CN115877377B - Radar networking vector flow field synthesis method, system, equipment and storage medium - Google Patents
Radar networking vector flow field synthesis method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN115877377B CN115877377B CN202211590964.7A CN202211590964A CN115877377B CN 115877377 B CN115877377 B CN 115877377B CN 202211590964 A CN202211590964 A CN 202211590964A CN 115877377 B CN115877377 B CN 115877377B
- Authority
- CN
- China
- Prior art keywords
- radar
- data
- radial
- observation
- flow field
- 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
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application discloses a method, a system, equipment and a storage medium for synthesizing a radar networking vector flow field, wherein the method comprises the following steps: acquiring radar radial data of radar networking; performing fixed-point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data; inputting the ocean observation data and the radar radial data into an untrained radar networking model for training to obtain a radar networking model after training; and acquiring radar observation data to be synthesized, and inputting the radar observation data to be synthesized into the trained radar networking model to obtain a synthesized vector flow field. The embodiment of the application can improve the accuracy of vector flow field synthesis and can be widely applied to the technical field of ground wave radars.
Description
Technical Field
The application relates to the technical field of ground wave radars, in particular to a method, a system, equipment and a storage medium for synthesizing a radar networking vector flow field.
Background
Ocean current is one of the most important kinetic parameters in seawater, and accurate observation of the ocean surface flow field has important significance for production and life of human beings. Compared with the existing fixed-point current meter observation, walking observation and satellite remote sensing observation, the high-frequency ground wave radar has the advantages of all weather, large range, high space-time resolution and the like. Along with the development of the ground wave radar technology, radial flow is gradually observed from a single station to double base station synthesized vector flow, and then networking observation is performed on multiple base stations for the radar observed in the same sea area. In the related art, the ground wave radar networking technology generally uses echo data quality to screen the observations of different radars at the same point, so as to synthesize a vector flow field. However, the method relies on echo data quality selection synthesis, does not consider the physical process of the ocean flow field, and the accuracy of the synthesized vector flow field is low. In view of the foregoing, there is a need for solving the technical problems in the related art.
Disclosure of Invention
In view of this, the embodiment of the application provides a method, a system, a device and a storage medium for synthesizing a radar networking vector flow field, so as to improve the accuracy of synthesizing the flow field.
In one aspect, the application provides a method for synthesizing a radar networking vector flow field, which comprises the following steps:
acquiring radar radial data of radar networking;
performing fixed-point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data;
inputting the ocean observation data and the radar radial data into an untrained radar networking model for training to obtain a radar networking model after training;
and acquiring radar observation data to be synthesized, and inputting the radar observation data to be synthesized into the trained radar networking model to obtain a synthesized vector flow field.
Optionally, the performing fixed point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data includes:
the ocean observation data comprises fixed-point observation data and navigation observation data;
performing fixed point observation processing on the area with overlapped detection ranges in the radar networking to obtain fixed point observation data;
and performing navigation observation processing on the high-precision area and the edge area in the radar networking to obtain navigation observation data.
Optionally, the inputting the ocean observation data and the radar radial data into an untrained radar networking model for training, to obtain a trained radar networking model, includes:
performing data preprocessing on the ocean observation data and the radar radial data to obtain a training data set;
synthesizing radar radial data between every two radars in the training data set to obtain a radar synthesized flow field data set;
inputting the radar synthesis flow field data set into an untrained radar networking model to obtain a trained radar networking model.
Optionally, the performing data preprocessing on the marine observation data and the radar radial data to obtain a training data set includes:
performing space gridding processing on the radar radial data according to an inverse distance weighting algorithm to obtain gridding data;
and carrying out time-by-time average processing on the ocean observation data and the gridding data to obtain a training data set.
Optionally, the synthesizing the radar radial data between every two radars in the training dataset to obtain a radar synthesized flow field dataset includes:
acquiring first radial data and second radial data, wherein the first radial data and the second radial data are radar radial data of any two radars in the training data set respectively;
and calculating to obtain a radar synthetic flow field data set according to the radial speed and the direction angle of the first radial data and the radial speed and the direction angle of the second radial data.
Optionally, inputting the radar synthesis flow field data set into an untrained radar networking model to obtain a trained radar networking model, including:
carrying out standardization processing on the radar synthetic flow field data set to obtain standardized data;
carrying out parameter initialization processing on the untrained radar networking model according to a grid search method to obtain an initialized radar networking model;
and inputting the standardized data into the initialized radar networking model to obtain the trained radar networking model.
Optionally, the inputting the standardized data into the initialized radar networking model to obtain a trained radar networking model includes:
acquiring ocean observation data;
inputting the standardized data into the initialized radar networking model to obtain an output result;
calculating to obtain a model error according to the output result and the ocean observation data;
and updating the radar networking model through a chain rule according to the model error to obtain the radar networking model after training.
On the other hand, the embodiment of the application also provides a radar networking vector flow field synthesis system, which comprises:
the first module is used for acquiring radar radial data of the radar networking;
the second module is used for carrying out fixed-point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data;
the third module is used for inputting the ocean observation data and the radar radial data into an untrained radar networking model for training to obtain a radar networking model after training;
and the fourth module is used for acquiring radar observation data to be synthesized, inputting the radar observation data to be synthesized into the trained radar networking model, and obtaining a synthesized vector flow field.
On the other hand, the embodiment of the application also discloses electronic equipment, which comprises a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
In another aspect, embodiments of the present application also disclose a computer readable storage medium storing a program for execution by a processor to implement a method as described above.
In another aspect, embodiments of the present application also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the foregoing method.
Compared with the prior art, the technical scheme provided by the application has the following technical effects: according to the embodiment of the application, the radar radial data of the radar networking are obtained; performing fixed-point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data; inputting the ocean observation data and the radar radial data into an untrained radar networking model for training to obtain a radar networking model after training; and acquiring radar observation data to be synthesized, and inputting the radar observation data to be synthesized into the trained radar networking model to obtain a synthesized vector flow field. According to the method, the accuracy of the synthesized vector flow field can be improved through the radar networking model obtained through ocean observation data training, and the more accurate radar networking vector flow field can be obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for synthesizing a radar networking vector flow field provided by an embodiment of the application;
fig. 2 is a coverage map of a radar networking provided by an embodiment of the present application;
FIG. 3 is a schematic diagram of the synthesis of radial data for a radar according to an embodiment of the present application;
fig. 4 is a frame diagram of a radar networking model according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. 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 application.
First, several nouns involved in the present application are parsed:
BP neural network: the BP neural network is a multi-layer feedforward network trained according to error back propagation, and comprises an input layer, an implicit layer and an output layer. If the actual output of the forward propagation does not match the desired output, error back propagation is performed, and the weights and biases in the network are adjusted to change the loss function value.
High-frequency ground wave radar: ground wave radar is a main sea detection means. The detection principle is that the characteristics of reduced diffraction propagation attenuation of the surface of the conductive ocean are utilized to emit high-frequency electric waves, so that targets outside 300 km can be detected through the horizon, and the detection precision is higher.
In the related art, the method for synthesizing the vector flow field is generally based on double-base radars, and the vector flow field obtained by synthesizing the radars used in different space points after selecting the radars is synthesized by taking the signal-to-noise ratio of echo signals as a standard for selecting a networking scheme. However, the related vector flow field synthesis method has limited applicability when the Yu Duoji radar is applied, the physical process of the ocean flow field and the constraint of field observation data on a networking scheme are not considered, and the accuracy of the synthesized vector flow field is not high.
In view of this, the embodiment of the application provides a method for synthesizing a radar networking vector flow field, which can be applied to a terminal, a server, software running in the terminal or the server, and the like. The terminal may be, but is not limited to, a tablet computer, a notebook computer, a desktop computer, etc. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligent platforms.
Referring to fig. 1, an embodiment of the present application provides a method for synthesizing a radar networking vector flow field, including:
s101, acquiring radar radial data of radar networking;
s102, performing fixed-point observation and navigation observation processing on a coverage area of the radar networking to obtain ocean observation data;
s103, inputting the ocean observation data and the radar radial data into an untrained radar networking model for training, and obtaining a radar networking model after training;
s104, acquiring radar observation data to be synthesized, and inputting the radar observation data to be synthesized into the trained radar networking model to obtain a synthesized vector flow field.
In the embodiment of the application, the radar radial data and the ocean observation data obtained by the ocean observation technology are input into the radar networking model for training, and the optimal parameters of the combination of the radar data and the ocean information are trained through machine learning, so that the error between the corrected radar echo data and the real ocean information is minimized, the trained radar networking model is obtained, and the more accurate vector flow field is obtained through the synthesis of the trained radar networking model. The radar networking in the embodiment of the application comprises more than two high-frequency ground wave radars, and can be compatible with multiple sets of radars with different frequencies and types.
Further as a preferred embodiment, the performing fixed point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data includes:
the ocean observation data comprises fixed-point observation data and navigation observation data;
performing fixed point observation processing on the area with overlapped detection ranges in the radar networking to obtain fixed point observation data;
and performing navigation observation processing on the high-precision area and the edge area in the radar networking to obtain navigation observation data.
In the embodiment of the application, the obtained ocean observation data can enable the synthesized vector flow field data to be more accurate, the radar networking model is trained by taking the ocean observation data as a target through combining a machine learning method, and the weight parameters of the radar networking model are adjusted by taking the error minimization as an objective function, so that the synthesis result is more accurate. According to the embodiment of the application, the coverage area of the radar networking is subjected to fixed point observation and navigation observation, and the fixed point observation needs to be performed on the area with overlapped detection ranges in the radar networking, so that fixed point observation data are obtained. Referring to fig. 2, fig. 2 is a coverage diagram of a Radar networking provided by an embodiment of the present application, where DGDA represents a Radar coverage of a pole island station, gui represents a Radar coverage of a bay island station, HEQI represents a Radar coverage of a cross-organ station, MWDA represents a Radar coverage of a temple island station, HESD represents a Radar coverage of a cross-organ island station, WSDL represents a Radar coverage of a Wu Shunde station, radar_station represents a Radar station position, ADCP represents an acoustic doppler flow velocity profiler, and path represents a route. The navigation observation needs to pass through a high-precision area and an edge area in the radar networking, wherein the high-precision area refers to an area with an included angle between a connecting line of any two radars being larger than 30 degrees and smaller than 120 degrees or with a data acquisition rate being larger than 80 percent; the edge region refers to the edge position of the coverage area of the radar networking. And obtaining the navigation observation data through a navigation observation technology, and unifying the fixed-point observation data and the navigation observation data into ocean observation data.
Further as a preferred embodiment, the inputting the marine observation data and the radar radial data into an untrained radar networking model for training, to obtain a trained radar networking model, includes:
performing data preprocessing on the ocean observation data and the radar radial data to obtain a training data set;
synthesizing radar radial data between every two radars in the training data set to obtain a radar synthesized flow field data set;
inputting the radar synthesis flow field data set into an untrained radar networking model to obtain a trained radar networking model.
In the embodiment of the application, the marine observation data and the radar radial data are subjected to data preprocessing, and the space-time resolution of the radar radial data and the marine observation data obtained by different radar detection in the radar networking is unified to obtain a training data set. And carrying out pairwise synthesis processing on all radar radial data with uniform resolution in the training data set to obtain a radar synthesis flow field data set. Inputting the radar synthesis flow field data set into an untrained radar networking model for training treatment, and finally obtaining the trained radar networking model. In the embodiment of the application, the radar networking model is constructed by adopting a BP neural network model.
Further as a preferred embodiment, the performing data preprocessing on the marine observation data and the radar radial data to obtain a training data set includes:
performing space gridding processing on the radar radial data according to an inverse distance weighting algorithm to obtain gridding data;
and carrying out time-by-time average processing on the ocean observation data and the gridding data to obtain a training data set.
In the embodiment of the application, radar radial data and ocean observation data are preprocessed, specifically, the radar radial data are gridded in space through an inverse distance weighting algorithm, data in an effective area covered by a radar networking are selected, namely, an area with the data acquisition rate of more than 60% is selected for gridding, the radar radial data coordinates are approximately set as the coordinates of nearest grid points, and the gridding spatial resolution can be determined according to specific requirements, so that gridded data are obtained. And (3) averaging the gridding data and the ocean observation data hour by hour in time, and unifying the gridding data and the ocean observation data into data with 1 hour of resolution to obtain a training data set.
Further as a preferred embodiment, the synthesizing the radar radial data between every two radars in the training dataset to obtain a radar synthesized flow field dataset includes:
acquiring first radial data and second radial data, wherein the first radial data and the second radial data are radar radial data of any two radars in the training data set respectively;
and calculating to obtain a radar synthetic flow field data set according to the radial speed and the direction angle of the first radial data and the radial speed and the direction angle of the second radial data.
In the embodiment of the application, the radar synthetic flow field data set is obtained by synthesizing radar radial data between every two radars in the training data set. The embodiment of the application is based on the principle of vector projection, the radial flow occasion between every two radars is changed into a vector flow field, and the synthesis method is shown in figure 3. In FIG. 3, r v 、r c Radial velocities, θ, respectively observed for two radar sites v 、θ c Vector is the direction angle of the radial velocity, and u and v are components of the vector flow in the weft and warp directions. In the embodiment of the application, radar radial data of any two radars in the training data set are called first radial data and second radial data, and a radar synthetic flow field is obtained by calculation according to the radial speed and the direction angle of the first radial data and the radial speed and the direction angle of the second radial data, so that a radar synthetic flow field data set is obtained by synthesizing all data in the training data set. Wherein, the synthetic calculation formula is as follows:
wherein u represents the weft component of the composite vector, v represents the flow component of the composite vector, r v 、r c Radial velocity, θ, of the first radial data and the second radial data, respectively v 、θ c The radial velocity direction angles of the first radial data and the second radial data, respectively.
Further as a preferred embodiment, the inputting the radar synthesis flow field data set into an untrained radar networking model to obtain a trained radar networking model includes:
carrying out standardization processing on the radar synthetic flow field data set to obtain standardized data;
carrying out parameter initialization processing on the untrained radar networking model according to a grid search method to obtain an initialized radar networking model;
and inputting the standardized data into the initialized radar networking model to obtain the trained radar networking model.
In the embodiment of the application, the radar synthetic flow field data set is input into a machine learning model for training, and the embodiment of the application constructs a radar networking model by using a BP neural network, as shown in fig. 4, and the radar networking model is obtained through training. The embodiment of the application firstly carries out standardization processing on the radar synthetic flow field data set to obtain standardized data, and the standardization method has the following formula:
wherein X is m Representing standardized data, X original Representing data in radar synthetic flow field data set, X min Representing the minimum value, X, in the radar synthetic flow field dataset max Representing the maximum in the radar composite flow field dataset.
According to the embodiment of the application, the untrained radar networking model is subjected to parameter initialization processing by a grid search method, and the used empirical formula is shown as follows:
wherein p, m and n are the numbers of neurons of the hidden layer, the input layer and the output layer respectively, and q is a constant with the size of 1 to 10.
According to the embodiment of the application, an initialized radar networking model is obtained through initialization by a grid search method, standardized data after standardized processing is input into the initialized radar networking model for training, and the radar networking model after training is obtained.
Further as a preferred embodiment, the inputting the standardized data into the initialized radar networking model to obtain a trained radar networking model includes:
acquiring ocean observation data;
inputting the standardized data into the initialized radar networking model to obtain an output result;
calculating to obtain a model error according to the output result and the ocean observation data;
and updating the radar networking model through a chain rule according to the model error to obtain the radar networking model after training.
Further as a preferred embodiment, referring to fig. 4, the normalized data X m And inputting an input layer of the initialized radar networking model, wherein the standardized data are all synthesized flow fields in the radar synthesized flow field data set, and Xmn represents a radar synthesized flow field obtained by synthesizing an mth radar and an nth radar in the radar synthesized flow field data set. The hidden layer in the radar synthesis model is used for calculation, and the output formula of the hidden layer is as follows:
in U j To conceal the output of the jth neuron of the layer, f () is the mapping of the neuron activation function, v ij For the ith input variable X i And jth hidden layer neuron U j Is used for the weight of the (c),is a hidden layer U n Threshold of the j-th neuron.
Inputting the output result of the hidden layer into an output layer Y of the radar networking model, wherein the output formula of the output layer is as follows:
where wj is the weight of the j-th neuron connected with the output layer, Θy is the threshold value of the neuron of the output layer, and y is the output result of the output layer.
According to the embodiment of the application, the error of the output result of the radar networking model and the ocean observation data is calculated through the selected objective function, the weight value of each layer in the radar networking model is updated according to the chain rule, the output value is calculated again, and thus the training is stopped after the repeated training is carried out for the designated times or the convergence of the objective function, and the radar networking model is obtained. The objective Function is measured by using a Loss Function (Loss Function), which is defined on single training data and is used for measuring the prediction error of one training data, specifically determining the Loss value of the training data through the label and the model of the single training data. In actual training, one training data set has a lot of training data, so that a Cost Function (Cost Function) is generally adopted to measure the overall error of the training data set, and the Cost Function is defined on the whole training data set and is used for calculating the average value of the prediction errors of all the training data, so that the prediction effect of the model can be better measured. For a general machine learning model, based on the cost function, a regular term for measuring the complexity of the model can be used as a training objective function, and based on the objective function, the loss value of the whole training data set can be obtained. There are many kinds of common loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., which can be used as the loss function of the machine learning model, and will not be described in detail herein. In the embodiment of the application, one loss function can be selected to determine the loss value of training. Based on the trained loss value, updating the parameters of the model by adopting a back propagation algorithm, and iterating for several rounds to obtain the trained radar networking model. Specifically, the number of iteration rounds may be preset, or training may be considered complete when the test set meets the accuracy requirements. In the embodiment of the application, the radar networking model can be built based on the BP neural network. The radial flow occasion obtained by observing multiple radars is changed into a complete vector flow field through the radar networking model obtained by training, so that the accuracy of vector flow field synthesis can be improved.
On the other hand, the embodiment of the application also provides a radar networking vector flow field synthesis system, which comprises:
the first module is used for acquiring radar radial data of the radar networking;
the second module is used for carrying out fixed-point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data;
the third module is used for inputting the ocean observation data and the radar radial data into an untrained radar networking model for training to obtain a radar networking model after training;
and the fourth module is used for acquiring radar observation data to be synthesized, inputting the radar observation data to be synthesized into the trained radar networking model, and obtaining a synthesized vector flow field.
Corresponding to the method of fig. 1, the embodiment of the application also provides an electronic device, which comprises a processor and a memory; the memory is used for storing programs; the processor executes the program to implement the method as described above.
Corresponding to the method of fig. 1, an embodiment of the present application also provides a computer-readable storage medium storing a program to be executed by a processor to implement the method as described above.
Embodiments of the present application also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the method shown in fig. 1.
In summary, the embodiment of the application has the following advantages: according to the embodiment of the application, by using a machine learning method and combining a synthesis algorithm of the ocean observation data constraint vector ocean current, the error minimization of the ocean observation data and the radar data is used as an objective function, and the radar for synthesizing the vector flow field is selected only by the radar echo data quality, so that the real ocean environment and physical process are fully considered, and the accuracy of vector flow field synthesis is improved.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present application are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the application is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the described functions and/or features may be integrated in a single physical device and/or software module or one or more functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present application. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the application as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the application, which is to be defined in the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
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 more wires, a portable computer diskette (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 application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, 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.
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 application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the application, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present application has been described in detail, the present application is not limited to the embodiments described above, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present application, and these equivalent modifications or substitutions are included in the scope of the present application as defined in the appended claims.
Claims (10)
1. The method for synthesizing the radar networking vector flow field is characterized by comprising the following steps of:
acquiring radar radial data of radar networking;
performing fixed-point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data;
inputting the ocean observation data and the radar radial data into an untrained radar networking model for training to obtain a radar networking model after training;
and acquiring radar observation data to be synthesized, and inputting the radar observation data to be synthesized into the trained radar networking model to obtain a synthesized vector flow field.
2. The method according to claim 1, wherein the performing fixed point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data includes:
the ocean observation data comprises fixed-point observation data and navigation observation data;
performing fixed point observation processing on the area with overlapped detection ranges in the radar networking to obtain fixed point observation data;
and performing navigation observation processing on the high-precision area and the edge area in the radar networking to obtain navigation observation data.
3. The method of claim 1, wherein the inputting the marine observation data and the radar radial data into an untrained radar networking model for training, to obtain a trained radar networking model, comprises:
performing data preprocessing on the ocean observation data and the radar radial data to obtain a training data set;
synthesizing radar radial data between every two radars in the training data set to obtain a radar synthesized flow field data set;
inputting the radar synthesis flow field data set into an untrained radar networking model to obtain a trained radar networking model.
4. A method according to claim 3, wherein said data preprocessing of said marine observations and said radar radial data to obtain a training data set comprises:
performing space gridding processing on the radar radial data according to an inverse distance weighting algorithm to obtain gridding data;
and carrying out time-by-time average processing on the ocean observation data and the gridding data to obtain a training data set.
5. A method according to claim 3, wherein said synthesizing radar radial data between every two radars in said training dataset to obtain a radar synthetic flow field dataset comprises:
acquiring first radial data and second radial data, wherein the first radial data and the second radial data are radar radial data of any two radars in the training data set respectively;
and calculating to obtain a radar synthetic flow field data set according to the radial speed and the direction angle of the first radial data and the radial speed and the direction angle of the second radial data.
6. A method according to claim 3, wherein said inputting the radar synthesis flow field dataset into an untrained radar networking model to obtain a trained radar networking model comprises:
carrying out standardization processing on the radar synthetic flow field data set to obtain standardized data;
carrying out parameter initialization processing on the untrained radar networking model according to a grid search method to obtain an initialized radar networking model;
and inputting the standardized data into the initialized radar networking model to obtain the trained radar networking model.
7. The method of claim 6, wherein inputting the standardized data into the initialized radar networking model to obtain a trained radar networking model comprises:
acquiring ocean observation data;
inputting the standardized data into the initialized radar networking model to obtain an output result;
calculating to obtain a model error according to the output result and the ocean observation data;
and updating the radar networking model through a chain rule according to the model error to obtain the radar networking model after training.
8. A radar networking vector flow field synthesis system, the system comprising:
the first module is used for acquiring radar radial data of the radar networking;
the second module is used for carrying out fixed-point observation and navigation observation processing on the coverage area of the radar networking to obtain ocean observation data;
the third module is used for inputting the ocean observation data and the radar radial data into an untrained radar networking model for training to obtain a radar networking model after training;
and the fourth module is used for acquiring radar observation data to be synthesized, inputting the radar observation data to be synthesized into the trained radar networking model, and obtaining a synthesized vector flow field.
9. An electronic device comprising a memory and a processor;
the memory is used for storing programs;
the processor executing the program implements the method of any one of claims 1 to 7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211590964.7A CN115877377B (en) | 2022-12-12 | 2022-12-12 | Radar networking vector flow field synthesis method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211590964.7A CN115877377B (en) | 2022-12-12 | 2022-12-12 | Radar networking vector flow field synthesis method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115877377A CN115877377A (en) | 2023-03-31 |
| CN115877377B true CN115877377B (en) | 2023-10-03 |
Family
ID=85767073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211590964.7A Active CN115877377B (en) | 2022-12-12 | 2022-12-12 | Radar networking vector flow field synthesis method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115877377B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116626682B (en) * | 2023-05-24 | 2024-01-30 | 无锡智鸿达电子科技有限公司 | Multi-radar networking space profile conversion method, system, medium and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103604944A (en) * | 2013-12-11 | 2014-02-26 | 哈尔滨工业大学 | Surface flow measurement method based on monostation shipborne high-frequency ground wave radar |
| CN113064129A (en) * | 2021-03-03 | 2021-07-02 | 湖北中南鹏力海洋探测系统工程有限公司 | High-frequency ground wave radar ocean current synthesis method |
| CN113466854A (en) * | 2021-06-29 | 2021-10-01 | 哈尔滨工业大学 | High-frequency ground wave radar inversion vector flow velocity method based on ocean power model |
| CN114812710A (en) * | 2022-06-28 | 2022-07-29 | 北京海兰信数据科技股份有限公司 | Vector flow synthesis method and system for radar radial flow |
| CN115204058A (en) * | 2022-08-02 | 2022-10-18 | 南方海洋科学与工程广东省实验室(珠海) | Ground wave radar flow field calculation method and device based on BP neural network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6590523B2 (en) * | 2001-07-26 | 2003-07-08 | Codar Ocean Sensors, Ltd. | Synthesis of total surface current vector maps by fitting normal modes to single-site HF radar data |
| US7690250B2 (en) * | 2007-08-17 | 2010-04-06 | Hickey Kenneth J | Method for measuring surface currents using a long-range single station high frequency ground wave radar system |
-
2022
- 2022-12-12 CN CN202211590964.7A patent/CN115877377B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103604944A (en) * | 2013-12-11 | 2014-02-26 | 哈尔滨工业大学 | Surface flow measurement method based on monostation shipborne high-frequency ground wave radar |
| CN113064129A (en) * | 2021-03-03 | 2021-07-02 | 湖北中南鹏力海洋探测系统工程有限公司 | High-frequency ground wave radar ocean current synthesis method |
| CN113466854A (en) * | 2021-06-29 | 2021-10-01 | 哈尔滨工业大学 | High-frequency ground wave radar inversion vector flow velocity method based on ocean power model |
| CN114812710A (en) * | 2022-06-28 | 2022-07-29 | 北京海兰信数据科技股份有限公司 | Vector flow synthesis method and system for radar radial flow |
| CN115204058A (en) * | 2022-08-02 | 2022-10-18 | 南方海洋科学与工程广东省实验室(珠海) | Ground wave radar flow field calculation method and device based on BP neural network |
Non-Patent Citations (3)
| Title |
|---|
| Cui Wen,et al.Wind Speed Extraction Based on High Frequency Radar Retrieved Wind-Driven Current.《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS》.2020,第1-5页. * |
| zili Li,et al.Detection and analysis of surface currents in western Guangdong by compact surface wave radar.《E3S Web of Conferences 》.2021,第1-5页. * |
| 高频地波雷达海态矢量场反演算法研究;张艳静;《中国优秀硕士学位论文全文数据库 信息科技辑》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115877377A (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pu | Deep SAR imaging and motion compensation | |
| Chen et al. | False-alarm-controllable radar detection for marine target based on multi features fusion via CNNs | |
| US5805098A (en) | Method and system for forming image by backprojection | |
| CN108845325B (en) | Towed line array sonar subarray error mismatch estimation method | |
| Wang et al. | An improved squirrel search algorithm for maximum likelihood DOA estimation and application for MEMS vector hydrophone array | |
| CN115877377B (en) | Radar networking vector flow field synthesis method, system, equipment and storage medium | |
| CN112612006B (en) | Deep learning-based non-uniform clutter suppression method for airborne radar | |
| CN109212466B (en) | Quantum dragonfly evolution mechanism-based broadband direction finding method | |
| CN108614235B (en) | Single-snapshot direction finding method for information interaction of multiple pigeon groups | |
| Whitaker et al. | Recurrent networks for direction-of-arrival identification of an acoustic source in a shallow water channel using a vector sensor | |
| Jin et al. | Semi-supervised underwater acoustic source localization based on residual convolutional autoencoder | |
| Zheng et al. | Zero-shot pipeline detection for sub-bottom profiler data based on imaging principles | |
| Li et al. | Sea/land clutter recognition for over-the-horizon radar via deep CNN | |
| CN100585429C (en) | Passive channel correcting method based on non-linear antenna array | |
| CN112612027B (en) | Ocean internal wave monitoring method utilizing sound energy fluctuation in shallow sea environment | |
| Wang et al. | Passive tracking of underwater acoustic targets based on multi-beam LOFAR and deep learning | |
| CN113126030B (en) | Deep sea direct sound zone target depth estimation method based on broadband sound field interference structure | |
| CN113075633A (en) | Target positioning method based on distance-pitching joint dictionary | |
| Lo | A matched-field processing approach to ranging surface vessels using a single hydrophone and measured replica fields | |
| Wan et al. | A range-Doppler-angle estimation method for passive bistatic radar | |
| Zhu et al. | An unsupervised ocean surface waves suppression algorithm based on sub-aperture SAR images | |
| Odom et al. | Heading and hydrophone data fusion for towed array shape estimation | |
| CN115932838B (en) | Data correction method for ground wave radar and navigation observation based on neural network | |
| CN116310399B (en) | AE-CNN-based high-dimensional feature map target identification method and system | |
| Krinitskiy et al. | Estimating Significant Wave Height from X-Band Navigation Radar Using Convolutional Neural Networks |
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 |