Induction motor dynamic neural stator flux estimation using active and reactive power for direct torque control

In this paper, a new dynamic neural network stator flux and electromagnetic torque estimation method of the squirrel cage motor direct torque control is developed. The proposed method is based on an instantaneous active and reactive power and delayed samples of stator currents and voltages of the machine. This approach requires neither resistances nor inductances. The technique is robust and independent of variation in the electromagnetic parameters. Simulation results using Simulink are presented to confirm the theoretical analysis.