A review on data-driven linear parameter-varying modeling approaches: A high-purity distillation column case study

Research output: Contribution to journalArticleAcademicpeer-review

42 Citations (Scopus)
11 Downloads (Pure)

Abstract

Model-based control strategies are widely used for optimal operation of chemical processes to respond to the increasing performance demands in the chemical industry. Yet, obtaining accurate models to describe the inherently nonlinear, time-varying dynamics of chemical processes remains a challenge in most model-based control applications. This paper reviews data-driven, Linear Parameter-Varying (LPV) modeling approaches for process systems by exploring and comparing various identification methods on a high-purity distillation column case study. Several LPV identification methods that utilize input–output and series expansion model structures are explored. Two LPV identification perspectives are adopted: (i) the local approach, which corresponds to the interpolation of Linear Time-Invariant (LTI) models identified at different steady-state operating points of the system and (ii) the global approach, where a parametrized LPV model structure is identified directly using a global data set with varying operating points. For the local approach, various model interpolation schemes are studied under an Output Error (OE) noise setting, whereas in the global case, a polynomial parametrization based OE prediction error minimization approach, an Orthonormal Basis Functions (OBFs) based model estimator and a Least-Square Support Vector Machine (LS-SVM) based non-parametric approach are investigated. Through extensive simulation studies, the aforementioned LPV identification approaches are analyzed in terms of the attainable model accuracy and local frequency response behavior of the obtained models. Recommendations are provided to achieve adequate choice between the methods for a particular process system at hand.
Original languageEnglish
Pages (from-to)272-285
Number of pages14
JournalJournal of Process Control
Volume24
Issue number4
DOIs
Publication statusPublished - 2014

Fingerprint

Distillation
Distillation columns
Data-driven
Modeling
Model-based Control
Chemical Processes
Model structures
Model
Identification (control systems)
Interpolation
Interpolate
Least Squares Support Vector Machine
Review
Orthonormal basis
Output
Prediction Error
Frequency Response
Chemical industry
Series Expansion
Parametrization

Cite this

@article{83421492018749408ffd462e5e2c0c61,
title = "A review on data-driven linear parameter-varying modeling approaches: A high-purity distillation column case study",
abstract = "Model-based control strategies are widely used for optimal operation of chemical processes to respond to the increasing performance demands in the chemical industry. Yet, obtaining accurate models to describe the inherently nonlinear, time-varying dynamics of chemical processes remains a challenge in most model-based control applications. This paper reviews data-driven, Linear Parameter-Varying (LPV) modeling approaches for process systems by exploring and comparing various identification methods on a high-purity distillation column case study. Several LPV identification methods that utilize input–output and series expansion model structures are explored. Two LPV identification perspectives are adopted: (i) the local approach, which corresponds to the interpolation of Linear Time-Invariant (LTI) models identified at different steady-state operating points of the system and (ii) the global approach, where a parametrized LPV model structure is identified directly using a global data set with varying operating points. For the local approach, various model interpolation schemes are studied under an Output Error (OE) noise setting, whereas in the global case, a polynomial parametrization based OE prediction error minimization approach, an Orthonormal Basis Functions (OBFs) based model estimator and a Least-Square Support Vector Machine (LS-SVM) based non-parametric approach are investigated. Through extensive simulation studies, the aforementioned LPV identification approaches are analyzed in terms of the attainable model accuracy and local frequency response behavior of the obtained models. Recommendations are provided to achieve adequate choice between the methods for a particular process system at hand.",
author = "A.A. Bachnas and R. Toth and A. Mesbah and J.H.A. Ludlage",
year = "2014",
doi = "10.1016/j.jprocont.2014.01.015",
language = "English",
volume = "24",
pages = "272--285",
journal = "Journal of Process Control",
issn = "0959-1524",
publisher = "Elsevier",
number = "4",

}

A review on data-driven linear parameter-varying modeling approaches: A high-purity distillation column case study. / Bachnas, A.A.; Toth, R.; Mesbah, A.; Ludlage, J.H.A.

In: Journal of Process Control, Vol. 24, No. 4, 2014, p. 272-285.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A review on data-driven linear parameter-varying modeling approaches: A high-purity distillation column case study

AU - Bachnas, A.A.

AU - Toth, R.

AU - Mesbah, A.

AU - Ludlage, J.H.A.

PY - 2014

Y1 - 2014

N2 - Model-based control strategies are widely used for optimal operation of chemical processes to respond to the increasing performance demands in the chemical industry. Yet, obtaining accurate models to describe the inherently nonlinear, time-varying dynamics of chemical processes remains a challenge in most model-based control applications. This paper reviews data-driven, Linear Parameter-Varying (LPV) modeling approaches for process systems by exploring and comparing various identification methods on a high-purity distillation column case study. Several LPV identification methods that utilize input–output and series expansion model structures are explored. Two LPV identification perspectives are adopted: (i) the local approach, which corresponds to the interpolation of Linear Time-Invariant (LTI) models identified at different steady-state operating points of the system and (ii) the global approach, where a parametrized LPV model structure is identified directly using a global data set with varying operating points. For the local approach, various model interpolation schemes are studied under an Output Error (OE) noise setting, whereas in the global case, a polynomial parametrization based OE prediction error minimization approach, an Orthonormal Basis Functions (OBFs) based model estimator and a Least-Square Support Vector Machine (LS-SVM) based non-parametric approach are investigated. Through extensive simulation studies, the aforementioned LPV identification approaches are analyzed in terms of the attainable model accuracy and local frequency response behavior of the obtained models. Recommendations are provided to achieve adequate choice between the methods for a particular process system at hand.

AB - Model-based control strategies are widely used for optimal operation of chemical processes to respond to the increasing performance demands in the chemical industry. Yet, obtaining accurate models to describe the inherently nonlinear, time-varying dynamics of chemical processes remains a challenge in most model-based control applications. This paper reviews data-driven, Linear Parameter-Varying (LPV) modeling approaches for process systems by exploring and comparing various identification methods on a high-purity distillation column case study. Several LPV identification methods that utilize input–output and series expansion model structures are explored. Two LPV identification perspectives are adopted: (i) the local approach, which corresponds to the interpolation of Linear Time-Invariant (LTI) models identified at different steady-state operating points of the system and (ii) the global approach, where a parametrized LPV model structure is identified directly using a global data set with varying operating points. For the local approach, various model interpolation schemes are studied under an Output Error (OE) noise setting, whereas in the global case, a polynomial parametrization based OE prediction error minimization approach, an Orthonormal Basis Functions (OBFs) based model estimator and a Least-Square Support Vector Machine (LS-SVM) based non-parametric approach are investigated. Through extensive simulation studies, the aforementioned LPV identification approaches are analyzed in terms of the attainable model accuracy and local frequency response behavior of the obtained models. Recommendations are provided to achieve adequate choice between the methods for a particular process system at hand.

U2 - 10.1016/j.jprocont.2014.01.015

DO - 10.1016/j.jprocont.2014.01.015

M3 - Article

VL - 24

SP - 272

EP - 285

JO - Journal of Process Control

JF - Journal of Process Control

SN - 0959-1524

IS - 4

ER -