Skip to content

A new fluid flow approximation method using a vision transformer and a U-shaped convolutional neural network

Document Type
Publications · Journal Article
Registered DB
SCIEScopus
Journal Ranking
JCR Q4Scopus Q2
Journal
AIP ADVANCES13(2) · 2023
Citation
Web of Science 20Scopus 22
FWCI (Scopus)
1.59
JCR IF
JCR 2022 1.6
ISSN
2158-3226

Authors

  1. Hyoeun KangFirst authorPusan Natl Univ, Sch Comp Sci & Engn, Busan 46241, South Korea
  2. Yongsu KimPusan Natl Univ, Sch Comp Sci & Engn, Busan 46241, South Korea
  3. Thi-Thu-Huong LePusan Natl Univ, Blockchain Platform Res Ctr, Busan 46241, South Korea
  4. Changwoo ChoiPusan Natl Univ, Sch Comp Sci & Engn, Busan 46241, South Korea
  5. YoonYoung HongPusan Natl Univ, Sch Comp Sci & Engn, Busan 46241, South Korea
  6. Hong, SeungdoLG Elect, Air Solut R&D Lab, Chang Won 51554, South Korea
  7. Chin, Sim WonLG Elect, Air Solut R&D Lab, Chang Won 51554, South Korea
  8. Kim, HowonCorresponding authorPusan Natl Univ, Sch Comp Sci & Engn, Busan 46241, South Korea

Abstract

© 2023 Author(s).Numerical simulation of fluids is important in modeling a variety of physical phenomena, such as weather, climate, aerodynamics, and plasma physics. The Navier-Stokes equations are commonly used to describe fluids, but solving them at a large scale can be computationally expensive, particularly when it comes to resolving small spatiotemporal features. This trade-off between accuracy and tractability can be challenging. In this paper, we propose a novel artificial intelligence-based method for improving fluid flow approximations in computational fluid dynamics (CFD) using deep learning (DL). Our method, called CFDformer, is a surrogate model that can handle both local and global features of CFD input data. It is also able to adjust boundary conditions and incorporate additional flow conditions, such as velocity and pressure. Importantly, CFDformer performs well under different velocities and pressures outside of the flows it was trained on. Through comprehensive experiments and comparisons, we demonstrate that CFDformer outperforms other baseline DL models, including U-shaped convolutional neural network (U-Net) and TransUNet models.

Identifiers

Scopus EID
2-s2.0-85147796049
WoS UID
000926849300035