Maintaining the temperature of liquid steel in the ladle in the required range affects the quality of casted billets, reduces energy consumption, and guarantees smooth control of the melting sequence. Measuring its temperature is a challenging task in industrial settings, often hindered by safety concerns and the expensive nature of equipment. This paper presents models which enable the prediction of the cooling rate of liquid steel for variable production parameters, i.e., steel grade and weight of melt. The models were based on the FEM solution of the Fourier equation, and machine learning approaches such as decision trees, linear regression, and artificial neural networks are utilized. The parameters of the model were identified using data from the monitoring system and inverse analysis. The results of simulations were verified with measurements performed in the production line.

The paper introduces a methodology for optimization in multistage industrial processes with multiple quality criteria. Two ways of formulation of optimization problem and four different approaches to solve the problem are considered. Proposed methodologies were tested first on a virtual process described by benchmark functions and next were applied in optimization of multistage lead refining process.

The goal of the research is an attempt of development of automatic control system of the oxidizing roasting process of zinc sulphide concentrates. The reliable modeling of the analyzed process is the preliminary step in solving of design of the control systems. A solution based on the Artificial Neural Networks (ANN) is presented. Two different ANN models of the analyzed process were created. Several different variants of ANN topologies were validated. Then, the possibilities of automatic control of the process based on elaborated ANN models using different input parameters were verified and the quality of obtained results was assessed. The details of modeling methods and the best obtained results are presented.

Improvement of the TR crank shaft forging technology is the objective of the paper. New concept of forging of crank shafts is considered. Plastometric tests were performed for steels used for manufacturing of crank shafts and a rheological model for these steels was determined. This model was implemented in the finite element software and simulations of various variants of forging were performed. Results of simulations were used to select the best variant, which gives the lowest loses of the material and proper shape of the final product. Two technological parameters are selected as the optimization variables. Finite element simulations of the forging process for various values of the selected parameters were performed. Optimization of the forging process is performed using the surface response methodology. Optimal forging parameters are given in the paper.