IP Library › Granted Patent US 12,234,808
Granted Patent B2
US 12,234,808 · App. 17/767,166 · Granted Feb 25, 2025

System and method for scheduling preventative maintenance actions based on operational usage

Inventors: Edward Lee McGrath (Greer, SC); Brian J. Theilemann (Ballston Lake, NY); Michael James Rizzo (Glenville, SC); Robert Randall Waara (Simpsonville, SC); Brian Scott Geist (Ballston Spa, NY); Kyle Edward Thompson (Rotterdam, NY)
Assignee: GE Infrastructure Technology LLC
F03D80/50F03D9/257G01M13/00G05B23/0283G06Q10/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,234,808
App. No.
17/767,166
Granted
Feb 25, 2025
Kind
B2
Abstract

A method for operating and maintaining a wind farm comprising a plurality of wind turbines includes determining an odometer for one or more components of at least one of the pluralities of wind turbines in the wind farm, the odometer representing operational usage of the component(s). The method also includes tracking the operational usage for the component(s) using the odometer and a usage threshold. Further, the method includes predicting an expected time frame for one or more preventative maintenance actions based on a comparison of the tracked operational usage and the usage threshold. Moreover, the method includes triggering scheduling of the one or more preventative maintenance actions when the prediction indicates that the tracked operational usage will exceed the usage threshold. In addition, the method includes shutting down the wind turbine or idling the wind turbine once the one or more preventative maintenance actions are scheduled.

Claims (62)

1. A method for operating and maintaining a wind farm comprising a plurality of wind turbines, the method comprising:

determining an odometer for one or more components of at least one of the plurality of wind turbines in the wind farm, the odometer representing operational usage of the one or more components;

tracking the operational usage for the one or more components using the odometer and a usage threshold;

predicting an expected time frame for one or more preventative maintenance actions based on a comparison of the tracked operational usage and the usage threshold;

triggering scheduling of the one or more preventative maintenance actions when the prediction indicates that the tracked operational usage will exceed the usage threshold; and,

shutting down the wind turbine or idling the wind turbine once the one or more preventative maintenance actions are scheduled.

2. The method of claim 1 , wherein determining the odometer for one or more components of the plurality of wind turbines in the wind farm further comprises:

calculating the odometer for one or more components of the plurality of wind turbines in the wind farm using at least one of physics analysis, a transfer function, operational data, turbine configuration specifics, materials, or combinations thereof, the operational data comprising sensor data, historical wind turbine operational data, historical wind farm operational data, historical maintenance data, historical quality issues, or combinations thereof.

3. The method of claim 2 , wherein the operational data comprises one or more of the following operational parameters: power output, torque, pitch angle, a loading condition, generator speed, generator revolution accumulation, rotor speed, rotor revolution accumulation, wind direction, air density, turbulence intensity, wind gusts, wind shear, wind speed, wind upflow, an amount of yawing, an amount of pitching, or temperature.

4. The method of claim 2 , wherein calculating the odometer for one or more components of the plurality of wind turbines in the wind farm further comprises:

receiving the operational data;

normalizing the operational data; and,

calculating the odometer by inputting the normalized operational data into a computer-implemented model.

5. The method of claim 4 , wherein the computer-implemented model comprises a damage accumulation model.

6. The method of claim 2 , further comprising:

grouping a plurality of preventative maintenance actions together into a plurality of modules based on at least one of maintenance type, maintenance location within a respective wind turbine, required tooling for the one or more preventative maintenance actions, or technician skill; and,

identifying one or more critical preventative maintenance actions within the plurality of modules based on risk.

7. The method of claim 6 , wherein determining the odometer for one or more components of the plurality of wind turbines in the wind farm further comprises:

determining a module odometer for the one or more critical preventative maintenance actions in each of the plurality of modules.

8. The method of claim 7 , further comprising:

setting a required reliability level for each of the plurality of wind turbines in the wind farm and/or the one or more components; and,

performing a reliability analysis for each of the one or more critical preventative maintenance actions using the operational data and the required reliability level; and,

determining a module usage threshold for each of the module odometers using the reliability analysis, each of the module usage thresholds corresponding to a value at which the one or more critical preventative maintenance actions is triggered.

9. The method of claim 8 , further comprising updating the reliability analysis over time using feedback from real-time operational data and/or maintenance data.

10. The method of claim 8 , further comprising utilizing machine learning to automatically adjust the module usage thresholds based on the real-time operational data and/or maintenance data.

11. The method of claim 8 , wherein predicting the expected time frame for one or more preventative maintenance actions based on the comparison of the tracked operational usage and the usage threshold further comprises:

predicting the expected time frame for the one or more critical preventative maintenance actions based on the comparison of the tracked operational usage and module usage thresholds.

12. The method of claim 11 , wherein triggering scheduling of the one or more preventative maintenance actions when the prediction indicates that the tracked operational usage will exceed the usage threshold further comprises:

triggering scheduling of the plurality of maintenance actions within one or more of the plurality of modules when the prediction indicates that the operational usage of the one or more components will exceed one or more of the module usage thresholds.

13. The method of claim 12 , further comprising:

delaying the triggering of the scheduling of each of the plurality of maintenance actions up to a maximum time frame for as long as the operational usage for the one or more components remains below the respective module usage thresholds; and,

triggering scheduling of the plurality of maintenance actions when the maximum time frame is reached.

14. The method of claim 12 , further comprising:

setting a minimum time frame for triggering scheduling of each of the plurality of maintenance actions; and,

if one or more of the respective module usage thresholds is reached before the minimum time frame, delaying scheduling of the plurality of maintenance actions until the minimum time frame is reached.

15. The method of claim 12 , wherein the triggering scheduling of the plurality of maintenance actions within one or more of the plurality of modules further comprises at least one of:

triggering scheduling of a first module of the plurality of modules every other time or a plurality of times scheduling of a second module of the plurality of modules is triggered; or

triggering scheduling of the first module of the plurality of modules only when both scheduling of the second module of the plurality of modules is triggered and another condition is met.

16. A method for operating and maintaining a wind farm comprising a plurality of wind turbines, the method comprising:

providing a schedule for preventative maintenance for each of the plurality of wind turbines, the schedule comprising a timeline for one or more preventative maintenance actions throughout a lifecycle of each of the plurality of wind turbines;

tracking an operational usage for each of the plurality of wind turbines in the wind farm up to a predetermined threshold;

triggering scheduling of the one or more preventative maintenance actions sooner than set forth via the schedule when the operational usage for one or more of the plurality of wind turbines exceeds a usage threshold during the lifetime and delaying the one or more preventative maintenance actions with respect to the schedule when the operational usage for one or more of the plurality of wind turbines remains below the usage threshold; and,

shutting down the wind turbine or idling the wind turbine once the one or more preventative maintenance actions are scheduled.

17. A system for operating and maintaining a wind turbine, the system comprising:

a controller comprising a maintenance software package, the maintenance software package configured to implement a plurality of operations, the plurality of operations comprising:

determining an odometer for one or more components of the wind turbine, the odometer representing operational usage of the one or more components;

tracking the operational usage for the one or more components using the odometer and a usage threshold;

predicting an expected time frame for one or more preventative maintenance actions based on a comparison of the tracked operational usage and the usage threshold;

triggering the one or more preventative maintenance actions when the prediction indicates that the tracked operational usage will exceed the usage threshold; and,

shutting down the wind turbine or idling the wind turbine once the one or more preventative maintenance actions are triggered.

18. The system of claim 17 , wherein determining the odometer for one or more components of the wind turbine further comprises:

calculating the odometer for one or more components of the wind turbine using at least one of physics analysis, a transfer function, operational data, or combinations thereof, the operational data comprising sensor data, historical wind turbine operational data, historical wind farm operational data, historical maintenance data, historical quality issues, or combinations thereof, the operational data further comprising one or more of the following operational parameters: power output, torque, pitch angle, a loading condition, generator speed, rotor speed, wind direction, air density, turbulence intensity, wind gusts, wind shear, wind speed, wind upflow, an amount of yawing, an amount of pitching, or temperature.

19. The system of claim 18 , wherein the plurality of operations further comprises:

grouping a plurality of maintenance actions together into a plurality of modules based on at least one of maintenance type, maintenance location within the wind turbine, required tooling for the one or more preventative maintenance actions, or technician skill;

identifying one or more critical preventative maintenance actions within the plurality of modules based on risk; and,

determining a module odometer for the one or more critical preventative maintenance actions in each of the plurality of modules.

20. The system of claim 19 , further comprising:

setting a required reliability level for the one or more components of the wind turbine; and,

performing a reliability analysis for each of the one or more critical preventative maintenance actions using the operational data and the required reliability level;

determining a module usage threshold for each of the module odometers using the reliability analysis, each of the module usage thresholds corresponding to a value at which the one or more critical preventative maintenance actions is triggered;

predicting the expected time frame for the one or more critical preventative maintenance actions based on the comparison of the tracked operational usage and module usage thresholds; and,

triggering scheduling of the plurality of maintenance actions within one or more of the plurality of modules when the prediction indicates that the operational usage of the one or more components will exceed one or more of the module usage thresholds.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 17, 2023
From: GENERAL ELECTRIC COMPANY
To: GE INFRASTRUCTURE TECHNOLOGY LLC
Reel/Frame 065727/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 7, 2022
From: MCGRATH, EDWARD LEE; THEILEMANN, BRIAN J.; RIZZO, MICHAEL JAMES; WAARA, ROBERT RANDALL; GEIST, BRIAN SCOTT; THOMPSON, KYLE EDWARD
To: GENERAL ELECTRIC COMPANY
Reel/Frame 059530/0884 →
Continuity (1)
Related Publication 20220364549A1 · Nov 17, 2022
References Cited (46)
US 2837984A · Klotz · 1958 [cited by applicant]
US 6922640B2 · Vezzu et al. · 2005 [cited by applicant]
US 7149657B2 · Goebel et al. · 2006 [cited by applicant]
US 7256508B2 · Altemark et al. · 2007 [cited by applicant]
US 7395188B1 · Goebel et al. · 2008 [cited by applicant]
US 7548830B2 · Goebel et al. · 2009 [cited by applicant]
US 7725293B2 · Bonissone et al. · 2010 [cited by applicant]
US 7889840B2 · Vasudevan et al. · 2011 [cited by applicant]
US 8108080B2 · Wakata et al. · 2012 [cited by applicant]
US 8249852B2 · Thulke · 2012 [cited by applicant]
US 8451134B2 · Bharadwaj et al. · 2013 [cited by applicant]
US 8554386B2 · Rutman · 2013 [cited by applicant]
US 9074468B1 · Selman et al. · 2015 [cited by applicant]
US 9194376B2 · Ritter et al. · 2015 [cited by applicant]
US 9395270B2 · Czerniak et al. · 2016 [cited by applicant]
US 9797328B2 · Martinez et al. · 2017 [cited by applicant]
US 9816483B2 · Nakamura et al. · 2017 [cited by applicant]
US 9859787B2 · Wagoner et al. · 2018 [cited by applicant]
US 9874107B2 · Falb et al. · 2018 [cited by applicant]
US 9897516B2 · Bechhoefer et al. · 2018 [cited by applicant]
US 10288043B2 · Yu et al. · 2019 [cited by applicant]
US 20040260512A1 · Olsson · 2004 [cited by applicant]
US 20050005186A1 · Goebel et al. · 2005 [cited by applicant]
US 20060228214A1 · Mabe et al. · 2006 [cited by applicant]
US 20080140361A1 · Bonissone et al. · 2008 [cited by applicant]
US 20110020122A1 · Parthasarathy et al. · 2011 [cited by applicant]
US 20120065901A1 · Bechhoefer et al. · 2012 [cited by applicant]
US 20120286509A1 · Rafoth · 2012 [cited by applicant]
US 20130073223A1 · Lapira et al. · 2013 [cited by applicant]
US 20140324495A1 · Zhou et al. · 2014 [cited by applicant]
US 20150381443A1 · Du Plessis · 2015 [cited by applicant]
US 20180173214A1 · Higgins et al. · 2018 [cited by applicant]
US 20180180026A1 · Spruce et al. · 2018 [cited by applicant]
US 20190203696A1 · Kaucic et al. · 2019 [cited by applicant]
CN 101218401A · 2008 [cited by applicant]
CN 102792240A · 2012 [cited by applicant]
CN 106097146A · 2016 [cited by applicant]
CN 107769254A · 2018 [cited by applicant]
CN 110059872A · 2019 [cited by applicant]
EP 2578874A1 · 2013 [cited by applicant]
EP 2457320B1 · 2014 [cited by applicant]
EP 2837984B1 · 2019 [cited by applicant]
EP 2956831B1 · 2019 [cited by applicant]
WO WO2017205221A1 · 2017 [cited by applicant]
PCT International Search Report & Opinion PCTUS2019055875 Jun. 15, 2020. [cited by applicant]
CN Office Action with Translation, Oct. 26, 2024. [cited by applicant]