FPGA implementation of an optimized neural network for CFD acceleration

Basit Öğe Kaydı
dc.authorid0009-0001-3171-9478
dc.contributor.authorCevik, Gokalp
dc.contributor.authorSarioglu, Baykal
dc.contributor.authorAka, Ibrahim Bazar
dc.date.accessioned2026-04-04T18:55:26Z
dc.date.available2026-04-04T18:55:26Z
dc.date.issued2025
dc.departmentİstanbul Bilgi Üniversitesi
dc.description.abstractIn this work, an evaluation of FPGAs as the central computation platform in domain-specific AI-accelerated CFD simulations is performed. This evaluation is performed in three categories: power efficiency, speed, and accuracy. The specific domain in the study is the FDA nozzle benchmark, which is simulated using SimpleFoam, a laminar solver that is a component of the OpenFOAM CFD toolbox. The proposed AI model is a low-parameter feed-forward neural network with three fully connected layers, trained using steadystate solutions distinguished by various Reynolds numbers, all of which are computed by the OpenFOAM framework. The proposed model can then generate the steady-state CFD simulation result given the initial few iterations generated by the solver. Moreover, this paper introduces a hardware implementation for inference of the simulation results using an SoC chip with minimal hardware resource utilization. The suggested hardware design is developed from scratch for Zynq-7000 System-on-Chip, using only VHDL, and requiring no dependencies on third-party commercial AI frameworks or costly FPGA boards designed for AI-related applications. The proposed workflow in the test case study achieves a 98% reduction in simulation time while maintaining relatively high accuracy and a 95.6% reduction in energy consumption compared with the regular CFD workflow.
dc.identifier.doi10.1016/j.aeue.2024.155574
dc.identifier.doi10.1016/j.aeue.2024.155574
dc.identifier.issn1434-8411
dc.identifier.issn1618-0399
dc.identifier.scopus2-s2.0-85209106951
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.aeue.2024.155574
dc.identifier.urihttps://hdl.handle.net/11411/10423
dc.identifier.volume188
dc.identifier.wosWOS:001359172400001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier Gmbh
dc.relation.ispartofAeu-International Journal of Electronics and Communications
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WoS_20260402
dc.snmzKA_Scopus_20260402
dc.subjectFpga
dc.subjectNeural Networks
dc.subjectCfd
dc.subjectEmbedded Computing
dc.titleFPGA implementation of an optimized neural network for CFD acceleration
dc.typeArticle

Dosyalar

Koleksiyon

Web of Science Indexed Publications
Scopus Indexed Publications