Method for predicting an item of information on the friction of a runway, and corresponding system

Abstract

The invention relates to a method for predicting an item of information on the friction of an aircraft landing runway, the method comprising, for a given time: obtaining (S100) items of runway context data, obtaining (S101) items of friction information history data for the runway comprising items of data that are all older than the given time, a prediction (S102) by a prediction model configured to receive, as input, at least the items of context data for the given time and the items of friction information history data, and to deliver an item of predicted friction information (p) for the runway for the given time.

Description

Description Title of the invention: Method for predicting information on the friction of a landing runway, and corresponding system Technical Field

[0001] The invention relates to the general field of aircraft landing runway management, and in particular to the prediction of runway friction.

[0002] Prior Art Knowledge of friction, or more precisely of a coefficient of friction, has become increasingly critical for traffic management within airports or more precisely for the management of airports and their runways.

[0003] Additionally, knowledge of runway condition information, such as friction, helps optimize landings and thus reduce their carbon footprint. Characterizing runway conditions thus helps improve the environmental performance of aircraft.

[0004] This friction information is also useful in aircraft for managing anti-skid braking. It therefore appears that knowledge of a friction coefficient or information relating to friction is also particularly critical for safety reasons.

[0005] As you can imagine, track weather conditions have an impact on friction. The presence of contaminants can also have an impact on friction. It should be noted that these contaminants can be either weather-related (water, ice, snow, etc.) or independent of these conditions (pollution, particles, rubber, etc.).

[0006] Although it is conceivable to calculate a friction coefficient within an aircraft by various measurements, this information is generally not instantly usable by air traffic / airport / runway managers. Indeed, this exploitation is generally only done after a landing, after the rolling phase, and once data communication means allow the transmission of this data to a remote server.

[0007] Real-time determination of friction for a track is therefore not possible with the solutions of the prior art.

[0008] The invention aims in particular to overcome these drawbacks. Statement of the invention

[0009] For this purpose, the invention proposes a method for predicting friction information of an aircraft landing runway implemented by a computer system, said method comprising a plurality (n, ni) of iterations of the following steps: a) obtaining (S100) context data of the runway for a current instant t, b) obtaining (S101) friction information history data for the runway, comprising data all older than the current instant t, c) prediction (S102) by a prediction model configured to receive as input at least said context data and said friction information history data, and to deliver predicted friction information Gu) of the runway for a given instant t+dt the method further comprising:

[0010] a step-by-step reconstruction (RP1) of a first portion of the evolution curve of the predicted friction information ( . of the runway, between an instant of a last landing of an aircraft on the runway and an instant of obtaining real information relating to friction determined by the aircraft during said landing, each point of the curve corresponding to predicted friction information ( . during one of the iterations of steps a) to c).

[0011]

[0012] It can be noted that the prediction can be considered as a temporal prediction.

[0013] Thus, the invention proposes to use a prediction model which delivers friction information for an instant for which we do not necessarily yet have historical friction information data. This allows to have friction information before, for example, downloading data acquired during the passage of an aircraft on the runway, and to implement real-time monitoring of friction within the runway. Finally, since the friction information is accessible in real time, it can be used to implement management of runway(s) (i.e. of the said runway and possibly other runways at the same airport).

[0014] The friction information history data and the context data may be older than the given time, for example older by a chosen time step. For example, for known data at t, the friction information at t + dt is predicted if dt is the time step.

[0015] It may be noted that one can use friction information history data and context data that are included in a time window extending between t and t - dt', dt' being either a time step equal to dt or a different time step.

[0016] Step-by-step reconstruction can be implemented with a given time step, said time step being for example determined according to a sampling step for one of the data used as input by the prediction model. This time step can be that of the prediction (we predict for an instant spaced from the last date of the data of the time step).

[0017] The method can be implemented by a computer system (one or more computers), for example a remote computer system. This results in particular from the fact that the historical friction information data are older than the time for which the prediction is implemented: it is not necessary to have information relating to the landing / taxiing of an aircraft on the runway in real time which takes a long time to transfer.

[0018] The friction information may be a friction coefficient, for example a time average of a friction coefficient, and / or for example a friction coefficient representative of the track. Alternatively, the friction information may be a set of friction coefficients, for example each associated with a location within the track.

[0019] The friction information history data may be of the same type as the friction information to be determined or of a different type.

[0020] The runway context data may be chosen from a group of data comprising a representative value of precipitation, a number of landings on the runway during a given period, a representative value of wind, a representative value of humidity, etc. The person skilled in the art will know how to choose this context data from this group, or even choose other context data, in particular if this other context data is available in real time, i.e. accessible / known for a prediction for the moment for which the method is implemented. The context data is chosen in particular if it has an impact or is linked to friction.

[0021] The prediction model may also be chosen by the person skilled in the art depending on the application.

[0022] According to a particular mode of implementation, after the last landing of an aircraft on the runway, the prediction is implemented for a given instant between an instant of said landing (for example its start) and an instant of obtaining real information relating to the friction determined by the aircraft during said landing.

[0023] The person skilled in the art will be able to identify the time at which real information relating to friction determined by the aircraft during landing is obtained. In particular, the real information is not predicted and is, for example, obtained following a transfer of the information determined by the aircraft during landing. This obtaining corresponds, for example, to an obtaining by the computer system which implements the present method; in this sense, the person skilled in the art knows how to identify this real, unpredicted information. This obtaining may correspond to the display of the information on a screen of the computer system.

[0024] For example, the time of obtaining may be after the following periods: taxiing of the aircraft (for example between 5 and 25 minutes), physical transfer of data (a few minutes via a communications network), and a frequency chosen to group and transfer the data (this frequency may be chosen by the airline).

[0025] In this particular implementation mode, it is not required to wait for information to be obtained from the last aircraft to have landed on the runway to estimate friction information (this obtaining being implemented by the entity which implements the method remotely from the aircraft). Therefore, the friction information can even be used for maintenance operations on the runway.

[0026]

[0027] According to a particular implementation mode, after the last landing of an aircraft on the runway, the prediction is further implemented for a time subsequent to the time of obtaining real friction information determined by the aircraft during the landing (thus, there is another prediction for this subsequent time), the obtaining of the runway context data comprising a prediction of the runway context data.

[0028] In this particular implementation, the context data of the runway are predicted. This can be done for example with weather predictions. The context data obtained by prediction can be analogous to the context data described above. They are nevertheless obtained from a predictive model and therefore, the person skilled in the art will choose context data that can be predicted, for example if predictive models are accessible. For information, data relating to wind and humidity are usually predicted.

[0029] It may be noted that a prediction may be necessary if the context data is not yet available for the given instant, although this instant is in the past, due to the context data transfer time (typically a few minutes).

[0030] Also, in this embodiment, the prediction can be limited by using a time that is prior to the expiration of a given duration.

[0031] According to a particular mode of implementation, a second portion of the evolution curve of the predicted friction information of the runway is reconstructed step by step, from the instant of obtaining real information relating to the friction determined by the aircraft during landing (and for example the instant of expiry of the given duration).

[0032] According to a particular implementation mode, the predicted friction information is compared with a given threshold, and an alert signal is generated based on the result of the comparison.

[0033] This alert signal can be an audible or visual signal, for example configured to be returned to runway management operators.

[0034] According to a particular embodiment, the predicted friction information comprises a friction coefficient associated with the track, or comprises a set of friction coefficients, each of the coefficients of said set preferably being associated with a location within the track.

[0035] It may be noted that the friction information history data may also include friction coefficients associated with the track, or include sets of friction coefficients, each of the coefficients of said sets preferably being associated with a location within the track.

[0036] According to a particular implementation mode, the prediction model is a model trainable by machine learning.

[0037] Typically, the model may be an artificial neural network executed by a computer system.

[0038] The person skilled in the art will know how to choose a type of model that can be trained by learning, and will be able, for example, to adapt the number of input neurons of the model according to the dimensions of the input data of the model.

[0039] Preferably, the prediction model is a model known by the English acronym LSTM (Long Short-Term Memory). Alternatively, a recurrent neural network (RNN) type model can be used.

[0040] According to a particular mode of implementation, the method comprises a preliminary phase of learning the prediction model in which historical friction information data are used (typically so-called real data, obtained during aircraft landings with sensors) and track context data previously obtained for a first instant, the learning being configured to increase a similarity between a model output and a prior friction information value, for a second instant spaced from the first instant by a given time step (the model output and the prior value each corresponding to the second instant).

[0041] The invention also proposes a system for predicting friction information of an aircraft landing runway, the system comprising: a module for obtaining context data of the runway, configured to obtain context data of the runway for a current instant t, a module for obtaining historical friction information data, configured to obtain historical friction information data for the runway comprising data all older than the current instant t, a prediction module by a prediction model, configured to receive as input at least said context data and said historical friction information data, and to deliver predicted friction information of the runway for a given instant t+dt, the system further comprising: a step-by-step reconstruction module (RP1) of a first portion of the evolution curve of the predicted friction information (n) of the runway,between an instant of a last landing of an aircraft on the runway and an instant of obtaining real information relating to friction determined by the aircraft during said landing, each point of the curve corresponding to friction information predicted (.) by said prediction module at different instants.,

[0042] This system can be configured to implement all modes of implementation of the method as described above.

[0043] The invention also provides a computer program comprising instructions for executing the steps of a method as defined above when said program is executed by a computer.

[0044] Note that the computer programs referred to herein may use any programming language, and may be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0045] The invention also provides a computer-readable recording medium on which is recorded a computer program comprising instructions for executing the steps of a method as defined above.

[0046] The recording (or information) media referred to in this disclosure may be any entity or device capable of storing the program. For example, the media may include a storage medium, such as a ROM, for example a CD ROM or a microelectronic circuit ROM, or a magnetic recording medium, for example a floppy disk or a hard disk.

[0047] On the other hand, the recording media may correspond to a transmissible medium such as an electrical or optical signal, which can be conveyed via an electrical or optical cable, by radio or by other means. The program according to the invention can in particular be downloaded from a network such as the Internet.

[0048] Alternatively, the recording media may correspond to an integrated circuit in which the program is incorporated, the circuit being adapted to carry out or to be used in carrying out the method in question. Brief description of the drawings

[0049] Other characteristics and advantages of the present invention will emerge from the description given below, with reference to the appended drawings which illustrate an exemplary embodiment thereof without any limiting character. In the figures: [Fig. 1] Figure 1 is a schematic representation of the steps of a method for predicting friction information according to an example. [Fig. 2] Figure 2 is a schematic representation of steps comprising the method of Figure 1. [Fig. 3] Figure 3 is an illustration of a machine learning phase of the friction model. [Fig. 4] Figure 4 is a friction coefficient curve obtained according to an example of implementation of the friction information prediction method. [Fig. 5] Figure 5 shows a system for predicting friction information according to an example. Description of the embodiments

[0050] We will now describe a method for predicting friction information from an aircraft landing runway.

[0051] This method can be implemented for any instant (for example, a past instant, the present, or a future instant). In particular, this method can be implemented while friction information from the last aircraft to land on the runway is not yet available, this information being transferred to remote servers only late, which delays its availability to runway managers. Here, the method can provide runway managers with friction information for a runway at any time, who can then provide this information to air traffic managers. It is in this sense that friction information is useful for optimized air traffic management.

[0052] In Figure 1, the steps of a method P1 for predicting friction information for a landing runway for a given instant are shown schematically: the friction information is a prediction of the friction at this instant.

[0053] This method may be implemented by a computer system, as will be described in more detail with reference to Figure 5.

[0054] In a first step S100, context data of the track is obtained. If the given time is in the past, this context data may result from observations, and if the given time is in the future, this context data may result from a prediction. The context data of the track can be chosen from a group of data including a representative value of precipitation, a number of landings on the runway during a given period, a representative value of wind, a representative value of humidity, etc.

[0055] In a second step S101, obtaining historical friction information data for the runway is implemented, comprising data all older than the given instant. This data may result from the landing and taxiing of aircraft on the runway (measurements implemented during these phases make it possible to obtain friction information). Alternatively, this historical data may result, for example, in part from a previous implementation of the method P1.

[0056] The historical friction information data may be of the same type as the predicted friction information obtained by means of method P1. By "historical" is meant that it concerns one or more times older than the given time targeted by the method.

[0057] Finally, in a step S102, a prediction is implemented by a prediction model configured to receive as input at least the context data and the friction information history data, and to deliver predicted friction information of the track at the given instant.

[0058] The prediction model is, for example, of the LSTM type (“Long Short-Term Memory”).

[0059] The model here delivers a predicted friction information value denoted / z, representative of the friction within the track. For example, if the data from steps S100 and S101 were associated with a time t, the prediction can be associated with a time t + dt where dt is a chosen time step.

[0060] Figure 2 shows how the process P1 described with reference to Figure 1 can be implemented, for example in the context of runway management or even air traffic.

[0061] The first step S001 refers to the phase during which aircraft landed on the runway referred to here. During these landings followed by taxiing, friction data were acquired in a manner known per se.

[0062] During a second step S002, friction information is obtained from the data acquired during step S001. It may be noted that for each aircraft, obtaining the actual (i.e., non-predicted) friction information from acquired data (for example, by sensors) is done after obtaining actual information from the aircraft by the entity that implements the method described here (for example, a computer system). It may be noted that the information transferred from the aircraft may be either friction information or friction-related data from which friction information may be obtained.

[0063] It may be noted that the determination of friction in an aircraft is known per se. For example, document US 10202204 describes obtaining information relating to friction within an aircraft.

[0064] Then, a step-by-step reconstruction of a curve of evolution of the runway friction information between the last landing of an aircraft on the runway and the time of obtaining real information (the duration Tl since the last landing has not expired) can be implemented. This is implemented by a repetition of the steps of the method P1 of figure 1, the repetition being designated by the reference RP1. To obtain a curve for the period Tl with a time step dt, n repetitions are implemented. At each repetition, historical friction information data partly estimated by the previous repetition are used (in other words, this is friction information predicted or obtained from landings preceding the one targeted here), and context data at the current time of the repetition.

[0065] It can be noted that Tl can typically be between 30 minutes and 6 hours, and depends as indicated above on the duration of landing, taxiing, and the duration of one or more data transfers to a server (possibly with pre-processing), until the data is obtained by the entity implementing the method.

[0066] After reconstructing the curve for the entire period T1, it is possible to move on to another reconstruction step designated by the reference RP1', in which, for a given duration T2, a first part of the friction information curve will be reconstructed. For example, for a process which is implemented implemented at the end of the period T1 for which the RP1 repetitions were implemented until this end, observed context information was used during these RP1 repetitions. For the RP1 repetitions, predicted context information (and therefore not observed) is used as input. To obtain a second part of the curve for the period T2 with a time step dt, m repetitions are implemented.

[0067] It can be noted that T2 can typically be between 30 minutes and 2 hours. For example, T2 can be chosen according to the application by runway management operators. A short T2 duration allows, for example, to predict more reliable information.

[0068] In the figure, we note C the friction information curve reconstructed after implementation of steps RP1 and RP1'.

[0069] During step S003, the predicted friction information obtained at the given time, for example illustrated on curve C, is compared with a given alert threshold i c visible in the figure. If the predictive friction information reaches the threshold, then an alert signal is generated during step S004 which can be returned to track managers.

[0070] For information purposes, several thresholds can be used, each associated with the generation of an alert signal linked to a specific maintenance action to be carried out on the runway (inspection, snow removal, spreading of de-icer).

[0071] The threshold(s) are preferably predetermined and fixed. They can be set during an observation phase of the operations carried out for a track based on, for example, real friction information values.

[0072] As indicated above, the prediction model used can be of the LSTM type, and therefore be a model trainable by machine learning.

[0073] Figure 3 illustrates a machine learning phase of the friction information prediction model, for which a previously obtained real friction information curve is used (e.g. over a period of about one year). During an individual step of this learning phase, a time t is considered, and the model output for time t + dt, i.e. a second time, is obtained. The comparison between the model output and the value real friction information at t + dt allows the implementation of learning.

[0074] Here, the model is configured to predict, for friction information at time t (either a single friction information or a time window preceding t and including several friction information), the friction information at time t + dt. The duration dt can be equal to the duration of the time window of the data used, or dt can differ from this duration.

[0075] Any appropriate cost function and backpropagation can be used to then train the model using a distance between the model output and the actual value at t + dt.

[0076] It can be noted that it is possible, during the model learning phase, to implement a model validation step by comparing real and predicted values.

[0077] Figure 4 shows in more detail the curve obtained after the implementation of the repetitions RP1 and RP1', that is, after implementations of the prediction method. The curve in Figure 4 is obtained after the implementation of the learning phase described with reference to Figure 3.

[0078] It is understood at this stage that it is possible to continuously establish friction information curves for a runway. Optionally, moving average processing can be implemented to follow an evolution of the friction information, for example over windows of several flights (number of flights between 3 and 20 for example) or over time windows (from 1 hour to 4 hours). Here, the curve remains above a given alert threshold n c visible in the figure, compared with the predictive friction information. Thus, in this example, there is no emission of an alert signal.

[0079] This information can also be used to help an airport anticipate runway interventions. For example, different thresholds can be used to trigger different actions (inspection, snow removal, de-icing).

[0080] Figure 5 is a schematic representation of a system 100 which is a computer system configured to implement the method described above with reference to Figure 1.

[0081] This computer system 100 comprises a processor 101 and a non-volatile memory 102. In the non-volatile memory, a computer program 103 is stored. The computer program 103 comprises instructions for executing the steps of a method as described above.

[0082] Thus, the processor 101 and the computer program form, during the execution of the program: a module for obtaining context data of the track at the given instant, a module for obtaining historical friction information data for the track comprising data all older than the given instant, a prediction module by a prediction model configured to receive as input at least the context data at the given instant and the historical friction information data, and to deliver a prediction of the friction information of the track at the given instant.

[0083] The embodiments described above make it possible to improve the management of the runway(s), in particular in terms of monitoring the state of a runway.

[0084] Furthermore, the embodiments described above make it possible to obtain knowledge of friction (or adhesion) as perceived by an aircraft, with its level, its variability, its temporal evolution.

[0085] In particular, the process makes it possible to obtain friction information continuously, to optimize track interventions.

[0086] For example, the process can even be used to measure the effectiveness of chemicals applied to runways, or to compare friction levels between airports, and the variability of friction.

[0087] This process is used in airport management, runway management, and can be useful for airlines.

Claims

Claims

1. Method for predicting friction information of an aircraft landing runway implemented by a computer system, said method comprising a plurality ( / 7, ni) of iteration of the following steps: a) obtaining (S100) context data of the runway for a current instant t, b) obtaining (S101) friction information history data for the runway, comprising data all older than the current instant t, c) prediction (S102) by a prediction model configured to receive as input at least said context data and said friction information history data, and to deliver predicted friction information O ) of the runway for a given instant t+dt the method further comprising: a step-by-step reconstruction (RP1) of a first portion of the evolution curve of the predicted friction information ( / z) of the runway,between an instant of a last landing of an aircraft on the runway and an instant of obtaining real information relating to friction determined by the aircraft during said landing, each point of the curve corresponding to predicted friction information ( / z) during one of the iterations of steps a) to c).,

2. The method of claim 1, wherein after the last landing of an aircraft on the runway, the prediction (S102) is further implemented for a time subsequent to the time of obtaining actual information relating to the friction determined by the aircraft during said landing, the obtaining (S100) of the runway context data comprising a prediction of the runway context data.

3. Method according to claim 2, in which a second portion of the curve of evolution of the runway friction information is reconstructed step by step (RP1'), from the moment of obtaining real information relating to the friction determined by the aircraft during landing.

4. Method according to any one of claims 1 to 3, in which the predicted friction information is compared with a given threshold and an alert signal is generated (S004) according to the result of the comparison.

5. A method according to any one of claims 1 to 4, wherein the predicted friction information comprises a friction coefficient associated with the track, or comprises a set of friction coefficients, each of the coefficients of said set preferably being associated with a location within the track.

6. A method according to any one of claims 1 to 5, wherein the prediction model is a model trainable by machine learning, the method comprising a preliminary phase of training the prediction model in which friction information history data and track context data previously obtained for a first instant are used, the training being configured to increase a similarity between an output of the model and a prior friction information value, for a second instant spaced from the first instant by a given time step.

7. System for predicting friction information of an aircraft landing runway, the system comprising: a module for obtaining context data of the runway, configured to obtain context data of the runway for a current instant t, a module for obtaining historical data of friction information, configured to obtain historical data of friction information for the runway comprising data all older than the current instant t, a prediction module by a prediction model, configured to receive as input at least said context data and said friction information history data, and to deliver predicted friction information of the runway for a given instant t+dt, the system further comprising: a step-by-step reconstruction module (RP1) of a first portion of the evolution curve of the predicted friction information ( / z) of the runway, between an instant of a last landing of an aircraft on the runway and an instant of obtaining real information relating to friction determined by the aircraft during said landing, each point of the curve corresponding to friction information predicted ( / z) by said prediction module at different instants.

8. Computer program comprising instructions for executing the steps of a method according to one of claims 1 to 6 when said program is executed by a processor.

Images