Application of physics-informed neural network in the analysis of hydrodynamic lubrication

Abstract The last decade has witnessed a surge of interest in artificial neural network in many different areas of scientific research. Despite the rapid expansion in the application of neural networks, few efforts have been carried out to introduce such a powerful tool into lubrication studies. Thu...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Zhao, Liang Guo, Patrick Pat Lam Wong
Format: Article
Language:English
Published: Tsinghua University Press 2022-09-01
Series:Friction
Subjects:
Online Access:https://doi.org/10.1007/s40544-022-0658-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850230301027991552
author Yang Zhao
Liang Guo
Patrick Pat Lam Wong
author_facet Yang Zhao
Liang Guo
Patrick Pat Lam Wong
author_sort Yang Zhao
collection DOAJ
description Abstract The last decade has witnessed a surge of interest in artificial neural network in many different areas of scientific research. Despite the rapid expansion in the application of neural networks, few efforts have been carried out to introduce such a powerful tool into lubrication studies. Thus, this work aims to apply the physics-informed neural network (PINN) to the hydrodynamic lubrication analysis. The 2D Reynolds equation is solved. The PINN is a meshless method and does not require big data for network training compared with classical methods. Our results are consistent with those obtained by experiments and the finite element method. Hence, we envision that the PINN method will have great application potential in lubrication and bearing research.
format Article
id doaj-art-213403a7522946418b5219adb9e3644e
institution OA Journals
issn 2223-7690
2223-7704
language English
publishDate 2022-09-01
publisher Tsinghua University Press
record_format Article
series Friction
spelling doaj-art-213403a7522946418b5219adb9e3644e2025-08-20T02:03:55ZengTsinghua University PressFriction2223-76902223-77042022-09-011171253126410.1007/s40544-022-0658-xApplication of physics-informed neural network in the analysis of hydrodynamic lubricationYang Zhao0Liang Guo1Patrick Pat Lam Wong2School of Automotive and Transportation Engineering, Shenzhen PolytechnicSchool of Mechatronic Engineering and Automation, Shanghai UniversityDepartment of Mechanical Engineering, City University of Hong KongAbstract The last decade has witnessed a surge of interest in artificial neural network in many different areas of scientific research. Despite the rapid expansion in the application of neural networks, few efforts have been carried out to introduce such a powerful tool into lubrication studies. Thus, this work aims to apply the physics-informed neural network (PINN) to the hydrodynamic lubrication analysis. The 2D Reynolds equation is solved. The PINN is a meshless method and does not require big data for network training compared with classical methods. Our results are consistent with those obtained by experiments and the finite element method. Hence, we envision that the PINN method will have great application potential in lubrication and bearing research.https://doi.org/10.1007/s40544-022-0658-xphysics-informed neural networkhydrodynamic lubricationslider bearing
spellingShingle Yang Zhao
Liang Guo
Patrick Pat Lam Wong
Application of physics-informed neural network in the analysis of hydrodynamic lubrication
Friction
physics-informed neural network
hydrodynamic lubrication
slider bearing
title Application of physics-informed neural network in the analysis of hydrodynamic lubrication
title_full Application of physics-informed neural network in the analysis of hydrodynamic lubrication
title_fullStr Application of physics-informed neural network in the analysis of hydrodynamic lubrication
title_full_unstemmed Application of physics-informed neural network in the analysis of hydrodynamic lubrication
title_short Application of physics-informed neural network in the analysis of hydrodynamic lubrication
title_sort application of physics informed neural network in the analysis of hydrodynamic lubrication
topic physics-informed neural network
hydrodynamic lubrication
slider bearing
url https://doi.org/10.1007/s40544-022-0658-x
work_keys_str_mv AT yangzhao applicationofphysicsinformedneuralnetworkintheanalysisofhydrodynamiclubrication
AT liangguo applicationofphysicsinformedneuralnetworkintheanalysisofhydrodynamiclubrication
AT patrickpatlamwong applicationofphysicsinformedneuralnetworkintheanalysisofhydrodynamiclubrication