Fault tolerant control of an offshore wind turbine model via identified fuzzy prototypes

In order to improve the safety, the reliability, the efficiency, and the sustainability of offshore wind turbine installations, thus avoiding expensive unplanned maintenance, the accommodation of faults in their earlier occurrence is fundamental. Therefore, the main contribution of this work consists of the development of a fault accommodation scheme applied to the control of a wind turbine nonlinear model. In particular, a data-driven strategy relying on fuzzy models is exploited to build the fault tolerant control scheme. Fuzzy theory is exploited here since it allows to approximate easily the unknown nonlinear model and manage uncertain data. Moreover, the fuzzy prototypes, which are directly identified from the wind turbine measurements, provide the reconstruction of the considered faults, thus leading to the direct design of the fault tolerant control module. In general, the nonlinearity of wind turbine system could generate complex analytic solutions. This aspect of the work, followed by the simpler strategy relying on fuzzy prototypes, represents the key point when on-line implementations are considered for a viable application of the proposed methodology. A realistic offshore wind turbine simulator is used to validate the achieved performances of the suggested methodology. Finally, comparisons with different fault tolerant control methods serve to highlight the advantages of the suggested approach.