Multi-step Ahead Prediction Analysis for MPC-relevant Models

Model predictive control (MPC) is one of the most successful controllers in industries and widely applied in petroleum refining and petrochemical processes. Its inherent model-based strategy, however, renders it sensitive to changes that occur when the plants operate outside the boundaries of its or...

Full description

Main Authors: H., Zabiri, M., Ramasamy, Lemma D, Tufa, Maulud, Abdulhalim
Format: Conference or Workshop Item
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.10750 /
Published: 2013
Subjects:
TP Chemical technology
Online Access: http://eprints.utp.edu.my/10750/1/HZb_paper107.pdf
http://eprints.utp.edu.my/10750/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.10750
recordtype eprints
spelling utp-eprints.107502017-03-20T01:59:22Z Multi-step Ahead Prediction Analysis for MPC-relevant Models H., Zabiri M., Ramasamy Lemma D, Tufa Maulud, Abdulhalim TP Chemical technology Model predictive control (MPC) is one of the most successful controllers in industries and widely applied in petroleum refining and petrochemical processes. Its inherent model-based strategy, however, renders it sensitive to changes that occur when the plants operate outside the boundaries of its original operating conditions. In this paper, a nonlinear empirical model based on parallel orthonormal basis function-neural networks structure, which has been shown to be able to extend the applicable regions of the model, is evaluated for its multi-step ahead prediction capability and compared to the conventional neural networks models with different scaling procedures. It has been shown that the nonlinear model exhibited sufficient multi-step ahead prediction capability that renders it a promising candidate for MPC applications that can potentially improve the closed-loop control performance in extended regions and this is important in retaining the positive benefits of MPC in industries. 2013-10 Conference or Workshop Item PeerReviewed application/pdf http://eprints.utp.edu.my/10750/1/HZb_paper107.pdf H., Zabiri and M., Ramasamy and Lemma D, Tufa and Maulud, Abdulhalim (2013) Multi-step Ahead Prediction Analysis for MPC-relevant Models. In: INTERNATIONAL OIL & GAS SYMPOSIUM AND EXHIBITION , 9-11 October, Kota Kinabalu, Sabah. http://eprints.utp.edu.my/10750/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
topic TP Chemical technology
spellingShingle TP Chemical technology
H., Zabiri
M., Ramasamy
Lemma D, Tufa
Maulud, Abdulhalim
Multi-step Ahead Prediction Analysis for MPC-relevant Models
description Model predictive control (MPC) is one of the most successful controllers in industries and widely applied in petroleum refining and petrochemical processes. Its inherent model-based strategy, however, renders it sensitive to changes that occur when the plants operate outside the boundaries of its original operating conditions. In this paper, a nonlinear empirical model based on parallel orthonormal basis function-neural networks structure, which has been shown to be able to extend the applicable regions of the model, is evaluated for its multi-step ahead prediction capability and compared to the conventional neural networks models with different scaling procedures. It has been shown that the nonlinear model exhibited sufficient multi-step ahead prediction capability that renders it a promising candidate for MPC applications that can potentially improve the closed-loop control performance in extended regions and this is important in retaining the positive benefits of MPC in industries.
format Conference or Workshop Item
author H., Zabiri
M., Ramasamy
Lemma D, Tufa
Maulud, Abdulhalim
author_sort H., Zabiri
title Multi-step Ahead Prediction Analysis for MPC-relevant Models
title_short Multi-step Ahead Prediction Analysis for MPC-relevant Models
title_full Multi-step Ahead Prediction Analysis for MPC-relevant Models
title_fullStr Multi-step Ahead Prediction Analysis for MPC-relevant Models
title_full_unstemmed Multi-step Ahead Prediction Analysis for MPC-relevant Models
title_sort multi-step ahead prediction analysis for mpc-relevant models
publishDate 2013
url http://eprints.utp.edu.my/10750/1/HZb_paper107.pdf
http://eprints.utp.edu.my/10750/
_version_ 1741196130442543104
score 11.62408

Similar Items