신경회로망을 이용한 유도전동기의 적응백스테핑 제어

Abstract

유도전동기의 계자저항 모델에 기초하여 특이성을 회피하고, 전력효율을 향상시킬수 있도록 속도 및 자속 추정을 위한 신경회로망을 이용한 적응 백스테핑 제어기를 제안하였다. Based on a field-oriented model of induction motor, adaptive backstepping approach using neural network(RBFN) is proposed for the control of induction motor in this paper. In order to achieve the speed regulation with the consideration of avoiding singularity and improving power efficiency, rotor angular speed and flux amplitude tracking objectives are formulated. rotor resistance uncertainty is compensated by adaptive backstepping and mechanical lumped uncertainty such as load torque disturbance, inertia moment, friction by RBFN. Simulation is provided to verify the effectiveness of the proposed approach.