APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN THE CONTEXT OF ACTIVE MAGNETIC BEARING CONTROL SYSTEMS

Authors

  • Alexander Kravtsov Department of Electric Power Engineering, Electric Drive and Automation Systems, Pskov State University (RU)
  • Konstantin Vukolov Department of Electric Power Engineering, Electric Drive and Automation Systems, Pskov State University (RU)
  • Igor Plokhov Department of Electric Power Engineering, Electric Drive and Automation Systems, Pskov State University (RU)
  • Igor Savraev Department of Electric Power Engineering, Electric Drive and Automation Systems, Pskov State University (RU)
  • Sergei Loginov Department of Electric Power Engineering, Electric Drive and Automation Systems, Pskov State University (RU)

DOI:

https://doi.org/10.17770/etr2021vol3.6531

Keywords:

Active magnetic bearing, neural network the neural network controller, transient simulation

Abstract

The article is devoted to the application of neural network methods and genetic algorithms in solving problems of controlling an electric drive of an active magnetic suspension. The method of rolling moment for eliminating an imbalance is considered. The scheme of the neural network controller and the curves of the transients in the open single-mass electromechanical system and in the system c of the neurocontrollers are presented.

Downloads

Download data is not yet available.

References

Zhuravlev U.N. Activnye magnitnye podshipniki: teoriya, raschet, primenenie [Active magnetic bearings: theory, calculations, application]. Saint-Petersburg.: Politekhnica Publ., 2003. pp. 22–30. (in Russian).

Bleuler H. Magnetic levitation: a challenge for control design in mechatronics. Toshiba Chair for Intelligent Mechatronics, 2011. pp. 578–583.

Bobokin G.I., Shprekher D.M. Primenenie neyronnykh setei dlya diagnostiki elektromekhanicheskikh sistem [Neural networks application in the field of electromechanical system diagnostics], 2003. Available at: https://cyberleninka.ru/article/n/primenenie-neyronnyh-setey-dlya-diagnostiki-elektromehanicheskih-sistem (in Russian).

Wang Ping, Li Bin, Huang Ruixiang, Li Guidan. Diangong jishu xuebaoTrans. China Electrotech, 2003. pp.5-8.

Gottapu K., Prashanth Y., Mahesh P., Sumith Y. Simulation of DTC IM Based on PI& Artificial Neural Network Technique. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering vol. 2, no. 7, issue 7, 2013.

Mamdani E.H., Assilian S. An experiment in linguistic synthesis with a fuzzy logic controller. Int. J. Man-Mach. Stud., vol. 7, pp.1-13, 1975.

F. Matsumura and T. Yoshimoto. System modeling and control design of horizontal shaft magnetic bearing system. IEEE Trans. Magn., vol. Mag-22, no. 5, 1986.

K. Noami and H. Yamaguchi. Robust control of magnetic bearing systems by means of sliding mode control. Proc. Int. Symp. Applicat. Electromagnetism, vol. ISEM 91, no. 1, 1991.

J. De Miras, A. Charara, B. Caron. Nonlinear control of a magnetic levitation system without premagnetization. IEEE Transactions on Control Systems Technology, vol.4, no.5, 1996, pp.513-523.

Narendra K.S., Parthasarathy K. Identification and control of dynamical systems using neural networks. IEEE Trans. on Neur. Net, vol. 1, no. 1, 1990, pp. 4-27.

Downloads

Published

2021-06-16

How to Cite

[1]
A. Kravtsov, K. Vukolov, I. Plokhov, I. Savraev, and S. Loginov, “APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN THE CONTEXT OF ACTIVE MAGNETIC BEARING CONTROL SYSTEMS”, ETR, vol. 3, pp. 159–162, Jun. 2021, doi: 10.17770/etr2021vol3.6531.