Predicting Hydraulic Oil Thermophysical Properties Using Physics-Informed Neural Networks
DOI:
https://doi.org/10.13052/ijfp1439-9776.2513Keywords:
Hydraulic oil, thermophysical properties, physics informed neural networksAbstract
The thermophysical properties of hydraulic oil, density, viscosity, thermal expansion, and compressibility, are pivotal factors influencing the functioning of hydraulic systems. With the multitude of hydraulic oils available for use, conducting numerous experiments to determine their specifications under different temperatures and pressures, or devising new empirical correlations, becomes a costly and time-consuming endeavour. Therefore, it becomes imperative to establish an efficient and comprehensive model based on minimal experimental data. This study adopts Physics Informed Neural Networks (PINNs) to design new correlation model to predict variations in hydraulic oil specifications using only 30 empirical data sets as a best-case scenario, enabling the prediction of 10,000 points spanning temperatures (20–100)∘C and pressures (0–300) bar. The results derived from the PINN model exhibit favourable high accuracy, reaching up to 99.96% when compared to empirical correlations results.
Downloads
References
Totten, G.E.; Negri, V.J.D. Handbook of Hydraulic Fluid Technology; CRC Press, 2011; ISBN 978-1-4200-8527-3.
Bair, S.; Michael, P. Modelling the Pressure and Temperature Dependence of Viscosity and Volume for Hydraulic Fluids. International Journal of Fluid Power 2010, 11, 37–42, doi:10.1080/14399776.2010.107 81005.
Hodges, P. Hydraulic Fluids; Butterworth-Heinemann, 1996; ISBN 978-0-08-052389-7.
Osterland, S.; Müller, L.; Weber, J. Influence of Air Dissolved in Hydraulic Oil on Cavitation Erosion. International Journal of Fluid Power 2021, doi:10.13052/ijfp1439-9776.2234.
Zhang, J.; Qi, N.; Jiang, J. Effect of Oil Viscosity on Hydraulic Cavitation Luminescence. Fluid Dyn 2021, 56, 371–382, doi:10.1134/S00154 62821030125.
Afrand, M.; Nazari Najafabadi, K.; Sina, N.; Safaei, M.R.; Kherbeet, A.Sh.; Wongwises, S.; Dahari, M. Prediction of Dynamic Viscosity of a Hybrid Nano-Lubricant by an Optimal Artificial Neural Network. International Communications in Heat and Mass Transfer 2016, 76, 209–214, doi:10.1016/j.icheatmasstransfer.2016.05.023.
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. International Communications in Heat and Mass Transfer 2020, 116, 104723, doi:10.1016/j.icheatmasstransfer.2020.104723.
Loh, G.C.; Lee, H.-C.; Tee, X.Y.; Chow, P.S.; Zheng, J.W. Viscosity Prediction of Lubricants by a General Feed-Forward Neural Network. J. Chem. Inf. Model. 2020, 60, 1224–1234, doi:10.1021/acs.jcim.9b01068.
Pan, B.; Zhu, Y.; Wang, C.; Su, S. A Process Neural Network Model for Calculation of Heavy Oil Viscosity in High Water Cut Stage. Petroleum Science and Technology 2018, 36, 313–318, doi:10.1080/10916466.2017.1421973.
Alade, O.; Al Shehri, D.; Mahmoud, M.; Sasaki, K. Viscosity–Temperature–Pressure Relationship of Extra-Heavy Oil (Bitumen): Empirical Modelling versus Artificial Neural Network (ANN). Energies 2019, 12, 2390, doi:10.3390/en12122390.
Omole, O.; Falode, O.A.; Deng, A.D. Prediction of Nigerian Crude Oil Viscosity Using Artificial Neural Network. Petroleum & Coal 2009, 51, 181–188.
Torabi, F.; Abedini, A.; Abedini, R. The Development of an Artificial Neural Network Model for Prediction of Crude Oil Viscosities. Petroleum Science and Technology 2011, 29, 804–816, doi:10.1080/10916460903485876.
Makinde, F.A.; Ako, C.T.; Orodu, O.D.; Asuquo, I.U. Prediction of Crude Oil Viscosity Using Feed-Forward Back-Propagation Neural Network (FFBPNN). Petroleum & Coal 2012, 54.
Lashkenari, M.S.; Taghizadeh, M.; Mehdizadeh, B. Viscosity Prediction in Selected Iranian Light Oil Reservoirs: Artificial Neural Network versus Empirical Correlations. Pet. Sci. 2013, 10, 126–133, doi:10.1007/s12182-013-0259-4.
Ghorbani, B.; Hamedi, M.; Shirmohammadi, R.; Mehrpooya, M.; Hamedi, M.-H. A Novel Multi-Hybrid Model for Estimating Optimal Viscosity Correlations of Iranian Crude Oil. Journal of Petroleum Science and Engineering 2016, 142, 68–76, doi:10.1016/j.petrol.2016.01.041.
Hadavimoghaddam, F.; Ostadhassan, M.; Heidaryan, E.; Sadri, M.A.; Chapanova, I.; Popov, E.; Cheremisin, A.; Rafieepour, S. Prediction of Dead Oil Viscosity: Machine Learning vs. Classical Correlations. Energies 2021, 14, 930, doi:10.3390/en14040930.
Gao, X.; Dong, P.; Cui, J.; Gao, Q. Prediction Model for the Viscosity of Heavy Oil Diluted with Light Oil Using Machine Learning Techniques. Energies 2022, 15, 2297, doi:10.3390/en15062297.
Witt, K.K. Die Berechnung physikalischer und thermodynamischer Kennwerte von Druckflüssigkeiten, sowie die Bestimmung des Gesamtwirkungsgrades an Pumpen unter Berücksichtigung der Thermodynamik für die Druckflüssigkeit. Ph.D. Thesis, Technische Hogeschool Eindhoven, 1974.
Hamrock, B.J.; Dowson, D. Ball Bearing Lubrication: The Elastohydrodynamics of Elliptical Contacts; 1981;
Sargent, L.B. Pressure-Viscosity Coefficients of Liquid Lubricants. A S L E Transactions 1983, 26, 1–10, doi:10.1080/05698198308981471.
Furbish, D.J. Fluid Physics in Geology: An Introduction to Fluid Motions on Earth’s Surface and within Its Crust; Oxford University Press, 1996; ISBN 978-0-19-536028-8.
Bair, S. Temperature and Pressure Dependence of Density and Thermal Conductivity of Liquids. In Encyclopedia of Tribology; Wang, Q.J., Chung, Y.-W., Eds.; Springer US: Boston, MA, 2013; pp. 3527–3533 ISBN 978-0-387-92896-8.
Ketelsen, S.; Michel, S.; Andersen, T.O.; Ebbesen, M.K.; Weber, J.; Schmidt, L. Thermo-Hydraulic Modelling and Experimental Validation of an Electro-Hydraulic Compact Drive. Energies 2021, 14, 2375, doi:10.3390/en14092375.
Dobrota, Ð.; Barle, J.; Bilić, B. Modeling of High-Pressure External Gear Pump.; 2011; pp. 83–91.
Gold, P.W.; Schmidt, A.; Dicke, H.; Loos, J.; Assmann, C. Viscosity–Pressure–Temperature Behaviour of Mineral and Synthetic Oils. Journal of Synthetic Lubrication 2001, 18, 51–79, doi:10.1002/jsl.3000180105.
Manning, R.E. Computational Aids for Kinematic Viscosity Conversions from 100 to 210∘
F to 40 and 100∘
C. J. Test. Eval. 1974, 2, 522–528, doi:10.1520/JTE11686J.
Stachowiak, G.; Batchelor, A.W. Engineering Tribology; Butterworth-Heinemann: USA, 2001; ISBN 978-0-7506-7304-4.
American Petroleum Institute, Technical Data Book Petroleum Refining; 1997;
Barus, C. ART. X.–Isothermals, Isopiestics and Isometrics Relative to Viscosity; American Journal of Science (1880-1910) 1893, 45, 87.
Roelands, C.J.A.; Vlugter, J.C.; Waterman, H.I. The Viscosity-Temperature-Pressure Relationship of Lubricating Oils and Its Correlation With Chemical Constitution. Journal of Basic Engineering 1963, 85, 601–607, doi:10.1115/1.3656919.
Cai, S.; Mao, Z.; Wang, Z.; Yin, M.; Karniadakis, G.E. Physics-Informed Neural Networks (PINNs) for Fluid Mechanics: A Review. Acta Mech. Sin. 2021, 37, 1727–1738, doi:10.1007/s10409-021- 01148-1.
Guo, Y.; Cao, X.; Liu, B.; Gao, M. Solving Partial Differential Equations Using Deep Learning and Physical Constraints. Applied Sciences 2020, 10, 5917, doi:10.3390/app10175917.
Karniadakis, G.E.; Kevrekidis, I.G.; Lu, L.; Perdikaris, P.; Wang, S.; Yang, L. Physics-Informed Machine Learning. Nat Rev Phys 2021, 3, 422–440, doi:10.1038/s42254-021-00314-5.
Skripov, V.P.; Faizullin, M.Z. Crystal-Liquid-Gas Phase Transitions and Thermodynamic Similarity; John Wiley & Sons, 2006;
Shchekin, A.K.; Shabaev, I.V. In Nucleation Theory and Applications, Edited by JWP Schmelzer, G. Röpke, and VB Priezzhev (JINR, Dubna, 2005) 2005, 267.
Schmelzer, J.W.P.; Zanotto, E.D.; Fokin, V.M. Pressure Dependence of Viscosity. The Journal of Chemical Physics 2005, 122, 074511, doi:10.1063/1.1851510.
Kashefi, A.; Mukerji, T. Physics-Informed PointNet: A Deep Learning Solver for Steady-State Incompressible Flows and Thermal Fields on Multiple Sets of Irregular Geometries. Journal of Computational Physics 2022, 468, 111510, doi:10.1016/j.jcp.2022.111510.
Eivazi, H.; Tahani, M.; Schlatter, P.; Vinuesa, R. Physics-Informed Neural Networks for Solving Reynolds-Averaged Navier–Stokes Equations. Physics of Fluids 2022, 34, 075117, doi:10.1063/5.0095270.
Jagtap, A.D.; Kawaguchi, K.; Karniadakis, G.E. Adaptive Activation Functions Accelerate Convergence in Deep and Physics-Informed Neural Networks. Journal of Computational Physics 2020, 404, 109136, doi:10.1016/j.jcp.2019.109136.
Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. 2014, doi:10.48550/ARXIV.1412.6980.
Baydin, A.G.; Pearlmutter, B.A.; Radul, A.A.; Siskind, J.M. Automatic Differentiation in Machine Learning: A Survey. 2015, doi:10.48550/ ARXIV.1502.05767.
Shin, Y.; Darbon, J.; Karniadakis, G.E. On the Convergence of Physics Informed Neural Networks for Linear Second-Order Elliptic and Parabolic Type PDEs. 2020, doi:10.48550/ARXIV.2004.01806.
Knežević, D.; Savić, V. Mathematical Modeling of Changing of Dynamic Viscosity, as a Function of Temperature and Pressure, of Mineral Oils for Hydraulic Systems. Facta universitatis - series: Mechanical Engineering 2006, 4, 27–34.
Technical Data Sheet, 77 Lubricants Available online: https:/www.77lubricants.nl/en/ (accessed on 8 July 2023).
Persson, B.N.T. History of Tribology. In Encyclopedia of Lubricants and Lubrication; Mang, T., Ed.; Springer: Berlin, Heidelberg, 2014; pp. 791–797 ISBN 978-3-642-22647-2.
Technical Data Sheet, Castrol Available online: https:/www.castrol.com/en/global/corporate.html (accessed on 14 July 2023).
