Physics-Informed Neural Networks for Heat Transfer Problems
Физически информированные нейронные сети для задач теплопереноса
2021-03-17
SCID: 54.1/k8knsnmx
Discuss with AI
Stefan problemautomatic differentiationheat transfermixed convectionphysics-informed neural networks
Figures from the paper
Abstract (AI)
Abstract Physics-informed neural networks (PINNs) have gained popularity across different engineering fields due to their effectiveness in solving realistic problems with noisy data and often partially missing physics. In PINNs, automatic differentiation is leveraged to evaluate differential operators without discretization errors, and a multitask learning problem is defined in order to simultaneously fit observed data while respecting the underlying governing laws of physics. Here, we present applications of PINNs to various prototype heat transfer problems, targeting in particular realistic conditions not readily tackled with traditional computational methods. To this end, we first consider forced and mixed convection with unknown thermal boundary conditions on the heated surfaces and aim to obtain the temperature and velocity fields everywhere in the domain, including the boundaries, given some sparse temperature measurements. We also consider the prototype Stefan problem for two-phase flow, aiming to infer the moving interface, the velocity and temperature fields everywhere as well as the different conductivities of a solid and a liquid phase, given a few temperature measurements inside the domain. Finally, we present some realistic industrial applications related to power electronics to highlight the practicality of PINNs as well as the effective use of neural networks in solving general heat transfer problems of industrial complexity. Taken together, the results presented herein demonstrate that PINNs not only can solve ill-posed problems, which are beyond the reach of traditional computational methods, but they can also bridge the gap between computational and experimental heat transfer.
Key Findings
1
For forced and mixed convection, PINNs infer unknown thermal boundary conditions and reconstruct temperature and velocity fields throughout the domain from sparse temperature measurements.
2
For the two-phase Stefan problem, PINNs infer the moving interface, velocity and temperature fields, and solid and liquid thermal conductivities from limited internal temperature data.
3
Industrial power-electronics applications demonstrate that PINNs can address heat-transfer problems of realistic industrial complexity.
4
PINNs use automatic differentiation and multitask learning to enforce heat-transfer governing equations while fitting observed data without discretization errors.
5
The results indicate that PINNs can solve ill-posed heat-transfer problems beyond traditional computational methods and connect computational modeling with experimental data.
Research Object
prototype and industrial heat transfer systems, including forced and mixed convection, two-phase Stefan flow, and power-electronics applications
Research Subject
inference of temperature and velocity fields, moving interfaces, thermal boundary conditions, and phase conductivities from sparse temperature measurements under realistic heat-transfer conditions
Publication Details
Publication Date
2021-03-17
Journal
Publisher
ISSN
Cited by
1735
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai2
Cited by6
Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next2022
A-PINN: Auxiliary physics informed neural networks for forward and inverse problems of nonlinear integro-differential equations2022
Physics‐Informed Neural Networks of the Saint‐Venant Equations for Downscaling a Large‐Scale River Model2023
Physics-informed machine learning in geotechnical engineering: a direction paper2025
Physics informed neural networks for surrogate modeling of accidental scenarios in nuclear power plants2023
Physics-Informed Neural Networks for Modeling Water Flows in a River Channel2022