Publication 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

Type

journal article - other

Language

English

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 Reinformcement Learning Automata (CARLAs). Influence of CARLAs parameters to learning is discussed. Parameters influence is proved by simulation study. It is shown that learning improvement can be reached by selecting appropriate parameters of learning.

Keywords

control, active magnetic bearing, reinforcement learning

Authors

BŘEZINA, T.; TUREK, M.; PULCHART, J.

RIV year

2007

Released

1. 1. 2007

ISBN

0032-4140

Periodical

Pomiary Automatyka Kontrola

Year of study

2007

Number

1

State

Republic of Poland

Pages from

6

Pages to

9

Pages count

4

BibTex

@article{BUT44001,
  author="Tomáš {Březina} and Milan {Turek} and Jaroslav {Pulchart}",
  title="Self-learning controller of active magnetic bearing based on CARLA method",
  journal="Pomiary Automatyka Kontrola",
  year="2007",
  volume="2007",
  number="1",
  pages="6--9",
  issn="0032-4140"
}