Towards a Selective Laser Melting Process Parameters Optimization Approach using Regression Algorithms for Inconel 718 Manufactured Parts

Abstract

In recent decades, Additive Manufacturing (AM) technologies have received increasing interest from both academia and industry. Thanks to an unprecedented opportunity to create designs and products difficult to create through conventional manufacturing processes, such as those from subtractive manufacturing, the understanding of these processes have become imperative for the creation of reliable products. Different processes may produce parts from different materials, and from the many processes available, Powder Bed Fusion (PBF) stands out for its capacity to produce high-quality products with metallic alloys. From these metallic alloys, nickel-based superalloys are of particular interest for the aerospace and defence industry, because it possesses excellent mechanical properties during high-performance applications, such as those found in turbines, where high stresses and high temperatures bring design and engineering to its limits. Novel crystallographic structures, process complexity, and mechanical defects are but a few of the challenges AM technologies face to produce consistent and reliable parts. Selective Laser Melting (SLM), a subprocess of PBF, has been found to produce defects such as porosities and rough surfaces on additively manufactured parts, which have been found to hinder the fatigue life of as-built products. This research attempts to understand the relationships between variables involved in the SLM process and the formation of these defects. To achieve this, a literature review is realized to create a causal-loop that helps to understand the impact and correlation between the variables involved in the process, and their effect on the mechanical properties of the part. A compilation of governing equations, boundary conditions, and loads was also reviewed to allow the simulation of the SLM process on a Finite Element (FE) environment. Finally, regression analysis is made to determine the significance of the impact the process parameters and temperature gradients determined through the FE Analysis have over the mechanical defects. Recommendations based on this analysis for optimal process parameters values are given. Further research is required to analyse the impact of process parameters on the formation of residual stresses and crack formation.