Deep learning method for super-resolution reconstruction of the spatio-temporal flow field

Advances in Aerodynamics

Research

Kairui Bao¹  Wei Peng²  Xiaoya Zhang²  Wen Yao² 

[1] College of Aerospace Science and Engineering, National University of Defense Technology, 410073, Changsha, China;Defense Innovation Institute, Chinese Academy of Military Science, 100071, Beijing, China;Defense Innovation Institute, Chinese Academy of Military Science, 100071, Beijing, China;

关键词: Super-resolution;    Flow field;    UNet;    Deep learning;   

DOI  :  10.1186/s42774-023-00148-y

 received in 2022-12-20, accepted in 2023-04-06,  发布年份 2023

来源: Springer

【 摘 要 】

The high-resolution (HR) spatio-temporal flow field plays a decisive role in describing the details of the flow field. In the acquisition of the HR flow field, traditional direct numerical simulation (DNS) and other methods face a seriously high computational burden. To address this deficiency, we propose a novel multi-scale temporal path UNet (MST-UNet) model to reconstruct temporal and spatial HR flow fields from low-resolution (LR) flow field data. Different from the previous super-resolution (SR) model, which only takes advantage of LR flow field data at instantaneous (SLR) or in a time-series (MTLR), MST-UNet introduces multi-scale information in both time and space. MST-UNet takes the LR data at the current frame and the predicted HR result at the previous moment as the model input to complete the spatial SR reconstruction. On this basis, a temporal model is introduced as the inbetweening model to obtain HR flow field data in space and time to complete spatio-temporal SR reconstruction. Finally, the proposed model is validated by the spatio-temporal SR task of the flow field around two-dimensional cylinders. Experimental results show that the outcome of the MST-UNet model in spatial SR tasks is much better than those of SLR and MTLR, which can greatly improve prediction accuracy. In addition, for the spatio-temporal SR task, the spatio-temporal HR flow field predicted by the MST-UNet model has higher accuracy either.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

41116_2023_37_Article_IEq32.gif

41116_2023_37_Article_IEq31.gif

41116_2023_37_Article_IEq30.gif

41116_2023_37_Article_IEq29.gif

41116_2023_37_Article_IEq28.gif

41116_2023_37_Article_IEq27.gif

41116_2023_37_Article_IEq26.gif

41116_2023_37_Article_IEq25.gif

41116_2023_37_Article_IEq24.gif

41116_2023_37_Article_IEq23.gif

41116_2023_37_Article_IEq22.gif

Fig. 3

41116_2023_37_Article_IEq18.gif

40854_2023_491_Article_IEq27.gif

41116_2023_37_Article_IEq16.gif

41116_2023_37_Article_IEq15.gif

Fig. 2

Fig. 3

Fig. 1

Fig. 1

Fig. 1

41116_2023_37_Article_IEq14.gif

41116_2023_37_Article_IEq13.gif

41116_2023_37_Article_IEq9.gif

41116_2023_37_Article_IEq7.gif

41116_2023_37_Article_IEq6.gif

41116_2023_37_Article_IEq4.gif

41116_2023_37_Article_IEq3.gif

41116_2023_37_Article_IEq2.gif

41116_2023_37_Article_IEq1.gif

Fig. 1

Fig. 1

Fig. 7

Fig. 6

Fig. 2

Fig. 24

Fig. 7

Fig. 2

Fig. 4

Fig. 1

Fig. 3

Fig. 1

Fig. 2

Fig. 6

Fig. 12

Fig. 1

Fig. 4

Fig. 5

Fig. 2

Fig. 21

40854_2023_491_Article_IEq12.gif

Fig. 1

Fig. 9

Fig. 2

12936_2023_4634_Article_IEq5.gif

12936_2023_4634_Article_IEq2.gif

Fig. 3

Fig. 1

Fig. 2

Fig. 4

Fig. 2

Fig. 1

Fig. 13

Fig. 8

Fig. 1

Fig. 1

Fig. 3

Fig. 8

Fig. 1

Fig. 12

Fig. 11

Fig. 1

Fig. 10

Fig. 9

Fig. 8

Fig. 8

Fig. 1

Fig. 7

Fig. 7

12888_2023_4863_Article_IEq1.gif

12968_2023_940_Article_IEq3.gif

Fig. 3

Fig. 6

Fig. 3

Fig. 5

Fig. 4

Fig. 2

Fig. 4

Fig. 7

Fig. 3

Fig. 5

Fig. 2

Fig. 1

13690_2023_1130_Article_IEq62.gif

13690_2023_1130_Article_IEq57.gif

13690_2023_1130_Article_IEq47.gif

Fig. 3

Fig. 2

13690_2023_1130_Article_IEq26.gif

13690_2023_1130_Article_IEq14.gif

13690_2023_1130_Article_IEq9.gif

12938_2023_1116_Article_IEq21.gif

Fig. 6

Fig. 8