The DOI matches its Crossref record; 87 of the 87 references it cites were found in a registry or an index; 10 of the 18 sources its claims cite were checked for support.
Predicting EHL film thickness parameters by machine learning approaches
Open accessAbstract
Non-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 ( R 2 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.
Overview
CoChat Summary
TL;DR
Machine learning models trained on EHL simulation data predict central and minimum film thickness parameters more accurately than analytical proximity equations, with R² above 0.99 when using original EHL inputs. An ANN also predicts locally resolved film thickness over the contact 25 times faster than FE-based EHL simulation with R² above 0.999.
Key findings
- With original EHL inputs, SVM and GPR predicted central and minimum film thicknesses with R² > 0.99; GPR was slightly superior to SVM. ANN configurations also reached R² > 0.99, with 12 neurons in two hidden layers performing best for the 3D circular point contact.
- Using non-dimensional groups U, G, W or M, L instead of original inputs substantially reduced accuracy: R² fell well below 0.9 and almost to zero in some cases (e.g., GPR for 2D U, G, W gave h_c R² = 0.100 and h_min R² = 0.091; GPR for 3D U, G, W gave h_c R² = 0.013).
- For the 2D line contact, 600 training data points were sufficient for 12 input parameters, giving R² = 1.000 for h_c and h_min; 300 and 100 points reduced accuracy but stayed above 0.9 (300: 0.961/0.963; 100: 0.922/0.927). The original 1,249-point set gave 0.988/0.988, which the authors suggest may imply some overfitting.
- The ANN predicted the local lubricant film distribution over the contact length with an overall R² of 1.000 against testing data and was over 25 times faster than the FEM-based EHL simulation (19 s vs 0.74 s), with prediction coefficients above 0.999.
Methods
- Data were generated from steady-state isothermal EHL simulations using a full-system finite element solution, with Latin hypercube sampling. The 2D infinite line and 3D circular point contacts were sampled with 1,500 and 1,000 data sets, respectively; 1,499 and 764 converged data sets were ultimately obtained.
- SVM, GPR, and multi-hidden-layer feedforward backpropagation ANNs were implemented in MATLAB. Data were normalized to [−1, 1], split into 85% training and 15% testing, and evaluated by R². ANN architecture varied 10–20 neurons per layer and zero to three hidden layers; activation functions tested were hyperbolic tangent, sigmoid, and identity.
- Predictions were compared with analytically solvable proximity equations from Dowson/Toyoda/Higginson for 2D line contacts and Hamrock/Dowson for 3D circular point contacts. For local film thickness prediction, position along the contact length was added as an input, using 86 uniformly distributed points and 128,914 total data sets.
Limitations
- Stated: the trained ML approaches were not physics-informed and cannot provide physical explanations; predictions must be considered carefully because negative film thicknesses are possible. The authors suggest future use of a strictly positive linear function and output normalization to avoid unphysical results.
- Stated: predictions were meaningful only for operating conditions covered by the training data. Future work should consider elliptical contacts, thermal effects, other rheological models, time-dependent squeeze, starvation effects, surface roughness, and solid asperity contact.
- Stated and evident: the proximity equations have a limited validity range, and the design of experiments slightly exceeded it; thermal effects, limited oil supply, and shear-thinning fluid behavior were not considered in those correlations. Evident from the text: the ML models were trained on isothermal EHL simulation data and were not experimentally validated.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
![Fig. 1 Schematic of an EHL infinite 2D line contact with relevant input variables. Reproduced with permission from Ref. [4], © The authors 2020.](https://figures.cochat.ai/paper-figures/57b8b35da5a1497a9b0255d2e3abbd02/predicting-ehl-film-thickness-parameters-by-machine-learning-approaches-figure-1.png)












Verification
Claims the paper makes
8 Valid · 0 Not valid · 5 Not checked · 63 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“In particular, the modeling of concentrated, elastohydrodynamically lubricated (EHL) contacts (see Fig. 1), in which local elastic deformation of the rubbing surfaces and hydrodynamic fluid film formation are superimposed, is comparatively complex and computationally expensive [4].”
What the sources say
- Supportedcites [4] Marian M, Bartz M, Wartzack S, Rosenkranz A. Non-dimensional groups, film thickness equations and correction factors for elastohydrodynamic lubrication: A review. Lubricants 8(10): 95 (2020) source
The Introduction describes EHL as the combination of local elastic deformation and a lubricant film, and says numerical simulation couples hydrodynamic and elastic-deformation equations. It also says CFD- or Navier–Stokes-based modeling requires high computational effort, supporting the characterization of EHL modeling as complex and computationally expensive. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Nevertheless, ML approaches have not yet been adapted to predict lubricant film parameters in EHL contacts as a function of standard input variables, as is also accomplished by the well-known proximity equations [4, 39], see Fig. 2.”
What the sources say
- Supportedcites [4] Marian M, Bartz M, Wartzack S, Rosenkranz A. Non-dimensional groups, film thickness equations and correction factors for elastohydrodynamic lubrication: A review. Lubricants 8(10): 95 (2020) source
The citation follows the comparison to established film-thickness equations. Section 4.5 says those analytical equations calculate the minimum or central lubricant gap and provide good film-thickness predictions; it also describes EHL results as depending on input parameters. The cited paper therefore supports the comparison for which the citation is placed. (LLM, conf=0.87)
- Partly supportedcites [39] Rosenkranz A, Marian M, Profito F J, Aragon N, Shah R. The use of artificial intelligence in tribology—A perspective. Lubricants 9(1): 2 (2020) sourceExperimental — accuracy not yet measured
Section 2.4 (p. 7) describes ML predictions of friction in EHL contacts and proposes extending the approach to predict film thickness and other lubrication outcomes. That supports the suggestion that film-thickness prediction remained prospective in the applications discussed, but it does not establish that no ML approach had been adapted to predict EHL film parameters from standard input variables, nor does it make the comparison with proximity equations. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“As shown in Table 4, the coefficients of determination of the analytically solvable proximity equations featured good prediction quality despite the DoE slightly exceeding these equations' validity range, see Table 3 and Ref. [4].”
What the sources say
- Partly supportedcites [4] Marian M, Bartz M, Wartzack S, Rosenkranz A. Non-dimensional groups, film thickness equations and correction factors for elastohydrodynamic lubrication: A review. Lubricants 8(10): 95 (2020) sourceExperimental — accuracy not yet measured
The review’s Section 4.5 says analytical film-thickness equations can give good predictions and recommends considering their validity ranges. It does not report the citing paper’s coefficients of determination or show that prediction quality remained good when its DoE exceeded those ranges. (LLM, conf=0.85)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, the implementation of these equations requires the definition of more complicated analytical expressions to fit the simulation results, which, in turn, increases the computational effort and the proneness to errors.”
What the sources say
- Partly supportedcites [19] Nijenbanning G, Venner C H, Moes H. Film thickness in elastohydrodynamically lubricated elliptic contacts. Wear 176(2): 217–229 (1994) sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 1 unverifiable. Expand the claim to see per-atom verdicts.
- Not checked — no full text of the sourcecites [21] Wolf M, Solovyev S, Arshia F. Film thickness in elastohydrodynamically lubricated slender elliptic contacts: Part I—Numerical studies of central film thickness. Proc Inst Mech Eng Part J J Eng Tribol 236(6): 1043–1055 (2022) source
- Partly supportedcites [22] Moes H. Optimum similarity analysis with applications to elastohydrodynamic lubrication. Wear 159(1): 57–66 (1992) sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 1 unverifiable. Expand the claim to see per-atom verdicts.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“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.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 3 assumptions not shown here.
41 more claims
Create a free account to see all 76 claims and every source verdict.
- Probably not a substantial claim. 16
- It may state two separate claims as one. 17
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The authors also illustrated ANNs' ability to predict locally-resolved film thickness values in EHL contacts approximately 25 times faster than the FEM-based simulations, achieving high 𝑅 2 values ( > 0.999) in isothermal line- and point-contacts.”
From Enhancing practical modeling: A neural network approach for locally-resolved prediction of elastohydrodynamic line contacts (2024) · cites this paper as [11]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The dimensionless parameters 𝑈 , 𝑊 , and 𝐺 (see Eq. (3)) have been shown time and time again to provide excellent predictive power for the EHL behavior of the contact [43-46][11,47].”
From Enhancing practical modeling: A neural network approach for locally-resolved prediction of elastohydrodynamic line contacts (2024) · cites this paper as [11]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“One previously developed EHL film thickness database constructed via a Finite Element Method (FEM) solver covered a vast range of lubricants and material properties for relatively low speed conditions ( < 0.4 m ∕ s of 2D line contacts) [29].”
From Application of Tribological Artificial Neural Networks in Machine Elements (2023) · cites this paper as [29]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Moreover, in scenarios where computational resources are constrained, as forecasted by Marian et al. [11], ML methods present a viable alternative to traditional regression-based techniques for estimating EHL film thickness.”
From Enhancing practical modeling: A neural network approach for locally-resolved prediction of elastohydrodynamic line contacts (2024) · cites this paper as [11]
The cited source says what the claim attributes to it.
In the citing paper
“Marian et al . used Latin Hypercube Sampling (LHS) for EHL film prediction as an effective method to generate a training database to cover a vast design space with many factors [29].”
From Application of Tribological Artificial Neural Networks in Machine Elements (2023) · cites this paper as [29]
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2.2 Design of experiments · p. 7
“| | η 0 | Pa·s | 0.005 | 0.05 | 0.01 | 0.2 |”
§ 3.2.2.1 Global EHL film parameters · p. 14
“| | η 0 | g/cm³ | 0.03 | 0.04 | 0.05 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.2.2.2 Local EHL film distribution · p. 16
“For the prediction of the local lubricant film distribution for the infinite 2D line contact by an ANN with 12 neurons in 2 hidden layers”
§ 3.2.2.2 Local EHL film distribution · p. 17
“Table 12 Computational time for determining the lubricant film distribution over the contact length for a representative infinite 2D line contact using the FEM-based EHL simulation and an ANN with 15 neurons in each of the two hidden layers.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2.2 Design of experiments · p. 7
“| EHL contact | ρ 0 | kg/cm³ | 850 | 1,100 | 850 | 1,100 |”
§ 3.2.2.1 Global EHL film parameters · p. 14
“| | ρ 0 | Pa·s | 897 | 870 | 1,069 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.2.2.1 Global EHL film parameters · p. 14
“Therefore, the lowest R ² values resulted in only one hidden layer, followed by three and finally two hidden layers with the highest accuracy.”
§ 3.2.2.1 Global EHL film parameters · p. 15
“| Number of hidden layers | 2 | 0.690 | 0.690 | 0.988 | 0.988 | 1.000 | 1.000 | 0.999 | 0.999 |”
Citations
Cites
An Algorithm for Least-Squares Estimation of Nonlinear Parameters
Marquardt, D. W. (1963) · Journal of the Society for Industrial and Applied Mathematics · doi:10.1137/0111030 · Cited by 30,728
A method for the solution of certain non-linear problems in least squares
Levenberg, K. (1944) · Quarterly of Applied Mathematics · doi:10.1090/qam/10666 · Cited by 12,359
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Schölkopf, B., & Smola, A. J. (2001) · The MIT Press eBooks · doi:10.7551/mitpress/4175.001.0001 · Cited by 11,703
The Nature of Statistical Learning Theory
Vapnik, V. N. (2000) · Springer eBooks · doi:10.1007/978-1-4757-3264-1 · Cited by 10,696
Chicco, D., Warrens, M. J., & Jurman, G. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.623 · Cited by 5,380
Learning With Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Williams, C. K. I. (2003) · Journal of the American Statistical Association · doi:10.1198/jasa.2003.s269 · Cited by 4,281
Influence of tribology on global energy consumption, costs and emissions
Holmberg, K., & Erdemir, A. (2017) · Friction · doi:10.1007/s40544-017-0183-5 · Cited by 2,190
Reynolds, O. (1886) · Philosophical Transactions of the Royal Society of London · doi:10.1098/rstl.1886.0005 · Cited by 2,009
Global energy consumption due to friction in passenger cars
Holmberg, K., Andersson, P., & Erdemir, A. (2012) · Tribology International · doi:10.1016/j.triboint.2011.11.022 · Cited by 1,614
Hughes, T. J. R., Franca, L. P., & Hulbert, G. M. (1989) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/0045-7825(89)90111-4 · Cited by 1,458
Research works printed but not linked: 10
- Moes H. Discussion on Paper D1 by D. Dowson. Proc Instn Mech Engrs 180: 244–245 (1966)
- Moes H. Communications. In Proc. of the Symposium on Elastohydrodynamic Lubrication, 1965: 244–245.
- Dowson D. Elastohydrodynamics. Proc Inst Mech Eng 182: 151–157 (1968)
- Moes H. Lubrication and Beyond—University of Twente Lecture Notes code 115531. Enschede, Netherlands: University of Twente, 2000.
- Wiśniewski M. Einfluß eines begrenzten Ölangebotes auf die elastohydrodynamische Schmierung von Zahnrädern. Tribologie und Schmierungstechnik 30: 270–277 (1983)
- Müller AC, Guido S. Introduction to machine learning with Python: A guide for data scientist. Beijing: O’Reilly, 2016.
- Gohar R. Elastohydrodynamics. Chichester: Halsted Press, 1988.
- Roelands C. Correlational aspects of the viscosity-temperature-pressure relationship of lubricating oils. Ph.D. Thesis. Delft University of Technology, 1966.
- Glantz SA, Slinker BK. Primer of Applied Regression and Analysis of Variance. New York, NY: McGraw-Hill, 1990.
- Montgomery D C, Runger G C. Applied Statistics and Probability for Engineers 6th Edition. Wiley, 2014.
Cited by
AI for tribology: Present and future
Yin, N., Yang, P., Liu, S., Pan, S., & Zhang, Z. (2024) · Friction · doi:10.1007/s40544-024-0879-2 · Cited by 109
Baş, H., & Karabacak, Y. E. (2023) · Tribology International · doi:10.1016/j.triboint.2023.108592 · Cited by 80
Physics-Informed Machine Learning—An Emerging Trend in Tribology
Marian, M., & Tremmel, S. (2023) · Lubricants · doi:10.3390/lubricants11110463 · Cited by 88
Self-citationApplication of Tribological Artificial Neural Networks in Machine Elements
Walker, J., Questa, H., Raman, A., Ahmed, M., Mohammadpour, M., Bewsher, S. R., & Offner, G. (2023) · Tribology Letters · doi:10.1007/s11249-022-01673-5 · Cited by 39
“Marian et al . used Latin Hypercube Sampling (LHS) for EHL film prediction as an effective method to generate a training database to cover a vast design space with many factors [29].”
BackgroundMethodResultInfluentialCartwright, S., Rothwell, B. C., Figueredo, G. P., Medina, H., Eastwick, C. N., Layton, J., & Ambrose, S. (2024) · Tribology International · doi:10.1016/j.triboint.2024.109670 · Cited by 45
Metadata
- Authors
- Marian, M., Mursak, J., Bartz, M., Profito, F. J., Rosenkranz, A., & Wartzack, S.
- Affiliations
- Pontificia Universidad Católica de Chile (CL)
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Universidade de São Paulo (BR)
- University of Chile (CL)
- Corresponding author
- Marian, Max
- Venue
- Friction
- Publisher
- Tsinghua University Press
- Published
- 2022-06-12
- Volume
- 11
- Issue
- 6
- Pages
- 992-1013
- ISSN
- 2223-7690 (ISSN-L)
- 2223-7704
- OpenAlex
- W4282599518
- Semantic Scholar
- 00e98b0f652dbee9dfb1d063027712e55f690f69
- Cited by
- 76
- References
- 80
- Citations by year
- 2026: 21 · 2025: 16 · 2024: 21 · 2023: 13 · 2022: 5
- FWCI
- 5.19
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Friction (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Universidad de Chile (submittedVersion, cc-by-nc-nd)
- Funders
- Universidad de Chile (UM‐04/19)
- Pontificia Universidad Católica de Chile
- Agencia Nacional de Investigación y Desarrollo (11180121, EQM190057)
- Topics
- Physical Sciences › Engineering › Mechanical Engineering › Tribology and Lubrication Engineering
- Physical Sciences › Engineering › Mechanical Engineering › Gear and Bearing Dynamics Analysis
- Physical Sciences › Engineering › Mechanical Engineering › Lubricants and Their Additives
- Keywords
- elastohydrodynamic lubrication, film thickness prediction, machine learning, artificial neural networks, support vector machine, Gaussian process regression, Latin hypercube sampling, training data size, activation functions, multibody dynamics, traction loss
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Predicting EHL film thickness parameters by machine learning approaches. https://app.cochat.ai/papers/10.1007/s40544-022-0641-6
- The paper
- Marian, M., Mursak, J., Bartz, M., Profito, F. J., Rosenkranz, A., & Wartzack, S. (2023). Predicting EHL film thickness parameters by machine learning approaches. Friction. https://doi.org/10.1007/s40544-022-0641-6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.