EfficientNet-B3 for iron ore pellet quality control: real-world image classification with high accuracy | ||
| International Journal of Mining and Geo-Engineering | ||
| مقاله 8، دوره 59، شماره 4، زمستان 2025، صفحه 377-383 اصل مقاله (462.33 K) | ||
| نوع مقاله: Research Paper | ||
| شناسه دیجیتال (DOI): 10.22059/ijmge.2025.395689.595261 | ||
| نویسندگان | ||
| Asma Shams-Kermani* ؛ Marziye Salehi | ||
| Faculty of Electrical and Computer Engineering, Sirjan University of Technology, Sirjan, Iran. | ||
| چکیده | ||
| This study proposes a deep learning–based quality control method for iron ore pellet production using real-world image classification. An EfficientNet-B3 architecture classifies pellet images into four size categories: very small, small, medium, and large. Trained on 17492 images captured under realistic conditions, the model achieved a classification accuracy of 99.9%, outperforming alternative architectures, including ResNet50, VGG16, and MobileNet. Additional performance metrics, such as precision, sensitivity, and Matthews correlation coefficient (MCC) which were further confirmed the robustness of the approach. The results demonstrated the potential of deep learning for automating pellet size monitoring and highlight its industrial relevance for improving efficiency and quality in steel production. | ||
| کلیدواژهها | ||
| Iron ore pelletization؛ Image classification؛ Deep learning؛ EfficientNet؛ Quality control | ||
| مراجع | ||
|
| ||
|
آمار تعداد مشاهده مقاله: 320 تعداد دریافت فایل اصل مقاله: 189 |
||