Artificial neural networks rotor time constant adaptation in indirect field oriented control drives

The decoupling between the flux and torque is lost in an indirect rotor field oriented control if there is a mismatch between the controller programmed rotor time constant and the actual time constant of the motor. This occurs due to the heating and saturation of the magnetizing inductance of the motor. Adaptation of this rotor time constant is thus required, and it is necessary to estimate this parameter on-line in order to maintain it equal to its nominal value programmed in the decoupling controller. This paper presents a new control scheme for rotor time estimation using artificial neural networks (ANNs). This method, based on estimation of the rotor time constant from motor terminal variables (stator voltage, current and frequency), can be applied to the conventional (FOC) as well as to the artificial neural network control method (ANN-FOC) of vector control. The training of the ANN and the simulation of the drive system is presented. Presented results confirm the feasibility of the proposed scheme for conventional and ANN field oriented control implementations.