Method for monitoring the health status of aircraft turbomachinery
The method uses a training database with transient and stabilized data to construct prediction models, addressing the challenge of calculating margins in aircraft turbomachines, especially helicopters, by enabling comprehensive health monitoring and steady-state behavior estimation.
Patent Information
- Authority / Receiving Office
- FR · FR
- Patent Type
- Patents
- Current Assignee / Owner
- SAFRAN SA
- Filing Date
- 2022-03-28
- Publication Date
- 2026-05-08
AI Technical Summary
Existing health monitoring methods for aircraft turbomachines, particularly helicopters, struggle with calculating margins due to the lack of steady-state data during operations like surveillance or slinging, and current solutions are limited to independent transformations of two parameters at a time, constraining relevant margin calculations.
A method involving a training database with transient and stabilized data from multiple flights to construct prediction models, allowing estimation of turbomachine behavior in steady-state conditions, enabling margin calculations at various points and comprehensive monitoring.
Enables efficient estimation of turbomachine behavior in steady-state conditions from transient data, facilitating margin calculations and comprehensive health monitoring for any flight scenario, overcoming limitations of previous methods.
Smart Images
Figure 00000022_0000 
Figure 00000022_0001
Abstract
Description
Title of the invention: Method for monitoring the health status of an aircraft turbomachine TECHNICAL FIELD OF THE INVENTION
[0001] The technical field of the invention is that of monitoring the condition of aircraft turbomachines.
[0002] The present invention relates to a method for monitoring the health status of an aircraft turbomachine. TECHNOLOGICAL BACKGROUND OF THE INVENTION
[0003] The "Health monitoring" of an aircraft turbomachine, for example an airplane or a helicopter, makes it possible to monitor the condition of the turbomachine throughout its life and to anticipate a defect of the turbomachine from data recorded during flights carried out by the aircraft including the turbomachine.
[0004] A classic indicator of health monitoring is the calculation of margins that allow comparison, for a desired value of at least one input parameter relating to the turbomachine, of a modeled theoretical value of at least one output parameter relating to the turbomachine with an actual value of said output parameter. For example, to obtain a desired power P emitted by the turbomachine, a physically modeled temperature To in the turbomachine's combustion chamber is theoretically required. The temperature To is compared to an actual temperature Ti in the turbomachine's combustion chamber required to obtain the power P emitted by the turbomachine.The actual temperature Ti increases throughout the turbomachine's lifecycle, and the difference between the theoretical value To and the actual value Ti is a margin studied and analyzed using physical models. This allows for the anticipation of potential failures and overheating of the turbomachine. The margin calculation can be performed for several input parameter values (for example, the rotational speed of one turbomachine shaft and the rotational speed of a second turbomachine shaft) and several output parameter values (for example, the power output of the turbomachine and the aforementioned turbomachine temperature).
[0005] Physical models allow the study of margins using turbomachine parameter data recorded during a stabilized turbomachine regime. However, a helicopter, for example, performing surveillance or slinging operations, may rarely or never operate in a stabilized regime during a particular flight, making margin calculations complex or even impossible.
[0006] In order to overcome the lack of data in steady state of a helicopter turbomachine, there are state-of-the-art solutions for monitoring the condition of the engine from indicators other than margins.
[0007] An alternative to the solution proposed above, also known in the prior art, relies on estimating, from transient input parameter values of the turbomachine during a given flight, steady-state output parameter values of the turbomachine. This solution allows for the independent transformation of two turbomachine parameters to obtain steady-state output parameter values for given input parameters. However, the proposed solution only works for two input parameters at a time, and each parameter is transformed independently of the other to obtain a steady-state output parameter. Furthermore, the margin can therefore only be calculated on the transformed parameters, and not for any value of the input parameters, which further limits a relevant margin calculation.
[0008] There is therefore a need to estimate the behavior of the turbomachine in steady state, from one or more input parameters relating to the turbomachine in transient state, without considering the input and output parameters independently of each other. Summary of the invention
[0009] The invention offers a solution to the problems mentioned above, by allowing more efficient estimation of the steady-state behavior of a turbomachine for a particular flight.
[0010] One aspect of the invention relates to a method for monitoring the health status of an aircraft turbomachine of interest for a flight of interest VI of the aircraft, from a setpoint matrix XSc comprising at least one value of at least one input parameter relating to the turbomachine of interest TMI, the method comprising the following steps: • Construction of a training database including: • a so-called transient set T comprising transient learning data recorded during at least one instant of flight of at least one flight V of at least one turbomachine TM operating in transient regime and of the flight of interest of the turbomachine of interest TMI; • a so-called stabilized set S comprising stabilized learning data recorded during at least one instant of flight of each flight V, with the exception of the flight of interest VI, of each turbomachine TM operating in stabilized regime; • Estimation of a transient prediction model f on the transient training data of the transient set T; the • Estimation of a stabilized prediction model H from the transient prediction model f and the stabilized training data included in the stabilized set S • Estimation of a matrix YSi representing the behavior of the turbomachine of interest TMI in stabilized regime for the flight of interest VI from the stabilized prediction model H, at least a part of the transient prediction model f and the setpoint matrix Xsc-
[0011] The model f may consist of one or more sub-models, specific or not to specific datasets.
[0012] By "input parameter relating to a turbomachine" is meant a parameter relating to the turbomachine for which a setpoint value is desired.
[0013] By "behavior of a turbomachine in stabilized regime for a flight V" we mean the estimation of at least one output parameter relating to the turbomachine, an output parameter being a consequence of one or more input parameters of the turbomachine and of the state of the turbomachine.
[0014] Thanks to the invention, the steady-state behavior of a turbomachine of interest, for any flight of interest, can be estimated from transient and stabilized data relating to at least one turbomachine in transient and stabilized regime for a plurality of flights, thanks to the stabilized prediction model H. Thus, unlike the prior art, the invention not only allows the prediction of output data relating to the turbomachine in steady state but a model allowing the prediction of output data from any setpoint, the estimation of the model H therefore making it possible to calculate margins at different points rather than being constrained to a transformation of the transient variables and thus to monitor the state of the turbomachine for any flight of interest.
[0015] Advantageously, the invention makes it possible to take into account all the data relating to the turbomachine at once rather than in pairs.
[0016] Advantageously, the invention allows the construction of a stabilized HVi prediction model which makes it possible to calculate margins at different points rather than being constrained to a transformation of the transient variables.
[0017] Advantageously, the training data can be taken without direct relation to the flight of interest.
[0018] In addition to the characteristics mentioned in the preceding paragraph, the method according to one aspect of the invention may have one or more additional characteristics from among the following, considered individually or in all technically possible combinations: The transient learning data for the set T are constructed, for each flight V of each turbomachine TM, from a torque (Y mh ^VT, ^VT / • the matrix comprising at least one row and at least one column, each row corresponding to an input parameter of the turbomachine TM in transient regime, each input parameter of each row being different from the other input parameters of the other rows, each column corresponding to a recording instant of flight V, each recording instant of each column being different from the other recording instants of the other columns, • the matrix comprising at least one row and at least one column, each row corresponding to an output parameter of the turbomachine TM in transient regime, each output parameter of each row being different from the other input parameters of the other rows, each column corresponding to a recording instant of flight V, each recording instant of each column being different from the other recording instants of the other rows, The stabilized learning data for the set S are constructed, for each flight V of each turbomachine TM, with the exception of the flight of interest, from the torque (Y w V • the matrix ^vs. comprising at least one row and at least one column, each row corresponding to an input parameter of the turbomachine TM in transient regime, each input parameter of each row being different from the other input parameters of the other rows, each column corresponding to a recording instant of flight V, each recording instant of each column being different from the other recording instants of the other columns, • the matrix comprising at least one row and at least one column, each row corresponding to an output parameter of the turbomachine TM in transient regime, each output parameter of each row being different from the other input parameters of the other rows, each column corresponding to a recording instant of flight V, each recording instant of each column being different from the other recording instants of the other columns. • The turbomachine TM is the turbomachine of interest. Thus, among the pairs of matrices (y ... \ of the transient set T, at least one of these pairs ^VT / represents a flight of the turbomachine of interest. This feature allows the inclusion of data relating to the turbomachine of interest for at least one flight, enabling the estimation of the prediction model f, the model f allowing the determination of the behavior for a flight from data retrieved on the turbomachine of interest. • A flight V of assembly T is the flight of interest. The turbomachine of interest and assembly T are further constructed from the couple (yw). This ca-\ZVZr vVJT characteristic of including parameters relating to the turbomachine of interest for the flight of interest, allowing estimation of the prediction model f, allowing representation of the turbomachine of interest for the flight of interest. • for each flight V of each turbomachine TM of assembly T: • The transient learning data of set T include the pair J: • The transient prediction model f is formed of at least one sub-model fv, such that = Wr- • According to an embodiment complementary to the first embodiment, the stabilized prediction model H is defined such that, for each flight V of each turbomachine TM of the assembly T, H(fv(v \ v \ — in Avsr Avs) ^vs • In one embodiment, the transient training data for set T includes: • A matrix XT resulting from a horizontal concatenation of each matrix ^vt, • A YT matrix resulting from the horizontal concatenation of each matrix • The stabilized training data for set S includes: • A matrix resulting from a horizontal concatenation of each matrix • A matrix Ys resulting from the horizontal concatenation of each matrix And the transient prediction model f is defined such that f(Xr) = YT. • According to an embodiment complementary to the previous embodiment, the stabilized prediction model H is defined such that H(f( XsK Xs) = Ys. • at least one input parameter relating to a turbomachine is a parameter of turbomachine operation among the following: • Rotation speed of the first shaft of the turbomachine; • Rotation speed of a second shaft of the turbomachine; • Temperature of a turbomachine combustion chamber; • Torque delivered by the turbomachine; • Any other relevant thermodynamic parameter or a parameter specific to the given environment in which the turbomachine is located, from among the following: • Temperature of the given environment; • Pressure from the given environment. • Pumping power • Any other parameter influencing the thermodynamic behavior of the turbomachine (e.g., valve); • at least one output parameter relating to a turbomachine is one of the following operating parameters of the turbomachine: • Rotation speed of the first shaft of the turbomachine; • Rotation speed of a second shaft of the turbomachine; • Temperature of a turbomachine combustion chamber; • Torque delivered by the turbomachine; • Any other relevant thermodynamic parameter or a parameter specific to the given environment in which the turbomachine is located, from among the following: • Temperature of the given environment; • Pressure from the given environment. • Pumping power • Any other parameter influencing the thermodynamic behavior of the turbomachine (e.g., valve) • The prediction model f and the prediction model H are chosen from among the classical regression methods, for example, but not limited to, a neural network, a decision tree, a random forest, a large margin separator or polynomial, random, large margin separator or linear regression.
[0019] Another aspect of the invention relates to a computer program product comprising instructions which, when the program is executed by a computer, lead the computer to implement the process according to the invention.
[0020] Another aspect of the invention relates to a computer-readable recording medium comprising instructions which, when executed by a computer, cause the computer to implement the process according to the invention.
[0021] The invention and its various applications will be better understood upon reading the following description and examining the accompanying figures. BRIEF DESCRIPTION OF THE FIGURES
[0022] The figures are presented for illustrative purposes only and are in no way limiting of the invention. • Fig. 1 shows a schematic representation of a synoptic diagram of the process according to the invention; • Fig. 2 is an example of data retrieved during the following flights: (Flight 0, Flight 1, Flight 2, Flight VI) of the turbomachine of interest. DETAILED DESCRIPTION
[0023] The figures are presented for illustrative purposes only and are not in any way limiting to the invention.
[0024] A first aspect of the invention relates to a method for monitoring the health status of an aircraft turbomachine of interest TMI for a flight of interest VI, from a setpoint matrix Xsc comprising at least one input parameter relating to the turbomachine of interest TMI in stabilized regime.
[0025] The aircraft is, for example, an airplane or a helicopter.
[0026] The term "turbomachine" means a system employing a gas turbine, in which energy is transferred between a rotating part and a gas.
[0027] The following characteristics are valid for any type of turbomachine within the scope of the invention, including the turbomachine of interest.
[0028] A turbomachine can include a combustion chamber, a first shaft, a second shaft.
[0029] The term "shaft" means a mechanical element that transmits power in the form of torque and rotational motion.
[0030] A turbomachine is for example a turbojet, a turboprop or preferably a turbomotor.
[0031] By "input parameter relating to a turbomachine" is meant a parameter relating to the turbomachine for which a setpoint value is desired.
[0032] An input parameter relating to the turbomachine may be one of the following operating parameters of the turbomachine: rotational speed of the first shaft of the turbomachine; rotational speed of the second shaft of the turbomachine; temperature of the combustion chamber of the turbomachine of interest; and torque delivered by the turbomachine, power delivered by the turbomachine. The input parameter relating to the turbomachine may also be a parameter specific to the external environment in which the aircraft comprising the turbomachine is located during a given flight, such as: temperature of the external environment; pressure of the external environment. An input parameter relating to the turbomachine may also be any relevant thermodynamic or environmental parameter. relevant
[0033] For example, two input parameters can be chosen from the parameters relating to the turbomachine previously: a setpoint value for the power delivered by the turbomachine and a setpoint value for the rotational speed of the first shaft of the turbomachine can be chosen or required.
[0034] An output parameter of the turbomachine is a parameter that is a consequence of one or more input parameters of the turbomachine and the state of the turbomachine.
[0035] At least one output parameter relating to the turbomachine of interest may be one of the following operating parameters of the turbomachine: the rotational speed of the first shaft of the turbomachine; the rotational speed of the second shaft of the turbomachine; the temperature of the combustion chamber of the turbomachine, torque delivered by the turbomachine and power delivered by the turbomachine.
[0036] For example, if the input parameters are: the rotational speed of the first shaft of the turbomachine, the rotational speed of the second shaft of the turbomachine, the temperature of the given external environment; the pressure of the given external environment, the output parameters relating to the turbomachine can be the temperature of the combustion chamber of the turbomachine, and the torque delivered by the turbomachine.
[0037] In the following text, the phrase "turbomachine-related parameters" includes the turbomachine-related input parameter(s) and the turbomachine-related output parameters.
[0038] By "steady state of a turbomachine" is meant a state during which the input and output parameters relating to the turbomachine do not change or change very little over time. A steady state can be called permanent or stationary state.
[0039] A steady-state regime of a turbomachine is opposed to a transient regime of a turbomachine, during which input parameters and output parameters relating to the turbomachine evolve over time.
[0040] The setpoint matrix Xsc is a matrix comprising at least one value for at least one input parameter relating to the turbomachine of interest in steady state, each value being able to be randomly generated or chosen. The matrix Xsc may have a number of rows greater than or equal to 1 and a number of columns greater than or equal to 1. The coefficients of the matrix Xsc are denoted (xscj)i>oj j>0.
[0041] The [Fig. 1] [Fig. 1] is a synoptic diagram of the process 100 according to the invention.
[0042] The method 100 may include a first step 101 of constructing a training database.
[0043] Construction step 101 may include a first substep 1011 of recovery data operation D, for at least one turbomachine TM, the data D being recorded during one or more moments of flight recordings during at least one flight V of said turbomachine TM.
[0044] According to one embodiment, the turbomachine TM is the turbomachine of interest TMI.
[0045] According to one embodiment, the data D comprises recorded data during one or more moments of flight of a plurality of flights (Vo, ... VN)N>0 of the same turbomachine.
[0046] According to one embodiment, the data D comprises data recorded for a plurality of turbomachines (TM0, ..., TMk)k>i during one or more flight recording moments of a plurality of flights (V0-Tmk-..., VN_TM0, V0-Tmk-..., VN_TMK)p>i of a plurality of turbomachines. For each turbomachine in the plurality of turbomachines, the number of flight moments for each flight in the plurality of flights may be different or the same from one flight to another and / or from one turbomachine to another.
[0047] According to an embodiment in which the turbomachine TM is the turbomachine of interest TMI, the flight V carried out by the turbomachine of interest is carried out prior to the flight of interest VI.
[0048] The recovered data D includes, for each turbomachine TM and for each flight V of the turbomachine TM, transient data recorded during the transient regime of the turbomachine TM during at least one instant of flight of each flight V of the turbomachine TM, flight V being the flight of interest VI, and includes stabilized data recorded during the stabilized regime of the turbomachine TM during at least one instant of flight of each flight V, with the exception of the flight of interest VI, of the turbomachine TM.
[0049] According to one embodiment, for each turbomachine TM and for each given flight V of the turbomachine TM, the transient data comprise a pair of matrices (v, ,, 'i "VT /
[0050] According to the preceding embodiment, each matrix XyT comprises at least one row and at least one column, each row corresponding to an input parameter of the turbomachine TM, each input parameter of each row being different from the other input parameters of the other rows, and each column corresponding to a recording instant of flight V during a transient phase, each recording instant of each column being different from the other recording instants of the other columns.
[0051] Let xTv_ij be a coefficient of the matrix A / / ” xTVjj, being equal to the value of the input parameter i for the recording time j during so-called transient phases of the given flight V. The coefficients i and j are respectively natural numbers greater than or equal to 0. The index V represents the given flight V and the index T represents the regime transitory.
[0052]
[0053]
[0054]
[0055]
[0056] For example, for a V flight of a TM turbomachine in transient regime, for which the values of p input parameters relating to the turbomachine TM are measured, p being an integer greater than 0, the values being measured for 1 flight time recordings, 1 being greater than 0, the XVT matrix is as follows: x V_00 rT 1 x V_0l ^VT XTv_pO According to the previous embodiment, each matrix ^yt comprises at least one row and at least one column, each row corresponding to the different parameters output of the TM turbomachine in transient regime, each column corresponding to the different times of recording of flight v during a transient phase. Let yTv_ij be a coefficient of the matrix yTv ij the value of the output parameter i for the recording time j during so-called transient phases of the given flight V. The coefficients i and j are respectively natural numbers greater than or equal to 0. The index V represents the given flight V and the index T represents the transient regime. For example, for a flight V of a turbomachine TM in steady state, for which the values of q input parameters relating to the turbomachine TM are measured, q being an integer greater than 0, the values being measured for 1 flight time records, 1 being greater than 0, the WVT matrix is as follows: yT X v_po Wvs VT yv„f / o yT ■y v_oi VT } V_ql
[0057]
[0058]
[0059]
[0060] For each flight V of the turbomachine TM, the flight recording times of XVT correspond to the recording times of ^vt- According to one embodiment, the transient data include, for each flight V of each turbomachine TM, the matrices vp^ and vr / being the transpose of the matrix XVTet (^vtY being the transpose of the matrix V\t- According to an embodiment complementary to the previous embodiment, for each turbomachine TM and for each given flight V of the turbomachine TM, with the exception of the flight of interest VI of the turbomachine of interest, the stabilized data includes a pair of matrices (v 3 ^VSJ' Each Xys matrix comprises at least one row and at least one column, each row corresponding to an input parameter of the TM turbomachine, each input parameter of each row being different from the other input parameters of the other rows, and each column corresponding to a time point in the V-phase flight recording stabilized, each recording moment of each column being different from the other recording moments of the other columns.
[0061] Let xsv ij be a coefficient of the matrix xsVJj being equal to the value of the input parameter i for the recording time j during so-called stabilized phases of the given flight V. The coefficients i and j are respectively natural numbers greater than or equal to 0. The index V represents the given flight V and the index T represents the transient regime.
[0062] For example, for a flight V of a turbomachine TM in steady state, for which the values of p input parameters relating to the turbomachine TM are measured, p being an integer greater than 0, the values being measured for r flight time records, r being greater than 0, the matrix Xvs is as follows:
[0063] ' ' ' Xvs~ : '■ ' ^V_pr_
[0064] Each Wys matrix, each comprising at least one column and at least one row, each row corresponding to the different output parameters of the TM turbomachine in transient regime, each column corresponding to the different times of recording of flight v.
[0065] Let ysv_ij be a coefficient of the matrix ysv_ij, the value of the output parameter i for the recording time j during so-called transient phases of the given flight V. The coefficients i and j are respectively natural numbers greater than or equal to 0. The index V represents the given flight V and the index T represents the transient regime.
[0066] For example, for a flight V of a turbomachine TM in steady state, for which the values of q input parameters relating to the turbomachine TM are measured, q being an integer greater than 0, the values being measured for r flight time records, r being greater than 0, the matrix V'vs is as follows: ' ■ ■ ■ yS' ; V_00 ; V„0r = J ■■■ J Ajr,
[0067] For each flight V of each turbomachine TM, the flight recording times of ^ys correspond to the recording times of Wys.
[0068] According to the embodiment in which the data D comprise transient data recorded for the turbomachine of interest TM! during at least one flight instant of the flight of interest V, said transient data comprise matrices ^vnet w VIT-
[0069] According to an embodiment complementary to the previous embodiment, for each turbomachine TM, and for each given flight V of the turbomachine TM, the distance between matrices XyjTet ^vrest less than an SI threshold.
[0070] According to an embodiment compatible (but not exclusive) with the preceding embodiment, the distance between the matrices ^vuet V'VT is less than a threshold S2.
[0071] The distance between the matrices can be any relevant distance, for example a Manhattan distance, a Euclidean distance, a Minkowski distance or a Chebyshev distance.
[0072] Fig. 2 is an example of data recovered during the following flights: (Flight 0, Flight 1, Flight 2, Flight VI) of the turbomachine of interest.
[0073] The first step 101 of the method according to the invention includes a second substep 1012 of distributing the data D into two sets: a so-called transient set T and a so-called stabilized set S. The transient data, for each turbomachine TM and for each flight V of the turbomachine TM, are used to construct transient learning data included in set T, and the stabilized data for each turbomachine TM and for each flight V of the turbomachine TM are used to construct stabilized learning data, are distributed in set S.
[0074] According to one embodiment, the transient learning data of the set T are constructed, for each flight V of each turbomachine TM, the flight V being the flight of interest VI, from the couple (XVT^
[0075] According to the preceding embodiment, the transient learning data of the set S are constructed, for each flight V of each turbomachine TM, with the exception of the flight of interest VI, from the torque
[0076] According to a first sub-embody complementary to the previous embodiment, the transient learning data of the set T include, for each turbomachine TM, and for each flight V, the pair of matrices (XvT,ipv_^, flight V being able to be the flight of interest VI.
[0077] According to the first sub-emphasis, the stabilized learning data of the set S includes, for each turbomachine TM, and for each flight V, with the exception of the flight of interest VI of the turbomachine of interest, the pair of matrices (Xv$,
[0078] For example, if the recorded data D includes flight data (VI,V2) of a turbomachine TM, the set T may comprise the following matrix pairs: (-^vit, V'vit) , (^V2T, ^V2t) and the set S may comprise the following matrix pairs: (Ans, ^vis), (^V2S, Vv2s) ■
[0079] For example, if the recorded data D includes data recorded during the flights (VI, V2, VI) of the turbomachine of interest TMI, the set T may include the following matrix pairs: (^vit, ^vu), (^V2T, ^V2t) and ^vit^'vit ) and The set S can include the following matrix pairs: (1^vis-^Vis), (^V2S, ^V2S) ■
[0080] According to a second sub-mode complementary to the previous embodiment, the transient learning data of the set T comprise a pair of matrices (XT, YT) constructed from each pair (Xvt^vt) for each flight V of each turbomachine TM.
[0081] According to the second sub-emphasis, the stabilized learning data of the set S comprise a pair of matrices (Xs, Kç) constructed from each pair (Xvs^vs) for each flight V of each turbomachine TM, with the exception of the flight of interest VI.
[0082] According to the second sub-emphasis, the matrix XT results from the horizontal concatenation of each matrix vt- Thus, when the data D includes transient data recorded for at least one recording of a flight instant of a plurality of flights (Vo,.. .,Vk)k>0, the matrix XT is of the following form:
[0083] X7=[Zor XkT]
[0084] In order to simplify the notations, each flight Vk has been denoted k in the matrix XT.
[0085] According to the second preceding sub-embody, the matrix YT results from the horizontal concatenation of each matrix ^vt-
[0086] Thus, when the data D includes transient data recorded for at least one flight instant recording of a plurality of flights (Vo,...,Vk)k>0, the matrix YT is of the following form:
[0087]
[0088] In order to simplify the notations, each flight Vk has been denoted k in the matrix k?.
[0089] Each column of XT and YT represents the same flight V.
[0090] According to the second sub-emphasis, the matrix Xs results from the horizontal concatenation of each matrix Xvs. Thus, when the data D includes transient data recorded for at least one flight instant of a plurality of flights (Vo,...,Vn)n>o, the matrix Xs is of the following form:
[0091] ••• Zy5]
[0092] To simplify the notation, each flight VN has been denoted N in the matrix Xs,
[0093] According to the second sub-emphasis, the matrix Ys results from the conca horizontal tenation of each matrix ^ys
[0094] Thus, when the data D includes transient data recorded for at least one flight instant recording from a plurality of flights (Vo,...,VN)N>0, the matrix Ys is of the following form:
[0095] / , = (¾
[0096] To simplify the notation, each flight VNa was denoted N in the matrix
[0097] Each row of the matrices of XT and Xs represents the same input parameter relating to a turbomachine TM, and each row of the matrices YT and Ys represents the same output parameter relating to the turbomachine TM.
[0098] The method further includes a second estimation step 102 of a transient prediction model f on the training data of the transient set T.
[0099] According to a first embodiment, in which the transient learning data of the set T comprise, for each flight V of each turbomachine TM, a pair of matrices, the transient prediction model is formed, from less a transient prediction submodel fv such that fv(%vz)= ^vt and estimation step 102 is performed by estimating each model fv
[0100] Thus, when the transient learning data of set T comprise a plurality of matrix pairs ( •••• ^>o for flights (Vo, ... VK)k>o of at least one turbomachine TM, the transient prediction model f can be formed from the sub-models (fv0,.. .fvK)k>0.
[0101] In particular, according to an embodiment in which the set T comprises the pair (^viT,ipVIT^ The transient prediction model f is formed of at least the transient prediction sub-model fvl> for the flight of interest VI.
[0102] According to a first sub-embody of the first embodiment, each transient prediction sub-model fv for each flight V of the transient set T is estimated independently of the other transient prediction sub-models. In particular, when the set T comprises the pair of matrices (vv, w) corresponding to the flight of interest Vv, the turbomachine of interest TMb, and the transient prediction model f is formed from at least the sub-model fvL
[0103] According to the first embodiment, each transient prediction model fv can be a model chosen from all classical regression models, for example a neural network, a regression tree, a random forest, a wide-margin separator or linear regression.
[0104] According to a second sub-emphasis of the first embodiment, each transient prediction sub-model fv for each flight V of the transient set T is estimated depending on the other transient prediction sub-models by means of a multi-task learning method.
[0105] Multitask learning is a subfield of machine learning that allows for the simultaneous resolution of several different tasks while taking into account the dependencies between the tasks. A multitask learning model includes a part common to each task and a part specific to each task. Multitask learning makes it possible to improve the learning of a particular model by using the features included in all the tasks. Thus, according to the second embodiment, for each flight V of each turbomachine TM, each prediction sub-model fv is equal to $ o Fv the function $ being common to each model fvet the function Fv being specific to each sub-model fv.
[0106] The multitask learning model can be a model chosen from a neural network, a regression tree, a random forest, a wide-margin separator or linear regression.
[0107] For example, Each prediction submodel fv can be associated with a set of training parameters, part of which is common to all other prediction submodels, and part specific to said model.
[0108] According to the first embodiment, the estimation of each transient prediction model fv is carried out by minimizing a cost function corresponding to the error between the output data fv vt) provided by the transient prediction model f and the true output data Vy / desiredc.
[0109] According to the first embodiment, for each flight V, the cost function is, for example, the root mean square deviation between fv(^vr) and ^vr. As a reminder, the coefficients of the matrix ^yy are denoted (xTv_ij)iojj>o and the coefficients of the matrix ^vr are denoted (yT vjj)i>o,j>o. We will denote (f(xTv_ij))i>o,j>o the coefficients of the matrix ïv0vt). Thus, the cost function can be equal to: VV / f / YT
[0110] The minimization of the cost function can be achieved using the gradient descent algorithm or the least squares algorithm or any state-of-the-art method for optimizing the estimation of each sub-model fv.
[0111] According to a second embodiment, in which the set T comprises the matrix XT and the matrix Y, the estimation step 102 of the transient prediction model f models the relationship between the matrix XT and the matrix LT such that f(Xy) = YT, f is said to be the global transient prediction model in this embodiment.
[0112] According to the second embodiment, the transient prediction model f can be a model chosen from all classical regression models, for example a neural network, a regression tree, a random forest, a wide-margin separator or linear regression.
[0113] According to the second embodiment, the estimation of the transient prediction model f is carried out by minimizing a cost function corresponding to the error between the output data f(Xr) provided by the transient prediction model f and the true output data Y ^desired.
[0114] According to the second embodiment, the cost function is, for example, the mean squared deviation between f(X? ) and YT. As a reminder, the matrix XT can be equal to the columns (zvr)v>i. We will denote (f(xTv_ij))i>o,j>ov>oles the coefficients of the matrix f(Xr).
[0115] Thus, the transient prediction model f can be defined such that, for each flight V of each turbomachine TM, f is formed of at least one sub-model fv defined such that fv vt) vt or can be defined such that f(X^) = YT.
[0116] The method 100 further includes an estimation step 103 of a stabilized prediction model H, as a function of the transient model f and the set S.
[0117] According to a first embodiment in which the transient model f is formed of at least one transient sub-model fv for each flight V of the transient set T, the stabilized prediction model H is defined, for each flight V of the set S, represented by the pair of matrices ^vs), such that H(fv(y Y y |= ^vs-^vsr Avs)
[0118] According to the first embodiment, the estimation step 103 of the stabilized prediction model H is carried out by minimizing a cost function, the cost function being, for example, equal to: v V / uf rfs \ s \ \ 2. The index V re-JLy JLj JL y.. - H [ ty ( Xvjj ), x v_;. j J presents each flight of the set S, the index i represents a flight instant of the flight V and the index j represents an input parameter of a turbomachine TM for a coefficient Xy and j represents an output parameter of the same turbomachine TM for a coefficient y^, .
[0119] The minimization of the cost function can be achieved using the gradient descent algorithm or the least squares algorithm or any state-of-the-art optimization method.
[0120] According to a second embodiment, in which the transient set T comprises the matrices XT and YT and the stabilized set S comprises the matrices %s and %s, and in which the transient prediction model f is defined such that Δε(X) = YT, the stabilized prediction model H is defined such that Ys = H(f(X)
[0121] According to the second embodiment, the estimation of the stabilized prediction model H is performed by minimizing a cost function, the cost function being, for example, equal to: ys ) S )) 2 The index V represents each In the flight of the assembly S, the index i represents a flight time of flight V, and the index j represents an input parameter of a turbomachine TM for a coefficient xy, and j re-“ij presents an output parameter of the same turbomachine TM for a coefficient yS. The minimization of the cost function can be achieved using the gradient descent algorithm, the least squares algorithm, or any state-of-the-art optimization method.
[0122] The prediction model H may be a model chosen from among a neural network, a regression tree, a random forest, a wide-margin separator or linear regression, but not exclusively.
[0123] The method 100 further includes an estimation step 104 of a matrix YSI of output parameter values relating to the turbomachine of interest for at least one instant of flight of the flight of interest as a function of the model H associated with the vector to the matrix Xscet at least a part of the transient model f.
[0124] According to a first embodiment, in which the transient model f is formed of at least one sub-model fv for each flight V of the set T, and in particular of the sub-model fVb the part of the transient model f is the sub-model fVb and the matrix Y S1 is estimated as a function of the model H associated with the matrix fVi(Xsc) and the matrix Xsc such that YS1 = H( fVi(Xsc), Xsc).
[0125] According to a second embodiment, in which the transient model f is the global transient prediction model such that f(X7) — YT, and in particular the sub-model fVb the part of the transient model f the global transient prediction model f, and the matrix YSiest estimated as a function of the model H associated with the matrix f(XSc) and the matrix Xsc such that YS1 = H( f(Xsc), Xsc).
[0126] The YSi matrix corresponds to the steady-state behavior of the turbomachine of interest for the flight of interest.
[0127] The method 100 may further include a margin calculation step 105, the margin being proportional to the difference between the matrix of interest YSi and a matrix Ymp, the matrix Ymp being the output of a physical model representing the worst case for the input Xsc. Thus, according to one embodiment, the margin calculation is performed such that: margin = YSI - Ymp.
[0128] The health status of the turbomachine of interest TMI is monitored by means of margin calculation.
Claims
Demands
1. A computer-implemented method (100) for monitoring the health status of an aircraft turbomachine of interest for an aircraft flight of interest VI, based on a setpoint matrix XSc comprising at least one value of at least one input parameter relating to the turbomachine of interest, the method comprising the following steps: - Construction (101) of a training database comprising: • a so-called transient set T comprising transient learning data recorded during at least one flight recording instant of at least one flight V of at least one turbomachine TM operating in transient regime and of the flight of interest of the turbomachine of interest TMI • a so-called stabilized set S comprising stabilized learning data recorded at each instant of flight recording of each flight V, with the exception of the flight of interest VI, of each turbomachine TM operating in stabilized regime; - Estimation (102) of a transient prediction model f on the transient training data of the transient set T; - Estimation (103) of a stabilized prediction model H from the transient prediction model f and the stabilized learning data included in the stabilized set S; - Estimation (104) of a matrix of interest YSi representing the behavior of the turbomachine of interest TMI in stabilized regime for the flight of interest Vlà from the stabilized prediction model H, at least a part of the transient prediction model f and the setpoint matrix XSc. - Monitoring the health status of the turbomachine of interest based on margin calculations dependent on the matrix of interest Y if*
2. A method according to the preceding claim wherein the TM turbomachine is the turbomachine of interest.
3. A method according to any one of the preceding claims, wherein: - The transient learning data for the set T are constructed, for each flight V of each turbomachine TM, from a torque (Y w ^vt, • the matrix ^vt, comprising at least one row and at least one column, each row corresponding to an input parameter of the turbomachine TM in transient regime, each input parameter of each row being different from the other input parameters of the other rows, each column corresponding to a recording instant of flight V, each recording instant of each column being different from the other recording instants of the other columns, • the matrix Wr; comprising at least one row and at least one column, each row corresponding to an output parameter of the turbomachine TM in transient regime, each output parameter of each row being different from the other input parameters of the other rows, each column corresponding to a recording instant of flight V, each recording instant of each column being different from the other recording instants of the other rows, - the stabilized training data of the set S are constructed, for each flight V of each turbomachine TM, with the exception of the flight of interest, from the torque (YV ^vs, ^vs} • the matrix Xvs, comprising at least one row and at least one column, each row corresponding to an input parameter of the turbomachine TM in transient regime, each input parameter of each row being different from the other input parameters of the other rows, each column corresponding to a recording instant of flight V, each recording instant of each column being different from the other recording instants of the other columns, • the matrix comprising at least one row and at least one column, each row corresponding to an output parameter of the turbomachine TM in transient regime, each output parameter of each row being different from the other input parameters of the other rows, each column corresponding to a recording instant of flight V, each recording instant of each column being different from the other recording instants of the other columns.
4. A method according to claims 2 and 3 wherein a flight V of the assembly T is the flight of interest VI and the assembly T is further constructed from the pair U, w ) v^vir *vit
5. A method according to claim 3 wherein, for each flight V of each turbomachine TM of assembly T: - the transient learning data of assembly T include the torque q, j; - the transient prediction model f is formed of at least one sub-model fv, such that fv(^vr) =
6. . Method according to claim 5 wherein the stabilized prediction model H is defined such that, for each flight V of each turbomachine TM of the assembly S, H(fv(v 1 v ï _ in *vsr *vs)
7. Method according to claim 3: - the transient training data of the set T comprises: • A matrix XT resulting from a horizontal concatenation of each matrix Xyr, • A matrix K? resulting from the horizontal concatenation of each matrix The stabilized training data for set S includes: • A matrix Xs resulting from a horizontal concatenation of each matrix ^vs, • A matrix Ys resulting from a horizontal concatenation of each matrix And according to which the transient prediction model f is defined such that f(Xr) = Yt.
8. Method according to claim 7 wherein the stabilized prediction model H is defined such that H(f(X5),
9. A method according to any one of the preceding claims comprising a margin calculation step (105), the margin being proportional to the difference between the matrix of interest YSiet a matrix Ymp, the matrix Ymp being the output of a physical model representing the worst case for the input Xsc.
10. Product computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method (100) according to any one of the preceding claims.