Real-time application of multivariate statistical methods for early event detection in an industrial slurry stripper

详细信息    查看全文

• 作者：Thomas Darkow^* ; ^{t.darkow@greylogix.de" class="auth_mail" title="E-mail the corresponding author} ; Rainer Dittmar^** ; ^{dittmar@fh-westkueste.de" class="auth_mail" title="E-mail the corresponding author} ; Helge Timm^*** ; ^{helge.timm@de.sasol.com" class="auth_mail" title="E-mail the corresponding author}
• 刊名：IFAC-PapersOnLine
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：47
• 期：3
• 页码：8879-8884
• 全文大小：576 K

文摘

Multivariate data analysis (MDA) is a well-established technique for abnormal situation management and early event detection (EED). This paper presents the development and on-line deployment of a Principle Component Analysis (PCA) model based EED system for an industrial-scale slurry stripper processing a solid state particle suspension. The developed solution was designed to detect plugging or blockage of the stripping column trays earlier than it is possible using traditional monitoring techniques and to avoid process disruption and production losses. The paper describes the project steps from data selection and preparation to the online implementation and utilization by operators and plant personnel. It was developed within a close collaboration between university and industry.