A neuro fuzzy PI controller used for speed control of a direct torque to twelve sectors controlled induction machine drive

This paper presents a new speed controller based on the theory of adaptive fuzzy inference system based on neural (ANFIS) for a direct torque to twelve sectors controlled of the induction motor. The proposed controller integrates fuzzy logic algorithm with a structure of artificial neural network (ANN) five-layer in order to reap the benefits of both methods, the learning abilities of the first and readability and flexibility of the second. The controller replaces the conventional PI is the rule fuzzy inference system with the hybrid learning algorithm. This makes learning the fuzzy system. The performance of the proposed neuro-fuzzy control for induction motor speed was studied at different operating conditions. The simulation study shows the robustness and relevance of control for applications in high performance driving.