Acoustic transmission modelling in locally periodic structures employing machine learning

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00376593" target="_blank" >RIV/68407700:21230/24:00376593 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Acoustic transmission modelling in locally periodic structures employing machine learning
Original language description
We are dealing with an acoustic analogy of electronic band structure, and we aim to locate the band gaps using the acoustic transmission model. The acoustic transmission model for locally periodic structures with smooth non-trivial geometries has been done mainly numerically. With the approach of data-driven physics, it is possible to obtain an analytical equation relating axis-symmetric geometry with dispersion relation. A dataset of Bloch phases for a given frequency band and structure geometry parameters was designed for this task. By applying Principal Component Analysis (PCA), we transform the Bloch phases from the dataset into a new coordinate system in a lower dimensional space (while keeping as much variance as possible), where the problem is solved with robust regression analysis. This paper provides an insight into the underlying physics and improves the readability of the system features. The results can be used, e.g., to optimize a design for a desired band gap width
Czech name
—
Czech description
—

Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the International Student Scientific Conference Poster – 28/2024
ISBN
978-80-01-07299-8
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
—
Publisher name
Fakulta elektrotechnická
Place of publication
Praha
Event location
Prague
Event date
May 23, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)