Distortion Prediction in Powder Bed Fusion Process using Data Driven Methods

Abstract

Metal additive manufacturing (AM) paves the way for industries to create new applications through unique design capabilities. The powder bed fusion process is one among many metal additive manufacturing technologies that are commercially successful. Despite its numerous advantages and application in various fields, defects may occur during processing, which causes premature failure of components. Distortion is one of the major defects, and it depends on the process settings, geometry, and the orientation. These distortions and dimensional deviations should be predicted faster for part qualification for many industrial applications. Understanding the temperature field evolution is essential in metal additive manufacturing process like PBF technology to produce the right quality parts. As the process of metal AM involves physical phenomena, including fluid flow, heat and mass transfer, as well as structural loads, the underlying physics is complex and difficult to predict temperature fields in reasonable time with increased accuracy. Physical experiments and numerical simulations can be expensive and time-consuming. Hence a data-driven approach has been introduced to address the issue of increased computational time to predict the thermal field developed during the process. The methodology proposed in this work consists of a surrogate thermal model based on Gaussian Process Regression (GPR). Initially, the transient thermal behaviour is studied based on Finite Element analysis (FE). Later, a surrogate model based on the GPR is developed from the FE simulated data to decrease the computational costs of highfidelity physics-based simulations. The GPR model has predicted the thermal fields in less time than that of the physics-based FEA model. To validate our approach, both the numerical simulations and GPR-based model are justified by conducting single-track experimentations using Inconel 625 (IN625).