Predicting EHL film thickness parameters by machine learning approaches

Simple item page
dc.contributor.authorMarian, Max
dc.contributor.authorMursak, Jonas
dc.contributor.authorBartz, Marcel
dc.contributor.authorProfito, Francisco J.
dc.contributor.authorRosenkranz, Andreas
dc.contributor.authorWartzack, Sandro
dc.date.accessioned2022-08-18T16:40:06Z
dc.date.available2022-08-18T16:40:06Z
dc.date.issued2022
dc.description.abstractNon-dimensional similarity groups and analytically solvable proximity equations can be used to estimate integral fluid film parameters of elastohydrodynamically lubricated (EHL) contacts. In this contribution, we demonstrate that machine learning (ML) and artificial intelligence (AI) approaches (support vector machines, Gaussian process regressions, and artificial neural networks) can predict relevant film parameters more efficiently and with higher accuracy and flexibility compared to sophisticated EHL simulations and analytically solvable proximity equations, respectively. For this purpose, we use data from EHL simulations based upon the full-system finite element (FE) solution and a Latin hypercube sampling. We verify that the original input data are required to train ML approaches to achieve coefficients of determination above 0.99. It is revealed that the architecture of artificial neural networks (neurons per layer and number of hidden layers) and activation functions influence the prediction accuracy. The impact of the number of training data is exemplified, and recommendations for a minimum database size are given. We ultimately demonstrate that artificial neural networks can predict the locally-resolved film thickness values over the contact domain 25-times faster than FE-based EHL simulations (R² values above 0.999). We assume that this will boost the use of ML approaches to predict EHL parameters and traction losses in multibody system dynamics simulations.
dc.format.extent22 páginas
dc.fuente.origenAutoarchivo
dc.identifier.citationFriction (2022)
dc.identifier.doi10.1007/s40544-022-0641-6
dc.identifier.urihttps://doi.org/10.1007/s40544-022-0641-6
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/64674
dc.information.autorucEscuela de ingeniería ; Marian, Max ; 0000-0003-2045-6649 ; 1247429
dc.language.isoen
dc.nota.accesoContenido completo
dc.pagina.final22
dc.pagina.inicio1
dc.revistaFriction
dc.rightsacceso abierto
dc.rights.holderThe Author(s)
dc.subjectMachine learninges_ES
dc.subjectElastohydrodynamices_ES
dc.subjectLubricationes_ES
dc.subjectFilm thicknesses_ES
dc.subjectSupport vector machinees_ES
dc.subjectGaussian process regressiones_ES
dc.subjectArtificial neural networkes_ES
dc.subject.ddc620
dc.subject.deweyIngenieríaes_ES
dc.titlePredicting EHL film thickness parameters by machine learning approacheses_ES
dc.typeartículo
sipa.codpersvinculados1247429
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Predicting EHL film thickness parameters by machine learning.pdf
Size:
3.89 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.98 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos de revistas