Process screening in additive manufacturing: Detection of keyhole mode using surface topography and machine learning

Abstract

Screening of defective additive manufactured (AM) parts is crucial for ensuring process consistency and part reliability, yet common microstructural inspection methods can be time-consuming or destructive. This study explores how surface analysis combined with machine learning (ML) algorithms can effectively infer the microstructure of laser powder bed fusion (LPBF) parts. As a case study, non-spherical ZrH₂ nanoparticle-enhanced AA7075 aluminum powders was fabricated using 60 different LPBF recipes. ML classification models were then employed to link side-surface topographical features to keyhole melting occurring within the parts. Among the tested ML models, random forest (RF) achieving a testing accuracy of 95 % and an F1-score of 0.98, outperforming both the neural network (NN) and support vector machine (SVM) models. To enhance the interpretability of the ML model, the RF model was leveraged to identify the hierarchical importance of surface features associated with keyhole melting mode. This resulted in the development of keyhole-probability maps based on superficial surface parameters, providing engineers with an effective and easy-to-use tool for screening keyhole mode parts. While further validation is needed, the proposed strategy lays a foundation for leveraging surface topography to infer microstructural features and adapting the method to different material systems.