Simulation of the temperature gradient in laser-based powder bed fusion using machine learning

Abstract

Laser-based powder bed fusion of metals (PBF-LB/M) is an additive manufacturing (AM) process for producing metal components. In current works, the simulation of the temperature gradient (TG) of PBF-LB/M is done by solving partial differential equations (PDEs) that describe the heat transfer between a laser beam and a powder bed. However, solving PDEs is time-consuming, especially when the number of mesh elements is large. Therefore, we have used machine learning to realize TG simulations, which is faster than solving PDEs. We have considered TG simulation as a problem of semantic segmentation and have studied five state-of-the-art machine learning models.