An Adaptive Neuro-Fuzzy Controller for a Wind Turbine Operating in Region 3

An adaptive neuro-fuzzy controller for large and flexible wind turbines operating in high-speed winds is presented. The control objective is to regulate the rotor speed at the given rated power in region 3 (full load) via collective blade pitch angle. The modeled turbine is a three-bladed, upwind machine with flexible blade and tower. We use the particle swarm optimization (PSO) method in off-line training of our adaptive neuro-fuzzy controller. Numerical simulations are performed using wind inflow step change with the nonlinear wind turbine model. We compare the performance of the proposed controller with the baseline PI controller. Simulation results confirm successful performance of the proposed controller.