Date of Award

Fall 2023

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Mechanical & Aerospace Engineering

Program/Concentration

Aerospace Engineering

Committee Director

Oktay Baysal

Committee Director

Christopher L. Rumsey

Committee Member

Jiang Li

Committee Member

Masha Sosonkina

Committee Member

Miltos Kotinis

Abstract

In recent years, the field of machine learning (ML) has made significant advances, particularly through applying deep learning (DL) algorithms and artificial intelligence (AI). The literature shows several ways that ML may enhance the power of computational fluid dynamics (CFD) to improve its solution accuracy, reduce the needed computational resources and reduce overall simulation cost. ML techniques have also expanded the understanding of underlying flow physics and improved data capture from experimental fluid dynamics.

This dissertation presents an in-depth literature review and discusses ways the field of fluid dynamics has leveraged ML modeling to date. The author selects and describes several studies that build upon the existing literature, then applies the selected ML techniques to construct models that produce higher-resolution aerodynamic predictions by utilizing significantly less computational resources and producing predictions at much lower costs.

These concepts are demonstrated via simple cases involving two-dimensional flow fields around several four-digit National Advisory Committee for Aeronautics (NACA) airfoil profiles at subsonic and transonic Mach numbers and pitched at very high angles of attack ranging from - 30-deg. to +30-deg. Presented here are several convolutional neural network (CNN) models trained to emulate detached eddy simulation (DES)-quality results from inputted unsteady Reynolds-averaged Navier-Stokes (URANS) input data, while progressively producing flow-field predictions with much higher accuracy.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/hk41-wn71

ISBN

9798381448375

ORCID

0009-0009-5004-8911

Download

Share

COinS