Evaluation of Machine Learning Models for Enhancing Sutainability in Additive Manufacturing

This paper investigates sustainability of additive manufacturing (AM) processes using machine learning (ML). Although AM is recognized as more sustainable than traditional manufacturing, the existing approaches to study AM sustainability are often time-consuming and resource intensive. This research fills the gap by directly linking AM parameters with sustainability metrics. Our research proposes a data-driven approach to predict sustainability outcomes and optimize AM processes. ML models of Linear Regression, Decision Trees, Random Forest and Gradient Boosting are evaluated to build a comprehensive framework which can understand AM process parameters and their effects on the AM sustainability. The findings demonstrate that ML can accurately predict AM sustainability based on relationships of AM parameters and their effects on sustainability. The optimal parameters can reduce the energy consumption and material waste in AM process. This work offers a scalable and efficient method to enhance AM sustainability. The results contribute to advancing sustainable AM practices and provide a foundation for the future exploration into broader AM processes.