基于置信规则库的工业控制系统安全状态评估  

Safety state evaluation of industrial control system based on belief rule base

作　　者：程超[1] 陈梅 李治霖 CHENG Chao;CHEN Mei;LI Zhilin(Computer Science and Engineering College,Changchun University of Technology,Changchun 130012,China)

机构地区：[1]长春工业大学计算机科学与工程学院,长春130012

出　　处：《自动化与仪器仪表》2021年第2期38-41,45,共5页Automation & Instrumentation

基　　金：国家自然科学基金资助项目(No.61903047);吉林省发改委资助项目(No.2019C040-3)。

摘　　要：当前工业控制系统存在严重安全问题,针对现有工业控制系统安全状态评估模型存在的不足,提出一种基于置信规则库(BRB)专家系统的工业控制系统安全状态评估方法。该方法首先利用置信规则库专家系统将工业控制系统中定性知识与定量监测数据相结合。然后采用证据推理(ER)算法进行知识推理,并对所建立的BRB模型初始参数进行优化。最后以某燃气工业控制系统数据为例,实验结果表明,其评估精度高于SVM和BP神经网络模型。At present,there are serious safety problems in the industrial control system,aiming at the shortcomings of the existing safety state evaluation model of the industrial control system.In this paper,a method of safety state evaluation of industrial control system based on BRB expert system is proposed.Firstly,the expert system of belief rule base is used to combine qualitative knowledge with quantitative monitoring data.Then ER algorithm is used for knowledge reasoning,and the initial parameters of BRB model are optimized.Finally,taking the data of a gas industry control system as an example,the experimental results show that the evaluation accuracy is higher than that of BP and SVM evaluation models.

关 键 词：置信规则库 工业控制系统 ER推理 安全状态评估 专家系统 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]