Closed-loop separation control using machine learning

Autores
Gautier, N.; Aider, J. L.; Duriez, Thomas Pierre Cornil; Noack, B. R.; Segond, M.; Abel, M.
Año de publicación
2015
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
We present the first closed-loop separation control experiment using a novel, model-free strategy based on genetic programming, which we call 'machine learning control'. The goal is to reduce the recirculation zone of backward-facing step flow at Reh = 1350 manipulated by a slotted jet and optically sensed by online particle image velocimetry. The feedback control law is optimized with respect to a cost functional based on the recirculation area and a penalization of the actuation. This optimization is performed employing genetic programming. After 12 generations comprised of 500 individuals, the algorithm converges to a feedback law which reduces the recirculation zone by 80 %. This machine learning control is benchmarked against the best periodic forcing which excites Kelvin-Helmholtz vortices. The machine learning control yields a new actuation mechanism resonating with the low-frequency flapping mode instability. This feedback control performs similarly to periodic forcing at the design condition but outperforms periodic forcing when the Reynolds number is varied by a factor two. The current study indicates that machine learning control can effectively explore and optimize new feedback actuation mechanisms in numerous experimental applications.
Fil: Gautier, N.. École Supérieure de Physique et Chimie Industrielles de la ville de Paris; Francia
Fil: Aider, J. L.. École Supérieure de Physique et Chimie Industrielles de la ville de Paris; Francia
Fil: Duriez, Thomas Pierre Cornil. Université de Poitiers; Francia. Universidad de Buenos Aires. Facultad de Ingeniería. Departamento de Ingeniería Mecánica. Laboratorio de Fluidodinámica; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Noack, B. R.. Université de Poitiers; Francia
Fil: Segond, M.. Ambrosys; Alemania
Fil: Abel, M.. Ambrosys; Alemania
Materia
Control Theory
Flow Control
Separated Flows
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/38415
Acceder
id CONICETDig_fca544efd0feda159226347e1feedaea
oai_identifier_str oai:ri.conicet.gov.ar:11336/38415
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Closed-loop separation control using machine learningGautier, N.Aider, J. L.Duriez, Thomas Pierre CornilNoack, B. R.Segond, M.Abel, M.Control TheoryFlow ControlSeparated Flowshttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1We present the first closed-loop separation control experiment using a novel, model-free strategy based on genetic programming, which we call 'machine learning control'. The goal is to reduce the recirculation zone of backward-facing step flow at Reh = 1350 manipulated by a slotted jet and optically sensed by online particle image velocimetry. The feedback control law is optimized with respect to a cost functional based on the recirculation area and a penalization of the actuation. This optimization is performed employing genetic programming. After 12 generations comprised of 500 individuals, the algorithm converges to a feedback law which reduces the recirculation zone by 80 %. This machine learning control is benchmarked against the best periodic forcing which excites Kelvin-Helmholtz vortices. The machine learning control yields a new actuation mechanism resonating with the low-frequency flapping mode instability. This feedback control performs similarly to periodic forcing at the design condition but outperforms periodic forcing when the Reynolds number is varied by a factor two. The current study indicates that machine learning control can effectively explore and optimize new feedback actuation mechanisms in numerous experimental applications.Fil: Gautier, N.. École Supérieure de Physique et Chimie Industrielles de la ville de Paris; FranciaFil: Aider, J. L.. École Supérieure de Physique et Chimie Industrielles de la ville de Paris; FranciaFil: Duriez, Thomas Pierre Cornil. Université de Poitiers; Francia. Universidad de Buenos Aires. Facultad de Ingeniería. Departamento de Ingeniería Mecánica. Laboratorio de Fluidodinámica; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Noack, B. R.. Université de Poitiers; FranciaFil: Segond, M.. Ambrosys; AlemaniaFil: Abel, M.. Ambrosys; AlemaniaCambridge University Press2015-05info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/38415Gautier, N.; Aider, J. L.; Duriez, Thomas Pierre Cornil; Noack, B. R.; Segond, M.; et al.; Closed-loop separation control using machine learning; Cambridge University Press; Journal of Fluid Mechanics; 770; 5-2015; 442-4570022-1120CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1017/jfm.2015.95info:eu-repo/semantics/altIdentifier/url/https://www.cambridge.org/core/journals/journal-of-fluid-mechanics/article/closedloop-separation-control-using-machine-learning/D28454120D1B533531BE9DADC9DF2548info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-10-15T15:12:51Zoai:ri.conicet.gov.ar:11336/38415instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-10-15 15:12:51.319CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Closed-loop separation control using machine learning
title Closed-loop separation control using machine learning
spellingShingle Closed-loop separation control using machine learning
Gautier, N.
Control Theory
Flow Control
Separated Flows
title_short Closed-loop separation control using machine learning
title_full Closed-loop separation control using machine learning
title_fullStr Closed-loop separation control using machine learning
title_full_unstemmed Closed-loop separation control using machine learning
title_sort Closed-loop separation control using machine learning
dc.creator.none.fl_str_mv Gautier, N.
Aider, J. L.
Duriez, Thomas Pierre Cornil
Noack, B. R.
Segond, M.
Abel, M.
author Gautier, N.
author_facet Gautier, N.
Aider, J. L.
Duriez, Thomas Pierre Cornil
Noack, B. R.
Segond, M.
Abel, M.
author_role author
author2 Aider, J. L.
Duriez, Thomas Pierre Cornil
Noack, B. R.
Segond, M.
Abel, M.
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Control Theory
Flow Control
Separated Flows
topic Control Theory
Flow Control
Separated Flows
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv We present the first closed-loop separation control experiment using a novel, model-free strategy based on genetic programming, which we call 'machine learning control'. The goal is to reduce the recirculation zone of backward-facing step flow at Reh = 1350 manipulated by a slotted jet and optically sensed by online particle image velocimetry. The feedback control law is optimized with respect to a cost functional based on the recirculation area and a penalization of the actuation. This optimization is performed employing genetic programming. After 12 generations comprised of 500 individuals, the algorithm converges to a feedback law which reduces the recirculation zone by 80 %. This machine learning control is benchmarked against the best periodic forcing which excites Kelvin-Helmholtz vortices. The machine learning control yields a new actuation mechanism resonating with the low-frequency flapping mode instability. This feedback control performs similarly to periodic forcing at the design condition but outperforms periodic forcing when the Reynolds number is varied by a factor two. The current study indicates that machine learning control can effectively explore and optimize new feedback actuation mechanisms in numerous experimental applications.
Fil: Gautier, N.. École Supérieure de Physique et Chimie Industrielles de la ville de Paris; Francia
Fil: Aider, J. L.. École Supérieure de Physique et Chimie Industrielles de la ville de Paris; Francia
Fil: Duriez, Thomas Pierre Cornil. Université de Poitiers; Francia. Universidad de Buenos Aires. Facultad de Ingeniería. Departamento de Ingeniería Mecánica. Laboratorio de Fluidodinámica; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Noack, B. R.. Université de Poitiers; Francia
Fil: Segond, M.. Ambrosys; Alemania
Fil: Abel, M.. Ambrosys; Alemania
description We present the first closed-loop separation control experiment using a novel, model-free strategy based on genetic programming, which we call 'machine learning control'. The goal is to reduce the recirculation zone of backward-facing step flow at Reh = 1350 manipulated by a slotted jet and optically sensed by online particle image velocimetry. The feedback control law is optimized with respect to a cost functional based on the recirculation area and a penalization of the actuation. This optimization is performed employing genetic programming. After 12 generations comprised of 500 individuals, the algorithm converges to a feedback law which reduces the recirculation zone by 80 %. This machine learning control is benchmarked against the best periodic forcing which excites Kelvin-Helmholtz vortices. The machine learning control yields a new actuation mechanism resonating with the low-frequency flapping mode instability. This feedback control performs similarly to periodic forcing at the design condition but outperforms periodic forcing when the Reynolds number is varied by a factor two. The current study indicates that machine learning control can effectively explore and optimize new feedback actuation mechanisms in numerous experimental applications.
publishDate 2015
dc.date.none.fl_str_mv 2015-05
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/38415
Gautier, N.; Aider, J. L.; Duriez, Thomas Pierre Cornil; Noack, B. R.; Segond, M.; et al.; Closed-loop separation control using machine learning; Cambridge University Press; Journal of Fluid Mechanics; 770; 5-2015; 442-457
0022-1120
CONICET Digital
CONICET
url http://hdl.handle.net/11336/38415
identifier_str_mv Gautier, N.; Aider, J. L.; Duriez, Thomas Pierre Cornil; Noack, B. R.; Segond, M.; et al.; Closed-loop separation control using machine learning; Cambridge University Press; Journal of Fluid Mechanics; 770; 5-2015; 442-457
0022-1120
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1017/jfm.2015.95
info:eu-repo/semantics/altIdentifier/url/https://www.cambridge.org/core/journals/journal-of-fluid-mechanics/article/closedloop-separation-control-using-machine-learning/D28454120D1B533531BE9DADC9DF2548
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Cambridge University Press
publisher.none.fl_str_mv Cambridge University Press
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1846083277063979008
score 12.891075

Publicaciones similares