Surrogate approaches for aerodynamic section performance modelling
Surrogate approaches for aerodynamic section performance modelling
The use of surrogate models (response surface models, curve fits) of various types (radial basis functions, Gaussian process models, neural networks, support vector machines, etc.) is now an accepted way for speeding up design search and optimization in many fields of engineering that require the use of expensive computer simulations, including problems with multiple goals and multiple domains. Surrogates are also widely used in dealing with uncertainty quantification of expensive black-box codes where there are strict limits on the number of function evaluations that can be afforded in estimating the statistical properties of derived performance quantities. This paper compares and contrasts a wide range of surrogate types on an aerodynamic section data set that allows for design variation, manufacturing uncertainty, and damage in service, all solved with a high-quality industrial-strength Reynolds-averaged Navier–Stokes solver. This paper examines speed of training and model quality for different sizes of problem up to one where there are 26 input variables and nearly half a million CFD results in the available data set.
16-24
Keane, Andrew
26d7fa33-5415-4910-89d8-fb3620413def
Voutchkov, Ivan
16640210-6d07-49cc-aebd-28bf89c7ac27
January 2020
Keane, Andrew
26d7fa33-5415-4910-89d8-fb3620413def
Voutchkov, Ivan
16640210-6d07-49cc-aebd-28bf89c7ac27
Keane, Andrew and Voutchkov, Ivan
(2020)
Surrogate approaches for aerodynamic section performance modelling.
AIAA Journal, 58 (1), .
(doi:10.2514/1.J058687).
Abstract
The use of surrogate models (response surface models, curve fits) of various types (radial basis functions, Gaussian process models, neural networks, support vector machines, etc.) is now an accepted way for speeding up design search and optimization in many fields of engineering that require the use of expensive computer simulations, including problems with multiple goals and multiple domains. Surrogates are also widely used in dealing with uncertainty quantification of expensive black-box codes where there are strict limits on the number of function evaluations that can be afforded in estimating the statistical properties of derived performance quantities. This paper compares and contrasts a wide range of surrogate types on an aerodynamic section data set that allows for design variation, manufacturing uncertainty, and damage in service, all solved with a high-quality industrial-strength Reynolds-averaged Navier–Stokes solver. This paper examines speed of training and model quality for different sizes of problem up to one where there are 26 input variables and nearly half a million CFD results in the available data set.
Text
Surrogate Models for Aero Sections AIAA accepted
- Accepted Manuscript
More information
Accepted/In Press date: 4 August 2019
e-pub ahead of print date: 29 August 2019
Published date: January 2020
Identifiers
Local EPrints ID: 433443
URI: http://eprints.soton.ac.uk/id/eprint/433443
ISSN: 0001-1452
PURE UUID: 099bfd35-6204-420a-bee3-4282c9fb316e
Catalogue record
Date deposited: 22 Aug 2019 16:30
Last modified: 17 Mar 2024 02:43
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
