基于PCA的动态化工过程实时故障监测系统研究  

A real-time fault monitoring system for the dynamic chemical process based on PCA

作　　者：董国胜[1] 任伟[2] 

机构地区：[1]中国石油化工股份有限公司青岛安全工程研究院,化学品安全控制国家重点实验室,山东青岛266071 [2]青岛科技大学化工学院,山东青岛266042

出　　处：《计算机与应用化学》2010年第10期1357-1360,共4页Computers and Applied Chemistry

基　　金：国家高技术研究发展计划(863)(No.2009AA04Z133).

摘　　要：如何确保化工过程安稳运行,被科研工作者视为1个重要研究方向。但能够成功应用于实际化工过程上的故障监测系统却寥寥无几。本文深入研究了主元分析的原理,在主元分析方法的基础上,利用VS2005开发工具,完成了基于主元分析算法的推理引擎,开发了动态化工过程实时故障监测系统,并利用乙烯装置热区分离工段的仿真系统,从中选取了21个可测变量,通过仿真实验,当故障发生时,能够准确的找到故障。验证了该监测系统的有效性,取得了较好的效果。It has been regarded as an important research direction for research workers to ensure the safe operation of chemical process.While the fault monitoring system that can be very successfully applied in chemical process is few.By studying the theory of PCA deeply and using VS2005, the dynamic real-time fault monitoring system for chemical process was developed in order to improve the problem,based on the Principal Component Analysis method.Further more,by using the simulation environment of hotspots separation sections in ethylene unit and choosing 21 measurable variables from it,it can accurately locate it when a fault occurred.It verified the effectiveness of the monitoring system,and achieved good results.

关 键 词：主元分析 动态 化工过程 实时 故障监测系统 

分 类 号：TQ021.8[化学工程] TP391.9[自动化与计算机技术—计算机应用技术]