Flow over an espresso cup: inferring 3-D velocity and pressure fields from tomographic background oriented Schlieren via physics-informed neural networks
TLDR
In this article, the authors proposed a new method based on physics-informed neural networks (PINNs) to infer the full continuous three-dimensional (3D) velocity and pressure fields from snapshots of 3-D temperature fields obtained by Tomo-BOS imaging.Abstract:
Tomographic background oriented Schlieren (Tomo-BOS) imaging measures density or temperature fields in three dimensions using multiple camera BOS projections, and is particularly useful for instantaneous flow visualizations of complex fluid dynamics problems. We propose a new method based on physics-informed neural networks (PINNs) to infer the full continuous three-dimensional (3-D) velocity and pressure fields from snapshots of 3-D temperature fields obtained by Tomo-BOS imaging. The PINNs seamlessly integrate the underlying physics of the observed fluid flow and the visualization data, hence enabling the inference of latent quantities using limited experimental data. In this hidden fluid mechanics paradigm, we train the neural network by minimizing a loss function composed of a data mismatch term and residual terms associated with the coupled Navier–Stokes and heat transfer equations. We first quantify the accuracy of the proposed method based on a two-dimensional synthetic data set for buoyancy-driven flow, and subsequently apply it to the Tomo-BOS data set, where we are able to infer the instantaneous velocity and pressure fields of the flow over an espresso cup based only on the temperature field provided by the Tomo-BOS imaging. Moreover, we conduct an independent PIV experiment to validate the PINN inference for the unsteady velocity field at a centre plane. To explain the observed flow physics, we also perform systematic PINN simulations at different Reynolds and Richardson numbers and quantify the variations in velocity and pressure fields. The results in this paper indicate that the proposed deep learning technique can become a promising direction in experimental fluid mechanics.read more
Citations
More filters
Journal ArticleDOI
Physics-informed machine learning
TL;DR: Some of the prevailing trends in embedding physics into machine learning are reviewed, some of the current capabilities and limitations are presented and diverse applications of physics-informed learning both for forward and inverse problems, including discovering hidden physics and tackling high-dimensional problems are discussed.
Journal ArticleDOI
Physics-Informed Neural Networks for Heat Transfer Problems
TL;DR: In this paper, physics-informed neural networks (PINNs) have been applied to various prototype heat transfer problems, targeting in particular realistic conditions not readily tackled with traditional computational methods.
Journal ArticleDOI
Parallel physics-informed neural networks via domain decomposition
TL;DR: In this article, a distributed framework for physics-informed neural networks (PINNs) based on two recent extensions, namely conservative PINNs and extended PINNs (XPINNs), which employ domain decomposition in space and in time-space, respectively, is developed.
Journal ArticleDOI
Meshless physics-informed deep learning method for three-dimensional solid mechanics
TL;DR: It is shown that the DCM can capture the response qualitatively and quantitatively, without the need for any data generation using other numerical methods such as the FEM.
Journal ArticleDOI
Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions
TL;DR: In this paper, the authors proposed a new type of neural networks, Kronecker neural networks (KNNs), which form a general framework for neural networks with adaptive activation functions.
References
More filters
Journal ArticleDOI
Dot tracking methodology for background-oriented schlieren (BOS)
TL;DR: This work proposes a dot-tracking methodology that utilizes the prior information about the dot pattern such as the location, size and number of dots to provide near 100% yield even for high dot densities and is robust to image noise.
Journal ArticleDOI
Density tagging velocimetry
TL;DR: Density tagging velocimetry, a novel optical technique for point-wise measurement of flow velocity is proposed in this paper, which is based on the detection and subsequent tracking of a local density variation deliberately inserted in the flow.
Laser speckle based background oriented schlieren measurements in a fire backlayering front
P. Bühlmann,M. Ehrensperger +1 more
TL;DR: In this article, the backlayering zone of a simulated tunnel fire is investigated in a custom designed hot air tunnel, where a buoyant plume rises and spreads from the location of the fire towards the ceiling.