DETERMINATION OF Q-FUNCTION OPTIMUM GRID APPLIED ON ACTIVE MAGNETIC BEARING CONTROL TASK

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F03%3APU34259" target="_blank" >RIV/00216305:26210/03:PU34259 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61388998:_____/03:51030188

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

DETERMINATION OF Q-FUNCTION OPTIMUM GRID APPLIED ON ACTIVE MAGNETIC BEARING CONTROL TASK

Popis výsledku v původním jazyce

Active magnetic bearing control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the convergence speed. Two-phase Q-learning can be used to speed up the learning process [2]. Efficient prelearning phase uses mathematical model, following tutorage phase runs on real system and uses conventional Q-learning. This method can increase learning speed significantly, however there are still certain issues remaining to solve in order to impprove the overall performance of the controllers based on Q-learning. When the table is used as Q-function approximation, the learning speed and precision of found controllers depend highly on the Q-function table grid properties. The paper is denoted tothe determination of optimum grid with respect to the properties of controllers found by given method. Comparison of the results with performance of referential PID controller is included. Obtained results indicate that using nonlinear g

Název v anglickém jazyce

DETERMINATION OF Q-FUNCTION OPTIMUM GRID APPLIED ON ACTIVE MAGNETIC BEARING CONTROL TASK

Popis výsledku anglicky

Active magnetic bearing control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the convergence speed. Two-phase Q-learning can be used to speed up the learning process [2]. Efficient prelearning phase uses mathematical model, following tutorage phase runs on real system and uses conventional Q-learning. This method can increase learning speed significantly, however there are still certain issues remaining to solve in order to impprove the overall performance of the controllers based on Q-learning. When the table is used as Q-function approximation, the learning speed and precision of found controllers depend highly on the Q-function table grid properties. The paper is denoted tothe determination of optimum grid with respect to the properties of controllers found by given method. Comparison of the results with performance of referential PID controller is included. Obtained results indicate that using nonlinear g

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/GA101%2F00%2F1471" target="_blank" >GA101/00/1471: Stabilita a řízení rotorů na magnetických ložiskách</a><br>

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2003

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Mechtronics, Robotics and Biomechanics 2003

ISBN

80-214-2312-9

ISSN

—

e-ISSN

—

Počet stran výsledku

2

Strana od-do

55-56

Název nakladatele

Institute of Mechanics of Solids Faculty of Mechanical Engineering Brno University of Technologi

Místo vydání

Brno

Místo konání akce

Hrotovice

Datum konání akce

24. 3. 2003

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—