Stator and rotor resistance observers for induction motor drive using fuzzy logic and artificial neural networks

This paper presents a new observer for the rotor resistance of an indirect vector controlled induction motor drive using artificial neural networks supplemented by a fuzzy logic based stator resistance observer. The error between the rotor flux linkages based on a neural network model and a voltage model is back propagated to adjust the weights of the neural network model for the rotor resistance estimation. The error between the measured stator current and its corresponding estimated value is mapped to a change in stator resistance with a proposed fuzzy logic. The stator resistance observed with this approach is used to correct the rotor resistance observer using neural networks. The performance of these observers and torque and flux responses of the drive, together with these estimators, are investigated with the help of simulations. Both modeling and experimental data on tracking performances of these observers are presented. With this approach accurate rotor resistance estimation was achieved and was made insensitive to stator resistance variations both in modeling and experiment.