Study of neural network application on direct torque control of induction machine

This paper presented a BP neural network resistance estimation scheme for direct torque control (DTC) of an induction machine. The neural estimator observes the stator current to detect the changes in the stator resistance. Simulation models are constructed using MATLAB/SIMULINK to analyse the application of the neural network on the DTC, which is trained to follow the relationship between the stator current and stator resistance. Improved performance such as dynamics characteristic can be tested through the simulation.