Robust Control based on Backstepping and adaptive neural network for the DFIG based WECS
Résumé
The objective of this paper is extracting the maximum wind power from a doubly fed induction generator (DFIG) based wind energy conversion system (WECS). The DFIG model is uncertain due to the absence of total knowledge to the system's parameters, such as inductances, resistance, and the external perturbations. Thus the need for intelligent robust controllers. In this article we propose a Backstepping controller based on Adaptive Neural Networks (ANN), the principle of the proposed strategy is that the controller uses a rejection term equivalent to the ANN estimated value of these uncertainties. The ANN weights are trained online based on an integral law, the stability of the system and the convergence of the tracking error is proven via Lyapunov theory. Simulation results confirm the ability of the ANN to estimate the uncertainties, the robustness and the efficiency of the proposed controller.