Method of controlling a rotor of a wind turbine to deal with the risk of blade icing
A first aspect of the invention provides a method of controlling a rotor of a wind turbine, the method comprising: obtaining a determination of whether there is ice on the rotor; obtaining one or more factors; generating an ice likelihood based on the obtained one or more factors, wherein the ice likelihood is indicative of whether it is likely that ice is building up on the rotor or thawing on the rotor; generating a confidence level based on the determination and the ice likelihood, wherein the confidence level provides an indication of the confidence that the determination is true; and controlling the wind turbine based on the confidence level.
1 . A method of controlling a rotor of a wind turbine, the method comprising:
obtaining a determination of whether there is ice on the rotor;
obtaining one or more factors;
generating an ice likelihood based on the obtained one or more factors, wherein the ice likelihood is indicative of whether it is likely that ice is building up on the rotor or thawing on the rotor;
generating a confidence level based on the determination and the ice likelihood, wherein the confidence level provides an indication of the confidence that the determination is true; and
controlling the wind turbine based on the confidence level to modify operation of the wind turbine, wherein controlling the wind turbine based on the confidence level comprises altering a pitch angle of a blade of the rotor.
2 . The method of claim 1 , comprising repeating the obtaining of the one or more factors, the generating of the ice likelihood, and the generating of the confidence level, so as to update the confidence level with time.
3 . The method of claim 1 , wherein generating the ice likelihood based on the obtained one or more factors comprises using any time dependent factors of the one or more factors to generate a number, and scaling the number based on any time independent factors of the one or more factors to generate the ice likelihood.
4 . The method of claim 3 , wherein the time dependent factors include temperature; humidity; rotor speed; wind speed; time elapsed since obtaining the determination; wind turbine state; and pressure.
5 . The method of claim 3 , wherein the time independent factors include height of nacelle above ground; height of nacelle above sea level; and geographic location of the wind turbine.
6 . The method of claim 1 , wherein the one or more factors comprise one or more of the following: temperature; humidity; rotor speed; wind speed; time elapsed since obtaining the determination; wind turbine state; pressure; height of nacelle above ground; height of nacelle above sea level; and geographic location of the wind turbine.
7 . The method of claim 1 , wherein controlling the wind turbine based on the confidence level comprises generating an ice detection signal on the basis of the confidence level; and controlling the wind turbine on the basis of the ice detection signal.
8 . The method of claim 1 , wherein the determination is obtained during one of the following operational states of the wind turbine: production; idling and stopped.
9 . The method of claim 1 , wherein the confidence level is a non-binary value.
10 . The method of claim 9 , wherein the confidence level is a number between 0 and 1 inclusive.
11 . The method of claim 1 , further comprising:
determining an accuracy of the confidence level; and
adjusting an algorithm for generating the confidence level based on the determined accuracy.
12 . The method of claim 11 , wherein determining the accuracy of the confidence level comprises comparing the confidence level to a measurement of ice on the rotor.
13 . A wind turbine, comprising:
a tower;
a nacelle disposed on the tower;
a rotor extending from the nacelle and having a plurality of blades disposed on a distal end thereof; and
a controller configured to perform an operation, comprising:
obtaining a determination of whether there is ice on the rotor;
obtaining one or more factors;
generating an ice likelihood based on the obtained one or more factors, wherein the ice likelihood is indicative of whether it is likely that ice is building up on the rotor or thawing on the rotor;
generating a confidence level based on the determination and the ice likelihood, wherein the confidence level provides an indication of the confidence that the determination is true; and
controlling the wind turbine based on the confidence level to modify operation of the wind turbine, wherein controlling the wind turbine based on the confidence level comprises altering a pitch angle of a blade of the rotor.
14 . The wind turbine of claim 13 , wherein the operation further comprises repeating the obtaining of the one or more factors, the generating of the ice likelihood, and the generating of the confidence level, so as to update the confidence level with time.
15 . The wind turbine of claim 13 , wherein generating the ice likelihood based on the obtained one or more factors comprises using any time dependent factors of the one or more factors to generate a number, and scaling the number based on any time independent factors of the one or more factors to generate the ice likelihood.
16 . A computer program product comprising a non-transitory memory storing software code which, when executed on a data processing system, performs an operation, comprising:
obtaining a determination of whether there is ice on a rotor of a wind turbine;
obtaining one or more factors;
generating an ice likelihood based on the obtained one or more factors, wherein the ice likelihood is indicative of whether it is likely that ice is building up on the rotor or thawing on the rotor;
generating a confidence level based on the determination and the ice likelihood, wherein the confidence level provides an indication of the confidence that the determination is true; and
controlling the wind turbine based on the confidence level to modify operation of the wind turbine, wherein controlling the wind turbine based on the confidence level comprises altering a pitch angle of a blade of the rotor.
17 . The computer program product of claim 16 , wherein the operation further comprises repeating the obtaining of the one or more factors, the generating of the ice likelihood, and the generating of the confidence level, so as to update the confidence level with time.
18 . The computer program product of claim 16 , wherein generating the ice likelihood based on the obtained one or more factors comprises using any time dependent factors of the one or more factors to generate a number, and scaling the number based on any time independent factors of the one or more factors to generate the ice likelihood.