Applications of deep learning-based super-resolution for reconstruction of flow around the CAARC benchmark model

LIANG Rengkang; ZHANG Wei; YANG Sifan; HUANG Gang; LI Lang

doi:10.7638/kqdlxxb-2022.0157

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Applications of deep learning-based super-resolution for reconstruction of flow around the CAARC benchmark model

更新时间：2026-05-28

- Applications of deep learning-based super-resolution for reconstruction of flow around the CAARC benchmark model
- Vol. 41, Issue 11, Pages: 116-126(2023)
- 作者机构：
  
  1. 西南科技大学土木工程与建筑学院,绵阳,621010
  2. 中国空气动力研究与发展中心超高速空气动力研究所,绵阳,621000
  3. 空天飞行空气动力科学与技术全国重点实验室,绵阳,621000
- 作者简介：
- 基金信息：
- DOI：10.7638/kqdlxxb-2022.0157
  CLC： O355;TP391.7;TU972+.8
- Published：2023
- 稿件说明：
移动端阅览
梁仍康, 张伟, 杨思帆, 等. 基于深度学习的超分辨率重构方法在CAARC标模绕流流场重构中的应用[J]. 空气动力学学报, 2023, 41(11): 116−126.

LIANG Rengkang, ZHANG Wei, YANG Sifan, et al. Applications of deep learning-based super-resolution for reconstruction of flow around the CAARC benchmark model[J]. 2023, 41(11): 116-126.
梁仍康, 张伟, 杨思帆, 等. 基于深度学习的超分辨率重构方法在CAARC标模绕流流场重构中的应用[J]. 空气动力学学报, 2023, 41(11): 116−126. DOI： 10.7638/kqdlxxb-2022.0157

LIANG Rengkang, ZHANG Wei, YANG Sifan, et al. Applications of deep learning-based super-resolution for reconstruction of flow around the CAARC benchmark model[J]. 2023, 41(11): 116-126. DOI： 10.7638/kqdlxxb-2022.0157.

摘要

基于深度学习的超分辨率重构方法是近年来发展的一种有效的流场精细化方法。本文超分辨率重构模型以卷积神经网络为基础，结合了混合下采样跳跃连接多尺度模型，并应用于CAARC标准建筑模型表面风压场和建筑绕流速度场的重构。通过对比分析对不同欠分辨率流场的高分辨重构能力，结果表明该深度学习模型重构高分辨率流场具有良好的精度，重构效果优于原始的卷积神经网络模型和传统的双三次插值方法。该方法具有一定的普适性，可推广应用到具有复杂湍流流动的任意建筑结构风场的超分辨率重构。

Abstract

The deep-learning-based super-resolution reconstruction methods developed in recent years are effective methods to obtain detailed flow fields. A deep learning-based super-resolution reconstruction method was applied to reconstructing high-resolution wind field of flow around building structures in this paper. The super-resolution reconstruction model was based on the convolutional neural network (CNN) and combined with the mixed downsampled skip-connection multi-scale (Multi-scale CNN) model. The super-resolution reconstruction model was applied to the reconstruction of the surface pressure on and the velocity field around the CAARC benchmark model. The reconstruction ability of the deep learning-based model for different under-resolution flow fields was investigated. The results show that the proposed deep learning model can greatly enhance the super-resolution reconstruction performance and the reconstruction accuracy is better than the original convolutional neural network model and the traditional bicubic interpolation method. Due to its universal applicability

this method can be extended to super-resolution reconstruction of wind field of any building structure with complex turbulent flow.

关键词

Keywords

references

HOLMES J D. Wind loading of structures[M]. Florida: CRC Press, 2001.

WU B G, WU J R, FU J Y. Non-stationary analysis on field measured wind speed data of tall buildings[J]. Acta Aerodynamica Sinica, 2014, 32(3): 410-415(in Chinese).

HUANG J, GU M. Experimental investigation of blockage effects on mean pressure of rectangular tall buildings in the wind tunnel[J]. Acta Aerodynamica Sinica, 2015, 33(3): 414-419, 426(in Chinese).

CAO H L, QUAN Y, GU M. Wind tunnel test on across-wind aerodynamic damping of rectangular super-high-rise buildings[J]. Acta Aerodynamica Sinica, 2014, 32(3): 351-359(in Chinese).

ZHU W L, YANG Q S, CAO S Y. Applicability research on the turbulent inflow for building LES simulation[J]. Acta Aerodynamica Sinica, 2011, 29(1): 124-128(in Chinese).

YANG X, WANG C Q, FEI S M. An adaptive method for simultaneous image super-resolution and motion estimation based on nonlinear least square[J]. Journal of Image and Graphics, 2010, 15(12): 1714-1719(in Chinese).

SUN R H, SHI L F, HUANG L Y, et al. Reversible data hiding based on image interpolation and reference matrix[J]. Journal of Guangxi Normal University(Natural Science Edition), 2019, 37(2): 90-104. doi: 10.16088/j.issn.1001-6600.2019.02.011

XI Z H, YUAN K P. Super-resolution image reconstruction based on residual channel attention and multilevel feature fusion[J]. Laser Optoelectronics Progress, 2020, 57(4): 041504 (in Chinese). doi: 10.3788/lop57.041504

ZHAO J T. Single-image defogging algorithm based on deep learning[J]. Laser Optoelectronics Progress, 2019, 56(11): 146-153(in Chinese).

DONG C, LOY C C, HE K M, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. DOI: 10.1109/TPAMI.2015.2439281

DONG C, LOY C C, TANG X O. Accelerating the super-resolution convolutional neural network[M]//Computer Vision - ECCV 2016. Cham: Springer International Publishing, 2016: 391-407. doi: 10.1007/978-3-319-46475-6_25

FUKAMI K, FUKAGATA K, TAIRA K. Super-resolution reconstruction of turbulent flows with machine learning[J]. Journal of Fluid Mechanics, 2019, 870: 106-120. DOI: 10.1017/jfm.2019.238

FUKAMI K, FUKAGATA K, TAIRA K. Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows[J]. Journal of Fluid Mechanics, 2021, 909: A9. DOI: 10.1017/jfm.2020.948

LIU B, TANG J P, HUANG H B, et al. Deep learning methods for super-resolution reconstruction of turbulent flows[J]. Physics of Fluids, 2020, 32(2): 025105. DOI: 10.1063/1.5140772

KIM H, KIM J, WON S, et al. Unsupervised deep learning for super-resolution reconstruction of turbulence[J]. Journal of Fluid Mechanics, 2021, 910: A29. DOI: 10.1017/jfm.2020.1028

BRUNTON S L, NOACK B R, KOUMOUTSAKOS P. Machine learning for fluid mechanics[J]. Annual Review of Fluid Mechanics, 2020, 52: 477-508. DOI: 10.1146/annurev-fluid-010719-060214

MELBOUME W H. Comparison of measurements on the CAARC standard tall building model in simulated model wind flows[J]. Journal of Wind Engineering and Industrial Aerodynamics, 1980, 6(1-2): 73-88. DOI: 10.1016/0167-6105(80)90023-9

ELSHAER A, ABOSHOSHA H, BITSUAMLAK G, et al. LES evaluation of wind-induced responses for an isolated and a surrounded tall building[J]. Engineering Structures, 2016, 115: 179-195. DOI: 10.1016/j.engstruct.2016.02.026

LU C L, LI Q S, HUANG S H, et al. Simulation of large eddy of wind load on a long-span complex roof structure[J]. China Civil Engineering Journal, 2011, 44(1): 1-10(in Chinese).

SKYTTE M, THORDAL, . Review for practical application of CFD for the determination of wind load on high-rise buildings[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2019, 186: 155-168. DOI: 10.1016/j.jweia.2018.12.019

DAGNEW A K, BITSUAMLAK G T. Computational evaluation of wind loads on a standard tall building using LES[J]. Wind and Structures, 2014, 18(5): 567-598. DOI: 10.12989/was.2014.18.5.567

YAN B W, LI Q S. Inflow turbulence generation methods with large eddy simulation for wind effects on tall buildings[J]. Computers Fluids, 2015, 116: 158-175. DOI: 10.1016/j.compfluid.2015.04.020

YUE, ZHANG, . Predicting wind-induced vibrations of high-rise buildings using unsteady CFD and modal analysis[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2015, 136: 165-179. DOI: 10.1016/j.jweia.2014.11.008

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Flow field reconstruction for Bolund Island based on CNN

A method of unsteady periodic flow field prediction based on the deep learning

Particle image velocimetry based on a deep neural network

Aerodynamic force measurement algorithm based on U-Net in maglev flight wind tunnel

Reconstruction method for three-dimensional temperature field on the aircraft model surface

Related Author

LI Yifeng

XUE Ming

WU Dingcong

ZHANG Wei

NI Zhangsong

HUI Xinyu

YUAN Zelong

BAI Junqiang

Related Institution

Chengdu Fluid Dynamics Innovation Center, Chengdu

School of Aeronautics, Northwestern Polytechnical University

State Key Laboratory of Strength and Vibration of Mechanical Structures, Xi'an Jiaotong University

School of Aeronautics and Astronautics, Zhejiang University

College of Control Science and Engineering, Zhejiang University

AI问答

⁰