Neural control of the Wells turbine-generator module

Wave energy is one of the most promising forms of ocean renewable sources because of its high availability. The Wells turbine has been one of the defining technologies in the development of wave energy. In this paper a neural control method for the Wells turbine-generator module is presented. For this purpose, a neural control using the backpropagation algorithm has been implemented, based on the addition of external resistances in series with the rotor winding of the induction generator connected to the turbine. The proposed control system does appropriately adapt the rotor resistance according to the pressure drop entry. It will be shown how the controller avoids the stalling behaviour and that the average power of the generator fed into the grid is significantly higher in the controlled case than in the uncontrolled one.