Process control and energy saving in the ladle stage of a metal casting process through physics-based and ANN-based modelling approaches

•New model for temperature estimation in metal casting ladles.•Comparison between physics-based and ANN approaches.•Analyze where and when each approach is more suitable to maximize prediction performance.•Limitations of machine learning approaches in extrapolation for this case study.•Optimization strategy for energy savings in foundry applications. The process and temperature control of metal casting applications is of utmost importance both to guarantee the good quality of the final product and also to pursue an energy saving policy. For this purpose, in this paper two different modelling approaches have been proposed to predict the liquid steel temperature inside a ladle for metal casting, shortly before the casting process. The first is a physics-based grey-box model relying on equations for the characterization of the heat transfer mechanisms inside the ladle structure, whereas the second approach relies on artificial neural networks (ANNs). Both methods have been calibrated with experimental data of a case study plant, and subsequently assessed and compared in terms of prediction accuracy. Results show that the physics-based approach is able to predict the casting temperature with a higher mean absolute error (MAE) of 14 °C, whereas the ANNs predictions result to be better, with MAEs around 6 °C. On the other hand, it has been demonstrated that the ANNs approach may lack of reliability, especially if input data strongly differ from the calibration dataset, whereas the physics-based approach results to be more consistent and trustworthy. Finally, an energy analysis is conducted to demonstrate the feasibility of the model in evaluating the potential energy saving compared with situations in which decisions are taken by operators without the aid of a model predictive control.