Usage Based Lifing

Patent metadata

Field	Value
Publication number	US-2018307784-A1
Application number	US-201715493513-A
Country	US
Kind code	A1
Filing date	Apr 21, 2017
Priority date	Apr 21, 2017
Publication date	Oct 25, 2018
Grant date	—

Abstract

Systems and methods for predicting usage based lifing and low cycle fatigue consumption are provided. In one example embodiment, a method can include obtaining historical flight data associated with one or more gas turbine engines of an aerial vehicle; obtaining data indicative of one or more operational conditions of the aerial vehicle during an operating period; determining whether the flight data is indicative of a usable flight; and constructing a model correlating low cycle fatigue consumption with flight data using a machine learning technique.

First claim

What is claimed is:

1 . A method for constructing a model correlating low cycle fatigue consumption with flight data, the method comprising:
obtaining, by one or more computing devices, historical data indicative of one or more operational conditions of an aerial vehicle; obtaining, by one or more computing devices, flight data indicative of one or more operational conditions of the aerial vehicle during an operating period; determining, by one or more computing devices, whether the flight data is indicative of a usable flight; and in response to determining that the flight data is indicative of a usable flight, constructing a model, based at least in part on historical data, correlating low cycle fatigue consumption with the flight data using a machine learning technique.

2 . The method of claim 1 , wherein the flight data is obtained by one or more sensors associated with a health and usage monitoring system.

3 . The method of claim 2 , wherein the flight data comprises:
engine flight data, wherein the engine flight data is indicative of one or more operational conditions of one or more gas turbine engines of an aerial vehicle during the operating period; and vehicle flight data, wherein the vehicle flight data is indicative of one or more operational conditions the aerial vehicle during the operating period.

4 . The method of claim 3 , further comprising determining a predicted usage based life (UBL) for one or more components of the gas turbine engines based at least in part on the model.

5 . The method of claim 4 , wherein determining whether the flight data is indicative of a usable flight comprises:
determining whether the flight data includes engine flight data and vehicle flight data.

6 . The method of claim 5 , wherein the components of the gas turbine engines comprise rotating life limited parts.

7 . The method of claim 6 , wherein during determining, it is determined that the flight data is not indicative of a usable flight, the method further comprises:
adjusting the predicted UBL to a first default value; and storing the first default value as a UBL Equivalent Cycle in a memory.

8 . The method of claim 6 , further comprising:
determining whether the predicted UBL is within an upper threshold and a lower threshold; and in response to determining that the predicted UBL in not within the upper threshold and the lower threshold, adjusting the predicted UBL to a second default value.

9 . The method of claim 8 , further comprising:
determining a UBL Equivalent Cycle for the one or more components of the gas turbine engine, based at least in part on a predetermined life factor and a predetermined life limit; and storing the determined UBL Equivalent Cycle in a memory.

10 . The method of claim 9 , further comprising:
determining maintenance requirements for one or more components of the gas turbine engine based at least in part on the UBL Equivalent Cycle.

11 . The method of claim 2 , wherein the model comprises a random forest model.

12 . The method of claim 11 , wherein the flight data is processed to determine one or more feature inputs for training the model.

13 . The method of claim 12 , wherein the one or more feature inputs comprise a time-at-value feature.

14 . The method of claim 13 , wherein the one or more feature inputs comprise a time-above-value feature.

15 . A system for modeling usage based life consumption of a gas turbine engine comprising:
one or more memory devices; one or more processors configured to:
obtain historical data indicative of operational conditions of the gas turbine engine;
obtain, flight data indicative of one or more operational conditions of an aerial vehicle during an operating period;
determine, whether the flight data is indicative of a usable flight;
generate a predicted usage based life (UBL) for one or more components of the gas turbine engine based on the historical data and the flight data using a machine learning technique;
determine a UBL Equivalent Cycle for the one or more components of the gas turbine engine based at least in part on a predetermined life factor and a predetermined life limit; and
store the determined UBL Equivalent Cycle in the memory device.

16 . The system of claim 15 , wherein the one or more processors are configured to:
generate one or more feature inputs, based on the flight data, for use with the machine learning technique.

17 . The system of claim 16 , wherein the machine learning technique is implemented at least in part by a random forest model.

18 . The system of claim 17 , wherein the one or more feature inputs comprise a time-at-value feature.

19 . The system of claim 18 , wherein the one or more feature inputs comprise a time-above-value feature.

20 . A computer-implemented method for predicting usage based life of one or more components of a gas turbine engine, the method comprising:
obtaining, by one or more computing devices, historical data indicative of operational conditions of one or more gas turbine engines of an aerial vehicle; obtaining, by one or more computing devices, flight data indicative of operational conditions of an aerial vehicle during an operating period; accessing a non-physics based model, based at least in part on historical data, correlating flight data with usage based life of one or more components of the gas turbine engine; and determining the remaining usage based life of the one or more components based at least in part on the model and the flight data.

Assignees

• Gen Electric

Inventors

• Stevens Craig Wesley
• Chan Simon Shu Kong
• Wu Siyu
• Vahldick Lauren Ashley
• Wight Ronald Burton
• Clements Robert Alan

Classifications

• G06F30/15 Primary

  Vehicle, aircraft or watercraft design · CPC title

• F05D2260/81

  Modelling or simulation · CPC title

• F05D2260/80

  Diagnostics · CPC title

• G06F30/20 Primary

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• F05D2270/71

  synthesized, i.e. parameter computed by a mathematical model · CPC title