Home > Research > Publications & Outputs > Using Evolving Fuzzy Models to predict Crude Oi...

Links

Text available via DOI:

View graph of relations

Using Evolving Fuzzy Models to predict Crude Oil Distillation Side Streams

Research output: Contribution in Book/Report/ProceedingsPaper

Published
Close
Publication date2011
Host publicationComputer-Aided Design, Manufacturing, Modeling and Simulation
EditorsXingui He, Ertian Hua, Yun Lin, Xiaozhu Liu
Place of PublicationZurich
PublisherTrans-Tech Publications
Pages432-437
Number of pages6
ISBN (Print)978-3-03785-236-1
<mark>Original language</mark>English

Conference

ConferenceInternational Conference on Computer-Aided Design, Manufacturing, Modeling and Simulation (CDMMS 2011)
CityHangzhou
Period13/09/1116/09/11

Conference

ConferenceInternational Conference on Computer-Aided Design, Manufacturing, Modeling and Simulation (CDMMS 2011)
CityHangzhou
Period13/09/1116/09/11

Abstract

Prediction of the properties of the crude oil distillation side streams based on statistical methods and laboratory-based analysis has been around for decades. However, it is difficult to identify, control or compensate the dynamic process behavior and the errors from instrumentation for an online model prediction. The objective of this work is to report an application and a study of a novel technique for real-time modelling, namely eXtended Evolving Fuzzy Takagi-Sugeno models (xTS) for prediction and online monitoring of these properties of the refinery distillation process. The results include the online prediction of Soft Sensors for distillation of Naptha and Gasoil Side Streams. The application predicts the quality of the side stream evolving its fuzzy structure and cluster parameters.