METHOD FOR COMPUTER-IMPLEMENTED DETERMINATION OF A DRAG COEFFICIENT OF A WIND TURBINE

Abstract

Provided is a method and a system for computer-implemented determination of a drag coefficient as a control variable for controlling of a wind turbine, by receiving, as a data stream, a set of data from a number of data sources, the set of data consisting, for each data source, of a plurality of time series data values, acquired within a given time period at given points in time, and estimating, by a processing unit, the control variable based on the set of data as input of a machine learning algorithm being trained with training data of simulation time series data containing a number of operating states at different wind conditions and respective number of drag coefficients.

Claims

1. A method for computer-implemented determination of a drag coefficient as a control variable for controlling of a wind turbine, the method comprising: S1) receiving, by an interface, as a data stream, a set of data from a number of data sources, the set of data comprising, for each data source, of a plurality of time series data values, acquired within a given time period at given points in time; and S2) estimating, by a processing unit, the control variable based on the set of data as input of a machine learning algorithm being trained with training data of simulation time series data containing a number of operating states at different wind conditions and a respective number of drag coefficients.

2. The method according to claim 1, wherein the number of data sources consists of sensor data and/or calculated data out of one or more of the following turbine measurements: produced power, rotor speed, blade pitch angle, air density, tower top fore-aft acceleration, blade root moment.

3. The method according to claim 1, wherein, as a machine learning algorithm, a neural network is used to estimate the control variable.

4. The method according to claim 1, wherein, according to the trained machine learning algorithm, the control variable is estimated on one or more specific locations of a blade of the wind turbine.

5. The method according to claim 1, wherein the machine learning algorithm is formulated as a nonlinear autoregressive with exogenous input network.

6. The method according to claim 5, wherein the estimation of the control variable is based on a first number of input data of the set of data and a second number of predicted outputs representing the control variable.

7. The method according to claim 6, wherein the first number of inputs corresponds to the number of given points in time within the given time period.

8. The method according to claim 6, wherein the first number of inputs and the second number of predicted outputs equals or not.

9. The method according to claim 1, wherein, based on the estimated control variable, a stall detection algorithm is conducted.

10. A computer program product, comprising computer readable hardware storage device having computer readable program code stored therein, said program code executable by a processor of a computer system to implement the method of claim 1 when the product is run on a computer.

11. A system for computer-implemented determination of a drag coefficient as a control variable for controlling of a wind turbine, the system comprising: an interface for receiving, as a data stream, a set of data from a number of data sources, the set of data comprising, for each data source, of a plurality of time series data values, acquired within a given time period at given points in time; and a processing unit adapted to, by using a machine learning algorithm being trained with training data of simulation time series data containing a number of operating states at different wind conditions and a respective number of drag coefficients, estimate the control variable based on the set of data received at the interface.

12. The system according to claim 11, wherein the processing unit is adapted to perform a method of determining the drag coefficient carry out the steps of claim 2.

Description

BRIEF DESCRIPTION

[0025] Some of the embodiments will be described in detail, with reference to the following figures, wherein like designations denote like members, wherein:

[0026] FIG. 1 shows a figure of a profile of a turbine blade in which, according to wind hitting on the turbine blade from a specific direction, different vectors including a drag path vector are outlined;

[0027] FIG. 2 is a diagram which shows the coefficients of lift and drag as a function of an angle of attack of wind hitting the turbine blade;

[0028] FIG. 3 is a block diagram illustrating a system according to embodiments of the invention; and

[0029] FIG. 4 is a flow chart illustrating steps for carrying out the method according to embodiments of the invention.

DETAILED DESCRIPTION

[0030] FIG. 1 shows the profile of a blade BL of a not illustrated wind turbine and different vectors resulting from wind hitting on a leading edge of the blade BL. The direction of the wind hitting on the leading edge of the blade BL is denoted with WD. The wind direction hits on the blade BL with an angle of attack AoA which is formed between the wind direction WD and a plane PBL of the blade BL in which the blade BL extends. In addition, FIG. 1 shows the vectors of drag D, lift L and the blade path BP. The blade path BP indicates the direction of movement of the blade BL and lies within a rotor plane. Drag D and lift L represent resulting forces from the wind hitting on the blade BL. The magnitudes of the drag coefficient DC given by the vector D and lift D in FIG. 1 are used to derive whether the blade BL is stalling at that specific position on the blade.

[0031] FIG. 2 shows a diagram of the coefficients of the vectors lift L and drag D as a function of the angle of attack AoA of the wind hitting the turbine blade BL. The maximum of lift L represents a stall point STLP which is a function of the angle of attack AoA of the wind. The value of the angle of attack AoA at the stall point STLP is a critical angle of attack AoAc. If the blade BL, as shown in FIG. 1, turns clockwise, the angle of attack AoA will increase. This means, the drag coefficient DC increases as well. When the angle of attack AoA reaches the critical angle AoAc lift L starts to drop meaning that the blade BL is stalling. If the pitch angle is chosen optimal, lift L should be greater than the drag coefficient DC.

[0032] FIG. 3 shows a computer system CS which is adapted to determine the drag coefficient DC as a control variable for controlling the wind turbine. The computer system comprises an interface IF for receiving data and a processing unit PU for computing the data received at the interface IF. The data received at the interface IF are turbine measurements TM provided by a couple of sensors (not illustrated) of the wind turbine. The turbine measurements TM as input data enable a trained machine learning algorithm carried out by the processing unit PU to estimate the drag coefficient DC. The estimation of the drag coefficient is based on produced power PP, rotor speed RS and blade pitch angle BPA as input data. As optional and additional input data an air density AD, a tower top fore-aft acceleration TTA and a blade root moment BRM may be provided at the interface IF.

[0033] The input data (i.e. turbine measurements TM) is provided as a data stream, i.e. as time series data. The data stream consists of a set of data from the data sources (i.e. the sensors) wherein, for each data source, a plurality of time series data values, acquired within a given time period at given points in time is received at the interface IF. In other word, data acquisition is made continuously and, in particular, in regular time intervals.

[0034] The processing unit processes the received data using a trained machine learning algorithm, for example a trained neural network. The neural network estimates the drag coefficient DC on a specific location on the blade which is available through a simulation. The machine learning algorithm MLA can be formulated as a nonlinear autoregressive with exogenous input (NARX) network. The NARX network predicts time series based on a given past number of input and a given past number of predicted outputs (as a feedback). The given past number of input and the given past number of predicted outputs may equal. However, the given past numbers of input and output may differ as well. The estimation of the drag coefficient DC may be made on a function

y(t)=f(x(t),x(t−1), . . . ,x(t−d.sub.1),y(t−1), . . . ,y(t−d.sub.2)),

where y(t) is the predicted time series at time t, x(t) is the input time series at time t and d.sub.1 and d.sub.2 are the time delays on input and output feedback.

[0035] The NARX network, which is an embodiment for a possible machine learning algorithm, is trained on simulation time series data containing all features that is desired to represent in the network, such as simulation cases for running the wind turbine at normal production, running the wind turbine at gust, running the wind turbine with an inertial response, running the wind turbine with power boost, running the wind turbine with soiled/icy blades and/or running the wind turbine with changing air densities. These simulation cases consist of simulation time series data SIM (see FIG. 4) which are input to a machine learning algorithm MLA to get trained (TR).

[0036] Providing the simulation time series data SIM and conducting the training TR with the NARX network is done in a simulation environment which is indicated by SIMENV above the dotted line in FIG. 4. The trained machine learning algorithm (TMLA) is deployed on the computer system CS. The deployment is indicated by the arrow with DPLM. The trained machine learning algorithm TMLA receives as input data the turbine measurements TM and estimates the drag coefficient DC. This is carried out by the computer system CS of the turbine online and shown below the dotted line with TUR in FIG. 4.

[0037] The drag coefficient DC can then be used as a control variable by the computer system CS to reduce the stall margin and pitch the blade into the wind as far as possible, thereby increasing AEP. By detecting the stall online and acting upon it, structural loads acting on the blade can be reduced. In addition, avoiding stall reduces the noise from the turbulence around the blades.

[0038] The machine learning algorithm, for example the described NARX network, enables to model the complex system of a wind turbine with high level of robustness using multiple domains, e.g. time and frequency, without knowing details on the physical relations in the system. This enables an online estimation of the drag coefficient according to the current operation of the wind turbine and wind conditions. As the drag coefficient can be estimated very precise, it can be used as a control variable for controlling the wind turbine. In particular, the drag coefficient may be used to determine the pitch operating point of the blades of the wind turbine. As an advantage, the stall margin may be reduced. It is possible to have a more aggressive use of the pitch angle. This leads to an increased AEP of the wind turbine, reduces structural loads to the components of the wind turbine and reduces noise.

[0039] Although the present invention has been disclosed in the form of preferred embodiments and variations thereon, it will be understood that numerous additional modifications and variations could be made thereto without departing from the scope of the invention.

[0040] For the sake of clarity, it is to be understood that the use of “a” or “an” throughout this application does not exclude a plurality, and “comprising” does not exclude other steps or elements.