- Project number:
- Title of the project:
- Machine Learning and Artificial Intelligence in Process Control and Automation
- Project type:
- Other projects
- Project duration (start):
- Project duration (end):
- Martin Kalúz, Michal Kvasnica
Funding: Postdoc research stays at the Slovak University of Technology in Bratislava
Principal investigator: doc. Ing. Michal Kvasnica, PhD.
Job offer: listed here
The aim of the project is to apply machine learning and artificial intelligence methods to synthesize control systems composed of three components: an inference mechanism, a process model, and a control strategy. The task of the inference mechanism is to deduce values of unmeasured parameters and process values from known measured signals. Subsequently, the inferred values are utilized by the process model to predict the future evolution of the controlled plant. Finally, the aim of the control strategy is to deduce optimal control actions based on the process model. The implementation of these blocks will be based on, respectively, machine learning techniques (SVM, PCA, etc.), deep neural networks, and model predictive control. The objective of the project is to extend existing machine learning and artificial intelligence techniques to systems that combine continuous dynamics with discrete logic (known as hybrid systems), to combine the methods in a systematic manner, and to implement developed algorithms in the form of open-source software packages.
- Ľ. Čirka – M. Kalúz – D. Dzurková – R. Valo: Educational Device Flexy2 in the Teaching of Experimental Identication. Editor(s): M. Fikar and M. Kvasnica, In Proceedings of the 22nd International Conference on Process Control, Slovak Chemical Library, Štrbské Pleso, Slovakia, pp. 239–244, 2019.
- M. Kalúz – M. Klaučo – Ľ. Čirka – M. Fikar: Flexy2: A Portable Laboratory Device for Control Engineering Education. In 12th IFAC Symposium Advances in Control Education, pp. 159–164, 2019.
- M. Klaučo – M. Kalúz – M. Kvasnica: Machine learning-based warm starting of active set methods in embedded model predictive control. Engineering Applications of Artificial Intelligence, vol. 77, pp. 1–8, 2019.
Responsibility for content: doc. Ing. Michal Kvasnica, PhD.
Last update: 23.08.2017 14:07