Machine learning-based prediction of coefficient of friction and specific wear rate in aluminum-based metal matrix composites
Tribology - Materials, Surfaces & Interfaces · 2026-03 · 20 (1) · 31-42
DOI: 10.1177/17515831251401637 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tribology - Materials, Surfaces & Interfaces, online erschienen am 03.12.2025. Verfasst von Ashok Kumar Mishra. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 30 Literaturangaben.
Abstract (Originalsprache)
This study introduces a machine learning (ML) framework to predict the Coefficient of Friction (CoF) and Specific Wear Rate (SWR) in aluminum-based composites reinforced with SiC and MoS 2 . Utilizing a robust dataset of 948 records, eight ML models were developed and optimized via GridSearchCV. Hyperparameter tuning was transformative, with the optimized Ridge model achieving exceptional test R² values of 0.96 for CoF and 0.90 for SWR. Feature importance analysis identified Material, Sliding Load, and MoS 2 % as critical factors. The models infer a key synergistic mechanism: SiC enhances wear resistance, while MoS 2 reduces friction. This work validates a finely-tuned ML approach as a highly accurate and efficient computational alternative to traditional experimental methods for tribological performance modeling and MMC design.
Zitieren
APA
Mishra, A. K. (2026). Machine learning-based prediction of coefficient of friction and specific wear rate in aluminum-based metal matrix composites. Tribology - Materials, Surfaces & Interfaces, 20(1), 31-42. https://doi.org/10.1177/17515831251401637
Vancouver
Mishra AK. Machine learning-based prediction of coefficient of friction and specific wear rate in aluminum-based metal matrix composites. Tribology - Materials, Surfaces & Interfaces. 2026;20(1):31-42. doi:10.1177/17515831251401637
BibTeX
@article{Mishra2026,
author = {Mishra, Ashok Kumar},
title = {Machine learning-based prediction of coefficient of friction and specific wear rate in aluminum-based metal matrix composites},
journal = {Tribology - Materials, Surfaces & Interfaces},
year = {2026},
volume = {20},
number = {1},
pages = {31--42},
doi = {10.1177/17515831251401637}
}
EUVIMED