Automatic detection and severity assessment of stringing defect in FDM 3D printing using deep learning
Author
Term
4. semester
Publication year
2024
Submitted on
2024-05-31
Pages
73
Abstract
The thesis investigates defects occurring dur- ing the Additive Manufacturing process and proposes a CNN-based solution to detect and assess the severity of the stringing defect. A YOLOv8 and MobileNetV3 solution to first de- tect and then assess stringing defects’ severity have been proposed to solve the problem. A labeled object detection dataset with severity labels have been created. Tests on the dataset and as well on a real-life capture from a web- cam overseeing the printing process have been conducted, to see whether the proposed solu- tion is viable to solve the problem of both man- ufacturing supervision and defect severity as- sessment. To find out if the solution is viable, several metrics have been calculated to mea- sure, how well the solution performs, as well re- source usage have been measured, to find out if the solution won’t interrupt the manufacturing process. On the test split of created dataset, the detection model performs well, however it fails to generalize on the real-life capture and the severity assessment model is not accurate enough.
Keywords
Documents