A Real-Time Defect Detection Strategy for Additive Manufacturing Processes Based on Deep Learning and Machine Vision Technologies

Abstract

Nowadays, additive manufacturing (AM) is advanced to deliver high-value end-use products rather than individual components. This evolution necessitates integrating multiple manufacturing processes to implement multi-material processing, much more complex structures, and the realization of end-user functionality. One significant product category that benefits from such advanced AM technologies is 3D microelectronics. However, the complexity of the entire manufacturing procedure and the various microstructures of 3D microelectronic products significantly intensified the risk of product failure due to fabrication defects. To respond to this challenge, this work presents a defect detection technology based on deep learning and machine vision for real-time monitoring of the AM fabrication process. We have proposed an enhanced YOLOv8 algorithm to train a defect detection model capable of identifying and evaluating defect images. To assess the feasibility of our approach, we took the extrusion 3D printing process as an application object and tailored a dataset comprising a total of 3550 images across four typical defect categories. Test results demonstrated that the improved YOLOv8 model achieved an impressive mean average precision (mAP50) of 91.7% at a frame rate of 71.9 frames per second.

Simultaneous Pore Detection and Morphological Features Extraction in Laser Powder Bed Fusion with Image Processing

“…With training on a small number of datasets, supervised models cannot obtain satisfactory results even for simple binary classification tasks. Obviously, increasing the training data would be a way to significantly improve the detection performance, but labeling a large amount of image data is bound to be a mechanically repetitive and tedious task for researchers [ 44 ]. When labeling the images used to train YOLOv8, the average time to label an image was tested to be about 4 min, while our method takes only about 7 s to label the pore defects.…”