Estimation of wind conditions at a wind turbine

Patent metadata

Field	Value
Publication number	US-9366235-B2
Application number	US-201113805997-A
Country	US
Kind code	B2
Filing date	Jun 16, 2011
Priority date	Jun 21, 2010
Publication date	Jun 14, 2016
Grant date	Jun 14, 2016

Abstract

The risk of an extreme gust of wind hitting a wind turbine is estimated by gathering data from one or more sensors for use as training data. This data is acquired over a period of time and is converted in to a feature vector for a given time period by a statistical measure. A number of feature zones are formed, each zone relating to a different estimate of risk with each feature vector being assigned to a risk category. The risk category is defined with reference to the value of one or more chosen turbine parameters at the time the data was acquired. The feature zones are formed from from a measure of distance such as the mean and co-variance of feature vectors from within a given category. Live data is processed by measuring the mahalonobis distance from the feature vector of the live data to the centre of each zone and the risk of an extreme gust is assessed as that of the feature zone to which the mahalonobis distance is lowest.

First claim

The invention claimed is:

1. A method of controlling a wind turbine, comprising:
acquiring and storing training data relating to one or more sensed variables, wherein the training data includes a feature vector obtained from at least one statistical measure indicative of risk;
assigning each of the training data to a risk category based on a measured parameter and defining feature zones for each category from at least a measure of distance of feature vectors in that category, the feature zones including a high risk zone indicative of a high risk of a gust; and
during operation of the wind turbine, determining an estimate of gust risk by calculating a feature vector periodically from data obtained from at least one sensor and determining to which of the feature zones to assign the feature vector, thereby determining an estimate of the risk of an extreme gust represented by the measured feature vector, wherein the feature vector is assigned to a feature zone by measuring the mahalonobis distance from the feature vector to the centre of each feature zone and assigning the feature vector to the zone having the smallest mahalonobis distance from the feature vector; and
adjusting the wind turbine to de-rate the wind turbine when the estimate of gust risk is above a threshold to prevent damage to the wind turbine.

2. The method according to claim 1 , comprising outputting a gust risk indicative signal to a wind turbine controller.

3. The method according to claim 1 , wherein the feature zones are defined for each category of risk from the mean of feature vectors in that category.

4. The method according to claim 1 , wherein the feature zones are defined for each category of risk from the mean and covariance of feature vectors in that category.

5. The method according to claim 1 , wherein the feature vectors are based on mean wind speeds.

6. The method according to claim 1 , comprising adjusting the feature zones in response to real time measurements.

7. The method according to claim 1 , comprising overrating the wind turbine when the estimate of the risk of an extreme gust is low.

8. The method according to claim 1 , wherein the gust risk estimate is output to a controller controlling two or more wind turbines.

9. The method according to claim 1 , wherein the level of risk assigned to a feature vector is based on the value of a measurable parameter following the measurement period in which the data from which the feature vector is derived was obtained.

10. The method according to claim 1 , wherein a feature vector is assigned a level of risk related to the maximum generator speed that followed the measurement period.

11. The method according to claim 1 , wherein the training data is preloaded into a wind turbine controller.

12. The method according to claim 1 , wherein the feature vector calculated periodically from sensor data is added to the stored training data.

13. The method according to claim 12 , comprising merging training data items together that have substantially the same value and weighting the values of the merged items.

14. The method according to claim 1 , wherein the estimate of gust risk is an estimate of an extreme gust.

15. A gust risk estimator for a wind turbine comprising:
a store of training data relating to one or more variables sensed by the wind turbine, wherein the training data includes a feature vector obtained from at least one statistical measure indicative of risk;
a comparator configured to compare each training data item to a measured parameter at the time of acquisition of the training data and assign each of the training data to a risk category based on the measured parameter;
a module configured to define feature zones for each category from a measure of distance of feature vectors in that category, the feature zones including a high risk zone indicative of a high risk of a gust; and
a module configured to determine an estimate of gust risk during operation of the wind turbine, by calculating a feature vector periodically from data obtained from at least one sensor associated with the wind turbine and determining to which of the feature zones to assign the feature vector, thereby determining an estimate of the risk of an extreme gust represented by the measured feature vector, wherein the module for determining an estimate of gust risk assigns a feature vector to a feature zone by measuring the mahalonobis distance from the feature vector to the centre of each feature zone and assigning the feature vector to the zone having the smallest mahalonobis distance from the feature vector; and
a controller configured to adjust the wind turbine to de-rate the wind turbine when the estimate of gust risk is above a threshold to prevent damage to the wind turbine.

16. The gust risk estimator according to claim 15 , wherein the module for determining an estimate of gust risk outputs a gust risk indicative signal to a wind turbine controller.

17. The gust risk estimator according to claim 16 , wherein the wind turbine controller controls the wind turbine from which the data processed by the gust risk estimator is obtained.

18. The gust risk estimator according to claim 16 , wherein the controller controls a plurality of wind turbines.

19. The gust risk estimator according to claim 15 , wherein the module for defining feature zones defines feature zones for each category of risk from the mean of feature vectors in that category.

20. The gust risk estimator according to claim 15 , wherein the module for defining feature zones defines feature zones for each category of risk from the mean and covariance of feature vectors in that category.

21. The gust risk estimator according to claim 15 , wherein the feature vectors are based on mean wind speeds.

22. The gust risk estimator according to claim 15 , wherein the controller is operable to overrate the wind turbine when the estimate of the risk of an extreme gust is low.

23. The gust risk estimator according to claim 15 , wherein the comparator assigns a level of risk to a feature vector based on the value of a measurable parameter following the measurement period in which the data from which the feature vector is derived was obtained.

24. The gust risk estimator according to claim 15 , wherein the comparator assigns to a feature vector a level of risk related to the maximum wind turbine generator speed that followed the measurement period.

25. The gust risk estimator according to claim 15 , wherein the feature vector calculated periodically from sensor data is added to the stored training data.

26. The gust risk estimator according to claim 25 , wherein training data items that have substantially the same value are merged together and weighted in the store.

27. The gust risk estimator according to claim 15 , wherein the estimate of gust risk is an estimate of extreme gust risk.

28. A wind turbine having a gust risk estimator according to claim 15 .

29. A wind park having a plurality of wind turbines and a gust risk estimator according to claim 15 .

Assignees

• Evans Martin
• Vestas Wind Sys As

Inventors

• Evans Martin

Classifications

• F05B2270/322

  the detection or prediction of a wind gust · CPC title

• F03D7/04

  Automatic control; Regulation · CPC title

• F05B2270/32

  Wind speeds · CPC title

• F03D11/0091 Primary

  Mechanical Engineering · mapped topic

• F03D7/042

  by means of an electrical or electronic controller · CPC title