Research of AC adjusting speed system based on DTC and neural network supervision control

摘要

The conventional direct torque control system in low speed condition has the larger motor torque ripple, that makes the system's low-speed performance poor. To address this problem, we use neural network supervisory controller to replace the original PID controller based on the traditional direct torque control system, and create a system model by the Sim Power Systems of MATLAB software. This system is simulated on the MATLAB / Simulink simulation platform, and the simulation results are compared with the original system's. Simulation results show that this method can effectively reduce the torque ripple of the direct torque control system in low-speed condition and improve the system's low-speed performance.