Akademska digitalna zbirka SLovenije - logo
Library of Technical Faculties, Maribor (KTFMB)
  • A fuzzy self-learning position control of hydraulic drive
    Detiček, Edvard
    Fluid power actuators are characterized by their high-power density and excellent dynamic response. The hydraulic actuator, in particular, is capable of very high output power levels combined with ... very compact drive unit dimensions. It is ideally suited for many high dynamic applications in modern machines and mechanical systems. However, the disadvantages of hydraulic systems, such as nolinear dynamic behaviour due to friction, fluid compressibility, etc., need to be overcome. This is successfully obtainable only by implementing modern digital control systems designed on the basis of modern control theory. In other words, the modrn electro-hydraulic drive has to posses more and more intelligence. The objective of many researchers is, therefore, to develop an algorithm that will be able to control the drive without any a priori knowledge of geometrical, operating, or any other parameters of the system. An attempt to achieve the above objective is presented in this article. The proposed new control strategy used a combination of a fuzzy logic controller designed as a self-learning fuzzy system, based on a reinforcement learnng method. The reference tracking behaviour is improved by inverse model digital force filter, while the accurate final positioning is achieved by a switching integrator. The obtained experimental results are included.
    Source: Cybernetics and systems. - ISSN 0196-9722 (Vol. 31, No.8, December 2000, str. 821-836)
    Type of material - article, component part
    Publish date - 2000
    Language - english
    COBISS.SI-ID - 5942550

source: Cybernetics and systems. - ISSN 0196-9722 (Vol. 31, No.8, December 2000, str. 821-836)

loading ...
loading ...
loading ...