•  
  •  
 

Turkish Journal of Electrical Engineering and Computer Sciences

DOI

10.3906/elk-0812-6

Abstract

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.

Keywords

Induction machine, direct torque control (DTC), artificial neural network, stator resistance estimation.

First Page

197

Last Page

210

Download

Share

COinS