CN112036074A - Radar signal sorting method and system under high pulse density environment - Google Patents
Radar signal sorting method and system under high pulse density environment Download PDFInfo
- Publication number
- CN112036074A CN112036074A CN202010731268.8A CN202010731268A CN112036074A CN 112036074 A CN112036074 A CN 112036074A CN 202010731268 A CN202010731268 A CN 202010731268A CN 112036074 A CN112036074 A CN 112036074A
- Authority
- CN
- China
- Prior art keywords
- pulse
- radar
- sorting
- repetition frequency
- toa
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000001208 nuclear magnetic resonance pulse sequence Methods 0.000 claims abstract description 33
- 230000015654 memory Effects 0.000 claims abstract description 27
- 238000013507 mapping Methods 0.000 claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 claims abstract description 21
- 230000008859 change Effects 0.000 claims abstract description 19
- 210000002569 neuron Anatomy 0.000 claims description 15
- 210000004205 output neuron Anatomy 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 7
- 230000005855 radiation Effects 0.000 description 7
- 230000006872 improvement Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000001351 cycling effect Effects 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003292 diminished effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/28—Details of pulse systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention belongs to the technical field of radar signal sorting in electronic countermeasure, and discloses a method and a system for sorting radar signals in a high-pulse-density environment, wherein received radar pulse description words are divided according to pulse arrival angles to obtain a plurality of groups of pulse sequences from different directions; inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade structure self-organizing mapping neural network to obtain a primary sorting result; obtaining a main sorting result by using an improved sequence difference value histogram algorithm on the primary sorting result; and traversing the combination condition of the main sorting results, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time and short-time memory network for repetition frequency identification, and combining to obtain the repetition frequency group-variable radar. The invention can effectively realize the separation of common radar signals (fixed repetition frequency, staggered repetition frequency, jittering repetition frequency, sliding repetition frequency, group repetition frequency change, and the like) in a high pulse density environment, and can realize the real-time separation of the radar signals in an actual electromagnetic environment.
Description
Technical Field
The invention belongs to the technical field of radar signal sorting in electronic countermeasure, and particularly relates to a method and a system for sorting radar signals in a high-pulse-density environment and application.
Background
Currently, radar signal sorting is generally to evaluate and acquire the number of radar radiation sources existing in the current electromagnetic environment. With the continuous improvement of the technical demand of radar and the continuous innovation and development of various processing means and technologies aiming at modern signals, a plurality of radars with new systems are continuously developed, developed and applied to practice. Particularly, the application of novel radars such as pulse compression radar and agile radar makes the specific position information of the radar not be effectively detected, especially in more and more complex electromagnetic environments. In order to effectively improve the sorting capability of radar signals and ensure that the radar system has good evaluation effect on complex electromagnetic battle environments. Currently, the radar signal sorting in the field of radar countermeasure mainly focuses on sorting algorithms based on intra-pulse information, and sorting research aiming at inter-pulse information still stays at an earlier research level. Prior art one discloses a minimum L1The method has higher sorting efficiency aiming at the problem of sorting the radar signals in the highly dense and complex signal environment, but the method is required to have stronger correlation or matching with input signals and certain adaptability, can evolve by self, and has low sorting accuracy and reliability of the radar signals when the correlation between the signals and an over-complete dictionary is low; the second prior art discloses a multimode radar signal sorting method based on data field hierarchical clustering, which is characterized in that the maximum value of a local potential value is searched by calculating the potential value of a data field, sample data closest to the maximum value is selected as an initial clustering center, then clustering is carried out by using a traditional clustering algorithm, and the radar signal sorting method is used for the radar signal sorting under the environment of high density and complex signalsThe method has the problems of higher sorting efficiency, but higher operation complexity and larger calculated amount of the data field potential value, so that the sorting instantaneity is lower; the method has good overall sorting rate by extracting the sample entropy and power spectrum entropy characteristics of radar radiation source signals and classifying a support vector machine, and the single signal identification rate is not high when the signal-to-noise ratio is low because the sample entropy does not consider the distribution of similar vectors in a sequence and the influence of the complexity of forming sequence vectors on the complexity of a time sequence when the complexity of the time sequence is calculated. In the prior art, a method for applying information fusion to radar signal sorting is disclosed, the method performs data level fusion on pulse description words before radar signal sorting, performs characteristic level fusion on sorting results after sorting, unifies parameters describing the same radar and sorts sorting results according to credibility, solves the sorting failure possibly existing when a single receiving device receives pulses, but because the D-S data fusion method cannot accurately judge under the special condition that provided evidence has large direction conflict, sorting errors are possible when radar parameters are overlapped, and further improvement is needed; in the fifth prior art, an expanded histogram is generated by using a pulse arrival time difference, and then pulse sequences of different radars are recursively sorted. The histogram method is suitable for processing aliasing radar signals with low pulse density and less pulse loss, but the sorting effect is sharply reduced when the pulse density and the pulse loss rate are increased; in the prior art, the arrival time difference of a radar sequence is converted into a PRI spectrum, a PRI value is locked through the position of a spectrum peak, and a PRI box with a non-constant width is adopted, so that the precision and the time consumption of PRI estimation are improved, but when the method is used for real-time sorting in an actual combat environment, the precision and the time consumption cannot meet the actual requirements; the seventh prior art carries out clustering processing on the carrier frequency and the arrival angle of the radar signal within a certain tolerance range, and further carries out secondary clustering processing by using the average value of the clustering results of two parameters, namely the pulse width and the arrival angle, but the technology depends on accurate estimation of the pulse arrival angle, and when the pulse arrival angle is estimatedThe effectiveness of this technique is greatly diminished when it is inaccurate or impossible to estimate. The first to seventh prior art have solved the problem of radar signal sorting to a certain extent, and as far as intra-pulse characteristics are concerned, the more general problem lies in that, because the frequency of radar signal is higher, the process of extracting intra-pulse characteristics is more complicated, and is more time-consuming, and this characteristic is not suitable for sorting radar signals in real time. In terms of inter-pulse characteristics, when a plurality of algorithms are used for processing the sorting problem in a high-density pulse environment, the algorithm effectiveness is rapidly reduced, and the sorting effect on the existing radar with repeated frequency and complex modulation is not good. In addition, the sorting technology is complex to realize and is easy to generate batch increase.
Through the above analysis, the problems and defects of the prior art are as follows: the existing radar signal sorting method has the problems that the sorting instantaneity is poor, the complicated radar with repeated frequency modulation cannot be sorted, the 'batch increase' is easy to generate, and the reliability is low.
The difficulty in solving the above problems and defects is:
under the pulse dense environment, the real-time sorting of radar signals is realized, and the repeated frequency group-changing radar cannot be batched into multiple repeated frequency fixed radars, so that the problem of 'batch increase' is formed.
The significance of solving the problems and the defects is as follows:
in the actual electronic countermeasure environment, with the improvement of the technological level, the electromagnetic environment is more and more complicated. The method is particularly important for determining the number of the radiation sources in the current environment, the countermeasure activity can be improved to a certain extent by solving the problems, and the method is of great significance for subsequent radiation source identification, threat level assessment and the like.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method, a system and application for sorting radar signals in a high-pulse-density environment.
The method for sorting the radar signals in the high-pulse-density environment divides received radar pulse description words according to the arrival angles of pulses to obtain a plurality of groups of pulse sequences from different directions; inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade structure self-organizing mapping neural network to obtain a primary sorting result; obtaining a main sorting result by using an improved sequence difference value histogram algorithm on the primary sorting result; and traversing the combination condition of the main sorting result, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time memory network (LSTM) for repetition frequency identification, and merging to obtain the repetition frequency group-change radar.
Further, dividing the received radar pulse description words according to the arrival angles of the pulses to obtain a plurality of groups of pulse sequences from different directions specifically comprises:
1) detecting an object P which is not checked in a database, if the object P is not processed and is classified as a certain cluster or marked as noise, checking the neighborhood of the object P, if the number of the included objects is not less than the minimum allowable object number minPts, establishing a new cluster C, and adding all points in the new cluster C into a candidate set N;
2) checking the neighborhood of all unprocessed objects q in the candidate set N, and adding the objects q to the candidate set N if at least minPts objects are contained; if q does not belong to any cluster, adding q to C;
3) repeating the step 2), and continuously checking the unprocessed objects in the N, wherein the current candidate set N is empty;
4) repeating steps 1) -3) until all objects fall into a certain cluster or are marked as noise.
Further, the preliminary sorting step of the cascade self-organizing map neural network comprises the following steps:
1) and (5) initializing. Determining a threshold for determining neuron merging or splittingσiCorrespondingly, the error of each parameter value obtained by the reconnaissance receiver is obtained; setting an initial value m of the number of output neurons of the self-organizing mapping neural network0The allowed maximum cycle is K, and the neurons are merged or split once into one cycle;
2) training by using a traditional self-organizing mapping learning algorithm to achieve an ordered mapping, and obtaining an initial clustering center;
3) calculating the intra-class average distance of each classAnd the distance D between classesj=||mj-mj+1Comparing with a set threshold R, | (j ═ 1, 2., c-1); if d isjIf R is greater than R, the neuron j is split; if D isjIf R is less than R, combining the neurons j, determining whether two types are combined into one type or one type is split into two types, adjusting the scale of the self-organizing mapping neural network to obtain the number of new output neurons, namely miA specific numerical value; if all output neurons are neither merged nor split, go to step 5); otherwise, go to step 4);
4) judging whether the circulation round is finished or not, and if so, turning to the step 5); otherwise, turning to the step 2);
5) calculating a value J of a clustering criterion function1,mAnd obtaining the clustering center values of various types;
6) calculating the number of output neurons as m +1 and J corresponding to m-11,m+1And J1,m-1And J1,mCompare, take max (J)1,m+1,J1,m,J1,m-1) The corresponding number of the neurons is the final result, and the clustering center values of various types are obtained.
Further, the improved sequence difference value histogram algorithm comprises the following main sorting steps:
1) inputting a pulse arrival time sequence to be sorted;
2) performing all possible pulse repetition interval PRI classification statistics;
3) setting a statistical threshold, and sequencing and de-duplicating the PRI larger than the threshold;
4) traversing PRI passing a threshold;
5) traversing all pulse arrival times TOA;
6) calculating the allowable time range [ TOA + PRI-mu, TOA + PRI + mu ] of the PRI at the current arrival time according to the noise tolerance mu;
7) judging whether a pulse exists in the allowable time range, if the TOA meets the condition, continuing to execute the step 6), otherwise, increasing the missing pulse number by the miscount + +;
8) judging whether the missing pulse number misscount reaches the set maximum value misscount _ max, if so, setting the missing pulse number to zero, changing the TOA into the TOA and executing the step 5), otherwise, continuing to execute the step 6) if the TOA is not the TOA';
9) and performing sub-harmonic detection on all the extracted TOA sequences, and merging the TOA sequences meeting detection rules to obtain a final main sorting result.
Further, the long and short term memory network performs the identification of the repetition frequency group change as follows:
1) combining and sequencing a radar Pulse Description Word (PDW) sequence according to the pulse arrival time obtained by the main sorting;
2) determining parameters of a piecewise random feature sampling method: the length k of the segments, the number d of the segments and the interval g between the segments;
3) randomly selecting k sequence data from the PDW sequence as a first section of characteristic data;
4) judging whether the data sampling is finished; if yes, executing step 4), otherwise, adding the interval g between the segments to the sampling start position, and executing step 2);
5) inputting the sampling result into a long-time memory network after training is completed to obtain a judgment result of the repetition frequency group change;
6) and if the repetition frequency group change rule is met, combining the PDW sequence to form a repetition frequency group change radar pulse sequence, otherwise, not combining.
It is a further object of the invention to provide a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of: dividing received radar pulse description words according to pulse arrival angles to obtain a plurality of groups of pulse sequences from different directions; inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade structure self-organizing mapping neural network to obtain a primary sorting result; obtaining a main sorting result by using an improved sequence difference value histogram algorithm on the primary sorting result; and traversing the combination condition of the main sorting result, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time memory network (LSTM) for repetition frequency identification, and merging to obtain the repetition frequency group-change radar.
It is another object of the present invention to provide a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of: dividing received radar pulse description words according to pulse arrival angles to obtain a plurality of groups of pulse sequences from different directions; inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade structure self-organizing mapping neural network to obtain a primary sorting result; obtaining a main sorting result by using an improved sequence difference value histogram algorithm on the primary sorting result; and traversing the combination condition of the main sorting result, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time memory network (LSTM) for repetition frequency identification, and merging to obtain the repetition frequency group-change radar.
Another object of the present invention is to provide a radar signal sorting system in a high pulse density environment, which operates the radar signal sorting method in a high pulse density environment, the radar signal sorting system in a high pulse density environment including:
the high-density pulse sparse module is used for carrying out sparse treatment on a high-density pulse environment to obtain a multi-channel pulse sequence for parallel processing;
the cascade self-organizing mapping neural network primary sorting module is used for carrying out primary clustering sorting on the radar pulse to obtain a clustering result of the primary sorting of the current radar signal;
the improved sequence difference value histogram main sorting module is used for carrying out main sorting on the sparse radar pulse sequence to obtain main sorting results of the radar signals with fixed repetition frequency, sliding change of the repetition frequency and dithering;
and the long-time and short-time memory network repeated frequency grouping and changing identification module is used for identifying and combining radar pulse sequences in the repeated frequency fixed radar which accord with the repeated frequency grouping and changing rule, and finally obtaining a repeated frequency grouping and changing radar signal sorting result.
Another object of the present invention is to provide a radar signal sorting system, which is equipped with the radar signal sorting system in the high pulse density environment.
Another object of the present invention is to provide a radar equipped with the radar signal sorting system in a high pulse density environment.
By combining all the technical schemes, the invention has the advantages and positive effects that: the invention can effectively realize the separation of common radar signals (fixed repetition frequency, staggered repetition frequency, jittering repetition frequency, sliding repetition frequency, grouped repetition frequency change, fixed pulse width, agile pulse width, fixed frequency, agile frequency among pulses, agile frequency group, simultaneous frequency diversity and time-sharing frequency diversity) in the high pulse density environment, and can realize the real-time separation of the radar signals in the actual electromagnetic environment.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
Fig. 1 is a flowchart of a method for sorting radar signals in a high pulse density environment according to an embodiment of the present invention.
FIG. 2 is a schematic structural diagram of a radar signal sorting system in a high pulse density environment according to an embodiment of the present invention;
in the figure: 1. a high-density pulse sparse module; 2. a cascade self-organizing mapping neural network primary sorting module; 3. a sequence difference value histogram main sorting module is improved; 4. and a long-time memory network repetition frequency group change identification module.
Fig. 3 to fig. 6 are graphs of clustering results after passing through the self-organizing map network with the cascade structure according to the embodiment of the present invention.
Fig. 7 and 8 are graphs of test results after long-term memory network training according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a method, a system and an application for sorting radar signals in a high pulse density environment, and the invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for sorting radar signals in a high pulse density environment provided by the present invention includes the following steps:
s101: dividing a radar radiation source pulse description word according to the arrival angle of the pulse to obtain a plurality of groups of pulse sequences from different directions;
s102: inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade self-organizing mapping neural network to obtain a primary sorting result;
s103: obtaining a main sorting result by using an improved sequence difference value histogram algorithm on the primary sorting result;
s104: and traversing the combination condition of the main sorting results, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time and short-time memory network for repetition frequency identification, and combining to obtain the repetition frequency group-variable radar.
Those skilled in the art can also use other steps to implement the method for sorting radar signals in the high pulse density environment provided by the present invention, and the method for sorting radar signals in the high pulse density environment provided by the present invention shown in fig. 1 is only one specific example.
As shown in fig. 2, the radar signal sorting system under the high pulse density environment provided by the present invention includes:
the high-density pulse sparse module 1 is used for carrying out sparse treatment on a high-density pulse environment to obtain a multi-channel pulse sequence for parallel processing;
the cascade self-organizing mapping neural network primary sorting module 2 is used for carrying out primary clustering sorting on the radar pulse to obtain a clustering result of the primary sorting of the current radar signal;
the improved sequence difference value histogram main sorting module 3 is used for carrying out main sorting on the sparse radar pulse sequence to obtain the main sorting results of the radar signals with fixed repetition frequency, sliding change of the repetition frequency and dithering;
and the long-time and short-time memory network repetition frequency group change identification module 4 is used for identifying and combining radar pulse sequences which accord with the repetition frequency group change rule in the repetition frequency fixed radar, and finally obtaining a signal sorting result of the repetition frequency group change radar.
The technical solution of the present invention is further described below with reference to the accompanying drawings.
The embodiment of the invention provides a method and a system for sorting radar signals in a high pulse density environment, which specifically comprise the following steps:
step one, the step of dividing the received radar pulse description words according to the arrival angles of the pulses to obtain a plurality of groups of pulse sequences from different directions specifically comprises:
1) detecting an object P which is not checked in the database, if the object P is not processed (classified as a certain cluster or marked as noise), checking the neighborhood of the object P, if the number of included objects is not less than the minimum allowed number of objects (minPts), establishing a new cluster C, and adding all points in the new cluster C into a candidate set N;
2) checking the neighborhood of all unprocessed objects q in the candidate set N, and adding the objects q to the candidate set N if at least minPts objects are contained; if q does not belong to any cluster, adding q to C;
3) repeating the step 2), and continuously checking the unprocessed objects in the N, wherein the current candidate set N is empty;
4) repeating steps 1) -3) until all objects fall into a certain cluster or are marked as noise.
Inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade self-organizing mapping neural network to obtain an initial sorting result:
1) and (5) initializing. Determining a threshold for determining neuron merging or splittingσiCorresponding to the error of each parameter value obtained by the spy receiver. Setting an initial value m of the number of output neurons of the self-organizing mapping neural network0The maximum number of allowed rounds of cycling is K (referred to herein as the neuron undergoing one merge or split into rounds of cycling);
2) training by using a traditional self-organizing mapping learning algorithm to achieve an ordered mapping, and obtaining an initial clustering center;
3) calculating the intra-class average distance of each classAnd the distance D between classesj=||mj-mj+1And | l (j ═ 1, 2.., c-1) and compared with a set threshold R. If d isjIf R is greater than R, the neuron j is split; if D isjIf R is less than R, combining the neurons j to determine whether two types are combined into one type or one type is split into two types, adjusting the scale of the self-organizing mapping neural network to obtain the number of new output neurons, namely miA specific numerical value; if all output neurons are neither merged nor split, go to step 5); otherwise, go to step 4);
4) judging whether the circulation round is finished or not, and if so, turning to the step 5); otherwise, turning to the step 2);
5) calculating a value J of a clustering criterion function1,mAnd obtaining the clustering center values of various types;
6) calculating the number of output neurons as m +1 and J corresponding to m-11,m+1And J1,m-1And J1,mCompare, take max (J)1,m+1,J1,m,J1,m-1) The corresponding number of the neurons is the final result, and the clustering center values of various types are obtained.
Step three, using an improved sequence difference value histogram algorithm for the primary sorting result to obtain a main sorting result:
1) inputting a pulse arrival time sequence to be sorted;
2) performing all possible Pulse Repetition Interval (PRI) classification statistics;
3) setting a statistical threshold, and sequencing and de-duplicating the PRI larger than the threshold;
4) traversing PRI passing a threshold;
5) traverse all pulse arrival Times (TOAs);
6) calculating the allowable time range [ TOA + PRI-mu, TOA + PRI + mu ] of the PRI at the current arrival time according to the noise tolerance mu;
7) judging whether a pulse exists in the allowable time range, if the TOA meets the condition, continuing to execute the step 6), otherwise, increasing the missing pulse number by the miscount + +;
8) judging whether the missing pulse number misscount reaches the set maximum value misscount _ max, if so, setting the missing pulse number to zero, changing the TOA into the TOA and executing the step 5), otherwise, continuing to execute the step 6) if the TOA is not the TOA';
9) and performing sub-harmonic detection on all the extracted TOA sequences, and merging the TOA sequences meeting detection rules to obtain a final main sorting result.
Step four, traversing the combination condition of the main sorting results, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time and short-time memory network for re-frequency identification, and combining to obtain a re-frequency group-change radar:
1) combining and sequencing a radar Pulse Description Word (PDW) sequence according to the pulse arrival time obtained by the main sorting;
2) determining parameters of a piecewise random feature sampling method: the length k of the segments, the number d of the segments and the interval g between the segments;
3) randomly selecting k sequence data from the PDW sequence as a first section of characteristic data;
4) and judging whether the data sampling is finished. If yes, executing step 4), otherwise, adding the interval g between the segments to the sampling start position, and executing step 2);
5) inputting the sampling result into a long-time memory network after training is completed to obtain a judgment result of the repetition frequency group change;
6) and if the repetition frequency group change rule is met, combining the PDW sequence to form a repetition frequency group change radar pulse sequence, otherwise, not combining.
The technical effects of the present invention will be described in detail with reference to simulations.
In order to test the clustering effect of the self-organizing mapping network with the cascade structure, 50 groups of real acquisition signals with different time periods are randomly selected, as shown in fig. 3-6.
And the subsequent long-time and short-time memory network algorithm requires that the category number of the clustering results is not less than the number of the repeated frequency group variable radar radiation sources. The clustering effect of 50 groups was evaluated in combination with standard sorting reference results. Wherein 48 groups meet the requirement of a subsequent algorithm, namely the number of the clustering result categories is not less than the number of the repeated frequency group variable radar radiation sources, and the total accuracy is 96 percent.
In order to test the judgment performance of the long-time and short-time memory network, the actual acquisition signals are sorted for 136 time periods, and 63 effective radar repetition frequency group variable pulse description word sequences are obtained. And constructing a data set by using the pulse description word sequence to train and test a long-time and short-time memory network, as shown in fig. 7 and 8.
It should be noted that the embodiments of the present invention can be realized by hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided on a carrier medium such as a disk, CD-or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier, for example. The apparatus and its modules of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, e.g., firmware.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A radar signal sorting method under a high pulse density environment is characterized in that the radar signal sorting method under the high pulse density environment divides received radar pulse description words according to pulse arrival angles to obtain a plurality of groups of pulse sequences from different directions; inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade structure self-organizing mapping neural network to obtain a primary sorting result; obtaining a main sorting result by using an improved sequence difference value histogram algorithm on the primary sorting result; and traversing the combination condition of the main sorting result, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time memory network (LSTM) for repetition frequency identification, and merging to obtain the repetition frequency group-change radar.
2. The method of claim 1, wherein the step of dividing the received radar pulse descriptors by pulse arrival angle to obtain the plurality of groups of pulse sequences from different directions comprises:
1) detecting an object P which is not checked in a database, if the object P is not processed and is classified as a certain cluster or marked as noise, checking the neighborhood of the object P, if the number of the included objects is not less than the minimum allowable object number minPts, establishing a new cluster C, and adding all points in the new cluster C into a candidate set N;
2) checking the neighborhood of all unprocessed objects q in the candidate set N, and adding the objects q to the candidate set N if at least minPts objects are contained; if q does not belong to any cluster, adding q to C;
3) repeating the step 2), and continuously checking the unprocessed objects in the N, wherein the current candidate set N is empty;
4) repeating steps 1) -3) until all objects fall into a certain cluster or are marked as noise.
3. The method for sorting radar signals in the high pulse density environment according to claim 1, wherein the cascade self-organizing map neural network primary sorting step is as follows:
1) initialization, determining thresholds for determining neuron merging or splittingσiCorrespondingly, the error of each parameter value obtained by the reconnaissance receiver is obtained; setting an initial value m of the number of output neurons of the self-organizing mapping neural network0The allowed maximum cycle is K, and the neurons are merged or split once into one cycle;
2) training by using a traditional self-organizing mapping learning algorithm to achieve an ordered mapping, and obtaining an initial clustering center;
3) calculating the intra-class average distance of each classAnd the distance D between classesj=||mj-mj+1Comparing with a set threshold R, | (j ═ 1, 2., c-1); if d isjIf R is greater than R, the neuron j is split; if D isjIf R is less than R, combining the neurons j, determining whether two types are combined into one type or one type is split into two types, adjusting the scale of the self-organizing mapping neural network to obtain the number of new output neurons, namely miA specific numerical value; if all output neurons are neither merged nor split, go to step 5); otherwise, go to step 4);
4) judging whether the circulation round is finished or not, and if so, turning to the step 5); otherwise, turning to the step 2);
5) calculating a value J of a clustering criterion function1,mAnd obtaining the clustering center values of various types;
6) calculating the number of output neurons as m +1 and J corresponding to m-11,m+1And J1,m-1And J1,mCompare, take max (J)1,m+1,J1,m,J1,m-1) The corresponding number of the neurons is the final result, and the clustering center values of various types are obtained.
4. The method for sorting radar signals in high pulse density environment according to claim 1, wherein the improved sequence difference histogram algorithm comprises the following main sorting steps:
1) inputting a pulse arrival time sequence to be sorted;
2) performing all possible pulse repetition interval PRI classification statistics;
3) setting a statistical threshold, and sequencing and de-duplicating the PRI larger than the threshold;
4) traversing PRI passing a threshold;
5) traversing all pulse arrival times TOA;
6) calculating the allowable time range [ TOA + PRI-mu, TOA + PRI + mu ] of the PRI at the current arrival time according to the noise tolerance mu;
7) judging whether a pulse exists in the allowable time range, if the TOA meets the condition, continuing to execute the step 6), otherwise, increasing the missing pulse number by the miscount + +;
8) judging whether the missing pulse number misscount reaches the set maximum value misscount _ max, if so, setting the missing pulse number to zero, changing the TOA into the TOA and executing the step 5), otherwise, continuing to execute the step 6) if the TOA is not the TOA';
9) and performing sub-harmonic detection on all the extracted TOA sequences, and merging the TOA sequences meeting detection rules to obtain a final main sorting result.
5. The method for sorting radar signals under the high pulse density environment according to claim 1, wherein the long-time and short-time memory network performs the identification of the repetition frequency group variation by the following steps:
1) combining and sequencing a radar Pulse Description Word (PDW) sequence according to the pulse arrival time obtained by the main sorting;
2) determining parameters of a piecewise random feature sampling method: the length k of the segments, the number d of the segments and the interval g between the segments;
3) randomly selecting k sequence data from the PDW sequence as a first section of characteristic data;
4) judging whether the data sampling is finished; if yes, executing step 4), otherwise, adding the interval g between the segments to the sampling start position, and executing step 2);
5) inputting the sampling result into a long-time memory network after training is completed to obtain a judgment result of the repetition frequency group change;
6) and if the repetition frequency group change rule is met, combining the PDW sequence to form a repetition frequency group change radar pulse sequence, otherwise, not combining.
6. A computer device, characterized in that the computer device comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the steps of: dividing received radar pulse description words according to pulse arrival angles to obtain a plurality of groups of pulse sequences from different directions; inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade structure self-organizing mapping neural network to obtain a primary sorting result; obtaining a main sorting result by using an improved sequence difference value histogram algorithm on the primary sorting result; and traversing the combination condition of the main sorting result, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time memory network (LSTM) for repetition frequency identification, and merging to obtain the repetition frequency group-change radar.
7. A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of: dividing received radar pulse description words according to pulse arrival angles to obtain a plurality of groups of pulse sequences from different directions; inputting the pulse frequency domain parameters and the pulse width of each group of pulse sequences into a cascade structure self-organizing mapping neural network to obtain a primary sorting result; obtaining a main sorting result by using an improved sequence difference value histogram algorithm on the primary sorting result; and traversing the combination condition of the main sorting result, inputting the pulse frequency domain parameters, the pulse width and the pulse arrival time into a long-time memory network (LSTM) for repetition frequency identification, and merging to obtain the repetition frequency group-change radar.
8. A radar signal sorting system in a high pulse density environment for operating the method for sorting radar signals in a high pulse density environment according to any one of claims 1 to 6, wherein the radar signal sorting system in a high pulse density environment comprises:
the high-density pulse sparse module is used for carrying out sparse treatment on a high-density pulse environment to obtain a multi-channel pulse sequence for parallel processing;
the cascade self-organizing mapping neural network primary sorting module is used for carrying out primary clustering sorting on the radar pulse to obtain a clustering result of the primary sorting of the current radar signal;
the improved sequence difference value histogram main sorting module is used for carrying out main sorting on the sparse radar pulse sequence to obtain main sorting results of the radar signals with fixed repetition frequency, sliding change of the repetition frequency and dithering;
and the long-time and short-time memory network repeated frequency grouping and changing identification module is used for identifying and combining radar pulse sequences in the repeated frequency fixed radar which accord with the repeated frequency grouping and changing rule, and finally obtaining a repeated frequency grouping and changing radar signal sorting result.
9. A radar signal sorting system, characterized in that the radar signal sorting system is equipped with the radar signal sorting system in a high pulse density environment according to claim 8.
10. A radar equipped with the high pulse density environment radar signal classification system according to claim 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010731268.8A CN112036074B (en) | 2020-07-27 | 2020-07-27 | Radar signal sorting method and system in high pulse density environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010731268.8A CN112036074B (en) | 2020-07-27 | 2020-07-27 | Radar signal sorting method and system in high pulse density environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112036074A true CN112036074A (en) | 2020-12-04 |
CN112036074B CN112036074B (en) | 2024-04-02 |
Family
ID=73583230
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010731268.8A Active CN112036074B (en) | 2020-07-27 | 2020-07-27 | Radar signal sorting method and system in high pulse density environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112036074B (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112526456A (en) * | 2020-12-28 | 2021-03-19 | 扬州健行电子科技有限公司 | Radar signal identification algorithm |
CN112698274A (en) * | 2020-12-05 | 2021-04-23 | 扬州宇安电子科技有限公司 | Radar signal sorting and pulse sequence extraction system based on hierarchical PRI transformation |
CN112799053A (en) * | 2020-12-09 | 2021-05-14 | 中国人民解放军战略支援部队信息工程大学 | Real-time pairing sorting method for single pulse signals |
CN112904287A (en) * | 2021-01-14 | 2021-06-04 | 无锡国芯微电子系统有限公司 | Tracking radiation source parameter estimation method based on passive radar finder and application thereof |
CN112904288A (en) * | 2021-01-14 | 2021-06-04 | 无锡国芯微电子系统有限公司 | System and method for pulse signal combination |
CN112949383A (en) * | 2021-01-22 | 2021-06-11 | 中国人民解放军63892部队 | Waveform agility radar radiation source identification method based on Hydeep-Att network |
CN112986928A (en) * | 2021-03-11 | 2021-06-18 | 哈尔滨工程大学 | Signal sorting multi-source fusion processing method in complex electromagnetic environment |
CN112986925A (en) * | 2021-02-01 | 2021-06-18 | 东南大学 | Radar pulse sequence sorting method based on image characteristics |
CN113033629A (en) * | 2021-03-09 | 2021-06-25 | 中南大学 | Radar signal sorting method and device based on improved cuckoo algorithm |
CN113128584A (en) * | 2021-04-15 | 2021-07-16 | 北京理工大学 | Mode-level unsupervised sorting method of multifunctional radar pulse sequence |
CN113127807A (en) * | 2021-04-19 | 2021-07-16 | 深圳华创电科技术有限公司 | Mode5 leading pulse jitter value calculation method and system based on constrained least square algorithm |
CN113253217A (en) * | 2021-05-27 | 2021-08-13 | 南京雷电信息技术有限公司 | Method for constructing complex electromagnetic environment based on pulse stream |
CN113259017A (en) * | 2021-05-13 | 2021-08-13 | 电子科技大学 | Intra-frame signal sorting method based on time hopping relation |
CN113721219A (en) * | 2021-10-08 | 2021-11-30 | 中国电子科技集团公司第三十八研究所 | Radar signal sorting method and system based on multi-parameter clustering |
CN113759323A (en) * | 2021-07-19 | 2021-12-07 | 西安电子科技大学 | Signal sorting method and device based on improved K-Means combined convolution self-encoder |
CN113962261A (en) * | 2021-10-21 | 2022-01-21 | 中国人民解放军空军航空大学 | Depth network model for radar signal sorting |
CN113985356A (en) * | 2021-10-29 | 2022-01-28 | 扬州宇安电子科技有限公司 | Method for realizing radar signal pulse description word sorting function |
CN114624645A (en) * | 2022-03-10 | 2022-06-14 | 扬州宇安电子科技有限公司 | Miniature rotor unmanned aerial vehicle radar reconnaissance system based on micro antenna array |
CN114924234A (en) * | 2022-07-21 | 2022-08-19 | 中国人民解放军国防科技大学 | Radar radiation source target signal detection method based on regional contrast |
CN115128569A (en) * | 2022-08-30 | 2022-09-30 | 中国电子科技集团公司第十五研究所 | Radar reconnaissance full-pulse data visual sorting method, server and storage medium |
CN117554919A (en) * | 2024-01-11 | 2024-02-13 | 成都金支点科技有限公司 | Radar signal sorting and searching method based on bidirectional LSTM network |
CN118131168A (en) * | 2024-05-08 | 2024-06-04 | 成都玖锦科技有限公司 | Complex environment signal sorting system and method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100283666A1 (en) * | 2009-05-08 | 2010-11-11 | Agency For Defense Development | Radar signals clustering method using frequency modulation characteristics and combination characteristics of signals, and system for receiving and processing radar signals using the same |
CN110764063A (en) * | 2019-10-15 | 2020-02-07 | 哈尔滨工程大学 | Radar signal sorting method based on combination of SDIF and PRI transformation method |
-
2020
- 2020-07-27 CN CN202010731268.8A patent/CN112036074B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100283666A1 (en) * | 2009-05-08 | 2010-11-11 | Agency For Defense Development | Radar signals clustering method using frequency modulation characteristics and combination characteristics of signals, and system for receiving and processing radar signals using the same |
CN110764063A (en) * | 2019-10-15 | 2020-02-07 | 哈尔滨工程大学 | Radar signal sorting method based on combination of SDIF and PRI transformation method |
Non-Patent Citations (3)
Title |
---|
岳志勇;肖军鹏;王鹏;: "重频抖动脉冲信号分选研究", 遥测遥控, no. 1, 15 November 2007 (2007-11-15) * |
陈恒;张友益;王玉梅;: "基于融合算法的多参数雷达信号分选", 舰船电子工程, no. 09, 20 September 2018 (2018-09-20) * |
魏娟, 杨万麟, 植强, 王松煜: "一种密集信号环境下雷达脉冲分选方法", 电子科技大学学报, no. 03, 25 June 2005 (2005-06-25) * |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112698274A (en) * | 2020-12-05 | 2021-04-23 | 扬州宇安电子科技有限公司 | Radar signal sorting and pulse sequence extraction system based on hierarchical PRI transformation |
CN112799053A (en) * | 2020-12-09 | 2021-05-14 | 中国人民解放军战略支援部队信息工程大学 | Real-time pairing sorting method for single pulse signals |
CN112799053B (en) * | 2020-12-09 | 2023-08-15 | 中国人民解放军战略支援部队信息工程大学 | Real-time pairing and sorting method for monopulse signals |
CN112526456A (en) * | 2020-12-28 | 2021-03-19 | 扬州健行电子科技有限公司 | Radar signal identification algorithm |
CN112904287B (en) * | 2021-01-14 | 2021-10-22 | 无锡国芯微电子系统有限公司 | Tracking radiation source parameter estimation method based on passive radar finder and application thereof |
CN112904287A (en) * | 2021-01-14 | 2021-06-04 | 无锡国芯微电子系统有限公司 | Tracking radiation source parameter estimation method based on passive radar finder and application thereof |
CN112904288A (en) * | 2021-01-14 | 2021-06-04 | 无锡国芯微电子系统有限公司 | System and method for pulse signal combination |
CN112904288B (en) * | 2021-01-14 | 2023-08-29 | 无锡国芯微电子系统有限公司 | Pulse signal combining system and pulse signal combining method |
CN112949383A (en) * | 2021-01-22 | 2021-06-11 | 中国人民解放军63892部队 | Waveform agility radar radiation source identification method based on Hydeep-Att network |
CN112986925B (en) * | 2021-02-01 | 2024-03-12 | 东南大学 | Radar pulse sequence sorting method based on image features |
CN112986925A (en) * | 2021-02-01 | 2021-06-18 | 东南大学 | Radar pulse sequence sorting method based on image characteristics |
CN113033629B (en) * | 2021-03-09 | 2022-08-05 | 中南大学 | Radar signal sorting method and device based on improved cuckoo algorithm |
CN113033629A (en) * | 2021-03-09 | 2021-06-25 | 中南大学 | Radar signal sorting method and device based on improved cuckoo algorithm |
CN112986928A (en) * | 2021-03-11 | 2021-06-18 | 哈尔滨工程大学 | Signal sorting multi-source fusion processing method in complex electromagnetic environment |
CN113128584A (en) * | 2021-04-15 | 2021-07-16 | 北京理工大学 | Mode-level unsupervised sorting method of multifunctional radar pulse sequence |
CN113127807A (en) * | 2021-04-19 | 2021-07-16 | 深圳华创电科技术有限公司 | Mode5 leading pulse jitter value calculation method and system based on constrained least square algorithm |
CN113127807B (en) * | 2021-04-19 | 2023-02-24 | 深圳华创电科技术有限公司 | Mode5 leading pulse jitter value calculation method based on constrained least square algorithm |
CN113259017A (en) * | 2021-05-13 | 2021-08-13 | 电子科技大学 | Intra-frame signal sorting method based on time hopping relation |
CN113253217A (en) * | 2021-05-27 | 2021-08-13 | 南京雷电信息技术有限公司 | Method for constructing complex electromagnetic environment based on pulse stream |
CN113253217B (en) * | 2021-05-27 | 2021-10-01 | 南京雷电信息技术有限公司 | Method for constructing complex electromagnetic environment based on pulse stream |
CN113759323A (en) * | 2021-07-19 | 2021-12-07 | 西安电子科技大学 | Signal sorting method and device based on improved K-Means combined convolution self-encoder |
CN113759323B (en) * | 2021-07-19 | 2024-02-06 | 西安电子科技大学 | Signal sorting method and device based on improved K-Means joint convolution self-encoder |
CN113721219A (en) * | 2021-10-08 | 2021-11-30 | 中国电子科技集团公司第三十八研究所 | Radar signal sorting method and system based on multi-parameter clustering |
CN113962261A (en) * | 2021-10-21 | 2022-01-21 | 中国人民解放军空军航空大学 | Depth network model for radar signal sorting |
CN113962261B (en) * | 2021-10-21 | 2024-05-14 | 中国人民解放军空军航空大学 | Deep network model construction method for radar signal sorting |
CN113985356A (en) * | 2021-10-29 | 2022-01-28 | 扬州宇安电子科技有限公司 | Method for realizing radar signal pulse description word sorting function |
CN114624645A (en) * | 2022-03-10 | 2022-06-14 | 扬州宇安电子科技有限公司 | Miniature rotor unmanned aerial vehicle radar reconnaissance system based on micro antenna array |
CN114624645B (en) * | 2022-03-10 | 2022-09-30 | 扬州宇安电子科技有限公司 | Miniature rotor unmanned aerial vehicle radar reconnaissance system based on micro antenna array |
CN114924234A (en) * | 2022-07-21 | 2022-08-19 | 中国人民解放军国防科技大学 | Radar radiation source target signal detection method based on regional contrast |
CN115128569B (en) * | 2022-08-30 | 2022-11-25 | 中国电子科技集团公司第十五研究所 | Radar reconnaissance full-pulse data visual sorting method, server and storage medium |
CN115128569A (en) * | 2022-08-30 | 2022-09-30 | 中国电子科技集团公司第十五研究所 | Radar reconnaissance full-pulse data visual sorting method, server and storage medium |
CN117554919A (en) * | 2024-01-11 | 2024-02-13 | 成都金支点科技有限公司 | Radar signal sorting and searching method based on bidirectional LSTM network |
CN117554919B (en) * | 2024-01-11 | 2024-03-29 | 成都金支点科技有限公司 | Radar signal sorting and searching method based on bidirectional LSTM network |
CN118131168A (en) * | 2024-05-08 | 2024-06-04 | 成都玖锦科技有限公司 | Complex environment signal sorting system and method |
Also Published As
Publication number | Publication date |
---|---|
CN112036074B (en) | 2024-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112036074B (en) | Radar signal sorting method and system in high pulse density environment | |
Bortolato et al. | Bump hunting in latent space | |
CN102938071B (en) | Fuzzy clustering analysis method for detecting synthetic aperture radar (SAR) image changes based on non-local means | |
CN112036239B (en) | Radar signal working mode identification method and system based on deep learning network | |
Heredia et al. | Density-based clustering methods for unsupervised separation of partial discharge sources | |
CN109766926B (en) | Radar radiation source signal intra-pulse characteristic comprehensive evaluation method and system | |
KR101313051B1 (en) | Method and device for recognizing pulse repetition interval modulation type of a radar signal | |
CN113486961A (en) | Radar RD image target detection method and system based on deep learning under low signal-to-noise ratio and computer equipment | |
CN112986925A (en) | Radar pulse sequence sorting method based on image characteristics | |
Zhang et al. | Feature selection and resampling in class imbalance learning: Which comes first? An empirical study in the biological domain | |
Chunjie et al. | Synthetic algorithm for deinterleaving radar signals in a complex environment | |
Nuhoglu et al. | Image segmentation for radar signal deinterleaving using deep learning | |
Kim et al. | Classification of the trained and untrained emitter types based on class probability output networks | |
Xie et al. | A novel method for deinterleaving radar signals: First‐order difference curve based on sorted TOA difference sequence | |
CN111487592A (en) | Radar signal sorting method based on GPU and CPU platform drift mean clustering | |
Shapero et al. | Identifying agile waveforms with neural networks | |
CN103076595B (en) | Abnormal type identifying method for multivariate discrete radar emitter signal | |
CN112904292A (en) | Broadband radar detection threshold determination and target detection method based on importance sampling | |
Zhang et al. | PRI modulation recognition and sequence search under small sample prerequisite | |
CN115980689A (en) | Point cloud detection-based radiation source signal sorting method, device, equipment and medium | |
CN115629365A (en) | Method and device for sorting few sample signals in high-density background signals | |
Han et al. | Radar clutter classification using expectation-maximization method | |
CN112927201A (en) | Curve detection method and device | |
Zheng et al. | An reconstruction bidirectional recurrent neural network‐based deinterleaving method for known radar signals in open‐set scenarios | |
Gu et al. | Detecting deep neural network defects with data flow analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |