PROJECT TITLE :

A Novel Neural Network Vector Control Technique for Induction Motor Drive

ABSTRACT:

This paper proposes a unique neural network (NN)-based mostly vector management technique for a three-part induction motor. The proposed NN vector control utilizes the rotor flux-oriented reference frame, and therefore the role of the NN controller is to substitute the 2 decoupled current-loop proportional-integral (PI) controllers in conventional vector management techniques. The objective of NN coaching is to approximate optimal management and also the NN controller was trained by Levenberg–Marquardt (LM) algorithm. Forward Accumulation Through Time algorithm for induction motor was developed to calculate Jacobian matrix required by the LM algorithm. The simulations showed that the NN vector control can give higher current tracking ability than the conventional vector management, like less oscillations and low harmonics. Especially, the NN vector management will better overcome the problem of detuning effects than the conventional vector control. The hardware experiments any demonstrated the good advantage of the NN vector management. The NN vector management can reach driving the induction motor without audible noise using comparatively lower switching frequency or lower sampling rate compared with the standard vector control, and so has the potential to enhance potency and scale back size and price of an induction motor drive system.