Optimal neural network sliding mode control without reaching phase using genetic algorithm for a wind turbine

In this paper, an optimal neural network sliding mode control without reaching phase based on genetic algorithm (NNSMC) is designed for a variable speed wind turbine. Classical sliding mode control can be used for nonlinear systems. However, it presents some drawbacks linked of chattering, due to the higher needed switching gain in the case of large uncertainties. In order to reduce this gain, neural network is used for the prediction of model unknown parts and hence enable a lower switching gain to be used. Genetic algorithm is used to optimize both, the learning rate of BP and the variable switching gain. The elimination of reaching phase yields in a considerable amelioration of system robustness, so the proposed approach is based on the modification of the output tracking error. The performance of the proposed approach is investigated in simulations.