Naslov
Multilayer Neural Network Verification of Mutual Inductance Choice in Sensorless Induction Motor Vector Control System

Autori
Smajo, Mate ; Vukadinović, Dinko

Izvornik
WSEAS transactions on systems (1109-2777) 3 (2004); 752-756

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Induction motor; vector control; observer; neural network; speed estimation

Sažetak
Squirrel-cage induction motor (IM) is the most frequently used electric machine in modern controlled electromotor drives. In this paper is analyzed IM sensorless vector control system based on MRAS (Model Reference Adaptive System) theory. It is especially important get knowledge of the IM rotor time constant incorporated into observer (Fig. 1.). In this constant is incorporated IM mutual inductance Lm. The characteristic of the observed IM is varying of mutual inductance Lm at lower frequency of supply voltage due to saturation effect in iron. In this paper accuracy of the mutual inductance Lm in the observer of induction motor vector control is verified by using feedforward static four layer artificial neural network (ANN).

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika

POVEZANOST RADA