The present invention relates to the field of electronic air traffic control systems,
typically electronic air traffic management (ATM) systems. Such a system provides th5 e
interfacing between an air traffic controller on the one hand, for example responsible for a
given geographical sector, and on the other hand the aircraft located within the geographical
sector or other air traffic controllers, in particular those responsible for the neighboring
geographical sectors.
10 Such a system receives data from outside systems (weather data, aircraft flight
plans, radar detection, messages from air traffic controllers from neighboring sectors, etc.),
processes this data, optionally combines it, etc., then retrieves, via an MMI (man-machine
interface), this data or the information resulting from the processing operations for the air
traffic controller. The air traffic controller, based on this data and information, determines air
15 traffic control instructions (commands intended for the aircraft, messages for the
neighboring controllers including information, data, etc.) and enters it via the MMI. The
system next processes these commands.
Such a system is regularly subjected to validation and integration tests. In a known
manner, such validation and integration tests seek to verify the proper operation of the
20 system, and to detect any bugs, first at the builder of the system, then once the system is
installed on the operating site. They for example made it possible to verify the compliance
of the system’s behavior with the specifications, both internal and in terms of its exchanges
with the outside interfaces, to test its performance, for example the response time, and its
robustness. These validation and integration tests take place with input data that may or
25 may not be predefined. These tests must be carried out during the introduction of new
functionalities into the electronic control system of the air traffic controller or to test the nonregression
of the existing functionalities. They require the participation, for days or even
weeks, of air traffic controllers to interact with the system, in the same way as during
traditional operational use, which is a brake to the implementation of complete and intensive
30 tests, and in so doing to the rapid deployment of technical upgrades to these systems.
As an example, a known functionality of an air traffic control system is the detection
of conflicts, where an alert is generated if the system detects a collision risk between two
aircraft in the next n minutes (for example, n = 3). In such a case, while thus being notified
by the alert and in light of the other data provided by the system regarding the current state
35 of air traffic and the air traffic environment, the controller gives commands to said aircraft
2
and if applicable communicates with the controllers of the neighboring sectors via their
respective ATM system.
When the conflict detection method changes, for example by using a new conflict
detection algorithm, tests are carried out, including supplying the ATM system with input
data that are next processed and/or displayed, analyzing them via the air traffic controller5 ,
providing instructions via the latter, then processing these instructions via the ATM system,
the behavior of the system being supervised in order to detect inconsistencies, drifts,
regressions, etc.
Another functionality of an ATM system is for example the supervision of the safety
10 distances between aircraft. When the retrieval form of this functionality changes, tests must
also be carried out.
There is therefore a need to facilitate the implementation of tests for air traffic control
electronic control systems.
To that end, according to a first aspect, the invention proposes a test method for an
15 air traffic control electronic control system delivering information relative to air traffic control
established as a function of input data representative of the state of the air traffic control
received by said system, said system further receiving, and processing, in the operational
phase, control instructions from air traffic control that are provided to it by at least one air
traffic controller,
20 said method being characterized in that it comprises, during a test phase of said system,
the following steps:
- reception by said system of input data representative of the state of air traffic;
- establishment by said system of information relative to the air traffic as a function
of said input data and delivery by said system of said information to an electronic
25 test device of the system;
- determination by said electronic test device of the system, as a function of the
delivered information, of air traffic control instructions and providing said system
with said instructions;
- reception and processing of said instructions by said system;
30 according to which said electronic device includes an algorithmic model for automatically
determining instructions as a function of information relative to the air traffic, said model
having been obtained during a learning phase, carried out by computer, of a deep learning
neural network, as a function of a set of instructions previously provided by at least one air
traffic controller to the system and information relative to the air traffic associated with said
35 instructions.
3
The invention thus makes it possible to perform electronic control tests of the air
traffic of much greater duration and intensity, which makes it possible to accelerate and
reliabilize the operational commissioning of new functionalities or more generally of new
versions of these systems.
In embodiments, the test method according to the invention further includes one o5 r
more of the following features:
- the test method comprises, during the test phase, the detection of one or more
nonconformities of the system as a function of the behavior of the system;
- the algorithmic model for automatically determining instructions has been
10 learned in order to determine instructions specific to at least one element, as a
function of a determination by element from among several elements of the
same type, during the learning of the instructions previously provided by at least
one air traffic controller to the system and of the information relative to the air
traffic control associated with said instructions, said element from among several
15 elements of the same type being a geographical sector from among several
geographical sectors and/or an air traffic controller role from among several roles
and/or a functionality of the electronic control system of the air traffic from among
several functionalities of said system;
- the test method comprises the steps of:
20 - determining an algorithmic constraint module adapted for identifying
instructions not compliant with the rules of the air traffic controllers;
- applying said algorithmic module to the set of instructions previously
supplied by at least one air traffic controller to the system and
removing said instructions identified as not compliant from the set
25 used for the learning of the neural network;
- applying said algorithmic module to the instructions determined by
the electronic test device and not considered in the phase for testing
instruction(s) identified as not compliant.
30 - the test method comprises, in a phase preliminary to the test, the steps of:
- collecting and storing a set of instructions previously provided to the
system by at least one air traffic controller and information relative to
the air traffic controller delivered by the system associated with said
instructions;
35 - determining the algorithmic model for automatically determining
instructions as a function of information relative to the air traffic
4
controller by learning, carried out by computer, of a neural network,
as a function of said stored set of instructions and said stored
information relative to the air traffic and associated with said
instructions.
According to a second aspect, the present invention proposes an electronic test
device for an air traffic control electronic control system delivering information relative to air
traffic control established as a function of input data representative of the state of the air
traffic control received by said system, said system further receiving, and processing control
instructions from air traffic control that are provided to it by at least one air traffic controller,
said electronic test device being characterized in that it is adapted for receiving information
relative to the air traffic delivered by the system and in that it includes an algorithmic model
for automatically determining instructions as a function of information relative to the air
traffic, said model having been obtained during a learning phase, carried out by computer,
of a deep learning neural network, as a function of a set of instructions previously provided
by at least one air traffic controller to the system and information relative to the air traffic
associated with said instructions.
In embodiments, the test device according to the invention further includes one o5 r
more of the following features:
- it is adapted for detecting the nonconformity of the system as a function of the
behavior of the system;
- the algorithmic model for automatically determining instructions has been
10 learned in order to determine instructions specific to at least one element, as a
function of a determination by element from among several elements of the
same type, during the learning of the instructions previously provided by at least
one air traffic controller to the system and of the information relative to the air
traffic control associated with said instructions, said element from among several
15 elements of the same type being a geographical sector from among several
geographical sectors and/or an air traffic controller role from among several roles
and/or a functionality of the electronic control system of the air traffic from among
several functionalities of said system.
According to a third aspect, the present invention proposes a test platform
20 for an air traffic control electronic control system delivering information relative to air traffic
control established as a function of input data representative of the state of the air traffic
control received by said system, said system further receiving, and processing, in the
operational phase, control instructions from air traffic control that are provided to it by at
least one air traffic controller,
5
said platform being adapted for collecting and storing a set of instructions previously
provided to the system by at least one air traffic controller and information relative to the air
traffic controller delivered by the system associated with said instructions;
- determining the algorithmic model for automatically determining instructions as a function
of information relative to the air traffic controller by learning, carried out by computer, of 5 a
neural network, as a function of said stored set of instructions and said stored information
relative to the air traffic and associated with said instructions;
- obtaining an electronic test device of the system including said algorithmic model for
automatically determining instructions;
10 - testing said system via said electronic test device.
According to a fourth aspect, the present invention proposes a test platform
including:
- an air traffic control electronic control system delivering information relative to
air traffic control established as a function of input data representative of the
15 state of the air traffic control received by said system, said system further
receiving, and processing control instructions from air traffic control that are
provided to it by at least one air traffic controller; and
- an electronic test device of said electronic system according to one of the claims
according to the second aspect of the invention.
20 These features and advantages of the invention will appear upon reading the
following description, provided solely as an example, and done in reference to the appended
drawings, in which:
- figure 1 shows a view of a test platform in one embodiment of the invention;
- figure 2 is a flowchart of steps implemented in one embodiment of the invention.
25 Figure 1 shows a test platform 1 of an air traffic control electronic control system. In
the considered example, the test platform 1 includes an air traffic control electronic control
system 2, called ATM system 2 hereinafter, and an electronic test device 6.
The ATM system 2 includes a memory 20, an MMI unit 21 and a processor 22.
The MMI unit 21 for example includes display screens, for instance touch-sensitive,
30 a speaker system, a keyboard, a microphone, etc.
Furthermore, the ATM system 2 is connected by telecommunication links to a set 4
of outside systems 4_1, 4_2, ..., 4_n.
These outside systems for example include aircraft, radars, weather stations,
telecommunication devices of other air traffic controllers, airport control rooms, etc.
35 The ATM system 2 is adapted for receiving, and storing in its memory 20, input data
(and the timestamp of such data).
6
This input data includes external data, i.e., which is delivered to it by the outside
systems 4_1, 4_2, ..., 4_n of the set 4 representing the current or future state of the airspace
(or a given sector of the airspace) for example and non-exhaustively including:
- for each aircraft currently or imminently in the sector: coordinates in 3
dimensions (3D), aircraft type, its heading, its speed, its flight plan5 ;
- current and future weather information;
- air traffic density indicators (such as the number of airplanes in the sector,
turbulence), data defining the current and future structure of the airspace (such
as the presence of military no-fly zones, air corridors, current and future
10 configuration of the airport (open runways, wind direction, available taxiways,
etc., surveillance data (as derived from primary and secondary radars, ADS-B,
WAM, etc. data);
- coordination messages with air traffic controllers operating on ATM systems
relative to adjacent sectors.
15 The ATM system 2 is further adapted for retrieving this data for the air traffic
controller, via the MMI unit 21.
The external data can further be processed (for example averaged, verified,
combined, analyzed, etc.) before retrieval.
The input data generally includes this processed data and its timestamp.
20 The ATM system 2 is further adapted for generating data internal to the ATM system
2, representative of its current state. It is in particular generated using probes or functions
installed in the ATM system 2 and for example, non-exhaustively, includes:
a queue of messages, shared data, logs, technical layouts, a focus action on a flight
tag, zoom in or zoom out factor on a given zone, voice conversation transcription between
25 a controller and an aircraft pilot, etc. The internal data is accessible to the air traffic controller
operating the ATM system 2 via the MMI 21. In one embodiment, the input data stored in
the memory 20 also includes this internal data, with the timestamp corresponding to said
data.
In one embodiment, the ATM system 2 is adapted for implementing upgraded
30 functions using the externals and generating internal data. These functions are carried out
for example using computer programs implementing the function, which are stored in the
memory 20 and executed on the processor 22. These functions for example include
detecting conflicts, identifying a collision risk between an aircraft and another aircraft, or a
risk of an aircraft entering a zone during a grounding period in the zone, etc., or determining
35 a solution making it possible to resolve the conflict. The results of these functions are
retrieved via the MMI 21, for the air traffic controller.
7
In a known manner, an air traffic controller operating the ATM system 2 can thus
learn, via the MMI 21, at each moment, of the current or future air traffic situation, as a
function of external data and/or as a function of internal data, including the results of the
upgraded functions. These data and results are provided to him via the MMI 21. Based on
these elements, the air traffic controller then makes decisions that he provides to the AT5 M
system 2 via the MMI 21 (in text or visual or voice form, etc.).
These decisions include instructions intended for aircraft and/or ATM systems of
controllers of adjacent sectors. They can thus include target flight altitude commands, target
speed commands (horizontal, vertical), target heading commands, target claim or descent
10 gradient commands, etc.
The electronic test device 6 includes a memory 61 and a processor 62. In the
memory 61, an artificial neural network 63 is in particular stored.
Figure 2 is a flowchart of steps implemented in one embodiment of the invention.
The neural network 63 is adapted, in a preliminary phase 101_0 for obtaining the
15 programmed network, for performing learning of the behavior of the air traffic controller(s),
from a history of input elements including external data of the ATM systems, and including,
in embodiments, internal data of the ATM systems and/or results of functions, and from a
history of output elements including the decisions made by the air traffic controllers in light
of these respective input elements.
20 This history is for example made from the collection over several months, from the
ATM system 2, or another ATM system similar to the ATM system 2 or from several
operational ATM systems, of all of these elements and their storage. In one embodiment,
said storage is done in the memory 20.
It will be noted that this preliminary phase 101_0 for learning of the neural network
25 63, according to the embodiments:
- is carried out, within the electronic test device 6, by using the memory 61 and the
processor 62, or
- is carried out on a specific learning platform (not shown), equipped with its own
memory and computing resources.
30 In one embodiment, for each test configuration, the preliminary phase 101_0
includes a preparation phase 101_01 for the input and output elements identifying which
are (the extracts of) those of the input and output elements useful for the test, in the
decision-making, as well as for example the minimum collection duration.
In a known manner, the preparation of these elements can include the segmentation
35 of the collected elements, the detection of missing elements and operations, the reduction
of the dimensions of the elements, the extraction of groups, the identification of causes and
8
relationships, and to finish, the definition of a set of training elements including input training
elements and associated output elements. For each test configuration, the preliminary
phase 101_0 includes a training phase 101_02 strictly speaking for the neural network 63
from input and output training elements associated with the set of training elements. One
neural network per test configuration is thus determined5 .
These principles of the definition of sets of training data, learning and use of neural
networks are well known, cf. for example:
- Tolk, A. (2015, July). The next generation of modeling & simulation: integrating
big data and deep learning. In Proceedings of the Conference on Summer
10 Computer Simulation (pp. 1-8). Society for Computer Simulation International;
- Akerkar, R. (2014). Analytics on Big Aviation Data: Turning Data into Insights.
IJCSA, 11(3),116-127;
- Boci, E., & Thistlethwaite, S. (2015, April). A novel big data architecture in
support of ADS-B data analytic. In Integrated Communication, Navigation, and
15 Surveillance Conference (ICNS), 2015 (pp. C1-1). IEEE;
- Bengio, Y. (2009). Learning deep architectures for AI. Foundations and
trends® in Machine Learning, 2(1), 1-127.
The result of the training phase 101_02 is the delivery 101_1 of a trained neural
20 network 63, also called (algorithmic) model air traffic controller. This model is next recorded
in the electronic device 6, which is then able to be used in the test phase 101_2 in order to
test the ATM system 2.
In embodiments, the input and output elements are structured by geographical air
sector, the training of the neural network then also being differentiated by sector, and the
25 behavior of the air traffic controller algorithmic model 63 obtained in step 101_1 being
specific to each sector.
Similarly, in embodiments, the sets of training elements are structured by technical
functionality of the ATM system (for example detection of conflicts or flight altitude
commands or coordination between controllers) or by specific role of an air traffic controller
30 (for example, command role or planning role and exchange with the adjacent sectors). In
such a case, the obtained trained model is then specific to a role or a functionality. Mixed
modes can further be generated, specific to at least two aspects among the sector,
functionality and role aspects.
Any type of artificial neural networks can be used. For example, a deep learning
35 network, a convolutional neural network (CNN) are used. The number of input nodes will be
9
chosen to be equal to the number of input elements and the number of output nodes will be
chosen to be equal to the number of output elements for each test configuration.
During a test phase 101_2 of the ATM system 2, the following steps are carried out
and reiterated:
- reception by the ATM system 2 of external data representative of the curren5 t
state of air traffic;
- establishment, by said ATM system 2, of information relative to the air traffic as
a function of said data, including at least some of the external data, as well as
updated internal data, for example results of functions of the ATM system 2, and
10 delivery, by said system 2, via the MMI 21, of information to the electronic test
device 6;
- determination, by the neural network 63 of the electronic test device 6, as a
function of the delivered information, of output elements including air traffic
control decisions; these decisions include instructions intended for aircraft
15 and/or ATM systems of controllers of adjacent sectors;
- and provision by the test device 6 via the MMI 21 to said ATM system 2 of said
output elements;
- reception and processing of said output elements by said system 2, including
the transmission of the decisions to the aircraft and/or to the ATM systems of
20 controllers of adjacent sectors.
The nonconformities of the system are detected during the test phase, by analysis
of the behavior of the system 2. This detection is done for example by the test device 6 or
any other means.
Several types of test targeting separate purposes can be implemented in the existing
25 test phase 101_2.
One type of test is for example an extensive verification test campaign, based on
actual input data (i.e., internal data, or even furthermore external data) of the ATM system
2, from which input data test sets of the controller model are randomly generated (some in
the accepted ranges, others outside the accepted ranges to test the robustness). The
30 decisions of the controller model 63 will be compliant with the behavior of the human
controller as learned.
Another type of test phase is for example a non-regression test campaign: in such
a case, one uses the test device 6 based on the controller model 63 generated before
upgrade of the ATM system 2, the ATM system 2 taking account of the upgrade by providing
35 the ATM system 2 with external input data equal to that having previously allowed this
controller model to learn. If there is no injection into the ATM system 2 of a functional
10
deviation of the specification (software bug, edge effect of a technical change such as
hardware update, etc.), it is expected that the test device 6 will deliver exactly the same
output decisions. Otherwise, there is potentially a regression in the ATM system 2 and
additional investigations must be conducted.
Another type of test phase is for example an endurance test campaign: such 5 a
campaign is similar to a non-regression campaign except that the objective is different. The
purpose of an endurance test campaign is to exploit the previous status of the nonregression
tests to build a service experience, which will be:
- done in an early stage of the lifecycle of the ATM system 2, i.e., before the
10 operational transition,
- done in an accelerated manner by duplicating many instances of the ATM
system 2 to be validated and many instances of models of controllers and test
input data sets.
An ATM system 2 evolving regularly, the updates, both functional (introduction of
15 new functions or modified functions) and technical (changes of hardware, operating system,
etc.), are to be taken into account in the tests. In such a situation, in one embodiment, the
algorithmic model 63 corresponding to the ATM system 2 before update is completed to
account for these updates. Thus in reference to figure 2, in a step 102_0, input elements
including internal data of the ATM systems, external data of the ATM systems, and output
20 elements including the decisions made by the air traffic controllers in light of these
respective input elements, are recorded and stored during validation sessions done by air
traffic controllers on a test platform representative of the operational platform relative to the
part of the ATM system 2 that is updated. The step 101_0 for obtaining a programmed
neural network is then carried out based on these input and output elements, and leads to
25 the delivery of an air traffic network controller model targeted on the part of the ATM system
2 that is updated. In step 101_1, a combination of the algorithmic model corresponding to
the ATM system 2 before update and the algorithmic model of the ATM system 2 targeted
on the updated aspects is done (for example, in embodiments, by a concatenation), thus
making it possible to deliver a complete algorithmic model corresponding to the updated
30 ATM system 2. Furthermore, in one embodiment, in a securing step 100_0, rules, principles,
constraints, conditions and prohibitions implemented by the air traffic controllers in the
application of their trade (for example corresponding to the ICAO standards as defined in
document 4444) are formalized in algorithmic form.
For example, these rules include that:
35 - a1/ an air traffic controller cannot provide commands regarding aircraft outside
the sector for which it is responsible,
11
- a2/ except for certain exceptions specifically defined by the conditions Cond1,
Cond2, Cond3;
- a3/ in a given situation corresponding to a given aircraft speed and altitude, a
commanded change in flight level altitude must be below a given threshold
depending on said speed and altitudes5 .
The resulting securing algorithm is, in one embodiment, implemented in a step
100_1 on the input and output training elements associated with the set of training elements
prior to the building of an air traffic controller model, which makes it possible to detect the
elements not conforming to the standardized practice, and next either to eliminate them
10 from the set of training elements, or to assign them to a "bad practice" class allowing the
model to better learn the behavior of the controller according to a "good practice".
In one embodiment, in a step 100_1, these rules, principles, constraints, conditions
and prohibitions implemented by the air traffic controllers in the application of their trade are
also provided as learning data to an artificial neural network and, at the end of the learning
15 phase, a model encompassing these rules is delivered, hereinafter called securing model.
In a step 101_3, each decision next made by the controller model 63 during the test phase
101_2 is provided to this securing model, which either validates the decision as conforming
to good practices (in particular validates that it is in the acceptable dynamic range for the
output decisions), or invalidates the decision, which is then not taken into account in the
20 context of tests and for example then enriches the class of "bad practice", which results in
reinforcing the air traffic controller model.
The present invention thus makes it possible to obtain an electronic test device 6
based on an air traffic controller model 63 learned by neural network.
In the test phases, the obtained air traffic controller model 63 can be duplicated and
25 each copy can be installed in the same electronic device 6 or installed in respective test
devices similar to the device 6; this makes it possible to increase the number and reach of
the tests done in parallel on the ATM system 2, or even on instances, also duplicated (on
the cloud, for example), of the ATM system 2. In embodiments of the test phase
implemented using these devices, the input data can be distributed among the different
30 models or devices, each model being assigned to a separate specific sector, or a separate
time period (peak hours, off-peak hours, weekly or monthly periods, etc.).
In another embodiment, the neural network model 63 is made in the form of a
programmable logic component, such as a GPU (Graphics Processing Unit) or multi-GPU.

CLAIMS
1.- A test method for an air traffic control electronic control system (2) delivering information
relative to air traffic control established as a function of input data representative of the state
of the air traffic control received by said system, said system further receiving, an5 d
processing, in the operational phase, air traffic control instructions that are provided to it by
at least one air traffic controller,
wherein said method comprises, during a test phase of said system, the following steps:
- reception by said system (2) of input data representative of the state of air traffic;
10 - establishment by said system of information relative to the air traffic as a function
of said input data and delivery by said system of said information to an electronic
test device (6) of the system;
- determination by said electronic test device (6) of the system, as a function of
the delivered information, of air traffic control instructions and providing said
15 system with said instructions;
- reception and processing of said instructions by said system;
according to which said electronic device (6) includes an algorithmic model (63) for
automatically determining instructions as a function of information relative to the air traffic,
said model having been obtained during a learning phase, carried out by computer, of a
20 deep learning neural network, as a function of a set of instructions previously provided by
at least one air traffic controller to the system and information relative to the air traffic
associated with said instructions.
2.- The test method for an electronic air traffic control system (2) according to claim 1,
25 comprising, during the test phase, the detection of one or more nonconformities of the
system as a function of the behavior of the system.
3.- The test method for an electronic air traffic control system (2) according to claim 1 or 2,
the algorithmic model (63) for automatically determining instructions has been learned in
30 order to determine instructions specific to at least one element, as a function of a
determination by element from among several elements of the same type, during the
learning of the instructions previously provided by at least one air traffic controller to the
system and of the information relative to the air traffic control associated with said
instructions, said element from among several elements of the same type being a
35 geographical sector from among several geographical sectors and/or an air traffic controller
13
role from among several roles and/or a functionality of the electronic control system (2) of
the air traffic from among several functionalities of said system.
4.- A method for testing an air traffic management electronic system according to one of
claims 1 to 3, comprising the steps of5 :
- determining an algorithmic constraint module adapted for identifying instructions not
compliant with the rules of the air traffic controllers;
- applying said algorithmic module to the set of instructions previously supplied by at least
one air traffic controller to the system and removing said instructions identified as not
10 compliant from the set used for the learning of the neural network;
- applying said algorithmic module to the instructions determined by the electronic test
device and not considered in the phase for testing instruction(s) identified as not compliant.
5.- The test method for an electronic air traffic control system (2) according to one of claims
15 1 to 4, comprising, in a phase preliminary to the test, the steps of:
- collecting and storing a set of instructions previously provided to the system by at least
one air traffic controller and information relative to the air traffic controller delivered by the
system associated with said instructions;
- determining the algorithmic model (63) for automatically determining instructions as a
20 function of information relative to the air traffic controller by learning, carried out by
computer, of a neural network (63), as a function of said stored set of instructions and said
stored information relative to the air traffic and associated with said instructions.
6.- An electronic test device (6) of an air traffic control electronic control system (2)
delivering information relative to air traffic control established as a function of input data
representative of the state of the air traffic control received by said system, said system
further receiving, and processing air traffic control instructions that are provided to it by at
least one air traffic controller,
wherein said electronic test device (6) is adapted for receiving information relative to the air
traffic delivered by the system (2) and in that it includes an algorithmic model (63) for
automatically determining instructions as a function of information relative to the air traffic,
said model having been obtained during a learning phase, carried out by computer, of a
deep learning neural network, as a function of a set of instructions previously provided by
at least one air traffic controller to the system and information relative to the air traffic
associated with said instructions.
14
7.- The electronic test device (6) according to claim 6, adapted for detecting the
nonconformity of the system as a function of the behavior of the system.
8.- The electronic test device (6) according to claim 6 or 7, wherein the algorithmic model
(63) for automatically determining instructions has been learned in order to determin5 e
instructions specific to at least one element, as a function of a determination by element
from among several elements of the same type, during the learning of the instructions
previously provided by at least one air traffic controller to the system and of the information
relative to the air traffic control associated with said instructions, said element from among
10 several elements of the same type being a geographical sector from among several
geographical sectors and/or an air traffic controller role from among several roles and/or a
functionality of the electronic control system (2) of the air traffic from among several
functionalities of said system.
15 9.- A test platform for an air traffic control electronic control system (2) delivering information
relative to air traffic control established as a function of input data representative of the state
of the air traffic control received by said system, said system further receiving, and
processing, in the operational phase, air traffic control instructions that are provided to it by
at least one air traffic controller,
20 said platform being adapted for collecting and storing a set of instructions previously
provided to the system by at least one air traffic controller and information relative to the air
traffic controller delivered by the system associated with said instructions;
- determining the algorithmic model (63) for automatically determining instructions as a
function of information relative to the air traffic controller by learning, carried out by
25 computer, of a neural network (63), as a function of said stored set of instructions and said
stored information relative to the air traffic and associated with said instructions;
- obtaining an electronic test device (6) of the system (2) including said algorithmic model
(63) for automatically determining instructions;
- testing said system (2) via said electronic test device (6).
30
10.- A test platform (1) including:
- an air traffic control electronic control system (2) delivering information relative
to air traffic control established as a function of input data representative of the
state of the air traffic control received by said system, said system further
35 receiving, and processing control instructions from air traffic control that are
provided to it by at least one air traffic controller; and
15
- an electronic test device of said electronic system according to one of claims 6
to 8.