Adaptive control using a hybrid-neural model: application to a polymerisation reactor
Autor(a) principal: | |
---|---|
Data de Publicação: | 2001 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Brazilian Journal of Chemical Engineering |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322001000100010 |
Resumo: | This work presents the use of a hybrid-neural model for predictive control of a plug flow polymerisation reactor. The hybrid-neural model (HNM) is based on fundamental conservation laws associated with a neural network (NN) used to model the uncertain parameters. By simulations, the performance of this approach was studied for a peroxide-initiated styrene tubular reactor. The HNM was synthesised for a CSTR reactor with a radial basis function neural net (RBFN) used to estimate the reaction rates recursively. The adaptive HNM was incorporated in two model predictive control strategies, a direct synthesis scheme and an optimum steady state scheme. Tests for servo and regulator control showed excellent behaviour following different setpoint variations, and rejecting perturbations. The good generalisation and training capacities of hybrid models, associated with the simplicity and robustness characteristics of the MPC formulations, make an attractive combination for the control of a polymerisation reactor. |
id |
ABEQ-1_7a241bc985ee612e258da08db40a6f48 |
---|---|
oai_identifier_str |
oai:scielo:S0104-66322001000100010 |
network_acronym_str |
ABEQ-1 |
network_name_str |
Brazilian Journal of Chemical Engineering |
repository_id_str |
|
spelling |
Adaptive control using a hybrid-neural model: application to a polymerisation reactorpolymerisation controlneural networkshybrid-neural modelThis work presents the use of a hybrid-neural model for predictive control of a plug flow polymerisation reactor. The hybrid-neural model (HNM) is based on fundamental conservation laws associated with a neural network (NN) used to model the uncertain parameters. By simulations, the performance of this approach was studied for a peroxide-initiated styrene tubular reactor. The HNM was synthesised for a CSTR reactor with a radial basis function neural net (RBFN) used to estimate the reaction rates recursively. The adaptive HNM was incorporated in two model predictive control strategies, a direct synthesis scheme and an optimum steady state scheme. Tests for servo and regulator control showed excellent behaviour following different setpoint variations, and rejecting perturbations. The good generalisation and training capacities of hybrid models, associated with the simplicity and robustness characteristics of the MPC formulations, make an attractive combination for the control of a polymerisation reactor.Brazilian Society of Chemical Engineering2001-03-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322001000100010Brazilian Journal of Chemical Engineering v.18 n.1 2001reponame:Brazilian Journal of Chemical Engineeringinstname:Associação Brasileira de Engenharia Química (ABEQ)instacron:ABEQ10.1590/S0104-66322001000100010info:eu-repo/semantics/openAccessCubillos,F.Callejas,H.Lima,E.L.Vega,M.P.eng2001-05-25T00:00:00Zoai:scielo:S0104-66322001000100010Revistahttps://www.scielo.br/j/bjce/https://old.scielo.br/oai/scielo-oai.phprgiudici@usp.br||rgiudici@usp.br1678-43830104-6632opendoar:2001-05-25T00:00Brazilian Journal of Chemical Engineering - Associação Brasileira de Engenharia Química (ABEQ)false |
dc.title.none.fl_str_mv |
Adaptive control using a hybrid-neural model: application to a polymerisation reactor |
title |
Adaptive control using a hybrid-neural model: application to a polymerisation reactor |
spellingShingle |
Adaptive control using a hybrid-neural model: application to a polymerisation reactor Cubillos,F. polymerisation control neural networks hybrid-neural model |
title_short |
Adaptive control using a hybrid-neural model: application to a polymerisation reactor |
title_full |
Adaptive control using a hybrid-neural model: application to a polymerisation reactor |
title_fullStr |
Adaptive control using a hybrid-neural model: application to a polymerisation reactor |
title_full_unstemmed |
Adaptive control using a hybrid-neural model: application to a polymerisation reactor |
title_sort |
Adaptive control using a hybrid-neural model: application to a polymerisation reactor |
author |
Cubillos,F. |
author_facet |
Cubillos,F. Callejas,H. Lima,E.L. Vega,M.P. |
author_role |
author |
author2 |
Callejas,H. Lima,E.L. Vega,M.P. |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Cubillos,F. Callejas,H. Lima,E.L. Vega,M.P. |
dc.subject.por.fl_str_mv |
polymerisation control neural networks hybrid-neural model |
topic |
polymerisation control neural networks hybrid-neural model |
description |
This work presents the use of a hybrid-neural model for predictive control of a plug flow polymerisation reactor. The hybrid-neural model (HNM) is based on fundamental conservation laws associated with a neural network (NN) used to model the uncertain parameters. By simulations, the performance of this approach was studied for a peroxide-initiated styrene tubular reactor. The HNM was synthesised for a CSTR reactor with a radial basis function neural net (RBFN) used to estimate the reaction rates recursively. The adaptive HNM was incorporated in two model predictive control strategies, a direct synthesis scheme and an optimum steady state scheme. Tests for servo and regulator control showed excellent behaviour following different setpoint variations, and rejecting perturbations. The good generalisation and training capacities of hybrid models, associated with the simplicity and robustness characteristics of the MPC formulations, make an attractive combination for the control of a polymerisation reactor. |
publishDate |
2001 |
dc.date.none.fl_str_mv |
2001-03-01 |
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=S0104-66322001000100010 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322001000100010 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/S0104-66322001000100010 |
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 |
Brazilian Society of Chemical Engineering |
publisher.none.fl_str_mv |
Brazilian Society of Chemical Engineering |
dc.source.none.fl_str_mv |
Brazilian Journal of Chemical Engineering v.18 n.1 2001 reponame:Brazilian Journal of Chemical Engineering instname:Associação Brasileira de Engenharia Química (ABEQ) instacron:ABEQ |
instname_str |
Associação Brasileira de Engenharia Química (ABEQ) |
instacron_str |
ABEQ |
institution |
ABEQ |
reponame_str |
Brazilian Journal of Chemical Engineering |
collection |
Brazilian Journal of Chemical Engineering |
repository.name.fl_str_mv |
Brazilian Journal of Chemical Engineering - Associação Brasileira de Engenharia Química (ABEQ) |
repository.mail.fl_str_mv |
rgiudici@usp.br||rgiudici@usp.br |
_version_ |
1754213171075219456 |