Neural networks applied for induction motor speed sensorless estimation

In this paper, two schemes using neural networks (NN) as speed estimators in induction motor field oriented controlled (FOC) drives are compared. The first estimator consists of a two-layer neural network (often called a perceptron) while in the second a three-layer neural network is used for motor speed estimation. Both estimators are simulated with an indirect field oriented controller (IFOC) for induction motor drives.