Implementation of an on-line resistance estimation using artificial neural networks for vector controlled induction motor drive

This paper presents a new method of on-line estimation for the stator and rotor resistances of the induction motor in the indirect vector controlled drive, using artificial neural networks. The backpropagation algorithm is used for training of the neural networks. The error between the desired state variable of an induction motor and the actual state variable of a neural model is back propagated to adjust the weights of the neural model, so that the actual state variable tracks the desired value. The performance of the neural estimator and torque and flux responses of the drive, together with this estimator, are investigated with the help of simulations for variations in the stator and rotor resistance from their nominal values. Both these resistances are estimated experimentally, in a vector controlled induction motor drive and found to give accurate estimates. The rotor resistance estimation was found to be insensitive to the stator resistance variations both in simulation and experiment.