Exploring Machine Learning Tools for Enhancing Additive Manufacturing: A Comparative Study

Abstract

Additive Manufacturing (AM), a technique leveraging 3D modeling data to fabricate objects through layer-by-layer material deposition, has seen a surge in adoption across industries. This has, in turn, spurred rapid advancements in design, process, and manufacturing technologies integral to AM. Simultaneously, Machine Learning (ML), a subset of artificial intelligence centered on enabling self-improvement in computer programs, has carved its niche in this burgeoning field. This review provides an in-depth exploration of recent advancements in the application of ML within the AM framework. Specifically, the focus is placed on regression, classification, and clustering tasks integral to anomaly identification and parameter optimization in AM processes. A comparative analysis of the efficacy of various ML algorithms in executing these tasks forms the crux of this review. In light of these developments, the paper seeks to underscore the potential of ML as a viable tool in augmenting the capabilities of AM, thereby offering insights that could guide future research and development efforts in this interdisciplinary domain.