Deep Neural Network Based Convergence Classification for Computational Fluid Dynamics
Publication Date
1-1-2024
Document Type
Conference Proceeding
Publication Title
AIAA SciTech Forum and Exposition, 2024
DOI
10.2514/6.2024-2515
Abstract
A supervised deep learning approach is coupled with heuristic convergence criteria to constructa classification model for detecting the completion (convergence) of computational fluid dynamics(CFD) simulations. Heuristic convergence criteria alone are not always sufficient and more complex decisions are often left to a human analyst. The proposed approach leverages heuristic convergence criteria as well as two deep neural network (DNN) models, one binary and one multi-class, to improve the efficiency and consistency of convergence classification across a wide range of flight regimes. The DNN models presented are each trained on a subset of ascent aerodynamic CFD simulations for NASA’s Space Launch System and were produced using NASA’s unstructured Navier-Stokes solverFUN3D. Individual solutions are analyzed intermittently and are classified as sufficiently converged, further iterations required, or switch from steady Reynolds Averaged Navier-Stokes (RANS) to unsteady RANS CFD based on the iterative histories of four aerodynamic coefficients. The implemented classification model is shown to produce solutions that closely correlate to solutions produced by a human analyst. This work lays groundwork for expanding the capabilities of DNNs for automating and improving more of the CFD process.
Department
Aerospace Engineering
Recommended Citation
Joshua F. Diaz, Derek J. Dalle, and Papadopoulos E. Periklis. "Deep Neural Network Based Convergence Classification for Computational Fluid Dynamics" AIAA SciTech Forum and Exposition, 2024 (2024). https://doi.org/10.2514/6.2024-2515
