Purdue University Graduate School
Browse
Sukirt_Thesis.pdf (10.09 MB)

Physics Informed Neural Networks for Engineering Systems

Download (10.09 MB)
thesis
posted on 2020-05-13, 00:59 authored by SukirtSukirt
This thesis explores the application of deep learning techniques to problems in fluid mechanics, with particular focus on physics informed neural networks. Physics
informed neural networks leverage the information gathered over centuries in the
form of physical laws mathematically represented in the form of partial differential
equations to make up for the dearth of data associated with engineering and physi-
cal systems. To demonstrate the capability of physics informed neural networks, an
inverse and a forward problem are considered. The inverse problem involves discov-
ering a spatially varying concentration ?field from the observations of concentration
of a passive scalar. A forward problem involving conjugate heat transfer is solved as
well, where the boundary conditions on velocity and temperature are used to discover
the velocity, pressure and temperature ?fields in the entire domain. The predictions of
the physics informed neural networks are compared against simulated data generated
using OpenFOAM.

History

Degree Type

  • Master of Science

Department

  • Mechanical Engineering

Campus location

  • West Lafayette

Advisor/Supervisor/Committee Chair

Arezoo Ardekani

Additional Committee Member 2

Luciano Castillo

Additional Committee Member 3

Marisol Koslowski

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC