Nozzle Shape Optimization based on Machine Learning using Higher Order Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F22%3A00362738" target="_blank" >RIV/68407700:21220/22:00362738 - isvavai.cz</a>

Výsledek na webu

<a href="https://efm.kez.tul.cz/" target="_blank" >https://efm.kez.tul.cz/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Nozzle Shape Optimization based on Machine Learning using Higher Order Neural Networks

Popis výsledku v původním jazyce

In this contribution, a methodology of plane nozzle shape optimization based on machine learning is introduced. In contrast to standard deep neural network, the proposed neural network is built using higher order neural units. Polynomial structures together with various activation functions are employed as approximators of strongly nonlinear Navier-Stokes equations which govern the flow. Shape of well-known NASA nozzle is chosen as initial geometry which is approximated with 5-th order Bezier curve. Different geometrical shapes, derived from the initial geometry, are employed in order to obtain training data set. Thus, the task consists of multi-variable optimization with defined cost function as a targets which are calculated by means of computational fluid dynamics (CFD) performed on fully structured meshes. The goal of this optimization is obtain geometry which meets desired conditions at the outlet of the nozzle e.g., flow field uniformity, specified flow regime etc. Finally, performance of different approximators is compared and best candidates of optimization are validated through CFD calculation.

Název v anglickém jazyce

Nozzle Shape Optimization based on Machine Learning using Higher Order Neural Networks

Popis výsledku anglicky

In this contribution, a methodology of plane nozzle shape optimization based on machine learning is introduced. In contrast to standard deep neural network, the proposed neural network is built using higher order neural units. Polynomial structures together with various activation functions are employed as approximators of strongly nonlinear Navier-Stokes equations which govern the flow. Shape of well-known NASA nozzle is chosen as initial geometry which is approximated with 5-th order Bezier curve. Different geometrical shapes, derived from the initial geometry, are employed in order to obtain training data set. Thus, the task consists of multi-variable optimization with defined cost function as a targets which are calculated by means of computational fluid dynamics (CFD) performed on fully structured meshes. The goal of this optimization is obtain geometry which meets desired conditions at the outlet of the nozzle e.g., flow field uniformity, specified flow regime etc. Finally, performance of different approximators is compared and best candidates of optimization are validated through CFD calculation.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20301 - Mechanical engineering

Projekt

<a href="/cs/project/EF16_019%2F0000826" target="_blank" >EF16_019/0000826: Centrum pokročilých leteckých technologií</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the International Conference Experimental Fluid Mechanics 2022

ISBN

—

ISSN

2100-014X

e-ISSN

2100-014X

Počet stran výsledku

8

Strana od-do

138-145

Název nakladatele

EPJ Web of Conferences

Místo vydání

Les Ulis Cedex A

Místo konání akce

Dvůr Kralové

Datum konání akce

29. 11. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—