Neural Network Based Field Oriented Control for Doubly-Fed Induction Generator

Abstract

The present research paper deals with a study of a variable speed wind energy conversion system (VSWECS) based on a Doubly Fed Induction Generator (DFIG), the stator is directly connected to the grid and driven by climbed back-to-back converters. Direct control of DFIG with a variable structure based on an artificial neural network is presented. Artificial Neuronal Network ANN is proposed to improve performances and to substitute the classical PI regulators in the direct control of active and reactive powers of the DFIG. The performance of the approach has been tested and validated by simulation for different operating conditions. Simulation results and improvement of the behavior of the DFIG are presented, using Matlab/Simulink software.