{"title":"Learning three-dimensional flow for interactive aerodynamic design","quality_controlled":"1","status":"public","related_material":{"link":[{"description":"News on IST Homepage","relation":"press_release","url":"https://ist.ac.at/en/news/new-interactive-machine-learning-tool-makes-car-designs-more-aerodynamic/"}]},"publisher":"ACM","scopus_import":"1","oa_version":"Submitted Version","oa":1,"user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","date_created":"2018-12-11T11:44:06Z","department":[{"_id":"BeBi"}],"abstract":[{"text":"We present a data-driven technique to instantly predict how fluid flows around various three-dimensional objects. Such simulation is useful for computational fabrication and engineering, but is usually computationally expensive since it requires solving the Navier-Stokes equation for many time steps. To accelerate the process, we propose a machine learning framework which predicts aerodynamic forces and velocity and pressure fields given a threedimensional shape input. Handling detailed free-form three-dimensional shapes in a data-driven framework is challenging because machine learning approaches usually require a consistent parametrization of input and output. We present a novel PolyCube maps-based parametrization that can be computed for three-dimensional shapes at interactive rates. This allows us to efficiently learn the nonlinear response of the flow using a Gaussian process regression. We demonstrate the effectiveness of our approach for the interactive design and optimization of a car body.","lang":"eng"}],"date_published":"2018-08-04T00:00:00Z","publication_status":"published","issue":"4","month":"08","article_processing_charge":"No","date_updated":"2023-09-13T08:46:15Z","type":"journal_article","file":[{"checksum":"7a2243668f215821bc6aecad0320079a","relation":"main_file","access_level":"open_access","creator":"system","file_name":"IST-2018-1049-v1+1_2018_sigg_Learning3DAerodynamics.pdf","content_type":"application/pdf","date_updated":"2020-07-14T12:46:22Z","date_created":"2018-12-12T10:16:28Z","file_size":22803163,"file_id":"5216"}],"day":"04","project":[{"call_identifier":"H2020","grant_number":"715767","name":"MATERIALIZABLE: Intelligent fabrication-oriented Computational Design and Modeling","_id":"24F9549A-B435-11E9-9278-68D0E5697425"}],"ddc":["003","004"],"isi":1,"file_date_updated":"2020-07-14T12:46:22Z","year":"2018","intvolume":" 37","volume":37,"publist_id":"8053","article_number":"89","_id":"4","language":[{"iso":"eng"}],"pubrep_id":"1049","citation":{"mla":"Umetani, Nobuyuki, and Bernd Bickel. “Learning Three-Dimensional Flow for Interactive Aerodynamic Design.” ACM Trans. Graph., vol. 37, no. 4, 89, ACM, 2018, doi:10.1145/3197517.3201325.","ieee":"N. Umetani and B. Bickel, “Learning three-dimensional flow for interactive aerodynamic design,” ACM Trans. Graph., vol. 37, no. 4. ACM, 2018.","ama":"Umetani N, Bickel B. Learning three-dimensional flow for interactive aerodynamic design. ACM Trans Graph. 2018;37(4). doi:10.1145/3197517.3201325","apa":"Umetani, N., & Bickel, B. (2018). Learning three-dimensional flow for interactive aerodynamic design. ACM Trans. Graph. ACM. https://doi.org/10.1145/3197517.3201325","ista":"Umetani N, Bickel B. 2018. Learning three-dimensional flow for interactive aerodynamic design. ACM Trans. Graph. 37(4), 89.","chicago":"Umetani, Nobuyuki, and Bernd Bickel. “Learning Three-Dimensional Flow for Interactive Aerodynamic Design.” ACM Trans. Graph. ACM, 2018. https://doi.org/10.1145/3197517.3201325.","short":"N. Umetani, B. Bickel, ACM Trans. Graph. 37 (2018)."},"ec_funded":1,"external_id":{"isi":["000448185000050"]},"author":[{"last_name":"Umetani","first_name":"Nobuyuki","full_name":"Umetani, Nobuyuki"},{"full_name":"Bickel, Bernd","id":"49876194-F248-11E8-B48F-1D18A9856A87","first_name":"Bernd","last_name":"Bickel","orcid":"0000-0001-6511-9385"}],"has_accepted_license":"1","publication":"ACM Trans. Graph.","doi":"10.1145/3197517.3201325"}