A neuro-adaptive maximum power tracking control of variable speed wind turbines with actuator faults

This paper presents a neural adaptive fault tolerant control design of wind turbines in partial load operation. The controller is designed to be robust against actuator faults as well as noise, while keeping the wind turbine generating as much power as possible. The wind speed variation is considered as an external disturbance, and an adaptive radial basis function neural network is utilized to estimate aerodynamic torque. Estimation of a fault size and establishment of a desired trajectory are adopted in the design. Using the proposed method, the reliability of wind power generation is increased so as to track the optimum power point under faulty conditions, close to the fault free case. Uniformly ultimately boundedness of the closed-loop system is achieved using Lyapunov synthesis. The designed controller is verified via numerical simulations, showing comparison with an industrial reference controller, using predefined criteria.