DESIGN OF ASYNCHRONOUS MOTOR CONTROLLER THROUGH Q-LEARNING

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F05%3APU52004" target="_blank" >RIV/00216305:26210/05:PU52004 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
DESIGN OF ASYNCHRONOUS MOTOR CONTROLLER THROUGH Q-LEARNING
Original language description
The paper is focused on the effect of reinforcement function and the effect of actions set extension on performance of Q-learning used for small asynchronous electric motor control. The learning process was divided into two phases - pre-learning stage and tutorage stage. Pre-learning stage uses conventional q-learning procedure and requires the computation model of asynchronous motor. This phase is very effective. Second stage - tutorage stage already uses real motor for improvement of settings obtainedd in the first stage. Controller designed this way is used in scalar control.
Czech name
DESIGN OF ASYNCHRONOUS MOTOR CONTROLLER THROUGH Q-LEARNING
Czech description
The paper is focused on the effect of reinforcement function and the effect of actions set extension on performance of Q-learning used for small asynchronous electric motor control. The learning process was divided into two phases - pre-learning stage and tutorage stage. Pre-learning stage uses conventional q-learning procedure and requires the computation model of asynchronous motor. This phase is very effective. Second stage - tutorage stage already uses real motor for improvement of settings obtainedd in the first stage. Controller designed this way is used in scalar control.

Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—

Publication year
2005
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)