Speed control of induction motors using neuro-fuzzy dynamic sliding mode control

Abstract

Abstract

This paper presents a novel approach for robust speed control of medium size induction motors using neuro-fuzzy dynamic sliding mode control. First, a simple dynamic model of induction motors is introduced. Then, a conventional sliding mode control is presented. To reduce the chattering phenomenon, dynamic sliding mode control is designed using a secondary PID-type sliding surface. Moreover, in order to eliminate the tedious trial and error procedure in choosing a proper uncertainty upper bound, uncertainties have been estimated using a neuro-fuzzy system. The online training of the neuro-fuzzy dynamic sliding mode control is based on the adaptation law derived from the stability analysis. In addition, the reconstruction error of the neuro-fuzzy system is compensated to guarantee the asymptotic convergence of the speed tracking error. Simulation results verify that the neuro-fuzzy dynamic sliding mode control is robust against various uncertainties including parametric variations, external load disturbance, unmodeled dynamics and input voltage disturbances.