A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty

Chemical process operation optimization aims at obtaining the optimal operating set-points by real-time solution of an optimization problem that embeds a steady-state model of the process. This task is challenged by unavoidable Uncertain Parameters (UPs) variations. MultiParametric Programming (MPP)...

Descripción completa

Detalles Bibliográficos
Autores: Shokry Abdelaleem Taha Zied, Ahmed, Medina González, Sergio, Baraldi, Piero, Zio, Enrico, Moulines, Eric François Victor, Espuña Camarasa, Antonio|||0000-0002-1238-8108
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/360198
Acceso en línea:https://hdl.handle.net/2117/360198
https://dx.doi.org/10.1016/j.cej.2021.131632
Access Level:acceso abierto
Palabra clave:Chemical processes
Operation optimization
Uncertainty
Multiparametric programming
Machine learning
Kriging
Gaussian process regression
Processos químics
Àrees temàtiques de la UPC::Enginyeria química
id ES_1d420bed57724f020161e53fcda5ee13
oai_identifier_str oai:upcommons.upc.edu:2117/360198
network_acronym_str ES
network_name_str España
repository_id_str
spelling A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertaintyShokry Abdelaleem Taha Zied, AhmedMedina González, SergioBaraldi, PieroZio, EnricoMoulines, Eric François VictorEspuña Camarasa, Antonio|||0000-0002-1238-8108Chemical processesChemical processesOperation optimizationUncertaintyMultiparametric programmingMachine learningKrigingGaussian process regressionProcessos químicsÀrees temàtiques de la UPC::Enginyeria químicaChemical process operation optimization aims at obtaining the optimal operating set-points by real-time solution of an optimization problem that embeds a steady-state model of the process. This task is challenged by unavoidable Uncertain Parameters (UPs) variations. MultiParametric Programming (MPP) is an approach for solving this challenge, where the optimal set-points must be updated online, reacting to sudden changes in the UPs. MPP provides algebraic functions describing the optimal solution as a function of the UPs, which allows alleviating large computational cost required for solving the optimization problem each time the UPs values vary. However, MPP applicability requires a well-constructed mathematical model of the process, which is not suited for process operation optimization, where complex, highly nonlinear and/or black-box models are usually used. To tackle this issue, this paper proposes a machine learning-based methodology for multiparametric solution of continuous optimization problems. The methodology relies on the offline development of data-driven models that accurately approximate the multiparametric behavior of the optimal solution over the UPs space. The models are developed using data generated by running the optimization using the original complex process model under different UPs values. The models are, then, used online to, quickly, predict the optimal solutions in response to UPs variation. The methodology is applied to benchmark examples and two case studies of process operation optimization. The results demonstrate the methodology effectiveness in terms of high prediction accuracy (less than 1% of NRMSE, in most cases), robustness to deal with problems of different natures (linear, bilinear, quadratic, nonlinear and/or black boxes) and significant reduction in the complexity of the solution procedure compared to traditional approaches (a minimum of 67% reduction in the optimization time).Elsevier20212021-12-0120222022-01-20journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/360198https://dx.doi.org/10.1016/j.cej.2021.131632reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivs 3.0 Spainhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3601982026-05-27T15:37:01Z
dc.title.none.fl_str_mv A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty
title A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty
spellingShingle A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty
Shokry Abdelaleem Taha Zied, Ahmed
Chemical processes
Chemical processes
Operation optimization
Uncertainty
Multiparametric programming
Machine learning
Kriging
Gaussian process regression
Processos químics
Àrees temàtiques de la UPC::Enginyeria química
title_short A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty
title_full A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty
title_fullStr A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty
title_full_unstemmed A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty
title_sort A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty
dc.creator.none.fl_str_mv Shokry Abdelaleem Taha Zied, Ahmed
Medina González, Sergio
Baraldi, Piero
Zio, Enrico
Moulines, Eric François Victor
Espuña Camarasa, Antonio|||0000-0002-1238-8108
author Shokry Abdelaleem Taha Zied, Ahmed
author_facet Shokry Abdelaleem Taha Zied, Ahmed
Medina González, Sergio
Baraldi, Piero
Zio, Enrico
Moulines, Eric François Victor
Espuña Camarasa, Antonio|||0000-0002-1238-8108
author_role author
author2 Medina González, Sergio
Baraldi, Piero
Zio, Enrico
Moulines, Eric François Victor
Espuña Camarasa, Antonio|||0000-0002-1238-8108
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Chemical processes
Chemical processes
Operation optimization
Uncertainty
Multiparametric programming
Machine learning
Kriging
Gaussian process regression
Processos químics
Àrees temàtiques de la UPC::Enginyeria química
topic Chemical processes
Chemical processes
Operation optimization
Uncertainty
Multiparametric programming
Machine learning
Kriging
Gaussian process regression
Processos químics
Àrees temàtiques de la UPC::Enginyeria química
description Chemical process operation optimization aims at obtaining the optimal operating set-points by real-time solution of an optimization problem that embeds a steady-state model of the process. This task is challenged by unavoidable Uncertain Parameters (UPs) variations. MultiParametric Programming (MPP) is an approach for solving this challenge, where the optimal set-points must be updated online, reacting to sudden changes in the UPs. MPP provides algebraic functions describing the optimal solution as a function of the UPs, which allows alleviating large computational cost required for solving the optimization problem each time the UPs values vary. However, MPP applicability requires a well-constructed mathematical model of the process, which is not suited for process operation optimization, where complex, highly nonlinear and/or black-box models are usually used. To tackle this issue, this paper proposes a machine learning-based methodology for multiparametric solution of continuous optimization problems. The methodology relies on the offline development of data-driven models that accurately approximate the multiparametric behavior of the optimal solution over the UPs space. The models are developed using data generated by running the optimization using the original complex process model under different UPs values. The models are, then, used online to, quickly, predict the optimal solutions in response to UPs variation. The methodology is applied to benchmark examples and two case studies of process operation optimization. The results demonstrate the methodology effectiveness in terms of high prediction accuracy (less than 1% of NRMSE, in most cases), robustness to deal with problems of different natures (linear, bilinear, quadratic, nonlinear and/or black boxes) and significant reduction in the complexity of the solution procedure compared to traditional approaches (a minimum of 67% reduction in the optimization time).
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-12-01
2022
2022-01-20
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/360198
https://dx.doi.org/10.1016/j.cej.2021.131632
url https://hdl.handle.net/2117/360198
https://dx.doi.org/10.1016/j.cej.2021.131632
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404269828898816
score 15,300719

Similares en LA Referencia