IP Library › Granted Patent US 11,181,898
Granted Patent B2
US 11,181,898 · App. 15/809,768 · Granted Nov 23, 2021

Methods and apparatus to generate a predictive asset health quantifier of a turbine engine

Inventors: Srikanth Akkaram (West Chester, OH); Mariusz Wiklo (Warsaw, PL); Youngwon Shin (Niskayuna, NY); Ricardo Cuevas (Queretaro, MX); William Keith Kincaid (West Chester, OH); Jesus Miguel Valenzuela (Queretaro, MX); Gregory Jon Chiaramonte (West Chester, OH); Vasanth Muralidharan (Bangalore, IN); Charles Larry Abernathy (West Chester, OH); Venkata Vamsi Bhagavan (Bangalore, IN); Andrew Scott Kessie (Springboro, OH)
Assignee: General Electric Company
G05B23/0254G05B23/0289G05B23/0294F05B2260/80G05B23/0267G05B2219/45071G06Q10/06375
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 11,181,898
App. No.
15/809,768
Granted
Nov 23, 2021
Kind
B2
Abstract

Methods, apparatus, systems, and articles of manufacture are disclosed to generate a predictive asset health quantifier of a turbine engine. An example apparatus includes a performance model analyzer to determine a fleet behavior parameter by generating a reference performance model using historical information for a fleet of operators using turbine engines, generate a residual performance model based on calculating a difference between the fleet behavior parameter and a plurality of operator behavior parameters, identify an operator as a candidate improvement target based on comparing the operator behavior parameters corresponding to the operator to the fleet in the residual performance model, and determine an adjusted operator behavior parameter for the candidate improvement target. The example apparatus further includes a system updater to update a computer-based model to replace the operator behavior parameter with the adjusted operator behavior parameter, and a task optimizer to determine a workscope for the turbine engine.

Claims (44)

1. An apparatus comprising:

a performance model analyzer to:

determine a fleet behavior parameter as a function of an engine performance characteristic by generating a reference performance model using historical information for a fleet of operators using turbine engines, wherein the engine performance characteristic is a characteristic that impacts a performance or an operation of a turbine engine;

generate a residual performance model based on calculating a difference between the fleet behavior parameter and a plurality of operator behavior parameters corresponding to an operation of turbine engines operated by the fleet;

identify an operator as a candidate improvement target based on comparing the operator behavior parameters corresponding to the operator to the fleet in the residual performance model; and

determine an adjusted operator behavior parameter for the candidate improvement target, wherein the adjusted operator behavior parameter represents an adjusted manner in which the candidate improvement target is to operate a turbine engine, and wherein the fleet behavior parameter, the operator behavior parameters, and the adjusted operator behavior parameter is an engine de-rate parameter or a turbine engine taper schedule;

a system updater to update a computer-based model to replace the operator behavior parameter with the adjusted operator behavior parameter to calculate an asset health quantifier of the turbine engine operated by the candidate improvement target; and

a task optimizer to determine a workscope for the turbine engine based on calculating the asset health quantifier using the adjusted operator behavior parameter, the workscope to be performed on the turbine engine to improve an operation of the turbine engine.

2. The apparatus of claim 1 , wherein the engine performance characteristic is at least one of an aircraft weight, an airport elevation, or an ambient temperature.

3. The apparatus of claim 1 , wherein the reference performance model is a multi-variable regression model including a mapping of the fleet behavior parameter to the engine performance characteristic.

4. The apparatus of claim 1 , further including the performance model analyzer to:

determine the fleet behavior parameter as a function of the engine performance characteristic by generating a physics-based reference model using simulated operator behavior parameters for the fleet; and

generate the residual performance model based on calculating a difference between the fleet behavior parameter and an operator behavior parameter for the fleet.

5. The apparatus of claim 4 , wherein the simulated operator behavior parameters are calculated using a digital twin model of a turbine engine.

6. The apparatus of claim 1 , further including to performance model analyzer to generate an alert dashboard including trend information corresponding to the operation behavior parameters for the fleet.

7. A method comprising:

determining a fleet behavior parameter as a function of an engine performance characteristic by generating a reference performance model using historical information for a fleet of operators using turbine engines, wherein the engine performance characteristic is a characteristic that impacts a performance or an operation of a turbine engine;

generating a residual performance model based on calculating a difference between the fleet behavior parameter and a plurality of operator behavior parameters corresponding to an operation of turbine engines operated by the fleet;

identifying an operator as a candidate improvement target based on comparing the operator behavior parameters corresponding to the operator to the fleet in the residual performance model;

determining an adjusted operator behavior parameter for the candidate improvement target, wherein the adjusted operator behavior parameter represents an adjusted manner in which the candidate improvement target is to operate a turbine engine, and wherein the fleet behavior parameter, the operator behavior parameters, and the adjusted operator behavior parameter is an engine de-rate parameter or a turbine engine taper schedule;

updating a computer-based model to replace the operator behavior parameter with the adjusted operator behavior parameter to calculate an asset health quantifier of the turbine engine operated by the candidate improvement target;

determining a workscope for the turbine engine based on calculating the asset health quantifier using the adjusted operator behavior parameter; and

performing the workscope on the turbine engine to improve an operation of the turbine engine.

8. The method of claim 7 , wherein the engine performance characteristic is at least one of an aircraft weight, an airport elevation, or an ambient temperature.

9. The method of claim 7 , wherein the reference performance model is a linear regression model including a mapping of the fleet behavior parameter to the engine performance characteristic.

10. The method of claim 7 , further including:

determining the fleet behavior parameter as a function of the engine performance characteristic by generating a physics-based reference model using simulated operator behavior parameters for the fleet; and

generating the residual performance model based on calculating a difference between the fleet behavior parameter and an operator behavior parameter for the fleet.

11. The method of claim 10 , wherein the simulated operator behavior parameters are calculated using a digital twin model of a turbine engine included in the fleet.

12. The method of claim 7 , further including generating an alert dashboard including trend information corresponding to the operation behavior parameters for the fleet.

13. A non-transitory computer readable storage medium comprising instructions which when executed, cause a machine to at least:

determine a fleet behavior parameter as a function of an asset characteristic by generating a reference performance model using historical information for a fleet of operators using turbine engines, wherein the engine performance characteristic is a characteristic that impacts a performance or an operation of a turbine engine;

generate a residual performance model based on calculating a difference between the fleet behavior parameter and a plurality of operator behavior parameters corresponding to an operation of turbine engines operated by the fleet;

identify an operator as a candidate improvement target based on comparing the operator behavior parameters corresponding to the operator to the fleet in the residual performance model;

determine an adjusted operator behavior parameter for the candidate improvement target, wherein the adjusted operator behavior parameter represents an adjusted manner in which the candidate improvement target is to operate a turbine engine, and wherein the fleet behavior parameter, the operator behavior parameters, and the adjusted operator behavior parameter is an engine de-rate parameter or a turbine engine taper schedule;

update a computer-based model to replace the operator behavior parameter with the adjusted operator behavior parameter to calculate an asset health quantifier of the turbine engine operated by the candidate improvement target; and

determine a workscope for the turbine engine based on calculating the asset health quantifier using the adjusted operator behavior parameter, the workscope to be performed on the turbine engine to improve an operation of the turbine engine.

14. The non-transitory computer readable storage medium of claim 13 , wherein the engine performance characteristic is at least one of an aircraft weight, an airport elevation, or an ambient temperature.

15. The non-transitory computer readable storage medium of claim 13 , wherein the reference performance model is a linear regression model including a mapping of the fleet behavior parameter to the engine performance characteristic.

16. The non-transitory computer readable storage medium of claim 13 , further including instructions which when executed, cause the machine to at least:

determine the fleet behavior parameter as a function of the engine performance characteristic by generating a physics-based reference model using simulated operator behavior parameters for the fleet; and

generate the residual performance model based on calculating a difference between the fleet behavior parameter and an operator behavior parameter for the fleet.

17. The non-transitory computer readable storage medium of claim 16 , wherein the simulated operator behavior parameters are calculated using a digital twin model of a turbine engine included in the fleet.

18. The non-transitory computer readable storage medium of claim 13 , further including instructions which when executed, cause the machine to at least generate an alert dashboard including trend information corresponding to the operation behavior parameters for the fleet.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 26, 2018
From: KESSIE, ANDREW SCOTT
To: GENERAL ELECTRIC COMPANY
Reel/Frame 044739/0126 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 14, 2017
From: AKKARAM, SRIKANTH; WIKLO, MARIUSZ; SHIN, YOUNGWON; CUEVAS, RICARDO; KINCAID, WILLIAM KEITH; VALENZUELA, JESUS MIGUEL; CHIARAMONTE, GREGORY JON; MURALIDHARAN, VASANTH; ABERNATHY, CHARLES LARRY; BHAGAVAN, VENKATA VAMSI
To: GENERAL ELECTRIC COMPANY
Reel/Frame 044120/0984 →
Continuity (1)
Related Publication 20190146470A1 · May 16, 2019
Cited By (1)
US 12,602,037