Method for monitoring an aircraft engine operating in a given environment

Patent metadata

Field	Value
Publication number	US-10486833-B2
Application number	US-201515525574-A
Country	US
Kind code	B2
Filing date	Nov 10, 2015
Priority date	Nov 10, 2014
Publication date	Nov 26, 2019
Grant date	Nov 26, 2019

Abstract

The present invention relates to method for monitoring an engine (1) of an aircraft (2) operating in a given environment. The invention is characterized in that it comprises the implementation, via means for data processing (31), of the steps of: (a) receiving a sequence of n-tuples (x1-exec. . . xn-exec; yexec) of physical-parameter values relating to said aircraft (2) engine (1), including at least one endogenous parameter specific to the operation of the engine (1) and at least one exogenous parameter specific to said environment; (b) For each n-tuple (x1-exec. . . xn-exec, yexec) of the received sequence, calculating, according to a regression model, a standardized value (yexec-norm) of the endogenous parameter in relation to the exogenous parameters; (c) identifying at least one stabilized phase in said normalized sequence of n-tuples (x1-exec. . . xn-exec; yexec-norm) from a set of phase signatures; (d) for each stabilized phase, calculating the mean values of the physical parameters on the portion of the sequence of n-tuples (x1-exec. . . xn-exec; yexec) corresponding to the stabilized phase, in order to obtain an n-tuple (x1. . . xn; y) defining a recurrent point of said flight of the aircraft (2).

First claim

The invention claimed is:

1. A method for monitoring an aircraft ( 2 ) engine ( 1 ) operating in a given environment, characterized in that it comprises the application by data processing means ( 31 ) of steps for:
(a) Receiving a sequence of n-uplets (x 1_exec . . . x n_exec ; y exec ) of values of physical parameters relating to said aircraft ( 2 ) engine ( 1 ), at least one endogenous parameter specific to the operation of the engine ( 1 ) and at least one exogenous parameter specific to said environment of which, said values being measured over time by sensors ( 20 ) so that each n-uplet of the sequence defines a point of flight of said aircraft ( 2 ), a set of reference sequences of n-uplets (x 1i . . . x ni ; y i ) iϵ[[1,p]] of values of said physical parameters being stored in a database stored on data storage means ( 32 );
(b) For each n-uplet (x 1_exec . . . x n_exec ; y exec ) of the received sequence, calculation according to a regression model associated with a subset of said set of reference sequences of n-uplets (x 1i . . . x ni ; y i ) iϵ[[1,p]] , of a standardized value (y exec_norm ) of the endogenous parameter relatively to the exogenous parameters, so as to obtain a sequence of standardized n-uplets (x 1_exec . . . x n_exec ; y exec_norm );
(c) Identifying at least one stabilized phase in said standardized sequence of n-uplets (x 1_exec . . . x n_exec ; y exec_norm ) from a set of phase signatures stored in said database of the data storage means ( 32 ), each signature being defined by an n-uplet (x 1s . . . x ns ; y s ) of values of the physical parameters and an n-uplet (var s (x 1 ) . . . var s (x n ); var s (y)) of values of associated variance, a stabilized phase corresponding to a portion of said representative sequence of a flight time greater than a given threshold and wherein the values of the standard n-uplets (x 1_exec . . . x n_exec ; y exec_norm ) coincide with the values of the n-uplet (x 1s . . . x ns ; y s ) of a signature to within the associated variance, comparing the standardized sequence of n-uplets with a set of phase signatures to identify at least one stabilized phase of the flight;
(d) For each said stabilized phase, calculating average values of the physical parameters on the portion of the sequence of n-uplets (x 1_exec . . . x n_exec ; y exec_norm ) corresponding to the stabilized phase, so as to obtain an n-uplet ( x 1 . . . x n ; y ) defining a snapshot of said flight of the aircraft ( 2 ), and transmission to interface means ( 33 ).

2. The method according to one of claims 1 , wherein each endogenous parameter is selected from among a pressure at the outlet of a booster of the engine ( 1 ), a static pressure at the inlet of a combustion chamber of the engine ( 1 ), a temperature at the outlet of the booster of the engine ( 1 ), a temperature of the exhaust gases of the engine ( 1 ), a fuel mass flow rate at the inlet of a High-Pressure compressor of the engine ( 1 ), and high-pressure rotation conditions at the inlet of the High-Pressure compressor of the engine ( 1 ).

3. The method according to one of claims 1 , wherein each exogenous parameter is selected from an altitude, a temperature at the inlet of a fan of the engine ( 1 ), and low pressure rotation conditions at the inlet of the fan of the engine ( 1 ).

4. The method according to one of claims 1 , comprising the addition of the received sequence of n-uplets (x 1_exec . . . x n_exec ; y exec ) to the said set of reference sequences of n-uplets (x 1i . . . x ni ; y i ) iϵ[[1,p]] .

5. The method according to claim 1 , wherein the step (a) comprises the separation of the values (x 1_exec . . . x n_exec ) of the exogenous parameters and of the values (y exec ) of the endogenous parameters.

6. The method according to claim 1 , wherein step (b) comprises, for each n-uplet (x 1_exec . . . x n_exec ; y exec ) of the received sequence, a preliminary step (b0) for determining an exogenous class of the n-uplet according to the values (x 1_exec . . . x n_exec ) of the exogenous parameters of said n-uplet, from among a plurality of exogenous classes each defined by the values (x 1i . . . x ni ) iϵ[[1,p]] of the exogenous parameters of a sub-set of said reference sequence set of n-uplets (x 1i . . . x ni ; y i ) iϵ[[1,p]] .

7. The method according to claim 6 , wherein the step (b0) comprises the projection of said n-uplet in the classes of contexts so as to identify the closest exogenous class according to a distance criterion.

8. The method according to one of claims 6 , wherein the regression model used in step (b) for an n-uplet (x 1_exec . . . x n_exec ; y exec ) of the received sequence is the model associated with the exogenous class determined for said n-uplet (x 1_exec . . . x n_exec ; y exec ).

9. The method according to claim 8 , comprising a preliminary phase for processing said set of reference sequences of n-uplets (x 1i . . . x ni ; y i ) iϵ[[1,p]] of the database, comprising the application by data processing means ( 31 ) of steps for:
(a0) classification of the reference sequences of n-uplets (x 1i . . . x ni ; y i ) iϵ[[1,p]] so as to generate said plurality of exogenous classes;
(a1) for each exogenous class, determining said regression model associated with the sub-set of said reference sequence set of n-uplets (x 1i . . . x ni ; y i ) iϵ[[1,p]] by a regression modelling the value y of the endogenous parameter according to the values x 1 . . . x n of the exogenous parameters from the set of n-uplets of the exogenous class;
(a2) for each n-uplet (x 1i . . . x ni ; y i ) iϵ[[1,p]] of the set of reference sequence set, calculation for the exogenous class (j) of the n-uplet (x 1i . . . x ni ; y i ) iϵ[[1,p]] of an estimated value (ŷ i j ) of the endogenous parameter and of an associated residue (res i j );
(a3) For each n-uplet (x 1i . . . x ni ; y i ) iϵ[[1,p]] of the set of reference sequences, calculating the standardized value (y i_norm j ) of the endogenous parameter relatively to the exogenous parameters, so as to obtain a set of standardized reference sequences of n-uplets (x 1i . . . x ni ; y i_norm ) iϵ[[1,p]] ;
(a4) for each reference sequence of standardized n-uplets (x 1i . . . x ni ; y i_norm ) iϵ[[1,p]] , identifying at least one stabilized phase in said standardized reference sequence of n-uplets (x 1i . . . x ni ; y i_norm ) iϵ[[1,p]] , a stabilized phase corresponding to a portion of said representative sequence of a flight time greater than a given threshold and wherein the values of the standardized n-uplets (x 1i . . . x ni ; y i_norm ) iϵ[[1,p]] are constant to within a given variance;
(a5) for each stabilized phase of each reference sequence, calculating average values of the physical parameters on the portion of the sequence of n-uplets (x 1i . . . x ni ; y i_norm ) iϵ[[1,p]] corresponding to the stabilized phase, so as to obtain an n-uplet ( x 1 . . . x n ; y ) defining a potential snapshot of a flight of the aircraft ( 2 );
(a6) classifying the n-uplets ( x 1 . . . x n ; y ) defining a potential snapshot obtained so as to generate a plurality of cells, each associated with a subset of the n-uplets ( x 1 . . . x n ; y ) defining a potential snapshot;
(a7) for at least one generated cell, calculating an n-uplet (x 1s . . . x ns ; y s ) of values of the physical parameters and an n-uplet (var s (x 1 ) . . . var s (x n ); var s (y)) of values of associated variance so as to define a signature of a phase associated with the cell, and storage of the phase signatures in said database of the data storage means ( 32 ).

10. The method according to claim 9 , wherein the classification of the steps (a0) and (a6) is applied according to a non-

Assignees

• Safran Aircraft Engines

Inventors

• Gouby Aurelie
• Bothier Guillaume

Classifications

• G07C5/0841

  Registering performance data (recording measured values G01D; information storage G11B) · CPC title

• B64F5/00

  Designing, manufacturing, assembling, cleaning, maintaining or repairing aircraft, not otherwise provided for; Handling, transporting, testing or inspecting aircraft components, not otherwise provided for · CPC title

• B64F5/60 Primary

  Testing or inspecting aircraft components or systems · CPC title

• G06F17/18

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title

• B64D2045/0085

  Devices for aircraft health monitoring, e.g. monitoring flutter or vibration · CPC title