Automated Surface Defect Detection in Copper Blanks Using YOLOv8 Segmentation and EfficientNetV2-S Classification
نویسندگان
1 Department of Electrical Engineering, Faculty of Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran
2 Department of Biomedical Engineering, Meybod University, Meybod, Iran
3 Technical and Engineering Research, Research and Development Department, Sarcheshmeh Copper Complex, Rafsanjan, Iran.
4 Expert, Refinery and Casting Division, Sarcheshmeh Copper Complex, Rafsanjan, Iran
5 Department of Electrical Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran.
6 Director of Training and Competency Development, Sarcheshmeh Copper Complex, Rafsanjan, Iran.
7 Research and Development Division, Sarcheshmeh Copper Complex, Rafsanjan, Iran.
8 Head of Operations, Refinery and Casting Division, Sarcheshmeh Copper Complex, Rafsanjan, Iran.
9 Technical and Engineering Research, Research and Development Department, Sarcheshmeh Copper Complex, Rafsanjan, Iran.
doi
10.22044/jadm.2026.16853.2818چکیده
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 YOLOv8-based segmentation model with an EfficientNetV2-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 5,266 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 98.32% accuracy, 96.71% precision, 95.67% recall, an F1-score of 96.19%, and an AUC of 0.9953. 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.
