基于BiGRU的水下可见光通信调制格式识别研究  

Research on Modulation Format Recognition for Underwater Visible Light Communication based on BiGRU

作　　者：高文笛 汪昀楷 徐迟[1,2,3] 徐增熠 迟楠 GAO Wendi;WANG Yunkai;XU Chi;XU Zengyi;CHI Nan(The Ministry of Education Key Laboratory of Electromagnetic Wave Information Science,Department of Communication Science and Engineering,Fudan University,Shanghai 200433,China;Shanghai Engineering Research Center of Low-Earth-Orbit Satellite Communication and Applications,Shanghai 200433,China;Shanghai Collaborative Innovation Center of Low-Earth-Orbit Satellite Communication Technology,Shanghai 200433,China)

机构地区：[1]复旦大学通信科学与工程系电磁波信息科学教育部重点实验室,上海200433 [2]上海低轨卫星通信与应用工程技术研究中心,上海200433 [3]上海市低轨卫星通信技术协同创新中心,上海200433

出　　处：《光通信研究》2025年第2期26-32,共7页Study on Optical Communications

基　　金：国家重点研发计划资助项目(2022YFB2802803);国家自然科学基金资助项目(61925104,62031011)。

摘　　要：【目的】水下可见光通信(UVLC)作为替代传统声波通信的前沿技术,以其高速率、大带宽、低延迟和高安全性获得了广泛关注,但同时也面临着水下信道环境复杂、信号功率衰减和光电器件不理想等因素导致的非线性效应等挑战。这些低信噪比(SNR)和非线性效应引起的信号劣化,会导致接收端难以正确识别并解调出原信号,而正确识别出信号调制格式才能为后续使用其他算法,如非线性补偿和频率偏移补偿,来提升通信性能打下基础。文章旨在解决UVLC系统中调制格式识别(MFR)的性能限制问题,特别关注在复杂水下环境中提高识别准确率和系统鲁棒性。【方法】针对以上问题,文章提出了一种结合双向门控循环单元(BiGRU)和坐标变换的创新MFR算法。文章所提算法充分利用BiGRU在时序数据处理上的优势和坐标变换的高效性,有效提取信号特征,显著提高了在水下环境中MFR的准确性。【结果】实验结果显示,在不同发射电压条件下,该算法对2正交振幅调制(QAM)、4QAM、8QAM、8幅度相移键控(APSK)、16QAM、16APSK、32QAM、32APSK、64QAM和64APSK共10种QAM和APSK信号调制格式的识别准确率均超过96%,训练速度提高了1倍,并且在低SNR和非线性失真环境下鲁棒性显著。【结论】文章所提算法显著提升了UVLC系统在复杂水下环境中的MFR性能,具有重要的应用价值和技术创新点,为未来水下高速通信技术的发展奠定了基础。【Objective】Underwater Visible Light Communication(UVLC),as a cutting-edge technology replacing traditional acoustic communication,has garnered widespread attention due to its high data rates,broad bandwidth,low latency,and enhanced security.However,it also faces challenges such as the complexity of underwater channel environments,signal power attenuation,and the imperfections of optoelectronic devices leading to nonlinear effects.The signal degradation caused by these low Signal-to-Noise Ratio(SNR)and nonlinear effects can make it difficult for the receiving end to correctly identify and demodulate the original signal.However,accurately identifying the signal modulation format lays the foundation for subsequent use of other agorithms,such as nonlinear compensation and frequency offset compensation,to enhance communication performance.Hence,this study aims to address the performance limitations in Modulation Format Recognition(MFR)within UVLC systems,with a special focus on improving recognition accuracy and system robustness in complex underwater environments.【Methods】To address these issues,we propose an innovative MFR algorithm that combines Bidirectional Gated Recurrent Units(BiGRU)with coordinate transformation.This algorithm leverages the advantages of BiGRU in sequential data processing and the efficiency of coordinate transformation to effectively extract the signal features,significantly enhancing the modulation format recognition accuracy in underwater environments.【Results】Experimental results demonstrate that under various transmission voltage conditions,the algorithm achieves recognition accuracy rates exceeding 96%for ten different Quadrature Amplitude Modulation(QAM)and Amplitude Phase Shift Keying(APSK)signal modulation formats,including 2QAM,4QAM,8QAM,8APSK,16QAM,16APSK,32QAM,32APSK,64QAM and 64APSK.The training speed has doubled,and robustness in low SNR and nonlinear distortion conditions is significantly improved.【Conclusion】The algorithm proposed in this study notably enhances

关 键 词：水下可见光通信 调制格式识别 双向门控循环单元 非线性失真 信号特征提取 

分 类 号：TN929[电子电信—通信与信息系统]