Classification of Zinc Recovery Quality from EAF Dust Using Machine Learning: A Waelz Process Study

Year 2024, Volume: 3 Issue: 4, 171 - 177, 31.12.2024

Didem Özcan Kürşat Mustafa Karaoğlan , Mehmet Çelik

Abstract

Zinc recovery from Electric Arc Furnace (EAF) dust represents a significant challenge in the iron and steel industry. This study aims to classify zinc quality in slag produced through the Waelz process, where zinc is reduced and volatilized at high temperatures (>1000°C) in rotary kilns, using machine learning techniques. The classification of zinc quality in slag is crucial for process optimization and environmental sustainability, as it directly impacts both resource recovery efficiency and waste management strategies. The dataset utilized for developing classification models was obtained from chemical analyses of Waelz process raw materials and slag samples. Four distinct classification algorithms (Support Vector Machine SVM, Decision Tree - DT, Naive Bayes - NB, and Random Forest - RF) were evaluated on the data labeled by experts according to zinc content in slag. The reliability of the models was assessed through 10-fold cross-validation. In experimental studies, the DT algorithm demonstrated superior performance with 100.0% accuracy, precision, sensitivity, and F1 score. The RF algorithm achieved second-place performance with 96.0-98.0% accuracy and 100.0% precision, followed byNB with 91.0-94.0% accuracy, and SVM with 84.0-88.0% accuracy. The results indicate that the DT algorithm can serve as a reliable tool for quality classification in the zinc re-covery process. These findings contribute significantly to the advancement of automated quality control systems in metallurgical processes, potentially enabling real-time monitoring and optimization of zinc recovery operations.

Keywords

Zinc Recovery, Electric Arc Furnace Dust, Waelz Process, Machine Learning Classification, Slag Quality

References

• 1. Mudd, G. M., Jowitt, S.M., & Werner, T. T. (2017). The world’s lead-zinc mineral resources: Scarcity, data, issues and opportuni-ties. Ore Geology Reviews, 80, 1160–1190.
• 2. Avachat, H., Sabnavis, M., & Jagasheth, U. H. (2018). Zinc industry: the unsung metal of the economy-industry research re-port. CARE Ratings: Professional Risk Opinion, 1-11
• 3. Ng, K. S., Head, I., Premier, G. C., Scott, K., Yu, E., Lloyd, J., & Sadhukhan, J. (2016). A multilevel sustainability analysis of zinc recovery from wastes. Resources, Conservation and Recycling, 113, 88–105.
• 4. Goodwin, F.E. (2017). Current status anf future expectations for the zinc market. International Zinc Association for Presentation at InterZAC 2017, Toronto.
• 5. Jia, Y., Zhang, T., Zhai, Y., Bai, Y., Ren, K., Shen, X., Cheng, Z., Zhou, X. & Hong, J. (2022). Exploring the potential health and ecological damage of lead–zinc production activities in Chi-na: A life cycle assessment perspective. Journal of Cleaner Pro-duction, 381(1), 135–218.
• 6. Shawabkeh, R. A. (2010). Hydrometallurgical extraction of zinc from Jordanian electric arc furnace dust. Hydrometallurgy, 104(1), 61–65.
• 7. Oustadakis, P., Tsakiridis, P. E., Katsiapi, A. & Agatzini-Leonardou, S. (2010). Hydrometallurgical process for zinc reco-very from electric arc furnace dust (EAFD): Part I: Characteriza-tion and leaching by diluted sulphuric acid. Journal of Hazar-dous Materials, 179(1-3), 1-7.
• 8. Özcan, D. (2024). Classification and regression analysis of zinc recovery in rotary kilns using machine learning. Published Mas-ter's Thesis, Karabük Üniversitesi, Karabük.
• 9. Polatgil, M. (2023). Investigation of the effects of data scaling and imputation of missing data approaches on the success of machine learning methods. Duzce University Journal of Science & Technology, 11, 78–88.
• 10. Başer, B. Ö., Yangın, M., & Sarıdaş, E. S. (2021). Classification of diabetes mellitus with machine learning techniques. Süleyman Demirel University Journal of Natural and Applied Sciences, 25(1), 112–120.
• 11. Tomak, L., & Bek, Y. (2010). The analysis of receiver operating characteristic curve and comparison of the areas under the curve. Journal of Experimental and Clinical Medicine, 27(2), 58–65.
• 12. Yiğit, P. (2011). Yapay sinir ağları ve kredi taleplerinin değer-lendirilmesi üzerine bir uygulama. Published Master's Thesis, İstanbul Üniversitesi, İstanbul.
• 13. Pintea, S., & Moldovan, R. (2009). The receiver-operating cha-racteristic(roc) analysis: Fundamentals and applications in clini-cal psychology. Journal of Cognitive and Behavioral Psychothe-rapies, 9(1), 49–66.