Method and electronic device for determining radio navigation beacons for an aircraft, computer program, navigation method and associated electronic navigation system

Abstract

Method and electronic device for determining radio navigation beacons for an aircraft, computer program, navigation method and associated electronic navigation system. The present invention relates to a method for determining radio navigation beacons (210) for an aircraft. The method (210) is implemented by an electronic determination device and comprises the following steps: selection (230) of an N-tuple of beacon identifiers, N being greater than or equal to 2, from an estimated position of the aircraft; and supplying (240) the selected N-tuple to an electronic computing device, for calculating a new estimated position of the aircraft from the N beacons corresponding to the N identifiers of the selected N-tuple.During the selection step (230), the N-tuple is selected from a set of admissible N-tuples, obtained through the implementation of an artificial intelligence algorithm. The AI ​​algorithm receives the estimated position of the aircraft as input and provides the set of admissible N-tuples as output. See Figure 4 for the abbreviation.

Description

Title of the invention: Method and electronic device for determining radio navigation beacons for an aircraft, computer program, navigation method and associated electronic navigation system

[0001] The present invention relates to a method for determining radio navigation beacons for an aircraft. It also relates to a computer program, an electronic beacon determination device, a navigation method, and an associated electronic navigation system.

[0002] It is located in the field of secure aeronautical navigation.

[0003] The International Civil Aviation Organization or ICAO (International Civil Aviation Organization), which participates in the development of standards to standardize international air transport, has defined performance-based navigation or PBN (for "Performance Based Navigation").

[0004] PBN navigation consists of determining, from sensors installed on the aircraft, a spatial position of the aircraft and using this position to guide the aircraft along an air route defined by waypoints.

[0005] Air routes usable in civil aviation are defined by IACI.

[0006] To ensure accuracy, this type of navigation requires calculating the aircraft's position with an associated uncertainty estimate, also called EPU (Estimate of Position Uncertainty). The EPU is calculated assuming the absence of any latent failures that could affect the measurements used for the position calculation. A level of positioning accuracy performance can then be imposed, for example, an accuracy of 95% + / - 10 Nm (nautical miles).

[0007] In Required Navigation Performance (RNP) navigation, it is also recommended to implement onboard a monitoring and alerting function to ensure a probabilistic protection radius around the calculated position with a low probability of exceeding the given protection radius without alarm, for example, 10⁵ / hour. This probability takes into account the assumption of latent failures affecting the measurements used for position calculation. The protection radius around a calculated position is called the Horizontal Integrity Limit (HIL).

[0008] In summary, RNP navigation imposes two positioning accuracy performance level indicators, namely a first indicator associated with the EPU, and a second indicator associated with the HIL.

[0009] As is known, RNP navigation is implemented using a satellite positioning system or GNSS (for "Global Navigation Satellite System"). However, there are situations in which satellite signals are weak or subject to interference, whether intentional or not, which disrupts the position calculation performed. In addition, there is also a risk that one of the onboard GNSS receivers may malfunction or fail.

[0010] In order to improve navigation safety, it is necessary to provide an alternative solution for calculating the aircraft's position, which can be implemented in navigation according to an RNP procedure.

[0011] Before the development of GNSS systems, air navigation used radio beacons, placed on the ground and adapted to transmit radio signals with a given transmission range. In particular, there are radio beacons adapted to provide a distance measurement relative to the aircraft, also called DME equipment (for "Distance Measuring Equipment") or DME beacons.

[0012] An aircraft equipped with radio sensors adapted to operate in the transmission frequency band of radio beacons can obtain a distance estimate from a radio beacon when it is within the radio beacon's transmission range. To obtain an aircraft position that meets the first positioning accuracy performance indicator, it is necessary to use several radio beacons.

[0013] A method for navigating an aircraft is known from document FR 3 088 443 Al, which allows the aircraft's position to be determined from radio beacons using a current aircraft position and stored beacon sets in order to comply with EPU and HIL criteria for RNP navigation during flight along a given route or area.

[0014] However, such a method only guarantees navigation performance along predefined routes. As soon as the aircraft leaves the predefined route, an alternative method must be applied to continue providing positioning. However, applying such a method to an area, for example around an airport, independent of a predefined route, requires the storage of a very large amount of data. Indeed, geographical areas in which, for any point, distance measurements to a given subset of beacons allow the calculation of a position with a protection radius smaller than a desired value, have irregular oval shapes of varying sizes, overlapping more or less partially, which are very poorly suited to a rectangular grid.The elementary size of the rectangular grid cell required to cover a rectangular area encompassing a zone around an airport is therefore very small, for example, a square of 1 NM. This implies, for example, 14,400 elementary grid cells to cover an area of ​​60 NM around an airport. Assuming that each grid cell is... represented by two geographical points coded on 32 bits, and considering for example that 5 identification elements of the DME beacons used per mesh also coded on 32 bits are required, the size of the database needed to code the airspace of 50 TMA is then 14,400,000 bytes.

[0015] The object of the invention is then to propose a method for determining radio navigation beacons for an aircraft, compatible with implementation in an onboard navigation system on board the aircraft, providing a set of beacons enabling the calculation of a position of the aircraft while respecting the RNP navigation performance criteria at any point in a useful area around an airport.

[0016] To this end, the invention relates to a method for determining radio navigation beacons for an aircraft, each radio navigation beacon being identified by a beacon identifier, the method being implemented by an electronic determination device and comprising the following steps:

[0017] - selection of an N-tuple of tag identifiers, N being greater than or equal to 2, from of an estimated position of the aircraft; and

[0018] - supplying the selected N-tuple to an electronic computing device, for the calculation of a new estimated position of the aircraft from the N beacons corresponding to the N identifiers of the selected N-tuple;

[0019] such that during the selection step, the N-tuple is selected from a set of admissible N-tuples, obtained via the implementation of an artificial intelligence algorithm, the artificial intelligence algorithm receiving as input the estimated position of the aircraft and providing as output the set of admissible N-tuples.

[0020] Thanks to the invention, the aircraft's new position can be calculated at any point in space on which the artificial intelligence algorithm has been trained. Furthermore, the position estimated by the method closely approximates the navigation performance of the training data of the artificial intelligence algorithm, which can be selected to meet the criteria of accuracy and integrity. In addition, the method requires only the artificial intelligence algorithm to be stored in a database.

[0021] Furthermore, in the prior art, there is no analytical method for performing the optimal selection that would yield the best localization performance when the radio beacons that can be selected are irregularly located around the current position. Nor is there a simple geometric criterion for selecting one set of beacons a priori over another to guarantee a result that meets the desired performance level. Consequently, the search for the best set of beacons is highly combinatorial, resulting from a heuristic analysis of the possible combinations of a limited number of beacons corresponding to the maximum number of beacons to to consider, among a potentially much larger number of available beacons. This search is generally incompatible with real-time processing by an onboard aircraft navigation system, which has limited computing power.

[0022] According to other advantageous aspects of the invention, the beacon determination method comprises one or more of the following features, taken individually or in all technically possible combinations:

[0023] - the set of admissible N-tuples provided by the artificial intelligence algorithm is ordered according to a decreasing performance level, the first N-tuple of the ordered set of admissible N-tuples being the admissible N-tuple with the highest performance level, the performance level of an admissible N-tuple corresponding to an accuracy and / or integrity of the position calculation performed from said admissible N-tuple;

[0024] - the set of admissible N-tuples provided by the artificial intelligence algorithm is ordered according to a decreasing covered area, the first N-tuple of the ordered set of admissible N-tuples being the admissible N-tuple with the largest covered area, the covered area of ​​an admissible N-tuple being the area of ​​a zone associated with said admissible N-tuple and enabling the calculation device to calculate the estimated position if the aircraft is in said zone;

[0025] - the selected N-tuple is the first N-tuple from the set of admissible N-tuples ordered;

[0026] - a previous N-tuple was retained during a prior iteration of the process, and the N- The selected tuple is: • the preceding N-tuple if the preceding N-tuple belongs to the set of admissible N-tuples; or • the first N-tuple of the set of otherwise admissible N-tuples;

[0027] - the selection step includes filtering the set of admissible N-tuples in order to eliminate eligible N-tuples including at least two tag identifiers corresponding to tags under maintenance, the filtering being preferably implemented if the first N-tuple of the ordered set of eligible N-tuples includes at least one tag identifier corresponding to a tag under maintenance;

[0028] - the artificial intelligence algorithm was previously trained during a initialization phase including: • a grid of a predetermined geographical area; • for each grid cell, a determination of beacons for which an aircraft located on said grid cell can receive information, called accessible beacons; • for each mesh, a determination of a set of N-tuples of tag identifiers, each tag identifier of each N-tuple corresponding to one of the accessible tags; • for each N-tuple in the set of N-tuples, a determination of the accuracy and / or integrity performance of the position calculation performed from said N-tuple; • a selection of a restricted set of N-tuples, including the N-tuples whose accuracy and / or integrity performance of the position calculation meets a required performance; • training the artificial intelligence algorithm from the restricted set of N-tuples;

[0029] - the initialization phase further includes: • a removal of redundancy(ies) in the restricted set of N-tuples before training the artificial intelligence algorithm, consisting of removing from the set of N-tuples one or more N-tuples covering an area already covered by at least one other N-tuple, Faire covered by an N-tuple being the area of ​​a zone associated with said N-tuple and allowing the computing device to calculate the estimated position if the aircraft is in said zone;

[0030] - the artificial intelligence algorithm comprises several intelligence models artificial intelligence, and the process includes a preliminary step of selecting one of the artificial intelligence models based on the estimated current position, each artificial intelligence model being associated with a respective predetermined geographical area.

[0031] The invention also relates to a computer program comprising software instructions which, when executed by a computer, implement a determination method as defined above.

[0032] The invention also relates to a method for navigating an aircraft, comprising:

[0033] - a determination of N radionavigation beacons via a determination method in accordance with the above and from an estimated position of the aircraft, the N radio navigation beacons determined corresponding to the N-tuple of identifiers selected;

[0034] - a step of obtaining a distance measurement relative to each of the N beacons determined;

[0035] - a step of calculating a new estimated position of the aircraft from the distance measurements obtained; and

[0036] - a step of using the new estimated position of the aircraft as position aircraft current.

[0037] The invention also relates to an electronic device for determining radio navigation beacons for an aircraft, configured to be carried on board the aircraft, each radio navigation beacon being identified by a beacon identifier, the device comprising:

[0038] - a tag selection module, configured to select an N-tuple of beacon identifiers, N being greater than or equal to 2, from an estimated aircraft position, the N-tuple being selected from a set of admissible N-tuples, obtained via the implementation of an artificial intelligence algorithm, the artificial intelligence algorithm receiving as input the estimated aircraft position and providing as output the set of admissible N-tuples; and

[0039] - a supply module, configured to supply the selected N-tuple to a electronic calculation device, for calculating a new estimated position of the aircraft from the N beacons corresponding to the N identifiers of the selected N-tuple.

[0040] The invention also relates to an electronic aircraft navigation system, configured to be carried on board the aircraft, comprising:

[0041] - an electronic determination device according to the foregoing, providing an N- tuple of tag identifiers; and

[0042] - an electronic computing device, comprising:

[0043] + a obtaining module, configured to obtain a distance measurement relative to to each of the N tags corresponding to the N-tuple of identifiers selected by the determination device;

[0044] + a calculation module, configured to calculate a new estimated position of the aircraft based on the distance measurements obtained; and

[0045] + a usage module, configured to use the new estimated position of the aircraft as the aircraft's current position.

[0046] The invention will become clearer upon reading the following description, given solely by way of non-limiting example, and made with reference to the drawings in which:

[0047] [Fig-1] [Fig.1] is a diagram of an aircraft comprising an electronic system of navigation according to the invention;

[0048] [Fig.2] [Fig.2] is a diagram illustrating the estimation of an aircraft position of the [Fig.1] from radio navigation beacons;

[0049] [Fig.3] [Fig.3] is a flowchart of an initialization phase prior to method for determining radio navigation beacons according to the invention; and

[0050] [Fig.4] [Fig.4] is a flowchart of a method for determining beacons of radionavigation according to the invention.

[0051] In [Fig. 1], an aircraft 1 is flying over an area of ​​interest 3 equipped with radio navigation beacons 5. The area of ​​interest 3 is, for example, a terminal maneuvering area of ​​an airport, or a square centered on an airport. The radio navigation beacons 5 are placed on the ground and capable of transmitting radio signals with a given transmission range. The radio navigation beacons 5 are, in particular, DME equipment and are adapted to provide a distance measurement relative to the aircraft 1. Each radio navigation beacon 5 is identified by a respective beacon identifier.

[0052] The aircraft 1 is equipped with an electronic navigation system 7. The role of the navigation system 7 is to calculate a current position of the aircraft, which is a position estimated from a set of beacons 5. To do this, the electronic navigation system 7 simultaneously takes measurements on signals emitted by several beacons 5 whose position is known to the electronic navigation system 7, and calculates the current position of the aircraft by a multilateration technique.

[0053] Navigation with required performance, or RNP navigation, as defined by ICAO, must meet two performance indicators: accuracy and integrity.

[0054] Accuracy is quantified by an uncertainty estimate associated with the calculation of the aircraft 1's position, called EPU. The EPU is calculated assuming no latent failures that could affect the measurements used for the position calculation. A positioning accuracy performance level can then be imposed, for example, an accuracy of 95% + / - 10 Nm (nautical miles).

[0055] Integrity is quantified by a probabilistic protection radius around the calculated position with a given probability of exceeding the protection radius, for example, equal to 10⁵ / hour. This probability takes into account the assumption of latent failures affecting the measurements used for the position calculation. The protection radius around a calculated position is called the HIL (Heading Integrity Limit).

[0056] Thus, the role of the electronic navigation system 7 is to make an estimate of the current position of the aircraft 1 while respecting the criteria of accuracy and integrity.

[0057] Physically, the electronic navigation system 7 can only take into account the signals emitted by a limited number of beacons 5. Therefore, the set of beacons 5 to be considered must be determined prior to calculating the position by multilateration. The accuracy of the current position estimate calculated in this way is linked to the relative position of the beacons 5 to the aircraft 1, and to the accuracy of the distance measurement itself.

[0058] Figure 2 illustrates the estimation of the position of aircraft 1 from two beacons. 5.

[0059] On insert A of [Fig. 2], the first circle 9A represents the possible positions of aircraft 1 given the exact distance DA separating aircraft 1 from a first beacon 5A. Due to measurement uncertainties in the distance DA, the first ring 1IA located around the first circle 9A represents the possible positions of aircraft 1 given the distance DA within the limits of uncertainty. Similarly, the second circle 9B represents the possible positions of aircraft 1 given the exact distance DB separating aircraft 1 from a second beacon 5B, and the second ring 11B represents the possible positions of aircraft 1 given the distance DB within the limits of uncertainty.

[0060] The position of aircraft 1 is at the intersection of circles 9A and 9B. Taking into account the uncertainties in measuring distances, the current position of aircraft 1 can be estimated at the intersection of rings 11A and 11B, this intersection forming an uncertainty zone 13, shown in [Fig.2].

[0061] Inset B of [Fig.2] shows the uncertainty zones 13 in two different situations corresponding to two different positions of the beacons 5A and 5B.

[0062] It is therefore understood that the uncertainty zone 13 will be all the greater, that is to say, the less precise the estimated position will be, the more flattened the triangle formed by the aircraft's position and the two positions of beacons 5A and 5B, or the lower the accuracy of the distance measurements. However, it turns out that in many cases, the number of beacons 5 considered for calculating the position is less, or even much less, than the number of beacons 5 that could be used. Determining the set of beacons 5 to be considered is therefore of great importance when optimizing the positioning performance of the navigation system 7.

[0063] Thus, the electronic navigation system 7 shown in [Fig.1] includes an electronic device for determining radio navigation beacons 15 and an electronic calculation device 17.

[0064] The electronic determination device 15 includes a beacon selection module 19 and a supply module 21. As an optional complement, the electronic determination device 15 includes a model selection module 23.

[0065] The beacon selection module 19 is configured to select an N-tuple of beacon identifiers, N being greater than or equal to 2, from an estimated aircraft position. The N-tuple is selected from a set of admissible N-tuples, obtained via the implementation of an artificial intelligence algorithm, the artificial intelligence algorithm receiving as input the estimated aircraft position 1 and providing as output the set of admissible N-tuples.

[0066] Advantageously, the artificial intelligence algorithm comprises one or more artificial intelligence models, each artificial intelligence model being associated with a respective area of ​​interest 3.

[0067] Each artificial intelligence model is advantageously a neural network whose structure is defined below.

[0068] Each neural network comprises an ordered succession of layers of neurons, each of which takes its inputs from the outputs of the previous layer.

[0069] More precisely, each layer comprises neurons taking their inputs from the outputs of the neurons of the previous layer, or from the input variables for the first layer.

[0070] Alternatively, more complex neural network structures can be envisaged with a layer that can be linked to a layer further away than the immediately preceding layer.

[0071] Each neuron is also associated with an operation, that is to say a type of processing, to be carried out by said neuron within the corresponding processing layer.

[0072] Each layer is connected to the other layers by a plurality of synapses. A synaptic weight is associated with each synapse, and each synapse forms a link between two neurons. It is often a real number, which takes on both positive and negative values. In some cases, the synaptic weight is a complex number.

[0073] Each neuron is designed to perform a weighted sum of the value(s) received from the neurons of the preceding layer, each value being multiplied by the respective synaptic weight of each synapse, or connection, between said neuron and the neurons of the preceding layer, and then to apply an activation function, typically a non-linear function, to said weighted sum, and to deliver at the output of said neuron, in particular to the neurons of the next layer connected to it, the value resulting from the application of the activation function. The activation function introduces non-linearity into the processing performed by each neuron. The sigmoid function, the hyperbolic tangent function, and the Heaviside function are examples of activation functions.

[0074] As an optional complement, each neuron is also capable of adding a bias to the weighted sum, and the value delivered at the output of said neuron is then the value resulting from the activation function, said function then being applied to the sum of the weighted sum and the bias.

[0075] A fully connected layer of neurons is a layer in which the neurons of said layer are each connected to all the neurons of the preceding layer. Such a layer is more often referred to by the English term "fully connected," and sometimes designated as a "dense layer."

[0076] In particular, each neural network of the artificial intelligence algorithm under consideration includes an input layer, at least one hidden layer, and an output layer.

[0077] The input layer includes, for example, two nodes, receiving respectively the latitude and longitude of the current position of aircraft 1, and typically normalizing these inputs between -1 and -1 from lower and upper bounds of the area of ​​interest 3. Alternatively, the input layer normalizes the inputs by calculating the deviation from the center of the area of ​​interest 3, divided by the variance of the deviations from the center of the area of ​​interest 3.

[0078] The at least one hidden layer comprises -V nodes and a first function activation. The first activation function is, for example, a function sigmoid of the form = _ ], where e denotes the exponential function. / 1](x) = max(0, x) or Leaky ReLU / U Alternatively, the first activation function is of the ReLU type. x if x > 0; with par ax if x < 0 example a = 0.01.

[0079] The output layer comprises M nodes and a second activation function. The A second activation function is, for example, the normalized exponential function.

[0080] Thus, taking the example of a single hidden layer, the nodes of the hidden layer calculate the values ​​from the normalized XH12 inputs]:

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088] where Wjj represent the associated synaptic weights, and bj represent the associated biases. And the M nodes of the output layer calculate the value from the values y, = kj JK where wkjj represent the associated synaptic weights, and bk represent the associated biases. z k =f [2 \y,k) =

[0089] The neural network associates, to a mesh, a vector of M elements, corresponding to each of the N-tuples considered.

[0090] The covered area of ​​an N-tuple is defined as the area of ​​a zone associated with said N-tuple and enabling the calculation device 17 to calculate the estimated position if the aircraft 1 is located in said zone. The performance level of an admissible N-tuple is defined as the accuracy and / or integrity, as defined above, of the position calculation performed from said admissible N-tuple.

[0091] The M elements vary, for example, between 0 and 1, the value 0 being reached when the covered area of ​​the N-tuple does not cover any point of the considered mesh, and the value 1 being reached when the covered area of ​​the N-tuple completely covers the considered grid.

[0092] Other scoring methods are possible by associating an intermediate score with N-tuples of intermediate area covered or performance level, or scored according to their distance from the N-tuple with the largest area covered or the highest performance level, which will have the maximum score of 1.

[0093] The set of admissible N-tuples is then the set of N-tuples whose predicted value is greater than a predetermined threshold between 0 and 1.

[0094] The set of admissible N-tuples is advantageously ordered according to an ordering criterion. The first N-tuple is then called the first N-tuple, the one ranked first in the ordered set of admissible N-tuples. In other words, the first N-tuple is the N-tuple in the set of admissible N-tuples that maximizes the ordering criterion.

[0095] According to a first embodiment of the invention, the ordering criterion is the performance level. In other words, the set of admissible N-tuples is ordered according to a decreasing performance level, the first N-tuple of the ordered set of admissible N-tuples then being the admissible N-tuple having the highest performance level.

[0096] According to a second embodiment of the invention, the ordering criterion is the area covered. In other words, the set of admissible N-tuples provided by the artificial intelligence algorithm is ordered according to a decreasing area covered. Thus, the first N-tuple in the ordered set of admissible N-tuples is the admissible N-tuple with the largest area covered.

[0097] The tag selection module 19 is then configured to select an N-tuple of tag identifiers from among the eligible N-tuples, according to rules which are explained below.

[0098] The supply module 21 is configured to provide the selected N-tuple to the electronic calculation device 17, for the calculation of a new estimated position of the aircraft 1 based on the N beacons corresponding to the N identifiers of the selected N-tuple. The supply module 21 includes for this purpose a digital transmission means, wired or wireless, to the electronic calculation device 17.

[0099] The model selection module 23 is advantageous when the artificial intelligence algorithm includes several artificial intelligence models. The role of the model selection module 23 is then to select the artificial intelligence model to be used by the tag selection module 19, from among the different artificial intelligence models of the artificial intelligence algorithm, based on the estimated current position.

[0100] In the example of [Fig.1], the electronic determination device 15 includes an information processing unit 24 formed for example of a processor 25 and a memory 27 associated with the processor 25.

[0101] In the example of [Fig. 1], the beacon selection module 19 and the supply module 21, as well as the optional model selection module 23, are each implemented as a software program, or a software component, executable by the processor 25. The memory 27 of the electronic determination device 15 is then capable of storing beacon selection software and supply software, as well as the optional model selection software. The processor is then capable of executing each of the following software programs: the beacon selection software and the supply software, as well as the optional model selection software.

[0102] In an alternative not shown, the tag selection module 19 and the supply module 21, as well as the optional model selection module 23, are each implemented as a programmable logic component, such as an FPGA (Field Programmable Gate Array), or an integrated circuit, such as an ASIC (Application Specified Integrated Circuit).

[0103] When the electronic determination device 15 is implemented in the form of one or more software programs, i.e., in the form of a computer program, also called a computer program product, it is further capable of being stored on a computer-readable medium, not shown. The computer-readable medium is, for example, a medium capable of storing electronic instructions and of being connected to a bus of a computer system. By way of example, the readable medium is an optical disc, a magneto-optical disc, ROM, RAM, any type of non-volatile memory (e.g., FLASH or NVRAM), or a magnetic card. A computer program comprising software instructions is then stored on the readable medium.

[0104] The electronic calculation device 17 includes a receiver 28 as well as a obtaining module 29, a calculation module 31 and a usage module 33.

[0105] The receiver 28 is a radio frequency signal receiver, which generally performs propagation delay measurements between a beacon 5 and the aircraft 1 from signals superimposed on a carrier signal defined in a given frequency band. It converts the propagation delay measurements into distances, and can then use a subset of these measurements, the original position of which is known, to calculate the reception position using a multilateration algorithm.

[0106] To perform a measurement, for example a distance measurement relative to a beacon 5, the receiver 28 tunes the reception frequency to the frequency of the signal carrier of the selected beacon, performs the measurements on the signal superimposed on the carrier signal, and continues these signals for as long as these measurements can be made and used.

[0107] The superimposed signal can be, for example, the replica of a limited duration pulse sequence superimposed on a carrier signal, re-emitted with a fixed delay, and on a frequency shifted by a beacon 5, in response to the interrogation of this beacon 5 by the electronic navigation system 7. The distance information is then deduced by the electronic navigation system 7 from the time delay observed between the emission and the reception of the pulse sequence.

[0108] The principle of discrimination between the signals emitted by the different beacons 5 is based on the frequency separation of the carrier signals.

[0109] The acquisition module 29 is configured to obtain, by means of the receiver 28, a distance measurement with respect to each of the N beacons corresponding to the N-tuple of identifiers selected by the radio navigation beacon selection device.

[0110] The calculation module 31 is configured to calculate a new estimated position of the aircraft from the distance measurements obtained.

[0111] The utilization module 33 is configured to use the new estimated position of the aircraft as the current position of aircraft 1. The current position of aircraft 1 is the position estimate used by aircraft 1.

[0112] The structure of the electronic computing device 17 is analogous to the structure of the electronic determining device 15. Thus, in the example of [Fig.1], the electronic computing device 17 comprises an information processing unit 35 formed for example of a processor 37 and a memory 39 associated with the processor 37.

[0113] Prior to use of the electronic navigation system 7, the artificial intelligence algorithm is trained during an initialization phase 100, represented in [Fig.3].

[0114] The initialization phase 100 includes a mesh 110, a determination of reachable tags 120, a determination of a set of N-tuples 130, a performance determination 140, a selection of a restricted set of N-tuples 150, a redundancy removal 160, a training 170 and a verification 180.

[0115] During meshing 110, the set of points located at the intersection of a regular mesh of the area of ​​interest 3 with a square mesh measuring for example 1 nautical mile on a side is determined.

[0116] When determining accessible beacons 120, a set of beacons 5 is determined for each grid cell, for which the aircraft 1 located on said cell can receive information. These beacons 5 are called accessible beacons. In other words, the accessible beacons in a grid cell are the beacons 5 for which the receiver 28 located on said cell is capable of receiving the signals emitted by said beacons. Accessible beacons. For a given grid, accessible beacons are determined from a global beacon database, including a position and characteristics of each beacon 5, as well as accessibility criteria defined by aeronautical standards.

[0117] For the determination of accessible beacons 120, it is necessary to consider a signal reception altitude relative to the ground. The altitude chosen for a grid cell will depend on the operation expected in the area of ​​interest. For example, in the case of a terminal maneuvering area, this altitude will depend on the distance of the grid cell from the destination airport. The function will model a typical minimum descent profile to the airport: for example, a fixed height of 1,500 feet up to 5 nautical miles from the airport, then a height determined by a 3° slope along radials from the airport to the grid cells of the terminal maneuvering area located 10 nautical miles away, then a constant altitude of approximately 3,000 feet for the grid cells located between 10 and 20 nautical miles around the airport, and then an increasing height along a 2° slope.5° when moving away along radials from the airport until reaching an altitude of 6,000 feet above the airport, then a constant altitude. The altitude used for the different grid squares will be the airport altitude plus the altitude derived from the glide slope. If the airport is located in rugged terrain, the altitude used for the different grid squares will be the airport altitude plus the altitude derived from the glide slope, and a height of the terrain surrounding the airport. Furthermore, for determining accessible beacons in rugged terrain, terrain masks may be used to account for signal obscuration by the terrain around the airport.

[0118] When determining the set of N-tuples 130, a set of N-tuples of beacon identifiers is determined for each grid cell, each beacon identifier in each N-tuple corresponding to one of the accessible beacons. The set of N-tuples determined for a grid cell does not necessarily include all possible combinations of accessible beacons for that grid cell. For example, the set of accessible beacon sets can be reduced by eliminating accessible beacons located at a distance less than a given threshold from another accessible beacon with better coverage characteristics. The given threshold is, for example, 3 nautical miles.

[0119] During the performance determination 140, for each N-tuple of the set of N-tuples, the accuracy and / or integrity performance of the position calculation performed from said N-tuple is determined. Advantageously, in order to avoid an excessive amount of computation, the performance calculation is stopped as soon as a predetermined number of solutions satisfying an optimum performance criterion, For example, a value significantly lower than the desired RNP performance is found. For example, the predetermined number is 10, and the optimum performance criterion corresponds to a predicted protection radius of less than 1.25 nautical miles for an RNP criterion requiring a protection radius of less than 2 nautical miles.

[0120] Performance determination is initially carried out at a given cell of the mesh, for example at the airport. Performance determination is then continued on adjacent cells, step by step, giving priority to testing the N-tuples that proved satisfactory at the previous cells. When the number of solutions becomes insufficient with the N-tuples already identified for the previous cells, other N-tuples are considered.

[0121] When selecting a limited set of N-tuples 150, an inventory is taken of all N-tuples that have satisfied the performance conditions as determined previously. Then, each N-tuple is associated with the mesh surface formed by the cells for which the N-tuple has been identified as a solution satisfying the desired performance constraints. Each cell of the region of interest 3 is part of one or more of these mesh surfaces. Thus, for each cell, there is a greater or lesser level of coverage redundancy.

[0122] The redundancy removal process aims to minimize the level of redundancy in the coverage of the different cells, retaining only the minimum number of surfaces that nevertheless provide almost complete coverage of the region of interest 3. To achieve this, the surfaces associated with the N-tuples are sorted, for example, in descending order of size. The cells covered by the largest surface are considered first. Then, among the remaining surfaces, the one that covers the maximum number of cells not yet covered by the first surface is sought. This process is repeated, searching among the remaining surfaces for the one that covers the maximum number of cells not already covered, and the process is stopped as soon as almost all the cells in the region of interest 3, for example 98%, are covered by a surface.Indeed, it is possible not to consider all the cells, since the optimum performance criterion considered for constructing the N-tuples is more demanding than the RNP performance criterion considered for RNP navigation in the region of interest 3. Outside a meshed surface, but in an area close to the boundary of this surface, the performance achievable by localization using the N-tuple associated with the surface is generally compatible with the RNP constraints. At the end of this phase, we have therefore obtained, for almost all the cells in the region of interest 3, associations between these cells and one or more N-tuples whose use is guaranteed to allow RNP navigation, and this in a more or less significant area around this cell. Therefore, we will consider that after the removal of redundancy 160, the final number of N-tuples associated with the surfaces. retained to cover area of ​​interest 3 may be all or part of the initial number of identified N-tuples.

[0123] Training 170 consists of training the previously defined artificial intelligence algorithm, that is to say, in particular, defining the values ​​of the synaptic weights and biases. To do this, we initially consider a number of nodes in the inner layer equal to half the number M of N-tuples retained for the region of interest.

[0124] The training data is formed by associating with each mesh a vector of M elements varying between 0 and 1, depending on the chosen configuration of the artificial intelligence model. The artificial intelligence model is trained on this training data until convergence criteria associated with the learning method indicate that the learning process has converged, and that the network parameters have been identified.

[0125] During verification 180, the convergence performance of the artificial intelligence algorithm is confirmed by verifying a posteriori that the algorithm's outputs for the meshes are indeed the N-tuples that were provided during training. To do this, the network is assumed to predict, for a given mesh, the first N-tuple from the ordered set of admissible N-tuples. The network's success rate is then calculated. If this success rate is greater than a given value, for example 95%, the network's convergence is considered satisfactory. If necessary, the size of the hidden layer(s) is increased by progressively increasing the number of nodes until a maximum of M nodes is reached. These verification data correspond to the complete mesh of the area of ​​interest 3, taking into account all possible longitude and latitude values ​​entering the neural network.In this way, we guarantee perfectly predictable behavior from the neural network, as it will have been verified for all possible requests. For example, longitude and latitude values ​​are rounded to the nearest tenth of a degree to query the artificial intelligence algorithm.

[0126] The initialization phase is advantageously executed with each evolution of the global beacon database. In other words, the artificial intelligence algorithm is regenerated with each evolution of the global beacon database, in order to take these changes into account.

[0127] Once the initialization phase has been completed, the electronic navigation system 7 is ready for use. A navigation method 200, implemented by the electronic navigation system 7, is shown in [Fig. 4] and described below.

[0128] The navigation method 200 includes, in the first stage, a determination of N radio navigation beacons via a beacon determination method 210. It further includes, in the second stage, an update of the position 250.

[0129] The value of N is fixed prior to the process. For position estimation to be possible, N must be greater than or equal to 2. Advantageously, the value of N is greater than or equal to 3, in order to calculate a protection radius, guaranteeing, for example, an integrity risk of less than 10⁵ / hour. Further advantageously, the value of N is greater than or equal to 4, in order to introduce redundancies to compensate for measurement uncertainties. In the preferred embodiment of the invention, the value of N is equal to 5.

[0130] The method for determining beacons 210 is implemented by the electronic determination device 15 and includes a beacon selection step 230 and a supply step 240. Advantageously, the method for determining beacons 210 further includes a model selection step 220, prior to the beacon selection step 230.

[0131] The model selection step 220 is implemented by the model selection module 23 and consists of selecting the artificial intelligence model used by the beacon selection module from among the various artificial intelligence models of the artificial intelligence algorithm. In particular, the selected artificial intelligence model is the artificial intelligence model associated with the area of ​​interest 3 to which the current position of aircraft 1 belongs.

[0132] The tag selection step 230 is implemented by the tag selection module 19 and consists of selecting an N-tuple from among the eligible N-tuples.

[0133] The selected N-tuple is advantageously the first N-tuple of the ordered set of admissible N-tuples.

[0134] Alternatively, the set of admissible N-tuples is compared to a previous N-tuple, selected during a prior iteration of the navigation method 200. If the previous N-tuple belongs to the set of admissible N-tuples, then the selected N-tuple is the previous N-tuple. Otherwise, the selected N-tuple is the first N-tuple from the ordered set of admissible N-tuples.

[0135] The tag selection step 230 advantageously includes filtering the set of eligible N-tuples to eliminate eligible N-tuples containing at least two tag identifiers corresponding to tags under maintenance. The filtering is preferably implemented if the first N-tuple in the ordered set of eligible N-tuples includes at least one tag identifier corresponding to a tag under maintenance.

[0136] The supply step 240 is implemented by the selection module 21. It is during this step that the selected N-tuple is supplied by the supply module 240 to the electronic computing device 17.

[0137] The update of position 250 is implemented by the calculation device 17 and includes a retrieval step 260, a calculation step 270 and a use step 280.

[0138] The acquisition step 260 is implemented by the acquisition module 29 and consists of obtaining, by means of the receiver 28, a distance measurement of the aircraft 1 with respect to each of the N determined beacons.

[0139] Calculation step 270 is implemented by the calculation module 31 and consists of calculating a new estimated position of the aircraft 1 from the distance measurements obtained. This step involves a multilateration technique known to those skilled in the art.

[0140] The utilization step 280 is implemented by the utilization module 33 and consists of using the new estimated position of the aircraft as the current position of aircraft 1.

[0141] At the end of the use step 280, the current position of aircraft 1 has been updated by a new estimation using the radio beacons 5. The navigation process 200 can then be executed again as needed to update the current position of the moving aircraft 1. For example, the navigation process 200 is executed iteratively at a predetermined frequency. Alternatively, the navigation process 200 can be triggered by equipment on board the aircraft or by a command from a pilot of aircraft 1. It is understood that the performance of the navigation process 200 described below depends on both the value of N and the frequency at which the current position is refreshed by a new iteration of the process.

[0142] Any feature described above for one example or variant may also be implemented in the other examples and variants described above, as far as technically possible.

Claims

Demands

1. A method for determining radio navigation beacons (210) for an aircraft (1), each radio navigation beacon (5) being identified by a beacon identifier, the method (210) being implemented by an electronic determination device (15) and comprising the following steps: • selection (230) of an N-tuple of beacon identifiers, N being greater than or equal to 2, from an estimated position of the aircraft (1); and • supplying (240) of the selected N-tuple to an electronic computing device (17), for calculating a new estimated position of the aircraft (1) from the N beacons (5) corresponding to the N identifiers of the selected N-tuple;characterized in that, during the selection step (230), the N-tuple is selected from a set of admissible N-tuples, obtained via the implementation of an artificial intelligence algorithm, the artificial intelligence algorithm receiving as input the estimated position of the aircraft (1) and providing as output the set of admissible N-tuples.;

2. Method (210) according to claim 1, wherein the set of admissible N-tuples provided by the artificial intelligence algorithm is ordered according to a decreasing performance level, the first N-tuple of the ordered set of admissible N-tuples being the admissible N-tuple having the highest performance level, the performance level of an admissible N-tuple corresponding to an accuracy and / or integrity of the position calculation performed from said admissible N-tuple.

3. Method (210) according to claim 1, wherein the set of admissible N-tuples provided by the artificial intelligence algorithm is ordered according to a decreasing covered area, the first N-tuple of the ordered set of admissible N-tuples being the admissible N-tuple having the largest covered area, the covered area of ​​an admissible N-tuple being the area of ​​a zone associated with said admissible N-tuple and enabling the computing device to calculate the estimated position if the aircraft (1) is in said zone.

4. Method (210) according to claim 2 or 3, wherein the selected N-tuple is the first N-tuple of the ordered set of admissible N-tuples.

5. A method (210) according to claim 2 or 3, wherein a previous N-tuple was retained during a prior iteration of the method (210), and wherein the selected N-tuple is: • the previous N-tuple if the previous N-tuple belongs to the set of admissible N-tuples; or • the first N-tuple of the set of admissible N-tuples otherwise.

6. A method (210) according to any one of claims 2 to 5, wherein the selection step (230) includes filtering the set of eligible N-tuples so as to eliminate eligible N-tuples including at least two tag identifiers corresponding to tags (5) under maintenance, the filtering preferably being implemented if the first N-tuple of the ordered set of eligible N-tuples includes at least one tag identifier corresponding to a tag (5) under maintenance.

7. A method (210) according to any one of the preceding claims, wherein the artificial intelligence algorithm has been previously trained during an initialization phase (100) comprising: • a mesh (110) of a predetermined geographical area; • for each mesh, a determination of beacons (120) for which an aircraft located on said mesh can receive information, referred to as accessible beacons; • for each mesh, a determination of a set of N-tuples of beacon identifiers (130), each beacon identifier of each N-tuple corresponding to one of the accessible beacons; • for each N-tuple of the set of N-tuples, a determination of the accuracy and / or integrity performance (140) of the position calculation performed from said N-tuple; • a selection (150) of a restricted set of N-tuples, comprising the N-tuples whose accuracy performance and / or integrity of the position calculation meet a required performance; • a training (170) of the artificial intelligence algorithm from the restricted set of N-tuples.

8. A method according to the preceding claim, wherein the initialization phase further comprises: • a redundancy removal (160) in the restricted set of N-tuples before training the artificial intelligence algorithm, consisting of removing from the set of N-tuples one or more N-tuples covering an area already covered by at least one other N-tuple, the area covered by an N-tuple being the area of ​​a zone associated with said N-tuple and enabling the computing device to calculate the estimated position if the aircraft is in said zone.

9. Method (210) according to claim 7 or 8, wherein the artificial intelligence algorithm comprises several artificial intelligence models, and the method (210) includes a preliminary step of selecting one of the artificial intelligence models (220) based on the estimated current position, each artificial intelligence model being associated with a respective predetermined geographical area.

10. Computer program comprising software instructions which, when executed by a computer, implement a method (210) according to any one of the preceding claims.

11. A method for navigating (200) an aircraft (1), comprising: • determining N radio navigation beacons (5) via a determination method (210) according to any one of claims 1 to 9 and from an estimated position of the aircraft, the N radio navigation beacons (5) determined corresponding to the selected N-tuple of identifiers; • a step of obtaining (260) a distance measurement from each of the N beacons (5) determined; • a step of calculating (270) a new estimated position of the aircraft (1) from the distance measurements obtained; and • a step of using (280) the new estimated position of the aircraft (1) as the current position of the aircraft (1).

12. An electronic device (15) for determining radio navigation beacons (5) for an aircraft (1), configured to be carried on board the aircraft (1), each radio navigation beacon (5) being identified by a beacon identifier, the device comprising: • a beacon selection module (19), configured to select an N-tuple of beacon identifiers, N being greater than or equal to 2, from an estimated aircraft position (1), the N-tuple being selected from a set of admissible N-tuples, obtained via the implementation of an artificial intelligence algorithm, the artificial intelligence algorithm receiving as input the estimated aircraft position (1) and providing as output the set of admissible N-tuples; and • a supply module (21), configured to supply the selected N-tuple to an electronic computing device (17), for the calculation of a new estimated position of the aircraft (1) from the N beacons (5) corresponding to the N identifiers of the selected N-tuple.

13. An electronic navigation system (7) of an aircraft (1), configured to be carried on board the aircraft (1), comprising: - an electronic determination device (15) according to the preceding claim, providing an N-tuple of beacon identifiers; and - an electronic computing device (17), comprising: + a obtaining module (29), configured to obtain a distance measurement relative to each of the N tags (5) corresponding to the N-tuple of identifiers selected by the determination device (15); + a calculation module (31), configured to calculate a new estimated position of the aircraft (1) from the distance measurements obtained; and + a utilization module (33), configured to use the new estimated position of the aircraft (1) as the current position of the aircraft (1).

Images