El-Mahjoub Boufounas, Jaouad Boumhidi, Mohammed Ouriagli, and Ismail Boumhidi
Doubly fed induction generator, sliding mode control, generalregression neural network, adaptive particle swarm optimizationNomenclaturev wind speed, m/s1ρ air density, kg/m3∗ LESSI Laboratory, Department of Physics, Faculty ofSciences Dhar Mehraz, Sidi Mohammed ben Abdellah Uni-versity, Morocco; e-mail: [email protected], [email protected]∗∗ LIIAN Laboratory, Department of Computer Science, Facultyof Sciences Dhar Mehraz, Sidi Mohammed ben AbdellahUniversity, Morocco
In the present paper, an optimal robust general regression neural network sliding mode (GRNNSM) controller is designed for a doubly fed induction generator (DFIG) wind turbine. Sliding mode control (SMC) technique appears as a particularly appropriate option to cope with DFIG-based wind turbine. However, it presents some drawbacks linked to the chattering due to the higher needed switching gain in the case of large uncertainties. In order to guarantee the wind power capture optimization without any chattering problems, this study proposes to combine the SMC with the general regression neural network (GRNN) based on adaptive particle swarm optimization (APSO) algorithm. The GRNN is used for the prediction of uncertain model part and hence enables 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 effectiveness of the designed method is illustrated in simulations by the comparison with the standard sliding mode technique using only the nominal model.
Important Links:
Go Back
