Skip to content

A Swin-transformer-based model for efficient compression of turbulent flow data

Document Type
Publications · Journal Article
Registered DB
SCIEScopus
Journal Ranking
JCR Q1Scopus Q1
Journal
PHYSICS OF FLUIDS35(8) · #85108 · 2023
Citation
Web of Science 17Scopus 21
FWCI (Scopus)
1.72
JCR IF
JCR 2022 4.6
ISSN
1070-6631

Authors

  1. Zhang, MengFirst authorPusan Natl Univ, Sch Mech Engn, Busan 46241, South Korea
  2. Yousif Mustafa Zuhair GheniPusan Natl Univ, Sch Mech Engn, Busan 46241, South Korea
  3. Yu, LinqiPusan Natl Univ, Sch Mech Engn, Busan 46241, South Korea
  4. Lim, HeechangCorresponding authorPusan Natl Univ, Sch Mech Engn, Busan 46241, South Korea

Abstract

This study proposes a novel deep-learning-based method for generating reduced representations of turbulent flows that ensures efficient storage and transfer while maintaining high accuracy during decompression. A Swin-transformer (ST) network combined with a physical constraints-based loss function is utilized to compress the turbulent flows with high compression ratios and then restore the data with underlying physical properties. The forced isotropic turbulence is used to demonstrate the ability of the ST-based model, where the instantaneous and statistical results show the excellent ability of the model to recover the flow data with a remarkable accuracy. Furthermore, the capability of the ST model is compared with a typical convolutional neural network-based auto-encoder (CNN-AE) by using the turbulent channel flow at two friction Reynolds numbers Re-tau = 180 and 550. The results generated by the ST model are significantly more consistent with the direct numerical simulation data than those recovered by the CNN-AE, indicating the superior ability of the ST model to compress and restore the turbulent flow. This study also compares the compression performance of the ST model at different compression ratios (CR s) and finds that the model has low enough error even at very high CR. Additionally, the effect of transfer learning (TL) is investigated, showing that TL reduces the training time by 64% while maintaining high accuracy. The results illustrate for the first time that the Swin-transformer-based model incorporating a physically constrained loss function can compress and restore turbulent flows with the correct physics. (c) 2023 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license (http:// creativecommons.org/licenses/by/4.0/).

Keywords

DIRECT NUMERICAL-SIMULATIONWINDALGORITHMSPREDICTION

Identifiers

Scopus EID
2-s2.0-85167364065
WoS UID
001074432500009