Improvement of the Vector Control for DFIG Integrated into a Wind System by Artificial Neural Networks Accompanied by a Reliability Study of the Control System

The aim of the current work presented in this paper is to integrate artificial intelligence (AI) techniques into field-oriented command to control the active and reactive powers of doubly fed induction generator (DFIG) integrated into a wind system, in order to improve the performances of the conventional vector control. In the first step we are particularly interested in the application of indirect vector control by stator field orientation of DFIG, using two types of controllers: conventional regulators (PI) and Neural Networks (NN) controllers, and compare their simulation results using Matlab/Simulink software. And in the second step we performed an uncertainty analysis to verify the reliability of our designed model by applying a stochastic analysis and a sensitivity study based on the Monte Carlo simulation. The obtained results are satisfactory and consistent with those of the references, which confirm that the intelligent controller's presents best performances in term of the response time as compared to that of the PI regulators. Moreover, the Monte Carlo test confirms the effectiveness and the reliability of the NN controllers against machine parameters variations.