EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning Prediction of Dry Friction in DLC Coatings Using Literature-Derived Data

Oussama Cherguy, Radoslaw Chmielowski, Elie Hachem, Imène Lahouij

Tribology Letters · 2025-12 · 73 (4)

DOI: 10.1007/s11249-025-02056-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tribology Letters, online erschienen am 25.08.2025. Verfasst von Oussama Cherguy und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 104 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fondation Maison de la Chimie, IMRA Europe, Mines Paris - PSL.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting the friction behavior of diamond-like carbon (DLC) coatings remains a key challenge in tribology due to the complex interplay of test conditions, material properties, and experimental variability. Although literature data are abundant, they are often non-standardized and are reported under highly variable conditions, which hinders their systematic reuse for predictive modeling. This study introduces a machine learning (ML) framework that exploits heterogeneous data with a focus on physical relevance and robustness. A dataset of approximately 4100 points (including 410 friction coefficient points) was compiled from an extensive literature review. Two modeling scenarios are defined: the first uses mechanical, structural, and tribological descriptors; the second adds chemical composition features, offering more detail but reducing dataset size. Six machine learning models are evaluated under standardized training conditions to predict friction. Model performance is evaluated using standard metrics. Extra Trees (ET) and Artificial Neural Networks (ANNs) achieve the highest performance. SHAP (SHapley Additive exPlanations) analysis identifies temperature and hertz pressure as dominant predictors, consistent with the tribological observations. Incorporating chemical composition improved prediction accuracy but reduced dataset size, highlighting a key trade-off between data completeness and feature richness. SHAP analysis shows that while temperature and hertz pressure remain key predictors, the importance of humidity increases, reflecting that chemical inputs enhance not only accuracy but also the physical interpretability of the models. The results demonstrate that literature-based data can support robust and physically meaningful friction modeling when feature richness is balanced with careful control of data quality.

Förderung

  • Fondation Maison de la Chimie
  • IMRA Europe
  • Mines Paris - PSL

Zitieren

APA

Cherguy, O., Chmielowski, R., Hachem, E., & Lahouij, I. (2025). Deep Learning Prediction of Dry Friction in DLC Coatings Using Literature-Derived Data. Tribology Letters, 73(4). https://doi.org/10.1007/s11249-025-02056-2

Vancouver

Cherguy O, Chmielowski R, Hachem E, Lahouij I. Deep Learning Prediction of Dry Friction in DLC Coatings Using Literature-Derived Data. Tribology Letters. 2025;73(4). doi:10.1007/s11249-025-02056-2

BibTeX
@article{Cherguy2025,
  author = {Cherguy, Oussama and Chmielowski, Radoslaw and Hachem, Elie and Lahouij, Imène},
  title = {Deep Learning Prediction of Dry Friction in DLC Coatings Using Literature-Derived Data},
  journal = {Tribology Letters},
  year = {2025},
  volume = {73},
  number = {4},
  doi = {10.1007/s11249-025-02056-2}
}
Kostenlos starten →