We develop a fully automated metrology pipeline using deep learning techniques for dimension analysis of additively manufactured parts. Our research employs Line Segment Detector (LSD) and CNN-based Ellipse Detector (EIDet) to accurately extract and measure geometric features from image data without manual intervention. This approach demonstrates robust generalizability across diverse geometries, achieving high accuracy with reduced runtime compared to traditional methods.

We show that every 3D printer has a unique “fingerprint” that is imprinted on the parts it manufactures. By utilizing images and deep learning, we can read this fingerprint and accurately identify the specific machine that produced a given part. Our technique provides critical insights for customers and manufacturers, and enables innovative methods for part authentication, counterfeit detection, and quality management strategies. 

We propose an optimization-based approach for selecting additive manufacturing (AM) process parameters for high quality parts made using laser powder bed fusion (LPBF). By optimizing three process parameters (layer thickness, laser power, and scanning speed), we achieved 17% better geometric accuracy while meeting porosity requirements. Our results reveal that laser power is the most influential parameter affecting both geometric accuracy and porosity.