This paper deals with the fault diagnosis of wind turbines and investigates viable solutions to the problem of earlier fault detection and isolation. The design of the fault indicator, i.e., the fault estimate, involves data-driven approaches, as they can represent effective tools for coping with poor analytical knowledge of the system dynamics, together with noise and disturbances. In particular, the proposed data-driven solutions rely on fuzzy systems and neural networks that are used to describe the strongly nonlinear relationships between measurement and faults. The chosen architectures rely on nonlinear autoregressive models with exogenous input, as they can represent the dynamic evolution of the system along time. The developed fault diagnosis schemes are tested by means of a high-fidelity benchmark model that simulates the normal and the faulty behaviour of a wind turbine. The achieved performances are also compared with those of other model-based strategies from the related literature. Finally, a Monte-Carlo analysis validates the robustness and the reliability of the proposed solutions against typical parameter uncertainties and disturbances.