ESTIMATION OF INDUCTION MOTOR PARAMETERS USING NEURAL NETWORKS PRINCIPLES

Dušan Balara - Jaroslav Timko

   Artificial Neural Networks (ANN) can be utilized in estimators both for nonparametric and parametric identification. A method for estimation of the electrical and mechanical parameters of an induction motor is presented in this paper. Adaptive models of particular subsystems of motor and simple adaptation rule are presented as well as the results of a simulation using a model of the squirrel-cage induction motor. The adaptation rule was derived based on the gradient descent algorithm widely used in training of Artificial Neural Networks.

Keywords: drives, estimation techniques, induction motors, neural networks

[full-paper]