Publication

Abstract : Weld quality inspection is vital for ensuring industrial safety and manufacturing reliability, but traditional manual inspection methods are limited by subjectivity, time, and cost. To address these limitations, this paper proposes an automated, real-time solution for weld defect detection and classification using the YOLOv8n deep learning model. The methodology utilizes a dataset of 2953 images for training, validation, and testing. The trained model achieved a mean Average Precision (mAP@0.5) of 98.1% and an inference speed of 4 ms, showing high accuracy and real-time capability. These results establish YOLOv8n as a highly effective and efficient solution for automated weld inspection, offering a practical and scalable alternative to manual processes.