GANs-based PIV resolution enhancement without the need of high-resolution input

Abstract

A data-driven approach to reconstruct high-resolution flow fields is presented. The method is based on exploiting the recent advances of SRGANs (Super-Resolution Generative Adversarial Networks) to enhance the resolution of Particle Image Velocimetry (PIV). The proposed approach exploits the availability of incomplete projections on high-resolution fields using the same set of images processed by standard PIV. Such incomplete projection is made available by sparse particle-based measurements such as super-resolution particle tracking velocimetry. Consequently, in contrast to other works, the method does not need a dual set of low/high-resolution images, and can be applied directly on a single set of raw images for training and estimation. This data-enhanced particle approach is assessed employing two datasets generated from direct numerical simulations: a fluidic pinball and a turbulent channel flow. The results prove that this data-driven method is able to enhance the resolution of PIV measurements even in complex flows without the need of a separate high-resolution experiment for training.

Dense velocity, pressure and Eulerian acceleration fields from single-instant scattered velocities through Navier–Stokes-based data assimilation

“…In the present study, we are interested in obtaining a dense and full description of the instantaneous flow observed here with 3D PTV, namely accurate but sparse velocity measurements. While this aim may be achieved through many approaches, including the use of advanced interpolation schemes or that of model-reduction techniques [5,6], or even recent machine learning methodologies [7,8], we here investigate the use of physical constraints/conservation laws to perform the reconstruction of the full flow. Such an approach may thus be referred to as data assimilation [9].…”