基于决策灰狼优化支持向量机的指挥控制网络故障检测方法
Fault Detection Method of Command and Control Network Based on Decision Gray Wolf Optimization Support Vector Machine
王建伟 1潘成胜 2施建锋1
作者信息
- 1. 南京信息工程大学电子与信息工程学院,江苏南京 210044
- 2. 南京信息工程大学电子与信息工程学院,江苏南京 210044;南京理工大学自动化学院,江苏南京 210044
- 折叠
摘要
针对复杂战场环境下,我军传统指挥控制网络故障检测方法准确率较低、耗时较长等问题,提出了一种基于决策灰狼优化支持向量机的方法来实现指挥控制网络故障检测.对采集到的网络故障数据集进行归一化处理;再利用主成分分析法(principal component analysis,PCA)对数据集进行降维处理从而剔除数据集中信息量较少的维度;构建支持向量机(support vector machines,SVM)模型,并运用决策灰狼优化(decision gray wolf optimization,DGWO)算法来进行全局寻优,以狼群所在的位置来代替SVM中核函数与惩罚因子的取值,通过不断地迭代寻优来更新狼群的位置,获得最优的核函数及惩罚因子,从而进行指挥控制网络故障检测.实验结果表明所提方法与其他方法相比检测准确率达到了 98.68％,具有更高的实用性和有效性.
Abstract
In view of the problems of low accuracy and long time-consuming of traditional command and control network fault detection methods of Chinese army in complex battlefield environment,a method based on decision gray wolf optimization support vector machine is proposed to realize the fault detection of command and control network.Firstly,the collected network fault data sets are processed for normalization;and then the Principal Component Analysis(PCA)is used to reduce the dimension of the data sets to eliminate the dimension with less information in the data sets;After that,the Support Vector Machines(SVM)model is built,and the Decision Gray Wolf Optimization(DGWO)algorithm is used to perform global optimization,and the position of the wolf pack is used to replace the values of kernel function and penalty factors in the SVM,the position of the wolf pack is updated through continuous iterative optimization,and the optimal kernel function and penalty factors are obtained,so as to detect the fault of the command and control network.The experimental results show that the proposed method has a detection accuracy of 98.68％compared with other methods,the proposed method has higher practicability and effectiveness.
关键词
指挥控制网络/故障检测/DGWO算法/SVM模型/PCA降维/参数优化Key words
command and control network/fault detection/DGWO algorithm/SVM model/PCA dimensionality reduction/parameter optimization引用本文复制引用
出版年
2024
NETL
NSTL
万方数据