Modelling the aerodynamic coefficients of wind turbines by using neural networks for control design purposes

Abstract

In the present contribution, the modelling of the aerodynamic coefficients of wind turbines are obtained by using an artificial neural network (ANN) and it is analysed from the control application point of view. The obtained results show that the artificial neural network approach is appropriate to fit the data of the aerodynamic coefficients with high accuracy. The advantage of the approach is that the ANN provides an analytical equation (including its derivatives) that can be embedded in the general dynamic model, which is used for the control system design.