A Novel Framework of Developing a Predictive Model for Powder Bed Fusion Process

Abstract

The powder bed fusion (PBF) process is a metal additive manufacturing process, which can build parts with any complexity from a wide range of metallic materials. PBF process research has predominantly focused on the impact of only a few parameters on product properties due to the lack of a systematic approach for predictive modeling of a large set of process parameters simultaneously. The pivotal challenges regarding this process require a quantitative approach for mapping the material properties and process parameters onto the ultimate quality; this will then enable the optimization of those parameters. In this study, we propose a two-phase framework for studying the process parameters and developing a predictive model for 316L stainless steel material. We also discuss the correlation between process parameters that is, laser specifications and mechanical properties, and how to obtain an optimum range of volumetric energy density for producing parts with high density (>99%), as well as better ultimate mechanical properties. In this article, we introduce and test an innovative approach for developing AM predictive models, with a relatively low error percentage (i.e., around 10%), which are used for process parameter selection in accordance with user or manufacturer part performance requirements. These models are based on techniques such as support vector regression, random forest regression, and neural network. It is shown that the intelligent selection of process parameters using these models can achieve a high density of up to 99.31% with uniform microstructure, which improves hardness, impact strength, and other mechanical properties.