Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Open-Source High-Speed Flight Surrogate Modeling Framework

Tyler E. Korenyi-Both, Nathan J. Falkiewicz, Matthew C. Jones

TL;DR

The primary conclusion is that the framework is effective and has been delivered to the Air Force for integration into real-world projects, and the author recommends further testing and refining modeling methods that explicitly incorporate physical laws and are robust enough to handle simulation and test data from varying resolutions and sources.

Abstract

High-speed flight vehicles, which travel much faster than the speed of sound, are crucial for national defense and space exploration. However, accurately predicting their behavior under numerous, varied flight conditions is a challenge and often prohibitively expensive. The proposed approach involves creating smarter, more efficient machine learning models (also known as surrogate models or meta models) that can fuse data generated from a variety of fidelity levels -- to include engineering methods, simulation, wind tunnel, and flight test data -- to make more accurate predictions. These models are able to move the bulk of the computation from high performance computing (HPC) to single user machines (laptop, desktop, etc.). The project builds upon previous work but introduces code improvements and an informed perspective on the direction of the field. The new surrogate modeling framework is now modular and, by design, broadly applicable to many modeling problems. The new framework also has a more robust automatic hyperparameter tuning capability and abstracts away most of the pre- and post-processing tasks. The Gaussian process regression and deep neural network-based models included in the presented framework were able to model two datasets with high accuracy (R^2>0.99). The primary conclusion is that the framework is effective and has been delivered to the Air Force for integration into real-world projects. For future work, significant and immediate investment in continued research is crucial. The author recommends further testing and refining modeling methods that explicitly incorporate physical laws and are robust enough to handle simulation and test data from varying resolutions and sources, including coarse meshes, fine meshes, unstructured meshes, and limited experimental test points.

Open-Source High-Speed Flight Surrogate Modeling Framework

TL;DR

The primary conclusion is that the framework is effective and has been delivered to the Air Force for integration into real-world projects, and the author recommends further testing and refining modeling methods that explicitly incorporate physical laws and are robust enough to handle simulation and test data from varying resolutions and sources.

Abstract

High-speed flight vehicles, which travel much faster than the speed of sound, are crucial for national defense and space exploration. However, accurately predicting their behavior under numerous, varied flight conditions is a challenge and often prohibitively expensive. The proposed approach involves creating smarter, more efficient machine learning models (also known as surrogate models or meta models) that can fuse data generated from a variety of fidelity levels -- to include engineering methods, simulation, wind tunnel, and flight test data -- to make more accurate predictions. These models are able to move the bulk of the computation from high performance computing (HPC) to single user machines (laptop, desktop, etc.). The project builds upon previous work but introduces code improvements and an informed perspective on the direction of the field. The new surrogate modeling framework is now modular and, by design, broadly applicable to many modeling problems. The new framework also has a more robust automatic hyperparameter tuning capability and abstracts away most of the pre- and post-processing tasks. The Gaussian process regression and deep neural network-based models included in the presented framework were able to model two datasets with high accuracy (R^2>0.99). The primary conclusion is that the framework is effective and has been delivered to the Air Force for integration into real-world projects. For future work, significant and immediate investment in continued research is crucial. The author recommends further testing and refining modeling methods that explicitly incorporate physical laws and are robust enough to handle simulation and test data from varying resolutions and sources, including coarse meshes, fine meshes, unstructured meshes, and limited experimental test points.

Paper Structure

This paper contains 23 sections, 3 equations, 17 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Methodology
  3. Data
  4. Dataset 1
  5. Dataset 2
  6. Model Implementation
  7. Results
  8. Future Work
  9. Conclusion
  10. Modeling Techniques
  11. Gaussian Process Regression
  12. Deep Neural Networks
  13. Surrogate Modeling
  14. N-Step Multi-fidelity Modeling
  15. Surrogate Modeling Pipeline Instructions
  16. ...and 8 more sections

Figures (17)

  • Figure 1: 3D tensor visualization, shape (n,m,l).
  • Figure 2: Data standard at import. 3D tensor, shape $(n,m,l)$. Prior to modeling pipeline ingestion, data should be in form (samples,scalar_values,coordinates) or $(n,m,l)$. $\eta$ is a notional coordinate, often ($\eta_1,\eta_2,\eta_3$) is ($x,y,z$). $\phi$ here represents a scalar value at each coordinate, either an input parameter or a quantity of interest (QoI). A "sample" is a single instance of the measured experiment (for CFD, this would be one CFD snapshot).
  • Figure 3: Output data example. Shape: (400, 7, 1828)
  • Figure 4: Input space pairplot for CBAERO dataset. Pairplots show pairwise relationships between parameters, in this case showing the input parameter space coverage.
  • Figure 5: Vehicle geometry
  • ...and 12 more figures