Physics-informed deep-learning applications to experimental fluid mechanics

TL;DR

This paper demonstrates the use of physics-informed neural networks (PINNs) to enhance flow-field data resolution from limited noisy measurements, ensuring physical consistency without high-resolution training data, across several fluid dynamics cases.

Contribution

The study introduces a PINNs-based framework for super-resolution of flow data that does not require high-resolution references and maintains physical laws, applicable to experimental fluid mechanics.

Findings

PINNs successfully reconstruct flow fields in canonical cases.

The method effectively reduces noise and improves resolution in experimental data.

PINNs provide physically consistent predictions without high-resolution training data.

Abstract

High-resolution reconstruction of flow-field data from low-resolution and noisy measurements is of interest due to the prevalence of such problems in experimental fluid mechanics, where the measurement data are in general sparse, incomplete and noisy. Deep-learning approaches have been shown suitable for such super-resolution tasks. However, a high number of high-resolution examples is needed, which may not be available for many cases. Moreover, the obtained predictions may lack in complying with the physical principles, e.g. mass and momentum conservation. Physics-informed deep learning provides frameworks for integrating data and physical laws for learning. In this study, we apply physics-informed neural networks (PINNs) for super-resolution of flow-field data both in time and space from a limited set of noisy measurements without having any high-resolution reference data. Our objective is to obtain a continuous solution of the problem, providing a physically-consistent prediction at any point in the solution domain. We demonstrate the applicability of PINNs for the super-resolution of flow-field data in time and space through three canonical cases: Burgers' equation, two-dimensional vortex shedding behind a circular cylinder and the minimal turbulent channel flow. The robustness of the models is also investigated by adding synthetic Gaussian noise. Furthermore, we show the capabilities of PINNs to improve the resolution and reduce the noise in a real experimental dataset consisting of hot-wire-anemometry measurements. Our results show the adequate capabilities of PINNs in the context of data augmentation for experiments in fluid mechanics.