Classical hydrodynamic lubrication simulation solves Reynolds equation to unveil the lubrication pressure and film thickness distributions, yet it overlooks the latent high-level representations buried beneath the lubrication data. While deep learning has illustrated that the mining of high-level representations helps to generate desired outputs from input prompts, the lubrication research, however, has not fully exploited generative deep learning in lubrication prediction and generation. Here, we propose to adopt a deconvolutional neural network to learn the latent representations in hydrodynamic lubrication data and directly generate 2D lubrication scenario from the given working condition without solving any governing equation. Compared to classical method, our approach can output the distribution of lubrication pressure and film thickness in less than 0.1 s on a personal computer and be extended to more complicated scenarios including cavitation.

Physics-informed neural network (PINN) provides a novel method for understanding the mechanical behavior of tribology contacts, and 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 the PINN for obtaining elastic deformations under Hertzian pressure. The PINN obtains the elastic deformation by transforming the linear elasticity equation into an optimized neural network, which presents a new method for obtaining elastic deformation in tribological contacts. Our results are consistent with the results from finite element method. Hence, we envision that our method has great application potential in dry and EHL contacts in the prediction of elastic deformation.

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.