Neural sliding mode field oriented control for DFIG based wind turbine

Abstract

Wind energy has many advantages, because it does not pollute and is an inexhaustible source of energy. The Double Fed Induction Generator (DFIG) is one of the most important generator used for Horizontal Axis Wind Turbine (HAWT). The DFIG stator is linked directly to the grid, whilst the DFIG rotor is coupled via an electronic converter. In this paper, a discrete-time Neural Sliding Mode (N-SM) Field Oriented Control (FOC) for DFIG stator active and reactive powers control is proposed. The adaptive nature of the proposed controller improves the transient response as compared with discrete-time Conventional Sliding Mode Control (C-SMC) for DFIG parameters variations and disturbances. The proposed controller is based on a Recurrent High Order Neural Network (RHONN), using an Extended Kalman Filter (EKF) as training law. The RHONN works as an identifier to obtain an accurate model, which is robust against disturbances and parameter variations. A comparison between C-SMC and N-SMC is included. The validity and the effectiveness of the proposed controller are tested using Matlab/Simulink simulation results.