文章基本信息

标题：SOFT SENSOR FOR BETTER CONTROL OF CARBON DIOXIDE REMOVAL PROCESS IN ETHYLENE GLYCOL PLANT
本地全文：下载
作者：NADEEM M. KHALFE ; SANDIP KUMAR LAHIRI ; SUNIL KUMAR SAWKE 等
期刊名称：Chemical Industry and Chemical Engineering Quarterly
印刷版ISSN：1451-9372
出版年度：2011
卷号：17
期号：01
页码：17-24
出版社：Association of the Chemical Engineers
摘要：Low carbon dioxide in cycle gas loop of ethylene glycol (EG) plant improves catalyst selectivity and overall economics of the plant. Carbon dioxide produced as a byproduct in ethylene oxide reactor is removed by the Benfield process. In this process, the carbonate and bicarbonate ratio in lean carbonate solution is considered as an important quality control (QC) variable as the efficiency of carbon dioxide removal largely depends on it. In the event of a process malfunction or operating under suboptimal condition, the CO2 content in the cycle gas loop will continue to rise until corrective action is taken after obtaining lab results for carbonate and bicarbonate ratio. This time consuming sampling process can be overcome by implementing a technological solution in form of an accurate and robust mathematical model capable of real time QC variable prediction. For well understood processes, the structure of the correlation for QC variables as well as the choice of the inputs may be well known in advance. However, the Benfield process is too complex and the appropriate form of the correlation and choice of input variables are not obvious. Here, knowledge of the processes, operating experience and statistical methods were applied in developing the soft sensor. This paper describes a systematic approach to the development of inferential measurements of carbonate and bi¬carbonate ratio using Support Vector Regression (SVR) analysis. Given histo¬rical process data, a simple SVR-based soft sensor model is found capable of identifying and capturing the cause and effect relationship between operating variables (model inputs) and QC variables (model outputs). Special care was taken to choose input variables, so that the final correlation and regression coefficient make senses from process engineering point of view. The developed soft sensor was implemented in commercial ethylene glycol plant in an Exa¬quantum interface and was found to satisfactorily predict the carbonate and bi-carbonate ratio in real time.
关键词：support vector regression ; soft sensor ; modeling