Abstract
Additive manufacturing (AM) has revolutionized the aerospace industry by enabling the production of lightweight and high-strength components, such as aerospace engine components and structural elements. The ability to create complex geometries and reduce material waste is particularly beneficial for aerospace applications, where performance and weight reduction are paramount. However, ensuring the quality and reliability of these components remains a challenge, particularly in mass production, which is related to material quality, expensive processes, and longer computational times than conventional manufacturing methods. This paper proposes an approach utilizing a Decision Tree Classification Machine Learning Algorithm to predict the possibility of defect occurrence in additive metal manufacturing processes. The research aims to create a machine learning algorithm that provides a new pathway for printing defect-free parts, eliminating the costs and time-consuming associated with trial-and-error testing typically required in Powder Bed Fusion (PBF). Correspondingly, the defect susceptibility index was developed to eliminate defect formation prior to the part’s manufacturing process, and the hierarchical significance of mechanistic variables influencing defect formation was determined. The results demonstrate that a trained machine-learning algorithm enables the production of defect-free components without incurring costs or requiring time-intensive trials. This approach enhances the reliability of additive manufacturing in aerospace applications and paves the way for its broader adoption in mass production. By integrating CFD analysis, machine learning, and experimental validation, the proposed methodology ensures the production of high-quality, defect-free components, making additive manufacturing a viable option for the aerospace industry and beyond.