Numerical Approximation in CFD Problems Using Physics Informed Machine Learning

11/01/2021
by   Siddharth Rout, et al.
43

The thesis focuses on various techniques to find an alternate approximation method that could be universally used for a wide range of CFD problems but with low computational cost and low runtime. Various techniques have been explored within the field of machine learning to gauge the utility in fulfilling the core ambition. Steady advection diffusion problem has been used as the test case to understand the level of complexity up to which a method can provide solution. Ultimately, the focus stays over physics informed machine learning techniques where solving differential equations is possible without any training with computed data. The prevalent methods by I.E. Lagaris et.al. and M. Raissi et.al are explored thoroughly. The prevalent methods cannot solve advection dominant problems. A physics informed method, called as Distributed Physics Informed Neural Network (DPINN), is proposed to solve advection dominant problems. It increases the lexibility and capability of older methods by splitting the domain and introducing other physics-based constraints as mean squared loss terms. Various experiments are done to explore the end to end possibilities with the method. Parametric study is also done to understand the behavior of the method to different tunable parameters. The method is tested over steady advection-diffusion problems and unsteady square pulse problems. Very accurate results are recorded. Extreme learning machine (ELM) is a very fast neural network algorithm at the cost of tunable parameters. The ELM based variant of the proposed model is tested over the advection-diffusion problem. ELM makes the complex optimization simpler and Since the method is non-iterative, the solution is recorded in a single shot. The ELM based variant seems to work better than the simple DPINN method. Simultaneously scope for various development in future are hinted throughout the thesis.

READ FULL TEXT

page 1

page 20

page 22

page 34

page 39

research
05/15/2020

Extreme Theory of Functional Connections: A Physics-Informed Neural Network Method for Solving Parametric Differential Equations

In this work we present a novel, accurate, and robust physics-informed m...
research
06/16/2023

Regression-based Physics Informed Neural Networks (Reg-PINNs) for Magnetopause Tracking

The ultimate goal of studying the magnetopause position is to accurately...
research
09/22/2022

Aggregation Methods for Computing Steady-States in Statistical Physics

We give a new proof of local convergence of a multigrid method called it...
research
11/09/2019

Physics-Informed Neural Networks for Power Systems

This paper introduces for the first time, to our knowledge, a framework ...
research
02/21/2023

Physics-informed Spectral Learning: the Discrete Helmholtz–Hodge Decomposition

In this work, we further develop the Physics-informed Spectral Learning ...
research
12/12/2020

Physics-Informed Machine Learning Simulator for Wildfire Propagation

The aim of this work is to evaluate the feasibility of re-implementing s...
research
10/23/2022

Less Emphasis on Difficult Layer Regions: Curriculum Learning for Singularly Perturbed Convection-Diffusion-Reaction Problems

Although Physics-Informed Neural Networks (PINNs) have been successfully...

Please sign up or login with your details

Forgot password? Click here to reset