Abstract
Porous aerostatic bearings as a new type of supporting component used in ultraprecision equipment. The study of porous models is essential as they are a basis for porous aerostatic bearings. However, the effects of micropore structure and flow state inside a material have not been addressed in previous studies. Herein, we propose a high-accuracy and low-cost method using deep learning to reconstruct a three-dimensional (3D) porous model and obtain the 3D flow state inside a porous material. It can reveal richer flow states such as the flow track and movement in three directions, which have not been revealed previously. This new method is effective for studying the properties of porous materials, micro-flow state, and simulation of parameters in detail.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
