High-fidelity reconstruction of large-area damaged turbulent fields with a physically constrained generative adversarial network
- 29 February 2024
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Fluids
- Vol. 9 (2) , 024608
Abstract
The reconstruction of incomplete information in flow fields is a pervasive challenge in numerous turbulence-related applications. This paper proposes a framework for the high-fidelity reconstruction of large-area damaged turbulent fields with high resolution based on a physically constrained generative adversarial network. The network incorporates some special designs, such as leveraging complete or sparse fields of velocity components as physical constraints, employing a ResNet-like network with a fast Fourier convolution module, and adopting a PatchGAN discriminator network. To train the network, we employ a combination of loss functions, which comprise mean absolute error, network-level loss, and feature matching loss. We validate our method on a dataset of compressible isotropic turbulent flow and investigate three distinct damaged distributions with gap ratios of and . The proposed reconstruction framework has been shown to achieve excellent reconstruction performance. The reconstructed flow fields are consistent with the raw flow fields in terms of magnitude, power spectrum, and two-point correlation function. We also provide extensive ablation studies to validate our approach. The results indicate that the utilization of physical constraints significantly improves the reconstruction performance in damaged regions, particularly in cases that involve a large damaged area. Furthermore, in the proposed reconstruction framework, the size of patch in the PatchGAN discriminator network can be flexibly adjusted according to the scale of turbulence structures, and the perceptual loss function plays a crucial role in evaluating differences between feature maps of flow fields at network levels based on a pretrained network. These special designs ensure consistency across diverse scales of turbulence structures and improve the accuracy and efficiency of network training.
Keywords
Funding Information
- Research Grants Council, University Grants Committee
- Basic and Applied Basic Research Foundation of Guangdong Province
- Special Fund Project for Science and Technology Innovation Strategy of Guangdong Province (2023A0505030005)
- Hong Kong University of Science and Technology (HZQB-KCZYB-2020083)
- National Natural Science Foundation of China (62306254, 11902139)
- Hong Kong Special Administrative Region
- RGC/ECS (26200222)
- RGC/GRF (16201023)
- RGC/STG (STG2/E-605/23-N)
This publication has 52 references indexed in Scilit:
- Super-resolution analysis via machine learning: a survey for fluid flowsTheoretical and Computational Fluid Dynamics, 2023
- Prediction of aerothermal characteristics of a generic hypersonic inlet flowTheoretical and Computational Fluid Dynamics, 2021
- Using physics-informed enhanced super-resolution generative adversarial networks for subfilter modeling in turbulent reactive flowsProceedings of the Combustion Institute, 2021
- Physics-constrained bayesian neural network for fluid flow reconstruction with sparse and noisy dataTheoretical and Applied Mechanics Letters, 2020
- Prediction of aerodynamic flow fields using convolutional neural networksComputational Mechanics, 2019
- Super-resolution reconstruction of turbulent flows with machine learningJournal of Fluid Mechanics, 2019
- Semantic Understanding of Scenes Through the ADE20K DatasetInternational Journal of Computer Vision, 2018
- Divergence-free smoothing for volumetric PIV dataExperiments in Fluids, 2016
- Turbulence, Coherent Structures, Dynamical Systems and Symmetry2012
- Gappy data: To Krig or not to Krig?Journal of Computational Physics, 2006