Extrapolative, progressive machine learning for turbulence modeling

Abstract

The design of revolutionary aero vehicle concepts requires computational tools with reasonable cost. Since resolving all turbulent scales in a simulation at high Reynolds numbers is not practical, turbulence modeling is a necessity. The research will make use of modern machine learning tools and high-fidelity numerical simulation data for turbulence modeling. The proposal differs from the current research in that it emphasizes extrapolation, which is achieved through progressive machine learning.

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 29, 2024
Source ID
FA95502310272

Entities

People

  • Xiang I. A. Yang

Organizations

  • Air Force Office of Scientific Research
  • Pennsylvania State University
  • United States Air Force

Tags

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Fluid Dynamics.
  • Military Training and Readiness Simulation

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks