摘要
化工过程具有高复杂性和高危险性等特点,且生产过程都是长周期连续运转,一旦出现故障就会造成巨大的损失,因此对化工过程进行实时的过程监控和故障诊断,对于确保化工生产过程的安全性具有十分重要的意义。动态不确定因果图(Dynamic Uncertain Causality Graph,DUCG)理论是一种动态不确定因果知识的表达和推理方法,能够以图形方式简洁表达不确定因果关系,并基于证据化简图形知识库和进行事件展开运算,最终得到定性推理结果(可能的假设事件集合)及其发生的概率。以TE(Tennessee Eastman)化工过程为测试平台,对基于DUCG理论开发的一种新的应用于化工过程的实时过程监控与故障诊断系统进行了知识库构建和实时在线故障诊断测试,结果证明基于DUCG的化工过程故障诊断方法及开发的软件系统非常有效。
Chemical processes have the characteristics of high complexity and high risk, and the production process is in a continuous operation for a long period of time. Once a fault occurs, huge losses will be the result, so the re- al-time process monitoring and fault diagnosis of the chemical process are of great significance to ensuring the safety of the chemical production. The Dynamic Uncertain Causality Graph (DUCG) is a methodology used to deal with knowledge representation and reasoning of dynamical uncertain causalities. DUCG is able to compactly and graphic- ally represent uncertain causalities, simplify the graphical knowledge base based on the online evidence and expand events as independent random event expressions, and finally reveals the qualitative reasoning results ( the set of the possible hypotheses) and the probabilities of these hypotheses. In this paper, we use the TE (Tennessee Eastman) process as the test platform, and the knowledge database is built for the new real-time process monitoring and the fault diagnosis is applied to the chemical process based on the DUCG and the real-time online fault diagnosis is per- formed. The results show that the fault diagnosis method based on the DUCG for chemical processes and our soft- ware system are very effective.
出处
《智能系统学报》
CSCD
北大核心
2014年第2期154-160,共7页
CAAI Transactions on Intelligent Systems
基金
国家自然科学基金资助项目(61273330)
关键词
动态不确定因果图
故障诊断
化工过程
TE过程
Dynamic Uncertain Causality Graph
fault diagnosis
chemical process
Tennessee Eastman