针对船用网络中流量和异常模式随着时间、船舶运行状态等因素而动态变化的特点，为判断网络的异常信息，提出基于改进C均值聚类算法的船用网络异常信息识别方法。该方法结合船用网络传输特性，分析该网络的传输流量情况，结合分析结果通过功率密度谱函数提取船用网络流量信息特征包络值，将提取结果输入基于模态稳定函数的模糊C均值聚类算法中，识别船用网络异常信息。测试结果显示，依据流量数据的包络特征值能够较好的描述网络信息的变化情况，信息识别后的分离性结果均在0.94以上；能够结合稳定函数完成船用网络异常信息分类识别，并且能够依据该函数确定不同异常信息的类别。
In response to the dynamic changes in traffic and abnormal patterns in marine networks over time, ship operation status, and other factors, a method for identifying abnormal information in marine networks based on an improved C-means clustering algorithm is proposed to determine the network's abnormal information. This method combines the transmission characteristics of the marine network to analyze the transmission traffic situation of the network. Based on the analysis results, the power density spectrum function is used to extract the characteristic envelope value of the marine network traffic information. The extraction results are input into the fuzzy C-means clustering algorithm based on modal stability function to identify abnormal information in the marine network. The test results show that the envelope feature values based on traffic data can better describe the changes in network information, and the separability results after information recognition are all above 0.94; Being able to combine stable functions to classify and identify abnormal information in marine networks, and being able to determine the categories of different abnormal information based on this function.
2025,47(11): 165-169 收稿日期：2025-1-12
DOI：10.3404/j.issn.1672-7649.2025.11.029
分类号：TP393
作者简介：赵晓华(1990-),女,硕士,讲师,研究方向为智能信息处理及信息安全
参考文献：
[1] 陶华宁, 刘荣才, 刘荣超. 基于5G通信技术的船用网络防拥塞机制研究 [J]. 舰船科学技术, 2024, 46 (16): 166-169.
TAO H N, LIU R C, LIU R C. Research on anti congestion mechanism of ship network based on 5G communication technology [J]. Ship Science and Technology, 2024, 46 (16): 166-169.
[2] 杨春霞, 陶可瑞, 宋永生. 深度学习算法的舰船网络安全状态识别 [J]. 舰船科学技术, 2023, 45 (21): 193-196.
YANG C X, TAO K R, SONG Y S. Deep learning algorithm for ship network security state recognition [J]. Ship Science and Technology, 2023, 45 (21): 193-196.
[3] 车丽娜, 任秀丽. 基于滑动窗口和置信度的无线传感器网络异常检测算法[J]. 传感技术学报, 2023, 36(11): 1801-1807.
CHE L N, REN X L. Anomaly detection algorithm based on sliding windows and confidence for WSN[J]. Chinese Journal of Sensors and Actuators, 2023, 36(11): 1801-1807.
[4] 张兵, 卞利. 基于FW-PSO的大区域无线传感网络流量异常检测算法[J]. 传感技术学报, 2023, 36(7): 1116-1121.
ZHANG B, BIAN L. Traffic anomaly detection algorithm for large area wireless sensor network based on FW-PSO[J]. Chinese Journal of Sensors and Actuators, 2023, 36(7): 1116-1121.
[5] 李道全, 李腾, 李玉秀. 基于机器学习的SDN异常流量检测架构[J]. 计算机工程与设计, 2023, 44(7): 1928-1936.
LI D Q, LI T, LI Y X. SDN abnormal traffic detection architecture based on machine learning[J]. Computer Engineering and Design, 2023, 44(7): 1928-1936.
[6] 刘东, 焦玉超, 宋晓男. 基于AHP-灰色聚类模型的舰艇自身抗损能力评估方法 [J]. 船舶工程, 2024, 46 (4): 54-59.
LIU D, JIAO Y C, SONG X N. A method for evaluating the self damage resistance of naval vessels based on AHP grey clustering model [J]. Ship Engineering, 2024, 46 (4): 54-59
[7] 叶志祥. 基于模糊聚类的情报侦察指挥要素能力评价 [J]. 舰船电子工程, 2024, 44 (2): 14-19.
YE Z X. Evaluation of intelligence reconnaissance command element capability based on fuzzy clustering [J]. Ship Electronic Engineering, 2024, 44 (2): 14-19
