Vestas Wind Systems A/s

Bombardier Transportation (signal) Denmark A/s

Johnny Nielsen

Jacob Deleuran Grunnet

Lars Glavind

Kristian Kiib

Jens Van Schelve

Claus Thybo

Ib Svend Olesen

Dan Hilton

Ines Pinto Frutuoso

Goncalo Artur Duarte Pereira

Fabio Caponetti

Keld Hammerum

Per Brath

Pradeep Bosukonda

Jes Rasmussen

Goncalo Lucas Marcos

Tobias Gybel Hovgaard

Morten Tim Thorsen

Lars Rohrmann Andersen

Peter Fogh Odgaard

Casper Hillerup Lyhne

Morten Thøgersen

Tobias Østergaard Rossel

Peter Gjellerup Schiønning

Brian Lembcke Melgaard

Tobias Rossel

Sten Dan Poulsen

Mikkel Kåe Skovdal

Carlo Alberto Ratti

Peter Gjellerup SCHIØNNING

Kristian Kiib Gregersen

Claus Vestergard Nielsen

The invention provides a computer-implemented method of controlling operation of a wind turbine in which a plurality of wind turbine zones are defined. The method comprises, for each of the plurality of wind turbine zones: receiving sensor data from at least one electromagnetic radiation sensor arranged to monitor the respective wind turbine zone; and, determining, based on the received sensor data, whether one or more people are in the respective wind turbine zone. The method comprises selecting an operational mode of the wind turbine based on the determination as to which of the plurality of zones have one or more people therein, and controlling the wind turbine to operate in the selected operational mode.

Controlling operation in different zones of a wind turbine

Disclosed is a method, performed by an electronic device, for control of operation of a wind turbine. The method comprises obtaining wind turbine data indicative of one or more alerting events of the wind turbine, wherein the wind turbine data comprises warning data indicative of a warning of the wind turbine, and/or alarm data indicative of an alarm state of the wind turbine. The method comprises obtaining sensor data from a plurality of sensors of the wind turbine indicative of operating conditions associated with the wind turbine. The method comprises predicting, based on the wind turbine data and the sensor data, an upcoming safety stop by applying a machine learning model to the wind turbine data and the sensor data. The method may comprise providing, based on the predicted upcoming safety stop, control data indicative of a controlled stop or a derating to be performed by the wind turbine.

Prediction and prevention of safety stop of a wind turbine

A method of calibrating a reference of a wind turbine. The method comprises monitoring performance of the wind turbine over a calibration period to generate performance data, wherein the calibration period comprises a series of sub-periods. The reference is calibrated by: setting the reference on the basis of the performance data; and, for each sub-period: determining a sub-period value on the basis of the performance data generated during that sub-period, comparing the sub-period value with the reference, and updating the reference with the sub-period value if the comparison shows that a performance of the wind turbine indicated by the sub-period value is better than a performance of the wind turbine indicated by the reference. The comparison and updating steps enable the reference to more accurately reflect more recent performance of the wind turbine. The method can also be reliably used in freezing temperatures.

Method of calibrating a reference of a wind turbine

A method of determining rotor speed of a wind turbine. The method involves receiving angular velocity sensor data indicative of an angular velocity of the wind turbine rotor hub, provided e.g., by a gyroscope and receiving acceleration sensor data indicative of an acceleration of the rotor hub in at least one radial direction relative to an axis of rotation of the rotor hub. The method further involves determining first and second estimated rotational speeds of the rotor hub based on the respective angular velocity sensor data and acceleration sensor data. The method also involves determining a correction value based on a difference between the first and second estimated rotational speeds, and applying the correction value to the first estimated rotational speed to determine the true current rotor speed of the wind turbine.

Determining wind turbine rotor speed

There is provided methods and systems for controlling a multi-rotor wind turbine generator having at least two rotor nacelle assemblies mounted to a support arrangement by a common yaw control system and each having a wind direction sensor mounted thereto configured to measure a wind direction relative to forward direction of its rotor nacelle assembly. The methods comprise the steps of measuring, for each rotor nacelle assembly, wind power parameter data over a plurality of relative wind directions, determining, based on the measured data, an optimum relative wind direction, either based on the average of two directions at which the parameter is maximum or on a combined data set, and controlling the yaw system accordingly.

Multi-rotor wind turbine yaw control

The invention provides a method of identifying recurrent free-flow wind disturbances associated with a wind turbine. The method comprises monitoring a signal indicative of a parameter associated with operation of the wind turbine, determining an expected signal of the parameter based on the monitored signal, determining a difference between values of the monitored signal and the determined expected signal, and correlating the determined differences with yaw position of a nacelle of the wind turbine. The method includes determining, based on the correlated differences, unexpected values of the parameter for different yaw positions, and identifying, based on a frequency of occurrence of the determined unexpected values, a recurrent free-flow wind disturbance associated with a yaw position of the nacelle.

Identifying recurrent free-flow wind disturbances associated with a wind turbine

A method of correcting a pitch angle deviation of a blade of a wind turbine is provided. First blade load measurements measured when the wind turbine was operating in a first operational mode are provided, and used to determine calibration parameters. Second blade load measurements measured when the wind turbine was operating in a second operational mode are provided, and the calibration parameters applied to determine calibrated blade load measurements. A pitch angle deviation of at least one blade of the turbine is estimated based on an identified difference between the calibrated blade load measurements, and a pitch angle is adjusted to correct for the pitch angle deviation.

Correcting pitch angle

A method of transitioning a wind turbine from a sleep state is provided in which a wind speed at the wind turbine is measured, and the measured wind speed is compared to a wake-up threshold. If the wind speed exceeds the wake-up threshold, the wind turbine is transitioned to an active state. Before comparing, either the measured wind speed or the wake-up threshold is adjusted based on an outcome of at least one previous transition from the sleep state of the wind turbine.

Waking a wind turbine from a sleep state

A wind turbine system comprising: a wind turbine; and a monitoring system, wherein the wind turbine comprises: a tower; an arm extending from the tower, a rotor-nacelle assembly (RNA) carried by the arm; and a Global Navigation Satellite System (GNSS) sensor carried by the arm or the RNA. The monitoring system is configured to receive position data from the GNSS sensor and obtain a moment or force measurement on the basis of the position data.

Wind turbine system

A method for determining a relative position of wind sensors on a wind turbine comprising: obtaining wind data from each of at least two wind sensors installed on a wind turbine at a location where airflow is affected by a rotor of the wind turbine, the obtaining occurring while the rotor is rotating, identifying oscillations in the wind data from each of the wind sensors, determining a phase or amplitude difference between the oscillations, and determining a relative position of the wind sensors based on the phase or amplitude difference.

Wind sensor configuration

A method of determining an orientation of a nacelle of a wind turbine, wherein the nacelle carries a Global Navigation Satellite System (GNSS) sensor, the method comprising: yawing the nacelle between a series of orientations; obtaining locus data based on a series of calibration positions measured by the GNSS sensor, wherein each calibration position is measured by the GNSS sensor when the nacelle is in a respective orientation of the series of orientations; storing the locus data; after storing the locus data, measuring a new position with the GNSS sensor; and determining the orientation of the nacelle on the basis of the stored locus data and the new position.

Method of determining orientation of a nacelle

A method for operating a cluster of a plurality of wind turbines is disclosed. For each of the wind turbines, one or more parameter values of a parameter being indicative for a condition occurring at the wind turbine are derived, based the measurements obtained by the wind turbine. In the case that a derived parameter value for a specific wind turbine exceeds a trigger value, measures for mitigating an effect of the condition at the specific wind turbine are initiated. The derived parameter values for the wind turbines of the cluster of wind turbines are compared to an expected distribution of the parameter values. In the case that a distribution of the derived parameter values differs from the expected distribution of the parameter values, the trigger value is adjusted, and the adjusted trigger value is subsequently applied when comparing the derived parameter values to the trigger value.

Method for operating a cluster of wind turbines

The present invention relates to a method of operating a wind turbine with an operational parameter where values of the operational parameter are obtained by different sensors and compared to determine the validity of the value. A first value and a second value of the operational parameter are obtained different sensors and validated by comparing the two values. The wind turbine being operated using a validated value as the operational parameter. The two sensors are selected among a trained machine learning model, a reference sensor and a computerized physical model.

Operating a wind turbine with sensors implemented by a trained machine learning model

Systems and methods for estimating a direction of wind incident on a wind turbine, the wind turbine comprising a tower; a rotor-nacelle-assembly (RNA) carried by the tower; a deflection sensor configured to sense a position of the RNA or a deflection of the tower; and a wind direction sensor. One approach includes: obtaining deflection training data from the deflection sensor; obtaining wind direction training data from the wind direction sensor; training a machine learning model on the basis of the deflection training data and the wind direction training data in order to obtain a trained machine learning model; obtaining further deflection data from the deflection sensor; inputting the further deflection data into the trained machine learning model; and operating the machine learning model to output a wind direction estimate on the basis of the further deflection data.

Growing community of inventors

Svenstrup J, Denmark

Johnny Nielsen