Data-Driven Modelling of Electrode Resistance in Submerged Arc Furnaces

We consider the problem of finding control-oriented models for the electrode resistance of submerged arc furnaces (SAF) to aid the metallurgical process control of ferrosilicon production. To accomplish this goal, we analyze the field data gathered from the Norwegian metal producer Wacker AS, which are the most important input parameters for accurately predicting electrode resistances. This is done by investigating the predictive capabilities of different linear and non-linear model structures in different furnace operating conditions, and discussing which type of non-linearity induces the best-performing models both in terms of prediction fit and modeling error in opportune test sets. We finally provide interpretations of why the presence of this non-linearity results in the best performance by connecting their structure with domain expertise about the electrical dynamics within SAF circuits.