CN115932770A - Method, system, equipment and terminal for accurately and intelligently identifying radar radiation source individuals - Google Patents
Method, system, equipment and terminal for accurately and intelligently identifying radar radiation source individuals Download PDFInfo
- Publication number
- CN115932770A CN115932770A CN202211264282.7A CN202211264282A CN115932770A CN 115932770 A CN115932770 A CN 115932770A CN 202211264282 A CN202211264282 A CN 202211264282A CN 115932770 A CN115932770 A CN 115932770A
- Authority
- CN
- China
- Prior art keywords
- radiation source
- radar radiation
- bispectrum
- individual
- radar
- 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.)
- Pending
Links
Images
Classifications
-
- 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
Abstract
The invention belongs to the technical field of individual identification of radiation sources in accurate radar identification, and discloses an accurate intelligent identification method, system, equipment and terminal of individual radar radiation sources, which are used for solving a corresponding bispectrum for a received radar radiation source signal; extracting the characteristics of the bispectrum according to a Laplace-Gaussian operator; inputting the extracted features into a deep residual error network based on norm and dynamic learning rate for training to obtain a trained model; and realizing individual intelligent identification of radar radiation source signals by using the trained model. The accurate and intelligent identification method for the radar radiation source individuals realizes individual identification of the radiation source under the condition that the differences of the radar fingerprint characteristics are not obvious, improves the individual identification efficiency of the radiation source under the condition of ensuring the accuracy of the individual identification efficiency, improves the generalization and the robustness of a network model and the accuracy in use, effectively and deeply mines the difference characteristics among the individual radiation sources, and can achieve better identification effect under the condition that the radar fingerprint characteristics are similar.
Description
Technical Field
The invention belongs to the technical field of individual identification of radiation sources in accurate identification of radars, and particularly relates to an accurate intelligent identification method, system, equipment and terminal for individual radar radiation sources.
Background
At present, radar radiation source identification is to determine which step of radar radiation source and information such as position and parameters of the received individual signal are from after a series of analysis and processing are performed on the received individual signal of the radar radiation source. Early radars are simple, and radar radiation source identification is mainly to manually process and analyze parameters between pulses obtained by measuring radar radiation sources, and then compare and analyze the parameters with individual information of each radar radiation source in a known and established database. However, in recent years, the radar technology is suddenly advanced, various new radars are in a large range, the electromagnetic environment of a battlefield becomes more complicated, the similarity of fingerprint information among all radar radiation sources is high, and the radar signals intercepted by a radar receiving device become difficult to distinguish. Therefore, finding a more accurate and faster identification mode becomes a problem and a main development direction which are urgently needed to be solved in the field of radar radiation sources.
Radiation source individual identification technology based on fingerprint information has been started in the last century. The American scholarn proposes a theory of Specific Emitter Identification (SEI), extracts fingerprint characteristics of signals by using Specific radar radiation source signals intercepted by the scholars, compares the fingerprint characteristics with an information base established previously, analyzes the fingerprint characteristics, classifies the fingerprint characteristics according to matching results, and identifies the radar radiation source emitting the signals. Meanwhile, the existing radar radiation source individual identification depends on the difference between radar fingerprint information, and if the difference is small, the identification result is seriously influenced. Based on the method, a method for extracting fingerprint information by using a constellation diagram is proposed abroad, and the fingerprint information is input into a convolutional neural network for identification; based on statistics of radiation source conventional parameters such as direction of arrival (DOA), pulse Width (PW), pulse Repetition Frequency (PRF), radar Frequency (RF) and the like as a basis for classification and identification, inputting the statistics into a network and adopting methods such as a naive Bayes classifier, clustering, SVM and the like; a predictive learning method based on Kernel Principal Component Analysis (KPCA); based on a method of calculating the inter-signal distance, the pulse envelope or the instantaneous frequency using the Frechet distance; based on the bispectrum + SURF (Speed-up robust features) feature. However, although the accuracy rate is high when partial fingerprint features are adopted, the calculation amount is huge, and the accuracy rate is lower when the calculation amount is small.
For China, a method based on a phase observation model and a long-short time memory network, a radar radiation source individual accurate intelligent identification method based on VMD decomposition, a method for constructing a data set based on pulse data flow, an individual identification method based on a fuzzy function, a radar radiation source individual accurate intelligent identification method based on Hilbert transform to extract features, and a radiation source individual classification method based on the utilization of a deep confidence network DBN and radiation source signal envelope characteristics are available. However, part of the network models are over-fitted to the training set, so that the accuracy is high during training but the effect is not ideal during test application. Therefore, it is highly desirable to find a fast and accurate radar fingerprint feature, highlight it and amplify its diversity; meanwhile, the network model is improved, so that the dependency on a training set is reduced, and overfitting is prevented.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) With the development of radar technology, the signal complexity and the electromagnetic environment complexity are increasing day by day, so that the inter-pulse parameters are difficult to meet the requirement of identification accuracy, and intra-pulse modulation information needs to be utilized. The existing radar radiation source individual identification by utilizing intra-pulse information depends on the difference between the radar radiation source fingerprint information, and if the difference between the radiation source fingerprint information to be identified is small, the identification accuracy rate is seriously reduced.
(2) The existing radiation source individual identification technology based on fingerprint information relies on expert judgment, the identification rate error is large by utilizing manual work, and deeper abstract features need to be mined for identification by utilizing an artificial intelligence method.
(3) When the existing artificial intelligence method is used for radar radiation source individual identification, shallow networks often cannot obtain good identification effects, deep networks can greatly increase the time consumption, and the problems of overfitting and network degradation exist.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method, a system, equipment and a terminal for accurately and intelligently identifying radar radiation source individuals, and particularly relates to a method, a system, a medium, equipment and a terminal for accurately and intelligently identifying radar radiation source individuals when fingerprint characteristics are similar.
The invention is realized in such a way that the accurate intelligent identification method of the radar radiation source individual comprises the following steps: obtaining a bispectrum corresponding to a radar radiation source signal and extracting features of a Laplace-Gaussian operator; and constructing a trained model by using the extracted features, and realizing accurate and intelligent identification of the radar radiation source individuals by using the trained model.
Further, the accurate and intelligent identification method for the radar radiation source individuals comprises the following steps:
step one, solving a corresponding bispectrum for a received radar radiation source signal, and mining deep features of the radar radiation source signal;
secondly, extracting features of the bispectrum according to a Laplace-Gaussian operator, and further highlighting edge difference information among radar radiation source individuals;
inputting the extracted features into a deep residual error network based on norm and dynamic learning rate for training to obtain a trained model, and achieving an ideal recognition effect under the condition of low consumption;
and fourthly, utilizing the trained model to realize the individual intelligent identification of the radar radiation source signal.
Further, the obtaining a corresponding bispectrum for the received radar radiation source signal in the first step includes:
calculating a third-order cumulant of a radar radiation source signal x (t), wherein the expression is as follows:
C 3s (τ 1 ，τ 2 )＝E{s * (t)x(t+τ 1 )x(t+τ 2 )}；
wherein x isFor receiving signals, τ is the time delay, s * (t) is a conjugate signal; e is the mathematical expectation of the corresponding value, resulting in C 3s (τ 1 ，τ 2 ) Is the corresponding third order cumulative quantity.
For third-order cumulant C 3s (τ 1 ，τ 2 ) And (3) solving a bispectrum transformation, wherein the expression is as follows:
wherein, C 3s (τ 1 ，τ 2 ) For the found corresponding third order cumulant,
two-dimensional Fourier transform to obtain third-order cumulant, resulting in B s (ω 1 ，ω 2 ) Is a bispectrum.
Further, the extracting the features of the bispectrum according to the laplacian-gaussian operator in the second step includes:
the laplacian-gaussian operator with 0 as the center and σ as the gaussian standard deviation has the following expression:
wherein G is σ (x, y) is a second order Gaussian function, and the expression is as follows:
where σ is the Gaussian standard deviation.
Performing Laplace-Gaussian operator feature extraction on the bispectrum:
LoGB s (ω 1 ，ω 2 )＝LoG*B s (ω 1 ，ω 2 )；
wherein, the star represents convolution operation, and the operator is used for carrying out convolution operation on the bispectrum.
Further, the step three of inputting the extracted features into a deep residual error network based on norm and dynamic learning rate for training, and obtaining a trained model includes:
when the network calculates each layer of parameters, L2 norm is introduced, square root is calculated after the square sum of each feature vector element, and the network is more sparse and smooth.
||x|| 2 ＝(|x 1 | 2 +|x 1 | 2 +|x 1 | 2 +...+|x n | 2 ) 1/2 ；
The dynamic learning rate is adopted in each round of learning as follows:
lr(n)＝lr*0.2 [n/10] ；
wherein lr (n) is the current learning rate, n is the batch, lr is the preset learning rate, the learning rate becomes 0.2 times the current learning rate after every 10 batches, and the learning rate is gradually reduced along with the round conversion.
The deep residual error network is composed of various residual error blocks, wherein each residual error fast learning rule is as follows:
F(x)＝H(x)-x；
wherein H (x) is a back propagation function, F (x) is a forward propagation function, and x is a network input.
Inputting the bispectrum extracted by the Laplacian-Gaussian operator into a single channel to generate H multiplied by W multiplied by 1 characteristics, wherein H and W are respectively the length and width of a characteristic diagram, and 1 is the number of channels; inputting the characteristics into a residual block 1 for convolution operation, and inputting the result into a residual block 2 until 4 residual blocks are operated; and finally, obtaining a final recognition result through the pooling layer and the full connection layer.
Further, the step four of utilizing the trained model to realize the individual intelligent identification of the radar radiation source signal comprises:
obtaining a corresponding bispectrum after receiving the unclassified preprocessed signals of the trained radar radiation source individuals, extracting the characteristics of the bispectrum according to a Laplacian-Gaussian operator, and loading a trained network model; inputting the characteristics into a network to obtain an identification result; obtaining probability matrixes of each radar radiation source individual through a Softmax layer, wherein the highest probability is an identification result, and the Softmax expression is as follows:
M＝max(z)；
wherein z is the result vector, max is the maximum value of z, z i Is the ith result.
Another object of the present invention is to provide a precise and intelligent identification system for individual radar radiation source, which applies the precise and intelligent identification method for individual radar radiation source, wherein the precise and intelligent identification system for individual radar radiation source comprises:
the double-spectrum calculating module is used for calculating the corresponding double spectrum of the received radar radiation source signal;
the characteristic extraction module is used for extracting the characteristics of the bispectrum according to a Laplace-Gaussian operator;
the feature training module is used for inputting the extracted features into a deep residual error network based on norm and dynamic learning rate for training to obtain a trained model;
and the individual identification module is used for realizing the individual intelligent identification of the radar radiation source signal by utilizing the trained model.
Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to execute the steps of the method for accurately and intelligently identifying an individual radar radiation source.
Another object of the present invention is to provide a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the method for accurately and intelligently identifying an individual from a radar radiation source.
The invention also aims to provide an information data processing terminal, which is used for realizing the accurate and intelligent identification system of the radar radiation source individuals.
By combining the technical scheme and the technical problem to be solved, the technical scheme to be protected by the invention has the advantages and positive effects that:
first, aiming at the technical problems and difficulties in solving the problems in the prior art, the technical problems to be solved by the technical scheme of the present invention are closely combined with results, data and the like in the research and development process, and some creative technical effects are brought after the problems are solved. The specific description is as follows:
the invention provides a precise and intelligent identification method of an individual radar radiation source, which comprises the steps of firstly, obtaining a corresponding bispectrum of a received radar radiation source signal; and extracting the features of the bispectrum according to a Laplacian of Gaussian operator (LoG); and finally, inputting the extracted features into a deep residual error network (Resnet) based on norm and dynamic learning rate for training to obtain a trained model, and realizing the individual intelligent identification of the radar radiation source signals by utilizing the model. The invention effectively and deeply excavates the difference characteristics among the radiation source individuals and can achieve better identification effect under the condition that the radar fingerprint characteristics are similar.
The method can effectively realize the individual identification of the radiation source under the condition of similar radar fingerprint characteristics, and has better performance compared with other methods. In addition, the radar radiation source individual identification method provided by the invention is also suitable for radiation source individual identification when the difference of radar fingerprint characteristics is large.
Secondly, considering the technical scheme as a whole or from the perspective of products, the technical effect and advantages of the technical scheme to be protected by the invention are specifically described as follows:
the accurate and intelligent identification method for the radar radiation source individuals provided by the invention realizes the individual identification of the radiation source under the conditions that the extraction of radar fingerprint features is insufficient and the difference between the radar fingerprint features is not obvious in a complex electromagnetic environment, improves the individual identification efficiency of the radiation source under the condition that the accuracy of the network is ensured, improves the generalization and robustness of a network model and improves the accuracy of the network model in use.
Third, as inventive supplementary proof of the claims of the present invention, there are several important aspects as follows:
the method for accurately and intelligently identifying the radar radiation source individuals strengthens and combines the neural network, the radar intra-pulse signal processing technology and the pattern identification theory.
(1) The technical scheme of the invention has the following converted commercial values:
the radar radiation source individual identification technology is really used for identifying the actual radar radiation source individual signals, and the identification is not only stopped at the identification of theoretical simulation signals.
(2) The technical scheme of the invention solves the technical problem that people are eagerly to solve but can not be successfully solved all the time:
the radar radiation source characteristics can be effectively further extracted under the current complex electromagnetic environment, the difference among the radar radiation sources is amplified, and higher identification accuracy is provided when the fingerprints of the radar radiation sources are similar. Meanwhile, the improved network prevents the over-fitting phenomenon while ensuring the training accuracy, the number of network layers is not required to be stacked during training, the expenditure is reduced, and the high accuracy is still maintained during recognition.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for accurately and intelligently identifying individuals of radar radiation sources according to an embodiment of the present invention;
fig. 2 (a) is a schematic diagram of a radiation source individual identification accuracy and a loss function by using a radar radiation source individual accurate intelligent identification method according to an embodiment of the present invention;
fig. 2 (b) is a schematic diagram of the accuracy and loss function of individual identification of radiation sources by using the dual spectrum method 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, equipment and a terminal for accurately and intelligently identifying radar radiation source individuals, and the invention is described in detail below by combining the attached drawings.
1. Illustrative embodiments are explained. This section is an explanatory embodiment expanding on the claims so as to fully understand how the present invention is embodied by those skilled in the art.
As shown in fig. 1, the method for accurately and intelligently identifying an individual radar radiation source provided by the embodiment of the present invention includes the following steps:
s101, solving a corresponding bispectrum for the received radar radiation source signal;
s102, extracting the characteristics of the bispectrum according to a Laplace-Gaussian operator;
s103, inputting the extracted features into a deep residual error network based on norm and dynamic learning rate for training to obtain a trained model;
and S104, utilizing the trained model to realize the individual intelligent recognition of the radar radiation source signal.
As a preferred embodiment, the method for accurately and intelligently identifying radar radiation source individuals with similar fingerprint characteristics provided in the embodiments of the present invention specifically includes the following steps:
the method comprises the following steps of firstly, obtaining a corresponding bispectrum of a received radar radiation source signal, and extracting the characteristics of the bispectrum according to a Laplacian of Gaussian (LoG), wherein the specific implementation process comprises the following steps:
calculating a third-order cumulant of a radar radiation source signal x (t), wherein the expression is as follows:
C 3s (τ 1 ，τ 2 )＝E{s * (t)x(t+τ 1 )x(t+τ 2 )}
where x is the received signal, τ is the time delay, s * (t) is the conjugate signal, E finds the mathematical expectation of its corresponding value, C 3s (τ 1 ，τ 2 ) Is its corresponding third order cumulative quantity.
For third-order cumulant C 3s (τ 1 ，τ 2 ) And (3) solving a bispectrum transformation, wherein the expression is as follows:
wherein, C 3s (τ 1 ，τ 2 ) For the found corresponding third order cumulant,
i.e. two-dimensional Fourier transform to obtain third-order cumulant, and B s (ω 1 ，ω 2 ) I.e. a bispectrum.
The laplacian-gaussian operator expression with 0 as the center and sigma as the gaussian standard deviation is as follows:
wherein G is σ (x, y) is a second order gaussian function, as follows:
where σ is the Gaussian standard deviation.
Then, further performing laplacian-gaussian operator feature extraction on the bispectrum specifically as follows:
LoGB s (ω 1 ，ω 2 )＝LoG＊B s (ω 1 ，ω 2 )
wherein, represents convolution operation, i.e. convolution operation is performed on the bispectrum by using an operator.
Secondly, inputting the extracted features into a deep residual error network (Resnet) based on norm and dynamic learning rate for training to obtain a trained model, wherein the specific implementation process comprises the following steps:
when the network calculates each layer of parameters, L2 norm is introduced, namely the square sum of each feature vector element is squared and then the square root of each feature vector element is calculated, so that the network is sparsely smooth.
||x|| 2 ＝(|x 1 | 2 +|x 1 | 2 +|x 1 | 2 +...+|x n | 2 ) 1/2
The dynamic learning rate adopted in each round of learning is specifically as follows:
lr(n)＝lr*0.2 [n/10]
wherein lr (n) is the current learning rate, n is the batch, and lr is the preset learning rate, that is, the learning rate becomes 0.2 times the current learning rate every 10 batches, that is, the learning rate is gradually reduced along with the round conversion.
The deep residual error network is composed of various residual error blocks, wherein each residual error fast learning rule is as follows:
F(x)＝H(x)-x
wherein H (x) is a back propagation function, F (x) is a forward propagation function, and x is a network input.
Inputting the bispectrum extracted by the Laplace-Gaussian operator into a single channel to generate H multiplied by W multiplied by 1 characteristics, wherein H and W are respectively the length and width of a characteristic diagram, 1 is the number of channels, then inputting the characteristics into a residual block 1 to carry out convolution operation, inputting the result into a residual block 2 until 4 residual blocks are operated, and finally obtaining the final identification result through a pooling layer and a full connection layer.
Thirdly, the model is utilized to realize the individual intelligent identification of radar radiation source signals, and the specific implementation process is as follows:
after receiving the unclassified preprocessed signals of the trained radar radiation source individuals, obtaining the corresponding bispectrum, extracting the characteristics of the bispectrum according to a Laplacian of Gaussian operator (LoG), and loading the trained network model. Inputting the characteristics into a network to obtain an identification result, and obtaining probability matrixes which are the individual radar radiation sources through a Softmax layer, wherein the highest probability is the identification result, and the Softmax expression is as follows:
M＝max(z)
wherein z is the result vector, max is the maximum value of z, z i Is the ith result.
The system for accurately and intelligently identifying the radar radiation source individuals comprises the following steps:
the double-spectrum calculating module is used for calculating the corresponding double spectrum of the received radar radiation source signal;
the characteristic extraction module is used for extracting the characteristics of the bispectrum according to a Laplace-Gaussian operator;
the characteristic training module is used for inputting the extracted characteristics into a deep residual error network based on norm and dynamic learning rate for training to obtain a trained model;
and the individual identification module is used for realizing the individual intelligent identification of the radar radiation source signal by utilizing the trained model.
2. Application examples. In order to prove the creativity and the technical value of the technical scheme of the invention, the part is the application example of the technical scheme of the claims on specific products or related technologies.
After the radar radiation source individual signal is intercepted, the signal is transmitted into the system after the receiver is preprocessed, and the bispectrum is extracted from the signal by the method and the characteristics are further extracted by a Gaussian Laplacian operator to form a training set and a verification set. And during training, loading the improved model, obtaining the trained model by using the training set and verifying the effect by using the verification set. After the radar radiation source individual signals are subsequently intercepted, the signals are transmitted into the system after the receiver is preprocessed, the bispectrum is extracted from the signals through the method, the features are further extracted through a Gaussian Laplace operator, and the trained model is used for judging which radar radiation source individual transmits the signals, so that the identification of the radar radiation source individuals is realized.
3. Evidence of the relevant effects of the examples. The embodiment of the invention has some positive effects in the process of research and development or use, and indeed has great advantages compared with the prior art, and the following contents are described by combining data, charts and the like in the test process.
The simulation experiment provided by the embodiment of the invention uses signals of 5 different radar radiation source individuals, the channel environment is Gaussian white noise, the signal-to-noise ratio is set to be 10dB, 1500 sample data are used for training a network for each individual, and 500 sample data are used for testing, so that the total number of training samples is 7500, and the number of test set samples is 2500 in total. During training, performing bispectrum feature extraction on all signals of a sample set by a comparison group, inputting a deep residual error network for training, and setting 100 training batches in total by adopting an SGD (sparse Gate detection) optimization method in the training process, wherein a loss function is a cross entropy loss function, and the sample data volume of each batch is set to be 32 in the training process. In addition, the method is adopted to perform bispectrum feature extraction on all signals of the sample set, a Laplacian-Gaussian operator is adopted to further extract features, the improved deep residual error network is input for training, an SGD optimization method is adopted in the training process, the loss function is a cross entropy loss function, the sample data volume of each batch in the training process is set to be 32, and 100 training batches are set in total. As shown in fig. 2 (a) - (b), the horizontal axis is the training round, the vertical axis is the accuracy and the loss function, and it can be seen from the comparison between the training set and the verification set of the two methods that, on the training set and the verification set, the accuracy of the method for accurately and intelligently identifying the individual radar radiation source provided by the embodiment of the present invention is increased from 67% to 80% and the loss function is greatly reduced, i.e. the feasibility of the method of the present invention under the condition that the radar fingerprint information is similar is proved, and a better effect is obtained.
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. The method for accurately and intelligently identifying the radar radiation source individuals is characterized by comprising the following steps of: obtaining a bispectrum corresponding to a radar radiation source signal and extracting features of a Laplace-Gaussian operator; and constructing a trained model by using the extracted features, and realizing accurate and intelligent identification of the radar radiation source individuals by using the trained model.
2. The method for accurately and intelligently identifying individuals with radar radiation sources according to claim 1, wherein the method for accurately and intelligently identifying individuals with radar radiation sources comprises the following steps:
step one, solving a corresponding bispectrum for a received radar radiation source signal;
secondly, extracting the characteristics of the bispectrum according to a Laplace-Gaussian operator;
inputting the extracted features into a deep residual error network based on norm and dynamic learning rate for training to obtain a trained model;
and fourthly, utilizing the trained model to realize the individual intelligent identification of the radar radiation source signal.
3. The method for accurately and intelligently identifying individuals as radar radiation sources according to claim 2, wherein the obtaining of the corresponding bispectrum of the received radar radiation source signals in the first step comprises:
calculating a third-order cumulant of a radar radiation source signal x (t), wherein the expression is as follows:
C 3s (τ 1 ,τ 2 )＝E{s * (t)x(t+τ 1 )x(t+τ 2 )}；
where x is the received signal, τ is the time delay, s * (t) is a conjugate signal; e is the mathematical expectation of the corresponding value, resulting in C 3s (τ 1 ,τ 2 ) Is the corresponding third order cumulant;
for third order cumulant C 3s (τ 1 ,τ 2 ) And (3) solving a bispectrum transformation, wherein the expression is as follows:
wherein, C 3s (τ 1 ,τ 2 ) For the found corresponding third order cumulant,
two-dimensional Fourier transform to obtain third-order cumulant, resulting in B s (ω 1 ,ω 2 ) Is a bispectrum.
4. The method for accurately and intelligently identifying individuals as radar radiation sources according to claim 2, wherein the step two of extracting features of the bispectrum according to a laplacian-gaussian operator comprises the following steps:
the laplacian-gaussian operator with 0 as the center and σ as the gaussian standard deviation has the following expression:
wherein G is σ (x, y) is a second order Gaussian function, and the expression is as follows:
wherein σ is a Gaussian standard deviation;
performing Laplace-Gaussian operator feature extraction on the bispectrum:
LoGB s (ω 1 ,ω 2 )＝LoG＊B s (ω 1 ,ω 2 )；
wherein, the star represents convolution operation, and the operator is used for carrying out convolution operation on the bispectrum.
5. The method for accurately and intelligently identifying individuals with radar radiation sources according to claim 2, wherein the step three of inputting the extracted features into a deep residual error network based on norm and dynamic learning rate for training, and obtaining the trained model comprises:
when the network calculates each layer of parameters, an L2 norm is introduced, and the square root is obtained after the square sum of each feature vector element, so that the network is more sparse and smooth;
||x|| 2 ＝(|x 1 | 2 +|x 1 | 2 +|x 1 | 2 +…+|x n | 2 ) 1/2 ；
the dynamic learning rate is adopted in each round of learning as follows:
lr(n)＝lr*0.2 [n/10] ；
wherein lr (n) is the current learning rate, n is the batch, lr is the preset learning rate, the learning rate becomes 0.2 times of the current learning rate every 10 batches, and the learning rate is gradually reduced along with the round conversion;
the deep residual error network is composed of various residual error blocks, wherein each residual error fast learning rule is as follows:
F(x)＝H(x)-x；
wherein H (x) is a reverse propagation function, F (x) is a forward propagation function, and x is a network input;
inputting the bispectrum extracted by the Laplace-Gaussian operator into a single channel to generate H multiplied by W multiplied by 1 characteristics, wherein H and W are the length and width of the characteristic diagram respectively, and 1 is the number of channels; inputting the characteristics into a residual block 1 for convolution operation, and inputting the result into a residual block 2 until 4 residual blocks are operated; and finally, obtaining a final recognition result through the pooling layer and the full connection layer.
6. The method for accurately and intelligently identifying individuals as radar radiation sources according to claim 2, wherein the step four of utilizing the trained model to perform intelligent identification of individuals as radar radiation source signals comprises:
obtaining a corresponding bispectrum after receiving the unclassified preprocessed signals of the trained radar radiation source individuals, extracting the characteristics of the bispectrum according to a Laplace-Gaussian operator, and loading a trained network model; inputting the characteristics into a network to obtain an identification result; obtaining probability matrixes of each radar radiation source individual through a Softmax layer, wherein the highest probability is an identification result, and the Softmax expression is as follows:
M＝max(z)；
wherein z is the result vector, max is the maximum value of z, z i Is the ith result.
7. The system for accurately and intelligently identifying the radar radiation source individuals by applying the method for accurately and intelligently identifying the radar radiation source individuals according to any one of claims 1 to 6, wherein the system for accurately and intelligently identifying the radar radiation source individuals comprises the following components:
the double-spectrum calculating module is used for calculating the corresponding double spectrum of the received radar radiation source signal;
the characteristic extraction module is used for extracting the characteristics of the bispectrum according to a Laplace-Gaussian operator;
the feature training module is used for inputting the extracted features into a deep residual error network based on norm and dynamic learning rate for training to obtain a trained model;
and the individual identification module is used for realizing the individual intelligent identification of the radar radiation source signal by utilizing the trained model.
8. A computer arrangement, characterized in that the computer arrangement 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 the method for accurate intelligent identification of an individual of a radar radiation source according to any one of claims 1 to 6.
9. A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to carry out the steps of the method for accurate intelligent identification of an individual of a radar radiation source as claimed in any one of claims 1 to 6.
10. An information data processing terminal, characterized in that the information data processing terminal is used for implementing the radar radiation source individual precise intelligent identification system according to claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211264282.7A CN115932770A (en) | 2022-10-17 | 2022-10-17 | Method, system, equipment and terminal for accurately and intelligently identifying radar radiation source individuals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211264282.7A CN115932770A (en) | 2022-10-17 | 2022-10-17 | Method, system, equipment and terminal for accurately and intelligently identifying radar radiation source individuals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115932770A true CN115932770A (en) | 2023-04-07 |
Family
ID=86549525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211264282.7A Pending CN115932770A (en) | 2022-10-17 | 2022-10-17 | Method, system, equipment and terminal for accurately and intelligently identifying radar radiation source individuals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115932770A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116842457A (en) * | 2023-07-17 | 2023-10-03 | 中国船舶集团有限公司第七二三研究所 | Long-short-term memory network-based radar radiation source individual identification method |
-
2022
- 2022-10-17 CN CN202211264282.7A patent/CN115932770A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116842457A (en) * | 2023-07-17 | 2023-10-03 | 中国船舶集团有限公司第七二三研究所 | Long-short-term memory network-based radar radiation source individual identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597043B (en) | Radar signal identification method based on quantum particle swarm convolutional neural network | |
| Liu | Multi-feature fusion for specific emitter identification via deep ensemble learning | |
| CN111160176B (en) | Fusion feature-based ground radar target classification method for one-dimensional convolutional neural network | |
| CN113156391B (en) | Radar signal multi-dimensional feature intelligent sorting method | |
| CN114564982B (en) | Automatic identification method for radar signal modulation type | |
| CN112036239B (en) | Radar signal working mode identification method and system based on deep learning network | |
| Li | Research on radar signal recognition based on automatic machine learning | |
| Wan et al. | Recognizing the HRRP by combining CNN and BiRNN with attention mechanism | |
| CN101598784A (en) | Based on distance by radar under the strong noise background of FA model as statistical recognition method | |
| CN115932770A (en) | Method, system, equipment and terminal for accurately and intelligently identifying radar radiation source individuals | |
| Zhao et al. | A novel aggregated multipath extreme gradient boosting approach for radar emitter classification | |
| Nuhoglu et al. | Image segmentation for radar signal deinterleaving using deep learning | |
| CN116165611A (en) | Accurate intelligent identification method, system, equipment and terminal for radar radiation source model | |
| CN114548170A (en) | Radar signal sorting method based on GPU (graphics processing Unit) end fuzzy C-means clustering algorithm | |
| CN112990125B (en) | Method for judging whether radiation source radar belongs to target platform | |
| CN112434662B (en) | Tea leaf scab automatic identification algorithm based on multi-scale convolutional neural network | |
| CN112213697B (en) | Feature fusion method for radar deception jamming recognition based on Bayesian decision theory | |
| CN113887583A (en) | Radar RD image target detection method based on deep learning under low signal-to-noise ratio | |
| CN111208483B (en) | Radar out-of-library target identification method based on Bayesian support vector data description | |
| CN105894035A (en) | SAR image classification method based on SAR-SIFT and DBN | |
| CN103076595B (en) | Abnormal type identifying method for multivariate discrete radar emitter signal | |
| CN111062322A (en) | Phased array radar behavior recognition method based on Support Vector Machine (SVM) | |
| CN114757225B (en) | Method, device, equipment and storage medium for determining signal sampling quality | |
| Shu et al. | An interference recognition method based on improved genetic algorithm | |
| CN116664826A (en) | Small sample point cloud semantic segmentation method |
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 |