Data-Driven Design of Fuzzy Logic Fault Tolerant Control for a Wind Turbine Benchmark

This paper proposes a fuzzy modelling and identification approach oriented to the design of a fault tolerant fuzzy controller for regulating both the pitch angle and the reference torque of a wind turbine benchmark. This strategy has been suggested for enhancing the regulator design that could represent an alternative to the standard switching controller, already implemented in the wind turbine test system. The controller project requires the knowledge of a dynamic model of the wind turbine, which is achieved by means of a fuzzy modelling and identification scheme. On the other hand, the proposed fuzzy controller structure is straightforward and easy to implement with respect to different strategies proposed in literature. Moreover, by exploiting the fuzzy identification procedure, the proposed strategy is also able to provide a fault tolerant controller. In this way, the fault tolerance properties are thus achieved by using a so called passive scheme. The results obtained with the designed fuzzy controller are compared to those of a switching controller already implemented for the wind turbine benchmark.