Defect detection in manufacturing processes is a critical requirement for ensuring product reliability and maintaining production stability. As smart manufacturing environments continue to advance, the need for precise and robust vision-based inspection methods has become increasingly significant. This study proposes a hybrid defect analysis framework that integrates YOLOv5-based defect candidate detection with an Attention U-Net–based segmentation module. Experiments conducted on chromate-coated industrial images demonstrate that the proposed framework achieves an accuracy of 0.97, precision of 0.91, recall of 0.89, F1-score of 0.93, and IoU of 0.88, exhibiting stable performance even for small defects and irregular boundaries. The combination of region- of-interest extraction and attention-enhanced pixel-level segmentation improves both computational efficiency and boundary reconstruction quality. The findings extend the applicability of attention-based segmentation to industrial defect inspection and provide practical insights for deploying deep learning–based quality monitoring systems in automated manufacturing environments.

Fe-Si-Cr ferroalloy is predominantly produced by carbothermic reduction. In this study, silicothermic and carbothermic mixed reduction of chromite ore to produce Fe-Si-Cr alloy is suggested. As reductants, silicon and silicon carbide are evaluated by thermochemical calculations, which prove that silicon carbide can be applied as a raw material. Considering the critical temperature of the change from the carbide to the metallic form of chromium, thereduction experiments were carried out. In these high temperature reactions, silicon and silicon carbide act as effective reductants to produce Fe-Si-Cr ferroalloy. However, at temperatures lower than the critical temperature, silicon carbide shows a slow reaction rate for reducing chromite ore. For the proper implementation of a commercial process that uses silicon carbide reductants, the operation temperature should be kept above the critical temperature. Using equilibrium calculations for chromite ore reduction with silicon and silicon carbide, the compositions of reacted metal and slag were successfully predicted. Therefore, the mass balance of the silicothermic and carbothermic mixed reduction of chromite ore can be proposed based on the calculations and the experimental results.