Method for monitoring the health of an aircraft engine

Abstract

One aspect of the invention relates to a method (1) for monitoring the health x of an aircraft engine, comprising training (40) a neural network, the neural network being configured to output a prediction of parameters of the health x of the aircraft engine and taking the measurement data Y of the aircraft engine as input, the training furthermore being carried out on a set of training data comprising noisy measurement data Y generated based on a simulation of the aircraft engine.

Description

DESCRIPTION TITLE: Method for monitoring the health of an aircraft engine TECHNICAL FIELD OF THE INVENTION The technical field of the invention is that of aeronautics. The present invention relates to a method for monitoring the health of an aircraft engine and in particular such monitoring using a neural network. TECHNOLOGICAL BACKGROUND OF THE INVENTION Methods for monitoring the health of an aircraft engine in aeronautics use measurement data from sensors and / or analysis data. This data may be data from an aircraft or data from an aircraft engine. These monitoring methods then use this data to generate indicators and alerts on the state of health and use of the engine. These indicators and alerts can be sent to an operator, in order to best manage the use of the aircraft engine.For example, it is possible to anticipate the future maintenance needs of an aircraft or an aircraft system. Such monitoring makes it possible, in particular, to optimize maintenance programs and / or reduce unplanned downtime and / or improve aircraft availability and reliability. The aircraft engine is, for example, a turbomachine and the method for monitoring the health of the turbomachine includes the monitoring of modular parameters such as the efficiencies and flow rates of different compressors and / or turbines of the turbomachine. Several classic methods for monitoring the health of the turbomachine exist, such as thermodynamic analysis, "gas path analysis", Bayesian filtering on variables of interest or methods by dimension reduction and nearest neighbors. Neural networks are also used to monitor the health of an aircraft engine.Typically, a neural network-based aircraft engine health monitoring method may include three steps: - Generation of a training data set consisting of values ​​of the efficiencies and airflows of the aircraft engine modules and measurements from a set of sensors simulated by a simulator. thermodynamics with a single predetermined operating point. As a reminder, an operating point, also called an operational point, corresponds to an operation of the aircraft engine for predetermined inputs provided to the aircraft engine, - Training the neural network using the training data set, and - using the trained neural network in real conditions to recover the efficiencies and airflows of the engine modules from the observed measurements. Engine health monitoring methods using neural networks have several advantages over other prior art methods. For example, engine health monitoring methods using neural networks allow for faster execution in real conditions than thermodynamic analysis since they do not require optimization during the processing of the real data.Furthermore, engine health monitoring methods using neural networks do not rely on strong assumptions of statistical laws unlike Bayesian filtering methods on variables of interest. Finally, engine health monitoring methods using neural networks do not require discretization of space, which introduces additional limitations in accuracy, as is the case with methods such as dimension reduction and nearest neighbor methods, which require discretization of space. When an aircraft engine, having given health parameters, is observed through sensors, it is possible that the system of equations modeling the relationship between the aircraft engine health and the measurement data for a given observation, does not allow to differentiate between several sets of aircraft engine health parameters.In other words, the same sensor observation can lead to multiple solutions for aircraft engine health parameters. This scenario is known as the underdetermined case, and occurs when few sensors are available relative to the number of health parameters to be determined. None of the conventional methods for monitoring the health of the turbomachinery can solve this problem satisfactorily. For example, conventional neural network methods fail to provide acceptable performance in underdetermined cases. One solution to this problem is to increase the number of sensors used. However, this solution has several drawbacks. First, adding measurement sensors presents a significant financial cost and adds additional constraints on the system such as additional weight to the system and / or additional maintenance tasks to manage these sensors. There is therefore a need to provide a method for monitoring the health of an aircraft engine that limits, at least partially, the problems associated with the prior art methods.SUMMARY OF THE INVENTION The invention provides a solution to the problems mentioned above, by proposing a method for monitoring the health of an aircraft engine based on a neural network combined with the use of a multi-point perspective, which consists of imposing one or more appropriate hypotheses of link between the health of the aircraft engine and the operating points. In addition, the generation of the training data set of the neural network includes the addition of noise to the measurement data used in order to improve the prediction accuracy of the health state of the engine in real conditions.One aspect of the invention relates to a method for monitoring a health x of an aircraft engine comprising training a neural network, the neural network being configured to provide as output a prediction of parameters of the health x of the aircraft engine and taking as input measurement data Y of the aircraft engine, the training being further carried out from: - a training data set comprising noisy measurement data Y and generated from a simulation of the aircraft engine carried out: - according to at least one business hypothesis relating to knowledge of the aircraft engine, and. - according to one or more operating points u of the set of operating points U of the aircraft engine and parameters of the health x of the aircraft engine, - a function penalizing a deviation between the parameters of the health x of the aircraft engine corresponding to the measurement data Y and the prediction of the parameters of the health x obtained by providing the trained neural network with the generated and noisy measurement data Y. Thanks to the invention, the method for monitoring the health of an aircraft engine has a high speed of execution in real conditions, that is to say during the inference phase of the neural network. In addition, the health of the aircraft engine is estimated accurately even in underdetermined cases.In addition to the characteristics which have just been mentioned in the preceding paragraph, the method according to one aspect of the invention may have one or more additional characteristics among the following, considered individually or according to all technically possible combinations: - The method is implemented by a monitoring device comprising a set of sensors adapted to carry out measurements of an operation of the aircraft engine and being configured to comprise a simulator ^. ^ of the aircraft engine, the simulator ^ ^ taking as input parameters of the health x of the aircraft engine and an operating point u of the aircraft engine, and providing as output corresponding generated measurement data Y, - The simulation of the aircraft engine allowing the generation of the training data set is carried out with the simulator ^ ^of the aircraft engine and the training data set is obtained by further performing, after the acquisition step and before the training step, additional steps of: - Obtaining at least one business hypothesis, the at least one business hypothesis being a hypothesis of the link between the health x of the aircraft engine and parameter values ​​of the set of operating points, - Generation of the training data set, each training data including generated and noisy measurement data Y as well as parameters of the health x of the aircraft engine and an operating point u of the aircraft engine, the generation being carried out respecting the link hypothesis and includes for each training data: ^ Obtaining the generated measurement data Y by providing the simulator ^ ^of the aircraft engine the parameters of the health x of the aircraft engine and an operating point u of the aircraft engine, the operating point u of the aircraft engine being included in the set of operating points U, ^ Adding noise to the generated measurement data Y, - training the neural network is further performed using the training data set, the neural network further taking as input the operating point u of the aircraft engine, the training function penalizing a deviation, for each training data, between the parameters of the health x of the aircraft engine of the training data and the parameters of the health x obtained by providing the neural network with the generated measurement data Y and the operating point of the aircraft engine of the training data, and - Diagnosing the health x of the aircraft engine using the trained neural network,- the business hypothesis includes at least one hypothesis from among a multi-point hypothesis and a temporal hypothesis, with: - the multi-point hypothesis consisting of considering that the health x of the aircraft engine has an influence on the values ​​of the parameters of all the operating points and that the link between the health x of the aircraft engine and the value of the operating points is predetermined, and, - the temporal hypothesis consisting of considering that the health x of the aircraft engine evolves over time and that the evolution over time of health x is predetermined. - the neural network is of the type: - A multi-layer perceptron, or - A recurrent neural network, or - A convolutional neural network, or - A transformer.- adding noise to the generated measurement data Y comprises, for each measurement data, adding a sample of a noise distribution having a predetermined mean and variances, - the method further comprises a step of validating the trained neural network, carried out between the training of the neural network and the diagnosis of the health x of the aircraft engine, and the validation step comprising: - Generation of a validation data set, each validation data item comprising measurement data Y and parameters of the health x of the aircraft engine and the operating point of the aircraft engine, the generation being carried out in compliance with the link hypothesis and comprises for each validation data item: ^ Obtaining the measurement data Y by providing the simulator ^. ^of the aircraft engine the parameters of the health x of the aircraft engine and the operating point of the aircraft engine, ^ Adding noise to the measurement data Y comprising, for each measurement data y, the addition of a sample respecting a Gaussian distribution of noise having a mean equal to zero and a variance equal to a predetermined variance matrix of the noises of all the sensors. - Validating the trained neural network using the validation data set and verifying that the difference, for each validation data item, between the health parameters x of the aircraft engine in the training data item and the health parameters x obtained is less than a predetermined threshold. Another aspect of the invention relates to a system comprising a set of sensors adapted to carry out measurements on an aircraft engine and a computer configured to implement the method according to the invention. A further aspect of the invention relates to an aircraft comprising the system according to the invention. The invention also relates to a computer program product comprising instructions which, when the program is executed on a computer, cause the latter to implement the steps of the method according to the invention.Finally, the invention relates to a computer-readable recording medium comprising instructions which, when executed by a computer, cause the latter to implement the steps of the method according to the invention. 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 The figures are presented for information purposes only and in no way limit the invention. - Figure 1 shows a block diagram illustrating the steps of an example of the method according to the invention. DETAILED DESCRIPTION Unless otherwise specified, the same element appearing in different figures has a single reference. Figure 1 is a block diagram illustrating the steps of an example of the method 1 according to the invention.Mandatory steps in the example of process 1 are indicated by a solid rectangle and optional steps are indicated by a dotted rectangle. The method 1 is implemented by a monitoring device comprising a set of sensors adapted to carry out measurements of an operation of the aircraft engine. In addition, the monitoring device is configured to comprise a simulator ^ ^ of the aircraft engine. For example, the device comprises a computer or processor configured to provide a simulator ^ ^of the aircraft engine. Thus, steps of method 1 may be implemented by a processor included in a system for monitoring the health of an aircraft engine. The monitoring system preferably has the structure of a calculator, in this case an on-board computer, and / or a computer. It comprises an electronic circuit, in one or more parts, equipped with at least one non-volatile type memory, and a processor for executing logical operations. It may also comprise one or more other memories, of the random access memory type or of another type, and one or more other processors. By "computer-implemented", it is meant that the steps, or practically all of the steps of method 1, are executed by at least one computer or processor or any other similar system. Thus, steps are carried out by the calculator, possibly in a fully automatic or semi-automatic manner.In examples, the triggering of at least some of the steps of the method may be performed by user-computer interaction. The required level of user-computer interaction may depend on the intended level of automation and balanced against the need to implement the user's wishes. In examples, this level may be user-defined and / or predefined. A typical example of computer implementation of a method is to execute the method with a system adapted for this purpose. The system may include a processor coupled to a memory and a graphical user interface (GUI), a computer program comprising instructions for implementing the method being stored in the memory. The memory may also store a database. Memory is any hardware adapted for such storage, possibly comprising several distinct physical parts.Method 1 includes simulations of the aircraft engine to generate a training dataset. The training dataset is used to train a neural network. The simulations can be performed. with a simulator ^ ^ of the aircraft engine. In one example, the aircraft engine is a turbomachine and the method of monitoring the health of the turbomachine includes tracking modular parameters such as the efficiencies and flow rates of different compressors and / or turbines of the turbomachine. The simulator ^ ^ can for example be previously stored on the computer implementing method 1. The aircraft engine can be modeled by a system S as described below: ^ ^ ^^^, ^^With: -^ ∈ ℝ^, the observation of the system, i.e. the measurement data y from at least one sensor, -^ ∈ ℝ^, the health of the system, i.e. for example the modular efficiencies and flow rates of the aircraft engine, or for example the differences to a reference of modular efficiencies and flow rates of the aircraft engine, -^ ∈ ℝ^, an operating point.The simulator ^ ^ of the aircraft engine is therefore governed by the following equation: ^^ ^ ^^^^, ^^The simulator ^ ^ of the aircraft engine therefore takes as input the health x of the aircraft engine, or parameters of the health x of the aircraft engine, and an operating point u of the aircraft engine. The simulator ^ ^ of the aircraft engine thus provides corresponding measurement data y as output, i.e. measurement data y corresponding to the health x of the aircraft engine and the operating point u of the aircraft engine provided as input. For example, a simulator ^ ^compatible with the invention is the simulator ^ ^ described in French patent application FR2202472. It is also possible to use other types of simulators ^ ^ such as those distributed: - in the TURBO® libraries distributed by EcosimPro® and in the commercial PROOSIS® software, or - in the GasTurb® software, or - in the commercial NPSS® software, or - by Elettronicavenata Veneta®, for example the STG / EV model which is a turbine simulator. A first advantageous step 10 of the method 1 comprises the acquisition of measurement data Y of an operation of the aircraft engine. The measurement data Y comprises parameters of the health x of the aircraft engine and a set of operating points U. This measurement data set Y may come from the measurement of an operation of the aircraft engine. This measurement data set Y may be provided by at least one sensor, having carried out the measurements during the operation of the aircraft engine. The measurement data set Y may come from the measurement of several days or several weeks of use of the aircraft engine. The measurement data set may also come from a single complete flight of the aircraft.The set of operating points U acquired may for example have been determined using the method described in French patent application FR2202472. This measurement data can be used to configure the simulator ^. ^ , that is, train the simulator ^ ^to accurately provide measurement data y of the aircraft engine corresponding to the health x of the aircraft engine and the operating point u of the aircraft engine provided as input. A second advantageous step 20 of the method 1 comprises obtaining a business hypothesis relating to the knowledge of the aircraft engine. The business hypothesis may be a hypothesis of a link between the health x of the aircraft engine and parameter values ​​of the set of operating points. In one example, the business hypothesis used in the method 1 is the multipoint hypothesis. The multipoint hypothesis consists of considering that the health x of the aircraft engine has an influence on the parameter values ​​of the set of operating points and that the link between the health x of the aircraft engine and the value of the operating points is predetermined.For example, the multipoint hypothesis consists of considering that when an observed degradation of the parameter values ​​is 1% on a first operating point (for example during the cruise phase during a flight), then we can deduce a degradation of these same parameters of 0.5% on a second operating point (for example during the takeoff phase of the same flight). Thus, with this multipoint hypothesis, it is for example possible to consider that when a degradation of the values ​​of the. aircraft engine parameters due to engine wear occurs during a flight, the efficiency curves versus the corrected airflow in the performance maps are linearly displaced along a fixed direction, and the amounts of displacements are the same for all operating points included in the set of operating points U. Alternatively, the business hypothesis used in method 1 is the time hypothesis. The time hypothesis consists of considering that the health x of the aircraft engine evolves over time and that the evolution over time of the health x is predetermined or at least partially known. For example, the time hypothesis consists of considering when a degradation of the health x of the engine of 1% is observed at a first operating time, then the degradation of the health x of the engine is 1.1% at a second operating time, the evolution of the health status of the aircraft engine can for example be modeled by a Gaussian function, which will model the uncertainty due to the partial aspect of the knowledge of this relationship. Thus, with this temporal hypothesis, it is for example possible to consider that given an operating point ^, we assume the existence of a function ^ which governs the changes in values ​​of the health parameters of an engine during a first flight to its new values ​​when the same engine is operated during a second flight, the second flight taking place after the first flight. An equation describing this example, with the function ^ in a form of a linear function, can for example be in the form of: ^^ ^ ^^^^^ ^ ^^ ^ ^ ∗ ^,With: - ^. ^ , the value of health parameters during the first flight, - ^ ^ the value of health parameters during the second flight, - ^ ∈ ℝ ^ ^ ^, a direction of degradation of aircraft engine parameter values, -^ ^ 0 is a scalar reflecting the rate of degradation of aircraft engine parameter values. Alternatively, the business hypothesis used is the combination of the multipoint hypothesis and the time hypothesis. For example, for a set of operating points U containing several operating points from two different flight missions of an aircraft engine, it is possible to impose the multipoint hypothesis for the changes in parameter values ​​at the different operating points of the same flight, and to impose the temporal hypothesis for the changes in parameter values ​​at the different operating points not belonging to the same flight. These business hypotheses therefore make it possible to add information to the problem to be solved, i.e. to carry out the diagnosis of the health x of the aircraft engine, thus they make it possible to resolve at least partially the problem of indeterminacy. It should be noted that this addition of information results in an increase in the dimension of the problem considered.It is possible to consider that the addition of the assumptions to method 1 fulfills its objective if the accuracy of the method is better with these assumptions than without its use, i.e. as it is done in the state of the art: using a single operating point. The accuracy of method 1 can be quantified by the measured error between the actual value to be estimated and the value estimated by method 1. This accuracy of method 1 can for example be calculated with the mean square error between the actual value to be estimated and the value estimated by method 1 or the mean absolute error between the actual value to be estimated and the value estimated by method 1 or any other sample-weighted or dimension-weighted metric. A third advantageous step 30 of method 1 comprises the generation of a training data set for an artificial neural network. Different types of neural network can be used in method 1.For example, it is possible to use a multilayer perceptron or a recurrent neural network or a transformer or a convolutional neural network. A multilayer perceptron is a type of neural network organized into several layers. A multilayer perceptron has at least three layers: an input layer, at least one hidden layer, and an output layer. Each layer is made up of a potentially different number of neurons. Information flows from the input layer to the output layer only. The neurons in the last layer are the outputs of the overall system. A recurrent neural network is a network of neurons with recurrent connections. A recurrent neural network is. Consisting of interconnected neurons interacting nonlinearly and for which there is at least one cycle in the structure. Neurons are connected by edges that have a weight. The output of a neuron is a nonlinear combination of its inputs. A transformer, or self-attentive model, is a deep learning architecture designed to handle sequential data. The transformer uses an encoder-decoder architecture. The encoder consists of a set of encoding layers that iteratively process the input sequence layer by layer, and the decoder consists of a set of decoding layers that performs the same on the encoder's output sequence. A convolutional neural network is a type of acyclic artificial neural network, in which the connection pattern between neurons is inspired by the visual cortex of animals.A convolutional neural network consists of two types of artificial neurons, arranged in “layers” successively processing the information: - processing neurons, which process a limited portion of the image through a convolution function. - output pooling neurons, called total or partial pooling. Each training data of the training data set may comprise generated and noisy measurement data Y as well as parameters of the health x of the aircraft engine and an operating point u of the aircraft engine, the generation being carried out in compliance with the business hypothesis(es) obtained in step 20. The generation 30 of the training data set may comprise, for each training data, two sub-steps. The first sub-step is obtaining the generated measurement data Y by providing the simulator ^. ^of the aircraft engine the health parameters x of the aircraft engine and an operating point u of the aircraft engine. The second substep is the addition of noise to the generated measurement data Y. In an example compatible with the previous examples, the addition of noise to the generated measurement data Y includes, for each measurement data y generated, adding a sample from a noise distribution having a predetermined mean and variances. For example, step 30 can be implemented by following this protocol when the multipoint hypothesis is used: - (a) determine a range, denoted ^, of possible values ​​in which the engine health parameters can vary. For example, each strain coefficient can vary in the range ^0.95, 1.00" and ^ ^^0.95, 1.00"^ where # is the number of health parameters to be estimated. - (b) determine the number, denoted $ %&'() , of samples included in the training dataset, - (c) generate $%&'() vectors in the range ^, for example, following a Latin hypercube sampling scheme. The set of such vectors is denoted * %&'() and represents the values ​​of the engine health parameters. The set of these vectors * %&'() will act as labeled outputs of this dataset. - (d) Generate the measurements corresponding to the values ​​of the engine health parameters in * %&'() and the operating points included in the set of operating points U. The generation of the measurements is carried out by the simulator ^ ^ respecting the business hypothesis(es) obtained in step 20. In particular, it is possible to calculate: - With: -^ ∈ *%&'(), a vector representing a value of the engine health parameters, -^^, … , ^, ∈ U, the operating points of the set of operating points U, -y^, … , ^^, ∈ 2&'3, the generated measurements included in the set of generated measurements 2&'3 . - Enrich the set of measures generated 2 &'3 by adding a sample respecting a noise distribution, representing for example the variance of the artificial noise from sensor measurements, for example a Gaussian noise distribution. In particular, for any ^^ ∈ 2&'3, it is possible to calculate: -^4 ^ ^^ 5 ^6^, … , 6,^With: - ^4, the generated and noisy measurements included in the set of generated and noisy measurements 2 %&'() , - 6( ∼ corresponding with each operating point ^ = , in which - 9 : % & ; ' () , the vector representing the bias, otherwise called the normal law of expectation, of the Gaussian function - < :; %&'() ∈ ℝ^ / ^, the variance of artificial noises of sensor measurements. It can be noted that when the temporal hypothesis is used, step (c) of the protocol consists of generating $%&'() vectors in the range P, for example, following a Latin hypercube sampling scheme. The set of these vectors is denoted *^. Then, for each vector ^^ ∈ *^ a degradation vector ^4 ∈ is sampled from the Gaussian distribution 8^^, >^with ^ ∈ ℝ^, the direction of degradation in the time hypothesis and > ∈ ℝ^ / ^ is a predetermined variance matrix. Finally, the calculation ^^ ^ ^^ ^ is performed in order to calculate ^ ^ , with ^ a deterministic value depending on the time elapsed between the two instants considered, for example, 0.01 for 100 flights. The set * %&'() of these generated vector pairs ^^^ , ^^^ will act as labeled outputs of this dataset. Thus, in this implementation mode, a training dataset^ 2%&'(), *%&'()^ is obtained at the end of step 30 of training dataset generation. Here, 2 %&'()serves as an entry into training, and * %&'() serves as the labeled output in training. In addition, the neural network used in this implementation mode will have a first layer with a size corresponding to the size of 2 %&'() and a final layer having a size corresponding to the size and * %&'() . Advantageously, the addition of noise during this data generation training makes the network more robust during its learning, and counterbalances the increase in the dimension to be noted in the paragraph

[0038] . A fourth step 40 of the method 1 comprises training the neural network using the training data set. Thus, the neural network is configured to take as input the generated and noisy measurement data Y obtained in step 30 and an operating point u of the aircraft engine. As output, the neural network is configured to provide as output a prediction of the health parameters x of the aircraft engine. The training of the neural network is carried out from a function penalizing a deviation, for each training data item, between the health parameters x of the aircraft engine of the training data item and the health parameters x obtained by providing the neural network with the generated measurement data Y and an operating point of the aircraft engine. The training of the neural network can for example be carried out using an optimization method such as stochastic gradient descent.A fifth advantageous step 50 of the method 1 comprises the validation of the trained neural network. This validation step 50 can be carried out after the training 40 of the neural network and before the diagnosis 60 of the health x of the aircraft engine, and the validation step (50) comprises two sub-steps. A first sub-step of the fifth advantageous step 50 of the method 1 is the generation of a validation data set. Each validation data comprising measurement data Y and parameters of the health x of the aircraft engine and the operating point of the aircraft engine. The generation of the validation data set can be carried out in a similar manner to the generation 30 of the training data set except that for the addition of the noises to the generated measurements, noises corresponding to the noises of the sensors that can be used are used, these noises of the sensors can be different from the noises used to generate the training data.Preferably, the validation dataset does not include any data in common with the training dataset. For example, generating the validation dataset may include, for each validation data, the substeps of:. - obtaining the measurement data Y by providing the simulator ^ ^of the aircraft engine the parameters of the health x of the aircraft engine and the operating point of the aircraft engine, - adding noise to the measurement data Y comprising, for each measurement data y, the addition of a sample respecting a Gaussian noise distribution having a mean equal to zero and a variance equal to a predetermined variance matrix of the noises of all the sensors, for example, a variance matrix obtained from the analysis of real measurements during flights or on a test bench. As an alternative to the previous example, this first sub-step of generating the validation data set may comprise obtaining data from measurements of an operation of an aircraft engine in real conditions. Thus, in this alternative, the validation data set therefore comprises these data from measurements of an operation of an aircraft engine in real conditions.This first sub-step of generating the validation data set can be performed before the training 40 of the neural network, for example at the same time as the generation of the training data set. A second sub-step is the validation of the trained neural network using the validation data set and verifying that the difference, for each validation data item, between the parameters of the health x of the aircraft engine of the training data item and the parameters of the health x obtained by the prediction of the neural network is less than a predetermined threshold. A sixth step 60 of the method 1 comprises the diagnosis of the health x of the aircraft engine using the trained neural network. A seventh advantageous step 70 of the method 1 comprises a modification of the conditions of use of the aircraft engine. This step 70 can be implemented when the health x of the aircraft engine is less than a predetermined health level x.This step 70 may for example comprise one of the following actions: - performing a maintenance operation on the aircraft engine, and / or. - change the operating conditions of the aircraft engine so that its health deteriorates less quickly.

Claims

CLAIMS

1. Method (1) for monitoring a health x of an aircraft engine comprising training (40) a neural network, the neural network being configured to provide as output a prediction of parameters of the health x of the aircraft engine and taking as input measurement data Y of the aircraft engine, the training being further carried out from: - a training data set comprising noisy measurement data Y and generated from a simulation of the aircraft engine carried out: o according to at least one business hypothesis relating to the knowledge of the aircraft engine, the at least one business hypothesis comprising at least one multipoint hypothesis consisting in considering that the health x of the aircraft engine has an influence on the values ​​of the parameters of all the operating points and that the link between the health x of the aircraft engine and the value of the operating points is predetermined,and o according to one or more operating points u of the set of operating points U of the aircraft engine and the health parameters x of the aircraft engine, - a function penalizing a deviation between the health parameters x of the aircraft engine corresponding to the measurement data Y and the prediction of the health parameters x obtained by providing the trained neural network with the generated and noisy measurement data Y.

2. Monitoring method (1) according to claim 1 wherein: - The method (1) is implemented by a monitoring device comprising a set of sensors adapted to carry out measurements of an operation of the aircraft engine and being configured to comprise a simulator ^, ^ of the aircraft engine, the simulator ^ ^ taking as input parameters of the health x of the aircraft engine and an operating point u of the aircraft engine, and providing corresponding generated measurement data Y as output, - The simulation of the aircraft engine allowing the generation of the training data set is carried out with the simulator ^ ^of the aircraft engine and the training data set is obtained by further performing, before the training step (40), additional steps of: o Obtaining (20) at least one business hypothesis, the at least one business hypothesis being a link hypothesis between the health x of the aircraft engine and parameter values ​​of the set of operating points, o Generating (30) the training data set, each training data item comprising generated and noisy measurement data Y as well as parameters of the health x of the aircraft engine and an operating point u of the aircraft engine, the generation being carried out in compliance with the link hypothesis and comprises for each training data item: • Obtaining the generated measurement data Y by providing the simulator ^ ^of the aircraft engine the parameters of the health x of the aircraft engine and an operating point u of the aircraft engine, the operating point u of the aircraft engine being included in the set of operating points U, • Adding noise to the generated measurement data Y, - the training (40) of the neural network is further carried out using the training data set, the neural network further taking as input the operating point u of the aircraft engine, the training function penalizing a deviation, for each training data, between the parameters of the health x of the aircraft engine of the training data and the parameters of the health x obtained by providing the neural network with the generated measurement data Y and the operating point of the aircraft engine of the training data, and - Diagnosis (60) of the health x of the aircraft engine using the trained neural network.

3. Method (1) according to claim 1 or 2 wherein the business hypothesis further comprises a temporal hypothesis consisting of considering that the health x of the aircraft engine evolves over time and that the evolution over time of the health x is predetermined.

4. Method (1) according to any one of the preceding claims wherein the neural network is of the type: - A multilayer perceptron, or - A recurrent neural network, or - A convolutional neural network, or - A transformer.

5. A method (1) according to claim 2 and any one of claims 3 to 4 wherein adding noise to the generated measurement data Y comprises, for each measurement data, adding a sample of a noise distribution having predetermined mean and variances.

6. Method (1) according to claim 2 and any one of claims 3 to 5 further comprising a step (50) of validating the trained neural network, carried out between the training (40) of the neural network and the diagnosis (60) of the health x of the aircraft engine, and the validation step (50) comprising: - Generation of a validation data set, each validation data item comprising measurement data Y and parameters of the health x of the aircraft engine and the operating point of the aircraft engine, the generation being carried out in compliance with the link hypothesis and comprises for each validation data item: o Obtaining the measurement data Y by providing the simulator ^. ^ of the aircraft engine health parameters x of the aircraft engine and the operating point of the aircraft engine, o Adding noise to the measurement data Y comprising, for each measurement data y, adding a sample respecting a Gaussian noise distribution having a mean equal to zero and a variance equal to a predetermined variance matrix of the noises of all the sensors. - Validating the trained neural network using the validation data set and verifying that the difference, for each validation data, between the parameters of the health x of the aircraft engine of the training data and the parameters of the health x obtained is less than a predetermined threshold.

7. System comprising a set of sensors adapted to carry out measurements on an aircraft engine and a computer configured to implement the method (1) according to one of the preceding claims.

8. Aircraft comprising the system according to the preceding claim.

9. A computer program product comprising instructions which, when the program is executed on a computer, cause the computer to implement the steps of the method (1) according to one of claims 1 to 6.

10. A computer-readable recording medium comprising instructions which, when executed by a computer, cause the computer to implement the steps of the method (1) according to one of claims 1 to 6.

Images