Machine Learning Composite-Nanoparticle-Enriched Lubricant Oil Development for Improved Frictional Performance—An Experiment
Abstract
:1. Introduction
2. Design of Experiment
3. Computational Models of Lubricants
3.1. Training Dataset Generation
3.2. Random Forest Trees
3.3. Support Vector Machines
3.4. Hyperparameter Estimation with Bayesian Optimization
3.5. Design of Lubricant ANN Model
4. Results and Discussion
5. Conclusions
- The computational models given by the data-driven ML-based approaches such as random forest trees (RFT), support vector machines (SVM), and artificial neural networks (ANN) are promising solutions to predict non-linearity in such complex interactions.
- The multi-layered ANN-based regression models of lubricants having single and multiple nanoparticles (NP) are developed to examine their tribological behavior. The complex interactions of input parameters (load, speed, and NP concentration) and the output parameter (CoF) is well estimated by the ANNs when their hyperparameters are optimized.
- A better performance for ML-optimized nano lubricant models is found in decreasing the CoF between metal-to-metal interactions in sliding lubricated contact for engineering applications.
- The results have shown that the optimum concentration of NP varies with varying lubrication domains and that a composite lubricant based on multiple NPs can be beneficial to reduce frictional energy loss and improve the lubrication conditions.
- The optimum concentration of multiple NPs can be reached for interfaces that experience fluctuating loads and thus varying lubrication conditions during their service.
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Lim, S.C. Recent developments in wear-mechanism maps. Tribol. Int. 1998, 31, 87–97. [Google Scholar] [CrossRef]
- Xiang, G.; Han, Y.; Wang, J.; Wang, J.; Ni, X. Coupling transient mixed lubrication and wear for journal bearing modeling. Tribol. Int. 2019, 138, 1–15. [Google Scholar] [CrossRef]
- Xie, Z.; Jiao, J.; Yang, K. Experimental and numerical study on the mixed lubrication performances of a new bearing. Tribol. Int. 2023, 182, 108334. [Google Scholar] [CrossRef]
- Li, W.; Wang, M.; Chen, Q.; Zhang, W.; Luo, T. A New Preparation Method of Copper oxide/Aluminium oxide Nanocomposites with Enhanced Anti-friction Properties. ES Mater. Manuf. 2023, 19, 692. [Google Scholar]
- Jaffar, S.S.; Baqer, I.A.; Soud, W.A. Effect of Bi2O3 Nanoparticles Addition to Lubricating Oil on the Dynamic Behavior of Rotor-Bearing Systems. J. Vib. Eng. Technol. 2022, 10, 2005–2017. [Google Scholar] [CrossRef]
- Zhao, Z.; Ma, Y.; Wan, H.; Ye, Y.; Chen, L.; Zhou, H.; Chen, J. Preparation and tribological behaviors of polyamide-imide/polytetrafluoroethylene lubricating coatings reinforced by in-situ synthesized CeO2 nanoparticles. Polym. Test. 2021, 96, 107100. [Google Scholar] [CrossRef]
- Ali, M.K.A.; Xianjun, H. Exploring the lubrication mechanism of CeO2 nanoparticles dispersed in engine oil by bis(2-ethylhexyl) phosphate as a novel antiwear additive. Tribol. Int. 2022, 165, 107321. [Google Scholar] [CrossRef]
- Lei, X.; Zhang, Y.; Zhang, S.; Yang, G.; Zhang, C.; Zhang, P. Study on the mechanism of rapid formation of ultra-thick tribofilm by CeO2 nano additive and ZDDP. Friction 2023, 11, 48–63. [Google Scholar] [CrossRef]
- Ghosh, S.K.; Miller, C.; Perez, G.; Carlton, H.; Huitink, D.; Beckford, S.; Zou, M. Effect of Cu nanoparticles on the tribological performance of polydopamine + polytetrafluoroethylene c oatings in oil-lubricated condition. Appl. Surf. Sci. 2021, 565, 150525. [Google Scholar] [CrossRef]
- Abdel-Rehim, A.A.; Akl, S.; Elsoudy, S. Investigation of the Tribological Behavior of Mineral Lubricant Using Copper Oxide Nano Additives. Lubricants 2021, 9, 16. [Google Scholar] [CrossRef]
- Okokpujie, I.P.; Tartibu, L.K.; Sinebe, J.E.; Adeoye, A.O.M.; Akinlabi, E.T. Comparative Study of Rheological Effects of Vegetable Oil-Lubricant, TiO2, MWCNTs Nano-Lubricants, and Machining Parameters’ Influence on Cutting Force for Sustainable Metal Cutting Process. Lubricants 2022, 10, 54. [Google Scholar] [CrossRef]
- Taha-Tijerina, J.; Aviña, K.; Diabb, J.M. Tribological and Thermal Transport Performance of SiO2-Based Natural Lubricants. Lubricants 2019, 7, 71. [Google Scholar] [CrossRef] [Green Version]
- Cortes, V.; Ortega, J.A. Evaluating the Rheological and Tribological Behaviors of Coconut Oil Modified with Nanoparticles as Lubricant Additives. Lubricants 2019, 7, 76. [Google Scholar] [CrossRef] [Green Version]
- Mirzaamiri, R.; Akbarzadeh, S.; Ziaei-Rad, S.; Shin, D.-G.; Kim, D.-E. Molecular dynamics simulation and experimental investigation of tribological behavior of nanodiamonds in aqueous suspensions. Tribol. Int. 2021, 156, 106838. [Google Scholar] [CrossRef]
- Wu, L.; Zhong, Y.; Yuan, H.; Liang, H.; Wang, F.; Gu, L. Ultra-dispersive sulfonated graphene as water-based lubricant additives for enhancing tribological performance. Tribol. Int. 2022, 174, 107759. [Google Scholar] [CrossRef]
- Xu, M.; Wang, X.; Wang, T.; Wang, Q.; Li, S. Ag nanoparticle decorated graphene for improving tribological properties of fabric/phenolic composites. Tribol. Int. 2022, 176, 107889. [Google Scholar] [CrossRef]
- Wang, G.; Ruan, Y.; Wang, H.; Zhao, G.; Cao, X.; Li, X.; Ding, Q. Tribological performance study and prediction of copper coated by MoS2 based on GBRT method. Tribol. Int. 2023, 179, 108149. [Google Scholar] [CrossRef]
- Yu, Z.; Wang, S.; Cheng, J.; Chen, J.; Chen, W.; Sun, Q.; Yang, J. Tribological behaviors of MoAlB ceramic in artificial seawater. Tribol. Int. 2022, 167, 107345. [Google Scholar] [CrossRef]
- Pham, S.T.; Huynh, K.K.; Tieu, K.A. Tribological performances of ceramic oxide nanoparticle additives in sodium borate melt under steel/steel sliding contacts at high temperatures. Tribol. Int. 2022, 165, 107296. [Google Scholar] [CrossRef]
- Simonovic, K.; Vitu, T.; Cammarata, A.; Cavaleiro, A.; Polcar, T. Tribological behaviour of W-S-C coated ceramics in a vacuum environment. Tribol. Int. 2022, 167, 107375. [Google Scholar] [CrossRef]
- Xu, Z.; Zhong, M.; Xu, W.; Xie, G.; Hu, H. Effects of aluminosilicate particles on tribological performance and friction mechanism of Cu-matrix pads for high-speed trains. Tribol. Int. 2023, 177, 107983. [Google Scholar] [CrossRef]
- Chen, F.; Yan, K.; Hong, J.; Song, J. Synergistic effect of graphene and β-Si3N4 whisker enables Si3N4 ceramic composites to obtain ultra-low friction coefficient. Tribol. Int. 2023, 178, 108045. [Google Scholar] [CrossRef]
- Fahad, M.R.; Abdulmajeed, B.A. Experimental investigation of base oil properties containing modified TiO2/CuO nanoparticles additives. J. Phys. Conf. Ser. 2021, 1973, 012089. [Google Scholar] [CrossRef]
- Sharma, A.K.; Tiwari, A.K.; Dixit, A.R.; Singh, R.K.; Singh, M. Novel uses of alumina/graphene hybrid nanoparticle additives for improved tribological properties of lubricant in turning operation. Tribol. Int. 2018, 119, 99–111. [Google Scholar] [CrossRef]
- Huang, S.; He, A.; Yun, J.-H.; Xu, X.; Jiang, Z.; Jiao, S.; Huang, H. Synergistic tribological performance of a water based lubricant using graphene oxide and alumina hybrid nanoparticles as additives. Tribol. Int. 2019, 135, 170–180. [Google Scholar] [CrossRef]
- de Oliveira, L.R.; Rodrigues, T.A.; Costa, H.L.; da Silva, W.M., Jr. Scuffing resistance of polyalphaolefin (PAO)-based nanolubricants with oleic acid (OA) and iron oxide nanoparticles. Mater. Today Commun. 2022, 31, 103837. [Google Scholar] [CrossRef]
- Liñeira del Río, J.M.; López, E.R.; González Gómez, M.; Yáñez Vilar, S.; Piñeiro, Y.; Rivas, J.; Gonçalves, D.E.P.; Seabra, J.H.O.; Fernández, J. Tribological Behavior of Nanolubricants Based on Coated Magnetic Nanoparticles and Trimethylolpropane Trioleate Base Oil. Nanomaterials 2020, 10, 683. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Alvi, M.A.A.; Belayneh, M.; Bandyopadhyay, S.; Minde, M.W. Effect of Iron Oxide Nanoparticles on the Properties of Water-Based Drilling Fluids. Energies 2020, 13, 6718. [Google Scholar] [CrossRef]
- Bhaumik, S.; Pathak, S.D.; Dey, S.; Datta, S. Artificial intelligence based design of multiple friction modifiers dispersed castor oil and evaluating its tribological properties. Tribol. Int. 2019, 140, 105813. [Google Scholar] [CrossRef]
- Humelnicu, C.; Ciortan, S.; Amortila, V. Artificial Neural Network-Based Analysis of the Tribological Behavior of Vegetable Oil–Diesel Fuel Mixtures. Lubricants 2019, 7, 32. [Google Scholar] [CrossRef] [Green Version]
- Haldar, A.; Chatterjee, S.; Kotia, A.; Kumar, N.; Ghosh, S.K. Analysis of rheological properties of MWCNT/SiO2 hydraulic oil nanolubricants using regression and artificial neural network. Int. Commun. Heat Mass Transf. 2020, 116, 104723. [Google Scholar] [CrossRef]
- Esfe, M.H.; Toghraie, D.; Amoozadkhalili, F. Optimization and design of ANN with Levenberg-Marquardt algorithm to increase the accuracy in predicting the viscosity of SAE40 oil-based hybrid nano-lubricant. Powder Technol. 2023, 415, 118097. [Google Scholar] [CrossRef]
- Sharma, G.; Kotia, A.; Ghosh, S.K.; Rana, P.S.; Bawa, S.; Ali, M.K.A. Kinematic viscosity prediction of nanolubricants employed in heavy earth moving machinery using machine learning techniques. Int. J. Precis. Eng. Manuf. 2020, 21, 1921–1932. [Google Scholar] [CrossRef]
- Qing, H.; Hamedi, S.; Eftekhari, S.A.; Alizadeh, S.M.; Toghraie, D.; Hekmatifar, M.; Ahmed, A.N.; Khan, A. A well-trained feed-forward perceptron Artificial Neural Network (ANN) for prediction the dynamic viscosity of Al2O3–MWCNT (40:60)-Oil SAE50 hybrid nano-lubricant at different volume fraction of nanoparticles, temperatures, and shear rates. Int. Commun. Heat Mass Transf. 2021, 128, 105624. [Google Scholar] [CrossRef]
Ref. | Methodology | Input/Output Parameter | Base Oil/Additive | Performance |
---|---|---|---|---|
[29] | ANN, GA | Load, speed, concentration/ CoF | NCO, CMO/ GRT, MWCNT, GRPHN, ZnO | CoF ↓ by 45–50% WSD ↓ by 87.5% |
[30] | FF-ANN | Concentration/ CoF | Regular diesel fuel/ Sunflower oil, Rapeseed oil | CoF: 1.56 × 10−3 with 4% sunflower oil |
[31] | ANN | Temperature, volume fraction, shear rate/Viscosity prediction | SAE68 hydraulic oil/ MWCNT, SiO2 | R2: 0.998 RMSE: 2.135415 |
[32] | LM-based MLP | Temperature, volume fraction, shear rate/Viscosity prediction | SAE40/ MWCNT, Al2O3 | R: 0.9999 MSE: 6.15 × 10−4 −2% < MOD < 2% |
[33] | DT, RF, GLM, ANN | Temperature, volume fraction/ Kinematic viscosity prediction | SAE30, Hydrex100, EP90/ Al2O3, CeO2 | R2: 0.861 (SAE30) R2: 0.971 (Hydrex100) R2: 0.973 (EP90) |
[34] | LM-ANN | Temperature, volume fraction, shear rate/Viscosity prediction | SAE50/ MWCNT, Al2O3 | MSE: 3.58 R: 0.999 |
Parameters | Minimum | Maximum | Average |
---|---|---|---|
SiO2 NP concentration (wt%) | 0.2 | 0.4 | 0.3 |
NG NP concentration (wt%) | 0.2 | 0.4 | 0.3 |
Load (N) | 30 | 50 | 40 |
Speed (RPM) | 35 | 100 | 58 |
Coefficient of friction | 0.02 | 0.3 | 0.16 |
Optimization Variable (Hyperparameter) | Search Range for Optimization |
---|---|
Number of hidden layers | |
Number of neurons in 1st, 2nd, 3rd hidden layers | for each layer |
L2 Regularization strength | |
Activation function |
ANN Model | Optimized Model Hyperparameters and Convergence Results | |||||||
---|---|---|---|---|---|---|---|---|
Hidden Layer Size | Activation Function | Validation MSE at Epoch | Iterations | Training Loss | Gradient | Training Time (s) | ||
SiO2 NP | 10 | sigmoid | 0 | 7.81 × 10−4 at 37 | 43 | 52.31 × 10−4 | 7.02 × 10−4 | 213 |
NG NP | 4 | sigmoid | 0 | 5.89 × 10−4 at 27 | 33 | 2.02 × 10−4 | 10.01 × 10−4 | 188 |
Multi-NP | 2 | sigmoid | 0.11 × 10−4 | 1.44 × 10−4 at 22 | 28 | 5.97 × 10−4 | 3.96 × 10−4 | 142 |
Regression Model | Nanoparticle | Performance Assessment Metrics (10-Fold Cross-Validation) | |||
---|---|---|---|---|---|
RMSE | R2 | MSE | MAE | ||
Random Forest Trees | SiO2 | 8.8662 × 10−3 | 0.7373 | 7.8609 × 10−5 | 7.9509 × 10−3 |
NG | 6.7444 × 10−2 | 0.7778 | 4.5487 × 10−3 | 6.3266 × 10−2 | |
Support Vector Machines | SiO2 | 2.2689 × 10−3 | 0.9790 | 5.1481 × 10−6 | 2.1874 × 10−3 |
NG | 3.2127 × 10−2 | 0.9727 | 1.0321 × 10−3 | 1.8183 × 10−2 | |
Artificial Neural Network | SiO2 | 2.2181 × 10−3 | 0.9753 | 4.9199 × 10−6 | 2.1026 × 10−3 |
NG | 4.2407 × 10−2 | 0.9909 | 1.7983 × 10−3 | 3.1608 × 10−2 | |
Hybrid | 3.6296 × 10−2 | 0.9546 | 1.3174 × 10−3 | 2.3902 × 10−2 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Usman, A.; Arif, S.; Raja, A.H.; Kouhia, R.; Almqvist, A.; Liwicki, M. Machine Learning Composite-Nanoparticle-Enriched Lubricant Oil Development for Improved Frictional Performance—An Experiment. Lubricants 2023, 11, 254. https://doi.org/10.3390/lubricants11060254
Usman A, Arif S, Raja AH, Kouhia R, Almqvist A, Liwicki M. Machine Learning Composite-Nanoparticle-Enriched Lubricant Oil Development for Improved Frictional Performance—An Experiment. Lubricants. 2023; 11(6):254. https://doi.org/10.3390/lubricants11060254
Chicago/Turabian StyleUsman, Ali, Saad Arif, Ahmed Hassan Raja, Reijo Kouhia, Andreas Almqvist, and Marcus Liwicki. 2023. "Machine Learning Composite-Nanoparticle-Enriched Lubricant Oil Development for Improved Frictional Performance—An Experiment" Lubricants 11, no. 6: 254. https://doi.org/10.3390/lubricants11060254
APA StyleUsman, A., Arif, S., Raja, A. H., Kouhia, R., Almqvist, A., & Liwicki, M. (2023). Machine Learning Composite-Nanoparticle-Enriched Lubricant Oil Development for Improved Frictional Performance—An Experiment. Lubricants, 11(6), 254. https://doi.org/10.3390/lubricants11060254