Advanced Neural Network Modeling of Synthetic Jet Flow Fields

Abstract

The purpose of this research was to continue development of a neural network-based, lumped deterministic source term (LDST) approximation module for modeling synthetic jets in large-scale CFD calculations. The LDST approximation technique developed by the author and his students was employed. The main exploration involved the grid sensitivity of the neural network model. A second task was originally planned on the portability of the approach to other solvers, but interesting developments on the first task prevented that study from being pursued.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2006
Accession Number
ADA473581

Entities

People

  • Paul D. Orkwis
  • Terry Daviaux

Organizations

  • University of Cincinnati

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Boundary Layer
  • Computational Fluid Dynamics
  • Computational Science
  • Computer Programs
  • Equations
  • Flow
  • Flow Fields
  • Fluid Dynamics
  • Fluid Flow
  • Geometry
  • Jet Flow
  • Mach Number
  • Neural Networks
  • Steady State
  • Training
  • Viscous Flow

Readers

  • Computational Fluid Dynamics (CFD)
  • Computer Networking

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks