Optimal intelligent control for a variable-speed wind turbine using general regression neural network and adaptive PSO algorithm

Abstract

In this paper, a robust optimal general regression neural network sliding mode (GRNNSM) controller is designed for a variable speed wind turbine (VSWT). The main objective of the controller is to optimise the energy captured from the wind. Sliding mode control (SMC) approach emerges as an especially suitable option to deal with a VSWT. However, for large uncertain systems, the SMC produces chattering problems due to the higher needed switching gain. In order to guarantee the wind power capture optimisation without any chattering problems, this study propose to combine the SMC with the general regression neural network (GRNN) based on adaptive particle swarm optimisation (APSO) algorithm. The GRNN is used for the prediction of uncertain model part and hence enable a lower switching gain to be used for compensating only the prediction errors. The APSO algorithm with efficient global search is used to train the weights of GRNN in order to improve the network performance in terms of the speed of convergence and error level. The stability is shown by the Lyapunov theory and the control action used did not exhibit any chattering behaviour. The effectiveness of the designed method is illustrated in simulations by the comparison with traditional SMC.