DSpace Repository

Support vector regression modeling in recursive just-in-time learning framework for adaptive soft sensing of naphtha boiling point in crude distillation unit

Show simple item record

dc.contributor.author Pani, Ajaya Kumar
dc.contributor.author Mohanta, Hare Krishna
dc.date.accessioned 2021-10-07T12:26:44Z
dc.date.available 2021-10-07T12:26:44Z
dc.date.issued 2021-08-15
dc.identifier.uri https://www.sciencedirect.com/science/article/pii/S1995822621000066?via%3Dihub
dc.identifier.uri http://dspace.bits-pilani.ac.in:8080/xmlui/handle/123456789/2642
dc.description.abstract Prediction of primary quality variables in real time with adaptation capability for varying process conditions is a critical task in process industries. This article focuses on the development of non-linear adaptive soft sensors for prediction of naphtha initial boiling point (IBP) and end boiling point (EBP) in crude distillation unit. In this work, adaptive inferential sensors with linear and non-linear local models are reported based on recursive just in time learning (JITL) approach. The different types of local models designed are locally weighted regression (LWR), multiple linear regression (MLR), partial least squares regression (PLS) and support vector regression (SVR). In addition to model development, the effect of relevant dataset size on model prediction accuracy and model computation time is also investigated. Results show that the JITL model based on support vector regression with iterative single data algorithm optimization (ISDA) local model (JITL-SVR:ISDA) yielded best prediction accuracy in reasonable computation time. en_US
dc.language.iso en en_US
dc.publisher Elsiever en_US
dc.subject Chemical Engineering en_US
dc.subject Adaptive soft sensor en_US
dc.subject Just in time learning en_US
dc.subject Regression en_US
dc.title Support vector regression modeling in recursive just-in-time learning framework for adaptive soft sensing of naphtha boiling point in crude distillation unit en_US
dc.type Article en_US


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account