prikaz prve stranice dokumenta Structure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning
  Download
PDF 13.15 MB
doctoral thesis
Structure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning
doctoral thesis
2025. urn:nbn:hr:190:638642
Nikolić, Filip
University of Rijeka
Faculty of Engineering

Cite this document

Nikolić, F. (2025). Structure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning : doctoral thesis (Doctoral thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:638642

Nikolić, Filip. "Structure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning : doctoral thesis." Doctoral thesis, University of Rijeka, Faculty of Engineering, 2025. https://urn.nsk.hr/urn:nbn:hr:190:638642

Nikolić, Filip. "Structure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning : doctoral thesis." Doctoral thesis, University of Rijeka, Faculty of Engineering, 2025. https://urn.nsk.hr/urn:nbn:hr:190:638642

Nikolić, F. (2025). 'Structure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning : doctoral thesis', Doctoral thesis, University of Rijeka, Faculty of Engineering, accessed 17 March 2025, https://urn.nsk.hr/urn:nbn:hr:190:638642

Nikolić F. Structure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning : doctoral thesis [Doctoral thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2025 [cited 2025 March 17] Available at: https://urn.nsk.hr/urn:nbn:hr:190:638642

F. Nikolić, "Structure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning : doctoral thesis", Doctoral thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2025. Available at: https://urn.nsk.hr/urn:nbn:hr:190:638642

Please login to the repository to save this object to your list.
Metadata
TitleStructure-Mechanical Property Relationship Modelling using the Finite Element Method and Machine Learning : doctoral thesis
Title (english)Modeliranje odnosa stukture i mehaničkih značajki metodom konačnih elemenata i strojnim učenjem : doktorski rad
AuthorFilip Nikolić https://orcid.org/0000-0002-4343-5069
MentorMarko Čanađija (mentor)
MentorIvan Štajduhar (komentor)
Committee memberMarino Brčić (predsjednik povjerenstva)
Committee memberZdenko Tonković (član povjerenstva)
Committee memberGoran Mauša (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
Rijeka
Defense date and country2025, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Universal decimal classification
(UDC)		62 - Engineering. Technology in general
Abstract
In the present study, the structure-property relationships (SPR) are investigated using finite element analysis (FEA) and machine learning (ML) methods. The objective of the research was to create an ML model capable of predicting the temperature-dependent stress-strain response of two-phase composites, as well as the amount of heat generated during plastic deformation considering different Taylor-Quinney coefficients (TQCs). The ML model aims to achieve industrially acceptable prediction... More accuracy and significantly better computational efficiency compared to FEA. Microstructure generation and FEA were used to create the datasets for the ML model, and both processes were automated using the Python programming language. FEA was performed for each representative volume element (RVE) to obtain the stress-strain response as well as the temperature increase-strain curve. This means that two separate datasets and two separate ML models were created: one for the stress-strain responses and one for the temperature increasestrain responses. Both ML models were developed in the form of complex 3D-convolutional neural networks (CNNs), taking the microstructural configuration as input. Other input parameters included the TQC value and temperature for the first and second ML models, respectively. The outputs of the CNNs were the temperature increase-strain curves and the stress-strain curves at specific temperatures for the first and second model, respectively. Compared to FEA, both the model for predicting temperature-dependent stress-strain curves and the model for predicting plastic deformation-induced heat generation demonstrated very good prediction accuracy suitable for industrial applications. Additionally, both models exhibited significantly faster prediction capabilities and better computational efficiency than FEA. Less
Abstract (english)
U ovoj studiji, odnos između strukture i svojstva (SPR) istraženi su korištenjem metode konačnih elemenata (MKE) i strojnog učenja (SU). Cilj istraživanja bio je napraviti SU model koji može predvidjeti temperaturno ovisnu vezu naprezanja i deformacije dvofaznih kompozita, kao i količinu topline koja se stvara tijekom plastične deformacije uzimajući u obzir različite TaylorQuinneyjeve koeficijente (TQK). SU model bi trebao postići industrijski prihvatljivu točnost predviđanja i značajno... More bolju računsku učinkovitost u usporedbi s MKE. Generiranje mikrostrukture i MKE korišteni su za izradu skupova podataka za SU model i oboje su automatizirani pomoću programskog jezika Python. Svaki reprezentativni volumenski element (RVE) je proračunat pomoću MKE kako bi se dobila krivulja naprezanje-deformacija kao i krivulja povećanje temperature-deformacija. To znači da su stvorena dva različita skupa podataka kao i dva različita SU modela, jedan za krivulje naprezanje-deformacija i drugi za porast temperature-deformacija. Oba SU modela kreirana su u obliku složene 3D-konvolucijske neuronske mreže (KNM) i mikrostrukturna konfiguracija je ulaz oba SU modela. Ostali ulazni parametri bili su vrijednost TQK za prvi i temperatura za drugi SU model. Rezultati KNM-a bili su krivulja porast temperature-deformacija za prvi te krivulje naprezanja-deformacije na specifičnim temperaturama za drugi model. U usporedbi s MKE, i model za predviđanje temperaturno-ovisnih krivulja naprezanje-deformacija te model za predviđanje krivulja povećanja temperature-deformacija pokazali su vrlo dobru točnost predviđanja prikladnu za industrijske primjene. Osim toga, oba modela su pokazala znatno brže mogućnosti predviđanja i bolju računalnu učinkovitost u odnosu na MKE. Less
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:190:638642
Promotion2025
Study programmeTitle: Postgraduate university (doctoral) study
Study programme type: university
Study level: postgraduate
Academic / professional title: doktor/doktorica znanosti, područje tehničkih znanosti (doktor/doktorica znanosti, područje tehničkih znanosti)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2025-03-17 12:55:12
accessibility

closeAccessibilityrefresh

If you wish to permanently save changes, click on Save, if not - your settings will be reset when you restart the browser.