针对船用通信系统光信号通常缺乏大量标记样本，且无标记样本未得到充分利用的情况，提出基于RBM-DSN的船用通信失真信号半监督识别方法。采集光通信信号，并对其进行转化处理；将转化后的光通信信号作为输入，利用限玻尔兹曼机学习挖掘光通信信号潜在特征，利用对比散度算法求解最优参数，并以此初始化深层堆叠网络输入权值，采用多模块堆叠结构，通过各模块独立的有监督训练，实现对光通信信号特征的分层提取，并采用梯度下降法微调网络参数，通过最小化误差函数优化识别效果。实验结果表明：对于不同失真光通信信号，本文方法的识别决定系数高，在样本标记率在20%时，该方法能够兼顾识别精度与计算成本，达到理想的失真信号识别效果。
Aiming at the situation that the optical signal of marine communication system usually lacks a large number of labeled samples and the unlabeled samples are not fully utilized, a semi-supervised identification method of marine communication distortion signal based on RBM-DSN is proposed. Collecting optical communication signals and converting them; Taking the converted optical communication signal as input, the potential features of optical communication signal are mined by Boltzmann machine learning, the optimal parameters are solved by contrast divergence algorithm, and the input weights of deep stack network are initialized. The multi-module stack structure is adopted, and the features of optical communication signal are extracted hierarchically through independent supervised training of each module. The network parameters are fine-tuned by gradient descent method, and the recognition effect is optimized by minimizing the error function. The experimental results show that the identification determination coefficient of this method is high for different distorted optical communication signals. When the sample labeling rate is 20%, this method can give consideration to the identification accuracy and calculation cost, and achieve the ideal distortion signal identification effect.
2025,47(23): 147-151 收稿日期：2025-5-24
DOI：10.3404/j.issn.1672-7649.2025.23.023
分类号：U697.33；TP181
作者简介：胡晓光(1978-),男,硕士,副教授,研究方向为移动通信技术及移动应用开发
参考文献：
[1] 钟子洋, 刘月胜. 沿海船岸宽带通信应用现状与完善[J]. 中国海事, 2025(5): 54-56.
ZHONG Z Y, LIU Y S. The application status and improvement of coastal ship-to-shore broadband communication[J]. China Maritime Affairs, 2025(5): 54-56.
[2] 陈香莲, 杨正祥. 基于5G通信网络的工程船舶载运信息监测系统[J]. 舰船科学技术, 2025, 47(7): 160-163.
CHEN X L, YANG Z X. Engineering ship carrying information monitoring system based on 5G communication network[J]. Ship Science and Technology, 2025, 47(7): 160-163.
[3] 赵晓华, 赵树升. 改进C均值聚类算法识别船用网络异常信息研究[J]. 舰船科学技术, 2025, 47(11): 165-169.
ZHAO X H, ZHAO S S. Research on improving C-means clustering algorithm for identifying anomalous information in marine networks[J]. Ship Science and Technology, 2025, 47(11): 165-169.
[4] 李永杰, 沈琼, 周锟, 等. 船岸通信网络恶意攻击与异常检测模块设计[J]. 科技创新与应用, 2025, 15(16): 39-43.
LI Y J, SHEN Q, ZHOU K, et al. Design of malicious attack and anomaly detection module for ship-to-shore communication network[J]. Science and Technology Innovation and Application, 2025, 15(16): 39-43.
[5] 马海洲, 丁爱萍. 大数据时代无人船通信网络入侵信号攻击源识别模型[J]. 舰船科学技术, 2021, 43(24): 142-144.
MA H Z, DING A P. Identification model of intrusion signal attack source in unmanned ship communication network in the era of big data[J]. Journal of Ship Science and Technology, 2021, 43(24): 142-144.
[6] 田艳超. 应用大数据分析的无人船通信网络安全态势识别模型[J]. 舰船科学技术, 2021, 43(22): 61-63.
TIAN Y C. A model for identifying the security situation of unmanned ship communication networks based on big data analysis[J]. Ship Science and Technology, 2021, 43(22): 61-63
[7] 李瑛, 杨丽娟, 朱蓬华. 基于数据挖掘的船用通信网络异常行为分类和识别研究方法[J]. 舰船科学技术, 2023, 45(21): 181-184.
LI Y, YANG L J, ZHU P H. Research method for classification and recognition of anomalous behaviors in marine communication networks based on data mining[J]. Ship Science and Technology, 2023, 45(21): 181-184.
[8] 贾林朋, 王霄, 何志琴, 等. 基于多智能体深度强化学习的海上风电传感器节点能效优化[J]. 计算机应用研究, 2025, 42(8): 2490-2496.
JIA L P, WANG X, HE Z Q, et al. Energy efficiency optimization of offshore wind power sensor nodes based on multi-agent deep reinforcement learning[J]. Journal of Computer Application and Research, 2025, 42(8): 2490-2496.
[9] 黄聪, 农英雄, 张毅. 基于高斯受限玻尔兹曼机的工业产品质量智能异常检测[J]. 工业工程, 2022, 25(6): 152-159.
HUANG C, NONG Y X, ZHANG Y. Intelligent anomaly detection for industrial product quality based on gaussian restricted boltzmann machines[J]. Industrial Engineering, 2022, 25(6): 152-159.
[10] 陈智君, 吴萌萌, 王忠俊, 等. 基于多级DSN的船舶柴油机故障在线诊断[J]. 内燃机学报, 2022, 40(4): 371-377.
CHEN Z J, WU M M, WANG Z J, et al. Online fault diagnosis of marine diesel engines based on multi-level DSN[J]. Transactions of the Chinese Society of Internal Combustion Engine, 2022, 40(4): 371-377.
