An AI-Accelerated CFD Application on a Benchmark Device: FDA Nozzle

Basit Öğe Kaydı
dc.contributor.authorAka, Ibrahim Basar
dc.contributor.authorIscan, Mehmet
dc.date.accessioned2024-07-18T20:47:28Z
dc.date.available2024-07-18T20:47:28Z
dc.date.issued2022
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.descriptionMedical Technologies Congress (TIPTEKNO) -- OCT 31-NOV 02, 2022 -- Antalya, TURKEYen_US
dc.description.abstractIn this study, we suggest a procedure for speeding CFD (computational fluid dynamics) analysis up by combining a conventional opensource CFD solver with a traditional AI module. The studied case is the FDA benchmark nozzle with various Reynolds numbers. The considered CFD simulations belong to a group of steady-state simulations and utilize the laminar flow solver SimpleFoam in the OpenFOAM toolbox. The proposed module is implemented as a Feed-Forward Neural Network (FFNN) supervised learning procedure. Our method distributes the data by creating a combined AI model for each quantity of the simulated phenomenon for various Reynolds numbers. The model can then be combined after the initial iteration phase to decrease the execution time or to lower memory requirements. We analyze the performance of the proposed method depending on the estimation accuracy of the data of interest, velocity, and pressure. For test data, we achieve time-to-solution discounts of nearly a factor of 10. Comparing simulation results based on the FFNN test results and 3D visualization shows the average accuracy for all the parameters over 99% for the velocity and the pressure.en_US
dc.description.sponsorshipBiyomedikal Klinik Muhendisligi Dernegi,Izmir Ekonomi Univen_US
dc.description.sponsorshipIstanbul Bilgi University Scientific Research Fund (BAP)en_US
dc.description.sponsorshipThis study is supported by Istanbul Bilgi University Scientific Research Fund (BAP).en_US
dc.identifier.doi10.1109/TIPTEKNO56568.2022.9960231
dc.identifier.isbn978-1-6654-5432-2
dc.identifier.scopus2-s2.0-85144053788en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://doi.org/10.1109/TIPTEKNO56568.2022.9960231
dc.identifier.urihttps://hdl.handle.net/11411/7797
dc.identifier.wosWOS:000903709700084en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartof2022 Medical Technologies Congress (Tiptekno'22)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAı Acceleration For Cfden_US
dc.subjectConvolutional Neural Networksen_US
dc.subjectFda Nozzleen_US
dc.subject3d Gridsen_US
dc.subjectOpenfoamen_US
dc.subjectCpu Computingen_US
dc.titleAn AI-Accelerated CFD Application on a Benchmark Device: FDA Nozzle
dc.typeConference Object

Dosyalar

Koleksiyon

Web of Science Indexed Publications
Scopus Indexed Publications