ANFIS Speed Controller and Intelligent Dual Observer Based DTC of an Induction Motor

In this paper, a dual observer is used to achieve the sensorless direct torque control (DTC) of an induction motor (1M); combining a Luenberger observer (LO) based on the adaptive-network-based fuzzy inference system (ANFIS) for adaptation mechanism to estimate the rotor speed, and a Kalman filter (KF) in order to estimate the flux components. Furthermore, the conventional PI speed controller is replaced by an ANFIS controller aiming to enhance the 1M response characteristics which are represented in the smallest overshoot, shortest time of rising and settling, along with the highest resistance to disturbances. The overall proposed system contributes as well to the ripples problem reduction at the level of electromagnetic torque, flux and current. The proposed ANFIS-DTC is validated through Matlab simulations; a satisfying performance is proven in large operating conditions.