Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks

Detalhes bibliográficos
Autor(a) principal: Meleiro,Luiz Augusto da Cruz
Data de Publicação: 2005
Outros Autores: Costa,Aline Carvalho da, Maciel Filho,Rubens
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Brazilian Archives of Biology and Technology
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132005000400002
Resumo: In this work a MIMO non-linear predictive controller was developed for an extractive alcoholic fermentation process. The internal model of the controller was represented by two MISO Functional Link Networks (FLNs), identified using simulated data generated from a deterministic mathematical model whose kinetic parameters were determined experimentally. The FLN structure presents as advantages fast training and guaranteed convergence, since the estimation of the weights is a linear optimization problem. Besides, the elimination of non-significant weights generates parsimonious models, which allows for fast execution in an MPC-based algorithm. The proposed algorithm showed good potential in identification and control of non-linear processes.
id TECPAR-1_df0a86a6f9df83ff1819a236bf4638bb
oai_identifier_str oai:scielo:S1516-89132005000400002
network_acronym_str TECPAR-1
network_name_str Brazilian Archives of Biology and Technology
repository_id_str
spelling Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networksExtractive alcoholic fermentationfunctional link neural networksnon-linear predictive controlIn this work a MIMO non-linear predictive controller was developed for an extractive alcoholic fermentation process. The internal model of the controller was represented by two MISO Functional Link Networks (FLNs), identified using simulated data generated from a deterministic mathematical model whose kinetic parameters were determined experimentally. The FLN structure presents as advantages fast training and guaranteed convergence, since the estimation of the weights is a linear optimization problem. Besides, the elimination of non-significant weights generates parsimonious models, which allows for fast execution in an MPC-based algorithm. The proposed algorithm showed good potential in identification and control of non-linear processes.Instituto de Tecnologia do Paraná - Tecpar2005-06-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132005000400002Brazilian Archives of Biology and Technology v.48 n.spe 2005reponame:Brazilian Archives of Biology and Technologyinstname:Instituto de Tecnologia do Paraná (Tecpar)instacron:TECPAR10.1590/S1516-89132005000400002info:eu-repo/semantics/openAccessMeleiro,Luiz Augusto da CruzCosta,Aline Carvalho daMaciel Filho,Rubenseng2005-08-15T00:00:00Zoai:scielo:S1516-89132005000400002Revistahttps://www.scielo.br/j/babt/https://old.scielo.br/oai/scielo-oai.phpbabt@tecpar.br||babt@tecpar.br1678-43241516-8913opendoar:2005-08-15T00:00Brazilian Archives of Biology and Technology - Instituto de Tecnologia do Paraná (Tecpar)false
dc.title.none.fl_str_mv Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks
title Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks
spellingShingle Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks
Meleiro,Luiz Augusto da Cruz
Extractive alcoholic fermentation
functional link neural networks
non-linear predictive control
title_short Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks
title_full Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks
title_fullStr Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks
title_full_unstemmed Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks
title_sort Non-linear multivariable predictive control of an alcoholic fermentation process using functional link networks
author Meleiro,Luiz Augusto da Cruz
author_facet Meleiro,Luiz Augusto da Cruz
Costa,Aline Carvalho da
Maciel Filho,Rubens
author_role author
author2 Costa,Aline Carvalho da
Maciel Filho,Rubens
author2_role author
author
dc.contributor.author.fl_str_mv Meleiro,Luiz Augusto da Cruz
Costa,Aline Carvalho da
Maciel Filho,Rubens
dc.subject.por.fl_str_mv Extractive alcoholic fermentation
functional link neural networks
non-linear predictive control
topic Extractive alcoholic fermentation
functional link neural networks
non-linear predictive control
description In this work a MIMO non-linear predictive controller was developed for an extractive alcoholic fermentation process. The internal model of the controller was represented by two MISO Functional Link Networks (FLNs), identified using simulated data generated from a deterministic mathematical model whose kinetic parameters were determined experimentally. The FLN structure presents as advantages fast training and guaranteed convergence, since the estimation of the weights is a linear optimization problem. Besides, the elimination of non-significant weights generates parsimonious models, which allows for fast execution in an MPC-based algorithm. The proposed algorithm showed good potential in identification and control of non-linear processes.
publishDate 2005
dc.date.none.fl_str_mv 2005-06-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132005000400002
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132005000400002
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/S1516-89132005000400002
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
dc.publisher.none.fl_str_mv Instituto de Tecnologia do Paraná - Tecpar
publisher.none.fl_str_mv Instituto de Tecnologia do Paraná - Tecpar
dc.source.none.fl_str_mv Brazilian Archives of Biology and Technology v.48 n.spe 2005
reponame:Brazilian Archives of Biology and Technology
instname:Instituto de Tecnologia do Paraná (Tecpar)
instacron:TECPAR
instname_str Instituto de Tecnologia do Paraná (Tecpar)
instacron_str TECPAR
institution TECPAR
reponame_str Brazilian Archives of Biology and Technology
collection Brazilian Archives of Biology and Technology
repository.name.fl_str_mv Brazilian Archives of Biology and Technology - Instituto de Tecnologia do Paraná (Tecpar)
repository.mail.fl_str_mv babt@tecpar.br||babt@tecpar.br
_version_ 1750318270289805312