Reduction of Current , Flux and Torque Ripple Contents of Dtc for an Induction Motor Drive by Using Pi and Ann Controller

Three-level neutral-point-clamped (NPC) inverters are very appropriate for high-power adjustable-speed drive applications. Direct torque control is characterized by the merits of fast response, simple structure and strong robustness to motor parameters variations. This paper presents a 3-level inverter-fed direct torque controlled (DTC) induction motor (IM) drive based on optimized switching table. The problems of high voltage jump, smooth vector switching and neutral point balance are investigated and solved by introducing appropriate intermediate vectors. Induction machine drive based on Direct Torque Control (DTC) allows high dynamic performance with very simple hysteresis control scheme. Conventional Direct Torque Control (CDTC) suffers from some drawbacks such as high current ripple, flux ripple and torque ripple, difficulties in torque as well as flux control at very low speed. In this paper an intelligent approach of artificial neural network to improve the direct torque control of induction machine. Comparison study is carried out between direct torque neural networks control (ANNDTC) and (CDTC). Both simulation and experimental results are presented to verify the effectiveness of the proposed schemes introduced in this paper.