水声通信信号识别为水声通信侦察和对抗的重要前提，具有重要作用。然而，传统的水声通信信号识别方法通常是基于信号处理和模式识别技术，依赖领域专家的专业知识和经验进行特征选择和提取，具有较强的主观性，且可能无法利用更复杂的信号特征。本文基于深度学习提出一种水声通信信号识别的智能方法。首先利用仿真数据对卷积神经网络进行训练，然后分别使用仿真和湖上试验数据对算法网络进行测试。仿真结果表明，在SNR=5 dB时，该方法对2ASK、4ASK、BPSK、QPSK、2FSK、4FSK和OFDM等7种水下通信信号的识别率均能达到90%以上，7种湖上试验的通信信号类型平均识别率达到97.9%。这表明该方法具有良好的宽容性。此外，本文还通过对基于高阶累积量和深度学习方法的比较，验证了本文提出方法具有显著的优越性。
Underwater acoustic communication signal recognition is an important prerequisite for underwater acoustic communication reconnaissance and countermeasures and plays an important role. However, traditional underwater acoustic communication signal recognition methods are usually based on signal processing and pattern recognition technology. The selection and extraction of features mainly rely on the professional knowledge and experience of domain experts, which is highly subjective and may not be able to use more complex signal characteristics. In this paper, the convolutional neural network in deep learning is used to automatically extract the characteristics of communication signals. First, the network is trained using the simulated data, and then the algorithm network is tested using the simulation and lake test data. The results show that when the SNR is 5 dB, the recognition rates of seven underwater communication signals, including the 2ASK, 4ASK, BPSK, QPSK, 2FSK, 4FSK and OFDM, can reach over 90%, and the average recognition rate of the seven types of communication signal types tested on the lake reaches 97.9%, which proves the good tolerance of the algorithm. At the same time, the comparison based on higher-order cumulant and deep learning method confirms the significant advantages of the proposed method.
2024,46(9): 117-124 收稿日期：2023-06-27
DOI：10.3404/j.issn.1672-7649.2024.09.020
分类号：TN911.7
作者简介：黄乐（1997 – ），男，硕士研究生，研究方向为水声信号处理
参考文献：
[1] 叶礼邦, 洪丽娜, 崔建岭, 等. 一种适合通信侦察能力试验的电磁环境复杂度定量评估方法[J]. 中国电子科学研究院学报，2014, 9(5): 531-537.
YE L B, HONG L N ,CUI J L, et al. A quantitative evaluation method of electromagnetic environment complexity suitable for communication reconnaissance capability test[J]. Journal of China Institute of Electronic Science, 2014, 9(5): 531-537.
[2] KIM. K, Polydoros. A. Digital modulation classification: The BPSK and QPSK case[C]// Processing MILCOM, 1988, 87: 431-436.
[3] BIJAN G M. Digital modulation classification using constellation shape[J]. Signal Processing. 2000, 80(2): 251-277.
[4] SANDERSON J, LI X, LIU Z, et al. Hierarchical blind modulation classification for underwater acoustic communication signal via cyclostationary and maximal likelihood analysis[C]// IEEE Military Communications Conference, San Diego, CA, USA, 2013.
[5] ZENG C Z, JIA X. Modulation recognition method of communication signals based on correlation characteristics[C]// 2015 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Ningbo, Zhejiang, China, 2015.
[6] 史文娟, 冯全源. 一种改进的基于支持向量机的 OFDM 识别算法[J]. 微电子学与计算机, 2014, 31(10): 98-102.
SHI Wen-juan, FENG Quan-yuan. An improved ofdm recognition algorithm based on support vector machine[J]. Microelectronics and Computers, 2014, 31(10): 98-102.
[7] 沈连腾, 巩克现 , 范磊. 利用局部密度与距离特征的MFSK识别方法[J]. 信号处 理, 2016(12): 1478-1488.
SHEN Lian-teng, GONG Ke-xian, FAN Lei. MFSK recognition method using local density and distance features[J]. Signal Processing, 2016(12): 1478-1488.
[8] 周青, 孙海信, 周明章. 一种水声通信信号调制模式识别方法[J]. 通信对抗, 2017, 2: 16-21.
ZHOU Qing, SUN Hai-xin, ZHOU Ming-zhang. A modulation pattern recognition method for underwater acoustic communication signals[J]. Communication Countermeasures, 2017, 2: 16-21.
[9] LU Na. Study of modulation identification and signals feature extraction [D]. Xi’an. Xidian University. 2008.
[10] 张贤达. 现代信号处理第2版[M]. 北京: 清华大学出版社, 2002.
