Controlling a wind turbine including measuring a wind speed for a location upwind of a wind turbine. Using the measured wind speed, a changed steady-state deflection of a structure of the wind turbine is predicted. The predicted changed steady-state deflection corresponds to a time when wind from the location is incident on the wind turbine. Oscillations of the structure are damped relative to the changed steady-state deflection. By damping the oscillations relative to the changed steady-state deflection, movements of the structure may be minimized when there is no predicted change in steady-state deflection, while permitting more rapid movements during transitions from one steady-state deflection to the predicted steady-state deflection, allowing more of the available power to be captured by the wind turbine.

A method for controlling a wind turbine connected to an electrical grid includes receiving, via a controller, a state estimate of the wind turbine. The method also includes determining, via the controller, a current condition of the wind turbine using, at least, the state estimate, the current condition defining a set of condition parameters of the wind turbine. Further, the method includes receiving, via the controller, a control function from a supervisory controller, the control function defining a relationship of the set of condition parameters with at least one operational parameter of the wind turbine. Moreover, the method includes dynamically controlling, via the controller, the wind turbine based on the current condition and the control function for multiple dynamic control intervals.

A system and method are provided for controlling a power generating system having at least one power generating subsystem connected to a point of interconnection (POI). Accordingly, the subsystem controller of the power generating subsystem obtains a first data signal indicative of an electrical parameter at the POI and a second data signal indicative of the electrical parameter at the generating subsystem. The second data signal has a higher fidelity than the first data signal. The second data signal is utilized by the subsystem controller to generate a first modeled value for the electrical parameter at the POI which compensates for the lower-fidelity first data signal. The subsystem controller generates a setpoint command for the power generating subsystem based, at least in part, on the first modeled value for the electrical parameter.

A method for controlling a wind turbine, the wind turbine having a generator with controllable generator torque and an aerodynamic rotor with rotor blades with adjustable pitch angle, the aerodynamic rotor driving the generator with variable rotor speed depending on a wind speed, comprising the steps operating the wind turbine in a subrated mode when the wind speed is below a predetermined rated wind speed, operating the wind turbine in a rated mode when the wind speed is at or above the predetermined rated wind speed, estimating the wind speed and operating the wind turbine in subrated mode or in rated mode in dependence on the estimated wind speed.

A method and device for controlling output power in a primary frequency modulation process of a wind turbine are provided by the present disclosure. The method includes predicting a rotational speed of the wind turbine; determining frequency modulation remaining time based on the predicted rotational speed, the frequency modulation remaining time being time for which the wind turbine is able to continue to output frequency modulation power as the output power used for the primary frequency modulation without affecting a recovery of the wind turbine after the primary frequency modulation; controlling the output power based on the determined frequency modulation remaining time.

A method for feeding electric power into an electric supply network using a wind park having wind power installations is provided. An expected power is determined for a predetermined feed-in period, where the expected power indicates a power value or temporal profile of power expected to be available to the park as power from wind in the predetermined feed-in period. An expected accuracy is determined and is a measure of how accurately the power reaches the expected power in the feed-in period. To determine the expected power, at least one expected wind variable representative of the expected wind speed is determined using a weather forecast, and the expected wind variable is additionally determined or verified, proceeding from the weather forecast, using a correction rule based on local weather data and/or operating data of the park. The expected power is determined on the basis of the expected wind variable.

A system and method are provided for determining a geographic location of a tower top pivot point (TPP) of a wind turbine tower having a nacelle that includes a machine head and rotor at a top thereof. At least one rover receiver of a global navigation satellite system (GNSS) is configured at a fixed position on the nacelle. A plurality of 360-degree yaw sweeps of the nacelle are conducted and the geo-location signals received by the rover receiver during the yaw sweeps are recorded. With a controller, the geo-location signals are converted into a circular plot and a radius of the plot is determined, the radius being a distance between the rover receiver and the TPP. Based on a GNSS geo-location of the rover receiver and the radius, a geo-location of the TPP is computed.

The present application discloses a chance constrained extreme learning machine method for nonparametric interval forecasting of wind power, which belongs to the field of renewable energy generation forecasting. The method combines an extreme learning machine with a chance constrained optimization model, ensures that the interval coverage probability is no less than the confidence level by chance constraint, and takes minimizing the interval width as the training objective. The method avoids relying on the probability distribution hypothesis or limiting the interval boundary quantile level, so as to directly construct prediction intervals with well reliability and sharpness. The present application also proposes a bisection search algorithm based on difference of convex functions optimization to achieve efficient training for the chance constrained extreme learning machine.

According to the disclosure, an artificial intelligence (AI) model receives a power production amount, a power production efficiency, a control variable and the like states as input information through information exchange between a wind turbine and the AI model, and therefore it is possible to provide a control method using the AI model with regard to even the wind turbine given no power coefficient.

A method for quickly predicting a fatigue life of a wrinkle defect-containing main spar in a wind turbine blade is provided. The method includes: S1: testing a tensile property of a wrinkle defect-containing main spar to be tested; S2: calculating, according to surface temperature data of the specimen obtained in step S1, intrinsic dissipated energy of the main spar specimen under different loading stresses; S3: plotting a relational graph between intrinsic dissipated energy of the specimen and a corresponding ultimate tensile strength (UTS) level; S4: establishing, based on a change of the intrinsic dissipated energy in a fatigue process, a normalized residual stiffness model containing parameters to be determined, and putting fatigue test data into the model; S5: deducing a fatigue life prediction model for the wrinkle defect-containing main spar specimen according to the normalized residual stiffness model with determined parameters; and S6: obtaining a normalized failure stiffness.