Predicting the passive control of fluid forces over circular cylinder in a time dependent flow using neuro-computing

The objective of this research is to combine Artificial Neural Networks (ANNs) and Computational Fluid Dynamics (CFD) approaches to leverage the advantages of both methods. To achieve this goal, we introduce a new artificial neural network architecture designed specifically for predicting fluid forc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:AIP advances 2024-12, Vol.14 (12), p.125103-125103-11
Hauptverfasser: Asghar, Atif, Mahmood, Rashid, Majeed, Afraz Hussain, Alotaibi, Hammad, Refaie Ali, Ahmed
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 125103-11
container_issue 12
container_start_page 125103
container_title AIP advances
container_volume 14
creator Asghar, Atif
Mahmood, Rashid
Majeed, Afraz Hussain
Alotaibi, Hammad
Refaie Ali, Ahmed
description The objective of this research is to combine Artificial Neural Networks (ANNs) and Computational Fluid Dynamics (CFD) approaches to leverage the advantages of both methods. To achieve this goal, we introduce a new artificial neural network architecture designed specifically for predicting fluid forces within the CFD framework, aiming to reduce computational costs. Initially, time-dependent simulations around a rigid cylinder and a passive device (attached and detached) were conducted, followed by a thorough analysis of the hydrodynamic drag and lift forces encountered by the cylinder and passive device with various length L=0.1,0.2,0.3 and gap spacing Gi=0.1,0.2,0.3. The inhibition of vortex shedding is noted for gap separations of 0.1 and 0.2. However, a splitter plate of insufficient length or placed at an unsuitable distance from an obstacle yields no significant benefits. The finite element method is employed as a computational technique to address complex nonlinear governing equations. The nonlinear partial differential equations are spatially discretized with the finite element method, while temporal derivatives are addressed using a backward implicit Euler scheme. Velocity and pressure plots are provided to illustrate the physical aspects of the problem. The results indicate that the introduction of a splitter plate has reduced vortex shedding, leading to a steady flow regime, as evidenced by the stable drag and lift coefficients. The data obtained from simulations were utilized to train a neural network architecture based on the feed-forward backpropagation algorithm of Levenberg–Marquardt. Following training and validation stages, predictions for drag and lift coefficients were made without the need for additional CFD simulations. These results show that the mean square error values are very close to zero, indicating a strong correlation between the fluid force coefficients obtained from CFD and those predicted by the ANN. Additionally, a significant reduction in computational time was achieved without sacrificing the accuracy of the drag and lift coefficient predictions.
doi_str_mv 10.1063/5.0235129
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1063_5_0235129</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_6cd013cbc63b4a569ad4c2334f70725e</doaj_id><sourcerecordid>3138960665</sourcerecordid><originalsourceid>FETCH-LOGICAL-c283t-49c3cbb105b6c8fda374b58d91b467fb766fab3a6ba59f6709f79dabbd184b543</originalsourceid><addsrcrecordid>eNp9kUtLAzEUhQdRsFQX_oOAK4XRZPKYyVLEFwi60HXIs6ZMJ2OSqfTfm9oirrybezl895wLt6rOELxCkOFregUbTFHDD6pZg2hX46Zhh3_m4-o0pSUsRTiCHZlV-TVa43X2wwLkDwtGmZJfW6DDkGPoQXDA9ZM3wIWobQJhbSPQPuqpl2XY9H4wRfEDkCD7lQXGjrZIQy574QtMaes82CmGWofVOG2TTqojJ_tkT_d9Xr3f373dPtbPLw9PtzfPtW46nGvCNdZKIUgV050zErdE0c5wpAhrnWoZc1JhyZSk3LEWctdyI5UyqCsgwfPqaedrglyKMfqVjBsRpBc_QogLIWP2ureCaQNRSdMMKyIp49IQ3WBMXAvbhtridb7zGmP4nGzKYhmmOJTzBUa44wwyRgt1saN0DClF635TERTbHwkq9j8q7OWOTdpnmX0Y_oG_AeP7khE</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3138960665</pqid></control><display><type>article</type><title>Predicting the passive control of fluid forces over circular cylinder in a time dependent flow using neuro-computing</title><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>Free Full-Text Journals in Chemistry</source><creator>Asghar, Atif ; Mahmood, Rashid ; Majeed, Afraz Hussain ; Alotaibi, Hammad ; Refaie Ali, Ahmed</creator><creatorcontrib>Asghar, Atif ; Mahmood, Rashid ; Majeed, Afraz Hussain ; Alotaibi, Hammad ; Refaie Ali, Ahmed</creatorcontrib><description>The objective of this research is to combine Artificial Neural Networks (ANNs) and Computational Fluid Dynamics (CFD) approaches to leverage the advantages of both methods. To achieve this goal, we introduce a new artificial neural network architecture designed specifically for predicting fluid forces within the CFD framework, aiming to reduce computational costs. Initially, time-dependent simulations around a rigid cylinder and a passive device (attached and detached) were conducted, followed by a thorough analysis of the hydrodynamic drag and lift forces encountered by the cylinder and passive device with various length L=0.1,0.2,0.3 and gap spacing Gi=0.1,0.2,0.3. The inhibition of vortex shedding is noted for gap separations of 0.1 and 0.2. However, a splitter plate of insufficient length or placed at an unsuitable distance from an obstacle yields no significant benefits. The finite element method is employed as a computational technique to address complex nonlinear governing equations. The nonlinear partial differential equations are spatially discretized with the finite element method, while temporal derivatives are addressed using a backward implicit Euler scheme. Velocity and pressure plots are provided to illustrate the physical aspects of the problem. The results indicate that the introduction of a splitter plate has reduced vortex shedding, leading to a steady flow regime, as evidenced by the stable drag and lift coefficients. The data obtained from simulations were utilized to train a neural network architecture based on the feed-forward backpropagation algorithm of Levenberg–Marquardt. Following training and validation stages, predictions for drag and lift coefficients were made without the need for additional CFD simulations. These results show that the mean square error values are very close to zero, indicating a strong correlation between the fluid force coefficients obtained from CFD and those predicted by the ANN. Additionally, a significant reduction in computational time was achieved without sacrificing the accuracy of the drag and lift coefficient predictions.</description><identifier>ISSN: 2158-3226</identifier><identifier>EISSN: 2158-3226</identifier><identifier>DOI: 10.1063/5.0235129</identifier><identifier>CODEN: AAIDBI</identifier><language>eng</language><publisher>Melville: American Institute of Physics</publisher><subject>Aerodynamic coefficients ; Algorithms ; Artificial neural networks ; Back propagation networks ; Circular cylinders ; Computational efficiency ; Computational fluid dynamics ; Computer simulation ; Computing costs ; Computing time ; Drag ; Drag reduction ; Finite element analysis ; Finite element method ; Neural networks ; Nonlinear differential equations ; Partial differential equations ; Passive control ; Predictive control ; Simulation ; Splitter plates ; Steady flow ; Time dependence ; Time dependent analysis ; Vortex shedding</subject><ispartof>AIP advances, 2024-12, Vol.14 (12), p.125103-125103-11</ispartof><rights>Author(s)</rights><rights>2024 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC) license (https://creativecommons.org/licenses/by-nc/4.0/).</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c283t-49c3cbb105b6c8fda374b58d91b467fb766fab3a6ba59f6709f79dabbd184b543</cites><orcidid>0000-0003-0523-2794 ; 0009-0007-5531-6255 ; 0000-0002-1012-0781</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,778,782,862,2098,27911,27912</link.rule.ids></links><search><creatorcontrib>Asghar, Atif</creatorcontrib><creatorcontrib>Mahmood, Rashid</creatorcontrib><creatorcontrib>Majeed, Afraz Hussain</creatorcontrib><creatorcontrib>Alotaibi, Hammad</creatorcontrib><creatorcontrib>Refaie Ali, Ahmed</creatorcontrib><title>Predicting the passive control of fluid forces over circular cylinder in a time dependent flow using neuro-computing</title><title>AIP advances</title><description>The objective of this research is to combine Artificial Neural Networks (ANNs) and Computational Fluid Dynamics (CFD) approaches to leverage the advantages of both methods. To achieve this goal, we introduce a new artificial neural network architecture designed specifically for predicting fluid forces within the CFD framework, aiming to reduce computational costs. Initially, time-dependent simulations around a rigid cylinder and a passive device (attached and detached) were conducted, followed by a thorough analysis of the hydrodynamic drag and lift forces encountered by the cylinder and passive device with various length L=0.1,0.2,0.3 and gap spacing Gi=0.1,0.2,0.3. The inhibition of vortex shedding is noted for gap separations of 0.1 and 0.2. However, a splitter plate of insufficient length or placed at an unsuitable distance from an obstacle yields no significant benefits. The finite element method is employed as a computational technique to address complex nonlinear governing equations. The nonlinear partial differential equations are spatially discretized with the finite element method, while temporal derivatives are addressed using a backward implicit Euler scheme. Velocity and pressure plots are provided to illustrate the physical aspects of the problem. The results indicate that the introduction of a splitter plate has reduced vortex shedding, leading to a steady flow regime, as evidenced by the stable drag and lift coefficients. The data obtained from simulations were utilized to train a neural network architecture based on the feed-forward backpropagation algorithm of Levenberg–Marquardt. Following training and validation stages, predictions for drag and lift coefficients were made without the need for additional CFD simulations. These results show that the mean square error values are very close to zero, indicating a strong correlation between the fluid force coefficients obtained from CFD and those predicted by the ANN. Additionally, a significant reduction in computational time was achieved without sacrificing the accuracy of the drag and lift coefficient predictions.</description><subject>Aerodynamic coefficients</subject><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Back propagation networks</subject><subject>Circular cylinders</subject><subject>Computational efficiency</subject><subject>Computational fluid dynamics</subject><subject>Computer simulation</subject><subject>Computing costs</subject><subject>Computing time</subject><subject>Drag</subject><subject>Drag reduction</subject><subject>Finite element analysis</subject><subject>Finite element method</subject><subject>Neural networks</subject><subject>Nonlinear differential equations</subject><subject>Partial differential equations</subject><subject>Passive control</subject><subject>Predictive control</subject><subject>Simulation</subject><subject>Splitter plates</subject><subject>Steady flow</subject><subject>Time dependence</subject><subject>Time dependent analysis</subject><subject>Vortex shedding</subject><issn>2158-3226</issn><issn>2158-3226</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNp9kUtLAzEUhQdRsFQX_oOAK4XRZPKYyVLEFwi60HXIs6ZMJ2OSqfTfm9oirrybezl895wLt6rOELxCkOFregUbTFHDD6pZg2hX46Zhh3_m4-o0pSUsRTiCHZlV-TVa43X2wwLkDwtGmZJfW6DDkGPoQXDA9ZM3wIWobQJhbSPQPuqpl2XY9H4wRfEDkCD7lQXGjrZIQy574QtMaes82CmGWofVOG2TTqojJ_tkT_d9Xr3f373dPtbPLw9PtzfPtW46nGvCNdZKIUgV050zErdE0c5wpAhrnWoZc1JhyZSk3LEWctdyI5UyqCsgwfPqaedrglyKMfqVjBsRpBc_QogLIWP2ureCaQNRSdMMKyIp49IQ3WBMXAvbhtridb7zGmP4nGzKYhmmOJTzBUa44wwyRgt1saN0DClF635TERTbHwkq9j8q7OWOTdpnmX0Y_oG_AeP7khE</recordid><startdate>20241201</startdate><enddate>20241201</enddate><creator>Asghar, Atif</creator><creator>Mahmood, Rashid</creator><creator>Majeed, Afraz Hussain</creator><creator>Alotaibi, Hammad</creator><creator>Refaie Ali, Ahmed</creator><general>American Institute of Physics</general><general>AIP Publishing LLC</general><scope>AJDQP</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-0523-2794</orcidid><orcidid>https://orcid.org/0009-0007-5531-6255</orcidid><orcidid>https://orcid.org/0000-0002-1012-0781</orcidid></search><sort><creationdate>20241201</creationdate><title>Predicting the passive control of fluid forces over circular cylinder in a time dependent flow using neuro-computing</title><author>Asghar, Atif ; Mahmood, Rashid ; Majeed, Afraz Hussain ; Alotaibi, Hammad ; Refaie Ali, Ahmed</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c283t-49c3cbb105b6c8fda374b58d91b467fb766fab3a6ba59f6709f79dabbd184b543</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Aerodynamic coefficients</topic><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Back propagation networks</topic><topic>Circular cylinders</topic><topic>Computational efficiency</topic><topic>Computational fluid dynamics</topic><topic>Computer simulation</topic><topic>Computing costs</topic><topic>Computing time</topic><topic>Drag</topic><topic>Drag reduction</topic><topic>Finite element analysis</topic><topic>Finite element method</topic><topic>Neural networks</topic><topic>Nonlinear differential equations</topic><topic>Partial differential equations</topic><topic>Passive control</topic><topic>Predictive control</topic><topic>Simulation</topic><topic>Splitter plates</topic><topic>Steady flow</topic><topic>Time dependence</topic><topic>Time dependent analysis</topic><topic>Vortex shedding</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Asghar, Atif</creatorcontrib><creatorcontrib>Mahmood, Rashid</creatorcontrib><creatorcontrib>Majeed, Afraz Hussain</creatorcontrib><creatorcontrib>Alotaibi, Hammad</creatorcontrib><creatorcontrib>Refaie Ali, Ahmed</creatorcontrib><collection>AIP Open Access Journals</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>AIP advances</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Asghar, Atif</au><au>Mahmood, Rashid</au><au>Majeed, Afraz Hussain</au><au>Alotaibi, Hammad</au><au>Refaie Ali, Ahmed</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting the passive control of fluid forces over circular cylinder in a time dependent flow using neuro-computing</atitle><jtitle>AIP advances</jtitle><date>2024-12-01</date><risdate>2024</risdate><volume>14</volume><issue>12</issue><spage>125103</spage><epage>125103-11</epage><pages>125103-125103-11</pages><issn>2158-3226</issn><eissn>2158-3226</eissn><coden>AAIDBI</coden><abstract>The objective of this research is to combine Artificial Neural Networks (ANNs) and Computational Fluid Dynamics (CFD) approaches to leverage the advantages of both methods. To achieve this goal, we introduce a new artificial neural network architecture designed specifically for predicting fluid forces within the CFD framework, aiming to reduce computational costs. Initially, time-dependent simulations around a rigid cylinder and a passive device (attached and detached) were conducted, followed by a thorough analysis of the hydrodynamic drag and lift forces encountered by the cylinder and passive device with various length L=0.1,0.2,0.3 and gap spacing Gi=0.1,0.2,0.3. The inhibition of vortex shedding is noted for gap separations of 0.1 and 0.2. However, a splitter plate of insufficient length or placed at an unsuitable distance from an obstacle yields no significant benefits. The finite element method is employed as a computational technique to address complex nonlinear governing equations. The nonlinear partial differential equations are spatially discretized with the finite element method, while temporal derivatives are addressed using a backward implicit Euler scheme. Velocity and pressure plots are provided to illustrate the physical aspects of the problem. The results indicate that the introduction of a splitter plate has reduced vortex shedding, leading to a steady flow regime, as evidenced by the stable drag and lift coefficients. The data obtained from simulations were utilized to train a neural network architecture based on the feed-forward backpropagation algorithm of Levenberg–Marquardt. Following training and validation stages, predictions for drag and lift coefficients were made without the need for additional CFD simulations. These results show that the mean square error values are very close to zero, indicating a strong correlation between the fluid force coefficients obtained from CFD and those predicted by the ANN. Additionally, a significant reduction in computational time was achieved without sacrificing the accuracy of the drag and lift coefficient predictions.</abstract><cop>Melville</cop><pub>American Institute of Physics</pub><doi>10.1063/5.0235129</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0003-0523-2794</orcidid><orcidid>https://orcid.org/0009-0007-5531-6255</orcidid><orcidid>https://orcid.org/0000-0002-1012-0781</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2158-3226
ispartof AIP advances, 2024-12, Vol.14 (12), p.125103-125103-11
issn 2158-3226
2158-3226
language eng
recordid cdi_crossref_primary_10_1063_5_0235129
source DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; Free Full-Text Journals in Chemistry
subjects Aerodynamic coefficients
Algorithms
Artificial neural networks
Back propagation networks
Circular cylinders
Computational efficiency
Computational fluid dynamics
Computer simulation
Computing costs
Computing time
Drag
Drag reduction
Finite element analysis
Finite element method
Neural networks
Nonlinear differential equations
Partial differential equations
Passive control
Predictive control
Simulation
Splitter plates
Steady flow
Time dependence
Time dependent analysis
Vortex shedding
title Predicting the passive control of fluid forces over circular cylinder in a time dependent flow using neuro-computing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T11%3A12%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predicting%20the%20passive%20control%20of%20fluid%20forces%20over%20circular%20cylinder%20in%20a%20time%20dependent%20flow%20using%20neuro-computing&rft.jtitle=AIP%20advances&rft.au=Asghar,%20Atif&rft.date=2024-12-01&rft.volume=14&rft.issue=12&rft.spage=125103&rft.epage=125103-11&rft.pages=125103-125103-11&rft.issn=2158-3226&rft.eissn=2158-3226&rft.coden=AAIDBI&rft_id=info:doi/10.1063/5.0235129&rft_dat=%3Cproquest_cross%3E3138960665%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3138960665&rft_id=info:pmid/&rft_doaj_id=oai_doaj_org_article_6cd013cbc63b4a569ad4c2334f70725e&rfr_iscdi=true