Method and system for evaluation of engine condition

• US 10,151,739 B2
• Filed: 04/25/2016
• Issued: 12/11/2018
• Est. Priority Date: 04/25/2016
• Status: Active Grant

• Current Assignee: Pratt & Whitney Canada Corporation (Raytheon Technologies Corporation d/b/a RTX)
• Original Assignee: Pratt & Whitney Canada Corporation (Raytheon Technologies Corporation d/b/a RTX)
• Inventors: Jean, Maurice
• Primary Examiner(s): McCall, Eric S
• Application Number:
  US15/137,841
• Publication Number:
  US 20170307583A1
• Time in Patent Office: 960 Days
• Field of Search: 7311455, 7311456
• CPC Class Codes: F01D 21/003 Arrangements for testing or measuring for measuring vibrations G01H
• CPC Class Codes: F01D 25/18 Lubricating arrangements of machines or engines in general F01M
• CPC Class Codes: F05D 2260/821 Parameter estimation or prediction
• CPC Class Codes: G01N 23/2252 Measuring emitted X-rays, e.g. electron probe microanalysis [EPMA]
• CPC Class Codes: G01N 33/2858 metal particles
• CPC Class Codes: Y02T 10/62 Hybrid vehicles
• CPC Class Codes: Y02T 50/60 Efficient propulsion technologies, e.g. for aircraft

Abstract

There is described herein methods and systems for comparing an engine fluid signature of a first engine with engine fluid signatures of other engines of a same engine family. A delta signature is obtained via the comparison and delta signatures below a given threshold are considered similar. Historical data for each engine having a similar signature may then be used to determine the condition and the future states of the first engine.

Claims

1. A method for evaluating a condition of an engine, the method comprising:

obtaining a sample signature of a first engine, the sample signature characterizing the first engine as a function of a fluid sample of the first engine;

comparing the sample signature to a plurality of reference signatures obtained from reference engines belonging to a common family with the first engine;

selecting ones of the reference engines for which a difference between a corresponding reference signature and the sample signature is below a threshold; and

providing historical engine data of the selected ones of the reference engines as a basis for evaluating the condition of the first engine;

wherein the difference between the corresponding reference signature and the sample signature is found using;

2. The method as claimed in claim 1, wherein the first engine and the reference engines belong to a common family when they correspond to a same engine model.

3. The method of claim 1, wherein providing historical engine data of the selected ones of the reference engines comprises providing a total number of operating hours of the selected ones of the reference engines.

4. The method of claim 1, wherein providing historical engine data of the selected ones of the reference engines comprises identifying which portion of the selected ones of the reference engines ran without any problems for at least one total number of operating hours.

5. The method of claim 1, further comprising estimating a condition of the first engine based on the historical data of the selected ones of the reference engines.

6. The method of claim 1, wherein obtaining a sample signature of the first engine comprises obtaining fluid sample data and generating the sample signature.

7. The method of claim 6, wherein generating the sample signature comprises assigning weights to different data sets of the fluid sample data, each one of the data sets corresponding to one or more classes of materials into which particles of the sample fluid are sorted.

8. The method of claim 7, wherein assigning weights to different data sets comprises assigning a total weight to each data set, the total weight composed of a predetermined weight and a variable weight.

9. The method of claim 8, wherein the variable weights are based on a deviation of a given value for a given data set from an average value for the given data set.

10. A system for evaluating a condition of an engine, the system comprising:

a processing unit; and

a non-transitory memory communicatively coupled to the processing unit and comprising computer-readable program instructions executable by the processing unit for;

obtaining a sample signature of a first engine, the sample signature characterizing the first engine as a function of a fluid sample of the first engine;

comparing the sample signature to a plurality of reference signatures obtained from reference engines belonging to a common family with the first engine;

selecting ones of the reference engines for which a difference between a corresponding reference signature and the sample signature is below a threshold; and

providing historical engine data of the selected ones of the reference engines as a basis for evaluating the condition of the first engine;

wherein the difference between the corresponding reference signature and the sample signature is found using;

11. The system as claimed in claim 10, wherein the first engine and the reference engines belong to a common family when they correspond to a same engine model.

12. The system of claim 10, wherein providing historical engine data of the selected ones of the reference engines comprises providing a total number of operating hours of the selected ones of the reference engines.

13. The system of claim 10, wherein providing historical engine data of the selected ones of the reference engines comprises identifying which portion of the selected ones of the reference engines ran without any problems for at least one total number of operating hours.

14. The system of claim 10, wherein the program instructions are further executable for estimating a condition of the first engine based on the historical data of the selected ones of the reference engines.

15. The system of claim 10, wherein obtaining a sample signature of the first engine comprises obtaining fluid sample data and generating the sample signature.

16. The system of claim 15, wherein generating the sample signature comprises assigning weights to different data sets of the fluid sample data, each one of the data sets corresponding to one or more classes of materials into which particles of the sample fluid are sorted.

17. The system of claim 16, wherein assigning weights to different data sets comprises assigning a total weight to each data set, the total weight composed of a predetermined weight and a variable weight.

18. The system of claim 17, wherein the variable weights are based on a deviation of a given value for a given data set from an average value for the given data set.