Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approach
Abstract A comprehensive understanding of the dynamics of tribological interactions is essential for enhancing efficiency and durability in a multitude of technical domains. Conventional experimental techniques in tribology are frequently costly and time-consuming. In contrast, elastohydrodynamic lu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Advanced Modeling and Simulation in Engineering Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40323-025-00283-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571489085292544 |
|---|---|
| author | Faras Brumand-Poor Freddy Kokou Azanledji Nils Plückhahn Florian Barlog Lukas Boden Katharina Schmitz |
| author_facet | Faras Brumand-Poor Freddy Kokou Azanledji Nils Plückhahn Florian Barlog Lukas Boden Katharina Schmitz |
| author_sort | Faras Brumand-Poor |
| collection | DOAJ |
| description | Abstract A comprehensive understanding of the dynamics of tribological interactions is essential for enhancing efficiency and durability in a multitude of technical domains. Conventional experimental techniques in tribology are frequently costly and time-consuming. In contrast, elastohydrodynamic lubrication (EHL) simulation models present a viable alternative for calculating frictional forces in sealing contacts. These calculations are based on the hydrodynamics within the sealing contact, as defined by the Reynolds equation, the deformation of the seal, and the contact mechanics. However, a significant drawback of these simulations is the time-consuming calculation process. To overcome these experimental and computational limitations, machine learning algorithms offer a promising solution. Physics-informed machine learning (PIML) improves on traditional data-driven models by incorporating physical principles. In particular, physics-informed neural networks (PINNs) are as effective hybrid solvers that combine data-driven and physics-based methods to solve the partial differential equations that drive EHL simulations. By integrating physical laws into the parameter optimization of the neural network (NN), PINNs provide accurate and fast solutions. Thus, unlike traditional NNs, PINNs have the potential to make accurate predictions beyond the limited training domain. The objective of this study is to demonstrate the feasibility of spatial and temporal extrapolation of the PINN and to analyze its reliability, both with and without consideration of cavitation. Two test cases are employed to examine the pressure and cavitation distribution within a sealing contact that extends beyond the spatial and temporal training range. The findings indicate that PINNs can surmount the typical constraints associated with NNs in the extrapolation of solution spaces, which represents a notable advancement in terms of computational efficiency and model flexibility. |
| format | Article |
| id | doaj-art-ffaf4250b56d4c3eaa11d4dfd4f49b00 |
| institution | Kabale University |
| issn | 2213-7467 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Advanced Modeling and Simulation in Engineering Sciences |
| spelling | doaj-art-ffaf4250b56d4c3eaa11d4dfd4f49b002025-02-02T12:34:25ZengSpringerOpenAdvanced Modeling and Simulation in Engineering Sciences2213-74672025-01-0112113410.1186/s40323-025-00283-9Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approachFaras Brumand-Poor0Freddy Kokou Azanledji1Nils Plückhahn2Florian Barlog3Lukas Boden4Katharina Schmitz5RWTH Aachen University, Institute for Fluid Power Drives and Systems (ifas)RWTH Aachen University, Institute for Fluid Power Drives and Systems (ifas)RWTH Aachen University, Institute for Fluid Power Drives and Systems (ifas)RWTH Aachen University, Institute for Fluid Power Drives and Systems (ifas)RWTH Aachen University, Institute for Fluid Power Drives and Systems (ifas)RWTH Aachen University, Institute for Fluid Power Drives and Systems (ifas)Abstract A comprehensive understanding of the dynamics of tribological interactions is essential for enhancing efficiency and durability in a multitude of technical domains. Conventional experimental techniques in tribology are frequently costly and time-consuming. In contrast, elastohydrodynamic lubrication (EHL) simulation models present a viable alternative for calculating frictional forces in sealing contacts. These calculations are based on the hydrodynamics within the sealing contact, as defined by the Reynolds equation, the deformation of the seal, and the contact mechanics. However, a significant drawback of these simulations is the time-consuming calculation process. To overcome these experimental and computational limitations, machine learning algorithms offer a promising solution. Physics-informed machine learning (PIML) improves on traditional data-driven models by incorporating physical principles. In particular, physics-informed neural networks (PINNs) are as effective hybrid solvers that combine data-driven and physics-based methods to solve the partial differential equations that drive EHL simulations. By integrating physical laws into the parameter optimization of the neural network (NN), PINNs provide accurate and fast solutions. Thus, unlike traditional NNs, PINNs have the potential to make accurate predictions beyond the limited training domain. The objective of this study is to demonstrate the feasibility of spatial and temporal extrapolation of the PINN and to analyze its reliability, both with and without consideration of cavitation. Two test cases are employed to examine the pressure and cavitation distribution within a sealing contact that extends beyond the spatial and temporal training range. The findings indicate that PINNs can surmount the typical constraints associated with NNs in the extrapolation of solution spaces, which represents a notable advancement in terms of computational efficiency and model flexibility.https://doi.org/10.1186/s40323-025-00283-9Cavitation extrapolationElastohydrodynamic lubrication simulationHydrodynamic pressure extrapolationPhysics-informed machine learningPhysics-informed neural networksPneumatic sealing |
| spellingShingle | Faras Brumand-Poor Freddy Kokou Azanledji Nils Plückhahn Florian Barlog Lukas Boden Katharina Schmitz Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approach Advanced Modeling and Simulation in Engineering Sciences Cavitation extrapolation Elastohydrodynamic lubrication simulation Hydrodynamic pressure extrapolation Physics-informed machine learning Physics-informed neural networks Pneumatic sealing |
| title | Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approach |
| title_full | Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approach |
| title_fullStr | Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approach |
| title_full_unstemmed | Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approach |
| title_short | Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approach |
| title_sort | extrapolation of cavitation and hydrodynamic pressure in lubricated contacts a physics informed neural network approach |
| topic | Cavitation extrapolation Elastohydrodynamic lubrication simulation Hydrodynamic pressure extrapolation Physics-informed machine learning Physics-informed neural networks Pneumatic sealing |
| url | https://doi.org/10.1186/s40323-025-00283-9 |
| work_keys_str_mv | AT farasbrumandpoor extrapolationofcavitationandhydrodynamicpressureinlubricatedcontactsaphysicsinformedneuralnetworkapproach AT freddykokouazanledji extrapolationofcavitationandhydrodynamicpressureinlubricatedcontactsaphysicsinformedneuralnetworkapproach AT nilspluckhahn extrapolationofcavitationandhydrodynamicpressureinlubricatedcontactsaphysicsinformedneuralnetworkapproach AT florianbarlog extrapolationofcavitationandhydrodynamicpressureinlubricatedcontactsaphysicsinformedneuralnetworkapproach AT lukasboden extrapolationofcavitationandhydrodynamicpressureinlubricatedcontactsaphysicsinformedneuralnetworkapproach AT katharinaschmitz extrapolationofcavitationandhydrodynamicpressureinlubricatedcontactsaphysicsinformedneuralnetworkapproach |