摘要
目前提升工业防火墙白名单技术的准确率已成为工控网络安全研究的重点和热点。针对此现状,于是提出了一种利用遗传算法和差分进化算法共同优化支持向量机的白名单技术。首先以准确率作为适应度函数,利用遗传算法与差分进化算法的交叉与变异环节相结合,选择出最佳的支持向量机参数惩罚因子c及高斯核参数g,然后使用支持向量机算法进行训练,最后利用PLC对其仿真验证。实验结果表明,该算法优化了分类效果,而且对正常数据的测试准确率提高了18%,异常数据测试准确率则提高了10%.
At present,improving the accuracy of industrial firewall whitelisting technology has become the focus and hotspot of industrial control network security research.In view of this situation,a whitelist technology using genetic algorithm and differential evolution algorithm is proposed to jointly optimize support vector machines.First,the accuracy is used as the fitness function,the genetic algorithm and the differential evolution algorithm are used to combine the crossover and mutation links to select the best support vector machine parameter penalty factor c and Gaussian kernel parameter g,and then use the support vector machine algorithm for training Finally,PLC is used to verify its simulation.Experimental results show that the algorithm optimizes the classification effect,and the test accuracy of normal data is increased by 18%,and the test accuracy of abnormal data is increased by 10%.
作者
渠东雨
潘峰
QU Dong-yu;PAN Feng(School of Electronic Information Engineering,Taiyuan University of Science and Technology,Taiyuan 030024,China;Department of Brewing Engineering Automation,Moutai College,Guizhou Renhuai 564507,China)
出处
《太原科技大学学报》
2023年第3期213-218,共6页
Journal of Taiyuan University of Science and Technology
基金
蓝盾PLC防火墙项目(201604)。
关键词
工控网络安全
白名单技术
支持向量机
改进遗传算法
差分进化算法
industrial control network security
whitelisting technology
support vector machines
improved genetic algorithm
differential evolution algorithm
