Abstract
This article explores the optimization of copper smelting processes at the Balkhash plant using big data analytics and mathematical modeling. The study focuses on developing a mathematical model of the Vanyukov furnace to improve process efficiency and reduce production costs. Data collected in real-time through a SCADA system were analyzed to identify key correlations between input and output parameters, such as temperature, pressure, and chemical composition. The developed model, based on parametric identification methods, demonstrated high accuracy in predicting process behavior, with a coefficient of determination of 0.95. The results show that the model can improve prediction accuracy by 15% and reduce regulation time by 20%. The research highlights the potential of big data analytics in enhancing automation and optimizing technological processes in the metallurgical industry. The findings provide a basis for further integration of advanced control systems in copper smelting production.