A system and method are provided for controlling a wind turbine. Accordingly, a component of the wind turbine is monitored by at least one sensor of a sensor system. An output is received from the sensor system which indicates a fault with the sensor. A fault accommodation response is generated by a fault module. The fault accommodation response includes an accommodation signal which replaces the output signal of the faulty sensor.

A method of designing a wind turbine rotor blade. The method includes selecting a gravity load safety factor associated with wind turbine rotor blade fatigue loading due to gravity, that is selected to be less than a defined wind load safety factor associated with wind turbine rotor blade fatigue loading that is not due to gravity. The method includes determining a gravity-corrected design load for wind turbine rotor blade deflection, that is determined based on the selected gravity load safety factor and the defined wind load safety factor. The method includes designing a gravity-corrected wind turbine rotor blade in accordance with the determined gravity-corrected design load.

A computer system suitable for estimating the expected change in annual energy production (AEP) of a wind turbine due to structural deterioration of blades of the wind turbine, said computer system being arranged to execute the following steps: loading a dataset representing estimated lift and drag curves at specific radial locations along the original blade of the wind turbine, building a baseline BEM model of the wind turbine based on said estimated lift and drag curves of the original blade and analysing the model to provide a baseline AEP estimation of the wind turbine with original blades, loading a dataset representing aerodynamic effects of identified structural deteriorations at specific radial locations along each of the blades of the wind turbine, using the dataset of aerodynamic effects to generate modified lift and drag curves at specific radial locations along each of the blades.

A system and method are provided for controlling a wind turbine of a wind farm. Accordingly, a controller implements a first model to determine a modeled performance parameter for the first wind turbine. The modeled performance parameter is based, at least in part, on an operation of a designated grouping of wind turbines of the plurality of wind turbines, which is exclusive of the first wind turbine. The controller then determines a performance parameter differential for the first wind turbine at multiple sampling intervals. The performance parameter differential is indicative of a difference between the modeled performance parameter and a monitored performance parameter for the first wind turbine. A second model is implemented to determine a predicted performance parameter of the first wind turbine at each of a plurality of setpoint combinations based, at least in part, on the performance parameter differential the first wind turbine. A setpoint combination is then selected based on the predicted performance parameter and an operating state of the first wind turbine is changed based on the setpoint combination.

The present disclosure is directed to a system and method for assessing farm-level performance of a wind farm. The method includes operating the wind farm in a first operational mode and identifying one or more pairs of wind turbines having wake interaction. The method also includes generating a pairwise dataset for the wind turbines pairs. Further, the method includes generating a first wake model based on the pairwise dataset and predicting a first farm-level performance parameter based on the first wake model. The method also includes operating the wind farm in a second operational mode and collecting operational data during the second operational mode. Moreover, the method includes predicting a first farm-level performance parameter for the second operational mode using the first wake model and the operational data from the second operational mode. The method further includes determining a second farm-level performance parameter during the second operational mode. Thus, the method includes determining a difference in the farm-level performance of the wind farm as a function of the first and second farm-level performance parameters.

A computer-implemented method for generating a prediction model for predicting rotor blade damages of a wind turbine is provided, wherein the method provides data including data sets for wind turbines, where each data set includes respective values of turbine variables(s), weather variable(s) and damage variable(s) wherein the method includes: a) discretizing the values, resulting in modified data sets; b) structure learning of a plurality of Bayesian networks based on the modified data sets, where each Bayesian network is learned by another learning method; c) determining an optimum Bayesian network based on a performance measure reflecting the prediction quality of a respective Bayesian network, where the optimum Bayesian network has the best performance measure; d) parameter learning of the optimum Bayesian network based on the modified data sets, resulting in conditional probabilities, where the optimum Bayesian network combination with the conditional probabilities is the prediction model.

A method for predicting remaining useful life of a wind or water turbine or component determines in step 116 an EOH for the turbine or component and compares this in step 118 to an EOH limit obtained in step 114. This provides a simple approach to estimating remaining useful life, giving the turbine operator an indication of the condition of turbines or farms under management.

The invention relates to monitoring a wind turbine having an electrical component. An exterior temperature and power loss associated with the electrical component is obtained, and a thermal model describing the electrical component is executed, based on the exterior temperature and power loss, to determine an internal temperature of the electrical component. A further thermal model describing the electrical component is executed, based on the internal temperature and an exterior component temperature, to predict a future thermal condition of the electrical component in order to monitor operation of the wind turbine.

The present disclosure is directed to a system and method for micrositing a wind farm having a plurality of wind turbines. The method includes (a) determining, via a loads optimization function, one or more wind directions with or without turbine shadow for each of the wind turbines in the wind farm, (b) determining, via the loads optimization function, at least one additional wind parameter for each of the wind directions, (c) calculating, via simulation, loads for each of the wind turbines in the wind farm based on the identified wind directions with or without turbine shadow for each of the wind turbines in the wind farm and the at least one additional wind parameter for each of the wind directions, and (d) determining a site layout for the wind farm based on the calculated loads.

Model-based predictive control method (MPC) for the reduction of structural load in wind turbines comprising: exclusively proposing a single internal linear model for the MPC for the entire operating range of the turbine; obtaining the adjustable parameters of the linear internal model from the experimental data previously measured in the turbine; choosing the discrete time values for the control and prediction horizons; adjusting the MPC controller and performing a practical implementation test.