Adaptive B-spline neural network-based vector control for a grid side converter in wind turbine-DFIG systems

This paper presents a novel control system design for the grid-side converter of doubly fed induction generator wind power generation systems. The control method proposed in this work is a vector control based on adaptive B-spline neural network by using a simple fixed-gain stabilizing control topology. The adaptive control is designed both for inner current loops and an outer DC-link voltage loop of the grid side converter control system. To guarantee the control stability, the weights updating rule for the B-spline neural network is synthesized by utilizing Lyapunov's direct method. To verify the effectiveness of the proposed control system, extensive simulations are performed using MATLAB/Simulink. Based on the simulation results, it is concluded that the proposed controller has improved performance compared to an optimum proportional integral control system. It is also relatively robust against external disturbances and variations of the control parameters.