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 many different areas scientific research. Despite the rapid expansion application networks, few efforts have been carried out to introduce such powerful tool into lubrication studies. Thus, this work aims apply physics-informed (PINN) hydrodynamic analysis. 2D Reynolds equation is solved. PINN meshless method and does not require big data for training compared with classical methods. Our results are consistent those obtained by experiments finite element method. Hence, we envision that will great potential bearing