture Feature of Time-Frequency Image [J ] . Journal of Projectiles, Rockets, Missiles and Guidance , 2017 , 37 ( 3 ): 152 - 156 .

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

OTDR系统中基于改进FOX算法的小波去噪方法

FSO通信系统中应用机器学习算法的研究进展

面向电力通信的Delta-sigma调制高可靠传输研究

大规模MIMO系统混合线性迭代信号检测算法

MIMO中基于预处理的广义加权Gauss-Seide算法