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

作     者：Venkata Vijayan S Hare Krishna Mohanta Ajaya Kumar Pani Venkata Vijayan S;Hare Krishna Mohanta;Ajaya Kumar Pani

作者机构：Department of Chemical EngineeringBirla Institute of Technology and SciencePilaniRajasthan333031India 

出 版 物：《Petroleum Science》 (石油科学（英文版）)

年 卷 期：2021年第18卷第4期

页      面：1230-1239页

核心收录：

学科分类：0820[工学-石油与天然气工程] 081702[工学-化学工艺] 08[工学] 0817[工学-化学工程与技术] 

主　　题：Adaptive soft sensor Just in time learning Regression Support vector regression Naphtha boiling point 

摘      要：Prediction of primary quality variables in real time with adaptation capability for varying process conditions is a critical task in process *** 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 *** this work,adaptive inferential sensors with linear and non-linear local models are reported based on recursive just in time learning(JITL)*** 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 *** 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.