Metamodeling of the Electrical Conditions in Submerged Arc Furnaces

Physics-based finite element method models can be used to investigate the electrical conditions in submerged arc furnaces (SAFs). However, their explicit solution may be very demanding in terms of time and computational resources, which complicates their use during control operations and fast prototyping. To address these challenges, this study develops metamodels that serve as surrogates to the original physics-based model. Metamodels rely on statistical analysis tools and are designed to approximate input–output relationships based on a database of simulations from the original model, thus ensuring computational efficiency. Our results demonstrate that these metamodels maintain comparable generalization capabilities to the original model while being significantly lighter in computational demands, making them more suitable for dynamic control and operational applications in SAFs. This work emphasizes the importance of understanding current density, thermal conditions, and mechanical stresses in SAF operation, ultimately contributing to more efficient metal production processes.