Real-Time Defect Detection in 3D Printing Using Deep Learning

Real-time defect detection in 3D printing is a critical aspect of ensuring the quality and reliability of printed objects. Detecting defects during the printing process can help prevent the production of faulty parts, reduce waste, and save time and resources. This research project focuses on developing an advanced defect detection system for real-time monitoring and control of 3D printing. The system integrates a camera, Octopi, and Ultimaker Cura for efficient monitoring and control of the printer. The YOLOv8 algorithm on Raspberry Pi 4B enables accurate and timely defect identification. The project aims to enhance the 3D printing process by proactively detecting errors, resulting in improved outcomes and a seamless user experience. Immediate notifications for print errors are facilitated through the GSM module, ensuring timely intervention. The proposed solution offers proactive error detection, contributing to time, cost, and resource savings while improving the overall quality of 3D prints.