Digital repository of Slovenian research organisations

Show document
A+ | A- | Help | SLO | ENG

Title:Optimizing foamed glass production with machine learning
Authors:ID Hribar, Uroš, Institut "Jožef Stefan" (Author)
ID Stevanoska, Sintija, Institut "Jožef Stefan" (Author)
ID Camacho Villalón, Christian Leonardo, Institut "Jožef Stefan" (Author)
ID Spreitzer, Matjaž, Institut "Jožef Stefan" (Author)
ID Koenig, Jakob, Institut "Jožef Stefan" (Author)
ID Džeroski, Sašo, Institut "Jožef Stefan" (Author)
Files:URL URL - Source URL, visit https://www.sciencedirect.com/science/article/pii/S0264127525008792?via%3Dihub
 
.pdf PDF - Presentation file, download (1,51 MB)
MD5: 6601A430FD2C782E745268E9713F234A
Description: The dataset from this study is available at https://doi.org/10.5281/zenodo.15023205. The code implementation for Task 2 and the multiobjective optimization algorithm (IBEA) are available at https://github.com/sintija-s/foaming-glass.
 
Language:English
Typology:1.01 - Original Scientific Article
Organization:Logo IJS - Jožef Stefan Institute
Abstract:Foamed glass is a lightweight material commonly used for insulation. However, optimizing its properties remains a challenge due to the large number of synthesis parameters involved in its production. While previous studies have investigated synthesis conditions, a comprehensive study applying machine learning approaches is lacking in the literature. In this paper, we apply machine learning methods, i.e., random forests of predictive clustering trees and a multilayer perceptron, training them on 124 experimental data points to accurately predict the apparent density and closed porosity of foamed glass. We then apply a multiobjective optimization algorithm together with the multilayer perceptron to find optimal values for the process parameters used in foamed glass production. Our results show that the combination of machine learning and multiobjective optimization is an effective proxy for the development of novel foamed glass materials.
Keywords:process optimization, machine learning, foamed glass
Publication status:Published
Publication version:Version of Record
Submitted for review:21.03.2025
Article acceptance date:23.07.2025
Publication date:30.07.2025
Publisher:Elsevier
Year of publishing:2025
Number of pages:str. 1-8
Numbering:Vol. 257
Source:Nizozemska
PID:20.500.12556/DiRROS-24178 New window
UDC:004.8+666.11+338.3
ISSN on article:1873-4197
DOI:10.1016/j.matdes.2025.114459 New window
COBISS.SI-ID:246226691 New window
Copyright:© 2025 The Authors.
Note:Nasl. z nasl. zaslona; Opis vira z dne 21. 8. 2025;
Publication date in DiRROS:18.11.2025
Views:263
Downloads:108
Metadata:XML DC-XML DC-RDF
:
Copy citation
  
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Record is a part of a journal

Title:Materials & design
Publisher:Elsevier Science
ISSN:1873-4197
COBISS.SI-ID:56288771 New window

Document is financed by a project

Funder:ARIS - Slovenian Research and Innovation Agency
Project number:P2-0091-2022
Name:Sodobni anorganski materiali in nanotehnologije

Funder:ARIS - Slovenian Research and Innovation Agency
Project number:P2-0103-2022
Name:Tehnologije znanja

Funder:ARIS - Slovenian Research and Innovation Agency
Project number:GC-0001-2024
Name:Umetna inteligenca za znanost

Funder:ARIS - Slovenian Research and Innovation Agency
Project number:J7-4636-2022
Name:Temeljno razumevanje reakcije tvorbe vodika za novo generacijo elektrokatalizatorjev na osnovi niklja v alkalni in kloralkalni elektrolizi

Funder:ARIS - Slovenian Research and Innovation Agency
Project number:J7-4637-2022
Name:4D STEM energijsko učinkovitih materialov do kvantne ravni

Funder:EC - European Commission
Project number:101120237
Name:European Lighthouse of AI for Sustainability
Acronym:ELIAS

Funder:EC - European Commission
Project number:101081355
Name:Machine learning for Sciences and Humanities
Acronym:SMASH

Licences

License:CC BY 4.0, Creative Commons Attribution 4.0 International
Link:http://creativecommons.org/licenses/by/4.0/
Description:This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
Licensing start date:30.07.2025
Applies to:VoR

Back