基于免疫识别技术的舰船光通信网络断点检测技术  

Fault detection technology for ship optical communication network based on immune recognition technology

作　　者：陶亮 陈健[2] TAO Liang;CHEN Jian(Information Construction and Management Center,Jinling Institute of Technology,Nanjing 211169,China;Department of Computer Science and Technology,NanJing University,Nanjing 210023,China)

机构地区：[1]金陵科技学院信息化建设与管理中心,江苏南京211169 [2]南京大学计算机科学与技术系,江苏南京210023

出　　处：《舰船科学技术》2025年第7期164-168,共5页Ship Science and Technology

基　　金：国家自然科学基金青年科学基金项目(61902163);江苏省现代教育技术研究课题资助项目(2017-R-54558)。

摘　　要：舰船光通信网络具有频谱类噪声干扰的特性,且光随机反馈环境使得信息动态叠加,难以提取有效运行数据,导致断点检测存在误差。为此,提出基于免疫识别的舰船光通信网络断点检测方法。将光通信网络信号分配至对应的小波系数上,通过小波变换处理,完成信号去噪。采用免疫识别算法挖掘信号,有效地挖掘信息并寻找最优解,获得通信正常和断点情况下的正常运行数据和异常运行数据,采用决策树方法递归地划分数据空间,以此判断光通信网络异常,输出断点检测结果。实验结果表明,本文方法可以获取高精度、高效率的检测结果。The ship′s optical communication network has the characteristic of spectral noise interference,and the optical random feedback environment makes it difficult to extract effective operational data due to the dynamic superposition of information,resulting in errors in breakpoint detection.Therefore,a breakpoint detection method for ship optical communication networks based on immune recognition is proposed.Allocate the optical communication network signal to the corresponding wavelet coefficients,and complete signal denoising through wavelet transform processing.Using immune recognition algorithm to mine signals,effectively mining information and finding optimal solutions,obtaining normal and abnormal operation data under normal and breakpoint communication conditions,recursively dividing the data space using decision tree method to determine optical communication network abnormalities,and outputting breakpoint detection results.The experimental results show that the proposed method can obtain high-precision and high-efficiency detection results.

关 键 词：免疫识别 小波变换 光通信网络 断点检测 决策树分类器 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]