Fault tolerant control design for a wind farm benchmark via fuzzy modelling and identification

In order to improve the safety, the reliability, and the efficiency of wind farm installations, thus avoiding expensive unplanned maintenance, the accommodation of faults in their earlier occurrence is fundamental. Therefore, the main contribution of this paper consists of the development of a tolerant control scheme applied by means of a direct and viable approach. In particular, a data-driven strategy based on fuzzy logic is exploited for deriving the fault tolerant control scheme. Fuzzy theory is exploited since it is able to approximate easily unknown nonlinear models and manage uncertain data. Moreover, these fuzzy prototypes are directly identified from the wind farm measurements and lead to the straightforward design of the fault tolerant control scheme. In general, an analytic approach, where the system nonlinearity is explicitly considered, would require more complex control design methodologies. This aspect of the work, followed by the simpler solution relying on fuzzy rules, represents the key point when on-line implementations are considered for a viable application of the proposed methodology. A realistic wind farm simulator is used to validate the achieved performances of the suggested methodology.