New Direct Torque Neuro-Fuzzy Control Based SVM for Dual Two Level Inverter-Fed Induction Motor

Abstract

In this paper, a novel direct torque neuro-fuzzy control (DTCNF) based space voltage modulation (SVM) technique for dual two level inverter fed induction motor is presented. The proposed scheme produces voltage space vector locations identical to those of a conventional three-level inverter. In this new scheme an adaptive NF inference system (ANFIS) to replace the switching table and the hysteresis comparators, for generate the reference voltage using space vector modulation (SVM) techniques for dual two level inverter. Compared with conventional direct torque control (C_DTC), in this new technique, the ripples of both torque and flux are reduced remarkable, and switching frequency is maintained constant. Simulation results verify the validity of the proposed method.
PDF