Machine learning for optimal flow control in an axial compressor
Air jets for active flow control have proved effective in postponing the onset of stall phenomenon in axial compressors. In this paper, we use a combination of machine learning and genetic algorithm to explore the optimal parameters of air jets to control rotating stall in the axial compressor CME2....
Gespeichert in:
| Veröffentlicht in: | The European physical journal. E, Soft matter and biological physics Soft matter and biological physics, 2023-04, Vol.46 (4), p.28-28, Article 28 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 28 |
|---|---|
| container_issue | 4 |
| container_start_page | 28 |
| container_title | The European physical journal. E, Soft matter and biological physics |
| container_volume | 46 |
| creator | Elhawary, M. A. Romanò, Francesco Loiseau, Jean-Christophe Dazin, Antoine |
| description | Air jets for active flow control have proved effective in postponing the onset of stall phenomenon in axial compressors. In this paper, we use a combination of machine learning and genetic algorithm to explore the optimal parameters of air jets to control rotating stall in the axial compressor CME2. Three control parameters are investigated: the absolute injection angle, the number of injector pairs and the injection velocity. Given an experimental dataset, the influence of the air jet parameters on the surge margin improvement and power balance is modeled using two shallow neural networks. Parameters of the air jets are then optimized using a genetic algorithm for three rotational velocities, i.e.,
Ω
=
3200
RPM
,
4500
RPM
and
6000
RPM
. First, surge margin improvement and power balance are being maximized independently. Then, a bi-objective optimization problem is posed to explore the trade-off between the two competing objectives. Based on the Pareto front, results suggest that a globally optimal set of parameters is obtained for a velocity ratio (defined as the ratio of the injection velocity to the rotor tip speed) ranging from 1.1 to 1.6 and an injection angle attack varying from
1
∘
to
11
∘
. These outcomes point out a potential generalization of the control strategy applicable to other compressors. |
| doi_str_mv | 10.1140/epje/s10189-023-00284-9 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_04164557v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2800198965</sourcerecordid><originalsourceid>FETCH-LOGICAL-c473t-d710280bd72ef7b5213e65a9ecc640c7ae41bf58258333fe6eb62ff2188a04883</originalsourceid><addsrcrecordid>eNqFkUtLAzEUhYMotlb_gg640cVonpPMThFfUHGj4C5k0hs7ZToZk9bHvzd1tIIbIZCQ-53DSQ5CBwSfEMLxKXQzOI0EE1XmmLIcY6p4Xm6gIaElzVUpnjbXZ04GaCfGGcY4adk2GjCJOcNSDNHZnbHTuoWsARPaun3OnA-Z7xb13DSZa_xbZn27CL7J6jYzab3XaWD9vAsQow-7aMuZJsLe9z5Cj1eXDxc3-fj--vbifJxbLtkin0iSIuJqIik4WQlKGBTClGBtwbGVBjipnFBUKMaYgwKqgjpHiVIGc6XYCB33vlPT6C6keOFDe1Prm_OxXt1hTgouhHwliT3q2S74lyXEhZ7X0ULTmBb8MuoUJP2EopIm9PAPOvPL0KaX9FSpykIkSvaUDT7GAG6dgGC9KkSvCtF9IToVor8K0WVS7n_7L6s5TNa6nwYSoHogplH7DOE3wH_enwOll7A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2800198965</pqid></control><display><type>article</type><title>Machine learning for optimal flow control in an axial compressor</title><source>Springer Nature - Complete Springer Journals</source><creator>Elhawary, M. A. ; Romanò, Francesco ; Loiseau, Jean-Christophe ; Dazin, Antoine</creator><creatorcontrib>Elhawary, M. A. ; Romanò, Francesco ; Loiseau, Jean-Christophe ; Dazin, Antoine</creatorcontrib><description>Air jets for active flow control have proved effective in postponing the onset of stall phenomenon in axial compressors. In this paper, we use a combination of machine learning and genetic algorithm to explore the optimal parameters of air jets to control rotating stall in the axial compressor CME2. Three control parameters are investigated: the absolute injection angle, the number of injector pairs and the injection velocity. Given an experimental dataset, the influence of the air jet parameters on the surge margin improvement and power balance is modeled using two shallow neural networks. Parameters of the air jets are then optimized using a genetic algorithm for three rotational velocities, i.e.,
Ω
=
3200
RPM
,
4500
RPM
and
6000
RPM
. First, surge margin improvement and power balance are being maximized independently. Then, a bi-objective optimization problem is posed to explore the trade-off between the two competing objectives. Based on the Pareto front, results suggest that a globally optimal set of parameters is obtained for a velocity ratio (defined as the ratio of the injection velocity to the rotor tip speed) ranging from 1.1 to 1.6 and an injection angle attack varying from
1
∘
to
11
∘
. These outcomes point out a potential generalization of the control strategy applicable to other compressors.</description><identifier>ISSN: 1292-8941</identifier><identifier>EISSN: 1292-895X</identifier><identifier>DOI: 10.1140/epje/s10189-023-00284-9</identifier><identifier>PMID: 37043075</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Active control ; Air jets ; Biological and Medical Physics ; Biophysics ; Complex Fluids and Microfluidics ; Complex Systems ; Condensed matter physics ; Engineering Sciences ; Flow control ; Fluid Dynamics ; Fluid mechanics ; Fluids mechanics ; Genetic algorithms ; Machine Learning ; Mechanics ; Nanotechnology ; Neural networks ; Optimization ; Parameters ; Physics ; Physics and Astronomy ; Polymer Sciences ; Quantitative AI in Complex Fluids and Complex Flows: Challenges and Benchmarks ; Regular Article - Flowing Matter ; Rotating stalls ; Soft and Granular Matter ; Statistics ; Surfaces and Interfaces ; Thin Films ; Tip speed ; Turbocompressors</subject><ispartof>The European physical journal. E, Soft matter and biological physics, 2023-04, Vol.46 (4), p.28-28, Article 28</ispartof><rights>The Author(s), under exclusive licence to EDP Sciences, SIF and Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2023. The Author(s), under exclusive licence to EDP Sciences, SIF and Springer-Verlag GmbH Germany, part of Springer Nature.</rights><rights>Copyright</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c473t-d710280bd72ef7b5213e65a9ecc640c7ae41bf58258333fe6eb62ff2188a04883</citedby><cites>FETCH-LOGICAL-c473t-d710280bd72ef7b5213e65a9ecc640c7ae41bf58258333fe6eb62ff2188a04883</cites><orcidid>0000-0003-3560-8596 ; 0000-0002-9511-4718</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1140/epje/s10189-023-00284-9$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1140/epje/s10189-023-00284-9$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>230,314,776,780,881,27901,27902,41464,42533,51294</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37043075$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://cnam.hal.science/hal-04164557$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Elhawary, M. A.</creatorcontrib><creatorcontrib>Romanò, Francesco</creatorcontrib><creatorcontrib>Loiseau, Jean-Christophe</creatorcontrib><creatorcontrib>Dazin, Antoine</creatorcontrib><title>Machine learning for optimal flow control in an axial compressor</title><title>The European physical journal. E, Soft matter and biological physics</title><addtitle>Eur. Phys. J. E</addtitle><addtitle>Eur Phys J E Soft Matter</addtitle><description>Air jets for active flow control have proved effective in postponing the onset of stall phenomenon in axial compressors. In this paper, we use a combination of machine learning and genetic algorithm to explore the optimal parameters of air jets to control rotating stall in the axial compressor CME2. Three control parameters are investigated: the absolute injection angle, the number of injector pairs and the injection velocity. Given an experimental dataset, the influence of the air jet parameters on the surge margin improvement and power balance is modeled using two shallow neural networks. Parameters of the air jets are then optimized using a genetic algorithm for three rotational velocities, i.e.,
Ω
=
3200
RPM
,
4500
RPM
and
6000
RPM
. First, surge margin improvement and power balance are being maximized independently. Then, a bi-objective optimization problem is posed to explore the trade-off between the two competing objectives. Based on the Pareto front, results suggest that a globally optimal set of parameters is obtained for a velocity ratio (defined as the ratio of the injection velocity to the rotor tip speed) ranging from 1.1 to 1.6 and an injection angle attack varying from
1
∘
to
11
∘
. These outcomes point out a potential generalization of the control strategy applicable to other compressors.</description><subject>Active control</subject><subject>Air jets</subject><subject>Biological and Medical Physics</subject><subject>Biophysics</subject><subject>Complex Fluids and Microfluidics</subject><subject>Complex Systems</subject><subject>Condensed matter physics</subject><subject>Engineering Sciences</subject><subject>Flow control</subject><subject>Fluid Dynamics</subject><subject>Fluid mechanics</subject><subject>Fluids mechanics</subject><subject>Genetic algorithms</subject><subject>Machine Learning</subject><subject>Mechanics</subject><subject>Nanotechnology</subject><subject>Neural networks</subject><subject>Optimization</subject><subject>Parameters</subject><subject>Physics</subject><subject>Physics and Astronomy</subject><subject>Polymer Sciences</subject><subject>Quantitative AI in Complex Fluids and Complex Flows: Challenges and Benchmarks</subject><subject>Regular Article - Flowing Matter</subject><subject>Rotating stalls</subject><subject>Soft and Granular Matter</subject><subject>Statistics</subject><subject>Surfaces and Interfaces</subject><subject>Thin Films</subject><subject>Tip speed</subject><subject>Turbocompressors</subject><issn>1292-8941</issn><issn>1292-895X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNqFkUtLAzEUhYMotlb_gg640cVonpPMThFfUHGj4C5k0hs7ZToZk9bHvzd1tIIbIZCQ-53DSQ5CBwSfEMLxKXQzOI0EE1XmmLIcY6p4Xm6gIaElzVUpnjbXZ04GaCfGGcY4adk2GjCJOcNSDNHZnbHTuoWsARPaun3OnA-Z7xb13DSZa_xbZn27CL7J6jYzab3XaWD9vAsQow-7aMuZJsLe9z5Cj1eXDxc3-fj--vbifJxbLtkin0iSIuJqIik4WQlKGBTClGBtwbGVBjipnFBUKMaYgwKqgjpHiVIGc6XYCB33vlPT6C6keOFDe1Prm_OxXt1hTgouhHwliT3q2S74lyXEhZ7X0ULTmBb8MuoUJP2EopIm9PAPOvPL0KaX9FSpykIkSvaUDT7GAG6dgGC9KkSvCtF9IToVor8K0WVS7n_7L6s5TNa6nwYSoHogplH7DOE3wH_enwOll7A</recordid><startdate>20230401</startdate><enddate>20230401</enddate><creator>Elhawary, M. A.</creator><creator>Romanò, Francesco</creator><creator>Loiseau, Jean-Christophe</creator><creator>Dazin, Antoine</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><general>EDP Sciences: EPJ</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0003-3560-8596</orcidid><orcidid>https://orcid.org/0000-0002-9511-4718</orcidid></search><sort><creationdate>20230401</creationdate><title>Machine learning for optimal flow control in an axial compressor</title><author>Elhawary, M. A. ; Romanò, Francesco ; Loiseau, Jean-Christophe ; Dazin, Antoine</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c473t-d710280bd72ef7b5213e65a9ecc640c7ae41bf58258333fe6eb62ff2188a04883</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Active control</topic><topic>Air jets</topic><topic>Biological and Medical Physics</topic><topic>Biophysics</topic><topic>Complex Fluids and Microfluidics</topic><topic>Complex Systems</topic><topic>Condensed matter physics</topic><topic>Engineering Sciences</topic><topic>Flow control</topic><topic>Fluid Dynamics</topic><topic>Fluid mechanics</topic><topic>Fluids mechanics</topic><topic>Genetic algorithms</topic><topic>Machine Learning</topic><topic>Mechanics</topic><topic>Nanotechnology</topic><topic>Neural networks</topic><topic>Optimization</topic><topic>Parameters</topic><topic>Physics</topic><topic>Physics and Astronomy</topic><topic>Polymer Sciences</topic><topic>Quantitative AI in Complex Fluids and Complex Flows: Challenges and Benchmarks</topic><topic>Regular Article - Flowing Matter</topic><topic>Rotating stalls</topic><topic>Soft and Granular Matter</topic><topic>Statistics</topic><topic>Surfaces and Interfaces</topic><topic>Thin Films</topic><topic>Tip speed</topic><topic>Turbocompressors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Elhawary, M. A.</creatorcontrib><creatorcontrib>Romanò, Francesco</creatorcontrib><creatorcontrib>Loiseau, Jean-Christophe</creatorcontrib><creatorcontrib>Dazin, Antoine</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>The European physical journal. E, Soft matter and biological physics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Elhawary, M. A.</au><au>Romanò, Francesco</au><au>Loiseau, Jean-Christophe</au><au>Dazin, Antoine</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine learning for optimal flow control in an axial compressor</atitle><jtitle>The European physical journal. E, Soft matter and biological physics</jtitle><stitle>Eur. Phys. J. E</stitle><addtitle>Eur Phys J E Soft Matter</addtitle><date>2023-04-01</date><risdate>2023</risdate><volume>46</volume><issue>4</issue><spage>28</spage><epage>28</epage><pages>28-28</pages><artnum>28</artnum><issn>1292-8941</issn><eissn>1292-895X</eissn><abstract>Air jets for active flow control have proved effective in postponing the onset of stall phenomenon in axial compressors. In this paper, we use a combination of machine learning and genetic algorithm to explore the optimal parameters of air jets to control rotating stall in the axial compressor CME2. Three control parameters are investigated: the absolute injection angle, the number of injector pairs and the injection velocity. Given an experimental dataset, the influence of the air jet parameters on the surge margin improvement and power balance is modeled using two shallow neural networks. Parameters of the air jets are then optimized using a genetic algorithm for three rotational velocities, i.e.,
Ω
=
3200
RPM
,
4500
RPM
and
6000
RPM
. First, surge margin improvement and power balance are being maximized independently. Then, a bi-objective optimization problem is posed to explore the trade-off between the two competing objectives. Based on the Pareto front, results suggest that a globally optimal set of parameters is obtained for a velocity ratio (defined as the ratio of the injection velocity to the rotor tip speed) ranging from 1.1 to 1.6 and an injection angle attack varying from
1
∘
to
11
∘
. These outcomes point out a potential generalization of the control strategy applicable to other compressors.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><pmid>37043075</pmid><doi>10.1140/epje/s10189-023-00284-9</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0003-3560-8596</orcidid><orcidid>https://orcid.org/0000-0002-9511-4718</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1292-8941 |
| ispartof | The European physical journal. E, Soft matter and biological physics, 2023-04, Vol.46 (4), p.28-28, Article 28 |
| issn | 1292-8941 1292-895X |
| language | eng |
| recordid | cdi_hal_primary_oai_HAL_hal_04164557v1 |
| source | Springer Nature - Complete Springer Journals |
| subjects | Active control Air jets Biological and Medical Physics Biophysics Complex Fluids and Microfluidics Complex Systems Condensed matter physics Engineering Sciences Flow control Fluid Dynamics Fluid mechanics Fluids mechanics Genetic algorithms Machine Learning Mechanics Nanotechnology Neural networks Optimization Parameters Physics Physics and Astronomy Polymer Sciences Quantitative AI in Complex Fluids and Complex Flows: Challenges and Benchmarks Regular Article - Flowing Matter Rotating stalls Soft and Granular Matter Statistics Surfaces and Interfaces Thin Films Tip speed Turbocompressors |
| title | Machine learning for optimal flow control in an axial compressor |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T17%3A25%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20learning%20for%20optimal%20flow%20control%20in%20an%20axial%20compressor&rft.jtitle=The%20European%20physical%20journal.%20E,%20Soft%20matter%20and%20biological%20physics&rft.au=Elhawary,%20M.%20A.&rft.date=2023-04-01&rft.volume=46&rft.issue=4&rft.spage=28&rft.epage=28&rft.pages=28-28&rft.artnum=28&rft.issn=1292-8941&rft.eissn=1292-895X&rft_id=info:doi/10.1140/epje/s10189-023-00284-9&rft_dat=%3Cproquest_hal_p%3E2800198965%3C/proquest_hal_p%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2800198965&rft_id=info:pmid/37043075&rfr_iscdi=true |