基于双分支神经网络的水声通信调制识别方法OA
Underwater Acoustic Communication Modulation Recognition Based on Dual-Branch Neural Networks
水声通信信号调制识别是信号截获处理的关键,近年来,结合时频特征与神经网络的识别方法受到关注.为解决传统调制识别方法在跨噪声分布时泛化能力不足,以及单一特征易导致相近类别混淆的问题,提出一种基于双分支神经网络的水声通信调制识别方法.以原始信号波形作为输入,同时构建预训练音频编码分支与谱特征分支,且进一步设计了基于静态融合引导的自适应决策融合策略,对 2 条分支的判别结果进行联合优化.实验结果表明,在包含未知噪声类型的测试条件下,相较于性能最优的传统时频图方法,模型平均识别准确率提升 13%;同时,模型对相近调制类别的区分能力得到增强,其中 QPSK 被误判为 BPSK 的比例由18.4%降至 5.0%,有效缓解了相近类别之间的混淆.
Modulation recognition of underwater acoustic communication signals is a key task in signal interception processing.In recent years,recognition methods combining time-frequency features with neural networks have attracted considerable attention.To address the insufficient generalization ability of conventional modulation recognition methods under cross-noise-distribution conditions and the confusion between similar modulation classes caused by single-feature representation,an underwater acoustic communication modulation recognition method based on a dual-branch neural network is proposed in this paper.Taking the raw signal waveform as input,the proposed method constructs a pre-trained audio encoder branch and a spectral feature branch,and further designs an adaptive decision fusion strategy guided by static fusion to jointly optimize the decisions of the two branches.Experimental results show that,under test conditions involving unseen noise types,the proposed method improves the average recognition accuracy by 13%compared with the best-performing traditional spectrogram-based method.Meanwhile,the discrimination ability for similar modulation classes is enhanced,with the proportion of QPSK samples misclassified as BPSK reduced from 18.4%to 5.0%,effectively alleviating confusion among similar categories.
黄子浩;满晓云;王劭婷;王晓燕;安良
东南大学 水声信号处理教育部重点实验室,江苏 南京 210096中国船舶集团有限公司第七〇五研究所,云南 昆明 650033中国船舶集团有限公司第七〇五研究所,云南 昆明 650033东南大学 水声信号处理教育部重点实验室,江苏 南京 210096东南大学 水声信号处理教育部重点实验室,江苏 南京 210096
信息技术与安全科学
水声通信信号调制识别双分支神经网络预训练音频编码器决策融合
underwater acoustic communication signalmodulation recognitiondual-branch neural networkpre-trained audio encoderdecision fusion
《数字海洋与水下攻防》 2026 (3)
257-267,11
中央高校基本科研业务费专项资金资助(2242025F20003).
评论