Direct Torque Control of Induction Motor Based on Neurofuzzy

Abstract

The main objective of this work is to improve the speed and torque responses of three phase Induction Motor (IM) during different loads and speeds conditions. Induction Motor is most commonly used in different industrial applications, that require fast dynamic response and accurate control over wide speed ranges. Therefore, this work proposes Direct Torque Control (DTC). Particle Swarm Optimization (PSO) technique is used for optimal gains tuning of PI. The results show the improvement in the speed response of DTC, in terms of reducing steady state error, ripple reduction in the torque and speed responses. Neurofuzzy (ANFIS) controller is used to improve the performance of PI-PSO controller. ANFIS controller is trained by using PI-PSO data. The results of the ANFIS controller are better than PI-PSO in terms of torque ripple minimization, less steady state error in the speed response and more robustness. The simulation of the overall drive system is performed using MATLAB/Simulink program version 7.10 (R2010a).

Keywords

• induction motor
• direct torque control
• pi controller
• particle swarm optimization