Artificial intelligence applications in direct torque control

The purpose of this paper is to show a new direct torque control (DTC) scheme that allows to improve the performance of a sensorless induction motor (IM) speed control in terms of less stator flux and currents distortions, keeping a constant switching frequency in the inverter. It is also shown a fuzzy logic application for tuning the PI speed controller, The work proposes a complete DTC scheme using two different stator resistance estimators, one of them is a neural network (ANN) and the other one is an adaptive neuro-fuzzy methodology to build a sugeno fuzzy estimator. Experimental and simulation results have been carried out, showing the advantages of the new scheme.