Method for training an aircraft combustion chamber outlet temperature model
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2026-01-26
- Publication Date
- 2026-08-13
Smart Images
Figure FR2026050072_13082026_PF_FP_ABST
Abstract
Description
DESCRIPTION TITLE: Method for training an aircraft combustion chamber outlet temperature model. TECHNICAL FIELD OF THE INVENTION
[0001] The technical field of the invention is that of aeronautics.
[0002] The present invention relates to a method of training a model configured to predict a value of an outlet temperature of a T45 combustion chamber of a twin-body turbomachine of an aircraft. TECHNOLOGICAL BACKGROUND OF THE INVENTION
[0003] Aircraft engine health monitoring processes utilize measurement data from sensors and / or analytical data. This data can be from the aircraft as a whole or from a specific engine within the aircraft. These monitoring processes then use this data to generate indicators and alerts about the engine's health and usage status. These indicators and alerts can be sent to an operator to optimize engine operation. For example, it is possible to anticipate future maintenance needs for an aircraft or an aircraft system. Such monitoring allows for the optimization of maintenance programs, the reduction of unplanned downtime, and the improvement of aircraft availability and reliability.
[0004] The health monitoring of an aircraft engine, such as a twin-spool turbomachine, is performed primarily through high-frequency performance margin calculations, commonly referred to as EPC (Engine Power Check). EPC calculations rely on the values of certain parameters, such as the gas generator speed, torque, and the turbomachine's combustion chamber outlet temperature (T45), as well as atmospheric conditions like temperature and altitude. However, the T45 combustion chamber outlet temperature is significantly affected by the aircraft cabin heating system, which can be activated manually or automatically. The order of magnitude of the change in the T45 combustion chamber outlet temperature due to cabin heating is 10 to 20 degrees Celsius.It is therefore impossible to use the T45 combustion chamber outlet temperature values for engine health monitoring when the cabin heater is activated. This discrepancy artificially lowers the calculated margins, rendering the data unusable for an aircraft engine. For aircraft, such as helicopters operating in cold conditions, high-frequency performance margin calculations are nearly impossible since the cabin heater is permanently on. Furthermore, the EPC (Engine Performance Control) procedure specifies that the cabin heater must be switched off.
[0005] Currently, a temporary solution to this problem involves filtering high-frequency performance margin calculations to avoid displaying margin values that are too low, such as negative values. This technique prevents users from seeing erroneous margins. However, this solution is unsatisfactory because it drastically reduces the amount of data available for monitoring the health of an aircraft engine.
[0006] Therefore, there is a need to propose an alternative solution that allows for the reliable use of T45 combustion chamber outlet temperatures measured on a twin-spool turbomachine of an aircraft, regardless of flight conditions and particularly when the aircraft cabin heating is activated. Specifically, a solution is sought that can be used even when the aircraft is operated in winter conditions. SUMMARY OF THE INVENTION
[0007] The invention provides a solution to the problems mentioned above by enabling the development of a model configured to predict the outlet temperature of the combustion chamber T45 based on the rotational speed of the turbomachine's gas generator N1. Thus, the predicted outlet temperature of the combustion chamber T45 can be used for health monitoring of a twin-spool turbomachine in an aircraft, for example, to correct the measured outlet temperature of the combustion chamber T45 when the aircraft cabin heating is activated.
[0008] One aspect of the invention relates to a computer-implemented training method for a model configured to predict an outlet temperature value of a T45 combustion chamber of a twin-spool turbomachine of an aircraft, the method comprising: obtaining measurement data, derived from measurements carried out during at least one stabilized flight phase of the aircraft, including: a measured outlet temperature of the T45 combustion chamber of the turbomachine, a rotational speed of the N1 gas generator of the turbomachine, , determination of the operating state of an aircraft cabin heater from the measured outlet temperature of combustion chamber T45 and the rotational speed of gas generator N1, and when the determined operating state of the aircraft cabin heater is an off state, training of the model including modification of the internal parameters of the model in order to minimize a difference between a prediction of the outlet temperature of combustion chamber T45 and the measured outlet temperature of combustion chamber T45, the prediction of the outlet temperature of combustion chamber T45 being obtained by providing the model with the rotational speed of gas generator N1 of the turbomachine.
[0009] Thanks to the invention, the high-frequency calculation of EPC performance margins is maintained regardless of measurement conditions, and health monitoring can be performed even on turbomachinery operating in cold conditions, i.e., when cabin heating is activated. Indeed, instead of filtering the T45 combustion chamber outlet temperature data when margin values are too low, the method according to the invention makes it possible to predict the T45 combustion chamber outlet temperature in the absence of cabin heating. This prediction can then be used when the T45 combustion chamber outlet temperature is artificially modified by activating the aircraft cabin heating. An estimated value of the T45 combustion chamber outlet temperature without cabin heating can thus be used, even during flight phases when cabin heating is actually active.
[0010] In addition to the characteristics mentioned in the preceding paragraph, the process according to one aspect of the invention may have one or more complementary characteristics from among the following, considered individually or in all technically possible combinations: The process also includes: calculation of a median and an average of the rotational speed of the N1 gas generator of the turbomachine, and in which the prediction of the outlet temperature of the combustion chamber T45 is obtained by providing the model with the median and mean of the rotational speed of the gas generator N1 of the turbomachine; The model is trained and the process further includes: when the specified operating state of the aircraft cabin heater is switched on: -prediction of the outlet temperature of the T45 combustion chamber without heating, by providing the driven model with the rotational speed of the N1 gas generator of the turbomachine, and -health monitoring by correcting the measured outlet temperature of the T45 combustion chamber with the prediction of the T45 combustion chamber outlet temperature without heating; Determining the operating status of the aircraft cabin heating system includes: detection of a change in the operating state of the aircraft cabin heater by comparing the evolution of the measured outlet temperature of combustion chamber T45 and the evolution of the rotational speed of gas generator N1 for the same measurement period in which: -when the measured outlet temperature of combustion chamber T45 increases and the rotational speed of gas generator N1 is stable for the same measurement period, the operating state of the aircraft cabin heater is determined as changing from "off" to "on", -when the measured outlet temperature of the combustion chamber T45 decreases and the rotation speed of the gas generator N1 is stable for the same measurement period, the operating state of the aircraft cabin heater is determined as changing from "on" to "off"; Obtaining measurement data also includes obtaining an outside temperature T0 and a cumulative number of flight hours for the turbomachine, and The outside temperature T0 and the number of cumulative flight hours of the turbomachine obtained are also provided to the model to obtain the prediction of the combustion chamber outlet temperature T45 during training; a median and mean of the outside temperature T0 is calculated and the median and mean of the outside temperature T0 are also provided to the model to obtain the prediction of the combustion chamber outlet temperature T45 during training; The outside temperature T0 and the cumulative number of flight hours of the turbomachine are also provided to the model during the prediction of the combustion chamber outlet temperature T45 without heating; the determination of the operating status of the aircraft cabin heating includes: Determination of an initial operating state of the aircraft cabin heating system as a function of the outside temperature T0 in which: When the outside temperature T0 is less than or equal to a predetermined threshold temperature, the initial operating state of the aircraft cabin heater is determined to be on, and when the outside temperature TO is above the predetermined threshold temperature, the initial operating state of the aircraft cabin heater is determined to be off; the model is a polynomial regression model or a linear regression model
[0011] Another aspect of the invention relates to a health monitoring device comprising: a set of sensors adapted to measure an outlet temperature of a T45 combustion chamber of an aircraft turbomachine, a rotational speed of an N1 gas generator of the turbomachine, and a computer configured to implement the process according to the invention.
[0012] According to one aspect of the invention, the sensor set of the health monitoring device is further adapted to measure an outside temperature T0 and a cumulative number of flight hours of the turbomachine.
[0013] An additional aspect of the invention relates to an aircraft comprising the health monitoring device according to the invention.
[0014] An additional aspect of the invention relates to a computer program comprising instructions which, when the program is executed on a computer, cause the computer to carry out the steps of the process according to the invention.
[0015] Another aspect of the invention relates to a computer-readable recording medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the process according to the invention.
[0016] 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
[0017] The figures are presented for illustrative purposes only and are in no way limiting to the invention. Figure 1 is a block diagram illustrating the steps of an example of the drive method according to an example implementation of the invention. Figure 2 is a schematic representation of an example of detecting a change in the operating state of the aircraft cabin heater that can be achieved with the drive method according to Figure 1. Figure 3 is a schematic representation of an example of predicting a temperature of a combustion chamber outlet T45 of a twin-body turbomachine of an aircraft that can be obtained with the drive method according to Figure 1.
[0018] Unless otherwise specified, the same element appearing on different figures has a unique reference. DETAILED DESCRIPTION
[0019] Figure 1 is a block diagram illustrating the steps of an example of process 100 according to the invention. The mandatory steps of the example of process 100 are indicated by a solid rectangle and the optional steps are indicated by a dashed rectangle.
[0020] The 100 method can be implemented by a health monitoring device comprising a set of sensors adapted to perform measurements on the aircraft and in particular on the aircraft's twin-body turbomachine.
[0021] In one example, the aircraft twin-spool turbomachine includes a low-pressure compressor, a high-pressure compressor, a high-pressure turbine, and a low-pressure turbine. A low-pressure shaft connects the low-pressure compressor to the low-pressure turbine. A high-pressure shaft connects the high-pressure compressor to the high-pressure turbine. A fan is mounted directly to the low-pressure shaft. The aircraft twin-spool turbomachine also includes a combustion chamber to consume a mixture of fuel and pressurized air accelerated by the low-pressure and high-pressure compressors. An exhaust flow drives the low-pressure and high-pressure turbines. Both the high-pressure and low-pressure shafts are propulsion shafts.
[0022] The sensor suite of the health monitoring system may include a set of sensors adapted to measure the outlet temperature of the turbomachine's combustion chamber T45 and the rotational speed of the turbomachine's gas generator N1. Optionally, the sensor suite can also be adapted to measure the ambient temperature T0 and the turbomachine's cumulative flight hours. Furthermore, the health monitoring system includes a computer or processor configured to implement Process 100. Thus, steps of Process 100 can be implemented by a computer within the health monitoring system. The health monitoring system is, for example, integrated into the turbomachine's computer, such as the FADED (Full Authority Digital Engine Control).It comprises an electronic circuit, in one or more parts, equipped with at least one non-volatile memory and a processor for executing logical operations. The non-volatile memory is, for example, suitable for storing the model configured to predict the outlet temperature of the T45 combustion chamber. It may also include one or more other memories, of the RAM type or another type, and one or more other processors.
[0023] By "computer-implemented," we mean that the steps, or virtually all of the steps, of process 100 are executed by at least one computer, processor, or similar system. Thus, steps are carried out by the computer, possibly fully automatically or semi-automatically. In some examples, the triggering of at least some of the process steps can be achieved through user-computer interaction. The level of user-computer interaction required may depend on the intended level of automation and be balanced against the need to implement the user's requirements. In some examples, this level may be user-defined and / or predefined.
[0024] A typical example of computer implementation of a process involves executing the process with a system designed for this purpose. The system may include a processor coupled with memory and a graphical user interface (GUI), a computer program containing instructions to implement the process stored in memory. Memory is any hardware adapted for such storage, possibly comprising several distinct physical parts.
[0025] Step 110 of Process 100 involves obtaining measurement data. In this application, the term "obtaining" can mean "receiving," for example, when the data has been previously collected and stored in a database. For instance, the measurement data is sent from the database to the computer implementing Process 100 to train the model. In another example, the data can be sent directly from the sensors performing these measurements to the computer. In this example, the model can be trained on the fly, i.e., during a flight mission, but can also be used to predict the outlet temperature of combustion chamber T45. The term "obtaining" can also include processing the received data or even performing additional calculations.For example, measurement data can be processed to reduce contained noise, or additional data, such as means or medians, can be calculated using this measurement data. The data are derived from the measurement of at least one stabilized flight phase of the aircraft, preferably several stabilized flight phases of the aircraft. The measurement data preferably include: the outlet temperature of the T45 combustion chamber of the turbomachine, a rotational speed of the N1 gas generator of the turbomachine.
[0026] Optionally, the measurement data also includes: an outside temperature T0, and a cumulative number of flight hours of the turbomachine.
[0027] All measurement data are temporal data, meaning that for each measurement value, it is possible to know a corresponding temporal value. It is therefore possible to temporally correlate, i.e., synchronize, the different measurement data.
[0028] Step 120 of process 100 includes determining the operating status of the aircraft cabin heater. The operating status of the aircraft cabin heater can be one of the following: turned off, i.e. the cabin heating is not activated, or lit, i.e. the cabin heating is activated.
[0029] The determination of the aircraft cabin heater's operating status (120) is based on the combustion chamber outlet temperature (T45) and the rotational speed of the gas generator (N1). For example, the aircraft cabin heater's operating status can be determined by comparing the evolution of the combustion chamber outlet temperature (T45) and the evolution of the gas generator's rotational speed (N1) over the same measurement period during a portion of a stabilized flight phase. The measurement period can range from 30 seconds to several minutes.
[0030] In an example consistent with the preceding examples, the determination 120 of the operating state of the aircraft cabin heater includes the detection of a change in the operating state of the aircraft cabin heater. The detection of the change in the operating state of the aircraft cabin heater is performed by comparing the evolution of the combustion chamber outlet temperature T45 and the evolution of the rotational speed of the gas generator N1 for the same measurement period during a portion of a stabilized flight phase. Figure 2 is a schematic representation of an example of detecting a change in the operating state of the aircraft cabin heater. In Figure 2, diagram 201 corresponds to the measurement of the combustion chamber outlet temperature T45.The vertical axis for diagram 201 represents the combustion chamber outlet temperature T45, and the horizontal axis represents time. In Figure 2, diagram 202 corresponds to the measurement of the rotational speed of gas generator N1. The vertical axis for diagram 202 represents the rotational speed of gas generator N1, and the horizontal axis represents time. Areas 203 correspond to a measurement period during which the cabin heater switches from an off state to an on state, and areas 204 correspond to a measurement period during which the cabin heater switches from an on state to an off state. These changes in the operating states of the aircraft cabin heater are detected by comparing the evolution of the combustion chamber outlet temperature T45 and the evolution of the rotational speed of gas generator N1 for the same measurement period during a portion of a stabilized flight phase.The measurement period used can be between 30 and 60 seconds.
[0031] In an example consistent with the previous examples, when the outlet temperature of combustion chamber T45 increases and the rotational speed of gas generator N1 remains stable for the same measurement period, the operating state of the aircraft cabin heater is determined to change from "off" to "on." The increase in the outlet temperature of combustion chamber T45 can be determined by calculating the temperature gradient of combustion chamber T45 over the measurement period. The gradient is calculated by processing the data in chronological order of measurement, i.e., reading the oldest data first and the most recent data last. The calculated gradient is then compared to a predefined threshold, for example, between 3 and 10, preferably 6.When the calculated gradient exceeds the predefined threshold, the combustion chamber outlet temperature T45 is considered to be increasing during the measurement period. The stability of the rotational speed of gas generator N1 can be determined by calculating the gradient of the evolution of the rotational speed of gas generator N1 over the measurement period. This calculated gradient is then compared to a predefined threshold, for example, between 0.05 and 0.2, preferably equal to 0.1. The gradient is calculated by processing the data in chronological order of measurement, i.e., reading the oldest data first and the most recent data last.
[0032] In an example consistent with the previous examples, when the outlet temperature of combustion chamber T45 decreases and the rotational speed of gas generator N1 remains stable for the same measurement period, the operating state of the aircraft cabin heater is determined to change from "on" to "off." The decrease in the outlet temperature of combustion chamber T45 can be determined by calculating the gradient of the combustion chamber outlet temperature T45 over the measurement period. This calculated gradient is then compared to a predefined threshold, for example, between -3 and -10, preferably equal to -6. The gradient is calculated by iterating through the data in chronological order of measurement, i.e., reading the oldest data first and the most recent data last.When the calculated gradient is below the predefined threshold, the outlet temperature of combustion chamber T45 is considered to be decreasing during the measurement period. Alternatively, the gradient can be calculated by processing the combustion chamber T45 outlet temperature data in reverse chronological order, i.e., reading the most recent data first and the oldest data last. In this example, the calculated gradient is compared to a predefined threshold, for example, between 3 and 10, preferably equal to 6. The stability of the rotational speed of gas generator N1 can be determined by calculating the gradient of the rotational speed of gas generator N1 for the measurement period. Then, the calculated gradient is compared to a predefined threshold, for example, between 0.05 and 0.2, preferably equal to 0.1.
[0033] In an example consistent with the preceding examples, determining the operating state of the aircraft cabin heater involves determining an initial operating state of the aircraft cabin heater. The initial state is the state of the aircraft cabin heater at the beginning of the measurement data collection. The initial operating state of the aircraft cabin heater can be determined from the outside temperature T0. For example, when the outside temperature T0 is less than or equal to a predetermined threshold temperature, the initial operating state of the aircraft cabin heater is determined to be on. When the outside temperature T0 is greater than a predetermined threshold temperature, the initial operating state of the aircraft cabin heater is determined to be off.The predetermined threshold temperature can, for example, be between 5 and 10 degrees Celsius, preferably 8 degrees Celsius.
[0034] In one example, consistent with the preceding examples, process 100 includes an optional step 130 for calculating a median and an average of the rotational speed of the gas generator N1 of the turbomachine. Furthermore, when the outside temperature is also obtained, step 130 can also include the calculation of a median and an average of the outside temperature T0.
[0035] Step 140 of process 100 involves training the model configured to predict the outlet temperature of combustion chamber T45. The model outputs the predicted outlet temperature of combustion chamber T45 and takes as input the rotational speed of the turbomachine's gas generator N1. Optionally, the model is also configured to take as input the outside temperature T0 and the turbomachine's cumulative flight hours. Model training includes modifying the model's internal parameters to minimize the difference between the predicted and measured outlet temperatures of combustion chamber T45. Step 140 is performed only with measurement data obtained when the aircraft cabin heater operating state 120 is off.Thus, the model is trained solely on measurement data taken when the aircraft cabin heating is off. The measured combustion chamber outlet temperature T45 is therefore used as a reference value to train the model to accurately predict the combustion chamber outlet temperature T45. The prediction of the combustion chamber outlet temperature T45 is obtained by providing the model with the rotational speed of the turbomachine's gas generator N1, and optionally the ambient temperature T0 and the turbomachine's cumulative flight hours.When step 130 has been carried out, the prediction of the combustion chamber outlet temperature T45 can be obtained by providing the model with the median and mean of the rotational speed of the gas generator N1 of the turbomachine and, optionally, the median and mean of the outside temperature T0 and the number of cumulative flight hours of the turbomachine.
[0036] In an example consistent with the previous examples, the model is one model among: a random forest model, a bagging model a K-neighbours model, a gradient boosting model, a polynomial regression model, or a linear regression model.
[0037] In a preferred example, the model is a polynomial regression model, or a linear regression model.
[0038] When the aircraft cabin heater is in its predetermined operating state and the model is being trained, steps 150 and 160 can be implemented. In other words, steps 150 and 160 can be implemented when the aircraft cabin heater is on and the model is being trained. The model can be considered trained when the difference between the predicted combustion chamber outlet temperature T45 and the measured combustion chamber outlet temperature T45 is less than a threshold difference for a set of test data. The threshold difference can be between 0 and 2 degrees Celsius. The test data can be a subset of the measurement data. Thus, a first subset of the measurement data can be used to train the model, and a second subset can be used to test the model to verify that it is being trained, i.e.the prediction of the outlet temperature of the T45 combustion chamber is sufficiently accurate.
[0039] In one example, consistent with the preceding examples, process 100 includes an optional step 150 for predicting the outlet temperature of combustion chamber T45. The prediction of the combustion chamber T45 outlet temperature is obtained by providing the trained model with the rotational speed of the turbomachine's gas generator N1, and optionally, the ambient temperature T0 and the turbomachine's cumulative flight hours. This data is not derived from the measurement data used to train the model. For example, this data could come from new measurements taken during a high-frequency calculation of EPC performance margins during a flight mission to monitor the turbomachine's health.When step 130 is implemented, the prediction of the combustion chamber outlet temperature T45 can be obtained by providing the model with the median and mean of the rotational speed of the gas generator N1 of the turbomachine and the median and, optionally, the mean of the outside temperature T0 and the number of cumulative flight hours of the turbomachine.
[0040] In one example, consistent with the preceding examples, process 100 includes a health monitoring step 160 that corrects the measured outlet temperature of combustion chamber T45 with the predicted outlet temperature of combustion chamber T45 (temperature without cabin heating). For example, the correction could consist of replacing the measured outlet temperature of combustion chamber T45 with the predicted outlet temperature of combustion chamber T45 without heating.
[0041] In an example consistent with the previous ones, the model is trained on the fly during stabilized flight phases of the twin-spool turbomachine aircraft for which health monitoring is performed; i.e., steps 150 and 160 are implemented. In this example, the model's accuracy is further increased in predicting the combustion chamber temperature T45, and therefore the turbomachine health monitoring is even more reliable.
[0042] Figure 3 illustrates an example of predicting the outlet temperature of combustion chamber T45 that can be obtained with process 100. In Figure 3, the vertical axis represents the outlet temperature of combustion chamber T45, and the horizontal axis represents time. Curve 301 represents the measured outlet temperature of combustion chamber T45, and curve 302 represents the predicted outlet temperature of combustion chamber T45 without heating that can be obtained with process 100. The periods during which the aircraft cabin heater is on are indicated by rectangle 303. Thus, it can be observed that when the aircraft cabin heater is off, curves 301 and 302 overlap most of the time, thereby illustrating the predicted outlet temperature of combustion chamber T45 without heating obtained with process 100.When the aircraft cabin heater is on, the measured outlet temperature of the T45 combustion chamber is on average 10 to 20 degrees Celsius higher than the predicted outlet temperature of the T45 combustion chamber without heating. This temperature difference is primarily due to the impact of the aircraft cabin heater on the measured outlet temperature of the T45 combustion chamber.
Claims
DEMANDS
1. A computer-implemented method (100) for training a model configured to predict an outlet temperature value of a T45 combustion chamber of a twin-spool turbomachine of an aircraft, the method comprising: - obtaining (110) measurement data, from measurements carried out during at least one stabilized flight phase of the aircraft, comprising: o a measured outlet temperature of the T45 combustion chamber of the turbomachine, and o a rotational speed of the N1 gas generator of the turbomachine, - determination (120) of the operating status of an aircraft cabin heater from the measured outlet temperature of combustion chamber T45 and the rotational speed of gas generator N1, and - when the determined state (120) of operation of the aircraft cabin heater is an off state, training (140) of the model including the modification of the internal parameters of the model in order to minimize a difference between a prediction of the outlet temperature of the combustion chamber T45 and the measured outlet temperature of the combustion chamber T45, the prediction of the outlet temperature of the combustion chamber T45 being obtained by providing the model with the rotational speed of the gas generator N1 of the turbomachine.
2. A method (100) according to claim 1 further comprising: - calculation (130) of a median and an average of the rotational speed of the gas generator N1 of the turbomachine, and wherein the prediction of the combustion chamber outlet temperature T45 is obtained by providing the model with the median and mean of the rotational speed of the gas generator N1 of the turbomachine.
3. Method (100) according to claim 1 or 2 wherein the model is driven and the method further comprises: - when the specified operating state (120) of the aircraft cabin heater is switched on: o prediction (150) of the outlet temperature of the combustion chamber T45 without heating, by providing the driven model with the rotational speed of the gas generator N1 of the turbomachine, and o health monitoring (160) by correcting the measured outlet temperature of the T45 combustion chamber with the predicted outlet temperature of the T45 combustion chamber without heating.
4. A method (100) according to any one of the preceding claims, wherein the determination (120) of the operating state of the aircraft cabin heater comprises: - detection of a change in the operating state of the aircraft cabin heater by comparing the evolution of the measured outlet temperature of combustion chamber T45 and the evolution of the rotational speed of gas generator N1 for the same measurement period in which: o When the measured outlet temperature of combustion chamber T45 increases and the rotational speed of gas generator N1 remains stable for the same measurement period, the operating state of the aircraft cabin heater is determined to change from "off" to "on"; o When the measured outlet temperature of combustion chamber T45 decreases and the rotational speed of gas generator N1 remains stable for the same measurement period, the operating state of the aircraft cabin heater is determined to change from "on" to "off". [Claims] A method (100) according to any one of the preceding claims, wherein: - obtaining (110) measurement data further includes obtaining an outside temperature T0 and a cumulative number of flight hours of the turbomachine, and - the outside temperature T0 and the number of cumulative flight hours of the turbomachine obtained (110) are also provided to the model to obtain the prediction of the combustion chamber outlet temperature T45 during training (140). [Claims] A method (100) according to claim 2 and the preceding claim wherein a median and mean of the outside temperature T0 is calculated (130) and the median and mean of the outside temperature T0 are also provided to the model to obtain the prediction of the combustion chamber outlet temperature T45 during the drive (140).
7. A method (100) according to claim 3 and any one of claims 5 or 6 wherein the outside temperature T0 and the number of cumulative flight hours of the turbomachine are further supplied to the model during the prediction (150) of the combustion chamber outlet temperature T45 without heating.
8. A method (100) according to any one of claims 5 to 7, wherein the determination (120) of the operating state of the aircraft cabin heater comprises: - Determination of an initial operating state of the aircraft cabin heating system as a function of the outside temperature T0 in which: o when the outside temperature T0 is less than or equal to a predetermined threshold temperature, the initial operating state of the aircraft cabin heater is determined to be on, and o when the outside temperature T0 is above the predetermined threshold temperature, the initial operating state of the aircraft cabin heater is determined to be off. [Claims] Method (100) according to any one of the preceding claims wherein the model is a polynomial regression model or a linear regression model.
10. Health monitoring device comprising: - a set of sensors adapted to measure the outlet temperature of a T45 combustion chamber of an aircraft turbomachine, the rotational speed of an N1 gas generator of the turbomachine, and - a computer configured to implement the method (100) according to one of the preceding claims.
11. Health monitoring device wherein the sensor set is further adapted to measure an outside temperature T0 and a cumulative number of turbomachine flight hours.
12. Aircraft comprising the health monitoring device according to claim 10 or 11.
13. A computer program comprising instructions which, when the program is executed on a computer, cause the computer to carry out the steps of the method (100) according to any one of claims 1 to 9.
14. A computer-readable recording medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the process (100) according to any one of claims 1 to 9.