Publication result detail

Self-learning Controller of Active Magnetic Bearing Based on CARLA method

Březina, T., Turek, M., Pulchart, J.

Original Title

Self-learning Controller of Active Magnetic Bearing Based on CARLA method

English Title

Self-learning Controller of Active Magnetic Bearing Based on CARLA method

Type

Paper in proceedings (conference paper)

Original Abstract

The active magnetic bearing control through analytically designed linear PD regulator, with parallel nonlinear compensation represented by automatic approximator is described in this contribution. Coefficient (parameter) values come from actions of Continuous Action Reinforcement Learning Automata (CARLAs). Influence of CARLAs parameters to learning is discused. Parameters influence is proved by simulation study. It is shown that improvement of learning can be reached by selecting apropriate parameters of learning.

English abstract

The active magnetic bearing control through analytically designed linear PD regulator, with parallel nonlinear compensation represented by automatic approximator is described in this contribution. Coefficient (parameter) values come from actions of Continuous Action Reinforcement Learning Automata (CARLAs). Influence of CARLAs parameters to learning is discused. Parameters influence is proved by simulation study. It is shown that improvement of learning can be reached by selecting apropriate parameters of learning.

Key words in English

active magnetic bearing

Authors

Březina, T., Turek, M., Pulchart, J.

Released

31.12.2005

Location

Warszawa

ISBN

83-905409-3-2

Book

Proceedings

Pages from

17

Pages to

22

Pages count

6

BibTex

@inproceedings{BUT20504,
  author="Tomáš {Březina} and Milan {Turek} and Jaroslav {Pulchart}",
  title="Self-learning Controller of Active Magnetic Bearing Based on CARLA method",
  booktitle="Proceedings",
  year="2005",
  pages="17--22",
  address="Warszawa",
  isbn="83-905409-3-2"
}