CaltechAUTHORS
  A Caltech Library Service

Self-critical machine-learning wall-modeled LES for external aerodynamics

Lozano-Durán, A. and Bae, H. J. (2020) Self-critical machine-learning wall-modeled LES for external aerodynamics. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20210315-144531131

[img] PDF - Submitted Version
Creative Commons Attribution.

6Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210315-144531131

Abstract

The prediction of aircraft aerodynamic quantities of interest remains among the most pressing challenges for computational fluid dynamics. The aircraft aerodynamics are inherently turbulent with mean-flow three-dimensionality, often accompanied by laminar-to-turbulent transition, flow separation, secondary flow motions at corners, and shock wave formation, to name a few. However, the most widespread wall models are built upon the assumption of statistically-in-equilibrium wall-bounded turbulence and do not faithfully account for the wide variety of flow conditions described above. This raises the question of how to devise models capable of accounting for such a vast and rich collection of flow physics in a feasible manner. In this work, we propose tackling the wall-modeling challenge by devising the flow as a collection of building blocks, whose information enables the prediction of the stress as the wall. The model relies on the assumption that simple canonical flows contain the essential flow physics to devise accurate models. Three types of building block units were used to train the model: turbulent channel flows, turbulent ducts and turbulent boundary layers with separation. This limited training set will be extended in future versions of the model. The approach is implemented using two interconnected artificial neural networks: a classifier, which identifies the contribution of each building block in the flow; and a predictor, which estimates the wall stress via non-linear combinations of building-block units. The output of the model is accompanied by the confidence in the prediction. The latter value aids the detection of areas where the model underperforms, such as flow regions that are not representative of the building blocks used to train the model. The model is validated in a unseen case representative of external aerodynamic applications: the NASA Juncture Flow Experiment.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2012.10005arXivDiscussion Paper
ORCID:
AuthorORCID
Lozano-Durán, A.0000-0001-9306-0261
Bae, H. J.0000-0001-6789-6209
Additional Information:Attribution 4.0 International (CC BY 4.0). A.L.-D. acknowledges the support of NASA under grant No. NNX15AU93A.
Group:GALCIT
Funders:
Funding AgencyGrant Number
NASANNX15AU93A
Record Number:CaltechAUTHORS:20210315-144531131
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210315-144531131
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108438
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:19 Mar 2021 21:10
Last Modified:19 Mar 2021 21:10

Repository Staff Only: item control page