Estimating an achievable power production of a wind turbine by means of a neural network

1. A method for estimating an achievable power production of a wind turbine which is operated with a reduced power set point, the method comprising:

determining values of three parameters, the three parameters are indicative of an operating condition of the wind turbine, wherein a first parameter is an actual power production of the wind turbine, a second parameter is a pitch angle of a plurality of rotor blades of the wind turbine, and a third parameter is rotor speed;

inputting values of the three parameters into a neural network; and

outputting an output value from the neural network, the output value is an estimate of the achievable power production of the wind turbine.

2. The method as claimed in claim 1 , wherein the neural network has been trained on measured data.

3. The method as claimed in claim 1 , wherein the neural network has been trained on calculated data.

4. The method as claimed in claim 1 , wherein the neural network comprises a plurality of network nodes which are arranged in three layers.

5. The method as claimed in claim 4 ,

wherein a plurality of first network elements are assigned to a first layer of the neural network and are connected to a plurality of second network elements that are assigned to a second layer of the neural network, and

wherein the plurality of second network elements are connected to a plurality of third network elements which are assigned to a third layer of the neural network.

6. A control system for estimating an achievable power production of a wind turbine which is operated with a reduced power set point, the control system comprising:

a determination unit for determining values of three parameters, the values of the three parameters are indicative of an operating condition of the wind turbine wherein a first parameter is an actual power production of the wind turbine, a second parameter is a pitch angle of a plurality of rotor blades of the wind turbine, and a third parameter is rotor speed;

a neural network which is adapted to receive the values of the three parameters; and

an output unit for outputting an output value from the neural network, the output value is an estimate of the achievable power production of the wind turbine.

7. The control system as claimed in claim 6 , wherein the neural network has been trained on measured data.

8. The control system as claimed in claim 6 , wherein the neural network has been trained on calculated data.

9. The control system as claimed in claim 6 , wherein the neural network comprises a plurality of network nodes which are arranged in three layers.

10. The control system as claimed in claim 9 ,

wherein a plurality of first network elements are assigned to a first layer of the neural network and are connected to a plurality of second network elements that are assigned to a second layer of the neural network, and

wherein the plurality of second network elements are connected to a plurality of third network elements which are assigned to a third layer of the neural network.

11. The control system as claimed in claim 6 , wherein the control system is realized using a computer program, an electronic circuit, or a combination of software and hardware modules.

12. A wind turbine for generating electric power, the wind turbine comprising:

a rotor including a plurality of blades;

a generator, mechanically coupled to the rotor; and

a control system, comprising:

a determination unit for determining values of three parameters, the values of the three parameters are indicative of an operating condition of the wind turbine, wherein a first parameter is an actual power production of the wind turbine, a second parameter is a pitch angle of the plurality of rotor blades of the wind turbine, and a third parameter is rotor speed;

a neural network which is adapted to receive the values of the three parameters; and

an output unit for outputting an output value from the neural network, the output value is an estimate of an achievable power production of the wind turbine;

wherein the rotor is rotatable around a rotational axis and the blades extend radially with respect to the rotational axis.

13. The wind turbine as claimed in claim 12 , further comprising:

a power sensor for measuring the actual power production of the wind turbine;

an angle sensor for measuring pitch angle of the blade; and

a rotational-speed sensor for measuring the speed of a rotor,

wherein the power sensor, the angle sensor, and the rotational-speed sensor are coupled to the control system, and

wherein the control system is adapted to estimate the achievable power production of the wind turbine based on the actual power production, the blade pitch angle, and the rotor speed.

14. The wind turbine as claimed in claim 12 , wherein the neural network has been trained on measured data.

15. The wind turbine as claimed in claim 12 , wherein the neural network has been trained on calculated data.

16. The wind turbine as claimed in claim 12 , wherein the neural network comprises a plurality of network nodes which are arranged in three layers.

17. The wind turbine as claimed in claim 16 ,

wherein a plurality of first network elements are assigned to a first layer of the neural network and are connected to a plurality of second network elements that are assigned to a second layer of the neural network, and

wherein the plurality of second network elements are connected to a plurality of third network elements which are assigned to a third layer of the neural network.