TY - JOUR
TI - Exergy analysis and machine learning for enhanced EAF steel recycling
AU - Ivanović Jelena B
AU - Manojlović Vaso D
AU - Gajić Nataša M
AU - Phuthi Nigel T
AU - Zakonović Jelena P
AU - Sokić Miroslav D
AU - Kamberović Željko J
JN - Thermal Science
PY - 2025
VL - 29
IS - 3
SP - 2167
EP - 2183
PT - Article
AB - This study relies on exergy principles to analyze the sustainability of the steel recycling process in electric arc furnaces. Focusing on a balance between material and energy efficiencies, the research addresses the degradation of elements such as manganese and silicon from steel to slag phase. Machine learning techniques were employed to predict and optimize element distribution coefficients. By leveraging HSC v.9 software, a detailed exergy analysis was performed, utilizing precise coefficients for element distribution in steel and slag, with energy consumption. The results demonstrate the potential of integrating exergy analysis and ma-chine learning to enhance the sustainability of steel production, aligning with circular economy principles.