In speed control of induction motors, generally the performance of induction motor by feedback controllers has been insufficient due to non-linear structure of the system, changing environmental conditions, and undesired disturbance input effects. Recently, researches clearly show that the benefits of using methods based on artificial intelligence to improve the performance of induction motor drive. In this study, an artificial intelligence-based controller is developed to control the speed of induction motor by using radial basis function neural networks (RBFNN) and the structure of model reference adaptive control (MRAC). Indirect vector control technique is widely preferred due to high torque response and accuracy in induction motor drive method. To determine the success of this method, its result is compared with conventional PI type controller in MATLAB/Simulink environment. In addition to that, the performance of controller is analyzed under fan type load used to determine reducing effect of speed. Simulation results show that MRAC controller performance based RBFNN are better than conventional PI type controller performance.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Model Reference Adaptive Control based on RBFNN for Speed Control of Induction Motors



    Erscheinungsdatum :

    2016-01-01


    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629





    RBFNN-Bagging-Model-Based Study on Bus Speed Predication

    Wang, Xiaoguang / Han, Hai-hua / Qie, Jin-hui et al. | Springer Verlag | 2020


    RBFNN Adaptive Longitudinal Direct Lift Control of Carrier-Based Aircraft Landing

    Sun, Xiaoyun / Jiang, Ju / Zhen, Ziyang et al. | TIBKAT | 2022


    RBFNN-Bagging-Model-Based Study on Bus Speed Predication

    Wang, Xiaoguang / Han, Hai-hua / Qie, Jin-hui et al. | British Library Conference Proceedings | 2020