The present disclosure relates to methods (100, 200) for estimating an actual value of an operational parameter (67) of a wind turbine (10). A method (100) comprises determining (120) which sensors of a plurality of sensors (61) of the wind turbine (10) are reliable and which sensors of the plurality of sensors (61) are unreliable. The method (100) further comprises estimating (130) the actual value of the operational parameter (67) based on a mathematical model and on data related to the operational parameter (63) measured by the reliable sensors.

Computer-implemented methods for optimizing energy production by a wind turbine having shadow energy generator are provided. Aspects include obtaining a geographic location of the wind turbine and a weather forecast for the geographic location. Aspects also include calculating an estimated wind energy production for each of a plurality of configurations of the wind turbine based on the weather forecast, calculating an estimated shadow energy generator energy production for each of the plurality of configurations of the wind turbine based on the weather forecast, and identifying one of the plurality of configurations of the wind turbines based on a combination of the estimated wind energy production and the estimated shadow energy generator energy production. Aspects further include reconfiguring the wind turbine into a first configurations, where the first configurations is identified as the configuration with a largest sum of estimated wind energy production and estimated shadow energy generator energy production.

An offshore wind power-based water electrolysis system includes an offshore wind turbine generator installed offshore to produce electricity using offshore wind energy, a water electrolysis facility installed offshore to produce hydrogen by electrolysis of water using the electricity, a hydrogen maritime transport apparatus to transport the hydrogen produced through the water electrolysis facility to onshore, a hydrogen above-ground storage facility installed on ground to store the transported hydrogen and dispense the hydrogen to ground transport apparatuses, and a system maintenance and management apparatus to calculate and notify a remaining useful life of blades in the offshore wind turbine generator by performing debonding damage simulation, fatigue crack growth simulation and remaining useful life simulation of the blades in a sequential order, and determine and notify stability through finite element analysis for each hydrogen tank in the hydrogen maritime transport apparatus and the hydrogen above-ground storage facility.

A motion controller for a floating wind turbine including a number of rotor blades is provided. The motion controller is arranged to adjust the blade pitch of each rotor blade when the floating wind turbine is operating in winds below the rated wind speed so as to create a net force that damps a surge motion of the floating wind turbine. Also provided is a method of damping the motion of a floating wind turbine and a wind turbine having such a motion controller.

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.

The present disclosure is directed to method for providing wind data at a prediction location includes providing training data sets for a plurality of installation locations for wind turbines, wherein the training data sets are obtained from public databases, preparing the training data sets for machine learning by transforming the training data sets into features, training a prediction model for predicting at least one statistical wind condition at the location based on the features, obtaining a target location, in particular from a Customer Relationship Management (CRM) system, predicting the at least one statistical wind condition at the target location using the trained prediction model, and providing wind data including the predicted at least one statistical wind condition to the CRM system.

A computer-implemented method for determining wind turbine performance. The computer-implemented method includes generating a digital image based on operation data of a wind turbine. The operation data includes wind speed data and associated power output data. The computer-implemented method also includes processing the digital image using a convolutional neural network to obtain processed digital image, and processing the processed digital image to determine a representation of a wind turbine power curve associated with operation of the wind turbine.

A wind power generation device control system includes: a blade wind detecting device for detecting at least one of a wind direction or a wind speed on at least one blade of a wind power generation device; and a blade control device for controlling at least one of (i) a pitch angle of the at least one blade or (ii) a yaw angle of the wind power generation device, based on at least one of the wind direction or the wind speed detected by the blade wind detecting device.

The present invention concerns a method for determining the production availability of an offshore wind farm comprising at least one floating wind turbine, the method comprising: obtaining wind farm data, obtaining strategy data relative to operation and maintenance resources to carry out an action on the floating wind turbine(s), obtaining meteorological data relative to an offshore environment for the offshore wind farm over a given period of time, determining motion parameters as a function of the wind farm data and of the meteorological data, and determining the production availability of the offshore wind farm in the offshore environment over the given period of time on the basis of the wind farm data, of the strategy data, of the meteorological data, and of the determined motion parameters.

A system and method for predicting power output of a wind farm are disclosed. The method includes determining first and second parameter values of a power curve for a plurality of wind turbines. A second relationship is determined between the densities associated with the wind turbines and the values of the first parameter. A third relationship is determined between the densities associated with the wind turbines and the values of the second parameter. A value of the first parameter for a specified wind farm density is determined based on the second relationship. A value of the second parameter for the specified wind farm density is determined based on the third relationship. An indication of a power output for the specified wind farm density is generated by applying the determined values of the first and second parameters to the power curve.