Improved radar system; Configuration method and associated computer program products.

Abstract

Improved radar system; Configuration method and associated computer program products. The present invention relates to a radar system (10) comprising a radar (12) and a computer (14), characterized in that the radar system (10) is provided with an electronic warfare functionality making it possible to associate with a radar spectrum (S) for observation of a target object, an identifier (Id) of the type of radiofrequency source - RF corresponding to said target object, the computer executing an identification algorithm so as to provide the radar system with the electronic warfare functionality, an identifier of the type of RF source deriving from an electronic warfare reference library. Figure for the abstract: Figure 1

Description

Title of the invention: Improved radar system; Configuration method and associated computer program products.

[0001] The technical field of the invention is that of electronic warfare and, more particularly, that of the identification of radiofrequency sources - RF present in the environment.

[0002] An electronic warfare system - GE is a dedicated system for automatically identifying an RF source from its electromagnetic signature.

[0003] GE systems are known which are adapted to, from electromagnetic waves collected by different sensors, detect a source, track this source over time, and, from a track, identify the type to which the corresponding source belongs.

[0004] For identification, the GE system relies on a reference library listing different types of source, and for each type of source, its characteristic attributes.

[0005] The identification consists for example in providing a list of candidates, a candidate being a type of source that can be associated with the detected source with a certain probability.

[0006] Once an identification has been made, the GE system, for example, controls a jammer or a radar system, in particular in order to obtain additional information on the identified RF source.

[0007] For example, a GE system often only gives the azimuth of the RF source. The radar system will then make it possible to locate this source by giving the elevation and especially the distance.

[0008] However, this architecture combining a GE system and a radar system lacks robustness. In particular, when the GE system fails, any source identification is made impossible.

[0009] The aim of the invention is to meet this need.

[0010] For this purpose, the invention relates to a radar system comprising a radar and a computer, characterized in that the radar system is provided with an electronic warfare functionality making it possible to associate with a radar observation spectrum of a target object, a radiofrequency source type identifier - RF corresponding to said target object, the computer executing an identification algorithm so as to provide the radar system with the electronic warfare functionality, an RF source type identifier deriving from an electronic warfare reference library.

[0011] According to particular embodiments, the radar system comprises one or more of the following characteristics, taken in isolation or in all technically possible combinations:

[0012] - the RF source type identifier is a list of candidates, each candidate being associated with a probability, the electronic warfare reference library referencing the various possible candidates.

[0013] - the identification algorithm is an artificial intelligence algorithm properly configured.

[0014] - the artificial intelligence algorithm is a similarity algorithm or a classification algorithm.

[0015] The invention also relates to a computer program comprising software instructions which, when executed by a computer of the preceding radar system, provide said radar system with an electronic warfare functionality.

[0016] The invention also relates to a method for configuring and using an identification algorithm making it possible to associate, with an observation radar spectrum of a target object, a radiofrequency source type identifier - RF corresponding to said target object, comprising: a phase of populating a training database by automatically labeling a radar spectrum obtained by means of a radar system with a true RF source type identifier obtained by means of an electronic warfare system, said electronic warfare system relying on an electronic warfare reference library; a training phase consisting of training and / or validating, using batches of labeled data from the training database, the identification algorithm so as to obtain a suitably parameterized identification algorithm;and, an operational phase in which the suitably parameterized identification algorithm is used in inference in order to associate with an observation radar spectrum of a target object present in the environment, an RF source type identifier.;

[0017] According to particular embodiments, the method comprises one or more of the following characteristics, taken in isolation or in all technically possible combinations:

[0018] - the population phase consists of: acquiring a radar spectrum by means of a radar system; obtaining, by means of an electronic warfare system, an RF source type identifier for an RF source detected and tracked by the electronic warfare system at the time of acquisition of the radar spectrum; and associating, in a labeled data item, the radar spectrum and the RF source type identifier delivered by the electronic warfare system as a true RF source type identifier of said radar spectrum.

[0019] - a radar spectrum being a raw radar spectrum, the method further comprises, a normalization step making it possible, from the raw radar spectrum, to obtain a normalized radar spectrum, said normalized spectrum being an input to the identification algorithm.

[0020] - the pre-processing step comprises a step of extracting one or more intermediate magnitude(s) of the radar spectrum so as to define a characteristic signature of the radar spectrum, said characteristic signature being an input to the identification algorithm.

[0021] The invention also relates to a computer program comprising software instructions which, when executed by a computer, allow the implementation of the preceding method.

[0022] The invention and its advantages will be better understood on reading the detailed description which follows of a particular embodiment, given solely as a non-limiting example, this description being made with reference to the appended drawings in which:

[0023] [Fig-1] [Fig.l] is a schematic representation of an embodiment of a radar system with electronic warfare functionality;

[0024] [Fig.2] [Fig.2] is a schematic representation of a configuration system for implementing the radar system configuration method of [Fig.l]; and,

[0025] [Fig.3] [Fig.3] is a block representation of the method of configuration according to the invention.

[0026] [Fig.l] schematically represents a preferred embodiment of a radar system according to the invention.

[0027] The radar system 10 associates a radar 12 (i.e. an antenna, transmission electronics and reception electronics) with a computer 14.

[0028] The radar 12 is adapted to deliver a raw signal s.

[0029] The radar 12 is for example a pulse radar. At each recurrence, the radar 12 emits, during an emission duration (or illumination time), an electromagnetic wave, then receives, during a reception duration, a received wave resulting from the reflection of the emitted wave on reflective objects present in the observation domain of the radar.

[0030] The computer 14 is programmed so as to provide the radar system 10 with various functionalities, including, in particular, a GE functionality for identifying RF sources present in the environment.

[0031] For this, according to the functional representation of [Fig.l], the radar system 10 comprises a module 22 for preprocessing the raw signal s to obtain a succession of spectra S, a module 24 for normalizing a spectrum S to obtain a spectrum standardized S', and a module 26 for identifying an RF source from a standardized spectrum S' so as to deliver an identifier Id.

[0032] The preprocessing module 22 makes it possible to apply one or more preprocessing operations, in accordance with the state of the art, to the raw signal s at the output of the reception electronics of the radar 12, to obtain a plurality of radar spectra.

[0033] More precisely, the raw signal is a signal sampled temporally at the rate of the analog / digital encoders of the radar acquisition electronics. These samples are “classified” (distance dimension) according to their delays relative to the start of each recurrence (recurrence dimension).

[0034] The raw signal is thus sampled temporally both according to a short time, corresponding to the distance dimension d, and according to a long time, corresponding to the recurrence dimension rec.

[0035] This sampling step makes it possible to obtain distance-recurrence samples E(d, rec) of the raw signal.

[0036] A processing is then applied consisting of carrying out a fast Fourier transform FFT according to the recurrence dimension, so as to distribute the spectrum over frequency channels. Distance-frequency samples E(d, f) are thus obtained from the distance-recurrence samples E(d, rec).

[0037] A sample E(d, f) is obtained by performing an FFT on a block of N' successive samples E(d, rec) according to the dimension in recurrence for the distance d considered. N' is for example chosen equal to 1024.

[0038] Frequency resolution boxes rf. are juxtaposed according to the frequency dimension. The frequency interval is subdivided into N frequency boxes, with for example N equal to 1024.

[0039] The frequency resolution rf depends on the duration of a block: tb = N.Tr, with Tr the duration of a recurrence:

[0040] r / =^

[0041] These samples E(d, f) can be represented in matrix form, by a distance-speed matrix presenting H rows according to the frequency dimension and W columns according to the distance dimension, each pixel corresponding to amplitude information.

[0042] Alternatively, the samples E(d, f) can be represented as a succession of radar spectra S according to the distance direction d. A radar spectrum is therefore a frequency-amplitude spectrum.

[0043] The normalization module 24, which is optional, advantageously makes it possible to normalize a radar spectrum S so as to obtain a normalized spectrum S'. In particular, the distance d is taken into account to normalize the amplitude of the spectrum. An example of normalization is given at the end of the description. Other additional information may be taken into account, such as the height of the carrier aircraft, the antenna elevation (or "tilt" in English) of the radar system, the speed of the carrier, etc.

[0044] The identification module 26 makes it possible to associate with a radar spectrum, raw S but preferably normalized S', an identifier Id corresponding to the type of RF source to which the RF source belongs that it is possible to associate with the object observed by the radar 12 in the spectrum considered. The identifier can consist of a list of candidates, each candidate being a type of source that can be associated with the detected source with a certain probability.

[0045] Thus, with the invention, the radar system 10 has an additional functionality of RF source identification from the acquisition of a radar spectrum.

[0046] In a preferred embodiment, the module 26 is an artificial intelligence algorithm - AL. This is suitably parameterized by the implementation of a configuration method, such as the method 100 of [Fig.3].

[0047] The implementation of the configuration method is based on a configuration system, such as for example that represented in [Fig.2].

[0048] The system 1 is advantageously carried on board an aircraft to carry out in-flight measurement campaigns making it possible to dynamically populate a training database 60.

[0049] The system 1 comprises a radar system 10' associated with an electronic warfare system - GE 30. The system 1 also comprises a computer 50 and the training database 60.

[0050] The radar system 10' is similar to the radar system 10. It comprises a radar 12 and a computer 14', the latter being programmed to comprise the preprocessing module 22 and the normalization module 24, when such a module is implemented.

[0051] The radar system 10' is only used to produce raw or normalized spectra. It therefore does not include the identification algorithm 26 of the radar system 10.

[0052] The GE 30 system is in accordance with the state of the art. It is suitable for detecting RF sources in the environment and for identifying the nature of the detected RF sources. An RF source is, for example, a radar of a threatening aircraft, a radiocommunication antenna, etc.

[0053] The GE system 30 associates a plurality of sensors 32 and a computer 34.

[0054] A sensor is a wideband sensor, such as a sensor operating from the L band (1 GHz) to the Ka band (40 GHz). It may, for example, be an electronic support measure (ESM) sensor, in particular to capture signals emitted by radars - RESM (“Radar Electronic Support Measures”), and / or communication systems - CESM (“Communication Electronic Support Measures”).

[0055] The computer 34 is suitably programmed to include a detection module 42, a tracking module 44 and an identification module 46.

[0056] The detection module 42 processes the signals delivered by the sensors so as to construct a synthetic object. A synthetic object provides, for example, a list of the frequencies captured, a list of the pulse durations captured, etc.

[0057] The tracking module 44 processes the synthetic objects output by the module 42 so as to create tracks, one track corresponding to the tracking of an RF source over time.

[0058] The identification module 46 is adapted to identify an RF source from a track at the output of the module 44.

[0059] This identification is carried out by comparison with a reference library 48. The reference library groups together a plurality of types of RF source.

[0060] Identifying an RF source preferably involves associating a list of possible candidates with an observed track. A candidate is a type of RF source from the reference library whose track matches the observed track with a certain probability.

[0061] The computer 50 is connected on the one hand to the computer 14' of the radar system 10 and on the other hand to the computer 34 of the electronic warfare system 30.

[0062] In the embodiment of [Fig.2], the computer 50 is on board the aircraft carrying the radar system 10' and the electronic warfare system 30. It is for example connected directly to the output of these systems.

[0063] Alternatively, the computer 50 is on the ground and communication with the radar system and the GE system is carried out by means of a suitable air link, or in delayed time, the information collected by the radar system on the one hand and by the GE system on the other hand being processed by the computer 50 at the end of a measurement campaign.

[0064] The computer 50 of the system 1 allows automatic labeling of a radar spectrum delivered by the radar system 10' with the identification delivered by the GE system 30 at the same time.

[0065] The identification given by the GE 30 system is therefore considered to be the true identification.

[0066] The computer 50 is adapted to store the labeled data thus obtained, in the training database 60.

[0067] Labeled data therefore associates:

[0068] - a radar spectrum, preferably normalized, i.e. an input to the algorithm of identification AI 26;

[0069] - a label or tag corresponding to the true identifier of the RF source to be associated with this spectrum.

[0070] The system 1 comprises a computer 70 allowing, once the base 60 is populated with a sufficient number of labeled data, to train the identification AI algorithm 26 from the database 60. The computer 70 and the computer 50 can be the same computer.

[0071] [Fig. 3] represents a preferred embodiment of a configuration method according to the invention.

[0072] The first phase 110 of the method 100 consists of automatically populating the training database 60 with labeled data using the system 1.

[0073] The radar system observes the same spatial region as the GE system, the GE system having advantageously previously transmitted at least one azimuth information from a tracked RF source to the RADAR system.

[0074] In a step 112, the radar system 10' acquires a raw radar spectrum of a domain observed by the radar 12 of the system 10' at the current time. This spectrum contains an observed target object. Optionally, this raw spectrum can be immediately normalized.

[0075] Simultaneously, in step 114, reference information is obtained by means of the GE system 20. The reference information is the RF source identification performed by the GE system 20 at the current time. This identifier corresponds to the detection and tracking of an RF source.

[0076] It should be noted that the observations of the radar system and the GE system are synchronized, or at least a temporal correlation is established making it possible to associate a radar spectrum delivered by the system 10' and an identifier Id delivered by the GE system 30. Thus the RF source identified by the GE system 30 is related to (is on board) the object observed by the radar system 10'.

[0077] In this particularly simple embodiment, the sole synchronization of the two systems (which observe the same region of the environment) makes it possible to match a radar spectrum and an RF source type identifier.

[0078] Alternatively, the object observed by the radar system is tracked (by implementing means known to those skilled in the art). It is then the correlation of the track given by the radar system with that given by the GE system which makes it possible to match the radar spectrum and the RF source type identifier.

[0079] Finally, the method 100 comprises a step 116 consisting of associating the radar spectrum, raw or normalized, obtained in step 112 with the identifier determined in step 114 as the true identifier of the radar spectrum. This association leads to a labeled radar spectrum.

[0080] In a step 118, the labeled spectrum obtained in step 116 is recorded in the training database 60 as new labeled data for training.

[0081] The spectrum acquisition conditions may be recorded with the labeled spectrum. This includes, for example, additional information, such as the height of the carrier aircraft, the distance from the target object, the antenna elevation (or "tilt" in English) of the radar system, the speed of the carrier, etc., used for the normalization of the raw spectrum when such a step is implemented, at step 112 or, alternatively, later in a deferred-time approach.

[0082] Once the training database 60 is sufficiently populated, the labeled radar spectra are used, in a learning phase 120 of the method 100, for training the RF source identification AI algorithm 26.

[0083] The training itself consists of progressively modifying the parameters of the algorithm 26 so that the identifier estimated by this algorithm on a radar spectrum approaches the true identifier associated with this same radar spectrum in the corresponding labeled data.

[0084] Once suitably trained, the artificial intelligence identification algorithm is downloaded into the computer 14 of a radar system 10 for a phase of use 130 of the method 100 during which the algorithm 26 operates in inference. From a radar spectrum S newly acquired by the radar system 10, the latter automatically determines an identifier Id characterizing the RF source, which represents the observed object.

[0085] The RF source types identifiable by the radar system 10 correspond to those in the reference library used by the GE system 30 to label the data.

[0086] This identifier can be used to choose or optimize radar processing adapted to the radar spectrum to extract additional information on the object corresponding to the RF source.

[0087] In the following a first particular embodiment of the identification AI algorithm 26 is presented.

[0088] This embodiment consists of learning a similarity function between two radar spectra.

[0089] Following an identification request on a track, the identification module 46 (which is not the subject of the present patent application), associates several candidates with said track, each candidate being associated with a probability, which quantifies the similarity between the characteristics of the detected track and the characteristics of the candidate (the characteristics of the candidate being provided by the reference library).

[0090] Following labeling, each radar spectrum is associated with an RF source identifier. An example of such associations is for example: - The SI spectrum corresponds to candidate A with probability 0.9, to candidate B with probability 0.87 and to candidate C with probability 0.7; - The spectrum S2 corresponds to candidate B with a probability of 0.35 and to candidate D with a probability of 0.9; and, - The spectrum S3 corresponds to candidate E with a probability of 0.92, to candidate F with a probability of 0.8 and to candidate G with a probability of 0.61.

[0091] Two spectra Sx and Sy are considered similar if they meet a similarity criterion. This can be defined, for example, as: two spectra are considered similar when the same candidate is identified with a high probability (for example, greater than a predefined similarity threshold) in the two lists associated by the GE system with these two spectra. Otherwise, these two spectra are considered dissimilar.

[0092] In the previous example, the SI and S2 spectra are similar because candidate B is common to both lists with a probability greater than 0.6 (as an example of a threshold value), while the SI and S3 spectra or the S2 and S3 spectra are dissimilar because they do not have a common candidate.

[0093] The objective of the learning is then to determine a function f:

[0094] f(Sx): Sx ^ y epM A J x

[0095] allowing to project a spectrum Sx into a latent space of dimension M. For example, M is chosen to be equal to 2, Yx being the projection of the spectrum Sx into this latent space.

[0096] The learning consists in bringing closer, in the latent space, the pairs of spectra that are similar and in separating the pairs of dissimilar spectra.

[0097] At the end of the learning, the learned similarity function f associates two similar spectra with two close projections in the latent space and two dissimilar spectra with two distant projections in the latent space.

[0098] In the operational phase, following the acquisition of a spectrum, for example S4, by the radar system 10, the learned function f is applied to this spectrum to determine its projection ^4 in the latent space.

[0099] Then, in a neighborhood of the 5'4 projection, we search for projections of labeled spectra from the database 60.

[0100] For example, this search consists of identifying all the projections of labeled spectra present in a hypersphere of radius R centered on the projection ^4. When M is equal to 2, the hypersphere is the disk of radius R and center Y4.

[0101] Advantageously, we limit ourselves to a maximum number of spectrum projections labeled.

[0102] For example, in the neighborhood of ^4, we find the projections and ^2 of the spectra SI and S2.

[0103] Then, the candidates to be associated with the spectrum S4 are those of the spectra Si and S2. For example, the identifier of S4 is the union of the identification candidates of St and S2, denoted Sj U S2, or the candidates A, B, C and D in the previous example. The probabilities of the different candidates associated with S4 are calculated from the probabilities of the candidates associated with Si and the probabilities of the candidates associated with S2 and, advantageously from the distance between )4 and ^i, on the one hand and ^4 and Y2, on the other hand.

[0104] A second possible embodiment of the identification AI algorithm 26 is based on a classification approach, in particular a multi-label classification, according to which an input can be associated with several output classes.

[0105] In this approach, and in order to be able to provide several candidates for a track, the objective function used is, for example, the binary cross-entropy:

[0106] Let JJ e ¢0,1 ]]J ' with 1 the number of candidates, be the true label of a spectrum S. For example, if J = 3 and candidates 1 and 2 are expected with certainty, then Id = (1 1 0)-

[0107] The objective function which is minimized during learning is then, for a given radar spectrum S, and noting jg _ gj e ^g jj', the output of the neural network parameterized by the parameter 0 and applied to the radar spectrum S; 101081 A(ld, Q) = + (1 - ïïiMl-Idj)

[0109] where j is an integer between 1 and J, and Id; the jth coordinate of the label Id and [g the jth coordinate of the true label jg.

[0110] It should be noted that it is possible to keep only candidates whose probability is greater than a certain probability threshold during learning. For example, only candidates whose probability is greater than 0.7 are kept and used during learning.

[0111] During the operational phase, where the AI ​​algorithm is used in inference, the output Id G [() if is available and, just as during learning, it is possible to keep only the candidates associated with a high probability, i.e. greater than a threshold T:

[0112] 1 if Id; > T 0 otherwise

[0113] In an alternative embodiment, the module 46 does not implement an algorithm of AI, but a procedure based on simple probability calculation.

[0114] During a measurement campaign, each type of carrier is characterized by a plurality of radar spectra.

[0115] The shape of the radar spectra is representative of the nature of the carrier illuminated by the radar and therefore provides a signature of the carrier.

[0116] Batches of training data consisting of radar spectra are recorded.

[0117] In practice, the GE system identifies a track by associating a list of several candidates with it.

[0118] Thus a list of candidates is associated with each spectrum:

[0119] Sx = {RADAR A: P = Pa; RADAR B: P = Pb; ... ; RADAR n: P = Pn]

[0120] Taking the previous example:

[0121] If = {RADAR A:p=0.9; RADAR B:p=0.87; RADAR C:p=0.7 RADAR D:p=0; RADAR E:p=0; RADAR F:p=0; G:p=0]

[0122] S2 = {RADAR A:p=0; RADAR B:p=0.65; RADAR C:p=0; RADAR D:p=0.9 E:p=0; F:p=0; G:p=0}

[0123] S3={RADAR A:p=0; RADAR B:p=0; RADAR C:p=0; RADAR D:p=0;E:p=0.92; F:p=0.8; G:p=0.61}

[0124] To label a particular radar spectrum, the best candidate must be identified from among the set of lists provided by the GE system.

[0125] The following method is for example implemented:

[0126] - Identify which candidate from list Li has the highest probability Maxi;

[0127] - Calculate the sum Sumi of the probabilities of the candidates in the list Li;

[0128] - Calculate the ratio Ri for the list Li: Ri = Maxi / Sumi;

[0129] - Average the ratios Ri over all the lists to obtain the value of a probability threshold Rmoy;

[0130] - Determine, for each list Li, the candidates whose probability is above the Rmoy threshold, to identify the predominant candidates;

[0131] - Count, on all the lists Li, how many times each candidate is came out;

[0132] - Label the radar spectrum with the candidate that appears most frequently.

[0133] Alternatively, the n most frequent candidates are associated with a particular radar spectrum.

[0134] This list of candidates can be improved from one measurement campaign to another. In particular, when candidate A is in the majority with a different distribution of probabilities for the other candidates X, then the probabilities become:

[0135] px= Efo+X,)

[0136] where xl is the probability associated with candidate X following a first campaign while candidate A is in the majority, and x2 is the probability associated with candidate X following a second campaign of measures, while candidate A still has the majority.

[0137] Alternatively, one or more newly labeled radar spectra are used immediately to configure the identification module 26. This variant is particularly interesting for allowing, following a first training of the module 26, an update of the parameters of this module 26 in order to expand its identification capabilities. This is therefore a “real-time” training, for example during an operational flight, as opposed to a “delayed-time” training, for example following a measurement campaign making it possible to populate the training database, then to carry out the training of the identification algorithm, for example on the ground on another computer.

[0138] For example again, it is not a radar spectrum, raw or standardized, which constitutes the input of the identification algorithm, but a set of intermediate quantities extracted from the radar spectrum and making it possible to define a characteristic signature of the radar spectrum, raw or standardized.

[0139] This may, for example, be a statistical quantity extracted from the radar spectrum, raw or normalized, or even minimum and maximum quantities in amplitude and / or frequency of the spectrum.

[0140] This may involve, for example, associating a plurality of attributes with the spectrum by comparison with a plurality of reference spectra present in a reference database.

[0141] Those skilled in the art will note that the invention ultimately consists of teaching a radar system to identify RF sources, based on the identification results obtained by another system, in this case an electronic warfare system, taken as a reference. This reference system is independent of the radar system.

[0142] It is therefore supervised learning with criteria from another system already trained. There is therefore a transfer of the experience acquired by the reference system, or teacher system, to the radar system, or student system.

[0143] The invention has numerous advantages:

[0144] The step of normalizing and / or extracting a signature from the spectrum makes it possible to reduce the space of the radar spectra, which facilitates the identification and training of the AI ​​algorithm. Consequently, this makes it possible to further reduce the number of flight campaigns necessary for populating the training database.

[0145] The labeled data is generated automatically, without human intervention. The method according to the invention makes it possible to dispense with the need for experts capable of recognizing the nature of an RF source from radar data.

[0146] The field of application of the invention is that of radars, in particular airborne, for observation, surveillance, etc.

[0147] Advantageously, the radar system augmented with an identification functionality is used in combination with a GE system so as to be ready to replace the latter in the event of a malfunction. This makes it possible to continue the mission with the radar system alone.

[0148] In the following, one way of carrying out the normalization step is presented.

[0149] The amplitudes and frequency spread of a spectrum generally depend on the height H of the carrier, the elevation angle a of the beam, and the beam aperture 0.

[0150] In absolute terms, it would be necessary to record spectra for different configurations in the database, i.e. several heights, several elevation angles and several apertures. But this solution would then require acquiring a large number of spectra and, consequently, would increase the necessary number of flight measurement campaigns.

[0151] It is therefore preferable that the identification is done on standardized rather than raw spectra.

[0152] For a fixed antenna aperture and beam site, the greater the height, the more the spectrum is spread (due to the increase in distances) and the lower the amplitudes.

[0153] Normalization then consists of reporting the different raw spectra on the same scales in amplitudes and frequencies. The scales are for example those of a calibration spectrum.

[0154] To normalize a raw spectrum along the frequency axis, its spectral spread Es is compensated.

[0155] It is shown that the spectral spread is written, as a function of the height, the elevation angle and the aperture:

[0156] iii \ Es= 2.KH -7¼ - -7¼ 13 \ cos[a+—) cos(a+— J y

[0157] with K a coefficient equal to the ratio of the emitted frequency band to the recurrence period, H the height, a the elevation angle and 0 the beam opening

[0158] The first step therefore consists of normalizing the raw spectrum along the frequency axis by applying a scale factor Eg0 / E , where Es is the spectral spread of the raw spectrum and Eso is the spectral spread of the calibration spectrum.

[0159] The second step consists of adjusting the amplitudes of the raw spectrum along the amplitude axis by applying a scale factor A2, where A is the maximum amplitude of the raw spectrum and A0 the maximum amplitude of the calibration spectrum.

[0160] In a third step, the normalized spectrum is obtained by taking a sample on R, with , where D is the maximum frequency of the raw spectrum and DO the frequency A) maximum of the calibration spectrum.

Claims

Claims

1. Radar system (10) comprising a radar (12) and a computer (14), characterized in that the radar system (10) is provided with an electronic warfare functionality making it possible to associate with a radar spectrum (S) for observation of a target object, an identifier (Id) of the type of radiofrequency source - RF corresponding to said target object, the computer executing an identification algorithm so as to provide the radar system with the electronic warfare functionality, an identifier of the type of RF source deriving from an electronic warfare reference library.

2. The radar system of claim 1, wherein the RF source type identifier (id) is a list of candidates, each candidate being associated with a probability, the electronic warfare reference library referencing the various possible candidates.

3. A radar system according to claim 1 or claim 2, wherein the identification algorithm is an artificial intelligence algorithm.

4. The radar system of claim 3, wherein the artificial intelligence algorithm is a similarity algorithm or a classification algorithm.

5. Computer program comprising software instructions which, when executed by a computer (2) of a radar system according to any one of claims 1 to 4, provide said radar system (10) with electronic warfare functionality.

6. A computer-implemented method (100) comprising: - a phase (110) of populating a training database (60) by automatically labeling a radar spectrum obtained by means of a radar system (10') with a true RF source type identifier obtained by means of an electronic warfare system (30), said electronic warfare system relying on an electronic warfare reference library; - a training phase (120) consisting of training and / or validating, using batches of labeled data from the training database, an identification algorithm so as to obtain a trained identification algorithm; and, - an operational phase (130) in which the trained identification algorithm is used in inference in order to associate with an observation radar spectrum of a target object present in an environment, an RF source type identifier.

7. Method according to claim 6, in which the populating phase consists of: - acquiring (110) a radar spectrum by means of a radar system (10'); - obtaining, by means of an electronic warfare system (30), an RF source type identifier for an RF source detected and tracked by the electronic warfare system at the time of acquisition of the radar spectrum; and, - associating (150), in a labeled data item, the radar spectrum and the RF source type identifier delivered by the electronic warfare system as a true RF source type identifier of said radar spectrum.

8. Method according to any one of claims 6 to 7, in which a radar spectrum being a raw radar spectrum (S), the method further comprises a normalization step making it possible, from the raw radar spectrum, to obtain a normalized radar spectrum (S'), said normalized spectrum being an input of the identification algorithm.

9. Method according to any one of claims 6 to 8, in which the method comprises a pre-processing step comprising a step of extracting one or more intermediate quantity(ies) from the radar spectrum so as to define a characteristic signature of the radar spectrum, said characteristic signature being an input to the identification algorithm.

10. A computer program comprising software instructions which, when executed by a computer, enable the implementation of a method according to any one of claims 6 to 9.

Images