System for detecting the first signs of a malfunction of an aircraft engine valve

• US 8,825,278 B2
• Filed: 02/22/2013
• Issued: 09/02/2014
• Est. Priority Date: 02/24/2012
• Status: Active Grant

• Current Assignee: Safran Aircraft Engine Company
• Original Assignee: Snecma (Safran SA)
• Inventors: Picart, Jean-Yves, Bense, William
• Primary Examiner(s): Black, Thomas
• Assistant Examiner(s): HUYNH, LUAT T
• Application Number:
  US13/774,065
• Publication Number:
  US 20130226395A1
• Time in Patent Office: 557 Days
• Field of Search: 701/29.1, 701/29.7, 701/29.9, 701/30.2, 701/100, 701/32.9
• US Class Current: 701/32.9
• CPC Class Codes: B64D 45/00 Aircraft indicators or protectors not otherwise provided for camouflage F41H3/00
• CPC Class Codes: F01D 17/08 responsive to condition of working-fluid, e.g. pressure
• CPC Class Codes: F01D 21/003 Arrangements for testing or measuring for measuring vibrations G01H
• CPC Class Codes: F02C 7/047 Heating to prevent icing
• CPC Class Codes: F05D 2260/80 Diagnostics
• CPC Class Codes: F05D 2260/81 Modelling or simulation
• CPC Class Codes: F05D 2270/3013 Outlet pressure
• CPC Class Codes: F16K 37/0083 by measuring valve parameters
• CPC Class Codes: F16K 37/0091 by measuring fluid parameters

Abstract

A method and a system for detecting the first signs of malfunction of an aircraft engine valve, including an acquisition device to acquire the output pressure measurements of the valve, and contextual and command data of the valve, a processor to define a set of indicators of the first signs of malfunction, according to the output pressure measurements and the contextual and command data. A set of estimators corresponding to the set of indicators of the first signs of a malfunction, is determined using a previously produced regression model. At least one distance between the set of indicators and the set of estimators is computed. The distance is compared to a threshold of the first signs of a malfunction, in order to detect the first signs of malfunction of the said valve.

Claims

1. A system for detecting the first signs of a malfunction of an aircraft engine valve, comprising:

an acquisition device to acquire the output pressure measurements of said valve, and contextual and command data of said valve,

a processor configured to define a set of indicators of the first signs of malfunction, according to said output pressure measurements and said contextual and command data, wherein said processor is further configured to determine a set of estimators corresponding to said set of indicators of the first signs of a malfunction, using a previously produced regression model,

said processor being further configured to compute at least one distance between said set of indicators and said set of estimators, and

said processor being further configured to compare said at least one distance to at least one threshold of the first signs of a malfunction, in order to detect the first signs of malfunction of the said valve.

2. A system according to claim 1, wherein the contextual data includes data of ambient pressure, of valve feed pressure and of temperature measurements, and wherein the command data includes instants when the orders are given to open and close said valve.

3. A system according to claim 2, wherein said set of indicators of the first signs of a malfunction includes one or more indicators among the following indicators:

opening time of said valve, determined by the period between the instant when the valve is given an order to open, and the instant when the output pressure confirms a predetermined function indicative of an open valve,

closure time of said valve, determined by the period between the instant when the valve is given an order to close, and the instant when the output pressure is approximately equal to the ambient pressure,

open state of said valve, determined by a comparison between the output pressure and said predetermined function indicative of an open valve, and

closed state of said valve, determined by a comparison between the output pressure and the ambient pressure.

4. The system according to claim 1, wherein the processor is configured to determine the set of estimators by computing, for each indicator of the first signs of a malfunction, a corresponding estimator, according to the other indicators, and to at least one contextual data element, in accordance with said regression model.

5. A system according to claim 1, wherein the processor is configured to compare said at least one distance to at least one anomaly threshold if the threshold for the first signs of a malfunction is exceeded.

6. A system according to claim 1, wherein said at least one distance of the first signs of a malfunction is a single global Mahalanobis distance defined between an estimator vector formed by the set of indicators and an indicator vector formed by the set of indicators of the first signs of a malfunction.

7. A system according to claim 1, wherein the processor is configured to compute a set of individual distances, where each is defined between each indicator and its corresponding estimator, and wherein the processor is configured to compare the set of distances to a corresponding set of thresholds of the first signs of a malfunction.

8. A system according to claim 1, wherein said valve is an NAI-type value.

9. An aircraft engine comprising a detection system according to claim 1.

10. A method for detecting the first signs of a malfunction of an aircraft engine valve, said method comprising the following steps:

acquiring output pressure measurements of said valve, and contextual and command data of said valve,

defining a set of indicators of the first signs of malfunction, according to said output pressure measurements and said contextual and command data,

determining a set of estimators corresponding to said set of indicators of the first signs of a malfunction, using a previously produced regression model,

computing at least one distance between said set of indicators and said set of estimators, and

comparing said at least one distance to at least one threshold of the first signs of a malfunction, in order to detect the first signs of malfunction of the said valve.