A Neural Network Based Space-Vector PWM Controller for Motor Drive

Abstract

This paper proposed an artificial neural network (ANN) based space vector pulse width modulation (SVPWM) for motor drive which fully covers the undermodulation and overmodulation regions. A neural network has the advantage of very fast implementation of an SVPWM algorithm that can increase the converter switching frequency, particularly when a dedicated application-specific integrated circuit chip is used in the modulator. Finally, in the environment of MATLAB/Simulink with the Neural Network Toolbox builds the simulation model of system with proposed ANN-SVPWM controller. The simulation results show that the performances of the motor drive with artificial-neural-network-based SVPWM are excellent.