Szczegóły publikacji
Opis bibliograficzny
Evaluation of artificial neural networks' capabilities for hardness predictions of heterogeneous materials / SITARZ Szymon, SITKO Mateusz, MADEJ Łukasz // International Scientific Journal Industry 4.0 ; ISSN 2534-8582 . — 2025 — vol. 10 iss. 6, s. 204–205. — Bibliogr. s. 205, Abstr.
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 169054 |
|---|---|
| Data dodania do BaDAP | 2026-07-31 |
| Tekst źródłowy | URL |
| Rok publikacji | 2025 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Creative Commons | |
| Czasopismo/seria | International Scientific Journal Industry 4.0 |
Abstract
Explosively welded materials exhibit heterogeneous microstructures and variable mechanical properties, making local analysis crucial for the evaluation of joint integrity. Nanoindentation effectively assesses interface properties but typically relies on a series of analytical calculations. This paper proposes a machine learning approach to predict hardness directly from measured load-displacement curves. A neural network model captures nonlinear relationships in indentation data, demonstrating high accuracy against reference measurements across heterogeneous microstructure. This data-driven method offers a scalable solution for rapid, reliable property assessment in complex engineering materials.
