Modelling band structure properties using physics-informed machine learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00384829" target="_blank" >RIV/68407700:21230/25:00384829 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.71568/dasdaga2025.605" target="_blank" >http://dx.doi.org/10.71568/dasdaga2025.605</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.71568/dasdaga2025.605" target="_blank" >10.71568/dasdaga2025.605</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Modelling band structure properties using physics-informed machine learning

Popis výsledku v původním jazyce

Although the variety of analytical approaches and numerical methods to solve sonic crystal problems is wide, the known analytical expressions used to model the band structure properties are limited to a few special cases. However, having access to a numerical model is a good starting point for data-driven discovery. Our approach employed the Webster equation for unit cell and Floquet-Bloch theory for periodic structures with waveguide parametrized by cubic splines. Analytical formulae relating the waveguide geometry to the corresponding dispersion relation were extracted using methods of physics-informed machine learning, such as coordinate transformation and symbolical regression. These results provide a deeper understanding of the underlying principles and offer an efficient alternative to computationally demanding numerical optimization. Moving towards a Schrödinger-like equation and parametrization by Gaussian curvature allows for a more multiphysical approach but also faces some challenges in terms of geometry feasibility limits.

Název v anglickém jazyce

Modelling band structure properties using physics-informed machine learning

Popis výsledku anglicky

Although the variety of analytical approaches and numerical methods to solve sonic crystal problems is wide, the known analytical expressions used to model the band structure properties are limited to a few special cases. However, having access to a numerical model is a good starting point for data-driven discovery. Our approach employed the Webster equation for unit cell and Floquet-Bloch theory for periodic structures with waveguide parametrized by cubic splines. Analytical formulae relating the waveguide geometry to the corresponding dispersion relation were extracted using methods of physics-informed machine learning, such as coordinate transformation and symbolical regression. These results provide a deeper understanding of the underlying principles and offer an efficient alternative to computationally demanding numerical optimization. Moving towards a Schrödinger-like equation and parametrization by Gaussian curvature allows for a more multiphysical approach but also faces some challenges in terms of geometry feasibility limits.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10307 - Acoustics

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of DAS|DAGA 2025

ISBN

978-3-939296-23-2

ISSN

—

e-ISSN

—

Počet stran výsledku

3

Strana od-do

998-1000

Název nakladatele

Deutsche Gesellschaft für Akustik

Místo vydání

Dresden

Místo konání akce

Copenhagen

Datum konání akce

17. 3. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—