Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
We present the first application of an artificial neural network trained through a deep reinforcement learning agent to perform active flow control. It is shown that, in a two-dimensional simulation of the Kármán vortex street at moderate Reynolds number ( $Re=100$ ), our artificial neural network i...
Uloženo v:
| Vydáno v: | Journal of fluid mechanics Ročník 865; s. 281 - 302 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Cambridge, UK
Cambridge University Press
25.04.2019
|
| Témata: | |
| ISSN: | 0022-1120, 1469-7645 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | We present the first application of an artificial neural network trained through a deep reinforcement learning agent to perform active flow control. It is shown that, in a two-dimensional simulation of the Kármán vortex street at moderate Reynolds number (
$Re=100$
), our artificial neural network is able to learn an active control strategy from experimenting with the mass flow rates of two jets on the sides of a cylinder. By interacting with the unsteady wake, the artificial neural network successfully stabilizes the vortex alley and reduces drag by approximately 8 %. This is performed while using small mass flow rates for the actuation, of the order of 0.5 % of the mass flow rate intersecting the cylinder cross-section once a new pseudo-periodic shedding regime is found. This opens the way to a new class of methods for performing active flow control. |
|---|---|
| AbstractList | We present the first application of an artificial neural network trained through a deep reinforcement learning agent to perform active flow control. It is shown that, in a two-dimensional simulation of the Kármán vortex street at moderate Reynolds number (\(Re=100\)), our artificial neural network is able to learn an active control strategy from experimenting with the mass flow rates of two jets on the sides of a cylinder. By interacting with the unsteady wake, the artificial neural network successfully stabilizes the vortex alley and reduces drag by approximately 8 %. This is performed while using small mass flow rates for the actuation, of the order of 0.5 % of the mass flow rate intersecting the cylinder cross-section once a new pseudo-periodic shedding regime is found. This opens the way to a new class of methods for performing active flow control. We present the first application of an artificial neural network trained through a deep reinforcement learning agent to perform active flow control. It is shown that, in a two-dimensional simulation of the Kármán vortex street at moderate Reynolds number ( $Re=100$ ), our artificial neural network is able to learn an active control strategy from experimenting with the mass flow rates of two jets on the sides of a cylinder. By interacting with the unsteady wake, the artificial neural network successfully stabilizes the vortex alley and reduces drag by approximately 8 %. This is performed while using small mass flow rates for the actuation, of the order of 0.5 % of the mass flow rate intersecting the cylinder cross-section once a new pseudo-periodic shedding regime is found. This opens the way to a new class of methods for performing active flow control. |
| Author | Rabault, Jean Réglade, Ulysse Jensen, Atle Kuchta, Miroslav Cerardi, Nicolas |
| Author_xml | – sequence: 1 givenname: Jean orcidid: 0000-0002-7244-6592 surname: Rabault fullname: Rabault, Jean email: jean.rblt@gmail.com organization: Department of Mathematics, University of Oslo, 0316 Oslo, Norway – sequence: 2 givenname: Miroslav surname: Kuchta fullname: Kuchta, Miroslav organization: Department of Mathematics, University of Oslo, 0316 Oslo, Norway – sequence: 3 givenname: Atle surname: Jensen fullname: Jensen, Atle organization: Department of Mathematics, University of Oslo, 0316 Oslo, Norway – sequence: 4 givenname: Ulysse surname: Réglade fullname: Réglade, Ulysse organization: Department of Mathematics, University of Oslo, 0316 Oslo, Norway – sequence: 5 givenname: Nicolas surname: Cerardi fullname: Cerardi, Nicolas organization: Department of Mathematics, University of Oslo, 0316 Oslo, Norway |
| BookMark | eNp1kE1LAzEURYNUsK2u_AMBlzI1yUxnJstS_IKCG10PmcxLmzpN6kvaor_eqa0Ioqu7Ofe9yxmQnvMOCLnkbMQZL26WZjUSjMtRLk5In2e5TIo8G_dInzEhEs4FOyODEJaM8ZTJok8-JhitsdqqljrY4FfEncfXQCMq66ChcYF-M1_QBmBNEawzHjWswEXagkJn3Zw2Nmi_BaTau4i-paFrR5hbCLTDqdLRboGa1u--kXNyalQb4OKYQ_Jyd_s8fUhmT_eP08ks0RkTMambvBR1ppWQXApW8NyU40xLyJUsy1SALk3N0_E4K-uGcS2b2ujcaFGzUhWpSYfk6nB3jf5tAyFWS79B172sBJepSHmasY7iB0qjDwHBVNpGFe1-q7JtxVm1V1x1iqu94ioXXef6V2eNdqXw_R86OdJqVaNt5vAz5C_-E4QKkZM |
| CitedBy_id | crossref_primary_10_3390_en15041513 crossref_primary_10_1016_j_apor_2021_102676 crossref_primary_10_1017_jfm_2021_812 crossref_primary_10_1038_s41598_023_36560_z crossref_primary_10_1088_2632_2153_abdaf8 crossref_primary_10_1016_j_jcp_2020_109824 crossref_primary_10_1017_jfm_2022_1088 crossref_primary_10_3390_biomimetics10070427 crossref_primary_10_1016_j_euromechflu_2023_12_001 crossref_primary_10_1177_09544100241264049 crossref_primary_10_1063_5_0287427 crossref_primary_10_1063_5_0291803 crossref_primary_10_1002_gamm_202100007 crossref_primary_10_1088_1361_6501_ab82be crossref_primary_10_1017_jfm_2023_775 crossref_primary_10_1016_j_engappai_2025_110749 crossref_primary_10_1016_j_flowmeasinst_2025_103039 crossref_primary_10_1016_j_ijheatfluidflow_2022_109010 crossref_primary_10_1073_pnas_2506351122 crossref_primary_10_1109_ACCESS_2022_3204968 crossref_primary_10_1063_5_0217692 crossref_primary_10_3390_s25165149 crossref_primary_10_1017_jfm_2024_333 crossref_primary_10_1007_s10409_021_01149_0 crossref_primary_10_1017_jfm_2020_1170 crossref_primary_10_1038_s41598_021_04204_9 crossref_primary_10_1080_14685248_2020_1797059 crossref_primary_10_1016_j_cja_2021_07_027 crossref_primary_10_1016_j_ijheatfluidflow_2022_109008 crossref_primary_10_2514_1_J059447 crossref_primary_10_1007_s00162_023_00663_0 crossref_primary_10_1016_j_icheatmasstransfer_2025_109203 crossref_primary_10_1063_5_0272178 crossref_primary_10_1016_j_combustflame_2023_113094 crossref_primary_10_1016_j_rineng_2023_101118 crossref_primary_10_1063_5_0223543 crossref_primary_10_1088_1361_6501_ad3fd3 crossref_primary_10_1007_s42241_020_0027_z crossref_primary_10_1007_s11012_024_01808_z crossref_primary_10_1017_jfm_2024_77 crossref_primary_10_1016_j_jcp_2024_113070 crossref_primary_10_1063_5_0190452 crossref_primary_10_1109_TCST_2025_3539219 crossref_primary_10_1063_5_0281470 crossref_primary_10_3390_computation8010015 crossref_primary_10_1016_j_ijthermalsci_2023_108618 crossref_primary_10_1007_s42241_020_0026_0 crossref_primary_10_1016_j_ijthermalsci_2021_107058 crossref_primary_10_1017_jfm_2023_637 crossref_primary_10_1063_5_0220149 crossref_primary_10_1088_1674_4926_24110006 crossref_primary_10_1002_fld_5025 crossref_primary_10_1016_j_jocs_2023_102171 crossref_primary_10_3390_fluids8070208 crossref_primary_10_1017_jfm_2024_558 crossref_primary_10_1017_jfm_2022_1050 crossref_primary_10_1063_5_0218408 crossref_primary_10_1007_s10483_022_2940_9 crossref_primary_10_3389_frlct_2024_1328004 crossref_primary_10_3390_jpm13050787 crossref_primary_10_1007_s00366_024_02093_w crossref_primary_10_1016_j_procs_2024_07_006 crossref_primary_10_1177_14680874231184002 crossref_primary_10_3390_aerospace8010018 crossref_primary_10_1017_jfm_2024_69 crossref_primary_10_1016_j_oceaneng_2021_110357 crossref_primary_10_1049_rpg2_13133 crossref_primary_10_1063_5_0253696 crossref_primary_10_1080_09544828_2024_2366686 crossref_primary_10_1016_j_ijheatfluidflow_2023_109200 crossref_primary_10_1016_j_paerosci_2022_100849 crossref_primary_10_1016_j_jcp_2022_111271 crossref_primary_10_1155_2024_5535800 crossref_primary_10_1007_s00348_023_03587_x crossref_primary_10_1063_5_0229981 crossref_primary_10_1016_j_jocs_2022_101884 crossref_primary_10_1017_jfm_2020_1028 crossref_primary_10_1088_1742_6596_2753_1_012022 crossref_primary_10_3390_act10110286 crossref_primary_10_1140_epje_s10189_023_00284_9 crossref_primary_10_3390_gels10060403 crossref_primary_10_1108_HFF_10_2023_0659 crossref_primary_10_1017_jfm_2025_27 crossref_primary_10_1016_j_oceaneng_2024_119116 crossref_primary_10_3390_act13120488 crossref_primary_10_1038_s41598_023_29525_9 crossref_primary_10_1063_5_0220129 crossref_primary_10_1063_1_5132378 crossref_primary_10_2514_1_A36237 crossref_primary_10_1007_s11012_024_01830_1 crossref_primary_10_1098_rspa_2024_0222 crossref_primary_10_1016_j_applthermaleng_2022_119633 crossref_primary_10_1063_5_0008889 crossref_primary_10_1016_j_ijheatmasstransfer_2022_123655 crossref_primary_10_1038_s41467_025_56408_6 crossref_primary_10_1063_5_0153181 crossref_primary_10_1017_jfm_2023_76 crossref_primary_10_1007_s00466_023_02434_4 crossref_primary_10_1007_s10494_025_00697_w crossref_primary_10_1007_s10409_021_01143_6 crossref_primary_10_2514_1_J064790 crossref_primary_10_1017_jfm_2019_469 crossref_primary_10_2514_1_J062801 crossref_primary_10_1016_j_engappai_2025_111125 crossref_primary_10_1017_jfm_2024_47 crossref_primary_10_3390_aerospace11080686 crossref_primary_10_1017_dce_2024_38 crossref_primary_10_1017_jfm_2025_10212 crossref_primary_10_1016_j_eswa_2021_115727 crossref_primary_10_1016_j_oceaneng_2022_111840 crossref_primary_10_1017_jfm_2024_525 crossref_primary_10_1063_5_0231805 crossref_primary_10_1140_epje_s10189_023_00285_8 crossref_primary_10_1016_j_jcp_2021_110317 crossref_primary_10_3390_en13225920 crossref_primary_10_1088_1742_6596_2767_3_032047 crossref_primary_10_1016_j_flowmeasinst_2021_102047 crossref_primary_10_1016_j_compfluid_2024_106191 crossref_primary_10_1016_j_physd_2024_134096 crossref_primary_10_1016_j_jweia_2023_105632 crossref_primary_10_3390_jmse9040376 crossref_primary_10_1016_j_oceaneng_2025_120989 crossref_primary_10_1016_j_engappai_2022_105724 crossref_primary_10_1016_j_buildenv_2025_113516 crossref_primary_10_3390_pr13041055 crossref_primary_10_1016_j_ijthermalsci_2024_109547 crossref_primary_10_1109_TGRS_2019_2933054 crossref_primary_10_1016_j_geoen_2023_211925 crossref_primary_10_1016_j_oceaneng_2024_118138 crossref_primary_10_1109_TAP_2021_3096994 crossref_primary_10_1016_j_ijmecsci_2025_110517 crossref_primary_10_3390_cryst10090791 crossref_primary_10_1016_j_compbiomed_2024_108383 crossref_primary_10_1016_j_jcp_2025_113893 crossref_primary_10_1088_1742_6596_1934_1_012022 crossref_primary_10_1016_j_eswa_2022_119192 crossref_primary_10_1017_jfm_2024_503 crossref_primary_10_1073_pnas_2004939117 crossref_primary_10_1063_5_0262891 crossref_primary_10_1007_s10494_025_00642_x crossref_primary_10_1016_j_engappai_2025_110463 crossref_primary_10_1186_s43251_021_00042_x crossref_primary_10_1016_j_expthermflusci_2025_111557 crossref_primary_10_1016_j_jcp_2025_114194 crossref_primary_10_1016_j_ijheatfluidflow_2023_109139 crossref_primary_10_1016_j_jcp_2023_112436 crossref_primary_10_1038_s41598_023_34007_z crossref_primary_10_1016_j_ijheatfluidflow_2022_109094 crossref_primary_10_1007_s42791_024_00067_z crossref_primary_10_1016_j_ast_2025_110347 crossref_primary_10_1371_journal_pone_0243107 crossref_primary_10_1017_jfm_2021_301 crossref_primary_10_1109_MCSE_2023_3264340 crossref_primary_10_1007_s10494_024_00619_2 crossref_primary_10_1063_5_0219476 crossref_primary_10_1002_nme_7624 crossref_primary_10_1016_j_oceaneng_2024_116668 crossref_primary_10_1103_PhysRevFluids_8_064603 crossref_primary_10_1016_j_compfluid_2021_104973 crossref_primary_10_1155_2024_9411326 crossref_primary_10_1038_s44172_025_00446_x crossref_primary_10_1007_s10409_021_01145_4 crossref_primary_10_1016_j_jweia_2021_104600 crossref_primary_10_1063_5_0266100 crossref_primary_10_1103_8t52_mtb9 crossref_primary_10_1017_jfm_2023_1096 crossref_primary_10_1088_1361_6501_ac93a4 crossref_primary_10_1063_5_0213256 crossref_primary_10_1063_5_0237682 crossref_primary_10_1017_jfm_2023_147 crossref_primary_10_3390_jmse12091597 crossref_primary_10_1063_5_0074724 crossref_primary_10_1017_dce_2023_28 crossref_primary_10_1007_s10494_024_00609_4 crossref_primary_10_1016_j_jcp_2020_110080 crossref_primary_10_1016_j_wroa_2025_100313 crossref_primary_10_1007_s11071_025_10953_3 crossref_primary_10_3390_pr9091620 crossref_primary_10_1016_j_paerosci_2025_101130 crossref_primary_10_1016_j_renene_2025_122887 crossref_primary_10_1016_j_ijheatmasstransfer_2024_125561 crossref_primary_10_1017_jfm_2019_814 crossref_primary_10_1016_j_ijheatfluidflow_2025_109913 crossref_primary_10_1017_jfm_2023_28 crossref_primary_10_1007_s42241_025_0009_2 crossref_primary_10_1109_ACCESS_2024_3512873 crossref_primary_10_1016_j_applthermaleng_2023_121919 crossref_primary_10_13111_2066_8201_2023_15_4_12 crossref_primary_10_1016_j_aei_2022_101612 crossref_primary_10_1016_j_autcon_2020_103424 crossref_primary_10_1016_j_buildenv_2024_111357 crossref_primary_10_1103_PhysRevE_104_014210 crossref_primary_10_1063_5_0281974 crossref_primary_10_1007_s40997_023_00632_2 crossref_primary_10_1063_5_0142198 crossref_primary_10_3390_fluids10050137 crossref_primary_10_1109_LCSYS_2022_3183526 crossref_primary_10_1063_5_0276738 crossref_primary_10_1016_j_ast_2021_107132 crossref_primary_10_1061__ASCE_EM_1943_7889_0001967 crossref_primary_10_1017_jfm_2021_974 crossref_primary_10_3390_fluids7020062 crossref_primary_10_1007_s42241_020_0028_y crossref_primary_10_1007_s00162_020_00518_y crossref_primary_10_3390_app14020859 crossref_primary_10_1016_j_cpc_2025_109748 crossref_primary_10_1017_jfm_2022_1043 crossref_primary_10_1016_j_engappai_2025_111873 crossref_primary_10_1063_5_0278006 crossref_primary_10_1007_s10494_024_00632_5 crossref_primary_10_3390_fluids7020056 crossref_primary_10_1007_s00162_020_00520_4 crossref_primary_10_1016_j_ast_2024_109424 crossref_primary_10_1016_j_engappai_2022_105106 crossref_primary_10_1017_jfm_2025_91 crossref_primary_10_1177_14680874211019345 crossref_primary_10_1038_s41598_023_35257_7 crossref_primary_10_1016_j_ijheatfluidflow_2021_108816 crossref_primary_10_1016_j_oceaneng_2024_118089 crossref_primary_10_3390_act11120359 crossref_primary_10_1007_s10514_021_10003_y crossref_primary_10_1007_s00521_021_06633_z crossref_primary_10_1016_j_ijheatfluidflow_2022_108997 crossref_primary_10_1063_5_0066077 crossref_primary_10_1002_we_2852 crossref_primary_10_1146_annurev_fluid_010719_060214 crossref_primary_10_1134_S001546282560066X crossref_primary_10_3390_fluids9090216 crossref_primary_10_3390_e23080941 crossref_primary_10_1016_j_matcom_2022_02_016 crossref_primary_10_1007_s00158_024_03755_5 crossref_primary_10_1063_5_0097241 crossref_primary_10_1109_TASE_2023_3315549 crossref_primary_10_1016_j_physrep_2024_05_004 crossref_primary_10_1063_5_0284388 crossref_primary_10_1017_jfm_2022_1020 crossref_primary_10_1140_epjp_s13360_023_04852_y crossref_primary_10_3934_era_2025144 crossref_primary_10_1016_j_oceaneng_2025_121453 crossref_primary_10_1016_j_ijheatfluidflow_2025_109950 crossref_primary_10_1016_j_jcp_2023_112018 crossref_primary_10_1016_j_oceaneng_2022_111436 crossref_primary_10_1016_j_ast_2024_109324 crossref_primary_10_1016_j_ijheatmasstransfer_2023_124788 crossref_primary_10_1016_j_applthermaleng_2023_120621 crossref_primary_10_1063_5_0275415 crossref_primary_10_1016_j_oceaneng_2023_115775 crossref_primary_10_1063_5_0263211 crossref_primary_10_1007_s12043_024_02794_3 crossref_primary_10_1063_5_0271616 crossref_primary_10_1016_j_atech_2024_100403 crossref_primary_10_1016_j_ast_2023_108737 crossref_primary_10_1088_1873_7005_ac4f2d crossref_primary_10_1016_j_oceaneng_2024_118531 crossref_primary_10_1038_s41598_021_01937_5 crossref_primary_10_1007_s11004_022_10033_x crossref_primary_10_1016_j_rse_2024_114425 crossref_primary_10_1088_1755_1315_867_1_012035 crossref_primary_10_1007_s00162_023_00641_6 crossref_primary_10_1017_jfm_2021_1045 |
| Cites_doi | 10.1007/978-3-642-23099-8 10.1017/jfm.2015.95 10.1145/992200.992206 10.1098/rsta.2010.0364 10.1017/jfm.2012.223 10.1098/rsta.2010.0201 10.1007/s00348-017-2382-2 10.1088/1361-6501/aa8b87 10.1109/TVCG.2016.2598838 10.1115/1.4033345 10.1006/jcss.1995.1013 10.1073/pnas.1800923115 10.1115/1.4031175 10.1017/S0022112009991418 10.1038/nature14236 10.1016/0021-9991(79)90088-3 10.1002/fld.4416 10.1002/nme.2579 10.1177/0278364913495721 10.1007/s00162-016-0392-y 10.1016/j.neunet.2014.09.003 10.1007/978-3-642-23099-8_21 10.1098/rsta.2010.0374 10.1103/PhysRevLett.96.064501 10.1063/1.869789 10.1103/PhysRevLett.109.074501 10.1017/S0022112008002073 10.1016/0893-6080(89)90020-8 10.1017/jfm.2016.803 10.1038/nature14539 10.1007/978-3-322-89849-4_39 |
| ContentType | Journal Article |
| Copyright | 2019 Cambridge University Press |
| Copyright_xml | – notice: 2019 Cambridge University Press |
| DBID | AAYXX CITATION 3V. 7TB 7U5 7UA 7XB 88I 8FD 8FE 8FG 8FK 8G5 ABJCF ABUWG AEUYN AFKRA ARAPS AZQEC BENPR BGLVJ BHPHI BKSAR C1K CCPQU DWQXO F1W FR3 GNUQQ GUQSH H8D H96 HCIFZ KR7 L.G L6V L7M M2O M2P M7S MBDVC P5Z P62 PCBAR PHGZM PHGZT PKEHL PQEST PQGLB PQQKQ PQUKI PRINS PTHSS Q9U S0W |
| DOI | 10.1017/jfm.2019.62 |
| DatabaseName | CrossRef ProQuest Central (Corporate) Mechanical & Transportation Engineering Abstracts Solid State and Superconductivity Abstracts Water Resources Abstracts ProQuest Central (purchase pre-March 2016) Science Database (Alumni Edition) Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) (purchase pre-March 2016) Research Library (Alumni Edition) ProQuest Materials Science & Engineering ProQuest Central (Alumni Edition) ProQuest One Sustainability (subscription) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central Technology Collection Natural Science Collection ProQuest Earth, Atmospheric & Aquatic Science Collection Environmental Sciences and Pollution Management ProQuest One Community College ProQuest Central Korea ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database ProQuest Central Student Research Library Prep Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources SciTech Premium Collection Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional ProQuest Engineering Collection Advanced Technologies Database with Aerospace Research Library Science Database (subscription) Engineering Database (subscription) Research Library (Corporate) Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Earth, Atmospheric & Aquatic Science Database ProQuest Central Premium ProQuest One Academic (New) ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection ProQuest Central Basic DELNET Engineering & Technology Collection |
| DatabaseTitle | CrossRef Research Library Prep ProQuest Central Student ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials SciTech Premium Collection ProQuest Central China Water Resources Abstracts Environmental Sciences and Pollution Management ProQuest One Applied & Life Sciences ProQuest One Sustainability Natural Science Collection ProQuest Central (New) Engineering Collection Advanced Technologies & Aerospace Collection Engineering Database ProQuest Science Journals (Alumni Edition) ProQuest One Academic Eastern Edition Earth, Atmospheric & Aquatic Science Database ProQuest Technology Collection ProQuest One Academic UKI Edition Solid State and Superconductivity Abstracts Engineering Research Database ProQuest One Academic ProQuest One Academic (New) Aquatic Science & Fisheries Abstracts (ASFA) Professional Technology Collection Technology Research Database ProQuest One Academic Middle East (New) Mechanical & Transportation Engineering Abstracts ProQuest Central (Alumni Edition) ProQuest One Community College Research Library (Alumni Edition) ProQuest Central Earth, Atmospheric & Aquatic Science Collection Aerospace Database ProQuest Engineering Collection ProQuest Central Korea ProQuest Research Library Advanced Technologies Database with Aerospace Civil Engineering Abstracts ProQuest Central Basic ProQuest Science Journals ProQuest SciTech Collection Advanced Technologies & Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources ASFA: Aquatic Sciences and Fisheries Abstracts ProQuest DELNET Engineering and Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) |
| DatabaseTitleList | Research Library Prep CrossRef |
| Database_xml | – sequence: 1 dbid: BENPR name: ProQuest Central - New (Subscription) url: https://www.proquest.com/central sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering Physics |
| DocumentTitleAlternate | ANNs discover control strategies for flow control J. Rabault, M. Kuchta, A. Jensen, U. Réglade and N. Cerardi |
| EISSN | 1469-7645 |
| EndPage | 302 |
| ExternalDocumentID | 10_1017_jfm_2019_62 |
| GroupedDBID | -2P -DZ -E. -~6 -~X .DC .FH 09C 09E 0E1 0R~ 29K 4.4 5GY 5VS 74X 74Y 7~V 88I 8FE 8FG 8FH 8G5 8R4 8R5 AAAZR AABES AABWE AACJH AAEED AAGFV AAKTX AAMNQ AARAB AASVR AAUIS AAUKB ABBXD ABGDZ ABITZ ABJCF ABJNI ABKKG ABMWE ABMYL ABQTM ABQWD ABROB ABTCQ ABUWG ABZCX ACBEA ACBMC ACCHT ACGFO ACGFS ACGOD ACIMK ACIWK ACQFJ ACREK ACUIJ ACUYZ ACWGA ACYZP ACZBM ACZUX ACZWT ADCGK ADDNB ADFEC ADFRT ADGEJ ADKIL ADOCW ADVJH AEBAK AEMTW AENEX AENGE AEYYC AFFUJ AFKQG AFKRA AFKSM AFLOS AFLVW AFRAH AFUTZ AGABE AGBYD AGJUD AGLWM AGOOT AHQXX AHRGI AIDUJ AIGNW AIHIV AIOIP AISIE AJ7 AJCYY AJPFC AJQAS ALMA_UNASSIGNED_HOLDINGS ALVPG ALWZO AQJOH ARABE ARAPS ATUCA AUXHV AZQEC BBLKV BENPR BGHMG BGLVJ BHPHI BKSAR BLZWO BMAJL BPHCQ C0O CBIIA CCPQU CCQAD CFAFE CHEAL CJCSC CS3 D-I DC4 DOHLZ DU5 DWQXO E.L EBS EJD F5P GNUQQ GUQSH HCIFZ HG- HST HZ~ I.6 I.7 IH6 IOEEP IS6 I~P J36 J38 J3A JHPGK JQKCU KCGVB KFECR L6V L98 LK5 LW7 M-V M2O M2P M7R M7S NIKVX O9- OYBOY P2P P62 PCBAR PQQKQ PROAC PTHSS PYCCK Q2X RAMDC RCA RNS ROL RR0 S0W S6- S6U SAAAG SC5 T9M TAE TN5 UT1 WFFJZ WH7 WQ3 WXU WXY WYP ZE2 ZMEZD ZYDXJ ~02 AAYXX ABUFD ABVKB ABVZP ABXAU ABXHF ACDLN ADMLS AEHGV AEUYN AFFHD AFZFC AKMAY CITATION PHGZM PHGZT PQGLB 3V. 7TB 7U5 7UA 7XB 8FD 8FK C1K F1W FR3 H8D H96 KR7 L.G L7M MBDVC PKEHL PQEST PQUKI PRINS Q9U |
| ID | FETCH-LOGICAL-c402t-bd682b4ca291920716f854c9e6a98832ec8fb135548bd01c9dbfc6fc2b08a73f3 |
| IEDL.DBID | M7S |
| ISICitedReferencesCount | 383 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000460815000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0022-1120 |
| IngestDate | Sat Aug 16 10:42:01 EDT 2025 Sat Nov 29 04:24:19 EST 2025 Tue Nov 18 22:18:18 EST 2025 Wed Mar 13 05:36:47 EDT 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | control theory drag reduction |
| Language | English |
| License | https://www.cambridge.org/core/terms |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c402t-bd682b4ca291920716f854c9e6a98832ec8fb135548bd01c9dbfc6fc2b08a73f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-7244-6592 |
| OpenAccessLink | http://hdl.handle.net/10852/67610 |
| PQID | 2193231340 |
| PQPubID | 34769 |
| PageCount | 22 |
| ParticipantIDs | proquest_journals_2193231340 crossref_citationtrail_10_1017_jfm_2019_62 crossref_primary_10_1017_jfm_2019_62 cambridge_journals_10_1017_jfm_2019_62 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-04-25 |
| PublicationDateYYYYMMDD | 2019-04-25 |
| PublicationDate_xml | – month: 04 year: 2019 text: 2019-04-25 day: 25 |
| PublicationDecade | 2010 |
| PublicationPlace | Cambridge, UK |
| PublicationPlace_xml | – name: Cambridge, UK – name: Cambridge |
| PublicationTitle | Journal of fluid mechanics |
| PublicationTitleAlternate | J. Fluid Mech |
| PublicationYear | 2019 |
| Publisher | Cambridge University Press |
| Publisher_xml | – name: Cambridge University Press |
| References | 1989; 2 2017; 814 1995; 50 2006; 96 2015; 521 2017; 28 2008; 608 2010; 368 2017; 23 2016; 30 1979; 30 2018; 86 2012; 703 2012; 109 2011; 369 2015; 67 2004; 30 2009; 79 2013; 32 2017; 58 2015; 61 2015; 770 2015; 518 2018 2009; 641 1998; 10 2016; 68 S0022112019000624_r5 S0022112019000624_r4 S0022112019000624_r6 S0022112019000624_r9 Abadi (S0022112019000624_r1) 2016; 16 Duan (S0022112019000624_r7) 2016 S0022112019000624_r24 S0022112019000624_r25 S0022112019000624_r22 S0022112019000624_r44 S0022112019000624_r23 S0022112019000624_r20 S0022112019000624_r42 S0022112019000624_r40 Goodfellow (S0022112019000624_r15) 2016; 1 S0022112019000624_r41 S0022112019000624_r28 S0022112019000624_r29 S0022112019000624_r26 S0022112019000624_r27 Krizhevsky (S0022112019000624_r21) 2012 Vernet (S0022112019000624_r43) 2014 Duriez (S0022112019000624_r8) 2016 He (S0022112019000624_r18) 2016 Gu (S0022112019000624_r16) 2016 S0022112019000624_r13 S0022112019000624_r35 S0022112019000624_r36 S0022112019000624_r14 S0022112019000624_r33 S0022112019000624_r11 S0022112019000624_r34 S0022112019000624_r12 S0022112019000624_r31 S0022112019000624_r32 S0022112019000624_r10 S0022112019000624_r30 S0022112019000624_r19 S0022112019000624_r17 S0022112019000624_r39 S0022112019000624_r3 S0022112019000624_r37 S0022112019000624_r38 S0022112019000624_r2 |
| References_xml | – year: 2018 article-title: Efficient collective swimming by harnessing vortices through deep reinforcement learning publication-title: Proc. Natl Acad. Sci. USA – volume: 79 start-page: 1309 issue: 11 year: 2009 end-page: 1331 article-title: Gmsh: a 3-D finite element mesh generator with built-in pre- and post-processing facilities publication-title: Intl J. Numer. Meth. Engng – volume: 30 start-page: 76 issue: 1 year: 1979 end-page: 95 article-title: A multistep technique with implicit difference schemes for calculating two- or three-dimensional cavity flows publication-title: J. Comput. Phys. – volume: 58 start-page: 103 issue: 8 year: 2017 article-title: Drag reduction of a car model by linear genetic programming control publication-title: Exp. Fluids – volume: 369 start-page: 1476 issue: 1940 year: 2011 end-page: 1494 article-title: Some aspects of aerodynamic flow control using synthetic-jet actuation publication-title: Phil. Trans. R. Soc. Lond. A – volume: 96 issue: 6 year: 2006 article-title: Delaying transition to turbulence by a passive mechanism publication-title: Phys. Rev. Lett. – volume: 32 start-page: 1238 issue: 11 year: 2013 end-page: 1274 article-title: Reinforcement learning in robotics: a survey publication-title: Intl J. Robotics Res. – volume: 68 issue: 2 year: 2016 article-title: Linear closed-loop control of fluid instabilities and noise-induced perturbations: a review of approaches and tools publication-title: Appl. Mech. Rev. – volume: 50 start-page: 132 issue: 1 year: 1995 end-page: 150 article-title: On the computational power of neural nets publication-title: J. Comput. Syst. Sci. – volume: 2 start-page: 359 issue: 5 year: 1989 end-page: 366 article-title: Multilayer feedforward networks are universal approximators publication-title: Neural Networks – volume: 608 start-page: 161 year: 2008 end-page: 196 article-title: Feedback shear layer control for bluff body drag reduction publication-title: J. Fluid Mech. – volume: 770 start-page: 442 year: 2015 end-page: 457 article-title: Closed-loop separation control using machine learning publication-title: J. Fluid Mech. – volume: 641 start-page: 1 year: 2009 end-page: 50 article-title: Closed-loop control of an open cavity flow using reduced-order models publication-title: J. Fluid Mech. – volume: 86 start-page: 255 issue: 4 year: 2018 end-page: 268 article-title: Model identification of reduced order fluid dynamics systems using deep learning publication-title: Intl J. Numer. Meth. Fluids – volume: 518 start-page: 529 issue: 7540 year: 2015 article-title: Human-level control through deep reinforcement learning publication-title: Nature – volume: 109 issue: 7 year: 2012 article-title: Revival of classical vortex generators now for transition delay publication-title: Phys. Rev. Lett. – volume: 369 start-page: 1382 issue: 1940 year: 2011 end-page: 1395 article-title: On active control of laminar–turbulent transition on two-dimensional wings publication-title: Phil. Trans. R. Soc. Lond. A – volume: 67 issue: 5 year: 2015 article-title: Closed-loop turbulence control: progress and challenges publication-title: Appl. Mech. Rev. – volume: 28 issue: 12 year: 2017 article-title: Performing particle image velocimetry using artificial neural networks: a proof-of-concept publication-title: Meas. Sci. Technol. – volume: 23 start-page: 101 issue: 1 year: 2017 end-page: 110 article-title: Visualizing the hidden activity of artificial neural networks publication-title: IEEE Trans. Vis. Comput. Graphics – volume: 521 start-page: 436 year: 2015 end-page: 444 article-title: Deep learning publication-title: Nature – volume: 30 start-page: 497 issue: 6 year: 2016 end-page: 510 article-title: A statistical learning strategy for closed-loop control of fluid flows publication-title: Theor. Comput. Fluid Dyn. – volume: 703 start-page: 326 year: 2012 end-page: 362 article-title: Closed-loop control of unsteadiness over a rounded backward-facing step publication-title: J. Fluid Mech. – volume: 814 start-page: 1 year: 2017 end-page: 4 article-title: Deep learning in fluid dynamics publication-title: J. Fluid Mech. – volume: 368 start-page: 4775 issue: 1929 year: 2010 end-page: 4806 article-title: Shark-skin surfaces for fluid-drag reduction in turbulent flow: a review publication-title: Phil. Trans. R. Soc. Lond. A – volume: 61 start-page: 85 year: 2015 end-page: 117 article-title: Deep learning in neural networks: an overview publication-title: Neural Networks – volume: 10 start-page: 1049 issue: 5 year: 1998 end-page: 1051 article-title: A large-scale control strategy for drag reduction in turbulent boundary layers publication-title: Phys. Fluids – volume: 30 start-page: 196 issue: 2 year: 2004 end-page: 199 article-title: Algorithm 832: UMFPACK v4.3 – an unsymmetric-pattern multifrontal method publication-title: ACM Trans. Math. Softw. – ident: S0022112019000624_r25 – ident: S0022112019000624_r26 doi: 10.1007/978-3-642-23099-8 – ident: S0022112019000624_r11 doi: 10.1017/jfm.2015.95 – start-page: 1097 volume-title: Adv. Neural Inform. Proc. Syst. year: 2012 ident: S0022112019000624_r21 – ident: S0022112019000624_r5 doi: 10.1145/992200.992206 – ident: S0022112019000624_r9 doi: 10.1098/rsta.2010.0364 – volume: 16 start-page: 265 volume-title: Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16) year: 2016 ident: S0022112019000624_r1 – ident: S0022112019000624_r2 doi: 10.1017/jfm.2012.223 – ident: S0022112019000624_r6 doi: 10.1098/rsta.2010.0201 – ident: S0022112019000624_r24 doi: 10.1007/s00348-017-2382-2 – ident: S0022112019000624_r30 doi: 10.1088/1361-6501/aa8b87 – ident: S0022112019000624_r31 doi: 10.1109/TVCG.2016.2598838 – ident: S0022112019000624_r40 doi: 10.1115/1.4033345 – ident: S0022112019000624_r36 – ident: S0022112019000624_r39 doi: 10.1006/jcss.1995.1013 – volume-title: Machine Learning Control – Taming Nonlinear Dynamics and Turbulence year: 2016 ident: S0022112019000624_r8 – ident: S0022112019000624_r42 doi: 10.1073/pnas.1800923115 – start-page: 1329 volume-title: International Conference on Machine Learning year: 2016 ident: S0022112019000624_r7 – ident: S0022112019000624_r4 doi: 10.1115/1.4031175 – ident: S0022112019000624_r3 doi: 10.1017/S0022112009991418 – ident: S0022112019000624_r28 doi: 10.1038/nature14236 – start-page: 2829 volume-title: Intl Conference on Machine Learning year: 2016 ident: S0022112019000624_r16 – ident: S0022112019000624_r14 doi: 10.1016/0021-9991(79)90088-3 – ident: S0022112019000624_r44 doi: 10.1002/fld.4416 – ident: S0022112019000624_r12 doi: 10.1002/nme.2579 – volume: 1 volume-title: Deep Learning year: 2016 ident: S0022112019000624_r15 – ident: S0022112019000624_r20 doi: 10.1177/0278364913495721 – ident: S0022112019000624_r17 doi: 10.1007/s00162-016-0392-y – ident: S0022112019000624_r34 doi: 10.1016/j.neunet.2014.09.003 – ident: S0022112019000624_r41 doi: 10.1007/978-3-642-23099-8_21 – ident: S0022112019000624_r32 – ident: S0022112019000624_r13 doi: 10.1098/rsta.2010.0374 – ident: S0022112019000624_r10 doi: 10.1103/PhysRevLett.96.064501 – ident: S0022112019000624_r35 doi: 10.1063/1.869789 – ident: S0022112019000624_r37 – start-page: 1 volume-title: First International Conference in Numerical and Experimental Aerodynamics of Road Vehicles and Trains (Aerovehicles 1), Bordeaux, France year: 2014 ident: S0022112019000624_r43 – ident: S0022112019000624_r38 doi: 10.1103/PhysRevLett.109.074501 – start-page: 770 volume-title: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition year: 2016 ident: S0022112019000624_r18 – ident: S0022112019000624_r29 doi: 10.1017/S0022112008002073 – ident: S0022112019000624_r19 doi: 10.1016/0893-6080(89)90020-8 – ident: S0022112019000624_r22 doi: 10.1017/jfm.2016.803 – ident: S0022112019000624_r23 doi: 10.1038/nature14539 – ident: S0022112019000624_r27 – ident: S0022112019000624_r33 doi: 10.1007/978-3-322-89849-4_39 |
| SSID | ssj0013097 |
| Score | 2.6949625 |
| Snippet | We present the first application of an artificial neural network trained through a deep reinforcement learning agent to perform active flow control. It is... |
| SourceID | proquest crossref cambridge |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 281 |
| SubjectTerms | Active control Actuation Algorithms Artificial neural networks Computer simulation Cylinders Drag reduction Flow control Flow rates Fluid dynamics Fluid flow Fluid mechanics JFM Papers Mass Mass flow rate Neural networks New class Reinforcement Reynolds number Stability Swimming |
| Title | Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control |
| URI | https://www.cambridge.org/core/product/identifier/S0022112019000624/type/journal_article https://www.proquest.com/docview/2193231340 |
| Volume | 865 |
| WOSCitedRecordID | wos000460815000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVPQU databaseName: Advanced Technologies & Aerospace Database customDbUrl: eissn: 1469-7645 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0013097 issn: 0022-1120 databaseCode: P5Z dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Earth, Atmospheric & Aquatic Science Database customDbUrl: eissn: 1469-7645 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0013097 issn: 0022-1120 databaseCode: PCBAR dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/eaasdb providerName: ProQuest – providerCode: PRVPQU databaseName: Engineering Database (subscription) customDbUrl: eissn: 1469-7645 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0013097 issn: 0022-1120 databaseCode: M7S dateStart: 20010101 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central - New (Subscription) customDbUrl: eissn: 1469-7645 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0013097 issn: 0022-1120 databaseCode: BENPR dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Research Library (subscription) customDbUrl: eissn: 1469-7645 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0013097 issn: 0022-1120 databaseCode: M2O dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/pqrl providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database (subscription) customDbUrl: eissn: 1469-7645 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0013097 issn: 0022-1120 databaseCode: M2P dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB7UVdCDj1XxueQgHoRqmr6Sk6i4eFoXHyBeSpMmosjuul0V_PVmsqmrIF68pIdO09JJJl-SyfcB7Jk4zGgpqJ2bUFsILgNppwmBtGMtzZiJFS-d2ETW6fC7O9H1C26VT6usY6IL1GVf4Rr5EUOkEYVRTI8HLwGqRuHuqpfQmIYGsiQwl7p3PdlFoCKr2cItrqD-fB5SRj8ZPIYeikOUyZmwKvwcnX4GZzfitJf--63LsOixJjkZN44VmNK9Jix53El8r66asPCNlLAJcy4pVFWr8IFPjhkmCPJeuovLGq-Ik5awtXidH1JqPSBD7XhYlVtyJF6Q4oHgyV_MFCU-L55Uo5qgglhzUriYS8xz_702WYPb9vnN2UXgtRoCZWego0CWKWcyVgUTFjNa3JIansRK6LQQ3EYNrbiRIYIbLksaKlFKo1KjmKS8yCITrcNMr9_TG0AiLhNWKI7gKhaS8TSSiRZxXKg0tfhyE_a__JX7Hlfl42y1LLeOzdGxeco24aB2Zq484zn-neffjfe-jAdjoo_fzXZql0_ePfH31t-3t2Ee68HdKJbswMxo-Kp3YVa9jR6rYQsap-ed7lXLNmJ26cpuyzVoW3aT-0_7NP1p |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3BTtwwEB0tUAQcoCytgNLWB-ihUorjeBP7gCpEi0DQVaWCxC2NHbuiWu0um4UV_ah-Ix7HYYuEuHHoJTlk4kjOy8w4nnkPYNvyOKOlpG5tQt1BChUpt0yIlIu1NGOWa1F6sYms2xUXF_J7C_42vTBYVtn4RO-oy4HGf-S7DDONJE44_Ty8ilA1CndXGwmNGhYn5nbilmzV3vEX9353GDv8enZwFAVVgUi7tdI4UmUqmOK6YNJlNy7CplZ0uJYmLaRw-DZaWBVjGBaqpLGWpbI6tZopKoossYkbdwbmOHp_Xyr4Y7prQWXWsJO7PIaGfkCkqP5tse09lp9QlmfK4vAwGj4MBj7CHa78b3PzEpZDLk32a_CvQsv027AS8moSvFbVhqV_SBfbMO-LXnW1Bn_wzppBgyCvpz_5qviKeOkMN0rQMSKlMUMyMp5nVvtfqiQIbvwi2NmMlbAk1P2TatwQcBBnTgofU4jtDSaNySs4f5aZeQ2z_UHfrANJhOqwQgtMHrlUTKSJ6hjJeaHT1OXPG_DhHh958ChVXlfjZbkDUo5AylO2AR8b8OQ6MLrj7PQeN96-Nx7WRCaPm201EJs-e4qvzacvv4eFo7Nvp_npcffkDSzimLjzxjpbMDseXZu38ELfjC-r0Tv_4RD4-dxovAM8jlY- |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Artificial+neural+networks+trained+through+deep+reinforcement+learning+discover+control+strategies+for+active+flow+control&rft.jtitle=Journal+of+fluid+mechanics&rft.au=Rabault%2C+Jean&rft.au=Kuchta%2C+Miroslav&rft.au=Jensen%2C+Atle&rft.au=Ulysse+R%C3%A9glade&rft.date=2019-04-25&rft.pub=Cambridge+University+Press&rft.issn=0022-1120&rft.eissn=1469-7645&rft.volume=865&rft.spage=281&rft.epage=302&rft_id=info:doi/10.1017%2Fjfm.2019.62 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0022-1120&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0022-1120&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0022-1120&client=summon |