Machine Learning-Enhanced Process Parameter Optimization and Microstructure Prediction in Additive Manufacturing

Abstract

Additive manufacturing (AM) is revolutionizing the production of three-dimensional objects by converting digital design into physical forms, offering benefits such as intricate shapes, lighter products, and reduced energy consumption compared to traditional methods. However, AM faces challenges like high equipment and material costs, long printing times, and limited material variety, which hinder widespread adoption and complicated process optimization. Investment in expensive 3D printers and materials, along with printing times from hours to days, are significant obstacles to mass production. To address these challenges, machine learning offers a solution by using algorithms to create optimal models and predict material properties, thereby expediting the optimization process. In AM, complex physical reactions and cooling rates can lead to deformations and defects that impact part quality and strength. This complexity is magnified in multi-layer, multi-track printing, requiring careful monitoring of melt pool morphology and defects. Fine-grained microstructure analysis is crucial for tailoring materials to specific performance requirements. Machine learning and deep learning, through data-driven modeling, provide a rapid path and potential for optimization. This dissertation explores accelerating AM optimization and underlines the pivotal role of machine learning in overcoming the associated challenges.