Flow Reconstruction Using Spatially Restricted Domains Based on Enhanced Super-Resolution Generative Adversarial Networks

TL;DR

This paper introduces an enhanced super-resolution GAN model capable of reconstructing complete flow fields from limited spatial data, effectively capturing complex flow features and matching statistical properties across laminar, turbulent, and experimental flows.

Contribution

The study presents a novel ESRGAN-based approach for flow reconstruction from limited data regions, demonstrating high accuracy and physical consistency in diverse flow scenarios.

Findings

Successfully reconstructs full flow fields from limited regions in laminar and turbulent flows.

Reconstructed flow statistics closely match original data and experimental measurements.

Model conforms to the temporal behavior of flow fields as shown by power spectrum density analysis.

Abstract

This study aims to reconstruct the complete flow field from spatially restricted domain data by utilizing an Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) model. The difficulty in flow field reconstruction lies in accurately capturing and reconstructing large amounts of data under nonlinear, multi-scale, and complex flow while ensuring physical consistency and high computational efficiency. The ESRGAN model has a strong information mapping capability, capturing fluctuating features from local flow fields of varying geometries and sizes. The model effectiveness in reconstructing the whole domain flow field is validated by comparing instantaneous velocity fields, flow statistical properties, and probability density distributions. Using laminar bluff body flow from Direct Numerical Simulation (DNS) as a priori case, the model successfully reconstructs the complete flow field from three non-overlapping limited regions, with flow statistical properties perfectly matching the original data. Validation of the power spectrum density (PSD) for the reconstruction results also proves that the model could conform to the temporal behavior of the real complete flow field. Additionally, tests using DNS turbulent channel flow with a friction Reynolds number ($Re_\tau = 180$) demonstrate the model ability to reconstruct turbulent fields, though the quality of results depends on the number of flow features in the local regions. Finally, the model is applied to reconstruct turbulence flow fields from Particle Image Velocimetry (PIV) experimental measurements, using limited data from the near-wake region to reconstruct a larger field of view. The turbulence statistics closely match the experimental data, indicating that the model can serve as a reliable data-driven method to overcome PIV field-of-view limitations while saving computational costs.