Artificial Neural Networks for Surrogate-based Optimization in Preliminary Aerodynamic Design

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F15%3APU115715" target="_blank" >RIV/00216305:26210/15:PU115715 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Artificial Neural Networks for Surrogate-based Optimization in Preliminary Aerodynamic Design

Popis výsledku v původním jazyce

A preliminary aerodynamic design often imposes requirements on global optimum search within a large, highly multimodal design space. Tools typically deployed to evaluate individual design candidates are very computationally expensive, being part of the finite volume computational fluid dynamics class. This virtually prevents deployment of traditional stochastic global optimization approaches, such as evolutionary algorithms. Hence, there has been a growing interest in metamodelling techniques, providing a reliable surrogate of the simulator response to an optimization algorithm. Efficient deployment of such techniques within preliminary aerodynamic design is of interest to Garteur Action Group 52 members. The present paper describes the involvement of Brno University of Technology, Institute of Aerospace Engineering in the AG52. The considered test case is based on the RAE2822 aerofoil constrained multipoint optimization problem. The overall problem setup is given along with selected surrogate modelling and optimization techniques. The presented approach featuring artificial neural networks is able to produce highly reliable metamodels with cutting-edge performance as documented by the AG52 performance metrics comparison.

Název v anglickém jazyce

Artificial Neural Networks for Surrogate-based Optimization in Preliminary Aerodynamic Design

Popis výsledku anglicky

A preliminary aerodynamic design often imposes requirements on global optimum search within a large, highly multimodal design space. Tools typically deployed to evaluate individual design candidates are very computationally expensive, being part of the finite volume computational fluid dynamics class. This virtually prevents deployment of traditional stochastic global optimization approaches, such as evolutionary algorithms. Hence, there has been a growing interest in metamodelling techniques, providing a reliable surrogate of the simulator response to an optimization algorithm. Efficient deployment of such techniques within preliminary aerodynamic design is of interest to Garteur Action Group 52 members. The present paper describes the involvement of Brno University of Technology, Institute of Aerospace Engineering in the AG52. The considered test case is based on the RAE2822 aerofoil constrained multipoint optimization problem. The overall problem setup is given along with selected surrogate modelling and optimization techniques. The presented approach featuring artificial neural networks is able to produce highly reliable metamodels with cutting-edge performance as documented by the AG52 performance metrics comparison.

Druh

D - Stať ve sborníku

CEP obor

JU - Aeronautika, aerodynamika, letadla

OECD FORD obor

—

Projekt

<a href="/cs/project/LO1202" target="_blank" >LO1202: NETME CENTRE PLUS</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Eurogen 2015 Extended Abstracts Book

ISBN

9788890632310

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

28-34

Název nakladatele

University of Strathclyde

Místo vydání

Glasgow, UK

Místo konání akce

Glasgow, UK

Datum konání akce

14. 9. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—