Publication detail

Improvement of Q-learning Used for Control of AMB

BŘEZINA, T. KREJSA, J. VĚCHET, S.

Original Title

Improvement of Q-learning Used for Control of AMB

Type

conference paper

Language

English

Original Abstract

Active magnetic bearing (AMB) is perspective design element; however AMB itself is unstable and must be stabilized by feedback control loop. Artificial intelligence methods, which use real time machine learning, can be used for the proposition of new control methods, which either improve the AMB control, or require less complex control electronics. The paper is focused on use of reinforcement learning version called Q-learning. As the conventional Q-learning architectures learning process is too slow to be practical for real control tasks, the paper proposes improvement of Q-learning by partitioning the learning process into two phases: prelearning phase and tutorage phase. Prelearning phase requires computational model but is highly efficient, tutorage phase uses conventional real time Q-learning and assumes the interaction with the real system. To demonstrate the qualities of developed controllers the performance of AMB model controlled by such controller is compared with the performance of AMB model controlled by referential PID controller.

Keywords

Control, Q-learning, Active Magnetic Bearing

Authors

BŘEZINA, T.; KREJSA, J.; VĚCHET, S.

RIV year

2003

Released

24. 9. 2003

Location

Košice, Slovak Republik

ISBN

80-89061-77-X

Book

Electrical Drives and Power Electronics 2003

Edition

Neuveden

Edition number

Neuveden

Pages from

51

Pages to

54

Pages count

4

BibTex

@inproceedings{BUT8152,
  author="Tomáš {Březina} and Jiří {Krejsa} and Stanislav {Věchet}",
  title="Improvement of Q-learning Used for Control of AMB",
  booktitle="Electrical Drives and Power Electronics 2003",
  year="2003",
  series="Neuveden",
  number="Neuveden",
  pages="4",
  address="Košice, Slovak Republik",
  isbn="80-89061-77-X"
}