{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:45:11Z","timestamp":1773103511511,"version":"3.50.1"},"reference-count":42,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"FCT, through IDMEC, under LAETA","award":["UIDB\/50022\/2020"],"award-info":[{"award-number":["UIDB\/50022\/2020"]}]},{"name":"FCT, through IDMEC, under LAETA","award":["UIDB\/50022\/2020"],"award-info":[{"award-number":["UIDB\/50022\/2020"]}]},{"name":"FCT, through IDMEC, under LAETA","award":["UIDP\/50022\/2020"],"award-info":[{"award-number":["UIDP\/50022\/2020"]}]},{"name":"FCT, through IDMEC, under LAETA","award":["LA\/P\/0079\/2020"],"award-info":[{"award-number":["LA\/P\/0079\/2020"]}]},{"name":"FCT, through AEROG of the Laborat\u00f3rio Associado em Energia, Transportes e Aeron\u00e1utica (LAETA), under LAETA","award":["UIDB\/50022\/2020"],"award-info":[{"award-number":["UIDB\/50022\/2020"]}]},{"name":"FCT, through AEROG of the Laborat\u00f3rio Associado em Energia, Transportes e Aeron\u00e1utica (LAETA), under LAETA","award":["UIDB\/50022\/2020"],"award-info":[{"award-number":["UIDB\/50022\/2020"]}]},{"name":"FCT, through AEROG of the Laborat\u00f3rio Associado em Energia, Transportes e Aeron\u00e1utica (LAETA), under LAETA","award":["UIDP\/50022\/2020"],"award-info":[{"award-number":["UIDP\/50022\/2020"]}]},{"name":"FCT, through AEROG of the Laborat\u00f3rio Associado em Energia, Transportes e Aeron\u00e1utica (LAETA), under LAETA","award":["LA\/P\/0079\/2020"],"award-info":[{"award-number":["LA\/P\/0079\/2020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Aerospace"],"abstract":"<jats:p>For the analysis of low-speed incompressible fluid dynamics with turbulence around airfoils, we developed a finite element formulation based on a stabilized pressure and velocity formulation. To shape the optimization of bidimensional airfoils, this formulation is applied using machine learning (TensorFlow) and public domain global optimization algorithms. The goal is to maximize the lift-over-drag ratio by using the class-shape function transformation (CST) parameterization technique and machine learning. Specifically, we propose equal-order stabilized three-node triangles for the flow problem, standard three-node triangles for the approximate distance function (ADF) required in the turbulence stage, and stabilized three-node triangles for the Spalart\u2013Allmaras turbulence model. The backward Euler time integration was employed. An implicit time-integration algorithm was adopted, and a solution was obtained using the Newton\u2013Raphson method. This was made possible in the symbolic form via Mathematica with the AceGen package. Three benchmarks are presented, with Reynolds numbers up to 1\u00d7107, demonstrating remarkable robustness. After the assessment of the new finite element, we used machine learning and global optimization for four angles of attack to calculate airfoil designs that maximized CL\/CD.<\/jats:p>","DOI":"10.3390\/aerospace10070638","type":"journal-article","created":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T01:06:36Z","timestamp":1689555996000},"page":"638","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Airfoil Analysis and Optimization Using a Petrov\u2013Galerkin Finite Element and Machine Learning"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6865-1326","authenticated-orcid":false,"given":"Pedro","family":"Areias","sequence":"first","affiliation":[{"name":"Instituto Superior T\u00e9cnico, 1049-001 Lisboa, Portugal"},{"name":"LAETA\/IDMEC, Instituto Superior T\u00e9cnico, 1049-001 Lisboa, Portugal"}]},{"given":"Rodrigo","family":"Correia","sequence":"additional","affiliation":[{"name":"Instituto Superior T\u00e9cnico, 1049-001 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1081-2729","authenticated-orcid":false,"given":"Rui","family":"Melicio","sequence":"additional","affiliation":[{"name":"LAETA\/IDMEC, Instituto Superior T\u00e9cnico, 1049-001 Lisboa, Portugal"},{"name":"LAETA\/AEROG, Universidade da Beira Interior, 1049-001 Lisboa, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"842","DOI":"10.2514\/3.49805","article-title":"Efficient algorithm for numerical airfoil optimization","volume":"16","author":"Vanderplaats","year":"1979","journal-title":"J. Aircr."},{"key":"ref_2","first-page":"1","article-title":"Automatic Differentiation in Machine Learning: A Survey","volume":"18","author":"Baydin","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1016\/j.ast.2019.07.002","article-title":"Application of deep learning based multi-fidelity surrogate model to robust aerodynamic design optimization","volume":"92","author":"Tao","year":"2019","journal-title":"Aerosp. Sci. Technol."},{"key":"ref_4","unstructured":"Zanichelli, M. (2021). Shape Optimization of Airfoils by Machine Learning-Based Surrogate Models. [Master\u2019s Thesis, Politecnico Milano]."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"116042","DOI":"10.1016\/j.cma.2023.116042","article-title":"Physics-informed deep learning for simultaneous surrogate modeling and PDE-constrained optimization of an airfoil geometry","volume":"411","author":"Sun","year":"2023","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wu, X., Zuo, Z., and Ma, L. (2022). Aerodynamic data-driven surrogate-assisted teaching-learning-based optimization (TLBO) framework for constrained transonic airfoil and wing shape designs. Aerospace, 9.","DOI":"10.3390\/aerospace9100610"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Deng, F., and Yi, J. (2023). Fast inverse design of transonic airfoils by combining deep learning and efficient global optimization. Aerospace, 10.","DOI":"10.3390\/aerospace10020125"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"015111","DOI":"10.1063\/5.0075784","article-title":"Airfoil design and surrogate modeling for performance prediction based on deep learning method","volume":"34","author":"Du","year":"2022","journal-title":"Phys. Fluids"},{"key":"ref_9","unstructured":"Selig, M. (1996). UIUC Airfoil Data Site, Department of Aeronautica, Astronautical Engineering University of Illinois at Urbana-Champaign."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"105949","DOI":"10.1016\/j.ast.2020.105949","article-title":"Fast pressure distribution prediction of airfoils using deep learning","volume":"105","author":"Hui","year":"2020","journal-title":"Aerosp. Sci. Technol."},{"key":"ref_11","first-page":"1","article-title":"A new nonlinear lifting line method for aerodynamic analysis and deep learning modeling of small unmanned aerial vehicles","volume":"13","author":"Karali","year":"2021","journal-title":"Int. J. Micro Air Veh."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4243","DOI":"10.2514\/1.J059254","article-title":"Efficient Aerodynamic Shape Optimization with Deep-Learning-Based Geometric Filtering","volume":"58","author":"Li","year":"2020","journal-title":"AIAA J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s42405-022-00507-x","article-title":"Rapid airfoil inverse design method with a deep neural network and hyperparameter selection","volume":"22","author":"Tyan","year":"2023","journal-title":"Int. J. Aeronaut. Space Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1416","DOI":"10.1007\/s10409-021-01119-6","article-title":"Machine learning for adjoint vector in aerodynamic shape optimization","volume":"37","author":"Xu","year":"2021","journal-title":"Acta Mech. Sin."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"105562","DOI":"10.1016\/j.ast.2019.105562","article-title":"Aerodynamic optimization of propellers for high altitude pseudo-satellites","volume":"96","author":"Gonzalo","year":"2020","journal-title":"Aerosp. Sci. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.taml.2020.01.039","article-title":"Physics-informed deep learning for incompressible laminar flows","volume":"10","author":"Rao","year":"2020","journal-title":"Theor. Appl. Mech. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100849","DOI":"10.1016\/j.paerosci.2022.100849","article-title":"Machine learning in aerodynamic shape optimization","volume":"134","author":"Li","year":"2022","journal-title":"Prog. Aerosp. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Mueller, T.J. (1989). Low Reynolds Number Aerodynamics, Springer.","DOI":"10.1007\/978-3-642-84010-4"},{"key":"ref_19","unstructured":"Areias, P. (2023, June 20). Simplas. Portuguese Software Association (ASSOFT) Registry Number 2281\/D\/17. Available online: http:\/\/www.simplassoftware.com."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lin, M.C., and Manocha, D. (1996). Applied Computational Geometry towards Geometric Engineering, Springer.","DOI":"10.1007\/BFb0014474"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5364","DOI":"10.1016\/j.matpr.2017.12.122","article-title":"Air foil shape optimization using CFD and parametrization methods","volume":"5","author":"Anitha","year":"2018","journal-title":"Mater. Today Proc."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"142","DOI":"10.2514\/1.29958","article-title":"Universal parametric geometry representation method","volume":"45","author":"Kulfan","year":"2008","journal-title":"J. Aircr."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Lane, K., and Marshall, D. (2010, January 4\u20137). Inverse airfoil design using CST parameterization. Proceedings of the Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition, AIAA, Orlando, FL, USA.","DOI":"10.2514\/6.2010-1228"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"G\u00fcl\u00e7at, \u00dclgen (2021). Fundamentals of Modern Unsteady Aerodynamics, Springer Nature. [3rd ed.].","DOI":"10.1007\/978-3-030-60777-7"},{"key":"ref_25","unstructured":"Research Inc. (2023, June 20). W. Mathematica. 2007. Available online: https:\/\/www.wolfram.com\/mathematica\/quick-revision-history\/."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1007\/s003660200028","article-title":"Multi-language and multi-environment generation of nonlinear finite element codes","volume":"18","author":"Korelc","year":"2002","journal-title":"Eng. Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/0045-7825(92)90141-6","article-title":"Incompressible flow computations with stabilized bilinear and linear equal-order-interpolation","volume":"95","author":"Tezduyar","year":"1992","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/S0045-7825(00)00211-5","article-title":"Finite element stabilization parameters computed from element matrices and vectors","volume":"190","author":"Tezduyar","year":"2000","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1002\/fld.505","article-title":"Computation of moving boundaries and interfaces and stabilization parameters","volume":"43","author":"Tezduyar","year":"2003","journal-title":"Int. J. Numer. Methods Fluids"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.compfluid.2005.02.010","article-title":"Finite elements in fluids: Special methods and enhanced solution techniques","volume":"36","author":"Tezduyar","year":"2007","journal-title":"Comput. Fluids"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zienkiewicz, O., Taylor, R., and Nithiarasu, P. (2014). The Finite Element Method for Fluid Dynamics, Elsevier.","DOI":"10.1016\/B978-1-85617-635-4.00014-5"},{"key":"ref_32","unstructured":"Areias, P. (2023, June 20). Turbulent 2D Subroutines for SimPlas. Available online: https:\/\/github.com\/PedroAreiasIST\/Fluid."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1002\/cpa.3160200210","article-title":"On the behavior of the fundamental solution of the heat equation with variable coefficients","volume":"20","author":"Varadhan","year":"1967","journal-title":"Commun. Pure Appl. Math."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Spalart, P., and Allmaras, S. (1992, January 6\u20139). A one-equation turbulence model for aerodynamic flows. Proceedings of the 30th Aerospace Sciences Meeting and Exhibit, Reno, NV, USA.","DOI":"10.2514\/6.1992-439"},{"key":"ref_35","unstructured":"Spalart, P., and Allmaras, S. (1994). A one-equation turbulence model for aerodynamic flows. Rech. A\u00e9rospatiale, 5\u201321."},{"key":"ref_36","unstructured":"NASA Langley Research Center (2023, June 20). The Spalart-Allmaras Turbulence Model, Available online: https:\/\/turbmodels.larc.nasa.gov\/spalart.html."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Areias, P., Melicio, R., and Correia, R. (2023, June 20). RANS with 10 Million Reynolds Number. Available online: https:\/\/youtu.be\/W7_nEaoUn9k.","DOI":"10.3390\/aerospace10070638"},{"key":"ref_38","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2023, June 20). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. 2015. Software. Available online: TensorFlow.org."},{"key":"ref_39","unstructured":"Mattmann, C. (2020). Machine Learning with TensorFlow, Manning. [2nd ed.]."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"25","DOI":"10.2514\/1.J058291","article-title":"Deep Learning Methods for Reynolds-Averaged Navier\u2013Stokes Simulations of Airfoil Flows","volume":"58","author":"Thuerey","year":"2020","journal-title":"AIAA J."},{"key":"ref_41","unstructured":"Chollet, F. (2021). Deep Learning with Python, Manning. [2nd ed.]."},{"key":"ref_42","unstructured":"Brederode, V. (2018). Aerodin\u00e2mica Incompress\u00edvel: Fundamentos, IST Press. [2nd ed.]."}],"container-title":["Aerospace"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2226-4310\/10\/7\/638\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:12:42Z","timestamp":1760127162000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2226-4310\/10\/7\/638"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,15]]},"references-count":42,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["aerospace10070638"],"URL":"https:\/\/doi.org\/10.3390\/aerospace10070638","relation":{},"ISSN":["2226-4310"],"issn-type":[{"value":"2226-4310","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,15]]}}}