engleski

Stator resistance tuning based on a neural network in an indirect rotor field oriented control system of an induction motor

This paper presents an ANN-based (artificial neural network-based) method of stator resistance tuning in an IRFO (indirect rotor field oriented) control system of an induction motor. This method is based on the conventional two-layer ANN in which the rotor time constant is not a constant parameter and is identified using a model reference adaptive system (MRAS) - based procedure. During the training, rotor speed estimation of the induction motor is enabled. The difference between the actual and the estimated rotor speed is used as a signal for manual stator resistance tuning. Computer simulations and experimental results show the effectiveness of the described approach in a low rotor speed region.

induction motor, indirect field-oriented control, neural network, adaptive control

DOI: 10.1007/978-3-540-85563-7 ; 12th International Conference KES 2008 : Proceedings. Part I. ; Zagreb, Hrvatska ; 03.-05.09.2008. ; ISSN 0302-9743