Physics-Informed Deep Learning for Computational Fluid Flow Analysis

Coupling of physics-informed neural networks and autoencoders for aerodynamic flow predictions on variable geometries

Master thesis (2022)

Authors

S. Kakkar Mechanical Engineering

Contributors

Rene Pecnik Energy Technology - Mechanical, Maritime and Materials Engineering (supervisor 1)
M. Möller Numerical Analysis - EEMCS (supervisor 1)
William Jennings (supervisor 1)
Faculty
Mechanical Engineering
Copyright: © 2022 Samarth Kakkar
Poisson equation Fluid dynamics Physics Informed Neural Networks Airfoils Scientific Machine Learning Operator Learning
More Info
expand_more

Published Date

24-08-2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical Engineering

Abstract

The main objective of this thesis was to explore the capabilities of neural networks in terms of representing governing differential equations, primarily in the purview of fluid/aero dynamic flows. The governing differential equations were accommodated within the loss functions for training the neural networks, thereby making them 'physics-informed'. Subsequently, this idea of physics-informed neural networks (PINNs) was extended to parameterized geometries generated with the help of commercial auto-encoders developed by the UK based company Monolith AI pvt. ltd. because neural networks have the capability to learn the desired PDEs over variable/parameterized geometries without the need to recompute the solution for every minor change in the input geometry, which proves out to be a huge advantage over classical numerical techniques. The advantages, limitations and scope for further research in the field of physics-informed deep learning have been discussed in the contents of the underlying thesis report.