贝叶斯网络在裂解炉工艺参数控制系统安全性分析中的应用  

Application of Bayesian Network to Safety Analysis of Cracking Furnace Process Parameter Control System

作　　者：王春利[1] 赵建平[1] 

机构地区：[1]南京工业大学机械与动力工程学院,江苏南京210009

出　　处：《石油化工》2010年第1期66-69,共4页Petrochemical Technology

基　　金：国家高技术研究发展计划项目(2006AA04Z439)

摘　　要：提出了将贝叶斯网络应用于裂解炉工艺参数控制系统安全性分析的方法。在对影响裂解炉安全运行的重要工艺参数进行分析后,确定了使裂解炉控制失效的20个变量;根据贝叶斯网络的分析原理,构建了贝叶斯网络模型,并采用Bayes NetToolbox软件包对所建立的模型进行安全性分析,求解出在以根结点为已知证据时,目标节点(叶节点)发生的概率及各根节点的后验概率。计算结果表明,原料流量、炉管出口温度和燃料气流量是工艺参数控制系统的薄弱环节,特别是炉管出口温度。贝叶斯网络的计算结果为裂解炉工艺参数控制的定量安全性分析提供了决策依据。Application of Bayesian network to safety analysis of cracking furnace process parameter control system was proposed. After effects of some important parameters on safe operation of cracking furnace were analyzed, 20 factors relevant to cracking furnace control failure were determined. A Bayesian network model was established based on Bayesian network analytical principle. Bayes Net Toolbox software package was used to the safety analysis, and the probability of leaf nodes （objective nodes） and posterior probability of every root node were acquired when the root nodes as the known evidences were given. Materials flowrate, furnace outlet temperature and fuel gas flowrate were weaknesses in cracking furnace process control system, especially furnace outlet temperature. The Bayesian network result could be used as decision-making reference of quantitative safety analysis for cracking furnace process parameter control system.

关 键 词：裂解炉 参数控制 贝叶斯网络 安全性分析 乙烯 

分 类 号：TQ018[化学工程]