Automated Surface Defect Detection in Copper Blanks Using YOLOv۸ Segmentation and EfficientNetV۲-S Classification

In this study, an intelligent deep learning–based system is proposed for automated detection of surface defects in copper cathode blanks used in the electrorefining process. The proposed pipeline combines a YOLOv۸-based segmentation model with an EfficientNetV۲-S classifier to localize and analyze defect-relevant regions of each blank. The segmentation module identifies the main copper regions, edge strips, and defect-prone areas associated with surface anomalies such as scratches, dents, misalignment, and discoloration, effectively reducing background interference and improving classification reliability. The dataset includes ۵,۲۶۶ labeled images with a significant class imbalance, addressed using focal loss and class weighting during training. Experimental results on the test set demonstrate strong performance, achieving ۹۸.۳۲% accuracy, ۹۶.۷۱% precision, ۹۵.۶۷% recall, an F۱-score of ۹۶.۱۹%, and an AUC of ۰.۹۹۵۳. Grad-CAM visualizations and error analysis further confirm that the model consistently focuses on meaningful defect regions while remaining robust to background and illumination variations. These results highlight the effectiveness of the proposed approach for reliable quality control in industrial copper electrorefining lines.

کلیدواژه ها:

Copper Electrorefining ، Surface Defect Detection ، Industrial Image Classification ، EfficientNetV۲-S ، Deep Learning in Quality Control