Vestas Wind Systems A/s

Morten Tim Thorsen

Martin Qvist

Tommy Frichot

Casper Hillerup Lyhne

Johnny Nielsen

Niels Erik Danielsen

Jan Krogh Jensen

Fabrice Krøyer-Loudet

Anders Kjeldgaard Olesen

Mikkel Kåe Skovdal

Anders Rhod Gregersen

Jesper Schmidt

Mehran Nourbakhsh

Roberto Ugo Di Cera Colazingari

A method for controlling wind turbines. Incident signal data is obtained from wind turbines and fed to an artificial intelligence (AI) model in order to identify patterns in the incident signals generated by the wind turbines. One or more actions are associated to the identified patterns, based on identified actions performed by the wind turbines in response to the generated incident signals. During operation of the wind turbines, one or more incident signals from one or more wind turbines are detected and compared to patterns identified by the AI model. In the case that the detected incident signal(s) match(es) at least one of the identified patterns, the wind turbine(s) are controlled by performing the action(s) associated with the matching pattern(s).

Method for controlling wind turbines of a wind park using a trained AI model

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

The present disclosure provides a method for obtaining site data from a power plant within a private network of the power plant, where the power plant comprises one or more wind turbine generators. The method comprises a step of providing at an internal computer system placed internally with respect to the private network site data relating to the power plant, where the site data is in a site data format. The site date is stored in the internal computer system, and pushes to an external data interface outside the private network. The site data is transformed to a universal data format being different from the site data format before or after pushing the site data.

Method of obtaining data

Testing data transfer at the application layer of a wind power surveillance computer system. One technique includes preparing a test message with a message id, transferring the test message from a first computer entity to a second computer entity, stamping the test message with a time stamp, when transfer is initiated, stamping the test message with a transfer id and a corresponding transfer time stamp, when the test message is received at the second entity, transferring the test message from the second computer entity at the application layer to the first computer entity, stamping the test message with an arrival time stamp, when the test message arrives at the first entity, storing the message id and the transfer id with corresponding time stamp and corresponding transfer time stamp, and the arrival time stamp, and comparing the stored time stamp with the transfer time stamp and with the arrival time stamp.

Method for testing data transfer in a wind power surveillance system

The invention relates to a method for controlling a wind turbine system, more particular for a method for determining shadow flicker at a location and identifying a wind turbine in a wind park with a plurality of wind turbines causing the shadow flicker. A remote detector located at or near the location is determining the presence of shadow flicker and generating flicker data representative of the shadow flicker. A target wind turbine potentially causing a shadow at the location is identified based on the turbine position and the position of the sun. Operational data from the target wind turbine is obtained and it is verified whether the target wind turbine generates the shadow flicker by comparing the flicker data and the operational data.

Method for determining shadow flicker from a wind turbine system

A method, controller, wind turbine, and computer program product are disclosed for processing and analyzing wind turbine operational data in a distributed data analysis system. An example method generally includes obtaining, at a first data analysis system, operational data from a plurality of wind turbines in a first wind power plant, determining adjustments to wind turbine operational parameters based on the operational data, pushing the adjustments to the first wind power plant, transmitting the operational data to a second data analysis system not located at the first wind power plant, and transmitting the operational data from the first wind power plant and at least a second wind power plant to a third data analysis system, wherein the third data analysis system comprises a global data analysis system.

Distributed data analysis system for wind power plants background

A method, controller, wind turbine, and computer program product are disclosed for collecting data from wind turbines in a wind farm. An example method generally includes receiving, from a client device, a subscription request identifying a plurality of data points to collect from a set of wind turbines. A wind farm server establishes a client interface with the client device. The wind farm server receives data points form the plurality of wind turbines and buffers the identified collected data points from the set of wind turbines in a data repository. Through the client interface, the wind farm server receives a request for data points collected from at least one wind turbine over a specified time period, and responsive to the request, transmits the requested data points to the client device. The wind farm server also may push collected data points from wind turbines to a data analysis system.

Growing community of inventors

Tilst, Denmark

Morten Tim Thorsen