Real time implementation of an ANFIS-based induction motor drive via feedback linearization for performance enhancement

Abstract

This research study displays a design of an adaptive neuro-fuzzy torque controller technique applied to induction motor drive via decoupling feedback linearization for enhancing the dynamic as well as the steady-state performance of induction motor drive. The decoupling controlled of induction motor 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. As the induction motor are represented by significantly complex and time-varying dynamics like parameter variation, outer annoyance and load changes, an adapted control strategy taking into account Adaptive Neuro-Fuzzy Inference System (ANFIS) based controller is implemented which is a coordinated methodology and it yields ideal results by selecting appropriate rule base unlike fuzzy logic control procedure. The execution and effectiveness of proposed control technique based linearized induction motor drive is investigated in MATLAB environment in various operating conditions and the superiority of the proposed controller is analysed and is contrasted with the conventional PI controller based linearized induction motor. The system is also implemented on real time system using DSP 2812 to validate the different control strategies.