000003604 001__ 3604
000003604 005__ 20141118153353.0
000003604 04107 $$acze
000003604 046__ $$k2006-05-15
000003604 100__ $$aTurek, M.
000003604 24500 $$aSelflearning controller of active magnetic bearing

000003604 24630 $$n12.$$pENGINEERING MECHANICS 2006
000003604 260__ $$bInstitute of Theoretical and Applied Mechanics, AS CR, v.v.i., Prague
000003604 506__ $$arestricted
000003604 520__ $$2eng$$aThe active magnetic bearing control through self learning controller is described in this contribution. Controller’s coefficient (parameter) values come from actions of Continuous Action Reinforcement Learning Automatas (CARLAs) which continuously update the controller’s coefficients according to behavior of the active magnetic bearing. The goal of this on-line training is formulated as achievement of minimum mean square of control error. It is shown that CARLA method is capable of learning better parameters than standard method of optimal control design called LQ (linear quadratic) design. Described concept of control is proved by control of the active magnetic bearing.

000003604 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb.
000003604 653__ $$a

000003604 7112_ $$aENGINEERING MECHANICS 2006$$cSvratka (CZ)$$d2006-05-15 / 2006-05-18$$gEM2006
000003604 720__ $$aTurek, M.$$iPulchart, J.$$iBřezina, T.
000003604 8560_ $$ffischerc@itam.cas.cz
000003604 8564_ $$s593444$$uhttps://invenio.itam.cas.cz/record/3604/files/Turek-133-PT.pdf$$y
             Original version of the author's contribution as presented on CD, , paper No. 133.
            
000003604 962__ $$r3410
000003604 980__ $$aPAPER