Diagnosis of aircraft gas turbine engines

• US 10,013,814 B2
• Filed: 03/02/2016
• Issued: 07/03/2018
• Est. Priority Date: 03/04/2015
• Status: Active Grant

• Current Assignee: MTU Aero Engines AG (MTU)
• Original Assignee: MTU Aero Engines AG (MTU)
• Inventors: Kando, Andre, Abdullahi, Hassan, Tsalavoutas, Anastasios, Speer, Thomas
• Primary Examiner(s): Butler, Rodney A
• Application Number:
  US15/058,237
• Publication Number:
  US 20160260263A1
• Time in Patent Office: 853 Days
• CPC Class Codes: B64D 2045/0085 Devices for aircraft health monitoring, e.g. monitoring flutter or vibration
• CPC Class Codes: B64D 45/00 Aircraft indicators or protectors not otherwise provided for camouflage F41H3/00
• CPC Class Codes: F02C 7/00 Features, components parts, details or accessories, not provided for in, or of interest apart form groups F02C1/00 - F02C6/00; Air intakes for jet-propulsion plants controlling F02C9/00
• CPC Class Codes: F05D 2230/72 Maintenance
• CPC Class Codes: F05D 2260/80 Diagnostics
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: G05B 23/0275 Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
• CPC Class Codes: G07C 5/004 Indicating the operating range of the engine economical driving B60R16/0236, F02B77/084; measuring liquid fuel of an engine G01F9/00

Abstract

A method for the at least partially automated diagnosis of aircraft gas turbine engines includes the steps of: 1) detecting actual parameter values of an aircraft gas turbine engine for several operational segments 2) determining deviations, of these actual parameter values from theoretical parameter values; and 3) determining damage pattern probabilities based on a similarity of at least one determined deviation, particularly based on a change between determined deviations, to deviation patterns of different known damage patterns.

Claims

1. A method for the at least partially automated diagnosis of aircraft gas turbine engines, comprising:

detecting actual parameter values of an aircraft gas turbine engine for several operational segments with sensors disposed within the aircraft gas turbine engine, the sensor types include at least one of a temperature sensor, a pressure sensor, a mass flow sensor, and a rotational speed sensor, the parameter values comprising temperatures in one or more operational segments of the gas turbine, pressures in one or more stages of the gas turbine, fuel consumption and/or fuel mass flow, and rotational speed values of a rotor of the aircraft gas turbine engine;

determining deviation, of these actual parameter values from theoretical parameter values of the operation of the aircraft gas turbine engine;

determining damage pattern probabilities based on a similarity of at least one determined deviation to deviation patterns of various known damage patterns to aircraft gas turbine engines;

determining a damage pattern probability for an unknown damage pattern; and

generating an error message if at least one determined deviation exceeds a predetermined limit value,

wherein damage patterns and/or causes comprise components, subassemblies, and/or defects.

2. The method according to claim 1, wherein cause probabilities are determined for an unknown damage pattern based on a model of the aircraft gas turbine engine.

3. The method according to claim 1, wherein cause probabilities based on variations in parameter values, combinatorial variations, of the model of the aircraft gas turbine engine are determined.

4. The method according to claim 2, wherein prior to determining the cause probabilities, the model of the aircraft gas turbine engine is calibrated, based on current actual parameter values of the aircraft gas turbine engine.

5. The method according to claim 4, wherein the current actual parameter values comprise detected actual parameter values for at least one of the most recent ten operational segments.

6. The method according to claim 1, wherein actual parameter values comprise values measured during operation and/or averaged values, and/or values transmitted via the internet, for different aircraft gas turbine engine parameters.

7. The method according to claim 1, wherein deviations of actual parameter values from theoretical parameter values are filtered.

8. The method according to claim 1, wherein theoretical parameter values are determined based on an initially calibrated model of the aircraft gas turbine engine.

9. The method according to claim 1, wherein the known damage patterns are stored in a database.

10. The method according to claim 1, wherein one or a plurality of the steps are carried out in an at least partially automated manner.

11. The method of claim 1, wherein the method is carried out in a system for the diagnosis of aircraft gas turbine engines.

12. The method of claim 1, wherein the method is carried out by a computer program product with a program code, which is stored on a medium readable by a computer.

13. The method according to claim 3, wherein prior to determining the cause probabilities, the model of the aircraft gas turbine engine is calibrated, based on current actual parameter values of the aircraft gas turbine engine.