The aim of the project is to contribute to the development of knowledge in the field of modern methods of automation and process control through the development of new approaches based on a combination of theoretical and experimental insights. The project focuses on the design, implementation, and investigation of advanced control algorithms that will enable more efficient control of complex processes with nonlinear behavior.

The main idea of the project is to link model-based and data-driven approaches into a unified control framework. In this way, space is created to leverage the advantages of both methods—namely, the accuracy and interpretability of physical models together with the adaptability of data-based models. The project will lead to the development of an adaptive multi-model predictive controller that can flexibly adapt to changes in the process, thereby improving control quality and system robustness.

The developed controller will first be tested through computer simulations in the Python and MATLAB software environments. In the next phase, its behavior will be experimentally verified on a laboratory distillation column at the workplace. By comparing simulation and real-world results, it will be possible to refine and tune the controller parameters in order to achieve higher control efficiency and better product quality.