System and method for predicting wind turbine shutdowns due to excessive vibration

Patent metadata

Field	Value
Publication number	US-11261844-B2
Application number	US-201916288839-A
Country	US
Kind code	B2
Filing date	Feb 28, 2019
Priority date	Feb 28, 2019
Publication date	Mar 1, 2022
Grant date	Mar 1, 2022

Abstract

A method for operating a wind turbine includes determining at least one wind condition of the wind turbine for a plurality of time intervals. The method also includes determining a status of the wind turbine at the beginning of each of the plurality of time intervals. Further, the method includes determining at least one vibration parameter of the wind turbine for one or more preceding time intervals of the plurality of time intervals. Moreover, the method includes predicting whether a trip event is imminent based on the at least one wind condition, the status of the wind turbine at the beginning of each of the plurality of time intervals, and the vibration parameter. Thus, the method further includes implementing a control action for the wind turbine so as to prevent the trip event.

First claim

What is claimed is:

1. A method for operating a wind turbine, the method comprising:
determining, via a processor, at least one wind condition of the wind turbine for a plurality of time intervals;
determining, via the processor, a status of the wind turbine at the beginning of each of the plurality of time intervals;
determining, via the processor, at least one vibration parameter of the wind turbine for one or more preceding time intervals of the plurality of time intervals;
predicting for a subsequent time interval and a wind condition at the subsequent time interval, via a predictive computer model programmed within the processor, whether a trip event is imminent for the subsequent time interval based on the following factors for the preceding time intervals: the at least one wind condition, the status of the wind turbine at the beginning of each of the plurality of time intervals, and the vibration parameter; and,
implementing, via the processor, a control action for the wind turbine so as to prevent the trip event.

2. The method of claim 1 , wherein determining the status of the wind turbine at the beginning of each of the plurality of time intervals further comprises determining whether the wind turbine is shut down at the beginning of each of the plurality of time intervals.

3. The method of claim 1 , wherein determining the least one vibration parameter of the wind turbine for one or more preceding time intervals of the plurality of time intervals further comprises:
determining, via the processor, a vibration level of one or more components of the wind turbine;
continuously comparing, via the processor, the vibration level to a vibration threshold;
generating, via the processor, a vibration-induced fault when the vibration level exceeds the vibration threshold; and,
determining, via the processor, a number of vibration-induced faults for the one or more preceding time intervals of the plurality of time intervals.

4. The method of claim 3 , wherein determining the vibration level of one or more components of the wind turbine further comprises collecting vibration data for the plurality of time intervals via one or more sensors.

5. The method of claim 1 , wherein determining the at least one wind condition of the wind turbine for the plurality of time intervals further comprises:
receiving, via the computer-generated model, real-time wind data for the plurality of time intervals; and,
estimating, via the computer-generated model, the at least one wind condition of the wind turbine as a function of the real-time wind data.

6. The method of claim 1 , wherein the at least one wind condition comprises wind speed or wind direction.

7. The method of claim 6 , wherein determining the at least one wind condition of the wind turbine for the plurality of time intervals further comprises determining at least one of an average wind speed and/or an average wind direction for the plurality of time intervals.

8. The method of claim 7 , wherein determining the at least one wind condition of the wind turbine for the plurality of time intervals further comprises:
determining at least one of a predominant wind speed and/or a predominant wind direction based on the average wind speed and/or the average wind direction for the plurality of time intervals.

9. The method of claim 8 , wherein determining at least one of the predominant wind speed and/or the predominant wind direction based on the average wind speed and/or the average wind direction for the plurality of time intervals further comprises:
generating a first wind rose for the plurality of time intervals without a trip event using the average wind speed and the average wind direction;
generating a second wind rose for the plurality of time intervals with a trip even using the average wind speed and the average wind direction; and,
determining the predominant wind speed and the predominant wind direction using the first and second wind roses.

10. The method of claim 9 , wherein predicting whether the trip event is imminent based on the at least one wind condition, the status of the wind turbine at the beginning of each of the plurality of time intervals, and the vibration parameter further comprises:
predicting whether the trip event is imminent based on the predominant wind speed and the predominant wind direction, the status of the wind turbine at the beginning of each of the plurality of time intervals, and the vibration parameter.

11. The method of claim 1 , wherein implementing the control action for the wind turbine so as to prevent the trip event further comprises at least one of pitching one or more rotor blades of the wind turbine, yawing a nacelle of the wind turbine, or derating the wind turbine.

12. The method of claim 3 , wherein the one or more components of the wind turbine comprise at least one of a bedplate, a tower, a gearbox, a generator, a main shaft, a rotor blade, or a rotor.

13. A system for operating a wind turbine, the system comprising:
a controller comprising at least one processor, the processor configured to perform a plurality of operations, the plurality of operations comprising:
determining at least one wind condition of the wind turbine for a plurality of time intervals;
determining a status of the wind turbine at the beginning of each of the plurality of time intervals;
determining at least one vibration parameter of the wind turbine for one or more preceding time intervals of the plurality of time intervals;
predicting for a subsequent time interval and a wind condition at the subsequent time interval, via a predictive computer model programmed within the processor, whether a trip event is imminent for the subsequent time interval based on the following factors for the preceding time intervals: the at least one wind condition, the status of the wind turbine at the beginning of each of the plurality of time intervals, and the vibration parameter; and,
implementing a control action for the wind turbine so as to prevent the trip event.

14. A method for operating a wind turbine, the method comprising:
determining, via the processor, whether a shutdown event occurred during one or more of a plurality of time intervals;
determining, via the processor, a vibration level of one or more components of the wind turbine;
continuously comparing, via the processor, the vibration level to a vibration threshold;
generating, via the processor, a vibration-induced fault when the vibration level exceeds the vibration threshold;
determining, via the processor, a number of vibration-induced faults for a preceding time interval within the plurality of time intervals;
predicting, via a predictive computer model programmed within the processor, whether a trip event is imminent based on whether the shutdown event occurred during one or more of the plurality of time intervals and the number of vibration-induced faults; and,
implementing, via the processor, a control action for the wind turbine so as to prevent the trip event.

15. The system of claim 14 , further comprising determining at least one wind condition of the wind turbine for the plurality of time intervals by:
receiving, via the computer-generated model, real-time wind data for a plurality of time intervals; and,
estimating, via the computer-generated model, the at least one wind condition of the wind turbine as a function of the real-time wind data.

16. The method of claim 15 , wherein the at least one wind condition comprises wind speed or wind direction.

17. The method of claim 16 , wherein determining the at least one wi

Assignees

• Gen Electric

Inventors

• Hotimsky Chad Moshe
• Doganaksoy Necip

Classifications

• F05B2270/32

  Wind speeds · CPC title

• F05B2260/70

  Adjusting of angle of incidence or attack of rotating blades · CPC title

• F03D7/0268

  Parking or storm protection · CPC title

• F05B2270/402

  passive or reactive, e.g. using large wind vanes · CPC title

• F03D7/045 Primary

  with model-based controls · CPC title