Home > Research > Publications & Outputs > Machine Learning-Driven Optimization of Micro-T...

Research

Links

Text available via DOI:

View graph of relations

Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance: A Comparative Analysis of Predictive Models

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance: A Comparative Analysis of Predictive Models. / Ge, Zhenghui; Hu, Qifan; Wang, Rui et al.
In: Coatings, Vol. 14, No. 12, 1539, 08.12.2024.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Ge, Z, Hu, Q, Wang, R, Fei, H, Zhu, Y & Wang, Z 2024, 'Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance: A Comparative Analysis of Predictive Models', Coatings, vol. 14, no. 12, 1539. https://doi.org/10.3390/coatings14121539

APA

Ge, Z., Hu, Q., Wang, R., Fei, H., Zhu, Y., & Wang, Z. (2024). Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance: A Comparative Analysis of Predictive Models. Coatings, 14(12), Article 1539. https://doi.org/10.3390/coatings14121539

Vancouver

Ge Z, Hu Q, Wang R, Fei H, Zhu Y, Wang Z. Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance: A Comparative Analysis of Predictive Models. Coatings. 2024 Dec 8;14(12):1539. doi: 10.3390/coatings14121539

Author

Ge, Zhenghui ; Hu, Qifan ; Wang, Rui et al. / Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance : A Comparative Analysis of Predictive Models. In: Coatings. 2024 ; Vol. 14, No. 12.

Bibtex

@article{5f225d7aec294aa9a163ca887147dad5,
title = "Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance: A Comparative Analysis of Predictive Models",
abstract = "Micro-textured surfaces show promise in improving tribological properties, but predicting their performance remains challenging due to complex relationships between surface features and frictional behavior. This study evaluates five algorithms—linear regression, decision tree, gradient boosting, support vector machine, and neural network—for their ability to predict load-carrying capacity and friction force based on texture parameters including depth, side length, surface ratio, and shape. The neural network model demonstrated superior performance, achieving the lowest MAE (24.01) and highest R-squared value (0.99) for friction force prediction. The results highlight the potential of machine learning techniques to enhance the understanding and prediction of friction-reducing micro-textures, contributing to the development of more efficient and durable tribological systems in industrial applications.",
author = "Zhenghui Ge and Qifan Hu and Rui Wang and Haolin Fei and Yongwei Zhu and Ziwei Wang",
year = "2024",
month = dec,
day = "8",
doi = "10.3390/coatings14121539",
language = "English",
volume = "14",
journal = "Coatings",
issn = "2079-6412",
publisher = "MDPI AG",
number = "12",

}

RIS

TY - JOUR

T1 - Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance

T2 - A Comparative Analysis of Predictive Models

AU - Ge, Zhenghui

AU - Hu, Qifan

AU - Wang, Rui

AU - Fei, Haolin

AU - Zhu, Yongwei

AU - Wang, Ziwei

PY - 2024/12/8

Y1 - 2024/12/8

N2 - Micro-textured surfaces show promise in improving tribological properties, but predicting their performance remains challenging due to complex relationships between surface features and frictional behavior. This study evaluates five algorithms—linear regression, decision tree, gradient boosting, support vector machine, and neural network—for their ability to predict load-carrying capacity and friction force based on texture parameters including depth, side length, surface ratio, and shape. The neural network model demonstrated superior performance, achieving the lowest MAE (24.01) and highest R-squared value (0.99) for friction force prediction. The results highlight the potential of machine learning techniques to enhance the understanding and prediction of friction-reducing micro-textures, contributing to the development of more efficient and durable tribological systems in industrial applications.

AB - Micro-textured surfaces show promise in improving tribological properties, but predicting their performance remains challenging due to complex relationships between surface features and frictional behavior. This study evaluates five algorithms—linear regression, decision tree, gradient boosting, support vector machine, and neural network—for their ability to predict load-carrying capacity and friction force based on texture parameters including depth, side length, surface ratio, and shape. The neural network model demonstrated superior performance, achieving the lowest MAE (24.01) and highest R-squared value (0.99) for friction force prediction. The results highlight the potential of machine learning techniques to enhance the understanding and prediction of friction-reducing micro-textures, contributing to the development of more efficient and durable tribological systems in industrial applications.

U2 - 10.3390/coatings14121539

DO - 10.3390/coatings14121539

M3 - Journal article

VL - 14

JO - Coatings

JF - Coatings

SN - 2079-6412

IS - 12

M1 - 1539

ER -