CN116400311A - Radar interference simulation method and device based on generation countermeasure network and electronic equipment - Google Patents
Radar interference simulation method and device based on generation countermeasure network and electronic equipment Download PDFInfo
- Publication number
- CN116400311A CN116400311A CN202310669139.4A CN202310669139A CN116400311A CN 116400311 A CN116400311 A CN 116400311A CN 202310669139 A CN202310669139 A CN 202310669139A CN 116400311 A CN116400311 A CN 116400311A
- Authority
- CN
- China
- Prior art keywords
- interference
- countermeasure network
- trained
- preset
- data
- 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
- 238000004088 simulation Methods 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 70
- 230000008569 process Effects 0.000 claims abstract description 30
- 230000006870 function Effects 0.000 claims description 50
- 238000012549 training Methods 0.000 claims description 42
- 238000005070 sampling Methods 0.000 claims description 26
- 238000010586 diagram Methods 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000010801 machine learning Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000004913 activation Effects 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 6
- 239000000203 mixture Substances 0.000 description 4
- 230000008485 antagonism Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
- G01S7/40—Means for monitoring or calibrating
-
- 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
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N3/0475—Generative networks
-
- 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
- G06N3/048—Activation functions
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06N3/094—Adversarial learning
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention relates to the technical field of intersection of radar simulation and machine learning, in particular to a radar interference simulation method and device based on a generation countermeasure network and electronic equipment, comprising the following steps: generating a target interference signal based on a preset classical interference principle, inputting the target interference signal into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics, inputting actual acquisition interference data and the simulation interference signal meeting the preset signal characteristics into a pre-trained generation countermeasure network discriminator to obtain a discrimination result, optimizing the pre-trained generation countermeasure network discriminator according to the discrimination result, and optimizing the pre-trained generation countermeasure network generator according to the new discrimination result generated by the optimized pre-trained generation countermeasure network discriminator until the simulation interference signal meeting the preset signal characteristics meets preset interference conditions. Therefore, the problems of difficult modeling and complex calculation in the process of obtaining the high-fidelity interference signal are solved.
Description
Technical Field
The present invention relates to the field of intersection technologies of radar simulation and machine learning, and in particular, to a radar interference simulation method and apparatus based on generation of an countermeasure network, and an electronic device.
Background
With the increasing intensity of electronic challenge, radar is one of the important electromagnetic detection devices, whose level of development directly affects the success or failure of modern warfare. The radar simulation technology plays an important role in radar scientific research and technological progress, and deeply influences the development direction of the radar. In recent years, electronic countermeasure technology is rapidly developed, radar interference and anti-interference simulation gradually draw attention of scientific researchers, and high-fidelity radar interference signal simulation has important significance. Firstly, the research of the radar anti-interference technology depends on effective interference data, and the test condition for collecting the interference data in the field is usually scarce, so that vivid and reliable interference signal simulation is a necessary basis for researching the radar anti-interference technology. Secondly, with rapid progress and deep application of artificial intelligence, intelligent radar technology using data driving as a main means has become a development trend in the beginning, and high-efficiency and high-reliability interference signal simulation is an indispensable technical support.
However, in the actual research process, radar interference simulation has complexity, firstly, in the actual interference scene, the pattern of the interference signal, the strategy of interference release, the characteristics of the interference hardware platform and the like are quite rich, and it is difficult to fully simulate various factors to achieve high fidelity. Secondly, because the working mechanism of the actual jammer is usually strictly kept secret, the signal generated by the actual jammer cannot be strictly simulated fundamentally, and the working rule of the actual jammer can only be summarized and described from the existing data. The modeling means can only sum up partial working mechanisms, and for non-ideal factors such as signal spurious and frequency dispersion generated in the working process of the hardware of the jammer, the generation mode of the non-traditional jamming mechanism is difficult to obtain in a mode of model induction. Therefore, accurately simulating the non-ideal factors is a key point of the high-fidelity interference simulation technology, and if the simulation conditions are ignored, a large gap exists between the simulation conditions and the actual radar test, so that the research and the actual application of the radar interference technology are further limited.
Disclosure of Invention
The invention provides a radar interference simulation method, a radar interference simulation device and electronic equipment based on a generation countermeasure network, which solve the problems of difficult modeling and complicated calculation in the process of acquiring high-fidelity interference signals, generate the fidelity radar interference signals through the existing actual acquisition interference signal data set, and enable the generated radar interference signals to accord with similar probability distribution with the original data set.
An embodiment of a first aspect of the present invention provides a radar interference simulation method based on generation of an countermeasure network, including the steps of: generating a target interference signal based on a preset classical interference principle, wherein the preset classical interference principle is obtained by adopting interference data; inputting the target interference signal into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics, and inputting the actual acquisition interference data and the simulation interference signal meeting the preset signal characteristics into a pre-trained generation countermeasure network discriminator to obtain a discrimination result; optimizing the pre-trained generation countermeasure network discriminator according to the discrimination result, and optimizing the pre-trained generation countermeasure network generator according to the new discrimination result generated by the optimized pre-trained generation countermeasure network discriminator until the simulation interference signal meeting the preset signal characteristic meets the preset interference condition.
Optionally, before inputting the target interference signal to the pre-trained generating countermeasure network generator to obtain the simulated interference signal satisfying the preset signal characteristic, the method further includes: and training the generated countermeasure network generator by using the to-be-trained interference data obtained by the preset classical interference principle to obtain a generator constructed by a self-encoder in a generation countermeasure network, so as to obtain the pre-trained generated countermeasure network generator, wherein in the training process, the to-be-trained interference data is encoded based on an encoding unit of the self-encoder to obtain a feature vector of the to-be-trained interference data, and a decoding unit of the self-encoder is used for decoding the feature vector of the to-be-trained interference data to obtain a reconstruction signal corresponding to the to-be-trained interference data.
Optionally, before inputting the actual acquisition interference data and the simulated interference signal meeting preset signal characteristics to the pre-trained generating countermeasure network discriminator, the method further comprises: inputting the target interference signal generated based on the preset classical interference principle into the pre-trained generation countermeasure network generator to obtain the simulation interference signal meeting preset signal characteristics; inputting the actual acquisition interference data and the simulation interference signals meeting the preset signal characteristics to a pre-trained generation countermeasure network discriminator, and optimizing a first cost function until the first cost function meets a first preset optimization requirement.
Optionally, the first cost function is:
wherein ,
generating an countermeasure network discriminator for pre-training, +.>
In order to achieve the desire to employ the distribution of the interference data,
for inputting data +.>
For the distribution of the actual acquisition data set +.>
Data set distribution learned by generator, < >>
For gradient penalty factor, ++>
Hybrid data distribution expectations for actual data and generated data>
For the distribution of the mix of data,
for the gradient process for x +.>
Is a norm.
Optionally, the preset interference condition is that a second cost function corresponding to the pre-trained generation countermeasure network generator meets a second preset optimization requirement, where the second cost function is:
wherein ,
generating an countermeasure network generator for a pre-training, +.>
Data distribution expectations learned by generator, < +.>
For the consistency loss of the time-frequency diagram, +.>
，/>
For->
Performing short-time Fourier transform, and performing->
For->
Performing short-time Fourier transform, and performing->
() Mean squared error>
Simulation interference samples output by the countermeasure network generator are generated for pre-training.
Optionally, acquiring the target interference data includes: acquiring the target interference data based on a preset sampling formula, wherein the preset sampling formula is as follows:
wherein ,
for intermittently sampling signals>
Is a unit rectangular window signal, ">
For sampling time, +.>
In the form of a pulse width,
for periodic impact function, +.>
For cycle number>
For repeating cycles.
An embodiment of a second aspect of the present invention provides a radar interference simulation apparatus based on generation of an countermeasure network, including: the generation module is used for generating a target interference signal based on a preset classical interference principle, wherein the preset classical interference principle is obtained by adopting interference data; the input module is used for inputting the target interference signal into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics, and inputting the actual acquisition interference data and the simulation interference signal meeting the preset signal characteristics into a pre-trained generation countermeasure network discriminator to obtain a discrimination result; the optimizing module is used for optimizing the pre-trained generating countermeasure network discriminator according to the discrimination result, and optimizing the pre-trained generating countermeasure network generator according to the new discrimination result generated by the optimized pre-trained generating countermeasure network discriminator until the simulation interference signal meeting the preset signal characteristic meets the preset interference condition.
Optionally, before inputting the target interference signal to the pre-trained generating countermeasure network generator to obtain the simulated interference signal satisfying the preset signal characteristic, the input module is further configured to: and training the generated countermeasure network generator by using the to-be-trained interference data obtained by the preset classical interference principle to obtain a generator constructed by a self-encoder in a generation countermeasure network, so as to obtain the pre-trained generated countermeasure network generator, wherein in the training process, the to-be-trained interference data is encoded based on an encoding unit of the self-encoder to obtain a feature vector of the to-be-trained interference data, and a decoding unit of the self-encoder is used for decoding the feature vector of the to-be-trained interference data to obtain a reconstruction signal corresponding to the to-be-trained interference data.
Optionally, before inputting the actual acquisition interference data and the simulated interference signal meeting preset signal characteristics to the pre-trained generating countermeasure network discriminator, the input module is further configured to: inputting the target interference signal generated based on the preset classical interference principle into the pre-trained generation countermeasure network generator to obtain the simulation interference signal meeting preset signal characteristics; inputting the actual acquisition interference data and the simulation interference signals meeting the preset signal characteristics to a pre-trained generation countermeasure network discriminator, and optimizing a first cost function until the first cost function meets a first preset optimization requirement.
Optionally, the first cost function is:
wherein ,
generating an countermeasure network discriminator for pre-training, +.>
In order to achieve the desire to employ the distribution of the interference data,
for inputting data +.>
For the distribution of the actual acquisition data set +.>
Data set distribution learned by generator, < >>
For gradient penalty factor, ++>
Hybrid data distribution expectations for actual data and generated data>
For the distribution of the mix of data,
for the gradient process for x +.>
Is a norm.
Optionally, the preset interference condition is that a second cost function corresponding to the pre-trained generation countermeasure network generator meets a second preset optimization requirement, where the second cost function is:
wherein ,
generating an countermeasure network generator for a pre-training, +.>
Data distribution expectations learned by generator, < +.>
For the consistency loss of the time-frequency diagram, +.>
，/>
For->
Performing short-time Fourier transform, and performing->
For->
Performing short-time Fourier transform, and performing->
() Mean squared error>
Simulation interference samples output by the countermeasure network generator are generated for pre-training.
Optionally, the generating module is further configured to: acquiring the target interference data based on a preset sampling formula, wherein the preset sampling formula is as follows:
wherein ,
for intermittently sampling signals>
Is a unit rectangular window signal, ">
For sampling time, +.>
In the form of a pulse width,
for periodic impact function, +.>
For cycle number>
For repeating cycles.
An embodiment of a third aspect of the present invention provides an electronic device, including: the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the radar interference simulation method based on the generation countermeasure network.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program for execution by a processor for implementing a method of radar interference simulation based on generating a countermeasure network as described in the above embodiments.
The method comprises the steps of generating a target interference signal based on a preset classical interference principle and actual acquisition interference data, inputting the target interference signal into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics, inputting the actual acquisition interference data and the simulation interference signal meeting the preset signal characteristics into a pre-trained generation countermeasure network discriminator to obtain a discrimination result, optimizing the pre-trained generation countermeasure network discriminator according to the discrimination result, and optimizing the pre-trained generation countermeasure network generator according to a new discrimination result generated by the optimized pre-trained generation countermeasure network discriminator until the simulation interference signal meeting the preset signal characteristics meets preset interference conditions. Therefore, the problems of difficult modeling and complicated calculation in the process of acquiring the high-fidelity interference signal are solved, the vivid radar interference signal is generated through the existing actual interference signal data set, and the generated radar interference signal and the original data set accord with similar probability distribution.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flowchart of a radar interference simulation method based on generation of an countermeasure network according to an embodiment of the present invention;
FIG. 2 is a flow chart of a radar interference simulation method based on generating a countermeasure network in accordance with one embodiment of the present invention;
FIG. 3 is a schematic diagram of a target interference signal according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of a structure for generating a generator in an antagonism network according to one embodiment of the present invention;
FIG. 5 is a schematic diagram of a arbiter in a generation countermeasure network according to one embodiment of the invention;
FIG. 6 is a training flow diagram for generating an countermeasure network in accordance with one embodiment of the invention;
FIG. 7 is a generator pre-training flowchart in accordance with one embodiment of the present invention;
FIG. 8 is a flow chart of obtaining a target interference signal after training according to one embodiment of the present invention;
FIG. 9 is a block diagram of a radar interference simulation apparatus based on generating a countermeasure network according to an embodiment of the present invention;
fig. 10 is a schematic diagram of an electronic device structure according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The following describes a radar interference simulation method, a radar interference simulation device and an electronic device based on a generation countermeasure network according to an embodiment of the invention with reference to the accompanying drawings. Aiming at the problems of difficult modeling and complex calculation in the process of acquiring the high-fidelity interference signal, which are mentioned in the background technology center, the invention provides a radar interference simulation method based on a generation countermeasure network. Therefore, the problems of difficult modeling and complicated calculation in the process of obtaining the high-fidelity interference signal are solved, the vivid radar interference signal is generated through the existing actual interference signal data set, and the generated radar interference signal and the original data set accord with similar probability distribution.
Based on the necessity and complexity of interference simulation, related technology adopts a deep learning mode to solve related problems. Deep learning is one of the fields of machine learning research, and the core idea is to learn the internal rule and the representation level of sample data by using a neural network model similar to a human brain neuron structure, so that the data model has analysis learning capability and can complete tasks such as pattern recognition or data generation. Generating a countering network (GAN, generative Adversarial Networks) is a typical deep learning framework from which a generated model with data enhancement capabilities can be learned. GAN trains two models simultaneously: a generation model G (Generator) for learning data distribution and a discrimination model D (Discriminator) for judging the source of data, respectively. During the course of the countermeasure training, the goal of G is to generate false samples that are as similar as possible to the samples in the real dataset, so that the error probability of D discriminating true or false is maximized, while the goal of D is to discriminate whether the samples are from G or from the real dataset. Ideally, G can be learned to the data distribution in the real dataset through training without explicitly mathematically modeling the distribution. The simulation generation of the high-fidelity interference signal is carried out by using the method, a part of complicated mathematical modeling and parameter estimation processes are omitted, the existing radar interference data set can be effectively expanded, the obtained simulation data has similar distribution with the real data, and necessary help is provided for the research of radar anti-interference.
Specifically, fig. 1 is a schematic flow chart of a radar interference simulation method based on generation of an countermeasure network according to an embodiment of the present invention.
In this embodiment, as shown in fig. 2, an embodiment of the present invention includes a target interference generating module, a generator module, and a discriminator module. The target interference generation module generates a target interference signal based on a typical interference principle; the generator module modifies and processes the target interference signal into a simulation interference signal with non-ideal signal characteristics through anti-learning training; the discriminator module is used for discriminating the authenticity of the target interference signal generated by the generator module and the interference signal from the actual acquisition interference data set in the process of resisting learning training, so as to drive the generator module to learn and simulate the distribution condition of the actual acquisition data set better.
As shown in fig. 1, the radar interference simulation method based on the generation countermeasure network includes the following steps:
in step S101, a target interference signal is generated based on a preset classical interference principle, wherein the preset classical interference principle is obtained by taking interference data in practice.
For example, as a way to generate the target interference signal based on the preset classical interference principle and the actual interference data, the target interference signal may be generated based on the radar slice forwarding interference principle.
As another way to generate the target interference signal based on the preset classical interference principle and the actual interference data, the target interference signal may be generated based on the single-frequency interference principle.
Fig. 3 is a time domain diagram of ideal single-frequency interference of the target interference signal as shown in fig. 3 (a), and a time-frequency domain diagram is shown in fig. 3 (b), as an example of generating the target interference signal by the target interference generating module.
Further, in some embodiments, obtaining the target interference data includes: acquiring target interference data based on a preset sampling formula, wherein the preset sampling formula is as follows:
wherein ,
for intermittently sampling signals>
Is a unit rectangular window signal, ">
For sampling time, +.>
In the form of a pulse width,
for periodic impact function, +.>
For cycle number>
For repeating cycles.
For example, the embodiment of the invention takes radar intermittent sampling forwarding interference as an example, and assumes that the transmitting signal of the radar is
The jammer performs intermittent sampling processing on the interference data based on a preset sampling formula to obtain target interference data, which is equivalent to using an intermittent sampling signal +.>
And transmit signal->
Multiplying. Wherein the intermittent sampling signal is in the form of a rectangular envelope pulse train, as shown in formula (1), whereby a radar target interference signal can be generated.
In step S102, the target interference signal is input to a pre-trained generating countermeasure network generator to obtain a simulated interference signal satisfying the preset signal characteristic, and the actual interference data and the simulated interference signal satisfying the preset signal characteristic are input to a pre-trained generating countermeasure network discriminator to obtain a discrimination result.
The simulated interference signal meeting the preset signal characteristics refers to the simulated interference signal of the decoding unit as close as possible to the input signal of the encoding unit.
The discrimination result of the pre-trained generating countermeasure network discriminator is a value between 0 and 1, and the closer the value is to 1, the greater the probability that the pre-trained generating countermeasure network discriminator considers that the sample is from the actual acquisition interference data set, namely the more true the sample is.
It can be understood that the pre-trained generation of the simulated interference signal meeting the preset signal characteristics is output by taking the input of the countermeasure network generator as the target interference signal; the input of the pre-trained generation countermeasure network discriminator is real acquisition interference data and simulation interference signals meeting preset signal characteristics, and the output is a discrimination result.
Optionally, in some embodiments, before inputting the target interference signal to the pre-trained generation countermeasure network generator, the method further includes: the method comprises the steps of training and generating a generator constructed by a self-encoder in an countermeasure network by utilizing to-be-trained interference data obtained by a preset classical interference principle to obtain a pre-trained generated countermeasure network generator, wherein in the training process, the to-be-trained interference data is encoded based on an encoding unit of the self-encoder to obtain a feature vector of the to-be-trained interference data, and a decoding unit of the self-encoder is used for decoding the feature vector of the to-be-trained interference data to obtain a reconstructed signal corresponding to the to-be-trained interference data.
It should be understood that, in the embodiment of the present invention, the generator constructed by the self-encoder is trained by using the interference data to be trained, so as to obtain a pre-trained generated countering network generator, the interference data to be trained is encoded to obtain a feature vector of the interference data to be trained, and the decoding unit of the self-encoder is used for decoding, so as to obtain a reconstructed signal corresponding to the interference data to be trained.
The pre-trained generated countermeasure network generator structure is shown in fig. 4, and the pre-trained generated countermeasure network generator comprises an encoding unit Encoder and a decoding unit Decoder. The main body of the Encoder consists of 4 layers of sub-modules comprising a one-dimensional complex convolution module, a batch standardization and an activation function, and finally a layer of full-connection module is connected to output the characteristic vector obtained by encoding; the main body of the Decoder is composed of 5 layers of sub-modules of one-dimensional complex deconvolution and activation functions, and finally a layer of tanh activation functions is connected, and the whole function is to recover new signals by the feature vectors.
Specifically, the embodiment of the invention trains the generator constructed by the self-encoder in the generation countermeasure network by utilizing the interference data to be trained, and pretrains the generator to obtain a pretrained generation countermeasure network generator. In the pre-training process, the embodiment of the invention acquires the target interference signal corresponding to the interference data to be trained and takes the target interference signal as the input of the coding unit encoder, the coding unit encoder encodes the input target interference signal and converts the target interference signal into the characteristic vector representation, and the decoding unit encoder decodes the characteristic vector to obtain the reconstruction signal corresponding to the interference data to be trained.
Therefore, the output of the decoding unit decoder is as close as possible to the input of the encoding unit encoder, and the whole self-encoder realizes the process of encoding and reconstructing the interference signal in the pre-training stage.
Optionally, in some embodiments, before inputting the actual acquisition interference data and the simulated interference signal satisfying the preset signal characteristic into the pre-trained generation countermeasure network arbiter, the method further comprises: inputting a target interference signal generated based on a preset classical interference principle into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics; according to the actual acquisition interference data and the simulation interference signals meeting the preset signal characteristics, inputting the simulation interference signals to a pre-trained generation countermeasure network discriminator, and optimizing the first cost function until the first cost function meets the first preset optimization requirement.
Optionally, in some embodiments, the first cost function is:
wherein ,
generating an countermeasure network discriminator for pre-training, +.>
In order to achieve the desire to employ the distribution of the interference data,
for inputting data +.>
For the distribution of the actual acquisition data set +.>
Data set distribution learned by generator, < >>
For gradient penalty factor, ++ >
Hybrid data distribution expectations for actual data and generated data>
For the distribution of the mix of data,
for the gradient process for x +.>
Is a norm.
The structure of the pre-trained generating countermeasure network arbiter is shown in fig. 5, the main body of the arbiter consists of 5 layers of one-dimensional complex convolution modules, batch standardization, activation functions and sub-modules with randomly mixed phases, and finally a layer of full-connection modules and activation functions tanh are connected, the modulus of full-connection output is taken, and the modulus is taken as the final output of the arbiter after the tanh activation functions.
The first preset optimization requirement is that the first cost function value is minimum.
It can be understood that in the embodiment of the invention, the actual acquisition interference data and the simulation interference signals meeting the preset signal characteristics are input into the pre-trained generation countermeasure network discriminator to obtain a discriminating result between 0 and 1.
In step S103, the pre-trained generating countermeasure network discriminator is optimized according to the discrimination result, and the pre-trained generating countermeasure network generator is optimized according to the new discrimination result generated by the optimized pre-trained generating countermeasure network discriminator until the simulated interference signal satisfying the preset signal feature satisfies the preset interference condition.
In some embodiments, the preset interference condition is that a second cost function corresponding to the pre-trained generation countermeasure network generator meets a second preset optimization requirement, where the second cost function is:
wherein ,
generating an countermeasure network generator for a pre-training, +.>
Data distribution expectations learned by generator, < +.>
For the consistency loss of the time-frequency diagram, +.>
，/>
For->
Performing short-time Fourier transform, and performing->
For->
Performing short-time Fourier transform, and performing->
() Mean squared error>
Imitation of the output of a generator for generating an countermeasure network for pre-trainingThe samples are truly disturbed.
Specifically, the embodiment of the invention optimizes the pre-trained generating countermeasure network discriminator according to the discrimination result, updates the parameters of the pre-trained generating countermeasure network discriminator, further inputs the simulation interference signals meeting the preset signal characteristics output by the pre-trained generating countermeasure network discriminator to the pre-trained generating countermeasure network discriminator, generates a new discrimination result, calculates a second cost function based on a second cost function formula, performs gradient back propagation, optimizes the pre-trained generating countermeasure network discriminator according to the new discrimination result, and updates the parameters of the pre-trained generating countermeasure network discriminator until the value of the optimized second cost function is minimum.
Wherein, when optimizing the pre-trained generation countermeasure network generator, the embodiment of the invention adopts interference data to practice
And pre-trained simulation interference samples generated against the output of the network generator +.>
And (3) performing short-time Fourier transformation to obtain time-frequency diagrams, and taking an average mean square error MSE (Mean squared error, average mean square error) between the time-frequency diagrams to enable the simulated interference signal with the preset signal characteristics to meet the preset interference condition.
Finally, through multiple rounds of iterative countermeasure learning, the pre-trained generation countermeasure network generator tends to add non-ideal factors of the actual acquisition interference data when reconstructing interference so as to cheat the arbiter. After training is completed, inputting the target interference signal generated according to the preset classical interference principle into a pre-trained generation countermeasure network generator, and obtaining the simulation interference signal modified by the generator and meeting the preset interference condition.
In order to enable those skilled in the art to further understand the radar interference simulation method based on the generation of the countermeasure network according to the embodiment of the present invention, the following description is provided in detail with reference to a specific embodiment, as shown in fig. 6.
The input of the target interference generation module is the baseband waveform of the radar, the appointed interference generation mechanism and necessary interference parameters, and the target interference signal generated according to the radar baseband waveform and the appointed interference mechanism is output; generating a generator module in an countermeasure network, inputting a target interference signal, and outputting a simulation interference signal subjected to generator modification processing; and generating an interference signal which is input into the processed simulation interference signal and the actual acquisition interference data set by a discriminator module in the countermeasure network, and outputting a value between 0 and 1 for each input sample to represent the evaluation of the discriminator on the sample reality.
In step 601, a certain amount of interference satisfying a certain mechanism, such as slice forwarding interference, is generated based on the target interference generation module to construct a target interference data set;
in step 602, a generator is built, and based on the obtained target interference data set, the generator is pre-trained to obtain a pre-trained generation countermeasure network generator, so that the process of reconstructing target interference signal codes can be realized;
in step 603, a discriminator is established, parameters of the discriminator are randomly initialized, and an outer loop for n=1 is performed: n;
in step 604, an inner loop is performed, training the arbiter for=1: m;
in step 605, a pre-trained generating countermeasure network discriminator is obtained, a target interference signal is input into a pre-trained generating countermeasure network generator, and interference modification processing is performed, so as to obtain a simulation interference signal meeting preset signal characteristics;
in step 606, the simulated interference signals meeting the preset signal characteristics and the actual acquisition interference signals from the actual acquisition data set are respectively input into a pre-trained generation countermeasure network discriminator to obtain discrimination results, a first cost function is calculated, and gradient counter propagation is performed;
In step 607, pre-trained generated countermeasure network arbiter parameters are updated;
in step 608, the inner loop of the training arbiter is ended;
in step 609, the simulation interference signal meeting the preset signal characteristics output by the pre-trained generating countermeasure network generator is input to the pre-trained generating countermeasure network discriminator to generate a new discrimination result;
in step 610, a second cost function is calculated;
in step 611, gradient counter-propagation is performed, and parameters of the pre-trained generation countermeasure network generator are updated until the simulated interference signal satisfying the preset signal characteristics satisfies the preset interference condition;
in step 612, the outer loop is ended, completing the training.
Wherein, the training process for the generator is as shown in fig. 7:
in step 701, randomly initializing generator parameters;
in step 702, a loop n=1 is performed: n;
in step 703, inputting the target interference signal into a generator;
in step 704, MSE is calculated using pre-trained generated real acquisition interference data output and input by the antagonism network generator, a second cost function is calculated, and gradient back propagation is performed;
in step 705, pre-trained generation of antagonism network generator parameters is updated;
In step 706, if the value of the second cost function is less than the threshold value, the loop is terminated in advance, and the training is completed, otherwise the training loop is continued.
Finally, after optimization of the pre-trained generation countermeasure network generator and the pre-trained generation countermeasure network discriminator is completed, a process of obtaining a target interference signal is performed, as shown in fig. 8, firstly, a target interference generation module generates target interference data by using a preset sampling formula, then the target interference data is input into the pre-trained generation countermeasure network generator, and the pre-trained generation countermeasure network generator is modified to obtain a simulation interference signal which is similar to the actual acquisition interference signal and meets preset signal characteristics.
According to the radar interference simulation method based on the generation countermeasure network, a target interference signal is generated based on a preset classical interference principle and actual acquisition interference data, the target interference signal is input into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics, the actual acquisition interference data and the simulation interference signal meeting the preset signal characteristics are input into a pre-trained generation countermeasure network discriminator to obtain a discrimination result, the pre-trained generation countermeasure network discriminator is optimized according to the discrimination result, and a pre-trained generation countermeasure network generator is optimized according to a new discrimination result generated by the optimized pre-trained generation countermeasure network discriminator until the simulation interference signal meeting the preset signal characteristics meets preset interference conditions. Therefore, the problems of difficult modeling and complicated calculation in the process of obtaining the high-fidelity interference signal are solved, the vivid radar interference signal is generated through the existing actual interference signal data set, and the generated radar interference signal and the original data set accord with similar probability distribution.
Next, a radar interference simulation apparatus based on generation of a countermeasure network according to an embodiment of the present invention will be described with reference to the accompanying drawings.
Fig. 9 is a block diagram of a radar interference simulation apparatus based on generation of an countermeasure network according to an embodiment of the present invention.
As shown in fig. 9, the radar interference simulation apparatus 10 based on the generation countermeasure network includes: a generation module 100, an input module 200 and an optimization module 300.
The generating module 100 is configured to generate a target interference signal based on a preset classical interference principle, where the preset classical interference principle is obtained by adopting interference data; the input module 200 is configured to input a target interference signal to a pre-trained generating countermeasure network generator to obtain a simulated interference signal satisfying a preset signal characteristic, and input actual interference data and the simulated interference signal satisfying the preset signal characteristic to a pre-trained generating countermeasure network discriminator to obtain a discrimination result; the optimizing module 300 is configured to optimize the pre-trained generating countermeasure network discriminator according to the discrimination result, and optimize the pre-trained generating countermeasure network generator according to the new discrimination result generated by the optimized pre-trained generating countermeasure network discriminator until the simulated interference signal satisfying the preset signal feature satisfies the preset interference condition.
Optionally, in some embodiments, before inputting the target interference signal to the pre-trained generation countermeasure network generator to obtain the simulated interference signal satisfying the preset signal characteristic, the input module 200 is further configured to: the method comprises the steps of training and generating a generator constructed by a self-encoder in an countermeasure network by utilizing to-be-trained interference data obtained by a preset classical interference principle to obtain a pre-trained generated countermeasure network generator, wherein in the training process, the to-be-trained interference data is encoded based on an encoding unit of the self-encoder to obtain a feature vector of the to-be-trained interference data, and a decoding unit of the self-encoder is used for decoding the feature vector of the to-be-trained interference data to obtain a reconstructed signal corresponding to the to-be-trained interference data.
Optionally, in some embodiments, before inputting the actual acquisition interference data and the simulated interference signal satisfying the preset signal characteristics into the pre-trained generation countermeasure network arbiter, the input module 200 is further configured to: inputting a target interference signal generated based on a preset classical interference principle into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics; according to the actual acquisition interference data and the simulation interference signals meeting the preset signal characteristics, inputting the simulation interference signals to a pre-trained generation countermeasure network discriminator, and optimizing the first cost function until the first cost function meets the first preset optimization requirement.
Optionally, in some embodiments, the first cost function is:
wherein ,
generating an countermeasure network discriminator for pre-training, +.>
Is to adopt in practiceThe desire to interfere with the distribution of the data,
for inputting data +.>
For the distribution of the actual acquisition data set +.>
Data set distribution learned by generator, < >>
For gradient penalty factor, ++>
Hybrid data distribution expectations for actual data and generated data>
For the distribution of the mix of data,
for the gradient process for x +.>
Is a norm.
Optionally, in some embodiments, the preset interference condition is that a second cost function corresponding to the pre-trained generation countermeasure network generator meets a second preset optimization requirement, where the second cost function is:
wherein ,
generating an countermeasure network generator for a pre-training, +.>
Data distribution expectations learned by generator, < +.>
For the consistency loss of the time-frequency diagram, +.>
，/>
For->
Performing short-time Fourier transform, and performing->
For->
Performing short-time Fourier transform, and performing->
() Mean squared error>
Simulation interference samples output by the countermeasure network generator are generated for pre-training.
Optionally, in some embodiments, the generating module 100 is further configured to: acquiring target interference data based on a preset sampling formula, wherein the preset sampling formula is as follows:
wherein ,
for intermittently sampling signals>
Is a unit rectangular window signal, ">
For sampling time, +.>
In the form of a pulse width,
for periodic impact function, +.>
For cycle number>
For repeating cycles.
It should be noted that the foregoing explanation of the embodiment of the radar interference simulation method based on the generation countermeasure network is also applicable to the radar interference simulation device based on the generation countermeasure network of the embodiment, and will not be repeated here.
According to the radar interference simulation device based on the generation countermeasure network, which is provided by the embodiment of the invention, a target interference signal is generated based on a preset classical interference principle and actual acquisition interference data, the target interference signal is input into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics, the actual acquisition interference data and the simulation interference signal meeting the preset signal characteristics are input into a pre-trained generation countermeasure network discriminator to obtain a discrimination result, the pre-trained generation countermeasure network discriminator is optimized according to the discrimination result, and the pre-trained generation countermeasure network generator is optimized according to the new discrimination result generated by the optimized pre-trained generation countermeasure network discriminator until the simulation interference signal meeting the preset signal characteristics meets preset interference conditions. Therefore, the problems of difficult modeling and complicated calculation in the process of obtaining the high-fidelity interference signal are solved, the vivid radar interference signal is generated through the existing actual interference signal data set, and the generated radar interference signal and the original data set accord with similar probability distribution.
Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device may include:
The processor 1002 implements the radar interference simulation method based on generation of the countermeasure network provided in the above embodiment when executing the program.
Further, the electronic device further includes:
a communication interface 1003 for communication between the memory 1001 and the processor 1002.
If the memory 1001, the processor 1002, and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001, and the processor 1002 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (Peripheral Component, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 10, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 1001, the processor 1002, and the communication interface 1003 are integrated on a chip, the memory 1001, the processor 1002, and the communication interface 1003 may complete communication with each other through internal interfaces.
The processor 1002 may be a central processing unit (Central Processing Unit, abbreviated as CPU) or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC) or one or more integrated circuits configured to implement embodiments of the present invention.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the radar interference simulation method based on generating an countermeasure network as above.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1. The radar interference simulation method based on the generation of the countermeasure network is characterized by comprising the following steps of:
generating a target interference signal based on a preset classical interference principle, wherein the preset classical interference principle is obtained by adopting interference data;
inputting the target interference signal into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics, and inputting the actual acquisition interference data and the simulation interference signal meeting the preset signal characteristics into a pre-trained generation countermeasure network discriminator to obtain a discrimination result;
optimizing the pre-trained generation countermeasure network discriminator according to the discrimination result, and optimizing the pre-trained generation countermeasure network generator according to the new discrimination result generated by the optimized pre-trained generation countermeasure network discriminator until the simulation interference signal meeting the preset signal characteristic meets the preset interference condition.
2. The radar interference simulation method based on a generation countermeasure network according to claim 1, further comprising, before inputting the target interference signal to the pre-trained generation countermeasure network generator, obtaining the simulated interference signal satisfying a preset signal characteristic:
training a generator constructed by a self-encoder in a generating countermeasure network by using the interference data to be trained obtained by the preset classical interference principle, obtaining the pre-trained generating countermeasure network generator, wherein,
in the training process, the to-be-trained interference data is encoded based on the encoding unit of the self-encoder to obtain the feature vector of the to-be-trained interference data, and the decoding unit of the self-encoder is used for decoding the feature vector of the to-be-trained interference data to obtain the reconstruction signal corresponding to the to-be-trained interference data.
3. The radar interference simulation method based on a generation countermeasure network according to claim 2, further comprising, before inputting the actual interference data and the simulated interference signal satisfying a preset signal characteristic to the pre-trained generation countermeasure network discriminator:
Inputting the target interference signal generated based on the preset classical interference principle into the pre-trained generation countermeasure network generator to obtain the simulation interference signal meeting preset signal characteristics;
inputting the actual acquisition interference data and the simulation interference signals meeting the preset signal characteristics to a pre-trained generation countermeasure network discriminator, and optimizing a first cost function until the first cost function meets a first preset optimization requirement.
4. A radar interference simulation method based on a generation countermeasure network according to claim 3, wherein the first cost function is:
wherein ,
generating an countermeasure network discriminator for pre-training, +.>
To achieve the desire to adopt an interference data distribution, +.>
For inputting data +.>
For the distribution of the actual acquisition data set +.>
Data set distribution learned by generator, < >>
For gradient penalty factor, ++>
Hybrid data distribution expectations for actual data and generated data>
For the distribution of the mixed data->
For the gradient process for x +.>
Is a norm.
5. The radar interference simulation method based on the generation countermeasure network according to claim 4, wherein the preset interference condition is that a second cost function corresponding to the pre-trained generation countermeasure network generator meets a second preset optimization requirement, wherein the second cost function is:
wherein ,
generating an countermeasure network generator for a pre-training, +.>
The data distribution expectations learned by the generator,
for the consistency loss of the time-frequency diagram, +.>
，/>
For->
Performing short-time Fourier transform, and performing->
For->
Performing short-time Fourier transform, and performing->
() Mean squared error>
Simulation interference samples output by the countermeasure network generator are generated for pre-training.
6. The radar interference simulation method based on generation of an countermeasure network according to claim 1, wherein acquiring target interference data includes:
acquiring the target interference data based on a preset sampling formula, wherein the preset sampling formula is as follows:
wherein ,
for intermittently sampling signals>
Is a unit rectangular window signal, ">
For sampling time, +.>
In the form of a pulse width,
for periodic impact function, +.>
For cycle number>
For repeating cycles.
7. A radar interference simulation apparatus based on generation of an countermeasure network, comprising:
the generation module is used for generating a target interference signal based on a preset classical interference principle, wherein the preset classical interference principle is obtained by adopting interference data;
the input module is used for inputting the target interference signal into a pre-trained generation countermeasure network generator to obtain a simulation interference signal meeting preset signal characteristics, and inputting the actual acquisition interference data and the simulation interference signal meeting the preset signal characteristics into a pre-trained generation countermeasure network discriminator to obtain a discrimination result;
The optimizing module is used for optimizing the pre-trained generating countermeasure network discriminator according to the discrimination result, and optimizing the pre-trained generating countermeasure network generator according to the new discrimination result generated by the optimized pre-trained generating countermeasure network discriminator until the simulation interference signal meeting the preset signal characteristic meets the preset interference condition.
8. The network-based radar interference simulation apparatus for generating an countermeasure of claim 7, wherein the input module is further configured to, prior to inputting the target interference signal to the pre-trained network-based generator, obtain the simulated interference signal satisfying a preset signal characteristic:
training a generator constructed by a self-encoder in a generating countermeasure network by using the interference data to be trained obtained by the preset classical interference principle, obtaining the pre-trained generating countermeasure network generator, wherein,
in the training process, the to-be-trained interference data is encoded based on the encoding unit of the self-encoder to obtain the feature vector of the to-be-trained interference data, and the decoding unit of the self-encoder is used for decoding the feature vector of the to-be-trained interference data to obtain the reconstruction signal corresponding to the to-be-trained interference data.
9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of generating a radar interference simulation based on a countermeasure network as claimed in any one of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor for implementing a method of generating a radar interference simulation based on a countermeasure network according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310669139.4A CN116400311B (en) | 2023-06-07 | 2023-06-07 | Radar interference simulation method and device based on generation countermeasure network and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310669139.4A CN116400311B (en) | 2023-06-07 | 2023-06-07 | Radar interference simulation method and device based on generation countermeasure network and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116400311A true CN116400311A (en) | 2023-07-07 |
| CN116400311B CN116400311B (en) | 2023-09-19 |
Family
ID=87016474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310669139.4A Active CN116400311B (en) | 2023-06-07 | 2023-06-07 | Radar interference simulation method and device based on generation countermeasure network and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116400311B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107979436A (en) * | 2017-11-10 | 2018-05-01 | 广州海格通信集团股份有限公司 | Interference signal generation method, device, computer equipment and storage medium |
| CN110988818A (en) * | 2019-12-09 | 2020-04-10 | 西安电子科技大学 | Cheating interference template generation method for countermeasure network based on condition generation formula |
| CN112949846A (en) * | 2021-03-26 | 2021-06-11 | 电子科技大学 | Method for constructing generated deception jamming signal suitable for direct sequence spread spectrum system |
| CN113139916A (en) * | 2021-04-15 | 2021-07-20 | 哈尔滨工程大学 | Underwater sonar simulation image generation and data expansion method based on generation type countermeasure network |
| CN113406579A (en) * | 2021-06-07 | 2021-09-17 | 哈尔滨工程大学 | Camouflage interference waveform generation method based on deep reinforcement learning |
| US20220291329A1 (en) * | 2019-11-28 | 2022-09-15 | HELLA GmbH & Co. KGaA | Method for identifying interference in a radar system |
| CN115201768A (en) * | 2022-06-10 | 2022-10-18 | 西安电子科技大学 | Active deception jamming method for generating countermeasure network based on cycle consistency |
-
2023
- 2023-06-07 CN CN202310669139.4A patent/CN116400311B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107979436A (en) * | 2017-11-10 | 2018-05-01 | 广州海格通信集团股份有限公司 | Interference signal generation method, device, computer equipment and storage medium |
| US20220291329A1 (en) * | 2019-11-28 | 2022-09-15 | HELLA GmbH & Co. KGaA | Method for identifying interference in a radar system |
| CN110988818A (en) * | 2019-12-09 | 2020-04-10 | 西安电子科技大学 | Cheating interference template generation method for countermeasure network based on condition generation formula |
| CN112949846A (en) * | 2021-03-26 | 2021-06-11 | 电子科技大学 | Method for constructing generated deception jamming signal suitable for direct sequence spread spectrum system |
| CN113139916A (en) * | 2021-04-15 | 2021-07-20 | 哈尔滨工程大学 | Underwater sonar simulation image generation and data expansion method based on generation type countermeasure network |
| CN113406579A (en) * | 2021-06-07 | 2021-09-17 | 哈尔滨工程大学 | Camouflage interference waveform generation method based on deep reinforcement learning |
| CN115201768A (en) * | 2022-06-10 | 2022-10-18 | 西安电子科技大学 | Active deception jamming method for generating countermeasure network based on cycle consistency |
Non-Patent Citations (2)
| Title |
|---|
| WEIWEI FAN等: "Deceptive jamming template synthesis for SAR based on generative adversarial nets", 《SIGNAL PROCESSING》, vol. 172, pages 1 - 15 * |
| 李雨辰: "SAR有源欺骗干扰模版生成与效果评估方法", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 2, pages 136 - 2132 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116400311B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ravanelli et al. | Multi-task self-supervised learning for robust speech recognition | |
| CN113935460B (en) | Intelligent diagnosis method for mechanical faults under unbalanced-like data set | |
| US10360899B2 (en) | Method and device for processing speech based on artificial intelligence | |
| EP3635637A1 (en) | Pre-training system for self-learning agent in virtualized environment | |
| CN111598762A (en) | Generating type robust image steganography method | |
| US20230325982A1 (en) | Methods, systems and computer programs for processing image data for generating a filter | |
| CN115860112B (en) | Model inversion method-based countermeasure sample defense method and equipment | |
| CN111348034B (en) | Automatic parking method and system based on generation countermeasure simulation learning | |
| CN115913643A (en) | Network intrusion detection method, system and medium based on countermeasure self-encoder | |
| CN116894394A (en) | Automatic driving test scene generation method and related equipment | |
| CN116400311B (en) | Radar interference simulation method and device based on generation countermeasure network and electronic equipment | |
| CN112084936B (en) | Face image preprocessing method, device, equipment and storage medium | |
| CN110633735A (en) | Progressive depth convolution network image identification method and device based on wavelet transformation | |
| CN110299921A (en) | A kind of Turbo code deep learning interpretation method of model-driven | |
| US20230385611A1 (en) | Apparatus and method for training parametric policy | |
| CN113298895A (en) | Convergence guarantee-oriented unsupervised bidirectional generation automatic coding method and system | |
| CN116204786B (en) | Method and device for generating designated fault trend data | |
| CN116561664A (en) | TCN network-based radar radiation source inter-pulse modulation mode identification method | |
| CN116430317A (en) | Radiation source modulation pattern and individual identification method and system | |
| CN115526986A (en) | Image processing method and device and electronic equipment | |
| CN113380270B (en) | Audio sound source separation method and device, storage medium and electronic equipment | |
| CN114842242A (en) | Robust countermeasure sample generation method based on generative model | |
| CN113485313A (en) | Anti-interference method and device for automatic driving vehicle | |
| CN111090269A (en) | Sensor simulation method, device and storage medium based on generation countermeasure network | |
| Phulpagar et al. | Segmentation of noisy binary images containing circular and elliptical objects using genetic algorithms |
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 |