Epoxy Adhesive Materials as Protective Coatings: Strength Property Analysis Using Machine Learning Algorithms
Artykuł w czasopiśmie
MNiSW
140
Lista 2024
| Status: | |
| Autorzy: | Miturska-Barańska Izabela, Antosz Katarzyna |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Rok wydania: | 2025 |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Język: | angielski |
| Numer czasopisma: | 12 |
| Wolumen/Tom: | 18 |
| Strony: | 1 - 33 |
| Impact Factor: | 3,2 |
| Web of Science® Times Cited: | 0 |
| Scopus® Cytowania: | 1 |
| Bazy: | Web of Science | Scopus |
| Efekt badań statutowych | NIE |
| Finansowanie: | The research leading to these results has received funding from the commissioned task entitled “VIA CARPATIA Universities of Technology Network named after the President of the Republic of Poland Lech Kaczyński” under the special purpose grant from the Minister of Education and Science, contract no. MEiN/2022/DPI/2575, as part of the action “In the neighborhood—inter-university research internships and study visits”. |
| Materiał konferencyjny: | NIE |
| Publikacja OA: | TAK |
| Licencja: | |
| Sposób udostępnienia: | Witryna wydawcy |
| Wersja tekstu: | Ostateczna wersja opublikowana |
| Czas opublikowania: | W momencie opublikowania |
| Data opublikowania w OA: | 12 czerwca 2025 |
| Abstrakty: | angielski |
| This study analyzed the mechanical properties of epoxy adhesive materials used as functional coatings, focusing on how physical modifications impact their microstructure and strength. Compositions based on Epidian 5, 53 and 57 resins were cured using TFF, Z-1, or PAC curing agents and modified with various fillers: mineral (CaCO3 calcium carbonate), active (activated carbon filler, CWZ-22), and nanostructured (montmorillonite, ZR-2) fillers. The best results were achieved with calcium carbonate (10–20 wt%) in Epidian 5 or 53 resins cured with TFF or Z-1, yielding tensile strength up to 64 MPa, compressive strength up to 145 MPa, and bending strength up to 123 MPa. Activated carbon and nanofillers showed moderate improvements, particularly in more flexible matrices. To support property prediction, machine learning algorithms were applied and successfully modeled the mechanical behavior based on composition data. The most accurate models reached R2 values of 0.93–0.95 for compression and bending strength. While the models for compression and bending strength demonstrated high accuracy, the tensile strength model yielded lower predictive performance, indicating that further refinement and expanded input features are necessary. Shapley analysis further identified curing agents and fillers as key predictive features. This integrated experimental and data-driven approach offers an effective framework for optimizing epoxy-based coatings in industrial applications. |
