Sensorless control of induction motor using a neural network for speed estimation
Marian P. Kaźmierkowski, Dariusz L. Sobczuk, Przemysław Filipek · 2002
In the paper the application of an on-line trained neural network working as a speed estimator is presented. Three different speed estimation algorithms: backpropagation, conjugate gradient as well as least squares are investigated and compared. Some oscillograms which illustrate properties and sensitivity to parameter changes of the speed estimation techniques are presented.