- Project number:
- 1/0239/24
- Title of the project:
- Advanced control of energy-intensive chemical-technological processes using learned approximate explicit controllers
- Grant scheme:
- VEGA
- Project type:
- VEGA Research Projects
- Project duration (start):
- 01.01.2024
- Project duration (end):
- 31.12.2027
- Principal investigator:
- Martin Klaučo
- Deputy investigator:
- Michaela Horváthová
- Investigators:
- Ľuboš Čirka, Matúš Furka, Lenka Galčíková, Ľubomíra Horanská, Karol Kiš, Michal Kvasnica, Juraj Oravec, Patrik Valábek, Peter Viceník
The project will design tools to design approximate explicit controllers for complex chemical processes that optimize energy consumption and improve process efficiency. This project will use machine learning techniques to synthesize controllers for processes with a high number of states, parameters, and long prediction horizons, which is impossible with traditional approaches to the design of explicit Model Predictive Controllers (MPC). The project will use the reinforcement learning approaches to create new techniques to design learned approximate explicit controllers that can dynamically adjust the controller performance in real-time. The learning part will adopt the philosophy of MPC and explicit MPC to ensure stability and constraint satisfaction of energy-intensive processes. The proposed research has the potential to significantly improve the performance and sustainability of energy-intensive chemical processes, leading to reduced energy consumption, lower costs, and decreased environmental impact.
Publications
2025
- M. Horváthová – P. Valábek – K. Kiš – L. Galčíková: Experimental Application of Stochastic Approximated MPC. Editor(s): R. Paulen and M. Fikar and J. Oravec, In Proceedings of the 2025 25th International Conference on Process Control, IEEE, pp. 130–135, 2025.
- R. Kohút – M. Klaučo – M. Kvasnica: Unified carbon emissions and market prices forecasts of the power grid. Applied Energy, vol. 377, 2025.
- E. Pavlovičová – B. Daráš – P. Bakaráč – M. Fikar – J. Oravec: From Theory to Harvest: Robust MPC Supervising Smart Greenhouse System. Editor(s): R. Paulen and M. Fikar and J. Oravec, In Proceedings of the 2025 25th International Conference on Process Control, IEEE, pp. 80–85, 2025. Zenodo
- P. Valábek – M. Wadinger – M. Kvasnica – M. Klaučo: Deep Dictionary-Free Method for Identifying Linear Model of Nonlinear System with Input Delay. Editor(s): R. Paulen and M. Fikar and J. Oravec, In Proceedings of the 2025 25th International Conference on Process Control, IEEE, pp. 13–18, 2025.
2024
- Ľ. Horanská: Mobius transform: History, generalizations and applications in aggregation theory. Editor(s): O. Hutník, In Uncertainty Modeling 2024, Pavol Jozef ˇSaf´arik University in Koˇsice, pp. 6–7, 2024.
- D. Horváth – M. Klaučo – M. Strémy: Virtual Commissioning with TIA Step7 and Simulink without S-Functions. Journal of Engineering, 2024. Zenodo
- M. Klaučo – P. Valábek: Application of Machine Learning in Accelerating MPC for Chemical Processes. In 12th IFAC Symposium on Advanced Control of Chemical Processes, 2024. Zenodo
Investigators
2024
Responsibility for content: doc. Ing. MSc. Martin Klaučo, PhD.
Last update: 19.05.2023 9:10
Institute of Information Engineering, Automation and Mathematics was established in 1.1.2006 from two departments: Department of Information Engineering and Process Control and Department of Mathematics.
Latest Posts
- IAM students defended Bachelor theses2.7.2025 15:56
- Graduation ceremony of IAM students 202521.6.2025 15:00
- Outstanding master theses19.6.2025 20:37
Contact
Radlinského 9
812 37 Bratislava, Slovakia
Tel.: +421 259 325 366
Fax: +421 259 325 340
Mobil: +421 918 674 366
e-mail: office@uiam.sk
6th floor, Block C NB
2025 © All Rights Reserved. UIAM FCHPT STU | webmaster@uiam.sk