Weighted physics-informed neural network (Weighted PINN) for obtaining elastic responses under Hertzian-like contact

Physics-informed neural network (PINN) provides a novel method towards the understanding of mechanical behaviour in tribology contacts where the deformation of the contacting body plays a pivotal role in determining the contact scenario of dry and elastohydrodynamic lubricated (EHL) contacts. Here, we delineate the design and construction of PINN for obtaining elastic deformations under Hertzian pressure. PINN obtains the elastic deformation by transforming the linear elasticity equation into optimizing a neural network, which presents a new method towards obtaining elastic deformation in tribological contacts. Our results are consistent with finite element method’s results. Hence, we envision our method provides great application potential in dry and EHL contacts in the prediction of elastic deformations.