A comparative experimental and AI-based study of wear behaviour in biomedical SS316L and Co–Cr–Mo alloys under angular reciprocating sliding
Journal of Materials Research and Technology · 2026-09 · 44 · 645-655
DOI: 10.1016/j.jmrt.2026.07.221 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Materials Research and Technology, 2026-09. Verfasst von Ahmed Ali Akbar Akbar und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Iran Telecommunication Research Center, IITP, Ministry of Science and ICT, South Korea.
Abstract (Originalsprache)
This work presents a hybrid predictive–optimisation framework that integrates experimental tribology, interpretable machine learning, and evolutionary optimisation to evaluate and reduce wear in biomedical SS316L and Co–Cr–Mo alloys under angular reciprocating sliding in simulated physiological conditions. A central composite design (CCD) controlled the experiments, with normal load, sliding frequency and contact time as the key variables. Co–Cr–Mo showed markedly higher wear resistance, consistent with its higher hardness and carbide-strengthened microstructure: its mean wear rate was 0.518 × 1 0 − 6 g/m against 7.032 × 1 0 − 6 g/m for SS316L, a 13.6-fold improvement. Ensemble machine-learning models (Random Forest and XGBoost) were highly predictive (accuracy-weighted ensemble R 2 = 0.847 for SS316L and 0.945 for Co–Cr–Mo), and SHapley Additive exPlanations (SHAP) identified normal load as the dominant driver (41.2% of the feature importance), followed by sliding frequency (33.5%) and contact time (18.1%). Coupling the calibrated surrogate with a genetic algorithm (GA) located low-wear operating windows; relative to each alloy’s own worst-case setting the GA achieved wear reductions of 62% (SS316L) and 78% (Co–Cr–Mo), and the predicted optimum was experimentally verified to within 4%. The framework offers a repeatable, scalable route to AI-guided wear optimisation for next-generation implant materials.
Förderung
- Iran Telecommunication Research Center
- IITP
- Ministry of Science and ICT, South Korea
- National Science Foundation
Zitieren
APA
Akbar, A. A. A., Algburi, R. N. A., Al-Huda, Z., Gu, Y. H., & Al-antari, M. A. (2026). A comparative experimental and AI-based study of wear behaviour in biomedical SS316L and Co–Cr–Mo alloys under angular reciprocating sliding. Journal of Materials Research and Technology, 44, 645-655. https://doi.org/10.1016/j.jmrt.2026.07.221
Vancouver
Akbar AAA, Algburi RNA, Al-Huda Z, Gu YH, Al-antari MA. A comparative experimental and AI-based study of wear behaviour in biomedical SS316L and Co–Cr–Mo alloys under angular reciprocating sliding. Journal of Materials Research and Technology. 2026;44:645-655. doi:10.1016/j.jmrt.2026.07.221
BibTeX
@article{Akbar2026,
author = {Akbar, Ahmed Ali Akbar and Algburi, Riyadh Nazar Ali and Al-Huda, Zaid and Gu, Yeong Hyeon and Al-antari, Mugahed A.},
title = {A comparative experimental and AI-based study of wear behaviour in biomedical SS316L and Co–Cr–Mo alloys under angular reciprocating sliding},
journal = {Journal of Materials Research and Technology},
year = {2026},
volume = {44},
pages = {645--655},
doi = {10.1016/j.jmrt.2026.07.221}
}
EUVIMED