A reduced MF-based self-tuned robust neuro-fuzzy control of a decoupling linearized IM drive

This paper presents a design of a self-tuned adaptive neuro-fuzzy torque controller (NFTC) technique with reduced number of membership functions (MF) applied to a decoupling linearized induction motor (IM) drive for enhancing the performance. The decoupling controlled of IM is modeled by making the flux and torque decoupled and simulation is carried out in the stationary reference frame with linearized controlled, based on state space linearization technique. The proposed NFTC incorporates self-tune based the integrated approach of fuzzy logic control (FLC) and artificial neural network (ANN) scheme with three MFs for two-input NFTC as torque error and change in torque error, which makes it computationally more efficient as compared to five MFs based NFC [8] and thus, making easy for real time applications of high performance industrial drive. The effectiveness and performance of the proposed control technique based linearized IM drive is investigated in MATLAB environment in various operating conditions and the superiority of the proposed controller is analysed by comparing it to a conventional PI-torque controller based linearized hysteresis pulse width modulation (PWM) fed IM drive.