Artificial Neural Network Based Speed Tracking of a Field Oriented Induction Motor Drive

In this paper, an Artificial Neural Network (ANN) is used as a speed tracker for induction motor drive. The control scheme consists of a neural network with Correlated Real Time Recurrent Learning (CRTRL) algorithm for changing the weights of neural network to track the command speed of induction motor drive accurately. The effectiveness of the controller is tested for the tracking property using different types of reference speed. A sensorless scheme is proposed to overcome the disadvantages of rotor position sensors. Through measurement of the voltages and the currents the neural network is capable to estimate the rotor position, thereby facilitating elimination of the rotor position sensor. Simulation and experimental results show that the proposed controller provides accurate speed tracking characteristics and is robust against the changes of motor command speed and external load disturbances.