Method for monitoring temperature of brake of landing gear of aircraft

Abstract

The invention relates to a method for monitoring the temperature of a brake of a landing gear of an aircraft. An apparatus for monitoring a maximum temperature reached by a brake of a landing gear of an aircraft during landing is disclosed. The monitoring device uses the predictive model to estimate (102) a maximum temperature reached by the brake during landing. An error between the estimated maximum temperature and the measured maximum temperature is then determined (103). Generating (106) a warning message if the error between the estimated maximum temperature and the measured maximum temperature is greater than a first predefined threshold S1 when the measured maximum temperature is greater than the estimated maximum temperature, or is greater than a second predefined threshold S2 when the measured maximum temperature is less than the estimated maximum temperature, and if the total number of errors is greater than a third predefined threshold S3, and thus, the attention of flight crew and / or ground crew is aroused. Therefore, the maintenance action of the landing gear component can be anticipated.

Description

Technical Field

[0001] The present invention relates to a method and apparatus for monitoring the temperature of brakes of a landing gear of an aircraft, such as a main landing gear (MLG). More specifically, the present invention relates to detecting, for each brake of a given landing gear, the difference between an estimated maximum temperature of the brake and a measured actual maximum temperature of said brake. Background Art

[0002] The main function of the landing gear is to allow the aircraft to move on the ground. In particular, the landing gear makes it possible to: move between different places in the airport (i.e. towing, taxiing, etc.), perform the take-off taxi, cushion the impact of landing, and stop the aircraft within an acceptable distance with the help of the associated braking system.

[0003] Typically, each wheel of the landing gear is equipped with a braking system (which in particular comprises brakes) and a temperature sensor located on or near these brakes. When the brakes of the landing gear are activated, the temperature of the brakes rises. Therefore, the temperature sensor measures the temperature of each brake individually and then transmits these measurements to the corresponding brake temperature monitoring unit located in the landing gear. In one example, the landing gear comprises four wheels and therefore four brakes and therefore four associated monitoring units. Each monitoring unit then transmits the brake temperature data to a brake and steering control unit that is integrated into the avionics system of the aircraft.

[0004] Before takeoff, in order to ensure safe operation of the aircraft and to avoid degradation of its performance, the brakes must not exceed a limit temperature (eg greater than 400° C.) This may involve, for example, preventing the brakes from heating to a temperature above their safe operating range.

[0005] The brake and steering control unit monitors the temperature changes of the brakes during a given landing, and also monitors the temperature changes of the brakes over a predefined time period where multiple landings have occurred.

[0006] Thus, after landing, when the temperature of at least one of the brakes of the landing gear is greater than a predefined threshold, the brake and steering control unit transmits a warning message via the man-machine interface of the electronic centralized aircraft monitor (ECAM) to draw the attention of the crew in case of abnormal behavior of the brakes. For example, if the temperature of the brakes is greater than 100° C., a message appears on the man-machine interface of the ECAM indicating that the aircraft can take off. If the temperature exceeds 300° C., a message appears on the man-machine interface of the ECAM indicating that take-off must be delayed to allow the brakes to cool.

[0007] In another example, the brake and steering control unit makes it possible to detect any asymmetry in the temperature of the brakes of a given landing gear. The asymmetry may be the result of an abnormal braking condition such as oxidation of the brake linings, residual braking or brake loosening. Therefore, if the temperature asymmetry between the brakes reaches a predefined maintenance threshold denoted S (e.g. 150° C.), a warning message generated by the brake and steering control unit and then transmitted to, for example, the ECAM indicates that a maintenance action or check is required (e.g. brake repair, brake replacement, etc.).

[0008] However, with this technique, it is difficult to accurately identify which brake of the landing gear or which other equipment of the landing gear (e.g., wheel, brake system equipment, etc.) is creating a temperature asymmetry between the brakes and requires maintenance action or inspection (e.g., repair, replacement, etc.).

[0009] In particular, an abnormally high maximum temperature of one brake may influence the value of the maximum temperature of another brake of the landing gear.

[0010] It would therefore be desirable to alleviate these shortcomings of the prior art.

[0011] It is particularly desirable to provide a solution that allows to monitor individually the maximum temperature of each brake of a given landing gear over time and therefore allows to anticipate whether to perform maintenance actions on the brakes or any other equipment of the landing gear (e.g.: wheels, sensors, etc.). Furthermore, it is also desirable to provide a solution that allows to accurately identify which brake or which other equipment of the landing gear (e.g.: wheels, sensors, etc.) requires maintenance actions or inspections. Summary of the invention

[0012] A method for monitoring the maximum temperature reached by the brakes of the landing gear of an aircraft during landing is provided. The method is implemented by a monitoring device. The method comprises:

[0013] The phase of using the prediction model to predict the maximum temperature reached by the brakes during landing includes the following steps

[0014] - obtaining a current set of values ​​of a plurality of braking parameters for the current landing;

[0015] - estimating, by means of a prediction model, the maximum temperature that the brakes will reach during landing based on the values ​​of the current set.

[0016] The method further comprises a comparison phase, the comparison phase comprising:

[0017] - obtain the maximum measured temperature reached by the brakes during the current landing;

[0018] - determining whether the error between the estimated maximum temperature and the measured maximum temperature is greater than a first predefined threshold S1 when the measured maximum temperature is greater than the estimated maximum temperature, or greater than a second predefined threshold S2 when the measured maximum temperature is less than the estimated maximum temperature;

[0019] - when the error is greater than the first predefined threshold S1 or the second predefined threshold S2, determining whether the total number of errors in the landing set including the N landings in the sliding window and the current landing is greater than a third predefined threshold S3, otherwise repeating the phase of using the prediction model and the comparison phase for subsequent landings;

[0020] - When the total number of errors is greater than a third predefined threshold S3, a warning message is generated, otherwise the phases of using the prediction model and of comparing are repeated for subsequent landings.

[0021] Thus, it is possible to monitor the temperature of each brake of the landing gear independently, at each wheel landing. Then, when a large difference is observed between the measured temperature and the estimated temperature of the analyzed brake, a warning is generated, which makes it possible to anticipate maintenance operations on the different elements of the landing gear.

[0022] According to a particular embodiment, prior to the stage of using the prediction model, the method comprises a stage of training the machine learning model, the training stage consisting in associating a set of reference values ​​of brake parameters obtained for each landing in a set of reference landings with reference maximum temperature values ​​reached by the brakes of the landing gear during the landing in question.

[0023] In a particular embodiment, estimating the maximum temperature reached by the brake for the current landing based on the values ​​of the current set of brake parameters further comprises calculating a weighted sum between the estimated maximum temperature of the brake and an estimated maximum temperature of another brake of the landing gear.

[0024] In a particular embodiment, the method further comprises determining a composite estimated temperature equal to a weighted sum of a moving average of an estimated maximum temperature of the brake over a sliding window of N landings and a measured temperature of the other brake of the landing gear.

[0025] In one particular embodiment, the error between the estimated maximum temperature and the measured maximum temperature is calculated by taking a weighted sum of a mean absolute error between a moving average of the maximum temperature reached by the brakes over a sliding window of N landings and the synthetic estimated temperature and a symmetric mean absolute percentage error between a moving average of the maximum temperature reached by the brakes over a sliding window of N landings and the synthetic estimated temperature.

[0026] In a particular embodiment, the braking parameter is one or more of: braking energy, maximum braking power, duration of activation of the brake fan, duration of thrust reversal of the engines, duration of landing, initial temperature of the brakes, length of time between the time when the maximum brake temperature is reached and the time when the rotational speed of the wheels reaches the 95th percentile value, static air temperature, average ground speed, maximum ground speed, sum of currents applied by the servovalves of the braking system, average altitude, manufacturer serial number of the aircraft, identifier of the engine type of the aircraft, identifier of the model of the aircraft.

[0027] In one particular embodiment, the warning message contains an indication that a maintenance action or inspection has to be performed on the brake, and an indication of the type of maintenance action or inspection to be performed.

[0028] In a specific embodiment, the method further comprises configuring the warning message such that the warning message indicates:

[0029] - information about a first type of problem and about a first type of maintenance action or check to be performed that is suitable for the first type of problem, when the measured maximum temperature is greater than the estimated maximum temperature and when the error between the estimated maximum temperature and the measured maximum temperature is greater than a first predefined threshold S1; or

[0030] - Information about a second type of problem and about a second type of maintenance action or inspection to be performed that is suitable for the second type of problem, when the measured maximum temperature is less than the estimated maximum temperature and when the error between the estimated maximum temperature and the measured maximum temperature is greater than a second predefined threshold S2.

[0031] A device for monitoring the maximum temperature reached by the brakes of the landing gear of an aircraft during landing is also provided. The monitoring device includes an electronic circuit system configured to implement:

[0032] The prediction model is used to predict the stage at which the maximum temperature reached by the brakes during landing. This stage of use includes the following steps:

[0033] - obtaining a current set of values ​​of a plurality of braking parameters for the current landing;

[0034] - estimating, by means of a prediction model, the maximum temperature that the brakes will reach during landing based on the values ​​of the current set;

[0035] The comparison phase includes:

[0036] - obtain the maximum measured temperature reached by the brakes during the current landing;

[0037] - determining whether the error between the estimated maximum temperature and the measured maximum temperature is greater than a first predefined threshold S1 when the measured maximum temperature is greater than the estimated maximum temperature, or greater than a second predefined threshold S2 when the measured maximum temperature is less than the estimated maximum temperature;

[0038] - when the error is greater than the first predefined threshold S1 or the second predefined threshold S2, determining whether the total number of errors in the landing set including the N landings in the sliding window and the current landing is greater than a third predefined threshold S3, otherwise repeating the phase of using the prediction model and the comparison phase for subsequent landings;

[0039] - When the total number of errors is greater than a third predefined threshold S3, a warning message is generated, otherwise the phases of using the prediction model and of comparing are repeated for subsequent landings.

[0040] An aircraft is also provided herein, comprising the monitoring device according to one embodiment as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and other characteristics of the invention will become more apparent after reading the following description of at least one example of embodiment, which description is given with reference to the accompanying drawings, in which:

[0042] [ Figure 1 ] The steps of a method for monitoring the maximum temperature of the brakes of the landing gear of an aircraft during landing according to one embodiment are shown in the form of a flow chart;

[0043] [ Figure 2 ] shows in the form of a flow chart the preliminary steps for characterizing braking parameters according to one embodiment;

[0044] [ Figure 3 ] shows in the form of a graph an example of the results obtained after implementing a method for monitoring the maximum temperature of the brakes of the landing gear of an aircraft during landing according to one embodiment;

[0045] [ Figure 4 ] shows in the form of a graph another example of the results obtained after implementing a method for monitoring the maximum temperature of brakes of a landing gear of an aircraft during landing according to one embodiment;

[0046] [ Figure 5 ] schematically illustrates an example of a hardware architecture of a monitoring device according to an embodiment; and

[0047] [ Figure 6 ] schematically shows a side view of an aircraft equipped with a monitoring device according to one embodiment. DETAILED DESCRIPTION

[0048] The general principle of the invention involves monitoring, independently of one another, the maximum temperature reached by each brake of a given landing gear (e.g., main landing gear) of an aircraft during its activation. More specifically, what is monitored for each brake of the landing gear during its activation is the difference or error between the so-called "estimated" maximum temperature of the brake and the so-called "actual" or "measured" maximum temperature.

[0049] In the following, for the purpose of illustrating the method described hereinafter, it will be considered that the application of the brakes has occurred during landing of the aircraft. It will be noted that the application of the brakes of the landing gear of the aircraft may also occur during taxiing or, in an emergency, during the take-off phase of the aircraft.

[0050] Hereinafter, the term "landing" or "landing phase" should be understood to mean the period of time extending from the time the aircraft touches the ground (i.e., the 8th flight phase) to the time the aircraft's engines are shut down (i.e., the 10th flight phase). In one embodiment, a margin is allowed before the 8th flight phase (e.g., 1 minute) and / or a margin is allowed after the 10th flight phase (e.g., 10 minutes) to ensure that the landing is fully covered.

[0051] The estimated maximum temperature is obtained by using, by a monitoring device denoted DISP, a model for predicting the maximum temperature reached by the brakes during a landing (hereinafter also referred to simply as prediction model). More specifically, this prediction model is implemented in a machine learning module (e.g. an artificial intelligence algorithm) of the monitoring device DISP. In order to obtain this prediction model, the machine learning module is trained (training phase) to associate the value of a parameter called "brake parameter" with the maximum temperature reached by each brake of the landing gear, as measured during a reference landing set. At the end of this training phase, the prediction model is used (use phase) to estimate the maximum temperature of each brake of the landing gear based on the new value of the brake parameter obtained for a new landing, which makes it possible to compare the maximum temperature thus estimated with the value of the maximum temperature actually measured during this new landing.

[0052] In the following, the term "brake parameters" is understood to mean parameters capable of influencing the temperature of the brakes during landing of the aircraft (i.e. increasing the temperature of the brakes during landing, or decreasing the temperature of the brakes). In one example, these brake parameters are: brake pressure, static air temperature, wind speed and direction, vertical acceleration, duration of application of reverse engine thrust, alternating brake pressure, duration of activation of the anti-skid system, duration of activation of the brake fan, duration of landing, gross weight of the aircraft, braking energy, rotation speed of the wheels of the landing gear during landing, etc.

[0053] With the help of the prediction model, it is possible to estimate individually for each landing the maximum temperature reached by each brake of the landing gear in so-called “nominal” landing conditions for a given type of aircraft (ie normal landing conditions of the aircraft assuming that the brakes require no maintenance actions or inspections).

[0054] Thus, for the landing in question, the estimated maximum temperature of each brake can be compared with the actual maximum temperature of the brake measured during the landing. Depending on the difference or error between the estimated maximum temperature and the measured maximum temperature, the monitoring device DISP generates a warning message in order to inform the crew (for example, via the human-machine interface of the ECAM) and / or the ground staff via air-ground communication that it is necessary to perform maintenance and / or inspection on one of the brakes of the landing gear and / or other equipment (for example: wheels, sensors, etc.).

[0055] Figure 1 The steps of a method for monitoring the maximum temperature reached by the brakes of a landing gear during landing according to one embodiment are presented in the form of a flow chart. This method for monitoring the maximum temperature of the brakes is implemented in a monitoring device DISP, which is for example referred to below in Figure 5 As described.

[0056] The monitoring device DISP comprises an electronic circuit system which is particularly configured to collect in real time from one or more sensors (e.g. temperature sensors) and / or information systems (e.g. a brake and steering control unit (BSCU) or an air data computer (ADC)) of the aircraft information about: the temperature of each brake of the landing gear of the aircraft (including the initial temperature of the brakes at the beginning of the landing phase), and braking parameters (e.g. the duration of activation of the brake fan, the duration of thrust reversal of the engines, etc.).

[0057] During a preliminary step (not shown), these braking parameters are characterized. These braking parameters will then be used in the phase of training the machine learning module and in the phase of using the prediction model.

[0058] It will be noted that, in a particular embodiment, the braking parameters can be classified according to their influence on the temperature of the brakes during landing. In particular, some braking parameters influence the temperature of the brakes to a greater extent than others. Therefore, in order to limit the amount of data, among the previously identified braking parameters, only those braking parameters that have a greater influence on the temperature of the brakes during landing will be used in the phases of training the machine learning module and of using the prediction model.

[0059] therefore, Figure 2 The preliminary steps for characterizing braking parameters according to one embodiment are presented in the form of a flow chart.

[0060] During sub-step 201COL_ST, data on braking parameters are obtained from one or more sensors and / or information systems (such as ADC) of the aircraft. This data collection is performed over a predefined time period corresponding to a flight window characteristic of the landing phase of the aircraft as defined above. Furthermore, this data collection is performed at a predefined sampling rate for each braking parameter. In particular, the sampling rate of the braking parameter depends on the recording frequency of the sensor or system in question, for example 2 Hz.

[0061] Thus, for a period of time corresponding to the landing phase of the aircraft, a time series of values ​​of each braking parameter is obtained.

[0062] In order to simplify the prediction model, during the sub-step 202EXT_V, the time series of these values ​​are processed to extract the characteristic value of the brake parameter. In other words, a single characteristic value of the brake parameter is extracted, instead of considering the variation of the value of this brake parameter from the beginning to the end of the time series. For example, the maximum temperature of the brake at landing can be extracted by the characteristic value from the time series of values ​​corresponding to the temperature variation of the brake throughout the landing phase. In general, the characteristic value is extracted from the time series to be used as input data of the prediction model.

[0063] Therefore, it is possible to characterize the brake parameters used to estimate the maximum temperature of these brakes during sub-step 203 ID_PC.

[0064] Thus, at the end of the preliminary step, the braking parameters are characterized so as to be able to be used for training the machine learning module. Thus, during the phase of using the prediction model, the estimation of the maximum temperature reached by the brakes during the landing phase takes into account these different braking parameters that affect the temperature of the brakes during the landing phase. Thus, the prediction model is trained and then used based on characteristic input data (or values) of the braking parameters to estimate the maximum temperature of the brakes during the landing phase.

[0065] Thus, during a step 101PHS_E corresponding to the phase of training a machine learning module to obtain a prediction model, a prediction model is trained to associate characteristic values ​​of braking parameters with the maximum measured temperature reached for each landing in the landing set, as a reference. This machine learning model is implemented, for example, by the artificial intelligence module MOD 506 of the monitoring device DISP.

[0066] To this end, the monitoring device DISP obtains, from one or more sensors and / or information systems of the aircraft (e.g. ADC), for each landing in a set of landings of so-called “reference” landings, characteristic values ​​of the braking parameters and of the maximum temperature reached by the brakes during each landing in the set of reference landings. The term “reference landing” is understood to mean a landing for which the values ​​of the braking parameters and of the maximum temperature reached by the brakes during the landing are standard values ​​used as reference, which are approved and correspond to a large number of measurement results.

[0067] It will be noted that the machine learning model is trained for each brake of the landing gear independently from the other brakes. In particular, a brake may have a tendency to behave differently depending on its side, etc. This is why the machine learning model is trained for each brake independently and for each aircraft.

[0068] Furthermore, all braking parameters identified during the preparation phase must be available for the flight to be considered valid for consideration by the machine learning model. In the opposite case, the flight is considered invalid and the landing data is not considered when training the machine learning model and then when using the prediction model.

[0069] The monitoring device DISP thus obtains, for each brake of the landing gear and for each landing in the reference landing set, reference characteristic values ​​of:

[0070] (i) braking parameters, such as: braking energy and maximum braking power, duration of activation of the brake fan, duration of thrust reversal of the engines; duration of landing, which duration corresponds to the length of time between the time of reaching the maximum rotational speed of the wheels associated with the brakes and the time of reaching the maximum temperature of the brakes; initial temperature of the brakes, which corresponds to the average of the brake temperature values ​​obtained during a predefined time interval corresponding to the beginning of the landing phase; length of time between the time of reaching the maximum brake temperature and the time when the rotational speed of the wheels reaches the 95th percentile value; static air temperature; average ground speed; maximum ground speed value; sum of the currents applied by the servovalves acting as hydraulic members controlling the braking system; average altitude (i.e. the average altitude relative to the sea level during the landing phase); manufacturer serial number (MSN) of the aircraft; identifier of the aircraft's engine type (each engine in particular has a different thrust reversal power); identifier of the aircraft's model (for example, each aircraft model has different aerodynamic characteristics);

[0071] (ii) The maximum brake temperature reached during landing. It will be noted that if the maximum temperature is less than the predefined minimum temperature, or if the maximum temperature is greater than the predefined maximum temperature, the flight is considered invalid and the data is not considered when training the machine learning model.

[0072] Reference characteristic values ​​of these braking parameters as well as the maximum temperature of the brake are then used as input data to train the machine learning model and thus obtain a predictive model.

[0073] In one embodiment, these input data are used to train a stacked regression machine learning algorithm. Specifically, this type of machine learning algorithm performs well, with a mean absolute error of about 15°C (about 7%). This is an ensemble method that combines multiple models and includes stacking the results of each estimator and using the regressor to calculate the final prediction.

[0074] Therefore, the machine learning model is trained based on the reference characteristic values ​​of the brake parameters and based on the maximum temperature of the brakes in the reference landing set to obtain a prediction model. The prediction model is then used in the use phase to estimate the maximum temperature of each brake for a new landing i (which is an integer greater than 0).

[0075] Thus, during the phase (denoted PHS_UT) in which the monitoring device DISP uses the prediction model, the monitoring device DISP obtains, via its artificial intelligence module MOD 506, for a new landing i (in the same way as in the training phase described above), the values ​​of the braking parameters and the maximum temperature reached by each brake of the landing gear.

[0076] The monitoring device DISP estimates, via a prediction model, for this new landing i the maximum temperature reached by each brake of the landing gear during a step 102 EST_TEMP, based on the above-mentioned braking parameters.

[0077] However, in order to enhance the estimation of the maximum temperature reached by the brakes and reduce the risk of over-adjustment, the maximum brake temperature estimated for the brakes is calculated by taking a weighted sum of the two prediction models for a pair of brakes of the same landing gear. For a given pair of brakes of the landing gear, the weighting factors then define the weight of each brake in the estimation of the maximum brake temperature. In other words, for the analyzed brake X, the estimated maximum temperature takes into account the maximum estimated temperature estimated via the prediction model for another brake Y of the same landing gear.

[0078] Once the maximum temperature has been estimated using the prediction model, the monitoring device DISP implements a phase of comparison of the estimated temperature with the measured temperature, this comparison phase comprising steps 103 to 106 described below.

[0079] During a step 103 COMP_TEMP, the monitoring device DISP compares, for each brake, the maximum temperature estimated using the prediction model with the maximum temperature measured in real time during landing i.

[0080] More specifically, the monitoring device DISP determines, for landing i, a difference or error between the estimated maximum temperature and the measured maximum temperature. To this end, the monitoring device DISP determines: a moving average of the estimated maximum temperature of the analyzed brake (for example, brake X) over a sliding window of N landings (N being an integer greater than 0), a moving average of the maximum temperature reached by the analyzed brake over a sliding window of N landings, a measured maximum brake temperature of another brake of the same landing gear (of a brake pair comprising the analyzed brake and another brake (for example, brake Y)), in order to limit the difference between the estimated maximum brake temperature and the measured maximum brake temperature of another brake of the same landing gear.

[0081] It will be noted that the maximum brake temperature measured for the other brake is obtained based on a moving average of the estimated maximum temperature of the brake analyzed, a moving average of the maximum temperatures reached by the other brake over a sliding window of N landings, and a parameter that makes it possible to limit the influence of the actual temperature measured for the other brake on the error calculation. Without this parameter limiting the actual temperature measured for the other brake, the error would be very high, but only because of the difference between the estimated temperature of the brake analyzed and the measured temperature of the other brake.

[0082] It will be noted that, for a given aircraft and a given brake, the sliding window of N landings corresponds to a fixed number of N landings preceding the current landing i. In other words, for each new flight, the last N flights are considered in a sliding manner, i.e. for flight i+1, flight i is added to the sliding window of N landings and the oldest flight is removed from this sliding window.

[0083] Next, according to a particular embodiment, the monitoring device DISP determines a synthetic estimated temperature by taking the weighted sum of the moving average of the estimated maximum temperature of brake X and the measured maximum brake temperature of brake Y of the same landing gear. The weighting factor corresponds to the proportional influence of brake Y on the estimated maximum brake temperature. Based on the moving average of the estimated maximum temperature of the analyzed brakes and the synthetic estimated temperature, the monitoring device DISP determines the mean absolute error (MAE) of the difference between the actual value and the synthetic estimated value, as well as the symmetric mean absolute percentage error (SMAPE).

[0084] Finally, the monitoring device DISP determines the error between the estimated temperature and the measured temperature by taking the weighted sum of the mean absolute error (MAE) and the symmetric mean absolute percentage error (SMAPE), where the weighting factor is the ratio of the absolute error to the relative error. The absolute error helps detect abnormally high temperatures, while the relative error helps detect abnormally low temperatures.

[0085] The monitoring device DISP then applies a strategy for detecting braking anomalies based on the error between the measured maximum temperature and the estimated maximum temperature of the analyzed brake.

[0086] Therefore, during step 104 DET_ER, based on the calculation of this error, or based on the difference between the estimated maximum temperature of the brakes analyzed for a given landing of the current flight i and the measured maximum temperature, the monitoring means DISP determine whether this error is greater than:

[0087] - a first predefined threshold S1, when the measured maximum temperature is greater than the estimated maximum temperature;

[0088] - A second predefined threshold S2, when the measured maximum temperature is less than the estimated maximum temperature.

[0089] Thus, different categories of problems with the brakes (or other equipment of the landing gear) can be detected, since a measured maximum temperature that is too high (i.e., the measured maximum temperature is greater than the estimated maximum temperature) and a measured maximum temperature that is too low (i.e., the measured maximum temperature is less than the estimated maximum temperature) indicate different problems. To remedy these problems, a maintenance action or maintenance inspection action specific to each problem is typically applied.

[0090] In one example, when there is substantial brake wear or piston friction, the brake in question will tend to heat up more than expected (i.e., the measured maximum temperature is greater than the estimated maximum temperature). In another example, when a servo valve or pressure sensor fails, the maximum brake temperature may be less than expected (i.e., the measured maximum temperature is less than the estimated maximum temperature).

[0091] In another example, a measured maximum temperature that is less than or greater than the estimated maximum temperature may indicate that the brake temperature sensor is indicating an abnormally very low or conversely very high temperature (eg, drift).

[0092] If the measured temperature is greater than the predefined threshold S1 or the predefined threshold S2, then during step 105DET_NER, the monitoring device DISP determines whether the total number of times (expressed as NT) when the error was greater than the predefined threshold S1 or S2 (as the case may be) during the landing set including the previous N flights of the sliding window and the current flight i is greater than a third predefined threshold S3.

[0093] Therefore, when the number NT is greater than the third predefined threshold S3, the monitoring device DISP generates a warning message during step 106G_MSG to draw the attention of the crew and / or ground staff.

[0094] - if the measured maximum temperature of the brake in question is abnormally high, i.e. if the number of times NT that the measured temperature of the brake is greater than the estimated maximum temperature plus a predefined threshold S1 (e.g. 60° C.) exceeds a predefined threshold S3, a warning message is generated for the brake;

[0095] If the measured maximum temperature of the brake in question is abnormally low, ie if the number NT when the measured temperature of the brake is less than the estimated maximum temperature minus a predefined threshold S2 (eg: 60° C.) exceeds a predefined threshold S3, a warning message is generated for the brake.

[0096] This warning message is transmitted to ECAM for display on its man-machine interface, for example, to attract the attention of the crew. Alternatively or additionally, the warning message is transmitted to the ground control system for display on the man-machine interface, for attracting the attention of the ground crew.

[0097] In one embodiment, the warning message is a text message indicating that the brake identified in the warning message, for example by means of an identifier, has an abnormally high or low temperature and requires maintenance action or inspection. In one embodiment, the warning message further contains an indication of the type of maintenance or inspection to be performed.

[0098] In one embodiment, the warning message is configured to reflect the different situations described below (i.e., different messages depend on the situation encountered). Specifically, the warning message of this configuration includes:

[0099] - information about a first type of problem and about a first type of maintenance action or check to be performed that is suitable for the first type of problem, when the measured maximum temperature is greater than the estimated maximum temperature and when the error between the estimated maximum temperature and the measured maximum temperature is greater than a first predefined threshold S1; or

[0100] - Information about a second type of problem and about a second type of maintenance action or inspection to be performed that is suitable for the second type of problem, when the measured maximum temperature is less than the estimated maximum temperature and when the error between the estimated maximum temperature and the measured maximum temperature is greater than a second predefined threshold S2.

[0101] In one example, when the error between the estimated maximum temperature and the measured maximum temperature is greater than a first predefined threshold S1, when the measured maximum temperature is greater than the estimated maximum temperature, the warning message indicates that there is significant brake wear or piston friction, or there is a problem with the temperature sensor, and action needs to be taken to replace or inspect this equipment.

[0102] In one example, when the error between the estimated maximum temperature and the measured maximum temperature is greater than a second predefined threshold S2, or when the measured maximum temperature is less than the estimated maximum temperature, a warning message indicates that there is a problem with the servo valve or temperature sensor of the braking system, and action needs to be taken to repair or check the servo valve or temperature sensor.

[0103] Only one warning message for each brake and each landing gear is triggered at a time to avoid generating multiple warnings for the same problem. An abnormality of one brake (especially in the case of a brake whose temperature is lower than the estimated temperature) may have an impact on the normal braking behavior of another brake of the same landing gear.

[0104] Figure 3 An example of a result obtained after implementing a monitoring method according to an embodiment is shown in the form of a graph.

[0105] In this example, the estimated average maximum values ​​of the temperatures of brakes numbered 3 and 4 (respectively denoted Temp_est_3 and Temp_est_4) and the actual measured values ​​of the temperatures of brakes 3 and 4 (respectively denoted Temp_mes_3 and Temp_mes_4) have been shown for the same aircraft and the same landing gear (see Figure 3 ).

[0106] The mean errors between the estimated and measured maximum temperatures for brakes 3 and 4 (denoted Err_mean_3 and Err_mean_4, respectively) have also been shown (see Figure 3 ).

[0107] In addition to the temperature asymmetry between brakes 3 and 4 , the prediction model accurately estimates the maximum temperature (COMP_N) of brakes 3 and 4 .

[0108] By using the above-mentioned prediction model, the monitoring device DISP is able to anticipate, for each brake of the landing gear independently, the temperature asymmetry between the estimated maximum temperature and the measured maximum temperature and is therefore able to accurately identify which brake requires maintenance action or inspection.

[0109] The temperature error or difference between the estimated maximum temperature and the measured maximum temperature of the brakes 4 continues to increase (ASY) until a warning message is generated. In other words, when the measured maximum temperature is greater than the estimated maximum temperature by a predefined threshold S1 (for example 60° C.) more times than a predefined threshold S3 during a plurality of landings, the monitoring device DISP generates a warning message.

[0110] In contrast, the temperature error or difference between the estimated maximum temperature and the measured maximum temperature for the brake 3 is small, ie, smaller than a predefined threshold value S1 .

[0111] The monitoring device DISP is therefore able to detect exactly which brake requires a maintenance action or inspection. In this example, brake 4 is the brake requiring a maintenance action or maintenance inspection.

[0112] After a maintenance action or inspection has been performed, the error or difference between the estimated maximum temperature and the measured maximum temperature tends to a low value (COMP_N).

[0113] Figure 4 Another example of results obtained after implementing the monitoring method according to one embodiment is shown in the form of a graph.

[0114] Prior to the maintenance action (ASY), the measured temperature of brake 1 tended to be greater than the estimated maximum temperature of the brake. This could be the effect of oxidation on the brakes, causing brake 1 to heat more than expected. After replacing these brakes (COMP_N), the prediction model accurately predicted the maximum brake temperature at each landing, which corresponded to the maximum temperature under nominal conditions.

[0115] Therefore, the monitoring device DISP can detect most events leading to temperature asymmetry between the estimated maximum temperature and the measured maximum temperature with a confidence level of 100% by using the prediction model.

[0116] The monitoring device DISP can also detect faults that require maintenance via predictive models, such as brake wear, wheel friction and sensor problems. For example, it can detect:

[0117] - Brake wear or wheel friction;

[0118] -Sensor problem;

[0119] - Abnormally cold brake conditions, for example associated with a faulty servo valve or pressure sensor.

[0120] Figure 5 An example of a hardware architecture of a monitoring device DISP is schematically shown, which comprises the following items connected via a communication bus 510: a central processing unit CPU 501; a random access memory RAM 502; a read-only memory ROM 503, such as a flash memory; a data storage device, such as a hard disk drive HDD or a storage medium reader, such as a SD card (SD stands for Secure Digital) reader 504; and at least one communication interface 505, which allows the monitoring device DISP to interact with different sensors and / or avionics systems.

[0121] The processor 501 can execute instructions loaded from the memory ROM 503, from an external memory (not shown), from a storage medium (such as an SD card), or from a communication network (not shown) into the memory RAM 502. When the monitoring device DISP is powered on, the processor 501 can read instructions from the memory RAM 502 and can execute these instructions. These instructions form a computer program that enables the processor 501 to implement the behaviors, steps and algorithms described herein.

[0122] In one embodiment, the monitoring device DISP further comprises an artificial intelligence module MOD 506 configured to implement a machine learning model during a training phase PHS_E and then use a predictive model during a usage phase PHS_UT as described herein.

[0123] In a variant, the monitoring device DISP comprises an artificial intelligence module MOD 506 configured to use the prediction model during the use phase PHS_UT as described herein. This artificial intelligence module MOD 506 was previously trained during a training phase PHS_E in a device different from the monitoring device DISP.

[0124] Therefore, all or some of the behaviors, steps and algorithms described herein can be implemented in software form by executing a set of instructions with the help of a programmable machine (e.g., a digital signal processor (DSP) or a microcontroller), or can be implemented in hardware form with the help of a machine or a dedicated chip or chipset (e.g., a field programmable gate array (FPGA) or an application specific circuit (ASIC)). Generally, the monitoring device DISP includes an electronic circuit system arranged and configured to implement the behaviors, steps and algorithms described herein.

[0125] In one example of an embodiment, the monitoring device DISP may be implemented in parallel with the BTMS to provide enhanced functionality and / or redundancy.

[0126] In one example of an embodiment, the monitoring device DISP may be integrated into the reference Figure 6 The monitoring device DISP may be integrated into the avionics system of the aircraft 600 described, or may be connected to the avionics system in any suitable manner, so that the monitoring device DISP may communicate the estimated brake temperature value to the avionics system of the aircraft 600. For example, the monitoring device DISP may be integrated into a controller of the BTMS of the aircraft 600 or connected to the controller.

[0127] Figure 6 Schematically, a side view of an aircraft 600 equipped with a monitoring device DISP 601 according to one embodiment is shown. Figure 6In the exemplary embodiment, the monitoring device DISP 601 belongs to the avionics system of the aircraft 600 .

[0128] In other examples, the monitoring device DISP may be completely independent of any onboard system of the aircraft 600. In these examples, the monitoring device DISP may form part of an off-board system (such as a portable maintenance device) that may or may not be able to communicate with the onboard systems of the aircraft 600, or the monitoring device may include a separate on-board system. In these examples, the monitoring device DISP is equipped with suitable means for receiving control commands and / or for delivering the estimated temperature value, such as a display or a user interface.

Claims

1. A method for monitoring the maximum temperature reached by the brakes of an aircraft landing gear during landing, the method being implemented by a monitoring device (DISP), the method comprising: The use of a prediction model to predict the maximum temperature reached by the brakes during landing (PHS_UT) comprises the following steps: - obtaining a current set of values ​​of a plurality of braking parameters for the current landing; - estimating (102) the maximum temperature that the brakes will reach during landing based on the values ​​of the current set by means of the prediction model; The method further comprises a comparison phase, the comparison phase comprising: - obtaining the measured maximum temperature reached by said brakes during said current landing; - determining (104) whether an error between the estimated maximum temperature and the measured maximum temperature is greater than a first predefined threshold value S1 when the measured maximum temperature is greater than the estimated maximum temperature, or greater than a second predefined threshold value S2 when the measured maximum temperature is less than the estimated maximum temperature; - when the error is greater than the first predefined threshold S1 or the second predefined threshold S2, determining (105) whether the total number of errors (NT) in a landing set including the N landings in the sliding window and the current landing is greater than a third predefined threshold S3, otherwise repeating the phase of using the prediction model and the phase of comparison for subsequent landings; - When the total number of errors (NT) is greater than the third predefined threshold S3, a warning message is generated (106), otherwise the phase of using the prediction model (PHS_UT) and the phase of comparison are repeated for a subsequent landing.

2. The method according to claim 1, further comprising before the stage (PHS_UT) of using the prediction model: A phase of training a machine learning model (PHS_E), the training phase consisting of associating a set of reference values ​​of brake parameters obtained for each landing in a set of reference landings with reference maximum temperature values ​​reached by the brakes of the landing gear during the landing in question.

3. The monitoring method according to claim 1 or 2, wherein: Estimating a maximum temperature reached by the brake for the current landing based on the values ​​of the current set of braking parameters further comprises calculating a weighted sum between the estimated maximum temperature of the brake and an estimated maximum temperature of another brake of the landing gear.

4. The monitoring method according to claim 3, further comprising determining a synthetic estimated temperature, the synthetic estimated temperature being equal to a weighted sum of a moving average of the estimated maximum temperature of the brake over the sliding window of the N landings and a measured temperature of the other brake of the landing gear.

5. The monitoring method according to claim 4, wherein: The error between the estimated maximum temperature and the measured maximum temperature is calculated by taking a weighted sum of a mean absolute error (MAE) between a moving average of the maximum temperature reached by the brake over the sliding window of N landings and the synthetic estimated temperature and a symmetric mean absolute percentage error (SMAPE) between a moving average of the maximum temperature reached by the brake over the sliding window of N landings and the synthetic estimated temperature.

6. The monitoring method according to claims 1 to 5, wherein: The braking parameter is one or more of the following: braking energy, maximum braking power, duration of activation of the brake fan, duration of thrust reversal of the engines, duration of landing, initial temperature of the brakes, length of time between the time when the maximum brake temperature is reached and the time when the rotation speed of the wheels reaches the 95th percentile value, static air temperature, average ground speed, maximum ground speed, sum of currents applied by the servovalves of the braking system, average altitude, manufacturer serial number of the aircraft, identifier of the engine type of the aircraft, identifier of the model of the aircraft.

7. The monitoring method according to claims 1 to 6, wherein: The warning message contains an indication that a maintenance action or inspection has to be performed on the brake and an indication of the type of maintenance action or inspection to be performed.

8. The monitoring method according to claim 7, further comprising configuring the warning message so that the warning message indicates: - information about a first type of problem and about a first type of maintenance action or check to be performed that is suitable for said first type of problem, when said measured maximum temperature is greater than said estimated maximum temperature and when the error between said estimated maximum temperature and said measured maximum temperature is greater than said first predefined threshold value S1; or - information about a second type of problem and about a second type of maintenance action or inspection to be performed that is suitable for said second type of problem, when said measured maximum temperature is less than said estimated maximum temperature and when the error between said estimated maximum temperature and said measured maximum temperature is greater than said second predefined threshold value S2.

9. A device (DISP) for monitoring the maximum temperature reached by the brakes of an aircraft landing gear during landing, said monitoring device (DISP) comprising an electronic circuit system configured to implement: The use of a prediction model to predict the maximum temperature reached by the brakes during landing (PHS_UT) comprises the following steps: - obtaining a current set of values ​​of a plurality of braking parameters for the current landing; - estimating (102) the maximum temperature that the brakes will reach during landing based on the values ​​of the current set by means of the prediction model; The comparison stage includes: - obtaining the measured maximum temperature reached by said brakes during said current landing; - determining (104) whether an error between the estimated maximum temperature and the measured maximum temperature is greater than a first predefined threshold value S1 when the measured maximum temperature is greater than the estimated maximum temperature, or greater than a second predefined threshold value S2 when the measured maximum temperature is less than the estimated maximum temperature; - when the error is greater than the first predefined threshold S1 or the second predefined threshold S2, determining (105) whether the total number of errors (NT) in a landing set including the N landings in the sliding window and the current landing is greater than a third predefined threshold S3, otherwise repeating the phase of using the prediction model and the phase of comparison for subsequent landings; - When the total number of errors (NT) is greater than the third predefined threshold S3, a warning message is generated (106), otherwise the phase of using the prediction model (PHS_UT) and the phase of comparison are repeated for a subsequent landing.

10. An aircraft (600) comprising a monitoring device (DISP) according to claim 9.

Images