Method, apparatus and system for wind converter management

Patent metadata

Field	Value
Publication number	US-11168669-B2
Application number	US-202016737982-A
Country	US
Kind code	B2
Filing date	Jan 9, 2020
Priority date	Jan 18, 2018
Publication date	Nov 9, 2021
Grant date	Nov 9, 2021

Abstract

A method for wind converter management, first and second data associated with a group of first measurements and a second measurement of the wind converter may be collected respectively. An association between the group of first measurements and the second measurement of the wind converter may be obtained. A condition of the wind converter may be determined based on a comparison of the collected first and second data and the obtained association. Also, the apparatuses, systems, computer readable media and IoT systems for wind converter management.

First claim

What is claimed is:

1. A method for managing a wind converter, comprising:
selecting a group of first measurements and a second measurement that have a causal relationship from a plurality of measurements of the wind converter based on a machine learning process, the group of first measurements and the second measurement being measurements for various components within the wind converter;
collecting first and second data associated with the group of first measurements and the second measurement of the wind converter, respectively;
obtaining an association between the group of first measurements and the second measurement of the wind converter, wherein the obtaining an association comprises:
selecting a reference association between a group of first measurements and a second measurement of a reference wind converter; and
obtaining the association by modifying the reference association based on at least one of:
types of the wind converter and the reference wind converter; and
geographic locations of the wind converter and the reference wind converter; and

determining a condition of the wind converter based on a comparison of the collected first and second data and the obtained association.

2. The method of claim 1 , wherein the determining a condition of the wind converter comprises:
generating an estimation of the second data based on the association and the collected first data; and
determining the condition of the wind converter based on a difference between the estimation of the second data and the collected second data.

3. The method of claim 2 , wherein the determining the condition of the wind converter based on the difference comprises:
in response to the difference being above a predefined threshold, identifying the condition as abnormal; and/or
in response to the difference being below the predefined threshold, identifying the condition as normal.

4. The method of claim 3 , further comprising:
in response to the determined condition being abnormal,
determining a severity of the wind converter based on a change over time in the difference;
determining a lifetime of the wind converter based on the determined severity; and/or
detecting a cause of the abnormal condition based on monitoring a condition of at least one component in the wind converter.

5. The method of claim 1 , wherein the obtaining an association comprises:
collecting historical first and second data associated with the group of first measurements and the second measurement of the wind converter, respectively; and
obtaining the association by establishing a knowledge model based on the collected historical first and second data.

6. The method of claim 5 , wherein the collecting historical first and second data comprises:
collecting the historical first and second data during a period when the condition of the wind converter is normal.

7. The method of claim 1 , further comprising:
adjusting an output power of the wind converter based on the determined condition.

8. The method of claim 1 , further comprising:
with respect to a group of wind converters located in a wind farm in which the wind converter is located, adjusting an output power dispatch among the group of converters based on the determined condition.

9. The method of claim 1 , wherein modifying the reference association further comprises:
modifying the reference association based on an operation period of the wind converter and the reference wind converter.

10. An apparatus for managing a wind converter, comprising:
a selecting unit configured to select a group of first measurements and a second measurement that have a causal relationship from a plurality of measurements of the wind converter based on a machine learning process, the group of first measurements and the second measurement being measurements for various components within the wind converter;
a collecting unit configured to collect first and second data associated with the group of first measurements and the second measurement of the wind converter, respectively;
an obtaining unit configured to obtain an association between the group of first measurements and the second measurement of the wind converter, wherein the obtaining unit comprises:
a reference selecting unit configured to selecting a reference association between a group of first measurements and a second measurement of a reference wind converter; and
a forming unit configured to form the association by modifying the reference association based on at least one of:
types of the wind converter and the reference wind converter; and
geographic locations of the wind converter and the reference wind converter; and

a determining unit configured to determine a condition of the wind converter based on a comparison of the collected first and second data and the obtained association.

11. The apparatus of claim 10 , wherein the determining unit comprises:
an estimation generating unit configured to generate an estimation of the second data based on the association and the collected first data; and
a condition determining unit configured to determine the condition of the wind converter based on a difference between the estimation of the second data and the collected second data.

12. The apparatus of claim 11 , wherein the condition determining unit is further configured to:
in response to the difference being above a predefined threshold, identify the condition as abnormal; and
in response to the difference being below the predefined threshold, identify the condition as normal.

13. The apparatus of claim 12 , further comprising:
a severity determining unit configured to, in response to the determined condition being abnormal, determine a severity of the wind converter based on a change over time in the difference;
a lifetime determining unit configured to determine a lifetime of the wind converter based on the determined severity; and
a cause determining unit configured to detect a cause of the abnormal condition based on monitoring a condition of at least one component in the wind converter.

14. The apparatus of claim 10 , wherein the obtaining unit comprises:
a historical data collecting unit configured to collect historical first and second data associated with the group of first measurements and the second measurement of the wind converter, respectively; and
an association obtaining unit configured to obtaining the association by establishing a knowledge model based on the collected historical first and second data.

15. The apparatus of claim 14 , wherein the historical data collecting unit is further configured to collect the historical first and second data during a period when the condition of the wind converter is normal.

16. The apparatus of claim 10 , further comprising:
an adjusting unit configured to adjust an output power of the wind converter based on the determined condition.

17. The apparatus of claim 10 , further comprising:
an adjusting unit configured to, with respect to a group of wind converters located in a wind farm in which the wind converter is located, adjust an output power dispatch among the group of converters based on the determined condition.

18. The apparatus of claim 10 , wherein the forming unit is further configured to form the association by modifying the reference association based on:
an operation period of the wind converter and the reference wind converter.

19. A system for managing a wind converter, comprising:
a computer processor coupled to a computer-readable memory unit, the mem

Assignees

• Abb Schweiz Ag

Inventors

• Yu Rongrong
• Chen Niya
• Xie Hailian
• Ruan Jiayang
• Vinko Antti

Classifications

• Y02E10/72

  Wind turbines with rotation axis in wind direction · CPC title

• F05B2270/335

  Output power or torque · CPC title

• F03D7/048

  controlling wind farms · CPC title

• F05B2260/80

  Diagnostics · CPC title

• F05B2260/821

  Parameter estimation or prediction · CPC title