Use of ss data trends in fault resolution process

• US 9,896,961 B2
• Filed: 09/15/2016
• Issued: 02/20/2018
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Rtx Corporation
• Original Assignee: United Technologies Corporation (Raytheon Technologies Corporation d/b/a RTX)
• Inventors: Brunschwig, Anya R., Grace, Amy Rose, Donovan, Bryan P., Ruestow, Andrew D., Kacprzynski, Gregory J., Pelosi, Charles
• Primary Examiner(s): GOLDMAN, RICHARD A
• Application Number:
  US15/266,070
• Publication Number:
  US 20170030217A1
• Time in Patent Office: 523 Days
• Field of Search: 701 314, 701 321, 701 334, 701 344, 701 99, 701100, 702185, 702183
• CPC Class Codes: F01D 21/003 Arrangements for testing or measuring for measuring vibrations G01H
• CPC Class Codes: F05D 2220/323 for aircraft propulsion, e.g. jet engines
• CPC Class Codes: G01M 15/14 Testing gas-turbine engines or jet-propulsion engines

Abstract

An automated method for resolving fault in an engine is disclosed. The method may include providing a reasoner module for recommending a set of maintenance actions to resolve fault in the engine, inputting steady state performance data from the engine into the reasoner module, and using the reasoner module to recommend a set of maintenance actions based at least in part on the steady state performance data. A fault resolution system for a gas turbine engine is also disclosed. The fault resolution system may include at least one computer processor operatively configured to receive steady state performance data from the gas turbine engine, and recommend a set of maintenance actions to resolve fault in the gas turbine engine based at least in part on the steady state performance data.

Claims

1. An automated method to resolve a fault in an engine, comprising:

collecting steady state performance data with an electronic control unit of the engine;

transmitting the steady state performance data from the electronic control unit to a fault resolution system;

compiling the steady state performance data via a parser module within the fault resolution system to create compiled steady state performance data readable by a reasoner module;

loading the compiled steady state performance data to a connectivity matrix of the reasoner module, the connectivity matrix linking the compiled steady state performance data to a maintenance action; and

outputting a ranked set of maintenance actions determined by an artificial intelligence module of the reasoner module based at least in part on the compiled steady state performance data.

2. The method of claim 1, further comprising using the reasoner module to compare the compiled steady state performance data to desired engine performance patterns, and using the artificial intelligence module of the reasoner module to provide a the ranked set of maintenance actions based at least in part on the comparison of the compiled steady state performance data to the desired engine performance patterns.

3. The method of claim 2, further comprising displaying the comparison of steady state performance data to the desired engine performance patterns as a percentage, the percentage determined by the accuracy of the compiled steady state performance data and matching the desired engine performance patterns.

4. The method of claim 1, further comprising inputting transmitting engine fault codes into the fault resolution system, compiling the engine fault codes with the parser module within the fault resolution system to create a compiled engine fault code data readable by the reasoner module, loading the compiled engine fault code data into the connectivity matrix of the reasoner module, the connectivity matrix linking the compiled engine fault code data to the maintenance action, and outputting the ranked set of maintenance actions determined by the artificial intelligence module of the reasoner module based at least in part on the compiled engine fault code data.

5. The method of claim 4, further comprising transmitting transient data from the engine into the fault resolution system, compiling the transient data with the parser module within the fault resolution system to create a compiled transient data readable by the reasoner module, loading the compiled transient data into the connectivity matrix of the reasoner module, the connectivity matrix linking the compiled transient data to the maintenance action, and outputting the ranked set of maintenance actions determined by the artificial intelligence module of the reasoner module based at least in part on the compiled transient data.

6. The method of claim 5, further comprising inputting maintainer observations into the reasoner module, and outputting the ranked set of maintenance actions determined by the artificial intelligence module of the reasoner module based at least in part on the maintainer observations.

7. The method of claim 6, further comprising providing the connectivity matrix linking the compiled steady state performance data, compiled engine fault code data, compiled transient data, and maintainer observations to maintenance actions.

8. The method of claim 7, further comprising using the artificial intelligence module of the reasoner module to rank the ranked set of maintenance actions in order of importance.

9. The method of claim 1, further comprising using the reasoner module to identify trends based on the steady state performance data.

10. The method of claim 9, further comprising using the reasoner module to match the steady state performance data trends to desired engine performance patterns.