Stator resistance estimation using ANN in DTC IM drives

Torque control of induction motors (IM) requires accurate estimation of the flux in the motor. But the flux estimate, when estimated from the stator circuit variables, is highly dependent on the stator resistance of the IM. As a result, the flux estimate is prone to errors due to variation in the st...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Elektrik : Turkish journal of electrical engineering & computer sciences 2010-01, Vol.18 (2), p.197-210
Hauptverfasser: OKUMUS, H. İbrahim, AKTAŞ, Mustafa
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Torque control of induction motors (IM) requires accurate estimation of the flux in the motor. But the flux estimate, when estimated from the stator circuit variables, is highly dependent on the stator resistance of the IM. As a result, the flux estimate is prone to errors due to variation in the stator resistance, especially at low stator frequencies. In this paper, an Artificial Neural Network (ANN) is used to adjust the stator resistance of an IM. A back propagation training algorithm was used in training the neural network for the simulation. The proposed ANN resistance estimator has shown good performance in both the transient and steady states. The system is first simulated with computer software and tested by hardware in the loop. Then, it is implemented using a TMS320C6711, 32-bit fixed point Digital Signal Processor (DSP). Experimental and simulated results prove the usefulness and feasibility of the proposed strategy as compared with conventional methods.
ISSN:1303-6203
1300-0632
1303-6203
DOI:10.3906/elk-0812-6