Neural estimators for shaft sensorless FOC control of induction motor

The paper deals with a problem of speed estimation in a shaft sensorless field oriented control structure with induction motor that is based on neural modelling approach. Two different neural estimators were developed; one for observing the magnetic flux and the other one for observing motor angular speed. Structures of the artificial neural network estimators are based on measurable motor variables: components of stator current and voltage in rotating system x-y. Simulation results of the neural angular speed estimator were verified by a Real-Time system. In case of the Real-Time verification the developed neural estimator of rotor angular speed is based on measurable motor variables, components of stator current and voltages in d-q reference system.