A wind turbine includes at least one wind speed sensor, a number of pitch-adjustable rotor blades, and a control system for changing the pitch of the rotor blades and/or a generator torque. The the control system determines at time intervals an error parameter as the difference between an estimated wind speed and a measured wind speed as measured by the wind speed sensor. Then, based on a number of pre-defined wind speed intervals, a group of error parameters is obtained over time for each wind speed interval. For each wind speed interval and for each group of error parameters a wind speed offset is determined based on the average of the error parameters within the group which wind speed offsets are used in adjusting the measured wind speed.

Controlling a wind turbine comprising a wind sensor, a number of pitch-adjustable rotor blades, a yawing system, and a control system for yawing the wind turbine rotor relative to the wind and for changing the pitch of the rotor blades. A wind parameter is measured by the wind sensor, and is indicative of the wind speed and/or the wind direction relative to the wind turbine. At least a first and a second set of wind correction parameters for different production modes of the wind turbine are obtained. The production mode of the wind turbine is then determined, which may be one of at least normal operation or non-production, and the measured wind parameter is then adjusted as a function of the set of wind correction parameters corresponding to the production mode at the time of adjusting. Hereby a more precise wind parameter is obtained which can be used in the controlling of the turbine.

A method and a system for controlling a wind turbine based on sectors. Original sectors of the wind turbine are reconstructed based on a wind resource parameter and a wake-flow effect. A load is calculated and superposed for a new sector obtained from the sector reconstruction. An optimization algorithm is applied, under a condition that a constraint condition of a fatigue load is met, to find an operation parameter for maximum power generation amount of the wind turbine.

A method for controlling a wind energy installation having a rotor which is rotatable about a rotor axis and which has at least one rotor blade and a generator coupled thereto. The method includes detecting a value of a forefield parameter, in particular a forefield wind parameter, which is present at a first point in time and in a first region which first region is at a first distance from the wind energy installation, in particular from the rotor blade, in particular detecting a sequence of values of the forefield parameter up to the first point in time with the aid of at least one sensor, and controlling the generator and/or at least one actuator of the wind energy installation on the basis of this detected forefield parameter value, in particular this detected forefield parameter value sequence, and a machine-learned relationship of a predicted near field parameter, in particular a predicted near field wind parameter, at the wind energy installation and/or of an operating parameter of the wind energy installation predicted for a later, second point in time and/or of a control variable of the actuator and/or of the generator to the forefield parameter or the forefield parameter sequences.

A method is provided for monitoring an operational parameter of a wind turbine. The method comprising defining a peer limit, measuring the operational parameter during operation of the wind turbine; and comparing the measured operational parameter to the peer limit. The wind turbine is a member of a peer group of wind turbines, each wind turbine of the peer group comprising a common characteristic. The peer limit is defined using measurements of the operational parameter measured on the wind turbines of the peer group of wind turbines.

A first aspect of the invention provides a method of testing a yaw system (200) of a wind turbine, the wind turbine comprising a rotor; the yaw system (200) comprising a yaw gear (202) coupled to the rotor so that rotation of the yaw gear (202) causes yaw rotation of the rotor, and first and second sub-systems (204a, 204b), the first sub-system (204a) comprising a first pinion gear (206a) and a first drive motor (208a) coupled to the yaw gear (202) by the first pinion gear (206a), the second sub-system (204b) comprising a second pinion gear (206b) and a second drive motor (208b) coupled to the yaw gear (202) by the second pinion gear (206b). The method comprises the steps of: testing the first sub-system (204a) by: applying a first yaw moment to the yaw gear (202) with the second drive motor (208b) via the second pinion gear (206b), reacting the first yaw moment with the first pinion gear (206a), monitoring a yaw motion parameter indicative of rotation of the yaw gear (202), and determining a condition of the first sub-system (204a) based on the monitored yaw motion parameter.

A method for detecting actual slip in a coupling of a rotary shaft, for example, in a wind turbine power system, includes monitoring, via a controller, a plurality of sensor signals relating to the coupling for faults. In response to detecting a fault in the plurality of sensor signals relating to the coupling, the method includes determining, via the controller, whether the fault is indicative of an actual slip or a no-slip event of the coupling using one or more classification parameters. When the fault is indicative of the actual slip, the method includes estimating, via the controller, a magnitude of the actual slip using the plurality of sensor signals and a time duration of the actual slip. Further, the method includes implementing, via the controller, a control action based on the magnitude of the actual slip in the coupling.

A blade pitch controller for a wind turbine includes a nominal control system and a tower feedback loop. The tower feedback loop includes a filtering system. The filtering system is arranged to control wind turbine blade pitch so as to provide additional effective stiffness to the wind turbine in response to motion of the wind turbine which is above a filter frequency of the filtering system.

A method for predicting a day-ahead wind power of wind farms, comprising: constructing a raw data set based on a correlation between the to-be-predicted daily wind power, the numerical weather forecast meteorological feature and a historical daily wind power; obtaining a clustered data set and performing k-means clustering, obtaining a raw data set with cluster labels, and generating massive labeled scenes based on robust auxiliary classifier generative adversarial networks; determining the cluster label category of the to-be-predicted day based on the known historical daily wind power and numerical weather forecast meteorological feature, and screening out multiple scenes with high similarity to the to-be-predicted daily wind power based on the cluster label category; and obtaining the prediction results of the to-be-predicted daily wind power at a plurality of set times based on an average value, an upper limit value and a lower limit value of the to-be-predicted daily wind power.

A method for controlling noise generated by a wind farm with a plurality of wind turbines is disclosed. In the event that a predicted noise level exceeds a predefined threshold noise value, one or more wind turbines are selected using a noise propagation model and respective wind turbine models for the selected one or more wind turbines, and by performing an optimisation process to reduce the predicted noise level at the predefined evaluation position to a level below the predefined threshold noise value while maximising the total power production of the wind farm.