prikaz prve stranice dokumenta Homogenizacija kompozitnih materijala korištenjem dubokog učenja
No public access
undergraduate thesis
Homogenizacija kompozitnih materijala korištenjem dubokog učenja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:450288
Mucko, Luka
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Mucko, L. (2023). Homogenizacija kompozitnih materijala korištenjem dubokog učenja (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:450288

Mucko, Luka. "Homogenizacija kompozitnih materijala korištenjem dubokog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:450288

Mucko, Luka. "Homogenizacija kompozitnih materijala korištenjem dubokog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:450288

Mucko, L. (2023). 'Homogenizacija kompozitnih materijala korištenjem dubokog učenja', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 24 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:450288

Mucko L. Homogenizacija kompozitnih materijala korištenjem dubokog učenja [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 July 24] Available at: https://urn.nsk.hr/urn:nbn:hr:168:450288

L. Mucko, "Homogenizacija kompozitnih materijala korištenjem dubokog učenja", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:450288

Metadata
TitleHomogenizacija kompozitnih materijala korištenjem dubokog učenja
Title (english)Deep learning approach to homogenization of composites
AuthorLuka Mucko
MentorDario Bojanjac (mentor)
Committee memberDario Bojanjac (predsjednik povjerenstva)
Committee memberFilip Turčinović (član povjerenstva)
Committee memberDubravko Tomić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Promatranje odaziva elektromagnetskih valova na kompozitnim materijalima je numerički zahtjevan proces koji se rješava homogenizacijom materijala odnosno pronalaženjem efektivnog parametra materijala. Korištenjem dubokog učenja smo istrenirali ResNet152 i EfficientNet-b4 da predvide efektivne parametre nad geometrijama koje se sastoje od nasumično postavljenih kvadrata na 1 × 1 jediničnoj ćeliji.
Abstract (english)
The observation of the response of electromagnetic waves on composite materials is a computationally demanding process that is solved through material homogenization, i.e., finding the effective material parameter. By using deep learning, we have trained ResNet152 and EfficientNet-b4 models to predict the effective parameters for geometries composed of randomly placed squares on a 1 × 1 unit cell.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:450288
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-10-11 09:54:11