Báo Cáo A New Artificial Neural Network Space Vector PWM Controller for Voltage Source Inverter

Abstract​

This paper presents a new neural-network-based controller of space vector modulation (SVM) of a voltage-fed inverter. This ANN-SVPWM controller completely covers the undermodulation and overmodulation modes linearly extending operation smootly up to square wave (six-step) by using theory of modulation between the limit trajectories with the famous linearity. The ANN controller has the advantage of very fast implementation of an SVM algorithm that can increase the switching frequency of power switches of the static converter. The design uses the individual training strategy with the fixed weight and supervised models. The ANN-SVPWM Controller can be used in V/Hz control technique and extended to a vector control method. A computer simulation program is developed using Matlab/Simulink together with the Neural Network Toolbox for training the ANN-controller.

Keyword: Space vector, Pulse-Width- Modulation, Artificial Neural Network, Voltage Source Inverter, undermodulation, overmodulation .