{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T04:52:46Z","timestamp":1790139166180,"version":"4.0.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100017266","name":"Gobierno de Navarra","doi-asserted-by":"publisher","award":["AEROSUN"],"award-info":[{"award-number":["AEROSUN"]}],"id":[{"id":"10.13039\/501100017266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The aim of this article is to evaluate the ability of a convolutional neural network (CNN) to predict velocity and pressure aerodynamic fields in heavy vehicles. For training and testing the developed CNN, various CFD simulations of three different vehicle geometries have been conducted, considering the RANS-based k-\u03c9 SST turbulent model. Two geometries correspond to the SC7 and SC5 coach models of the bus manufacturer SUNSUNDEGUI and the third one corresponds to Ahmed body. By generating different variants of these three geometries, a large number of representations of the velocity and pressure fields are obtained that will be used to train, verify, and evaluate the convolutional neural network. To improve the accuracy of the CNN, the field representations obtained are discretized as a function of the expected velocity gradient, so that in the areas where there is a greater variation in velocity, the corresponding neuron is smaller. The results show good agreement between numerical results and CNN predictions, being the CNN able to accurately represent the velocity and pressure fields with very low errors. Additionally, a substantial improvement in the computational time needed for each simulation is appreciated, reducing it by four orders of magnitude.<\/jats:p>","DOI":"10.1038\/s41598-023-48419-4","type":"journal-article","created":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T14:02:32Z","timestamp":1701439352000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["CNN-based flow field prediction for bus aerodynamics analysis"],"prefix":"10.1038","volume":"13","author":[{"given":"Roberto","family":"Garcia-Fernandez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koldo","family":"Portal-Porras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oscar","family":"Irigaray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zugatz","family":"Ansa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Unai","family":"Fernandez-Gamiz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,1]]},"reference":[{"key":"48419_CR1","unstructured":"Ansa, Z., Garcia, R. , Fernandez Gamiz, U. , Portal-Porras, K. , Zulueta, E., & Lopez Guede, J. M. CFD and fuel consumption analysis and study of a bus, Istanbul, Turkey, May 7 2022."},{"key":"48419_CR2","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.jcp.2018.04.029","volume":"25","author":"D Ray","year":"2018","unstructured":"Ray, D. & Hesthaven, J. S. An artificial neural network as a troubled-cell indicator. J. Comput. Phys. 25, 166\u2013191 (2018).","journal-title":"J. Comput. Phys."},{"key":"48419_CR3","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1016\/j.ast.2019.02.003","volume":"20","author":"X Yan","year":"2019","unstructured":"Yan, X., Zhu, J., Kuang, M. & Wang, X. Aerodynamic shape optimization using a Novel optimizer based on machine learning techniques. Aerosp. Sci. Technol. 20, 826\u2013835 (2019).","journal-title":"Aerosp. Sci. Technol."},{"key":"48419_CR4","doi-asserted-by":"publisher","first-page":"8205","DOI":"10.1038\/s41598-022-12157-w","volume":"12","author":"K Portal-Porras","year":"2022","unstructured":"Portal-Porras, K., Fernandez-Gamiz, U., Zulueta, E., Ballesteros-Coll, A. & Zulueta, A. CNN-based flow control device modelling on aerodynamic airfoils. Sci. Rep. 12, 8205. https:\/\/doi.org\/10.1038\/s41598-022-12157-w (2022).","journal-title":"Sci. Rep."},{"key":"48419_CR5","first-page":"12","volume":"20","author":"SJ Jacob","year":"2021","unstructured":"Jacob, S. J., Mrosek, M., Othmer, C. & K\u00f6stler, H. Deep learning for real-time aerodynamic evaluations of arbitrary vehicle shapes. Volkswagen AG 20, 12 (2021).","journal-title":"Volkswagen AG"},{"key":"48419_CR6","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1038\/s41598-020-61450-z","volume":"20","author":"S Ye","year":"2020","unstructured":"Ye, S. et al. A flow feature detection method for modeling pressure distribution around a cylinder in non-uniform flows by using a convolutional neural network. Sci. Rep. 20, 10. https:\/\/doi.org\/10.1038\/s41598-020-61450-z (2020).","journal-title":"Sci. Rep."},{"key":"48419_CR7","unstructured":"Ribeiro, M. D., Rehman, A., Ahmed, S., & Dengel, A. DeepCFD: Efficient Steady-State Laminar Flow Approximation with Deep Convolutional Neural Networks. arXiv:2004.08826 [physics] 2020."},{"key":"48419_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sung, J., & Mavris, D. N. Application of convolutional neural network to predict airfoil lift coefficient. In Structures, Structural Dynamics, and Materials Conference; 2018.","DOI":"10.2514\/6.2018-1903"},{"key":"48419_CR9","doi-asserted-by":"publisher","first-page":"656","DOI":"10.3390\/vehicles5020036","volume":"5","author":"A Misar","year":"2023","unstructured":"Misar, A., Tison, N. A., Korivi, V. M. & Uddin, M. Application of the DMD approach to high-Reynolds-number flow over an idealized ground vehicle. Vehicles 5, 656\u2013681. https:\/\/doi.org\/10.3390\/vehicles5020036 (2023).","journal-title":"Vehicles"},{"key":"48419_CR10","doi-asserted-by":"publisher","first-page":"225","DOI":"10.4271\/06-12-03-0016","volume":"12","author":"M Mrosek","year":"2019","unstructured":"Mrosek, M., Othmer, C. & Radespiel, R. Reduced-order modeling of vehicle aerodynamics via proper orthogonal decomposition. SAE Int. J. Passeng. Cars Mech. Syst. 12, 225\u2013236. https:\/\/doi.org\/10.4271\/06-12-03-0016 (2019).","journal-title":"SAE Int. J. Passeng. Cars Mech. Syst."},{"key":"48419_CR11","doi-asserted-by":"publisher","first-page":"201823","DOI":"10.1109\/ACCESS.2020.3035318","volume":"8","author":"F Jaffar","year":"2020","unstructured":"Jaffar, F., Farid, T., Sajid, M., Ayaz, Y. & Khan, M. J. Prediction of drag force on vehicles in a platoon configuration using machine learning. IEEE Access 8, 201823\u2013201834. https:\/\/doi.org\/10.1109\/ACCESS.2020.3035318 (2020).","journal-title":"IEEE Access"},{"key":"48419_CR12","doi-asserted-by":"crossref","unstructured":"Mrosek, M., Othmer, C., & Radespiel, R. Variational autoencoders for model order reduction in vehicle aerodynamics. In AIAA AVIATION 2021 FORUM (American Institute of Aeronautics and Astronautics).","DOI":"10.2514\/6.2021-3049"},{"key":"48419_CR13","first-page":"12","volume":"20","author":"I Bayraktar","year":"2001","unstructured":"Bayraktar, I., Landman, D. & Baysal, O. Experimental and computational investigation of Ahmed body for ground vehicle aerodynamics. SAE Int. 20, 12 (2001).","journal-title":"SAE Int."},{"key":"48419_CR14","first-page":"13","volume":"06","author":"H Lienhart","year":"2003","unstructured":"Lienhart, H. & Becker, S. Flow and turbulence structure in the wake of a simplified car model. SAE Int. 06, 13 (2003).","journal-title":"SAE Int."},{"key":"48419_CR15","doi-asserted-by":"publisher","first-page":"318","DOI":"10.3390\/vehicles2020018","volume":"2","author":"C Fu","year":"2020","unstructured":"Fu, C., Uddin, M. & Zhang, C. Computational analyses of the effects of wind tunnel ground simulation and blockage ratio on the aerodynamic prediction of flow over a passenger vehicle. Vehicles 2, 318\u2013341. https:\/\/doi.org\/10.3390\/vehicles2020018 (2020).","journal-title":"Vehicles"},{"key":"48419_CR16","first-page":"32","volume":"93","author":"SR Ahmed","year":"1984","unstructured":"Ahmed, S. R., Ramm, G. & Faltin, G. Some salient features if the time-averaged ground vehicle wake. SAE Int. 93, 32 (1984).","journal-title":"SAE Int."},{"key":"48419_CR17","unstructured":"SIEMENS Siemens Star-CCM+."},{"key":"48419_CR18","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/S0167-6105(97)00147-5","volume":"20","author":"W Rodi","year":"1997","unstructured":"Rodi, W. Comparison of LES and RANS calculations of the flow around bluff bodies. J. Wind Eng. Ind. Aerodyn. 20, 55\u201375 (1997).","journal-title":"J. Wind Eng. Ind. Aerodyn."},{"key":"48419_CR19","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/S0142-727X(96)00134-8","volume":"18","author":"P Bradshaw","year":"1997","unstructured":"Bradshaw, P. Understanding and prediction of turbulent flow. Int. J. Heat Fluid Flow 18, 45\u201354 (1997).","journal-title":"Int. J. Heat Fluid Flow"},{"key":"48419_CR20","first-page":"38","volume":"20","author":"FR Menter","year":"1992","unstructured":"Menter, F. R. Improved two-equation k\u2013\u03c9 turbulence models for aerodynamic flows. NASA 20, 38 (1992).","journal-title":"NASA"},{"key":"48419_CR21","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.2514\/3.10041","volume":"26","author":"DC Wilcox","year":"1998","unstructured":"Wilcox, D. C. Reassesment of the scale-determining equation for advanced turbulence models. AIAA J. 26, 1299\u20131310 (1998).","journal-title":"AIAA J."},{"key":"48419_CR22","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1016\/0017-9310(73)90125-7","volume":"16","author":"WP Jones","year":"1973","unstructured":"Jones, W. P. & Launder, B. E. The Calculation of low-Reynods-number-phenomena with a two-equation model of turbulence. Int. J. Heat Mass Transf. 16, 1119\u20131130 (1973).","journal-title":"Int. J. Heat Mass Transf."},{"key":"48419_CR23","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1017\/jfm.2013.83","volume":"722","author":"M Grandemange","year":"2013","unstructured":"Grandemange, M., Gohlke, M. & Cadot, O. Turbulent wake past a three-dimensional blunt body. Part 1. global modes and bi-stability. J. Fluid Mech. 722, 51\u201384. https:\/\/doi.org\/10.1017\/jfm.2013.83 (2013).","journal-title":"J. Fluid Mech."},{"key":"48419_CR24","doi-asserted-by":"publisher","first-page":"A36","DOI":"10.1017\/jfm.2021.748","volume":"926","author":"K He","year":"2021","unstructured":"He, K. et al. Numerical Investigation of the wake bi-stability behind a notchback Ahmed body. J. Fluid Mech. 926, A36. https:\/\/doi.org\/10.1017\/jfm.2021.748 (2021).","journal-title":"J. Fluid Mech."},{"key":"48419_CR25","doi-asserted-by":"publisher","first-page":"2522","DOI":"10.1177\/0954407020916671","volume":"234","author":"CP Bounds","year":"2020","unstructured":"Bounds, C. P., Zhang, C. & Uddin, M. Improved CFD prediction of flows past simplified and real-life automotive bodies using modified turbulence model closure coefficients. Proc. Inst. Mech. Eng. Part D J. Automob. Eng. 234, 2522\u20132545. https:\/\/doi.org\/10.1177\/0954407020916671 (2020).","journal-title":"Proc. Inst. Mech. Eng. Part D J. Automob. Eng."},{"key":"48419_CR26","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.compfluid.2017.01.005","volume":"176","author":"E Guilmineau","year":"2018","unstructured":"Guilmineau, E. et al. Assessment of hybrid RANS-LES formulations for flow simulation around the Ahmed body. Comput. Fluids 176, 302\u2013319. https:\/\/doi.org\/10.1016\/j.compfluid.2017.01.005 (2018).","journal-title":"Comput. Fluids"},{"key":"48419_CR27","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3390\/math9161939","volume":"2021","author":"K Portal-Porras","year":"1939","unstructured":"Portal-Porras, K., Fernandez-Gamiz, U., Ugarte-Anero, A., Zulueta, E. & Zulueta, A. Alternative artificial neural network structures for turbulent flow velocity field prediction. Mathematics 2021, 9. https:\/\/doi.org\/10.3390\/math9161939 (1939).","journal-title":"Mathematics"},{"key":"48419_CR28","doi-asserted-by":"crossref","unstructured":"Guo, X., Li, W., & Iorio, F. Convolutional neural networks for steady flow approximation. In Proceedings of the Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 481\u2013490 (ACM, 2016).","DOI":"10.1145\/2939672.2939738"},{"key":"48419_CR29","unstructured":"MATLAB. https:\/\/es.mathworks.com\/products\/matlab.html. Accessed 9 June 2021."},{"key":"48419_CR30","unstructured":"Deep Learning Toolbox. https:\/\/es.mathworks.com\/products\/deep-learning.html. Accessed 3 July 2021."},{"key":"48419_CR31","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015 (Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F., Eds.), 234\u2013241 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"48419_CR32","doi-asserted-by":"crossref","unstructured":"Kashefi, A., Rempe, D., & Guibas, L. J. A point-cloud deep learning framework for prediction of fluid flow fields on irregular geometries. arXiv:2010.09469 [physics]; 2020.","DOI":"10.1063\/5.0033376"},{"key":"48419_CR33","unstructured":"Kingma, D. P., & Ba, J. Adam: A method for stochastic optimization. arXiv:1412.6980 [cs]; 2017."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-48419-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-48419-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-48419-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T14:13:07Z","timestamp":1701439987000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-48419-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["48419"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-48419-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,1]]},"assertion":[{"value":"15 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"21213"}}