Double Cone Flow Field Reconstruction Between Mach 4 and 12 Using Machine Learning Techniques

Abstract

Analysis of hypersonic systems poses a challenge due, in part, to the physical phenomena unique to the hypersonic flight regime. One needs to consider as many of these phenomena as possible early in vehicle design. Reduced order models can provide insight into these complex phenomena at a low cost by leveraging previous results. Toward this end, we investigate the utility of machine learning models for predicting the pressure field in hypersonic flow. For this effort, we simulate compressible flow over a parameterized double cone model at hypersonic speeds using a steady-state RANS solver, Kestrel. The computed pressure fields are used to train two neural network NN models, the U Net and the Multiscale Network, as well as two meta-models: K-Nearest Neighbors and Regression Kriging. The NN models are designed to reconstruct flow field relationships using distinct methodologies: the U-Net utilizes auto-encoding while the Multiscale Network utilizes a sequential refinement scheme. All models predict the pressure values on a uniform Cartesian grid of much smaller resolution than the unstructured mesh required for CFD simulation. The accuracy, computational complexity, and versatility of the NN are compared against the meta models. Additionally, the ability for each method to accurately predict shock interactions or impingement with downstream vehicle geometry is examined. Such closed-form machine learning ML models have advantages over conventional CFD solutions as they do not require any meshing of the computational domain and can quickly generate flow field predictions - on the order of seconds compared to hours. Our analysis shows the NN models to have robust predictive performance over the generated double cone dataset. Additionally, the NN models easily apply to arbitrary geometries that the existing geometric parameterization cannot describe.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2022
Accession Number
AD1201832

Entities

People

  • Benjamin J. Grier
  • C. C. Fischer
  • Jose A. Camberos
  • Logan P. Riley
  • Ramana V. Grandhi
  • Trevor A. Toros

Organizations

  • Air Force Institute of Technology
  • Air Force Research Laboratory
  • Ohio State University

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Energy and Power Technologies
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence Software
  • Bayesian Networks
  • Boundary Layer
  • Computational Fluid Dynamics
  • Computational Science
  • Computer Vision
  • Data Mining
  • Dimensionality Reduction
  • Fluid Dynamics
  • Fluid Flow
  • Information Science
  • Kernel Functions
  • Machine Learning
  • Neural Networks
  • Probabilistic Models
  • Supervised Machine Learning

Readers

  • Computational Fluid Dynamics (CFD)
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks
  • Hypersonics
  • Hypersonics - Hypersonic Flow