Neural network based efficiency optimization of an induction motor drive with vector control

In this paper an efficient optimization controller for a vector control induction motor drive is studied using a neural network. A 2-5-7-1 neural network has been designed to estimate the optimum rotor flux for the motor. The network has been trained using a complete motor loss model, taking into account the magnetic deviations of the motor parameters. Simulation results are shown to demonstrate the validity of the proposed methods.