Methods, systems, and devices for controlling a yaw offset of an upstream wind turbine based on reinforcement learning are provided. The method includes receiving data indicative of a current state of the first wind turbine and of a current state of a second wind turbine adjacent to the first wind turbine downstream along a wind direction, determining one or more controlling actions associated with the yaw offset of the first wind turbine based on the current state of the first wind turbine, the current state of the second wind turbine, and a reinforcement learning algorithm, and applying the determined one or more controlling actions to the first wind turbine.

The present invention provides a method of estimating an orientation of a wind turbine. The method comprises determining, using a polarising light compass of the wind turbine, a sun polarisation value, and determining a yaw angle of the wind turbine associated with the sun polarisation value. A sun direction vector is determined based on the sun polarisation value and the associated yaw angle; and an orientation of the wind turbine is estimated relative to a fixed direction using the sun direction vector.

Systems and methods to monitor a wind turbine azimuth drivetrain. Azimuth variation characteristics data are accumulated from wind turbines over a period of time. Clusters of values within the azimuth variation characteristics data are identified and a respective condition of the main drivetrain is associated with different clusters of values. After the associating, a measured set of azimuth variation characteristics data is received. A cluster corresponds to values in the measured set of azimuth variation characteristics data is determined and a condition associated with that cluster is determined to be a condition associated with the subject main drivetrain. That condition is then reported.

A method and apparatus for applying optimized yaw settings to wind turbines including receiving operating data from at least one wind turbine on a wind farm and sending the data to a supervisory control and data acquisition (SCADA) system on the at least one wind turbine to generate current SCADA data. The current SCADA data is sent a central processing center away from the wind farm. The central processing center includes an optimization system that can generate a new look up table (LUT) including at least one new wind turbine yaw setting calculated using information comprising wind direction, wind velocity, wind turbine location in the wind farm, information from a historic SCADA database, and yaw optimizing algorithms. The new LUT is then sent to a yaw setting selection engine (YSSE) where instructions regarding the use of the new LUT are generated.

The present invention relates to adjustment and/or drive units which can be used in wind power plants for adjusting the azimuth angle of the nacelle of the wind power plant or the pitch angle of the rotor blades, wherein such an adjustment and/or drive unit has at least two adjusting drives for rotating two assemblies which are mounted so as to be rotatable relative to each other, and has a control device for controlling the adjusting drives. The control device controls the adjusting drives in such a manner that the adjusting drives are braced relative to each other during the rotation of the two assemblies and/or when the assemblies are at standstill. The invention further relates to a wind power plant comprising such an adjustment and/or drive unit, and to a method for controlling such an adjustment and/or drive unit. According to the invention, the control device comprises a bracing-adjustment device for variably adjusting the intensity of the bracing of the adjusting drives as a function of a variable external load on the assemblies being adjusted, wherein the intensity can be determined by means of a load determining device. According to another aspect of the invention, an overload protection is included, wherein the individual loads of the individual adjusting drives are determined by load determining devices and, in the event that an adjusting drive reaches overload, the distribution of the drive torques is modified in such a manner that the adjusting drive reaching overload is relieved or at least not further loaded, and at least one further adjusting drive is more heavily loaded in a supporting manner or is less heavily loaded in a bracing manner.

A yaw sensor for a wind turbine comprises a plurality of rotary switches, each configured to be coupled to a yaw drive gearbox of a wind turbine nacelle, the rotary switches each being operable to activate and deactivate respective associated electrical contacts in dependence on an amount of yaw rotation of the nacelle relative to a start position. Each electrical contact is active at a plurality of first yaw rotation ranges with respect to the start position, and inactive at a plurality of second yaw rotation ranges with respect to the start position, the first and second yaw rotation ranges being interleaved.

A method for controlling wind alignment correction of a wind turbine comprises: acquiring environmental wind speed values, wind alignment angle measured values, and generated power values of the wind turbine in real time; dividing each acquired environmental wind speed value into multiple wind speed sections according to the magnitude of the environmental wind speed value, and extracting wind alignment angle measured values and generated power values in at least one wind speed section; determining a maximum value of extracted generated power values in each wind speed section; calculating a wind alignment correction deviation of the wind turbine according to a wind alignment angle measured value corresponding to the maximum value; and performing correction processing on a subsequently acquired wind alignment angle measured value by using the wind alignment correction deviation.

A method for controlling the operation of a wind turbine may generally include monitoring a current yaw position of a nacelle of the wind turbine, wherein the current yaw position is located within one of a plurality of yaw sectors defined for the nacelle. In addition, the method may include monitoring a wind-dependent parameter of the wind turbine and determining a variance of the wind-dependent parameter over time, wherein the variance is indicative of variations in a wind parameter associated with the wind turbine. Moreover, the method may include determining at least one curtailed operating setpoint for the wind turbine when the variance exceeds a predetermined variance threshold, wherein the curtailed operating setpoint(s) is determined based at least in part on historical wind data for the yaw sector associated with the current yaw position.

A method for determining a rotor orientation of a rotor of a wind turbine, the rotor having a rotor blade, to a method for determining a geographical position of a rotor of a wind turbine, the rotor having a rotor blade, to a wind turbine and to a wind farm. A method for determining a rotor orientation of a rotor of a wind turbine, the rotor having a rotor blade, comprising the steps of: receiving at least two sets of position data of a GNSS receiver arranged in the rotor blade, the two sets of position data representing two different horizontal positions of the GNSS receiver; and ascertaining the rotor orientation of the rotor on the basis of the position data.

Provided is an apparatus for detecting properties of a rotor blade of a wind turbine the apparatus including: at least one leaky feeder configured to be arranged around the tower, an electromagnetic transmitter connected to the at least one leaky feeder and configured for transmitting a first electromagnetic signal along the at least one leaky feeder, a reflector for diverting and/or focusing the first electromagnetic signal in a predetermined direction, thereby forming a reflected first electromagnetic signal, an electromagnetic receiver connected to the at least one leaky feeder and configured for receiving a second electromagnetic signal from the at least one leaky feeder, the second electromagnetic signal being reflected from the rotor blade, and a processing unit connected to the electromagnetic transmitter and the electromagnetic receiver and configured to determine the properties of the rotor blade by analysing the first electromagnetic signal and the second electromagnetic signal.