Method and system for failure prediction using lubricating fluid analysis

• US 9,897,582 B2
• Filed: 10/26/2012
• Issued: 02/20/2018
• Est. Priority Date: 10/26/2012
• Status: Active Grant

• Current Assignee: Pratt & Whitney Canada Corporation (Rtx Corporation)
• Original Assignee: Pratt & Whitney Canada Corporation (Rtx Corporation)
• Inventors: Jean, Maurice, Meilleur, Daniel
• Primary Examiner(s): Breene, John
• Assistant Examiner(s): Islam, Mohammad
• Application Number:
  US13/661,181
• Publication Number:
  US 20140121994A1
• Time in Patent Office: 1,943 Days
• CPC Class Codes: F01M 2011/14 for indicating the necessity to change the oil
• CPC Class Codes: F02D 41/22 Safety or indicating devices for abnormal conditions in air/fuel ratio feedback systems F02D41/1495, in electric control linkage F02D11/107, in purge control systems F02M25/0809
• CPC Class Codes: G01N 31/22 using chemical indicators G01N31/02 takes precedence
• CPC Class Codes: G01N 33/2858 Metal particles
• CPC Class Codes: G06F 15/00 Digital computers in general details G06F1/00 – G06F13/00; Data processing equipment in general
• CPC Class Codes: Y02T 10/40 Engine management systems

Abstract

Methods and systems for failure prediction using analysis of oil or other lubricant. Raw data about feature(s) of each of a plurality of particles filtered from a fluid sample are used to categorize each particle into one of a plurality of categories, each category being defined by one or more of: chemical composition, size and morphology. Particle physical characteristics in each category are quantified to obtain a set of categorized data. The categorized data are compared with historical data. Results of the comparing are evaluated to generate a prediction of any failure or mechanism of failure.

Claims

1. A method for failure prediction in an engine, the method comprising:

receiving a sample of lubricant fluid from the engine, the sample of lubricant fluid having particles suspended therein;

filtering a plurality of the particles from the sample of lubricant fluid;

collecting raw data representing a plurality of features of each of the plurality of particles filtered from the lubricant fluid of the engine, the engine belonging to an engine type, the plurality of features including at least one physical characteristic and one chemical composition, the collecting of the raw data comprising performing particle analysis using X-ray spectroscopy;

using one or more processors and the raw data;

categorizing each particle into one of a plurality of categories according to at least one of the plurality of features by calculating a likelihood that a given particle belongs to a given category, at least one category being defined by a chemical composition zone within a three-chemical-element system;

quantifying particle physical characteristics in each category to obtain a set of categorized data;

comparing the set of categorized data with at least one set of historical data associated with the engine type, the historical data being retrieved from a database;

evaluating results of the comparing using a set of predefined rules to generate a prediction of any failure or mechanism of failure; and

generating an output indicating the prediction to indicate one or both of the following;

when the engine is expected to fail and the mechanism of failure of the engine.

2. The method of claim 1, wherein quantifying comprises determining a number of particles for a given category, and normalizing the number of particles.

3. The method of claim 1, wherein each particle within each category is further sorted into a plurality of bins according to physical characteristics, wherein quantifying the particle physical characteristics in each category comprises determining a number of particles sorted into each bin.

4. The method of claim 1, wherein the physical characteristics comprise at least one of a size and a morphology of each particle.

5. The method of claim 1, wherein the chemical composition comprises an alloy composition of each particle.

6. The method of claim 1, wherein the at least one set of historical data is in the form of a historical model generated from a plurality of sets of historical data.

7. The method of claim 1, wherein the plurality of particles comprises particles smaller than about 30 μ

m in diameter.

8. The method of claim 1, wherein the plurality of particles comprises particles sized in the range of about 0.5 μ

m to about 1600 μ

m in diameter.

9. The method of claim 1, wherein the plurality of categories comprises at least one sub-category.

10. The method of claim 1, wherein the plurality of categories comprises at least one category defined according to:

elemental composition, alloy composition and particle source.

11. The method of claim 1, wherein the comparison comprises at least one of a calculation of deviation of the categorized data from the historical data, and a calculation of variation of the categorized data from the historical data.

12. The method of claim 1, wherein the comparison comprises at least one of a comparison of the categorized data in each category to the historical data, and a comparison of a composite of the categorized data to the historical data.

13. The method of claim 1, wherein the predicted mechanism of failure comprises at least one of a determination of premature wear of an engine component and a determination of an expected failure of an engine.

14. The method of claim 13 wherein the predicted mechanism of failure includes at least one of:

excess vibration, bearing wear, external contamination following engine maintenance, bearing rubbing, gear degradation, and bearing cage and race degradation.

15. The method of claim 1, wherein the engine is an aircraft engine.

16. The method of claim 1, wherein using X-ray spectroscopy includes using X-ray fluorescence.

17. A system for fluid analysis, the system comprising one or more processors and a memory containing machine-readable instructions for execution by the one or more processors of the system, the machine-readable instructions causing the one or more processors of the system to carry out the steps performed by the one or more processors in the method of claim 1.

18. The system of claim 17 further comprising spectroscopy equipment for carrying out particle analysis.

19. A non-transitory computer-readable medium or media embodying computer-executable instructions configured for causing the one or more processors of the method of claim 1 to carry out the steps performed by the one or more processors in the method of claim 1.