Application of machine learning for film thickness prediction in elliptical EHL contact with varying entrainment angle

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Marko Tošić
  • Max Marian
  • Wassim Habchi
  • Thomas Lohner
  • Karsten Stahl

External Research Organisations

  • Technical University of Munich (TUM)
  • Pontificia Universidad Catolica de Chile
  • Lebanese American University
View graph of relations

Details

Original languageEnglish
Article number109940
Number of pages14
JournalTribology international
Volume199
Early online date5 Jul 2024
Publication statusPublished - Nov 2024

Abstract

This contribution demonstrates the potential of machine learning (ML) algorithms in predicting elastohydrodynamic lubrication (EHL) film thickness in elliptical contact with varying direction of lubricant entrainment, ranging from wide to slender elliptical configurations. The input parameters pertain to worm gear contacts, which are characterized by slender-like elliptical contact between a steel and a soft metal component. The study encompasses generating a database using numerical Finite Element Method (FEM) simulations, training artificial neural network (ANN) models, and evaluating their performance in terms of bias and variance. Key outcomes include the successful training of the ANN models, detailed analysis of the impact of tailored architecture on the ANN models' performance, and the superiority of the ANN compared to other ML regression algorithms. The study further identifies key input parameters that influence prediction accuracy and introduces a strategic dataset augmentation procedure to increase local and overall prediction accuracy. This strategic dataset augmentation enhances model robustness and precision while providing insights for expanding databases collaboratively. It holds potential for broader applications of ML for performance prediction of tribological contacts, thus paving the way for advanced ML models that consider additional factors and collaborative databases refined by multiple research groups.

Keywords

    Artificial intelligence, Artificial neural network, Elastohydrodynamics, Film thickness, Machine learning, Regression, Worm gears

ASJC Scopus subject areas

Cite this

Application of machine learning for film thickness prediction in elliptical EHL contact with varying entrainment angle. / Tošić, Marko; Marian, Max; Habchi, Wassim et al.
In: Tribology international, Vol. 199, 109940, 11.2024.

Research output: Contribution to journalArticleResearchpeer review

Tošić M, Marian M, Habchi W, Lohner T, Stahl K. Application of machine learning for film thickness prediction in elliptical EHL contact with varying entrainment angle. Tribology international. 2024 Nov;199:109940. Epub 2024 Jul 5. doi: 10.1016/j.triboint.2024.109940
Download
@article{18d1f18f2d2948aabc1aae7ab7e3bc25,
title = "Application of machine learning for film thickness prediction in elliptical EHL contact with varying entrainment angle",
abstract = "This contribution demonstrates the potential of machine learning (ML) algorithms in predicting elastohydrodynamic lubrication (EHL) film thickness in elliptical contact with varying direction of lubricant entrainment, ranging from wide to slender elliptical configurations. The input parameters pertain to worm gear contacts, which are characterized by slender-like elliptical contact between a steel and a soft metal component. The study encompasses generating a database using numerical Finite Element Method (FEM) simulations, training artificial neural network (ANN) models, and evaluating their performance in terms of bias and variance. Key outcomes include the successful training of the ANN models, detailed analysis of the impact of tailored architecture on the ANN models' performance, and the superiority of the ANN compared to other ML regression algorithms. The study further identifies key input parameters that influence prediction accuracy and introduces a strategic dataset augmentation procedure to increase local and overall prediction accuracy. This strategic dataset augmentation enhances model robustness and precision while providing insights for expanding databases collaboratively. It holds potential for broader applications of ML for performance prediction of tribological contacts, thus paving the way for advanced ML models that consider additional factors and collaborative databases refined by multiple research groups.",
keywords = "Artificial intelligence, Artificial neural network, Elastohydrodynamics, Film thickness, Machine learning, Regression, Worm gears",
author = "Marko To{\v s}i{\'c} and Max Marian and Wassim Habchi and Thomas Lohner and Karsten Stahl",
note = "Publisher Copyright: {\textcopyright} 2024 The Authors",
year = "2024",
month = nov,
doi = "10.1016/j.triboint.2024.109940",
language = "English",
volume = "199",
journal = "Tribology international",
issn = "0301-679X",
publisher = "Elsevier Inc.",

}

Download

TY - JOUR

T1 - Application of machine learning for film thickness prediction in elliptical EHL contact with varying entrainment angle

AU - Tošić, Marko

AU - Marian, Max

AU - Habchi, Wassim

AU - Lohner, Thomas

AU - Stahl, Karsten

N1 - Publisher Copyright: © 2024 The Authors

PY - 2024/11

Y1 - 2024/11

N2 - This contribution demonstrates the potential of machine learning (ML) algorithms in predicting elastohydrodynamic lubrication (EHL) film thickness in elliptical contact with varying direction of lubricant entrainment, ranging from wide to slender elliptical configurations. The input parameters pertain to worm gear contacts, which are characterized by slender-like elliptical contact between a steel and a soft metal component. The study encompasses generating a database using numerical Finite Element Method (FEM) simulations, training artificial neural network (ANN) models, and evaluating their performance in terms of bias and variance. Key outcomes include the successful training of the ANN models, detailed analysis of the impact of tailored architecture on the ANN models' performance, and the superiority of the ANN compared to other ML regression algorithms. The study further identifies key input parameters that influence prediction accuracy and introduces a strategic dataset augmentation procedure to increase local and overall prediction accuracy. This strategic dataset augmentation enhances model robustness and precision while providing insights for expanding databases collaboratively. It holds potential for broader applications of ML for performance prediction of tribological contacts, thus paving the way for advanced ML models that consider additional factors and collaborative databases refined by multiple research groups.

AB - This contribution demonstrates the potential of machine learning (ML) algorithms in predicting elastohydrodynamic lubrication (EHL) film thickness in elliptical contact with varying direction of lubricant entrainment, ranging from wide to slender elliptical configurations. The input parameters pertain to worm gear contacts, which are characterized by slender-like elliptical contact between a steel and a soft metal component. The study encompasses generating a database using numerical Finite Element Method (FEM) simulations, training artificial neural network (ANN) models, and evaluating their performance in terms of bias and variance. Key outcomes include the successful training of the ANN models, detailed analysis of the impact of tailored architecture on the ANN models' performance, and the superiority of the ANN compared to other ML regression algorithms. The study further identifies key input parameters that influence prediction accuracy and introduces a strategic dataset augmentation procedure to increase local and overall prediction accuracy. This strategic dataset augmentation enhances model robustness and precision while providing insights for expanding databases collaboratively. It holds potential for broader applications of ML for performance prediction of tribological contacts, thus paving the way for advanced ML models that consider additional factors and collaborative databases refined by multiple research groups.

KW - Artificial intelligence

KW - Artificial neural network

KW - Elastohydrodynamics

KW - Film thickness

KW - Machine learning

KW - Regression

KW - Worm gears

UR - http://www.scopus.com/inward/record.url?scp=85200209282&partnerID=8YFLogxK

U2 - 10.1016/j.triboint.2024.109940

DO - 10.1016/j.triboint.2024.109940

M3 - Article

AN - SCOPUS:85200209282

VL - 199

JO - Tribology international

JF - Tribology international

SN - 0301-679X

M1 - 109940

ER -