Data-driven design exploration method using conditional variational autoencoder for airfoil design
An objective of mechanical design is to obtain a shape that satisfies specific requirements. In the present work, we achieve this goal using a conditional variational autoencoder (CVAE). The method enables us to analyze the relationship between aerodynamic performance and the shape of aerodynamic pa...
Saved in:
| Published in: | Structural and multidisciplinary optimization Vol. 64; no. 2; pp. 613 - 624 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Berlin/Heidelberg
Springer Berlin Heidelberg
01.08.2021
Springer Nature B.V |
| Subjects: | |
| ISSN: | 1615-147X, 1615-1488 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | An objective of mechanical design is to obtain a shape that satisfies specific requirements. In the present work, we achieve this goal using a conditional variational autoencoder (CVAE). The method enables us to analyze the relationship between aerodynamic performance and the shape of aerodynamic parts, and to explore new designs for the parts. In the CVAE model, a shape is fed as an input and the corresponding aerodynamic performance index is fed as a continuous label. Then, shapes are generated by specifying the continuous label and latent vector. When CVAE is applied to mechanical design, it is desired to draw shapes that reproduce the specified aerodynamic performance. In ordinal CVAE, the model is trained to minimize reconstruction loss and latent loss, and it is usually optimized considering the sum of these losses. However, the present study shows that the optimal network is not always optimal in terms of reproducing the aerodynamic performance. The proposed method is verified using two numerical examples: a two-dimensional (2D) airfoil and a turbine blade. In the airfoil example, we demonstrate the effects of latent dimension, and in the turbine design example, we demonstrate that the proposed method can be applied to a real turbine design problem and reduce the design time. |
|---|---|
| AbstractList | An objective of mechanical design is to obtain a shape that satisfies specific requirements. In the present work, we achieve this goal using a conditional variational autoencoder (CVAE). The method enables us to analyze the relationship between aerodynamic performance and the shape of aerodynamic parts, and to explore new designs for the parts. In the CVAE model, a shape is fed as an input and the corresponding aerodynamic performance index is fed as a continuous label. Then, shapes are generated by specifying the continuous label and latent vector. When CVAE is applied to mechanical design, it is desired to draw shapes that reproduce the specified aerodynamic performance. In ordinal CVAE, the model is trained to minimize reconstruction loss and latent loss, and it is usually optimized considering the sum of these losses. However, the present study shows that the optimal network is not always optimal in terms of reproducing the aerodynamic performance. The proposed method is verified using two numerical examples: a two-dimensional (2D) airfoil and a turbine blade. In the airfoil example, we demonstrate the effects of latent dimension, and in the turbine design example, we demonstrate that the proposed method can be applied to a real turbine design problem and reduce the design time. |
| Author | Yonekura, Kazuo Suzuki, Katsuyuki |
| Author_xml | – sequence: 1 givenname: Kazuo orcidid: 0000-0002-1955-069X surname: Yonekura fullname: Yonekura, Kazuo email: yonekura@struct.t.u-tokyo.ac.jp organization: The University of Tokyo, IHI Corporation – sequence: 2 givenname: Katsuyuki surname: Suzuki fullname: Suzuki, Katsuyuki organization: The University of Tokyo |
| BookMark | eNp9kEtLAzEQx4NUsK1-AU8Bz6uT3c1u9ij1CQUvCt5CNo-ask1qki367d0-UPDQwzwY_r9h5j9BI-edRuiSwDUBqG8iAKEsg5wMweiQT9CYVIRmpGRs9NvX72doEuMSABiUzRi1dyKJTAW70Q4rHe3CYf217nwQyXqHVzp9eIX7aN0CS--U3Y5FhzciWHHoRZ-8dtIrHbDxAQsbjLfdYd85OjWii_riUKfo7eH-dfaUzV8en2e380wWjKZM5QSkLIVo2oZRDbJtmwZKQRWAqSpSF4YwpWVDWAG5UqSipgZDQJSqrlReTNHVfu86-M9ex8SXvg_DfZHnlDaE0rpig4rtVTL4GIM2XNq0eyQFYTtOgG8d5XtH-eAo3znKYUDzf-g62JUI38ehYg_FQewWOvxddYT6Ab_ljFE |
| CitedBy_id | crossref_primary_10_3390_computation12110227 crossref_primary_10_1016_j_engappai_2022_105697 crossref_primary_10_3390_ai6060129 crossref_primary_10_3390_ai5040102 crossref_primary_10_1016_j_engappai_2021_104560 crossref_primary_10_1016_j_neunet_2024_106251 crossref_primary_10_1007_s00158_022_03253_6 crossref_primary_10_1007_s12273_023_1083_4 crossref_primary_10_1016_j_taml_2025_100591 crossref_primary_10_3390_aerospace12050389 crossref_primary_10_1080_19942060_2024_2384465 crossref_primary_10_1007_s00158_022_03290_1 crossref_primary_10_3390_app14093564 crossref_primary_10_1016_j_eswa_2023_119513 crossref_primary_10_1016_j_paerosci_2024_101007 crossref_primary_10_1016_j_renene_2024_120115 crossref_primary_10_1016_j_ins_2023_119066 crossref_primary_10_1007_s44163_023_00089_x crossref_primary_10_1016_j_cad_2022_103327 crossref_primary_10_1016_j_cma_2024_116746 crossref_primary_10_1093_jcde_qwaf002 crossref_primary_10_1093_jcde_qwac140 crossref_primary_10_1016_j_engappai_2023_106413 crossref_primary_10_1016_j_cma_2025_117972 crossref_primary_10_1007_s00366_023_01789_9 crossref_primary_10_1115_1_4069199 crossref_primary_10_1007_s00158_022_03369_9 crossref_primary_10_1007_s00158_025_04111_x crossref_primary_10_2514_1_J061673 crossref_primary_10_1016_j_bprint_2024_e00331 crossref_primary_10_1016_j_compbiomed_2022_106289 crossref_primary_10_1016_j_rineng_2025_106181 crossref_primary_10_1016_j_cma_2025_117848 crossref_primary_10_1109_TAES_2023_3276735 crossref_primary_10_1016_j_paerosci_2022_100849 |
| Cites_doi | 10.1115/1.4001005 10.1007/s00158-009-0459-0 10.2514/1.2159 10.1115/1.1467599 10.1007/s00158-016-1472-8 10.1080/174159795088027593 10.1007/978-3-642-23783-6_41 10.1007/s00158-014-1123-x 10.1007/978-3-642-58106-9 10.1145/3178876.3185996 10.1126/science.1127647 10.1115/85-GT-6 10.1016/j.cma.2019.112732 10.1145/3292500.3330701 10.1007/s00158-018-2101-5 10.1016/j.cma.2020.113357 10.1080/17445302.2019.1606877 10.2514/3.11276 10.1007/s00158-019-02276-w 10.1016/j.cma.2019.112737 10.1590/S1678-58782007000400003 10.1007/s00158-019-02424-2 10.1007/978-3-642-84010-4_1 10.1080/174159794088027573 10.1115/GT2014-27239 10.1007/s00158-019-02222-w 10.1115/1.1881697 10.1115/1.4028273 |
| ContentType | Journal Article |
| Copyright | The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature 2021 The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature 2021. |
| Copyright_xml | – notice: The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature 2021 – notice: The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature 2021. |
| DBID | AAYXX CITATION 8FE 8FG ABJCF AFKRA BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PHGZM PHGZT PKEHL PQEST PQGLB PQQKQ PQUKI PRINS PTHSS |
| DOI | 10.1007/s00158-021-02851-0 |
| DatabaseName | CrossRef ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central UK/Ireland ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Collection (ProQuest) ProQuest Engineering Collection Engineering Database Proquest Central Premium ProQuest One Academic ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
| DatabaseTitle | CrossRef Engineering Database Technology Collection ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic ProQuest Central (New) Engineering Collection ProQuest One Academic (New) |
| DatabaseTitleList | Engineering Database |
| Database_xml | – sequence: 1 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1615-1488 |
| EndPage | 624 |
| ExternalDocumentID | 10_1007_s00158_021_02851_0 |
| GroupedDBID | -5B -5G -BR -EM -Y2 -~C .86 .VR 06D 0R~ 0VY 123 199 1N0 2.D 203 29Q 29~ 2J2 2JN 2JY 2KG 2KM 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5QI 5VS 67Z 6NX 78A 8FE 8FG 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABJCF ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACHXU ACIWK ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACZOJ ADHIR ADINQ ADKNI ADKPE ADPHR ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFEXP AFGCZ AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AOCGG ARCEE ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN B-. BA0 BDATZ BENPR BGLVJ BGNMA BSONS CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP EBLON EBS EIOEI EJD ESBYG FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I09 IHE IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV L6V LAS LLZTM M4Y M7S MA- N2Q N9A NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM P19 P9P PF0 PT4 PT5 PTHSS QOK QOS R89 R9I RHV RIG RNI RNS ROL RPX RSV RZK S16 S1Z S26 S27 S28 S3B SAP SCLPG SDH SDM SEG SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TSG TSK TSV TUC U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z5O Z7R Z7S Z7V Z7X Z7Y Z7Z Z81 Z83 Z85 Z86 Z88 Z8M Z8N Z8P Z8R Z8S Z8T Z8U Z8W Z8Z Z92 ZMTXR _50 ~02 AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG AEZWR AFDZB AFFHD AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION PHGZM PHGZT PQGLB DWQXO PKEHL PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c385t-d210cc4aa9b985e0cbb9904a5d00f66173f18dec918302dd165f70f10a4d76d23 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 48 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000671914300002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1615-147X |
| IngestDate | Wed Nov 05 00:40:26 EST 2025 Sat Nov 29 02:50:17 EST 2025 Tue Nov 18 22:38:29 EST 2025 Fri Feb 21 02:47:49 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Keywords | Variational autoencoder Design exploration Airfoil design |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c385t-d210cc4aa9b985e0cbb9904a5d00f66173f18dec918302dd165f70f10a4d76d23 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-1955-069X |
| PQID | 2559155768 |
| PQPubID | 2043658 |
| PageCount | 12 |
| ParticipantIDs | proquest_journals_2559155768 crossref_citationtrail_10_1007_s00158_021_02851_0 crossref_primary_10_1007_s00158_021_02851_0 springer_journals_10_1007_s00158_021_02851_0 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-08-01 |
| PublicationDateYYYYMMDD | 2021-08-01 |
| PublicationDate_xml | – month: 08 year: 2021 text: 2021-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Berlin/Heidelberg |
| PublicationPlace_xml | – name: Berlin/Heidelberg – name: Heidelberg |
| PublicationTitle | Structural and multidisciplinary optimization |
| PublicationTitleAbbrev | Struct Multidisc Optim |
| PublicationYear | 2021 |
| Publisher | Springer Berlin Heidelberg Springer Nature B.V |
| Publisher_xml | – name: Springer Berlin Heidelberg – name: Springer Nature B.V |
| References | BonaiutiDZangenehMAartojarviRErikssonJParametric design of a waterjet pump by means of inverse design, CFD calculations and experimental analysesJ Fluids Eng2010132303110410.1115/1.4001005 Raifai S, Vincent P, Muller X, Glorot X, Bengio Y (2011) Contractive auto-encoders: explicit invariance during feature extraction. In: Proceedings of the 28th international conference on machine learning (ICML) LeeIChoiKKGorsickDSystem reliability-based design optimization using the MPP-based dimension reduction methodStruct Multidiscipl Optim201041682383910.1007/s00158-009-0459-0 Nita K, Okita Y, Nakamata C, Kubo S, Yonekura K, Watanabe O (2014) Film cooling hole shape optimization using proper orthogonal decomposition. In: ASME Turbo expo 2014: turbine technical conference and exposition, pp GT2014–27239 BrownNCMuellerCTDesign variable analysis and generation for performance-based parametric modeling in architectureInt J Archit Comput20191713652 Tolstikhin I, Bousquet O, Gelly S (2018) Wasserstein auto-encoders. In: The International Conference on Learning Representations (ICLR) Zhengming W (1985) Inverse design calculations for transonic cascades. In Turbo Expo: Power for Land, Sea, and Air, pp 85-GT-6 PedregosaFVaroquauxGGramfortAMichelVThirionBGriselOBlondelMPrettenhoferPWeissRDubourgVVanderplasJPassosACournapeauDBrucherMPerrotMDuchesnayEScikit-learn: machine learning in PythonJ Mach Learn Res2011122825283028543481280.68189 YonekuraKHattoriHFramework for design optimization using deep reinforcement learningStruct Multidiscip Optim20196041709171310.1007/s00158-019-02276-w ImaizumiMFukumizuKDeep neural networks learn non-smooth functions effectivelyJ Mach Learn Res201989869878 YuYHurTJungJJangIGDeep learning for determining a near-optimal topological design without any iterationStruct Multidiscip Optim201959378779910.1007/s00158-018-2101-5 van den Oord A, Vinyals O, Kavukcuoglu K (2017) Neural discrete representation learning. In: Advances in neural information processing systems, vol. 30, pp 6306–6315 Akiba T, Sano S, Yanase T, Ohta T, Koyama M (2019) Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery and data mining, pp 2623–2631 GaggeroSVernengoGVillaDBonfiglioLA reduced order approach for optimal design of efficient marine propellersShips Offshore Struc202015231932810.1080/17445302.2019.1606877 NarducciRGrossmanBHaftkaRTSensitivity algorithms for an inverse design problem involving a shock waveInverse Probl Eng199521498310.1080/174159795088027593 CaoSPengGYuZHydrodynamic design of rotodynamic pump impeller for multiphase pumping by combined approach of inverse design and CFD analysisJ Fluids Eng2005172233033810.1115/1.1881697 PetrucciDRFilhoNMA fast algorithm for inverse airfoil design using a transpiration model and an improved vortex panel methodJ Braz Soc Mech Sci Eng200729435436510.1590/S1678-58782007000400003 YonekuraKKannoYErratum to: A flow topology optimization method for steady state flow using transient information of flow field solved by lattice Boltzmann methodStruct Multidiscip Optim2016541193195350815610.1007/s00158-016-1472-8 KennonSRDulikravichGSInverse design of coolant flow passage shapes with partially fixed internal geometriesInt J Turbo Jet-Engines198531320 Kingma DP, Welling M (2013) Auto-encoding variational bayes. In: The International Conference on Learning Representation (ICLR) YonekuraKWatanabeOA shape parameterization method using principal component analysis in application to shape optimizationJ Mech Des20141361212140110.1115/1.4028273 Bui-ThanhTDamodaranMWillcoxKAerodynamic data reconstruction and inverse design using proper orthogonal decompositionAIAA J20044281505151610.2514/1.2159 SokolowskiJZolesioJPIntroduction to shape optimization1992BerlinSpringer10.1007/978-3-642-58106-9 TanRKZhangNLYeWA deep learning-based method for the design of microstructural materialsStruct Multidiscip Optim202061414171438408107810.1007/s00158-019-02424-2 LiXNingSLiuZYanZLuoCZhuangZDesigning phononic crystal with anticipated band gap through a deep learning based data-driven methodComput Methods Appl Mech Eng2020361112737405500810.1016/j.cma.2019.112737 Drela M (1989) Xfoil: An analysis and design system for low Reynolds number airfoils. In: Mueller TJ (ed) Low Reynolds number aerodynamics, lecture notes in engineering, vol 54. Springer, Berlin, pp 1–12 SunLGaoHPanSWangJXSurrogate modeling for fluid flows based on physics-constrained deep learning without simulation dataComput Methods Appl Mech Eng2020361112732405500410.1016/j.cma.2019.112732 Pu Y, Gan Z, Henao R, Yuan X, Li C, Stevens A, Carin L (2016) Variational autoencoder for deep learning of images, labels and captions. In: Advances in neural information processing systems 29, pp 2352–2360 Davidson TR, Falorsi L, de Cao N, Kipf T, Tomczak JM (2018) Hyperspherical variational auto-encoders. In: 34th conference on uncertainty in artificial Intelligence (UAI-18) Nita K, Okita Y, Nakamata C, Kubo S, Yonekura K, Watanabe O (2017) Turbine blade. US Patent 9,759,069 Sohn K, Lee H, Yan X (2015) Learning structured output representation using deep conditional generative models. In: Advances in neural information processing systems 28, pp 3483–3491 Liu MY, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. In: Advances in neural information processing systems 30. pp 700–708 WangCYan XuLSheng FanJA general deep learning framework for history-dependent response prediction based on ua-seq2seq modelComput Methods Appl Mech Eng2020372113357413832410.1016/j.cma.2020.113357 Xu H, Chen W, Zhao N, Li Z, Bu J, Li Z, Liu Y, Zhao Y, Pei D, Feng Y, Chen J, Wang Z, Qiao H (2018) Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications. In: Proceedings of the 2018 world wide web conference, pp 187–196 SeligMSMaughmerMDGeneralized multipont inverse airfoil designAIAA J199230112618262510.2514/3.11276 TortorelliDAMichalerisPDesign sensitivity analysis: overview and reviewInverse Probl Eng1994117110510.1080/174159794088027573 ZhangYYeWDeep learning-based inverse method for layout designStruct Multidiscip Optim2019602527536397752510.1007/s00158-019-02222-w BendsøeMPSigmundOTopology optimization: theory, methods and applications20032nd ednBerlinSpringer1059.74001 GotoAZangenehMHydrodynamic design of pump diffuser using inverse design method and CFDJ Fluids Eng2002124231932810.1115/1.1467599 HintonGESalakhutdinovRRReducing the dimensionality of data with neural networksScience20063135786504507224250910.1126/science.1127647 Abbot IH, von Doenhoff AE, Stivers L Jr (1945) Summary of airfoil data. NACA-TR-824 YonekuraKKannoYA flow topology optimization method for steady state flow using transient information of flow field solved by lattice Boltzmann methodStruct Multidiscip Optim2015511159172331876810.1007/s00158-014-1123-x DorneyDJLakeJPKingPAshpisDExperimental and numerical investigation of losses in low-pressure turbine blade rowsInt J Turbo Jet Eng2000174241253 Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mané D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: large-scale machine learning on heterogeneous systems. Software available from tensorflow.org M Imaizumi (2851_CR14) 2019; 89 S Gaggero (2851_CR11) 2020; 15 L Sun (2851_CR31) 2020; 361 DA Tortorelli (2851_CR35) 1994; 1 K Yonekura (2851_CR40) 2016; 54 D Bonaiuti (2851_CR5) 2010; 132 Y Yu (2851_CR42) 2019; 59 DJ Dorney (2851_CR9) 2000; 17 2851_CR10 2851_CR34 X Li (2851_CR18) 2020; 361 2851_CR16 2851_CR37 2851_CR19 GE Hinton (2851_CR13) 2006; 313 Y Zhang (2851_CR43) 2019; 60 DR Petrucci (2851_CR25) 2007; 29 A Goto (2851_CR12) 2002; 124 2851_CR3 MP Bendsøe (2851_CR4) 2003 2851_CR2 2851_CR1 K Yonekura (2851_CR38) 2019; 60 I Lee (2851_CR17) 2010; 41 2851_CR21 2851_CR8 2851_CR23 2851_CR22 2851_CR44 MS Selig (2851_CR28) 1992; 30 SR Kennon (2851_CR15) 1985; 3 2851_CR27 2851_CR26 RK Tan (2851_CR33) 2020; 61 2851_CR29 K Yonekura (2851_CR41) 2014; 136 R Narducci (2851_CR20) 1995; 2 F Pedregosa (2851_CR24) 2011; 12 NC Brown (2851_CR6) 2019; 17 J Sokolowski (2851_CR30) 1992 C Wang (2851_CR36) 2020; 372 T Bui-Thanh (2851_CR32) 2004; 42 K Yonekura (2851_CR39) 2015; 51 S Cao (2851_CR7) 2005; 172 |
| References_xml | – reference: YuYHurTJungJJangIGDeep learning for determining a near-optimal topological design without any iterationStruct Multidiscip Optim201959378779910.1007/s00158-018-2101-5 – reference: Kingma DP, Welling M (2013) Auto-encoding variational bayes. In: The International Conference on Learning Representation (ICLR) – reference: BendsøeMPSigmundOTopology optimization: theory, methods and applications20032nd ednBerlinSpringer1059.74001 – reference: CaoSPengGYuZHydrodynamic design of rotodynamic pump impeller for multiphase pumping by combined approach of inverse design and CFD analysisJ Fluids Eng2005172233033810.1115/1.1881697 – reference: Liu MY, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. In: Advances in neural information processing systems 30. pp 700–708 – reference: DorneyDJLakeJPKingPAshpisDExperimental and numerical investigation of losses in low-pressure turbine blade rowsInt J Turbo Jet Eng2000174241253 – reference: Zhengming W (1985) Inverse design calculations for transonic cascades. In Turbo Expo: Power for Land, Sea, and Air, pp 85-GT-6 – reference: Akiba T, Sano S, Yanase T, Ohta T, Koyama M (2019) Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery and data mining, pp 2623–2631 – reference: Drela M (1989) Xfoil: An analysis and design system for low Reynolds number airfoils. In: Mueller TJ (ed) Low Reynolds number aerodynamics, lecture notes in engineering, vol 54. Springer, Berlin, pp 1–12 – reference: GotoAZangenehMHydrodynamic design of pump diffuser using inverse design method and CFDJ Fluids Eng2002124231932810.1115/1.1467599 – reference: PedregosaFVaroquauxGGramfortAMichelVThirionBGriselOBlondelMPrettenhoferPWeissRDubourgVVanderplasJPassosACournapeauDBrucherMPerrotMDuchesnayEScikit-learn: machine learning in PythonJ Mach Learn Res2011122825283028543481280.68189 – reference: SeligMSMaughmerMDGeneralized multipont inverse airfoil designAIAA J199230112618262510.2514/3.11276 – reference: KennonSRDulikravichGSInverse design of coolant flow passage shapes with partially fixed internal geometriesInt J Turbo Jet-Engines198531320 – reference: LiXNingSLiuZYanZLuoCZhuangZDesigning phononic crystal with anticipated band gap through a deep learning based data-driven methodComput Methods Appl Mech Eng2020361112737405500810.1016/j.cma.2019.112737 – reference: YonekuraKKannoYA flow topology optimization method for steady state flow using transient information of flow field solved by lattice Boltzmann methodStruct Multidiscip Optim2015511159172331876810.1007/s00158-014-1123-x – reference: Davidson TR, Falorsi L, de Cao N, Kipf T, Tomczak JM (2018) Hyperspherical variational auto-encoders. In: 34th conference on uncertainty in artificial Intelligence (UAI-18) – reference: Nita K, Okita Y, Nakamata C, Kubo S, Yonekura K, Watanabe O (2014) Film cooling hole shape optimization using proper orthogonal decomposition. In: ASME Turbo expo 2014: turbine technical conference and exposition, pp GT2014–27239 – reference: BrownNCMuellerCTDesign variable analysis and generation for performance-based parametric modeling in architectureInt J Archit Comput20191713652 – reference: BonaiutiDZangenehMAartojarviRErikssonJParametric design of a waterjet pump by means of inverse design, CFD calculations and experimental analysesJ Fluids Eng2010132303110410.1115/1.4001005 – reference: Raifai S, Vincent P, Muller X, Glorot X, Bengio Y (2011) Contractive auto-encoders: explicit invariance during feature extraction. In: Proceedings of the 28th international conference on machine learning (ICML) – reference: YonekuraKKannoYErratum to: A flow topology optimization method for steady state flow using transient information of flow field solved by lattice Boltzmann methodStruct Multidiscip Optim2016541193195350815610.1007/s00158-016-1472-8 – reference: SunLGaoHPanSWangJXSurrogate modeling for fluid flows based on physics-constrained deep learning without simulation dataComput Methods Appl Mech Eng2020361112732405500410.1016/j.cma.2019.112732 – reference: HintonGESalakhutdinovRRReducing the dimensionality of data with neural networksScience20063135786504507224250910.1126/science.1127647 – reference: Nita K, Okita Y, Nakamata C, Kubo S, Yonekura K, Watanabe O (2017) Turbine blade. US Patent 9,759,069 – reference: LeeIChoiKKGorsickDSystem reliability-based design optimization using the MPP-based dimension reduction methodStruct Multidiscipl Optim201041682383910.1007/s00158-009-0459-0 – reference: YonekuraKHattoriHFramework for design optimization using deep reinforcement learningStruct Multidiscip Optim20196041709171310.1007/s00158-019-02276-w – reference: PetrucciDRFilhoNMA fast algorithm for inverse airfoil design using a transpiration model and an improved vortex panel methodJ Braz Soc Mech Sci Eng200729435436510.1590/S1678-58782007000400003 – reference: TortorelliDAMichalerisPDesign sensitivity analysis: overview and reviewInverse Probl Eng1994117110510.1080/174159794088027573 – reference: NarducciRGrossmanBHaftkaRTSensitivity algorithms for an inverse design problem involving a shock waveInverse Probl Eng199521498310.1080/174159795088027593 – reference: WangCYan XuLSheng FanJA general deep learning framework for history-dependent response prediction based on ua-seq2seq modelComput Methods Appl Mech Eng2020372113357413832410.1016/j.cma.2020.113357 – reference: Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mané D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: large-scale machine learning on heterogeneous systems. Software available from tensorflow.org – reference: ImaizumiMFukumizuKDeep neural networks learn non-smooth functions effectivelyJ Mach Learn Res201989869878 – reference: Sohn K, Lee H, Yan X (2015) Learning structured output representation using deep conditional generative models. In: Advances in neural information processing systems 28, pp 3483–3491 – reference: TanRKZhangNLYeWA deep learning-based method for the design of microstructural materialsStruct Multidiscip Optim202061414171438408107810.1007/s00158-019-02424-2 – reference: Abbot IH, von Doenhoff AE, Stivers L Jr (1945) Summary of airfoil data. NACA-TR-824 – reference: SokolowskiJZolesioJPIntroduction to shape optimization1992BerlinSpringer10.1007/978-3-642-58106-9 – reference: Xu H, Chen W, Zhao N, Li Z, Bu J, Li Z, Liu Y, Zhao Y, Pei D, Feng Y, Chen J, Wang Z, Qiao H (2018) Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications. In: Proceedings of the 2018 world wide web conference, pp 187–196 – reference: YonekuraKWatanabeOA shape parameterization method using principal component analysis in application to shape optimizationJ Mech Des20141361212140110.1115/1.4028273 – reference: Bui-ThanhTDamodaranMWillcoxKAerodynamic data reconstruction and inverse design using proper orthogonal decompositionAIAA J20044281505151610.2514/1.2159 – reference: Pu Y, Gan Z, Henao R, Yuan X, Li C, Stevens A, Carin L (2016) Variational autoencoder for deep learning of images, labels and captions. In: Advances in neural information processing systems 29, pp 2352–2360 – reference: Tolstikhin I, Bousquet O, Gelly S (2018) Wasserstein auto-encoders. In: The International Conference on Learning Representations (ICLR) – reference: ZhangYYeWDeep learning-based inverse method for layout designStruct Multidiscip Optim2019602527536397752510.1007/s00158-019-02222-w – reference: GaggeroSVernengoGVillaDBonfiglioLA reduced order approach for optimal design of efficient marine propellersShips Offshore Struc202015231932810.1080/17445302.2019.1606877 – reference: van den Oord A, Vinyals O, Kavukcuoglu K (2017) Neural discrete representation learning. In: Advances in neural information processing systems, vol. 30, pp 6306–6315 – volume: 132 start-page: 031104 issue: 3 year: 2010 ident: 2851_CR5 publication-title: J Fluids Eng doi: 10.1115/1.4001005 – volume: 41 start-page: 823 issue: 6 year: 2010 ident: 2851_CR17 publication-title: Struct Multidiscipl Optim doi: 10.1007/s00158-009-0459-0 – volume: 42 start-page: 1505 issue: 8 year: 2004 ident: 2851_CR32 publication-title: AIAA J doi: 10.2514/1.2159 – ident: 2851_CR29 – volume: 124 start-page: 319 issue: 2 year: 2002 ident: 2851_CR12 publication-title: J Fluids Eng doi: 10.1115/1.1467599 – ident: 2851_CR23 – ident: 2851_CR2 – ident: 2851_CR8 – volume: 89 start-page: 869 year: 2019 ident: 2851_CR14 publication-title: J Mach Learn Res – volume: 54 start-page: 193 issue: 1 year: 2016 ident: 2851_CR40 publication-title: Struct Multidiscip Optim doi: 10.1007/s00158-016-1472-8 – volume: 2 start-page: 49 issue: 1 year: 1995 ident: 2851_CR20 publication-title: Inverse Probl Eng doi: 10.1080/174159795088027593 – volume: 17 start-page: 241 issue: 4 year: 2000 ident: 2851_CR9 publication-title: Int J Turbo Jet Eng – ident: 2851_CR16 – ident: 2851_CR27 doi: 10.1007/978-3-642-23783-6_41 – volume: 51 start-page: 159 issue: 1 year: 2015 ident: 2851_CR39 publication-title: Struct Multidiscip Optim doi: 10.1007/s00158-014-1123-x – volume-title: Introduction to shape optimization year: 1992 ident: 2851_CR30 doi: 10.1007/978-3-642-58106-9 – ident: 2851_CR37 doi: 10.1145/3178876.3185996 – volume: 313 start-page: 504 issue: 5786 year: 2006 ident: 2851_CR13 publication-title: Science doi: 10.1126/science.1127647 – ident: 2851_CR44 doi: 10.1115/85-GT-6 – volume: 361 start-page: 112732 year: 2020 ident: 2851_CR31 publication-title: Comput Methods Appl Mech Eng doi: 10.1016/j.cma.2019.112732 – ident: 2851_CR3 doi: 10.1145/3292500.3330701 – volume: 59 start-page: 787 issue: 3 year: 2019 ident: 2851_CR42 publication-title: Struct Multidiscip Optim doi: 10.1007/s00158-018-2101-5 – volume: 372 start-page: 113357 year: 2020 ident: 2851_CR36 publication-title: Comput Methods Appl Mech Eng doi: 10.1016/j.cma.2020.113357 – volume: 15 start-page: 319 issue: 2 year: 2020 ident: 2851_CR11 publication-title: Ships Offshore Struc doi: 10.1080/17445302.2019.1606877 – ident: 2851_CR1 – ident: 2851_CR26 – volume: 30 start-page: 2618 issue: 11 year: 1992 ident: 2851_CR28 publication-title: AIAA J doi: 10.2514/3.11276 – volume: 60 start-page: 1709 issue: 4 year: 2019 ident: 2851_CR38 publication-title: Struct Multidiscip Optim doi: 10.1007/s00158-019-02276-w – volume: 361 start-page: 112737 year: 2020 ident: 2851_CR18 publication-title: Comput Methods Appl Mech Eng doi: 10.1016/j.cma.2019.112737 – volume: 29 start-page: 354 issue: 4 year: 2007 ident: 2851_CR25 publication-title: J Braz Soc Mech Sci Eng doi: 10.1590/S1678-58782007000400003 – volume: 61 start-page: 1417 issue: 4 year: 2020 ident: 2851_CR33 publication-title: Struct Multidiscip Optim doi: 10.1007/s00158-019-02424-2 – ident: 2851_CR22 – ident: 2851_CR10 doi: 10.1007/978-3-642-84010-4_1 – volume: 17 start-page: 36 issue: 1 year: 2019 ident: 2851_CR6 publication-title: Int J Archit Comput – volume: 1 start-page: 71 issue: 1 year: 1994 ident: 2851_CR35 publication-title: Inverse Probl Eng doi: 10.1080/174159794088027573 – ident: 2851_CR19 – ident: 2851_CR34 – ident: 2851_CR21 doi: 10.1115/GT2014-27239 – volume: 12 start-page: 2825 year: 2011 ident: 2851_CR24 publication-title: J Mach Learn Res – volume: 60 start-page: 527 issue: 2 year: 2019 ident: 2851_CR43 publication-title: Struct Multidiscip Optim doi: 10.1007/s00158-019-02222-w – volume: 172 start-page: 330 issue: 2 year: 2005 ident: 2851_CR7 publication-title: J Fluids Eng doi: 10.1115/1.1881697 – volume: 3 start-page: 13 year: 1985 ident: 2851_CR15 publication-title: Int J Turbo Jet-Engines – volume: 136 start-page: 121401 issue: 12 year: 2014 ident: 2851_CR41 publication-title: J Mech Des doi: 10.1115/1.4028273 – volume-title: Topology optimization: theory, methods and applications year: 2003 ident: 2851_CR4 |
| SSID | ssj0008049 |
| Score | 2.5847433 |
| Snippet | An objective of mechanical design is to obtain a shape that satisfies specific requirements. In the present work, we achieve this goal using a conditional... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 613 |
| SubjectTerms | Aerodynamics Airfoils Approximation Computational Mathematics and Numerical Analysis Deep learning Design Designers Engineering Engineering Design Machine learning Methods Neural networks Optimization Performance indices Research Paper Theoretical and Applied Mechanics Turbine blades Turbines |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELagMMDAG_GWBzawcJq4sSfEoxVThRBI3SInZ6NKVVvSlN_P2XFbQKILS5bYpyh3vu_z-XxHyGUCoERuORPcpCxR1jKpWgJtmWuIcYmkMvfNJtJuV_Z66jkE3CYhrXLmE72jhlHhYuQ3jvoi9iE7vh1_MNc1yp2uhhYaq2TNVSpLGmTtvt19fpn7YlkTYEdrWJSkvXBtxl-ec3RBMpeigBgr8PkTmhZ889cRqUeezvZ_v3mHbAXOSe9qI9klK2a4Rza_VSLcJ_mjrjSD0vk-Cj6rgxqfnuc1R-tG09Rlyb9T3EJDv44h0k_ca4d4ItXTauTqYoIpKXJhqvulHfUHQd4Beeu0Xx-eWGi_wIpYiooB7gaLItFa5UoKw4s8R-hKtADOLcJ6GttIgilU5GqIAUQtYVNuI64TSFvQjA9JYzgamiNCVZyo1FoDTY1o2JJS5IDgzJsWB0aaH5No9uezItQmdy0yBtm8qrLXVobayry2MpxzNZ8zritzLB19NlNRFlbpJFvo55hcz5S8eP23tJPl0k7JRtPblcsTPCONqpyac7JefFb9SXkRbPQL-qjtXg priority: 102 providerName: ProQuest |
| Title | Data-driven design exploration method using conditional variational autoencoder for airfoil design |
| URI | https://link.springer.com/article/10.1007/s00158-021-02851-0 https://www.proquest.com/docview/2559155768 |
| Volume | 64 |
| WOSCitedRecordID | wos000671914300002&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: Engineering Database customDbUrl: eissn: 1615-1488 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0008049 issn: 1615-147X databaseCode: M7S dateStart: 19970201 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1615-1488 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0008049 issn: 1615-147X databaseCode: BENPR dateStart: 19970201 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1615-1488 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008049 issn: 1615-147X databaseCode: RSV dateStart: 20000301 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwELagZYCBN6JQKg9sYMl5uLFHXhVTVbWAukVObKNIVYvStL-fs5O0gAAJliyxLevO9ndnf3eH0GWolGCJoYRRHZFQGEO46DJYy1SqALZIxBNXbCLq9_l4LAZVUNi8ZrvXT5LupF4Fu1l458RSCgATGXw3URPgjtvtOBy9rM5fXhq91pQhXhiNq1CZ78f4DEdrG_PLs6hDm97e_-a5j3Yr6xLflMvhAG3o6SHa-ZBz8Agl97KQROX2lMPK8TewdkQ8pyNclpTGlg__isFZVll5W4iX4FVXN4dYLoqZzYCpdI7B6sUyy80sm1TjHaPn3sPT3SOpCi2QNOCsIAr8vjQNpRSJ4EzTNEkApELJFKUGADwKjMeVToVns4Up5XWZiajxqAxV1FV-cIIa09lUnyIsglBExmjlS8C9LucsUQDD1DfQ0JO0hbxa3nFaZSG3xTAm8Sp_spNfDPKLnfxi6HO16vNW5uD4tXW7VmNc7cd5bB0nsJxgQi10Xatt_fvn0c7-1vwcbftO85Yh2EaNIl_oC7SVLotsnndQ8_ahPxh2LMF01HGr9h0u9ORa |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LTtwwFL1CFKntotAHgpa2XtBVa9XJxBN7gRAqRSDoCKlUml3q-IFGQhOaCVT9qX5j73WSmVIJdiy6ySa2pcTH5x7b9wGwnTmnZRkEl8LnPNMhcKWHErEsjBvgEslVGYtN5KORGo_16RL87mNhyK2y58RI1K6ydEb-kaQv2j5Ux7uXPzhVjaLb1b6ERguLY__rJ27ZZjtH-zi_79L04PPZp0PeVRXgdqBkwx1ucqzNjNGlVtILW5bIyJmRToiA1iofhEQ5b3VCqbGcS4Yy5CIkwmQuHzpKdICU_yAj9o-ugl_nzK9auU0iiidZPu6CdGKoHokTxckhAi26xOdNQ7hQt_9cyEY7d7D6v_2hNXjSKWq21y6Bp7Dkp8_g8V95Fp9DuW8aw11NzM5c9FlhPjofRlyytow2oxiAc2YrusWPJ6Ts2tST7rSUmaumoqyfztcMlT4zkzpUk4tuvBfw7V4-ch2Wp9XUbwDTg0znIXiXGrT1Q6Vk6VB6iDRgw8SITUj6mS5sl3mdCoBcFPOc0REdBaKjiOgosM_7eZ_LNu_Ina23ekgUHQfNigUeNuFDD6rF69tHe3n3aG_h4eHZl5Pi5Gh0_AoepRHT5BG5BctNfeVfw4q9biaz-k1cHQy-3zfY_gBW-UiT |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDI54CcGBN-IxIAduEC1dmzU5ImACgSYkHtqtSusETZq2qev2-3HSbjwESIhLL03SynHy2Yn9mZDTCECJ1HImuIlZpKxlUjUF6jLXEOISiWXqi03E7bbsdNTDhyx-H-0-vZIscxocS1O_qA_B1meJbw7qJXPhBYiPAp_zZDFyRYOcv_74MtuLZWkAO7OGBVHcqdJmvh_jMzS925tfrkg98rTW___PG2StsjrpRakmm2TO9LfI6gcuwm2SXulCM8jd7kfBx3VQ4wP0_NzRstQ0dXHyrxS_DN3yFJFO0NuuThSpHhcDx4wJJqdoDVPdze2g26vG2yHPreunyxtWFWBgWShFwQD9wSyLtFapksLwLE0RvCItgHOLwB6HNpBgMhU4FjGAoClszG3AdQRxExrhLlnoD_pmj1AVRiq21kBDIx42pRQpIDzzhsWGgeb7JJjKPskqdnJXJKOXzHiVvfwSlF_i5Zdgn7NZn2HJzfFr69p0SpNqnY4S51ChRYU_tE_Op1P4_vrn0Q7-1vyELD9ctZL72_bdIVlpeCVwQYQ1slDkY3NElrJJ0R3lx1593wA5e-2Q |
| 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=Data-driven+design+exploration+method+using+conditional+variational+autoencoder+for+airfoil+design&rft.jtitle=Structural+and+multidisciplinary+optimization&rft.au=Yonekura%2C+Kazuo&rft.au=Suzuki%2C+Katsuyuki&rft.date=2021-08-01&rft.issn=1615-147X&rft.eissn=1615-1488&rft.volume=64&rft.issue=2&rft.spage=613&rft.epage=624&rft_id=info:doi/10.1007%2Fs00158-021-02851-0&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s00158_021_02851_0 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1615-147X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1615-147X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1615-147X&client=summon |