CN115494455B - Self-adaptive wind radar signal anti-interference processing method - Google Patents

Self-adaptive wind radar signal anti-interference processing method Download PDF

Info

Publication number
CN115494455B
CN115494455B CN202211444742.4A CN202211444742A CN115494455B CN 115494455 B CN115494455 B CN 115494455B CN 202211444742 A CN202211444742 A CN 202211444742A CN 115494455 B CN115494455 B CN 115494455B
Authority
CN
China
Prior art keywords
signal
interference
image matrix
model
wind 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.)
Active
Application number
CN202211444742.4A
Other languages
Chinese (zh)
Other versions
CN115494455A (en
Inventor
彭燕
肖科
黄巍
吴自厚
肖秀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan Saineng Environmental Measurement Technology Co ltd
Original Assignee
Hunan Saineng Environmental Measurement Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan Saineng Environmental Measurement Technology Co ltd filed Critical Hunan Saineng Environmental Measurement Technology Co ltd
Priority to CN202211444742.4A priority Critical patent/CN115494455B/en
Publication of CN115494455A publication Critical patent/CN115494455A/en
Application granted granted Critical
Publication of CN115494455B publication Critical patent/CN115494455B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G01S7/023—Interference mitigation, e.g. reducing or avoiding non-intentional interference with other HF-transmitters, base station transmitters for mobile communication or other radar systems, e.g. using electro-magnetic interference [EMI] reduction techniques
    • 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
    • G01S7/36—Means for anti-jamming, e.g. ECCM, i.e. electronic counter-counter measures
    • 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
    • G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • G01S7/414—Discriminating targets with respect to background clutter
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention relates to the technical field of signal processing, and discloses an anti-interference processing method for a self-adaptive wind radar signal, which comprises the following steps: collecting a wind radar signal as a target signal under the condition of no interference environment, applying noise interference to the target signal to obtain an interference signal, and carrying out imaging representation on the interference signal and the target signal; constructing a self-adaptive wind radar interference signal identification model; according to the training set and the constructed self-adaptive wind radar interference signal identification model, designing an optimization objective function and carrying out random optimization solution; and acquiring a wind radar signal image matrix to be subjected to anti-interference processing, and inputting the wind radar signal image matrix to a generation model to obtain an anti-interference processed wind radar signal. The invention converts the signals into the image matrix, carries out finer signal anti-interference processing on different code element signals, builds a model based on a game model optimization method, and realizes the mapping from the image matrix containing interference information to the image matrix not containing interference information.

Description

Self-adaptive wind radar signal anti-interference processing method
Technical Field
The invention relates to the technical field of signal anti-interference processing, in particular to a self-adaptive wind radar signal anti-interference processing method.
Background
The laser wind-finding radar is an active three-dimensional wind-finding remote sensing radar, which adopts a Doppler heterodyne method to measure parameters such as wind speed and wind direction according to Doppler frequency shift of laser backward scattering echoes of particulate matters (dust, cloud water drops, salt crystals, polluted aerosol, biological combustion aerosol, high-rise cloud and the like) in the air, and has the characteristics of small detection blind area, high precision, high stability, small volume, light weight and the like. However, multiple stray light sources, such as port crosstalk and APC end reflection of the circulator, polarization controller, etc., may be introduced into each optical end face of the wind radar system. The stray light sources can introduce phase induction intensity noise into beat frequency signals, reduce the signal-to-noise ratio of the system, seriously influence the application of a laser wind-finding radar, and bring great challenges for wind speed identification and parameter judgment of the wind-finding radar. Aiming at the problem, the invention provides an anti-interference processing method for an adaptive wind radar signal, which realizes fast and accurate wind radar signal anti-interference processing.
Disclosure of Invention
In view of the above, the present invention provides an adaptive wind radar signal anti-interference processing method, which aims to: 1) The signals are decomposed to be converted into an image matrix, baseband information and different code element information of the signals are converted into strong texture features in the image matrix, and the converted image matrix can more highlight the integral distribution of the wind radar signals, so that finer signal anti-interference processing is realized; 2) And constructing and optimizing a generating model and a judging model by using a game-based model optimizing method to realize the mapping from an image matrix containing interference information to an image matrix not containing interference information, wherein the generating model is responsible for receiving a signal image matrix with the interference information and outputting the signal image matrix after anti-interference processing, the judging model is responsible for judging the output result of the generating model, and if the judging finds that the output result of the generating model is poor, the generating model is trained again, so that a more accurate mapping relation is established to realize better signal anti-interference processing.
The invention provides an anti-interference processing method for a self-adaptive wind radar signal, which comprises the following steps:
s1: collecting a wind radar signal as a target signal under the condition of no interference environment, applying noise interference to the target signal to obtain an interference signal, carrying out imaging representation on the interference signal and the target signal, respectively constructing the interference signal and the target signal containing interference information as an image matrix, and taking the image matrix as a training set;
s2: the method comprises the steps of constructing a self-adaptive wind radar interference signal identification model, wherein the interference signal identification model comprises a generation model and a discrimination model, the generation model takes an interference signal image matrix as input, takes an image matrix of an anti-interference processed wind radar signal as output, and the discrimination model takes an image matrix output by the generation model and a target signal image matrix as input, and takes an anti-interference processing effect as output;
s3: according to the training set and the constructed self-adaptive wind radar interference signal identification model, an optimization objective function is designed, independent variables of the optimization objective function are self-adaptive wind radar interference signal identification model parameters, and the independent variables are anti-interference treatment effects;
S4: carrying out random optimization solution on the constructed objective function to obtain optimal self-adaptive wind radar interference signal identification model parameters, wherein a dynamic punishment secondary gradient is a main implementation mode of the random optimization method;
s5: and constructing a self-adaptive wind radar interference signal identification model according to the optimal self-adaptive wind radar interference signal identification model parameters obtained by optimization solution, collecting wind radar signals to be subjected to anti-interference processing, converting the wind radar signals into a wind radar signal image matrix, inputting the wind radar signal image matrix into a generation model, and reconstructing an output result of the generation model into the wind radar signals subjected to the anti-interference processing.
As a further improvement of the present invention:
optionally, in the step S1, the wind radar signal is collected as a target signal under the condition of no interference environment, and noise interference is applied to the target signal to obtain an interference signal, which includes:
the method comprises the steps that a wind-finding radar transmits pulse waves to a measurement balloon drifting along with wind and receives the pulse waves returned from the measurement balloon, the wind-finding radar determines the position of the measurement balloon according to the time for receiving the returned pulse waves, and determines the horizontal wind speed at each altitude according to the motion track of the measurement balloon in space, wherein the measurement balloon is provided with a reflecting target capable of reflecting radio waves, and the pulse waves transmitted by the wind-finding radar are wind-finding radar signals;
When the wind radar signal contacts air particles in the air, part of the signals form scattering echo noise, so that the time of the wind radar signal reaching a measuring balloon is influenced, and parameters such as the frequency phase of the wind radar signal and the like are changed, so that the application of the laser wind-finding radar is influenced;
the wind-finding radar transmits and collects wind-finding radar signals under the condition of no interference environment, the collected signals are used as target signals, the condition of no interference environment is an air environment without air particles, and the collected target signals are
Figure 34008DEST_PATH_IMAGE001
：
Figure 529580DEST_PATH_IMAGE002
Wherein:
t represents timing information of a target signal;
a represents the signal amplitude of the target signal;
f represents the frequency of the target signal;
Figure 495393DEST_PATH_IMAGE003
representing an initial phase of the target signal;
applying noise interference to the acquired target signal to obtain an interference signal, the applied noise including Gaussian white noise
Figure 948021DEST_PATH_IMAGE004
Analog air particulate matter noise signal composed of multiple frequency different cosine signals +.>
Figure 70698DEST_PATH_IMAGE005
：
Figure 187821DEST_PATH_IMAGE006
Wherein:
Figure 649501DEST_PATH_IMAGE007
indicating a frequency of +.>
Figure 225976DEST_PATH_IMAGE008
N represents the amplitude of the noise signal of the formed analog air particulate matter
Figure 981705DEST_PATH_IMAGE009
Is a sum of frequencies of (a);
the interference signal is expressed as
Figure 154933DEST_PATH_IMAGE010
。
Optionally, in the step S1, the interference signal and the target signal are represented in an image, and the interference signal and the target signal containing the interference information are respectively configured as an image matrix, which includes:
To interference signals
Figure 508554DEST_PATH_IMAGE011
And (2) target signal->
Figure 932845DEST_PATH_IMAGE001
Respectively carrying out imaging representation, and constructing an interference signal containing interference information and a target signal into an image matrix, wherein the signal imaging representation comprises the following steps: />
S11: to interference signals respectively
Figure 410706DEST_PATH_IMAGE011
And (2) target signal->
Figure 735377DEST_PATH_IMAGE001
Sampling with a sampling frequency of +.>
Figure 761364DEST_PATH_IMAGE012
Obtaining an interference signal sampling result with R sampling points and a target signal sampling result, wherein each sampling point signal has M code elements;
s12: the expression of the interference signal sampling result and the target signal sampling result is as follows:
Figure 437065DEST_PATH_IMAGE013
Figure 537526DEST_PATH_IMAGE014
Figure 546064DEST_PATH_IMAGE015
Figure 834963DEST_PATH_IMAGE016
wherein:
x represents a target signal
Figure 965337DEST_PATH_IMAGE017
Is>
Figure 787930DEST_PATH_IMAGE018
Representing interference signal->
Figure 87194DEST_PATH_IMAGE019
Is a sampling result of (a);
j represents an imaginary unit and,
Figure 242932DEST_PATH_IMAGE020
；
Figure 830908DEST_PATH_IMAGE021
represents the sampling frequency, +.>
Figure 722772DEST_PATH_IMAGE022
The signal parameter of the mth symbol representing the mth sample point,
Figure 781601DEST_PATH_IMAGE023
if the mth symbol of the mth sampling point is sampled, then +.>
Figure 100718DEST_PATH_IMAGE024
Otherwise->
Figure 70598DEST_PATH_IMAGE025
；
f represents the frequency of the target signal;
n represents a gaussian white noise matrix;
s represents the simulated air particulate noise signal
Figure 15420DEST_PATH_IMAGE026
Is>
Figure 649795DEST_PATH_IMAGE027
Representing an analog air particulate noise signal +.>
Figure 746671DEST_PATH_IMAGE026
The i-th mixing frequency of (a);
Figure 404179DEST_PATH_IMAGE028
representing the real part of the result of the sampling of the target signal,
Figure 480589DEST_PATH_IMAGE029
an imaginary part representing a result of the target signal sampling;
s13: sampling result of interference signal
Figure 430DEST_PATH_IMAGE030
And the object signal sampling result X is divided into a real part signal and an imaginary part signal, the real part signal of the object signal sampling result X is +.>
Figure 785983DEST_PATH_IMAGE031
The method comprises the following steps:
Figure 272066DEST_PATH_IMAGE032
imaginary signal of the target signal sampling result X
Figure 152166DEST_PATH_IMAGE033
The method comprises the following steps: />
Figure 557871DEST_PATH_IMAGE034
The interference signal sampling result
Figure 612196DEST_PATH_IMAGE030
Is>
Figure 946094DEST_PATH_IMAGE035
The method comprises the following steps:
Figure 69033DEST_PATH_IMAGE036
Figure 326314DEST_PATH_IMAGE037
the interference signal sampling result
Figure 640621DEST_PATH_IMAGE030
Is>
Figure 838646DEST_PATH_IMAGE038
The method comprises the following steps:
Figure 794970DEST_PATH_IMAGE039
Figure 900899DEST_PATH_IMAGE040
s14: the real part and the imaginary part signals of the interference signal sampling result and the target signal sampling result are respectively constructed into an image matrix:
Figure 559675DEST_PATH_IMAGE041
/>
Figure 805849DEST_PATH_IMAGE042
Figure 64399DEST_PATH_IMAGE043
Figure 502464DEST_PATH_IMAGE044
Figure 220890DEST_PATH_IMAGE045
Figure 193175DEST_PATH_IMAGE046
Figure 428985DEST_PATH_IMAGE047
Figure 721557DEST_PATH_IMAGE048
wherein:
Figure 843840DEST_PATH_IMAGE049
real part signal corresponding image matrix representing sampling result of target signal,/->
Figure 471131DEST_PATH_IMAGE050
An imaginary signal corresponding image matrix representing the sampling result of the target signal; in the embodiment of the invention, each row in the image matrix represents the same code element, and each point in the same row represents a sampling point of the code element at different moments;
Figure 995784DEST_PATH_IMAGE051
real representation of interference signal sampling resultsPartial signal corresponds to the image matrix,>
Figure 501719DEST_PATH_IMAGE052
an imaginary signal corresponding image matrix representing the result of the interference signal sampling; />
S15: the interference signal
Figure 561948DEST_PATH_IMAGE053
The corresponding image matrix is +.>
Figure 177999DEST_PATH_IMAGE054
Target signal->
Figure 972255DEST_PATH_IMAGE055
The corresponding image matrix is +.>
Figure 285425DEST_PATH_IMAGE056
；
Repeating the step S1, acquiring K target signals, acquiring K groups of image matrixes to form a training set data,
Figure 955703DEST_PATH_IMAGE057
Wherein->
Figure 151061DEST_PATH_IMAGE058
Representing the acquired kth target signal +.>
Figure 286026DEST_PATH_IMAGE059
Is>
Figure 486325DEST_PATH_IMAGE060
Representing the target signal +.>
Figure 888357DEST_PATH_IMAGE059
Corresponding interference signal->
Figure 944912DEST_PATH_IMAGE061
Is a matrix of images of (a).
Optionally, the constructing an adaptive wind radar interference signal identification model in the step S2 includes:
constructing an adaptive wind radar interference signal identification model, wherein the adaptive wind radar interference signal identification model comprises a generation model G and a discrimination model D;
the generation model takes an image matrix of an interference signal as input, takes an image matrix of an anti-interference processed wind radar signal as output, and the discrimination model takes an image matrix output by the generation model and a target signal image matrix as input, and takes an anti-interference processing effect of the anti-interference processed wind radar signal as output;
the structure of the generated model sequentially comprises a convolution layer, an activation function layer and a deconvolution layer, wherein the number of the convolution layers is 5, the number of the deconvolution layer is 5, an activation function layer is arranged between any two convolution layers, the activation function is a ReLU function, and an interference image matrix sequentially passes through the 5 convolution layers and the 5 deconvolution layers to obtain an image matrix of the wind radar signal after anti-interference treatment; the discriminant model is a support vector machine model for two classifications, and the model output result comprises
Figure 457802DEST_PATH_IMAGE062
Indicating whether the image matrix output by the generation model has interference information or not and whether the target signal image matrix has interference information or not, if the judgment model outputs 1, indicating that the interference information exists, otherwise, indicating that the interference information does not exist.
Optionally, in the step S3, designing an optimization objective function according to the training set and the constructed adaptive wind radar interference signal identification model includes:
according to the constructed self-adaptive wind radar interference signal identification model, an optimization objective function is designed, the independent variable of the optimization objective function is self-adaptive wind radar interference signal identification model parameters, the dependent variable is anti-interference processing effect, and the optimization objective is maximizing the anti-interference processing effect, wherein the self-adaptive wind radar interference signal identification model parameters comprise generation model parameters
Figure 699558DEST_PATH_IMAGE063
Discrimination model parameters->
Figure 640533DEST_PATH_IMAGE064
Generating model parameters->
Figure 341642DEST_PATH_IMAGE063
Weight and bias parameters including convolution layer and deconvolution layer, discriminant model parameters +.>
Figure 284321DEST_PATH_IMAGE064
The method comprises the steps of supporting hyperplane parameters of a vector machine model;
the optimization objective function is as follows:
Figure 987441DEST_PATH_IMAGE065
Figure 200117DEST_PATH_IMAGE066
wherein:
Figure 234194DEST_PATH_IMAGE067
the representation is based on the parameters +.>
Figure 780232DEST_PATH_IMAGE064
Is a discriminant model of->
Figure 308165DEST_PATH_IMAGE068
1 indicates the presence of interference information, -1 indicates the absence of interference information;
Figure 599732DEST_PATH_IMAGE067
the representation is based on the parameters +. >
Figure 9853DEST_PATH_IMAGE069
The generated model output result is the image matrix of the wind radar signal after the anti-interference treatment; />
Figure 370034DEST_PATH_IMAGE070
Represents the kth target signal +.>
Figure 175310DEST_PATH_IMAGE071
Is>
Figure 995367DEST_PATH_IMAGE072
Representing the target signal +.>
Figure 815423DEST_PATH_IMAGE071
Corresponding interference signal->
Figure 638017DEST_PATH_IMAGE073
Is a matrix of images of (a).
Optionally, in the step S4, a random optimization solution is performed on the constructed optimization objective function to obtain an optimal adaptive wind radar interference signal identification model parameter, which includes:
carrying out random optimization solving on the constructed optimization objective function to obtain optimal self-adaptive wind radar interference signal identification model parameters, wherein a dynamic punishment secondary gradient is a main implementation mode of the random optimization method;
the random optimization solving flow of the optimization objective function is as follows:
s41: random generation of initial model parameters
Figure 78225DEST_PATH_IMAGE074
Step sequence->
Figure 833298DEST_PATH_IMAGE075
Wherein
Figure 578532DEST_PATH_IMAGE076
The step length of the max iteration is represented, max represents the maximum iterative optimization frequency of the algorithm for random optimization solution, and the initial model parameter +.>
Figure 844297DEST_PATH_IMAGE077
Setting the current iteration times of the algorithm as d, and setting the initial value of d as 0;
s42: if it is
Figure 705723DEST_PATH_IMAGE078
Output +.>
Figure 274108DEST_PATH_IMAGE079
For optimal discrimination model parameters->
Figure 772216DEST_PATH_IMAGE080
Step S44 is entered, otherwise step S43 is entered, wherein +.>
Figure 74628DEST_PATH_IMAGE081
；
S43: update to get
Figure 958271DEST_PATH_IMAGE082
：
Figure 995759DEST_PATH_IMAGE083
Let->
Figure 355065DEST_PATH_IMAGE084
Returning to step S42;
s44: discriminating model parameters in fixed optimization objective function
Figure 48784DEST_PATH_IMAGE085
Calculated to make->
Figure 678611DEST_PATH_IMAGE086
Is the optimal generator model parameter +.>
Figure 323219DEST_PATH_IMAGE087
。
Optionally, in the step S5, an adaptive wind radar interference signal recognition model is constructed according to the optimal adaptive wind radar interference signal recognition model parameters obtained by the optimization solution, and the method includes:
identifying model parameters according to optimal adaptive wind radar interference signals obtained by optimization
Figure 58569DEST_PATH_IMAGE085
And +.>
Figure 643396DEST_PATH_IMAGE087
And respectively constructing an optimal discriminant model and an optimal generator model.
Optionally, in the step S5, the acquired wind radar signal image matrix is input to a generating model, and an output result of the generating model is reconstructed into a wind radar signal after the anti-interference processing, which includes:
the method comprises the steps of collecting a wind radar signal to be subjected to anti-interference processing, converting the wind radar signal into a wind radar signal image matrix, inputting the wind radar signal image matrix into a generated model obtained by optimizing and solving, outputting the model into the wind radar signal image matrix subjected to the anti-interference processing, and reconstructing the wind radar signal image matrix subjected to the anti-interference processing into the wind radar signal subjected to the anti-interference processing.
In order to solve the above problems, the present invention provides an adaptive wind radar signal anti-interference processing device, which includes:
the signal image matrix extraction module is used for collecting a wind radar signal as a target signal under the interference-free environment condition, applying noise interference to the target signal to obtain an interference signal, carrying out imaging representation on the interference signal and the target signal, and respectively constructing the interference signal and the target signal containing interference information into an image matrix; collecting a wind radar signal to be subjected to anti-interference processing and converting the wind radar signal into a wind radar signal image matrix;
the model construction device is used for constructing an adaptive wind radar interference signal identification model, designing an optimization objective function according to the training set and the constructed adaptive wind radar interference signal identification model, carrying out random optimization solution on the constructed objective function, and constructing the adaptive wind radar interference signal identification model according to the optimal adaptive wind radar interference signal identification model parameters obtained by the optimization solution;
the signal anti-interference processing device is used for inputting the wind radar signal image matrix into the generation model and reconstructing the output result of the generation model into an anti-interference processed wind radar signal.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
a memory storing at least one instruction; and the processor executes the instructions stored in the memory to realize the self-adaptive wind radar signal anti-interference processing method.
In order to solve the above-mentioned problems, the present invention further provides a computer readable storage medium, in which at least one instruction is stored, the at least one instruction being executed by a processor in an electronic device to implement the adaptive wind radar signal anti-interference processing method described above.
Compared with the prior art, the invention provides an anti-interference processing method for a self-adaptive wind radar signal, which has the following advantages:
firstly, the proposal provides a signal imaging representation method by aiming at interference signals
Figure 32789DEST_PATH_IMAGE011
With the target signal
Figure 477327DEST_PATH_IMAGE001
Respectively carrying out imaging representation, and constructing an interference signal containing interference information and a target signal into an image matrix, wherein the signal imaging representation comprises the following steps: respectively->
Figure 906165DEST_PATH_IMAGE011
And (2) target signal->
Figure 996481DEST_PATH_IMAGE001
Sampling with the sampling frequency of
Figure 988183DEST_PATH_IMAGE088
Obtaining an interference signal sampling result with R sampling points and a target signal sampling result, wherein each sampling point signal has M code elements; the expression of the interference signal sampling result and the target signal sampling result is as follows:
Figure 272797DEST_PATH_IMAGE089
Figure 828412DEST_PATH_IMAGE090
Figure 425482DEST_PATH_IMAGE091
Figure 822091DEST_PATH_IMAGE092
Wherein: x represents a target signal
Figure 461626DEST_PATH_IMAGE001
Is>
Figure 911062DEST_PATH_IMAGE018
Representing interference signal->
Figure 93913DEST_PATH_IMAGE093
Is a sampling result of (a); j represents imaginary units, ">
Figure 410274DEST_PATH_IMAGE094
；/>
Figure 472908DEST_PATH_IMAGE088
Represents the sampling frequency, +.>
Figure 239001DEST_PATH_IMAGE095
The signal parameter of the mth symbol representing the mth sample point,
Figure 222613DEST_PATH_IMAGE096
if the mth symbol of the mth sampling point is sampled, then +.>
Figure 498874DEST_PATH_IMAGE097
Otherwise->
Figure 624087DEST_PATH_IMAGE098
；/>
Figure 790058DEST_PATH_IMAGE099
Representing the frequency of the target signal; n represents a gaussian white noise matrix; s represents the analog air particulate noise signal +.>
Figure 767242DEST_PATH_IMAGE100
Is>
Figure 320845DEST_PATH_IMAGE101
Representing an analog air particulate noise signal +.>
Figure 318757DEST_PATH_IMAGE100
The i-th mixing frequency of (a); />
Figure 712305DEST_PATH_IMAGE102
Representing the real part of the sampling result of the target signal, +.>
Figure 260223DEST_PATH_IMAGE103
An imaginary part representing a result of the target signal sampling; sampling result of interference signal->
Figure 901289DEST_PATH_IMAGE104
Target signal sampling result->
Figure 230289DEST_PATH_IMAGE105
Divided into real and imaginary signals, the objectStandard signal sampling result +.>
Figure 458270DEST_PATH_IMAGE105
Is>
Figure 42835DEST_PATH_IMAGE106
The method comprises the following steps:
Figure 36942DEST_PATH_IMAGE107
imaginary signal of the target signal sampling result X
Figure 799493DEST_PATH_IMAGE108
The method comprises the following steps:
Figure 13306DEST_PATH_IMAGE109
the interference signal sampling result
Figure 792492DEST_PATH_IMAGE104
Is>
Figure 80254DEST_PATH_IMAGE110
The method comprises the following steps:
Figure 13706DEST_PATH_IMAGE111
Figure 682191DEST_PATH_IMAGE112
the interference signal sampling result
Figure 405297DEST_PATH_IMAGE104
Is>
Figure 501560DEST_PATH_IMAGE113
The method comprises the following steps:
Figure 484209DEST_PATH_IMAGE114
Figure 610297DEST_PATH_IMAGE115
respectively constructing real part and imaginary part signals of the interference signal sampling result and the target signal sampling result into an image matrix; according to the scheme, the signals are decomposed, the signals are converted into the image matrix, the baseband information of the signals and the information of different code elements are converted into the strong texture characteristics in the image matrix, the converted image matrix can better highlight the integral distribution of the wind radar signals, and the signals of different code elements are subjected to anti-interference processing, so that finer signal anti-interference processing is realized.
Meanwhile, the scheme provides a method for constructing an adaptive wind radar interference signal identification model, wherein the adaptive wind radar interference signal identification model comprises a generation model G and a discrimination model D; the generation model takes an image matrix of an interference signal as input, takes an image matrix of an anti-interference processed wind radar signal as output, and the discrimination model takes an image matrix output by the generation model and a target signal image matrix as input, and takes an anti-interference processing effect of the anti-interference processed wind radar signal as output; the structure of the generated model sequentially comprises a convolution layer, an activation function layer and a deconvolution layer, wherein the number of the convolution layers is 5, the number of the deconvolution layer is 5, an activation function layer is arranged between any two convolution layers, the activation function is a ReLU function, and an interference image matrix sequentially passes through the 5 convolution layers and the 5 deconvolution layers to obtain an image matrix of the wind radar signal after anti-interference treatment; the discriminant model is a support vector machine model for two classifications, and the model output result comprises
Figure 638558DEST_PATH_IMAGE116
Indicating whether the image matrix output by the generation model has interference information or not and whether the target signal image matrix has interference information or not, if the judgment model outputs 1, indicating that the interference information exists, otherwise, indicating that the interference information does not exist. The present solution is based on utilizing a game-based model The optimization method is used for constructing and optimizing a generating model and a judging model to realize the mapping from an image matrix containing interference information to an image matrix without the interference information, wherein the generating model is responsible for receiving a signal image matrix with the interference information and outputting a signal image matrix after anti-interference processing, the judging model is responsible for judging the output result of the generating model, and if the judging result of the generating model is poor, the generating model is trained again, so that a more accurate mapping relation is established to realize better signal anti-interference processing.
Drawings
Fig. 1 is a schematic flow chart of an adaptive wind radar signal anti-interference processing method according to an embodiment of the present invention;
FIG. 2 is a functional block diagram of an adaptive wind radar signal anti-interference processing device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for implementing an anti-interference processing method for adaptive wind radar signals according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides an anti-interference processing method for a self-adaptive wind radar signal. The execution main body of the adaptive wind radar signal anti-interference processing method includes, but is not limited to, at least one of a server, a terminal and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the adaptive wind radar signal anti-interference processing method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Example 1:
s1: and acquiring a wind radar signal as a target signal under the condition of no interference environment, applying noise interference to the target signal to obtain an interference signal, carrying out imaging representation on the interference signal and the target signal, respectively constructing the interference signal and the target signal containing interference information as an image matrix, and taking the image matrix as a training set.
In the step S1, a wind radar signal is collected as a target signal under an interference-free environment condition, and noise interference is applied to the target signal to obtain an interference signal, which includes:
The method comprises the steps that a wind-finding radar transmits pulse waves to a measurement balloon drifting along with wind and receives the pulse waves returned from the measurement balloon, the wind-finding radar determines the position of the measurement balloon according to the time for receiving the returned pulse waves, and determines the horizontal wind speed at each altitude according to the motion track of the measurement balloon in space, wherein the measurement balloon is provided with a reflecting target capable of reflecting radio waves, and the pulse waves transmitted by the wind-finding radar are wind-finding radar signals;
when the wind radar signal contacts air particles in the air, part of the signals form scattering echo noise, so that the time of the wind radar signal reaching a measuring balloon is influenced, and parameters such as the frequency phase of the wind radar signal and the like are changed, so that the application of the laser wind-finding radar is influenced;
the wind-finding radar transmits and collects wind-finding radar signals under the condition of no interference environment, the collected signals are used as target signals, the condition of no interference environment is an air environment without air particles, and the collected target signals are
Figure 166491DEST_PATH_IMAGE001
：
Figure 438816DEST_PATH_IMAGE117
Wherein:
t represents timing information of a target signal;
a represents the signal amplitude of the target signal;
f represents the frequency of the target signal;
Figure 350403DEST_PATH_IMAGE118
representing an initial phase of the target signal;
Applying noise interference to the acquired target signal to obtain an interference signal, the applied noise including Gaussian white noise
Figure 884152DEST_PATH_IMAGE119
Analog air particulate matter noise signal composed of multiple frequency different cosine signals +.>
Figure 821585DEST_PATH_IMAGE120
：
Figure 267741DEST_PATH_IMAGE121
Wherein:
Figure 165158DEST_PATH_IMAGE122
indicating a frequency of +.>
Figure 469975DEST_PATH_IMAGE123
N represents the amplitude of the noise signal of the constituted analog air particulate matter noise signal +.>
Figure 769239DEST_PATH_IMAGE120
Is a sum of frequencies of (a);
the interference signal is expressed as
Figure 386296DEST_PATH_IMAGE124
。
In the step S1, the interference signal and the target signal are represented by imaging, and the interference signal and the target signal containing the interference information are respectively configured as an image matrix, which includes:
to interference signals
Figure 9825DEST_PATH_IMAGE011
And (2) target signal->
Figure 885377DEST_PATH_IMAGE001
Respectively carrying out imaging representation, and constructing an interference signal containing interference information and a target signal into an image matrix, wherein the signal imaging representation comprises the following steps:
s11: to interference signals respectively
Figure 540612DEST_PATH_IMAGE011
And (2) target signal->
Figure 591220DEST_PATH_IMAGE001
Sampling with a sampling frequency of +.>
Figure 197650DEST_PATH_IMAGE125
Obtaining an interference signal sampling result with R sampling points and a target signal sampling result, wherein each sampling point signal has M code elements;
s12: the expression of the interference signal sampling result and the target signal sampling result is as follows:
Figure 440675DEST_PATH_IMAGE126
Figure 121055DEST_PATH_IMAGE127
Figure 94564DEST_PATH_IMAGE128
Figure 361859DEST_PATH_IMAGE129
wherein:
x represents a target signal
Figure 703848DEST_PATH_IMAGE001
Is >
Figure 268428DEST_PATH_IMAGE130
Representing interference signal->
Figure 460506DEST_PATH_IMAGE011
Is a sampling result of (a);
j represents an imaginary unit and,
Figure 916895DEST_PATH_IMAGE131
；
Figure 301390DEST_PATH_IMAGE125
represents the sampling frequency, +.>
Figure 644777DEST_PATH_IMAGE132
The signal parameter of the mth symbol representing the mth sample point,
Figure 319341DEST_PATH_IMAGE133
if the mth symbol of the mth sampling point is sampled, then +.>
Figure 761562DEST_PATH_IMAGE134
Otherwise->
Figure 868189DEST_PATH_IMAGE135
；
Figure 439985DEST_PATH_IMAGE136
Representing the frequency of the target signal; />
n represents a gaussian white noise matrix;
s represents the simulated air particulate noise signal
Figure 919071DEST_PATH_IMAGE120
Is>
Figure 474686DEST_PATH_IMAGE137
Representation modelPseudo-air particulate noise signal->
Figure 322688DEST_PATH_IMAGE120
The i-th mixing frequency of (a);
Figure 513104DEST_PATH_IMAGE138
representing the real part of the result of the sampling of the target signal,
Figure 670416DEST_PATH_IMAGE139
an imaginary part representing a result of the target signal sampling;
s13: sampling result of interference signal
Figure 949213DEST_PATH_IMAGE130
Target signal sampling result->
Figure 869414DEST_PATH_IMAGE140
Dividing into a real part signal and an imaginary part signal, the target signal sampling result +.>
Figure 884643DEST_PATH_IMAGE140
Is>
Figure 838955DEST_PATH_IMAGE141
The method comprises the following steps:
Figure 978950DEST_PATH_IMAGE142
imaginary signal of the target signal sampling result X
Figure 493720DEST_PATH_IMAGE143
The method comprises the following steps:
Figure 271445DEST_PATH_IMAGE144
the interference signal sampling result
Figure 160773DEST_PATH_IMAGE145
Is>
Figure 553444DEST_PATH_IMAGE146
The method comprises the following steps:
Figure 422305DEST_PATH_IMAGE147
Figure 818652DEST_PATH_IMAGE148
the interference signal sampling result
Figure 111836DEST_PATH_IMAGE149
Is>
Figure 977155DEST_PATH_IMAGE150
The method comprises the following steps:
Figure 882663DEST_PATH_IMAGE151
Figure 637911DEST_PATH_IMAGE152
s14: the real part and the imaginary part signals of the interference signal sampling result and the target signal sampling result are respectively constructed into an image matrix:
Figure 869041DEST_PATH_IMAGE041
/>
Figure 956076DEST_PATH_IMAGE042
Figure 163810DEST_PATH_IMAGE043
Figure 534749DEST_PATH_IMAGE044
Figure 94037DEST_PATH_IMAGE153
Figure 534947DEST_PATH_IMAGE154
/>
Figure 454361DEST_PATH_IMAGE155
/>
Figure 164959DEST_PATH_IMAGE156
wherein:
Figure 236427DEST_PATH_IMAGE157
real part signal corresponding image matrix representing sampling result of target signal,/->
Figure 547323DEST_PATH_IMAGE158
An imaginary signal corresponding image matrix representing the sampling result of the target signal; in the embodiment of the invention, each row in the image matrix represents the same code element, and each point in the same row represents a sampling point of the code element at different moments;
Figure 99789DEST_PATH_IMAGE159
Real part signal corresponding image matrix representing interference signal sampling result,/->
Figure 464561DEST_PATH_IMAGE160
An imaginary signal corresponding image matrix representing the result of the interference signal sampling;
s15: the interference signal
Figure 349340DEST_PATH_IMAGE161
The corresponding image matrix is +.>
Figure 508051DEST_PATH_IMAGE162
Target signal
Figure 251492DEST_PATH_IMAGE163
The corresponding image matrix is +.>
Figure 576163DEST_PATH_IMAGE164
；
Repeating the step S1, acquiring K target signals, acquiring K groups of image matrixes to form a training set data,
Figure 336571DEST_PATH_IMAGE165
wherein->
Figure 746692DEST_PATH_IMAGE166
Representing the acquired kth target signal
Figure 780244DEST_PATH_IMAGE071
Is>
Figure 460886DEST_PATH_IMAGE167
Representing the target signal +.>
Figure 107375DEST_PATH_IMAGE071
Corresponding interference signal->
Figure 270371DEST_PATH_IMAGE168
Is a matrix of images of (a).
S2: and constructing an adaptive wind radar interference signal identification model.
And in the step S2, an adaptive wind radar interference signal identification model is constructed, which comprises the following steps:
constructing an adaptive wind radar interference signal identification model, wherein the adaptive wind radar interference signal identification model comprises a generation model G and a discrimination model D;
the generation model takes an image matrix of an interference signal as input, takes an image matrix of an anti-interference processed wind radar signal as output, and the discrimination model takes an image matrix output by the generation model and a target signal image matrix as input, and takes an anti-interference processing effect of the anti-interference processed wind radar signal as output;
the structure of the generated model sequentially comprises a convolution layer, an activation function layer and a deconvolution layer, wherein the number of the convolution layers is 5, the number of the deconvolution layer is 5, an activation function layer is arranged between any two convolution layers, the activation function is a ReLU function, and an interference image matrix sequentially passes through the 5 convolution layers and the 5 deconvolution layers to obtain an image matrix of the wind radar signal after anti-interference treatment; the judging model is a support vector machine model for two classifications, and the model output result comprises the information of whether the image matrix output by the generating model exists or not and whether the image matrix of the target signal exists or not, if the judging model outputs 1, the information of the interference exists, otherwise, the information of the interference does not exist.
S3: and designing and optimizing an objective function according to the training set and the constructed self-adaptive wind radar interference signal identification model.
In the step S3, an optimization objective function is designed according to the training set and the constructed self-adaptive wind radar interference signal identification model, and the method comprises the following steps:
according to the constructed self-adaptive wind radar interference signal identification model, an optimization objective function is designed, the independent variable of the optimization objective function is self-adaptive wind radar interference signal identification model parameters, the dependent variable is anti-interference processing effect, and the optimization objective is maximizing the anti-interference processing effect, wherein the self-adaptive wind radar interference signal identification model parameters comprise generation model parameters
Figure 906014DEST_PATH_IMAGE169
Discrimination model parameters->
Figure 80644DEST_PATH_IMAGE170
Generating model parameters->
Figure 575997DEST_PATH_IMAGE169
Weight and bias parameters of convolution layer and deconvolution layer, discriminant model parameters +.>
Figure 586809DEST_PATH_IMAGE170
The method comprises the steps of supporting hyperplane parameters of a vector machine model;
the optimization objective function is as follows:
Figure 321416DEST_PATH_IMAGE171
Figure 114666DEST_PATH_IMAGE172
wherein:
Figure 276526DEST_PATH_IMAGE173
the representation is based on the parameters +.>
Figure 509056DEST_PATH_IMAGE170
Is a discriminant model of->
Figure 540029DEST_PATH_IMAGE174
1 indicates the presence of interference information, -1 indicates the absence of interference information;
Figure 423671DEST_PATH_IMAGE175
the representation is based on the parameters +.>
Figure 523477DEST_PATH_IMAGE169
The generated model output result is the image matrix of the wind radar signal after the anti-interference treatment;
Figure 37110DEST_PATH_IMAGE176
represents the kth target signal +. >
Figure 988886DEST_PATH_IMAGE071
Is>
Figure 8925DEST_PATH_IMAGE177
Representing the target signal +.>
Figure 282562DEST_PATH_IMAGE071
Corresponding interference signal->
Figure 535688DEST_PATH_IMAGE178
Is a matrix of images of (a).
S4: and carrying out random optimization solution on the constructed objective function to obtain the optimal self-adaptive wind radar interference signal identification model parameters.
And S4, carrying out random optimization solving on the constructed optimization objective function to obtain optimal self-adaptive wind radar interference signal identification model parameters, wherein the method comprises the following steps:
carrying out random optimization solving on the constructed optimization objective function to obtain optimal self-adaptive wind radar interference signal identification model parameters, wherein a dynamic punishment secondary gradient is a main implementation mode of the random optimization method;
the random optimization solving flow of the optimization objective function is as follows:
s41: random generation of initial model parameters
Figure 776308DEST_PATH_IMAGE074
Step sequence->
Figure 398657DEST_PATH_IMAGE075
Wherein
Figure 496057DEST_PATH_IMAGE076
The step length of the max iteration is represented, max represents the maximum iterative optimization frequency of the algorithm for random optimization solution, and the initial model parameter +.>
Figure 564376DEST_PATH_IMAGE077
Setting the current iteration times of the algorithm as d, and setting the initial value of d as 0;
s42: if it is
Figure 92177DEST_PATH_IMAGE078
Output +.>
Figure 165437DEST_PATH_IMAGE079
For optimal discrimination model parameters->
Figure 683006DEST_PATH_IMAGE179
Step S44 is entered, otherwise step S43 is entered, wherein +.>
Figure 127369DEST_PATH_IMAGE180
；
S43: update to get
Figure 522841DEST_PATH_IMAGE181
：
Figure 843751DEST_PATH_IMAGE182
Let->
Figure 266642DEST_PATH_IMAGE084
Returning to step S42;
s44: discriminating model parameters in fixed optimization objective function
Figure 466810DEST_PATH_IMAGE179
Calculated to make->
Figure 663043DEST_PATH_IMAGE183
Is the optimal generator model parameter +.>
Figure 209431DEST_PATH_IMAGE184
。
S5: and constructing a self-adaptive wind radar interference signal identification model according to the optimal self-adaptive wind radar interference signal identification model parameters obtained by optimization solution, collecting wind radar signals to be subjected to anti-interference processing, converting the wind radar signals into a wind radar signal image matrix, inputting the wind radar signal image matrix into a generation model, and reconstructing an output result of the generation model into the wind radar signals subjected to the anti-interference processing.
In the step S5, an adaptive wind radar interference signal identification model is constructed according to the optimal adaptive wind radar interference signal identification model parameters obtained by optimization solution, and the method comprises the following steps:
identifying model parameters according to optimal adaptive wind radar interference signals obtained by optimization
Figure 22797DEST_PATH_IMAGE179
And +.>
Figure 452205DEST_PATH_IMAGE184
And respectively constructing an optimal discriminant model and an optimal generator model.
In the step S5, the acquired wind radar signal image matrix is input into a generation model, and the output result of the generation model is reconstructed into the wind radar signal after the anti-interference processing, which includes:
the method comprises the steps of collecting a wind radar signal to be subjected to anti-interference processing, converting the wind radar signal into a wind radar signal image matrix, inputting the wind radar signal image matrix into a generated model obtained by optimizing and solving, outputting the model into the wind radar signal image matrix subjected to the anti-interference processing, and reconstructing the wind radar signal image matrix subjected to the anti-interference processing into the wind radar signal subjected to the anti-interference processing.
Example 2:
fig. 2 is a functional block diagram of an adaptive wind radar signal anti-interference processing device according to an embodiment of the present invention, which can implement the adaptive wind radar signal anti-interference processing method in embodiment 1.
The adaptive wind radar signal anti-interference processing device 100 of the present invention may be installed in an electronic device. According to the implemented functions, the adaptive wind radar signal anti-interference processing device may include a signal image matrix extraction module 101, a model building device 102, and a signal anti-interference processing device 103. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
The signal image matrix extraction module 101 is configured to collect a wind radar signal as a target signal under an interference-free environment condition, apply noise interference to the target signal to obtain an interference signal, perform imaging representation on the interference signal and the target signal, and respectively construct the interference signal and the target signal containing interference information as an image matrix; collecting a wind radar signal to be subjected to anti-interference processing and converting the wind radar signal into a wind radar signal image matrix;
The model construction device 102 is used for constructing an adaptive wind radar interference signal identification model, designing an optimized objective function according to the training set and the constructed adaptive wind radar interference signal identification model, carrying out random optimization solution on the constructed objective function, and constructing the adaptive wind radar interference signal identification model according to the optimal adaptive wind radar interference signal identification model parameters obtained by the optimization solution;
the signal anti-interference processing device 103 is configured to input the wind radar signal image matrix into the generation model, and reconstruct an output result of the generation model into an anti-interference processed wind radar signal.
In detail, the modules in the adaptive wind radar signal anti-interference processing apparatus 100 in the embodiment of the present invention use the same technical means as the adaptive wind radar signal anti-interference processing method described in fig. 1, and can generate the same technical effects, which are not described herein.
Example 3:
fig. 3 is a schematic structural diagram of an electronic device for implementing an adaptive wind radar signal anti-interference processing method according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication interface 13 and a bus, and may further comprise a computer program, such as program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of the program 12, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects respective parts of the entire electronic device using various interfaces and lines, executes or executes programs or modules (a program 12 for implementing adaptive wind radar signal anti-interference processing, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process data.
The communication interface 13 may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device 1 and other electronic devices and to enable connection communication between internal components of the electronic device.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:
collecting a wind radar signal as a target signal under the condition of no interference environment, applying noise interference to the target signal to obtain an interference signal, carrying out imaging representation on the interference signal and the target signal, respectively constructing the interference signal and the target signal containing interference information as an image matrix, and taking the image matrix as a training set;
Constructing a self-adaptive wind radar interference signal identification model;
designing and optimizing an objective function according to the training set and the constructed self-adaptive wind radar interference signal identification model;
carrying out random optimization solution on the constructed objective function to obtain optimal self-adaptive wind radar interference signal identification model parameters;
and constructing a self-adaptive wind radar interference signal identification model according to the optimal self-adaptive wind radar interference signal identification model parameters obtained by optimization solution, collecting wind radar signals to be subjected to anti-interference processing, converting the wind radar signals into a wind radar signal image matrix, inputting the wind radar signal image matrix into a generation model, and reconstructing an output result of the generation model into the wind radar signals subjected to the anti-interference processing.
Specifically, the specific implementation method of the above instructions by the processor 10 may refer to descriptions of related steps in the corresponding embodiments of fig. 1 to 3, which are not repeated herein.
It should be noted that, the foregoing reference numerals of the embodiments of the present invention are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims (6)

1. An adaptive wind radar signal anti-interference processing method, which is characterized by comprising the following steps:
S1: collecting a wind radar signal as a target signal under the condition of no interference environment, applying noise interference to the target signal to obtain an interference signal, carrying out imaging representation on the interference signal and the target signal, respectively constructing the interference signal and the target signal containing interference information as an image matrix, and taking the image matrix as a training set;
s2: constructing a self-adaptive wind radar interference signal identification model;
the self-adaptive wind radar interference signal identification model comprises a generation model G and a discrimination model D;
the generation model takes an image matrix of an interference signal as input, takes an image matrix of an anti-interference processed wind radar signal as output, and the discrimination model takes an image matrix output by the generation model and a target signal image matrix as input, and takes an anti-interference processing effect of the anti-interference processed wind radar signal as output;
the structure of the generated model sequentially comprises a convolution layer, an activation function layer and a deconvolution layer, wherein the number of the convolution layers is 5, the number of the deconvolution layer is 5, an activation function layer is arranged between any two convolution layers, the activation function is a ReLU function, and an interference image matrix sequentially passes through the 5 convolution layers and the 5 deconvolution layers to obtain an image matrix of the wind radar signal after anti-interference treatment; the judging model is a support vector machine model for two classifications, the model output result comprises { -1,1}, which indicates whether the image matrix output by the generating model has interference information or not and whether the target signal image matrix has interference information or not, if the judging model outputs 1, the judging model indicates that the interference information exists, otherwise, the judging model indicates that the interference information does not exist;
S3: designing and optimizing an objective function according to the training set and the constructed self-adaptive wind radar interference signal identification model;
the design optimization objective function according to the training set and the constructed self-adaptive wind radar interference signal identification model comprises the following steps:
according to the constructed self-adaptive wind radar interference signal identification model, an optimization objective function is designed, the independent variable of the optimization objective function is self-adaptive wind radar interference signal identification model parameters, the dependent variable is anti-interference processing effect, and the optimization objective is maximizing the anti-interference processing effect, wherein the self-adaptive wind radar interference signal identification model parameters comprise generation model parameters theta G Discriminating model parameter θ D Generating model parameters theta G The model parameters theta are judged by the weight and offset parameters of the convolution layer and the deconvolution layer D The method comprises the steps of supporting hyperplane parameters of a vector machine model;
the optimization objective function is as follows:
Figure FDA0004057904960000011
wherein:
Figure FDA0004057904960000012
the representation is based on a parameter theta D Is a discriminant model of->
Figure FDA0004057904960000013
1 indicates the presence of interference information, -1 indicates the absence of interference information;
Figure FDA0004057904960000014
the representation is based on a parameter theta G The generated model output result is the image matrix of the wind radar signal after the anti-interference treatment;
I(x k (t)) represents the kth target signal x collected in the training set data k The image matrix of (t),
Figure FDA0004057904960000015
representing the target signal x k (t) corresponding interference signal->
Figure FDA0004057904960000016
Is a matrix of images of (a);
s4: carrying out random optimization solution on the constructed objective function to obtain optimal self-adaptive wind radar interference signal identification model parameters;
s5: and constructing a self-adaptive wind radar interference signal identification model according to the optimal self-adaptive wind radar interference signal identification model parameters obtained by optimization solution, collecting wind radar signals to be subjected to anti-interference processing, converting the wind radar signals into a wind radar signal image matrix, inputting the wind radar signal image matrix into a generation model, and reconstructing an output result of the generation model into the wind radar signals subjected to the anti-interference processing.
2. The method for adaptive wind radar signal anti-interference processing according to claim 1, wherein in the step S1, a wind radar signal is collected as a target signal under a non-interference environment condition, and noise interference is applied to the target signal to obtain an interference signal, and the method comprises the steps of:
the wind-finding radar transmits and collects wind-finding radar signals under the condition of no interference environment, the collected signals are used as target signals, the condition of no interference environment is an air environment without air particles, and the collected target signals are x (t):
Figure FDA0004057904960000017
Wherein:
t represents timing information of a target signal;
a represents the signal amplitude of the target signal;
f represents the frequency of the target signal;
Figure FDA00040579049600000213
representing an initial phase of the target signal;
applying noise interference to the acquired target signal to obtain an interference signal, wherein the applied noise comprises Gaussian white noise n (t) and an analog air particulate noise signal s (t) formed by a plurality of frequency different cosine signals:
Figure FDA0004057904960000021
wherein:
A i the representation frequency is f i N represents the total number of frequencies of the composed analog air particulate noise signal s (t);
the interference signal is expressed as
Figure FDA00040579049600000210
3. The method for anti-interference processing of adaptive wind radar signals according to claim 2, wherein in the step S1, the interference signal and the target signal are represented by imaging, and the interference signal and the target signal containing the interference information are respectively constructed as an image matrix, and the method comprises the steps of:
to interference signals
Figure FDA00040579049600000211
The method comprises the steps of respectively carrying out imaging representation with a target signal x (t), and constructing an interference signal containing interference information and the target signal into an image matrix, wherein the signal imaging representation process comprises the following steps:
s11: to interference signals respectively
Figure FDA00040579049600000212
Sampling with the target signal x (t) with a sampling frequency f c Obtaining an interference signal sampling result with R sampling points and a target signal sampling result, wherein each sampling point signal has M code elements;
s12: the expression of the interference signal sampling result and the target signal sampling result is as follows:
Figure FDA0004057904960000022
Figure FDA0004057904960000023
Figure FDA0004057904960000024
wherein:
x represents the sampling result of the target signal X (t),
Figure FDA0004057904960000025
representing interference signal->
Figure FDA0004057904960000026
Is a sampling result of (a);
j represents an imaginary unit, j 2 ＝-1；
f c Represents the sampling frequency, a mr Signal parameter of mth symbol representing mth sampling point, a mr = { -1,1}, if the mth symbol of the mth sampling point is sampled, a mr =1, otherwise a mr ＝-1；
f represents the frequency of the target signal;
n represents a gaussian white noise matrix;
s represents the sampling result of the analog air particulate noise signal S (t), f i Representing the ith mixing frequency in the simulated air particulate noise signal s (t);
Figure FDA0004057904960000027
representing the real part of the result of the sampling of the target signal,
Figure FDA0004057904960000028
an imaginary part representing a result of the target signal sampling;
s13: sampling result of interference signal
Figure FDA0004057904960000029
And dividing the object signal sampling result X into a real signal and an imaginary signal, the real signal X of the object signal sampling result X re The method comprises the following steps:
Figure FDA0004057904960000031
the imaginary signal X of the target signal sampling result X im The method comprises the following steps:
Figure FDA0004057904960000032
the interference signal sampling result
Figure FDA0004057904960000033
Is>
Figure FDA0004057904960000034
The method comprises the following steps:
Figure FDA0004057904960000035
the interference signal sampling result
Figure FDA0004057904960000036
Is>
Figure FDA0004057904960000037
The method comprises the following steps:
Figure FDA0004057904960000038
s14: the real part and the imaginary part signals of the interference signal sampling result and the target signal sampling result are respectively constructed into an image matrix:
Figure FDA0004057904960000039
Figure FDA00040579049600000310
Figure FDA00040579049600000311
/>
Figure FDA00040579049600000312
wherein:
I(X re ) Real part signal representing the sampling result of the target signal corresponds to the image matrix, I (X im ) An imaginary signal corresponding image matrix representing the sampling result of the target signal; each row in the image matrix represents the same code element, and each point in the same row represents a sampling point of the code element at different moments;
Figure FDA00040579049600000313
real part signal corresponding image matrix representing interference signal sampling result,/->
Figure FDA00040579049600000314
An imaginary signal corresponding image matrix representing the result of the interference signal sampling;
s15: the interference signal
Figure FDA00040579049600000315
The corresponding image matrix is +.>
Figure FDA00040579049600000316
The corresponding image matrix of the target signal x (t) is +.>
Figure FDA00040579049600000317
Repeating the step S1, acquiring K target signals, acquiring K groups of image matrixes to form a training set data,
Figure FDA00040579049600000318
Figure FDA00040579049600000319
wherein I (x) k (t)) represents the kth acquired target signal x k Image matrix of (t),>
Figure FDA00040579049600000320
representing the target signal x k (t) corresponding interference signal->
Figure FDA00040579049600000321
Is a matrix of images of (a).
4. The method for anti-interference processing of adaptive wind radar signals according to claim 1, wherein in the step S4, a random optimization solution is performed on the constructed optimization objective function to obtain optimal adaptive wind radar interference signal recognition model parameters, which comprises the following steps:
Carrying out random optimization solving on the constructed optimization objective function to obtain optimal self-adaptive wind radar interference signal identification model parameters, wherein a dynamic punishment secondary gradient is a main implementation mode of the random optimization method;
the random optimization solving flow of the optimization objective function is as follows:
s41: randomly generating initial model parameters θ D (0),θ G (0) Step sequence (alpha) 1 ,α 2 ,...,α max ) Wherein alpha is max Represents the step length of the max iteration, max represents the maximum iterative optimization frequency of the algorithm for random optimization solution, and the initial model parameter theta is fixed G (0) Setting the current iteration times of the algorithm as d, and setting the initial value of d as 0;
s42: if it is
Figure FDA0004057904960000041
Output theta D (d) For optimal discrimination model parameters->
Figure FDA0004057904960000042
Step S44 is entered, otherwise step S43 is entered, wherein +.>
Figure FDA0004057904960000043
S43: updating to obtain theta D (d+1)：
Figure FDA0004057904960000044
Let d=d+1, return to step S42;
s44: discriminating model parameters in fixed optimization objective function
Figure FDA0004057904960000045
Calculated to make->
Figure FDA0004057904960000046
Is the optimal generator model parameter +.>
Figure FDA0004057904960000047
5. The method for anti-interference processing of adaptive wind radar signals according to claim 4, wherein in the step S5, an adaptive wind radar interference signal recognition model is constructed according to optimal adaptive wind radar interference signal recognition model parameters obtained by optimization solution, and the method comprises the following steps:
Identifying model parameters according to optimal adaptive wind radar interference signals obtained by optimization
Figure FDA0004057904960000048
And +.>
Figure FDA0004057904960000049
And respectively constructing an optimal discriminant model and an optimal generator model.
6. The adaptive wind radar signal anti-interference processing method according to claim 1, wherein in the step S5, the acquired wind radar signal image matrix is input into a generation model, and an output result of the generation model is reconstructed into an anti-interference processed wind radar signal, and the method comprises the steps of:
the method comprises the steps of collecting a wind radar signal to be subjected to anti-interference processing, converting the wind radar signal into a wind radar signal image matrix, inputting the wind radar signal image matrix into a generated model obtained by optimizing and solving, outputting the model into the wind radar signal image matrix subjected to the anti-interference processing, and reconstructing the wind radar signal image matrix subjected to the anti-interference processing into a wind radar signal subjected to the anti-interference processing.
CN202211444742.4A 2022-11-18 2022-11-18 Self-adaptive wind radar signal anti-interference processing method Active CN115494455B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211444742.4A CN115494455B (en) 2022-11-18 2022-11-18 Self-adaptive wind radar signal anti-interference processing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211444742.4A CN115494455B (en) 2022-11-18 2022-11-18 Self-adaptive wind radar signal anti-interference processing method

Publications (2)

Publication Number Publication Date
CN115494455A CN115494455A (en) 2022-12-20
CN115494455B true CN115494455B (en) 2023-05-19

Family

ID=85116203

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211444742.4A Active CN115494455B (en) 2022-11-18 2022-11-18 Self-adaptive wind radar signal anti-interference processing method

Country Status (1)

Country Link
CN (1) CN115494455B (en)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104459668B (en) * 2014-12-03 2017-03-29 西安电子科技大学 radar target identification method based on deep learning network
CN108226892B (en) * 2018-03-27 2021-09-28 天津大学 Deep learning-based radar signal recovery method in complex noise environment
US11836852B2 (en) * 2019-12-20 2023-12-05 Board Of Trustees Of The University Of Illinois Neural network-based millimeter-wave imaging system
CN112731309B (en) * 2021-01-06 2022-09-02 哈尔滨工程大学 Active interference identification method based on bilinear efficient neural network
CN114429156B (en) * 2022-01-21 2023-06-20 西安电子科技大学 Radar interference multi-domain characteristic countermeasure learning and detection recognition method

Also Published As

Publication number Publication date
CN115494455A (en) 2022-12-20

Similar Documents

Publication Publication Date Title
CN112734691B (en) Industrial product defect detection method and device, terminal equipment and storage medium
CN114970705B (en) Running state analysis method, device, equipment and medium based on multi-sensing data
CN113486961A (en) Radar RD image target detection method and system based on deep learning under low signal-to-noise ratio and computer equipment
CN109919862B (en) Radar image denoising system and method and computer equipment
CN113673312B (en) Deep learning-based radar signal intra-pulse modulation identification method
CN116338608B (en) Method, device, equipment and storage medium for adjusting detection angle of microwave radar
CN115795282B (en) Shock tube dynamic pressure reconstruction method and device, electronic equipment and storage medium
CN111353391B (en) Radar interference effect evaluation method and device, electronic equipment and storage medium thereof
CN117388835B (en) Multi-spelling fusion sodar signal enhancement method
CN113567975B (en) Human body rapid security inspection method based on vortex electromagnetic wave mode scanning
CN116934098A (en) Risk quantitative evaluation method for technical trade measures
CN115494455B (en) Self-adaptive wind radar signal anti-interference processing method
CN114722520A (en) Planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning
Van Komen et al. A CNN for range and seabed estimation on normalized and extracted time-series impulses
CN115393251A (en) Defect detection method and device for printed circuit board, storage medium and electronic equipment
CN112966815A (en) Target detection method, system and equipment based on impulse neural network
CN117055726A (en) Micro-motion control method for brain-computer interaction
CN116225070A (en) Environment monitoring method and system based on unmanned aerial vehicle automatic patrol
CN116755005A (en) Model-based method and system for monitoring magnetic field during lightning generation
CN116205918A (en) Multi-mode fusion semiconductor detection method, device and medium based on graph convolution
CN115327553A (en) Rapid laser radar sample generation method for inducing variation
CN112712015B (en) Human body key point identification method and device, intelligent terminal and storage medium
CN118050716B (en) Sodar signal processing method for multi-scale morphological processing
CN113011223A (en) Image recognition method, system, equipment and storage medium
CN116821622B (en) Method and device for analyzing extraction effect of centella asiatica total glycosides based on neural network

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