Method of determining the wind speed in the rotor plane of a wind turbine

Patent metadata

Field	Value
Publication number	US-2022145856-A1
Application number	US-202117514061-A
Country	US
Kind code	A1
Filing date	Oct 29, 2021
Priority date	Nov 6, 2020
Publication date	May 12, 2022
Grant date	—

Abstract

The present invention relates to a method of determining the wind speed in the plane of a rotor (PR) of a wind turbine (1), by measuring (MES2) the rotational speed of the rotor, the angle of the blades and the generated power. The method according to the invention uses a wind turbine model (MOD) constructed from wind speed measurements (LID), and by use of measurement clustering (GRO) and regressions (REG).

First claim

1 - 10 . (canceled)

11 . A method for determining a wind speed in the rotor plane of a wind turbine, comprising steps of:
a) constructing a wind turbine model relating rotational speed of the rotor of the wind turbine, an inclination angle of blades of the wind turbine and power generated by a conversion machine of the wind turbine to the wind speed in the rotor plane of the wind turbine comprising steps of:
i. measuring simultaneously the wind speed in the rotor plane of the wind turbine and the rotational speed of the rotor, the inclination angle of the blades and the power generated by the conversion machine of wind turbine;
ii. classifying the simultaneous measurements of wind speed in the rotor plane of the wind turbine and the rotational speed of rotor, of the inclination angle of the blades and of the power generated by the conversion machine of the wind turbine into at least two classes of wind turbine operating conditions; and
iii. for each class, determining a regression between measurements of the wind speed in the rotor plane of the wind turbine and the rotating speed of the rotor, the inclination angle of the blades and the power generated by the conversion machine of the wind turbine by use of a basis function decomposition method, and by means of a method allowing establishment of a relation between the basis functions and the wind speed in the rotor plane, by use of a Gaussian process regression method and a least-squares regression method; and
iv. constructing the model of the wind turbine by use of the regressions determined for each class;
b) measuring in real time the rotational speed of the rotor, the inclination angle of the blades and the power generated by the conversion machine of the wind turbine; and
c) determining in real time the wind speed v in the plane of the rotor of the wind turbine by use of the real-time measurements of the rotational speed of the rotor, of the inclination angle of the blades and of the power generated by the conversion machine of the wind turbine and the wind turbine model.

12 . A method of determining wind speed as claimed in claim 11 , wherein the measurements of the wind speed, of the rotational speed of the rotor, of the inclination angle of the blades and of the power generated by the conversion machine of the wind turbine are classified into at least two wind turbine operating condition classes by using a k-means algorithm classification method.

13 . A method of determining wind speed when the k-means algorithm is a k-means++algorithm.

14 . A method of determining the wind speed as claimed in claim 11 , wherein a number of classes ranges between 3 and 10.

15 . A method of determining wind speed in accordance with claim 14 wherein the classes range between 4 and 7.

16 . A method of determining the wind speed as claimed in claim 11 , wherein the wind speed in the rotor plane is measured based on LiDAR sensor measurements.

17 . A method of determining the wind speed as claimed in claim 12 , wherein a number of classes ranges between 3 and 10.

18 . A method of determining the wind speed as claimed in claim 15 , wherein the wind speed in the rotor plane is measured based on LiDAR sensor measurements.

19 . A method of determining wind speed as claimed in claim 11 , wherein the wind speed in a plane of the rotor of the wind turbine is determined in real time by determining a Euclidean distance between the real-time measurements of the rotational speed of the rotor, of the inclination angle of the blades and of the power generated by the conversion machine of the wind turbine and a center of each class, and the wind turbine model is applied by a weighted combination of the regressions of each class with the weighting depending on the Euclidean distance.

20 . A method of determining wind speed as claimed in claim 11 , wherein the wind speed in the plane of the rotor of the wind turbine is predicted for at least one future time interval, by the wind turbine model (MOD) and the real-time measurements of the rotational speed of the rotor, of the inclination angle of the blades and of the power generated by the conversion machine of the wind turbine.

21 . A method of controlling a wind turbine, by steps of:
a) determining wind speed in the rotor plane of wind turbine by the method as claimed in claim 11 , and b) controlling the wind turbine according to the wind speed in the rotor plane of the wind turbine.

22 . A computer program product comprising code instructions designed to carry out the steps of a method as claimed in claim 11 , when the program is executed on a control and diagnosis unit of the wind turbine.

23 . A wind turbine, characterized in that it comprises means for measuring the rotational speed of the rotor, means for measuring the inclination angle of the blades of the wind turbine, means for measuring the power generated by the conversion machine of the wind turbine, and means for determining the wind speed in the rotor plane of the wind turbine able to implement the method as claimed in claim 11 .

24 . A wind turbine as claimed in claim 23 , comprising a real-time control and data acquisition system including the means for measuring the rotational speed of the rotor, the means for measuring the inclination angle of the blades of the wind turbine and the means for measuring the power generated by the conversion machine of the wind turbine.

Assignees

• Ifp Energies Now

Inventors

• Bezerra Rufino Ferreira Paiva Eduardo
• Nguyen Hoai-Nam
• Lepreux Olivier

Classifications

• G06F18/23

  Clustering techniques · CPC title

• G01S17/95

  for meteorological use · CPC title

• G01S17/58

  Velocity or trajectory determination systems; Sense-of-movement determination systems · CPC title

• G06F2113/06

  Wind turbines or wind farms · CPC title

• G06F30/28

  using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD] · CPC title