Artificial Inteligence in Electromechanic Systems Control

2nd Level of Study, 1st Year, Winter Semester

Students will acquire fundamental knowledge in selected methods of artificial intelligence and gain an overview of modern techniques and their applications in the fields of fuzzy sets, artificial neural networks, and hybrid systems. They will become familiar with interesting and practically relevant applications of artificial intelligence, particularly in control engineering, system modeling, and prediction using AI-based methods. Upon completion of the course, students will have the knowledge and experience necessary to analyze data for the design of electromechanical system control, design controllers based on artificial intelligence techniques (fuzzy logic and neural networks) for electromechanical systems, and use software tools for the simulation and control design of various electromechanical systems.

1. Selected methods of Artificial Intelligence (AI), their characteristics, principles, classification, and applications.
2. Fuzzy set theory, comparison of classical and fuzzy sets, operations on fuzzy sets.
3. Takagi-Sugeno fuzzy systems, dynamic fuzzy systems, and data consistency.
4. Fuzzy controllers, methodology for the design of fuzzy controllers, and their applications in the control of electrical systems.
5. Software and hardware tools for the design and application of fuzzy controllers, with practical use of the Fuzzy Logic Toolbox in the MATLAB and Simulink environment; design of a fuzzy controller.
6. Biological neural networks, theory of artificial neural networks (ANNs), basic topologies, properties, and learning principles.
7. Feedforward neural networks and supervised learning. Multilayer neural networks and backpropagation learning. Recurrent neural networks.
8. Software and hardware tools for the design and application of neural networks.
9. Methodology for the design of neural controllers and neural models of systems and processes.
10. Methods for parameter identification and design of state observers for electrical engineering systems.
11. Application of neural networks to modeling, control of electrical systems, and prediction using the Neural Network Toolbox in the MATLAB and Simulink environment.
12. Design of neural networks for modeling applications using the Neural Network Toolbox (Deep Learning) in the MATLAB and Simulink environment.

[1] O. Modrlák, Fuzzy řízení a regulace, Liberec, 2002. [Online].

[2] D. Perduková, P. Fedor, J. Bačík, J. Herčko, and J. Rofár, "Multi-motor drive optimal control using a fuzzy model based approach," Journal on Ambient Intelligence and Smart Environments, vol. 9, no. 3, pp. 329-344, 2017. DOI: 10.3233/AIS-17043.

[3] P. Fedor and D. Perduková, "Use of fuzzy logic for design and control of nonlinear MIMO systems," in Modern Fuzzy Control Systems and Its Applications, Z. Zainuddin, Ed. INTECH, 2017, pp. 377-397. DOI: 10.5772/65834.

[4] D. Perduková, P. Fedor, and M. Lacko, "DC Motor Fuzzy Model Based Optimal Controller," MM Science Journal, vol. 2021, pp. 4879-4885, 2021. DOI: 10.17973/MMSJ.2021_10_2021033.

[5] V. Kvasnička, L. Beňušková, J. Pospíchal, I. Farkaš, P. Tiňo, and A. Kráľ, Úvod do teórie neurónových sietí, Bratislava: IRIS, 1997. ISBN: 80-88778-30-1.

[6] M. Leso, J. Žilková, M. Pastor, and J. Dudrik, "Fuzzy Logic Control of Soft-Switching DC-DC Converter," Elektronika ir Elektrotechnika, vol. 22, no. 5, pp. 72-80, 2016. DOI: 10.1109/EPEPEMC.2018.8521896.

[7] M. Leso, J. Žilková, and P. Girovský, "Development of a Simple Fuzzy Logic Controller for DC-DC Converter," in Proceedings - 2018 IEEE 18th International Conference on Power Electronics and Motion Control, PEMC 2018, pp. 86-93, Budapest, Hungary, 2018.

[8] P. Fedor and D. Perduková, "Fuzzy Model for Middle Section of Continuous Line," International Journal of Engineering Research in Africa, vol. 18, pp. 75-84, 2015. DOI: 10.4028/www.scientific.net/JERA.18.75.

[9] P. Fedor and D. Perduková, "Model Based Fuzzy Control Applied to a Real Nonlinear Mechanical System," Iranian Journal of Science and Technology, Transactions of Mechanical Engineering, vol. 40, no. 2, pp. 113-124, 2016. DOI: 10.1007/S40997-016-0005-9.

[10] J. Bačík, F. Ďurovský, P. Fedor, and D. Perduková, "Autonomous flying with quadrocopter using fuzzy control and ArUco markers," Intelligent Service Robotics, vol. 10, no. 3, pp. 185-194, 2017. DOI: 10.1007/s11370-017-0219-8.

[11] P. Fedor, "Fuzzy logic applications in process control," Study material prepared within the Leonardo da Vinci project No SK/98/2/05381/PI/II.1.1c/CONT: Training in Electrical Engineering for Industry Automation, “ELINA”, Mercury-Smékal, Košice, 2001, p. 37. ISBN: 80-89061-14-1.

[12] J. Timko, J. Žilková, and D. Balara, Aplikácie umelých neurónových sietí v elektrických pohonoch, Košice: Calypso s.r.o., 2002, pp. 1-239. ISBN: 80-85723-27-1.

[13] J. Žilková, Aplikácie umelých neurónových sietí pri riadení procesov, Košice: Mercury, 2001, pp. 1-56. ISBN: 80-89061-33-8.

[14] J. Žilková and J. Timko, "On-line estimation of quantities using artificial neural networks," Acta Technica CSAV (Ceskoslovensk Akademie Ved), vol. 47, no. 3, pp. 305-315, 2002.

[15] J. Žilková, J. Timko, and P. Girovský, "An inverse neural model for controlling non-linear dynamic systems," Acta Technica CSAV (Ceskoslovensk Akademie Ved), vol. 48, no. 4, pp. 365-377, 2003.

[16] J. Žilková, J. Timko, and P. Girovský, "Nonlinear system control using neural networks," Acta Polytechnica Hungarica, vol. 3, no. 4, pp. 85-94, 2006.

[17] J. Žilková, J. Timko, and M. Kováč, "Fuzzy vector control of asynchronous motor," Acta Technica CSAV (Ceskoslovensk Akademie Ved), vol. 55, no. 3, pp. 259-274, 2010.

[18] J. Žilková, J. Timko, and P. Girovský, "Modelling and control of tinning line entry section using neural networks," International Journal of Simulation Modelling, vol. 11, no. 2, pp. 97-109, 2012. DOI: 10.2507/IJSIMM11(2)1.189.

[19] P. Girovský, J. Timko, and J. Žilková, "Shaft sensor-less FOC control of an induction motor using neural estimators," Acta Polytechnica Hungarica, vol. 9, no. 4, pp. 31-45, 2012.

[20] D. Balara, J. Timko, and J. Žilková, "Application of neural network model for parameters identification of non-linear dynamic system," Neural Network World, vol. 23, no. 2, pp. 81-91, 2013.

[21] J. Žilková, P. Girovský, and M. Batmend, "Modelling the technological part of a line by use of neural networks," in Advances in Intelligent Systems and Computing, vol. 239, M. Katalinic, Ed., Heidelberg: Springer, 2014, pp. 349-358.

[22] D. Balara, J. Timko, J. Žilková, and M. Leso, "Neural networks application for mechanical parameters identification of asynchronous motor," Neural Network World, vol. 27, no. 3, pp. 259-315, 2017.