Three-dimensional generative adversarial networks for turbulent flow estimation from wall measurements
Authors:
- Antonio CuéllarACAntonio Cuéllar
- Alejandro GüemesAGAlejandro Güemes
- Andrea IaniroAIAndrea Ianiro
- Óscar FloresÓFÓscar Flores
- Ricardo VinuesaRVRicardo Vinuesa
- Stefano DiscettiSDStefano Discetti
Preprint
Abstract
Different types of neural networks have been used to solve the flow sensing problem in turbulent flows, namely to estimate velocity in wall-parallel planes from wall measurements. Generative adversarial networks (GANs) are among the most promising methodologies, due to their more accurate estimations and better perceptual quality. This work tackles this flow sensing problem in the vicinity of the wall, addressing for the first time the reconstruction of the entire three-dimensional (3-D) field with a single network, i.e. a 3-D GAN. With this methodology, a single training and prediction process overcomes the limitation presented by the former approaches based on the independent estimation of wall-parallel planes. The network is capable of estimating the 3-D flow field with a level of error at each wall-normal distance comparable to that reported from wall-parallel plane estimations and at a lower training cost in terms of computational resources. The direct full 3-D reconstruction also unveils a direct interpretation in terms of coherent structures. It is shown that the accuracy of the network depends directly on the wall footprint of each individual turbulent structure. It is observed that wall-attached structures are predicted more accurately than wall-detached ones, especially at larger distances from the wall. Among wall-attached structures, smaller sweeps are reconstructed better than small ejections, while large ejections are reconstructed better than large sweeps as a consequence of their more intense footprint.Keywords
All Related Versions
- Version 1, 2024-09-10, ArXiv
- Published version: Journal of Fluid Mechanics, 991, A1.
This publication has 49 references indexed in Scilit:
- Pressure from data-driven estimation of velocity fields using snapshot PIV and fast probesExperimental Thermal and Fluid Science, 2022
- Characterization of very-large-scale motions in high-Re pipe flowsExperimental Thermal and Fluid Science, 2019
- Estimation of time-resolved turbulent fields through correlation of non-time-resolved field measurements and time-resolved point measurementsExperimental Thermal and Fluid Science, 2018
- Estimation of turbulent channel flow at based on the wall measurement using a simple sequential approachJournal of Fluid Mechanics, 2017
- Modal energy flow analysis of a highly modulated wake behind a wall-mounted pyramidJournal of Fluid Mechanics, 2016
- Generalized phase average with applications to sensor-based flow estimation of the wall-mounted square cylinder wakeJournal of Fluid Mechanics, 2013
- The three-dimensional structure of momentum transfer in turbulent channelsJournal of Fluid Mechanics, 2012
- Extended proper orthogonal decomposition: a tool to analyse correlated events in turbulent flowsExperiments in Fluids, 2003
- Neural Network Modeling for Near Wall Turbulent FlowJournal of Computational Physics, 2002
- Compact finite difference schemes with spectral-like resolutionJournal of Computational Physics, 1992