A Comparison of Anomaly Detection Algorithms with applications on Recoater Streaking in an Additive Manufacturing Process

Additive manufacturing has recently seen substantial growth, yet consistently producing high-quality parts remains a challenge. Recoating streaking is a common anomaly that impairs print quality. Several data-driven models for automatically detecting this anomaly have been proposed, each with varying effectiveness. However, comprehensive comparisons among them is lacking. Additionally, these models are often tailored to specific datasets. This research addresses this gap by implementing and comparing these anomaly detection models for recoating streaking in a reproducible way. We offer a clearer, more objective evaluation of their performance, strengths, and weaknesses. Furthermore, we propose an improvement to the Line Profiles detection model to broaden its applicability, and a novel preprocessing step was introduced to enhance the models' performances. These improvements established the Line Profiles model as the most efficient detection approach in our benchmark dataset.