CN114430294B - Method and device for calibrating ground beams of GEO satellite, electronic equipment and storage medium - Google Patents
Method and device for calibrating ground beams of GEO satellite, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114430294B CN114430294B CN202111544788.9A CN202111544788A CN114430294B CN 114430294 B CN114430294 B CN 114430294B CN 202111544788 A CN202111544788 A CN 202111544788A CN 114430294 B CN114430294 B CN 114430294B
- Authority
- CN
- China
- Prior art keywords
- representing
- angle deviation
- deviation
- pitch angle
- predicted
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/1851—Systems using a satellite or space-based relay
- H04B7/18519—Operations control, administration or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Variable-Direction Aerials And Aerial Arrays (AREA)
- Radio Relay Systems (AREA)
Abstract
The application provides a method and a device for calibrating a ground beam of a GEO satellite, electronic equipment and a storage medium. The method comprises the following steps: acquiring a measurement power value of a calibration beam of a satellite; obtaining the pointed pitch angle deviation and azimuth angle deviation of the satellite antenna according to the measured power value; according to the obtained pitch angle deviation and azimuth angle deviation, obtaining predicted pitch angle deviation and predicted azimuth angle deviation at the next moment through a trained deviation prediction model; and transmitting the predicted pitch angle deviation and the predicted azimuth angle deviation to a satellite. For the GEO satellite, through the steps, the pitch angle and the azimuth angle deviation angle at the subsequent moment can be effectively predicted according to the past deviation data under the condition that the GEO satellite pitch angle and azimuth angle deviation prior information model is difficult to obtain. Thereby further aligning the GEO satellite beams and reducing the maximum earth pointing offset.
Description
Technical Field
The present application relates to the field of satellite communications technologies, and in particular, to a method and an apparatus for calibrating a ground beam for a GEO satellite, an electronic device, and a storage medium.
Background
Satellite communication is a key technology of the next generation of information communication systems because it can guarantee large coverage and ultra-high data rate transmission. Among them, GEO satellites are widely used in the fields of communication transmission, television broadcasting, weather forecasting, etc. due to their characteristics of large coverage area, uninterrupted communication throughout the day, etc., and are also important components of global navigation systems. However, the GEO satellite has a problem that, during its operation, the antenna beam is shifted due to the influence of the rotation of the earth or the like, and thus, coverage drift or the like occurs.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method and an apparatus for calibrating GEO satellite to ground beam, an electronic device, and a storage medium.
Based on the above purpose, the present application provides a method for calibrating GEO satellite terrestrial beams, comprising:
acquiring a measurement power value of a satellite calibration beam;
obtaining the pointed pitch angle deviation and azimuth angle deviation of the satellite antenna according to the measured power value;
according to the pitch angle deviation and the azimuth angle deviation, obtaining predicted pitch angle deviation and predicted azimuth angle deviation at the next moment through a trained deviation prediction model;
and transmitting the predicted pitch angle deviation and the predicted azimuth angle deviation to a satellite.
As can be seen from the above, according to the GEO satellite-to-ground beam calibration method and apparatus, the electronic device, and the storage medium provided by the present application, on the basis of obtaining the pitch angle and azimuth angle deviation angle of the satellite antenna beam, the deviation prediction model is used, and under the condition that it is difficult to obtain the GEO satellite pitch angle and azimuth angle deviation prior information model, the pitch angle and azimuth angle deviation angle at the subsequent time are effectively predicted according to the past deviation data. Thereby further aligning the GEO satellite beams and reducing the maximum earth pointing offset.
Drawings
In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for the embodiments or related technologies in the following description are briefly introduced, and it is obvious that the drawings in the following description are only the embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart illustrating a method for calibrating a ground beam for a GEO satellite according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a bias prediction model according to an embodiment of the present application;
FIG. 3 is a schematic diagram of the LSTM model of FIG. 2;
FIG. 4 is a schematic diagram illustrating a training process of a bias prediction model according to an embodiment of the present application;
FIG. 5 is a schematic structural diagram of a device for calibrating a ground beam for a GEO satellite according to the embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to specific embodiments and the accompanying drawings.
It should be noted that technical terms or scientific terms used in the embodiments of the present application should have a general meaning as understood by those having ordinary skill in the art to which the present application belongs, unless otherwise defined. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used only to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
As described in the background art, GEO satellites have a problem of coverage drift or the like due to a phenomenon in which antenna beams are shifted by the influence of the rotation of the earth or the like during the operation thereof. In a beam calibration scheme in the related art, a priori information model is generally established under the condition that the deviation of the pitch angle and the azimuth angle of the GEO satellite presents strong correlation between periodicity and strong correlation, and then calibration is performed.
However, the pitch angle and azimuth angle deviation of the GEO satellite are affected by various factors, and the prior information model is a very complex nonlinear relation and is difficult to model by using a traditional model. Therefore, although the related art can calibrate the beam angle deviation to some extent, the calibrated beam still has large drift.
In view of the above, one or more embodiments of the present application provide a method for calibrating a ground beam of a GEO satellite, where a pre-trained deviation prediction model is used to obtain a predicted deviation value at the next time by using a pitch angle deviation and an azimuth angle deviation, which are obtained by measurement and calculation from a satellite antenna pointing direction at a historical time, so as to calibrate a satellite pointing direction deviation.
The technical solutions of one or more embodiments of the present application are described in detail below with reference to specific embodiments.
Referring to fig. 1, a method for calibrating a ground beam for a GEO satellite according to one or more embodiments of the present application includes the following steps:
step S101: and acquiring the measurement power value of the satellite calibration beam.
In the step, firstly, a measurement power value of a calibration beam of the GEO satellite is obtained through a ground calibration station, and then the deviation of the pitch angle and the azimuth angle of the satellite antenna is predicted based on the measurement power value.
In the process of implementing the present application, the inventors found that although the center boresight of the satellite multi-beam antenna can be maintained to point to a fixed position by controlling the satellite attitude bias control through the ground calibration station, the centers of the beams other than the boresight still move periodically in units of days. Therefore, the pointing deviation of other beams except the visual axis is calculated by measuring the measurement power value of the calibration beam, and the satellite attitude is adjusted according to the deviation.
In particular, as satellite antennasAnd when the central visual axis points to the receiving antenna of the ground calibration station, the measurement power values of the four azimuth calibration beams from east, west, south and north emitted by the satellite are obtained. Wherein, the east beam measurement power value is E 2 The west beam measurement power value is W 2 The south beam measurement power value is S 2 The northbound beam power measurement is N 2 。
Step S102: and obtaining the pointed pitch angle deviation and azimuth angle deviation of the satellite antenna according to the measured power value.
In the step, according to the obtained measurement power values of the calibration beams in the four directions, the pitch angle deviation and the azimuth angle deviation pointed by the satellite antenna are obtained by using a normalized difference pointing error measurement method.
Specifically, the calculation formula of the pointing angle deviation Δ β in the north-south direction corresponding to the pointing direction of the satellite antenna is as follows:
the calculation formula corresponding to the azimuth angle deviation pointed by the satellite antenna corresponding to the east-west direction deviation delta alpha is as follows:
wherein k is NS And k EW To measure the correction factor.
Step S103: and obtaining the predicted pitch angle deviation and the predicted azimuth angle deviation at the next moment through a trained deviation prediction model according to the pitch angle deviation and the azimuth angle deviation.
In this step, the pitch angle deviation and the azimuth angle deviation pointed by the satellite antenna at the current moment of the deviation prediction model are input, and the output predicted pitch angle deviation and the output predicted azimuth angle deviation at the next moment are obtained.
Specifically, the bias prediction model includes an LSTM sub-model and an FNN sub-model. LSTM (Long Short-term memory, long Short-term memory artificial neural network) has strong nonlinear fitting capability and time memory characteristic. Due to the fact that the pitch angle deviation and the azimuth angle deviation pointed by the satellite antenna are influenced by various factors, a priori information model is difficult to obtain. Therefore, the maximum ground surface pointing offset can be further reduced through the LSTM which can better predict and calibrate the pitch angle deviation and the azimuth angle deviation at the next moment. Meanwhile, the LSTM has lower computational complexity and faster inference speed compared to the related art.
And inputting the pitch angle deviation and the azimuth angle deviation at the current moment obtained in the step S102 into a deviation prediction model. The deviation prediction model firstly calls n continuous historical time pitch angle deviations and azimuth angle deviations from the last time, normalization processing is carried out on the pitch angle deviations and the azimuth angle deviations of the current time and the historical time to obtain characteristic values, and the LSTM submodel processes the characteristic values and outputs vectors containing deviation information. And outputting the predicted elevation deviation and azimuth deviation of the next time through the FNN submodel according to the obtained vectors containing deviation information at the current time and the historical time.
In some embodiments, the present embodiment takes the current time as an example, and explains the operation principle of the deviation prediction model, as shown in fig. 2, the model calculation steps are as follows:
firstly, the elevation deviation and the azimuth deviation at the moment t are normalized to obtain a characteristic value x t 。
Then, the characteristic value information x is converted into the characteristic value information t Input into the LSTM submodel. Referring to fig. 3, the diagram of the lstm submodel is as follows:
calculating forgetting door f t ，f t ＝σ(U f x t +W f h t-1 +b f ). Where σ (-) denotes a sigmoid activation function, U f ，W f ，b f The expression is input weight matrix, forgetting gate weight matrix and offset vector. h is t-1 The output value of the LSTM submodel at the last moment.
Calculating external input gate g t ，g t ＝σ(U g x t +W g h t-1 +b g ). Where σ (-) denotes the sigmoid activation function, U g ，W g ，b g The expression is input weight matrix, forgetting gate weight matrix and offset vector.
Computing the internal state c of the LSTM submodel t ，c t ＝f t c t-1 +g t tanh(Ux t +Wh t_1 + b). Wherein tanh (-) represents an activation function, U, W and b respectively represent an input weight matrix, a forgetting gate weight matrix and an offset vector. c. C t-1 Is the internal state of the LSTM submodel at the previous time.
Computation output gate q t ，q t ＝σ(U q x t +W q h t-1 +b q ). Where σ (-) denotes a sigmoid activation function, U q ，W q ，b q The expression is input weight matrix, forgetting gate weight matrix and offset vector.
Calculating the output h of the LSTM submodel at the current moment t ，h t ＝tanh(c t )q t . Where tanh (-) represents the activation function.
The LSTM submodel can obtain a vector containing offset information at time t.
Then, the LSTM submodel outputs a value h t And a historical time output value h t-1+1 、h t-1+2 、…、 h t-1 、h t And input into the FNN submodel together. And obtaining the predicted pitch angle deviation and azimuth angle deviation at the t +1 moment. The calculation formula is as follows:
[Δα′ t+1 ，Δβ′ t+1 ]＝ f FNN ([Δα t ，Δβ t ]，…，[Δα t-l+2 ，Δβ t-l+2 ]，[Δα t-l+1 ，Δβ t-l+1 ])。
in some optional embodiments, the LSTM sub-model and the FNN sub-model are taken as examples in this embodiment, and the training process of the deviation prediction model is described in detail. As shown in fig. 4, the training process of the model includes the following steps:
step S201: and acquiring pitch angle deviation and azimuth angle deviation for training.
Specifically, the ground calibration station obtains pitch angle deviation and azimuth angle deviation of one day according to the frequency of once per minute, and the total number of sampled values is 1440.
Step S202: according to the pitch angle deviation and the azimuth angle deviation, a plurality of training data sets are determined, and a target result corresponding to each data set is determined.
And performing segmentation operation on the 1440 groups of deviation angles, and determining a plurality of training data sets, wherein each training data set comprises 20 continuous historical pitch angle deviations and azimuth angle deviations at historical time and the pitch angle deviations and the azimuth angle deviations serving as input values. And the target result corresponding to each training data set is pitch angle deviation and azimuth angle deviation data at the next moment.
Step S203: and constructing a training set according to the data set for training and the target result.
Step S204: and training a deviation prediction model according to the training set.
And inputting the pitch angle deviation and the azimuth angle deviation of the historical moment and the current moment into a deviation prediction model, comparing and verifying the pitch angle deviation and the azimuth angle deviation of the output predicted next moment and the pitch angle deviation and the azimuth angle deviation of a target result, and adjusting parameters in the deviation prediction model if the deviation value obtained by the deviation prediction model is smaller than a threshold value.
In some embodiments, a test set test bias prediction model may be set up. The construction mode of the test set is consistent with that of the training set. The method has the function of testing whether the deviation prediction model can effectively predict the pitch angle deviation and the azimuth angle deviation at the next moment or not, and retraining the deviation prediction model if the deviation value obtained by the deviation prediction model is smaller than a threshold value.
Step S104: and transmitting the predicted pitch angle deviation and the predicted azimuth angle deviation to a satellite.
In this step, the obtained pitch angle deviation and azimuth deviation predicted value at the next moment are transmitted to the satellite. The satellite system may make beam angle adjustments based on this information.
It should be noted that the method of the embodiment of the present application may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and is completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment, and the multiple devices interact with each other to complete the method.
It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, corresponding to the method of any embodiment, the application also provides a device for calibrating the ground beam of the GEO satellite.
Referring to fig. 5, the device for calibrating a ground beam for a GEO satellite includes:
an acquisition module 11 configured to acquire a measurement power value of a satellite calibration beam;
the measurement module 12 is configured to obtain a pitch angle deviation and an azimuth angle deviation pointed by the satellite antenna through an error measurement model according to the measurement power value;
the prediction module 13 is configured to obtain a predicted pitch angle deviation and a predicted azimuth angle deviation at the next moment through a deep neural network model according to the pitch angle deviation and the azimuth angle deviation;
an output module 14 configured to transmit the predicted pitch angle deviation and the predicted azimuth angle deviation to a satellite.
Wherein, the prediction module 13 comprises:
the LSTM submodule 131 is configured to obtain a vector with predicted value information according to the preprocessed data;
the FNN sub-module 132 is configured to obtain a predicted pitch angle deviation and a predicted azimuth angle deviation at a next time according to the vector.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware implementations as the present application.
The device of the above embodiment is used to implement the corresponding ground beam calibration method for the GEO satellite in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to the method of any embodiment described above, the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the method for calibrating a beam to ground for a GEO satellite according to any embodiment described above is implemented.
Fig. 6 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via a bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present Application.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiment of the present application is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called by the processor 1010 to be executed.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component within the device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and the output devices may include a display, speaker, vibrator, indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (for example, USB, network cable, etc.), and can also realize communication in a wireless mode (for example, mobile network, WIFI, bluetooth, etc.).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may also include only those components necessary to implement the embodiments of the present application, and not necessarily all of the components shown in the figures.
The electronic device of the foregoing embodiment is used to implement the corresponding ground beam calibration method for the GEO satellite in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to any of the above-described embodiment methods, the present application further provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method for calibrating a beam to ground for a GEO satellite according to any of the above embodiments.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, for storing information may be implemented in any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method for calibrating a ground beam for a GEO satellite according to any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which are not described herein again.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the context of the present application, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the embodiments of the application. Further, devices may be shown in block diagram form in order to avoid obscuring embodiments of the application, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the embodiments of the application are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that the embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures, such as Dynamic RAM (DRAM), may use the discussed embodiments.
The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present application are intended to be included within the scope of the present application.
Claims (8)
1. A method for calibrating a ground beam for a GEO satellite, comprising:
acquiring a measurement power value of a satellite calibration beam;
obtaining the pointed pitch angle deviation and azimuth angle deviation of the satellite antenna according to the measured power value;
obtaining a characteristic value through normalization processing according to the pitch angle deviation and the azimuth angle deviation;
obtaining a feature vector with predicted value information through an LSTM model according to the feature value;
obtaining the predicted pitch angle deviation and the predicted azimuth angle deviation at the next moment through an FNN model according to the feature vector;
transmitting the predicted pitch angle deviation and the predicted azimuth angle deviation to a satellite;
obtaining a feature vector with predicted value information through an LSTM model according to the feature value, wherein the obtaining of the feature vector with the predicted value information comprises the following steps:
the forgetting matrix is calculated by the following formula:
f t =σ(U f x t +W f h t-1 +b f )
wherein, U f Representing a predetermined first input weight matrix, x t Represents the characteristic value, W f Representing a predetermined first forgetting-gate weight matrix, h t-1 Representing the output value of the last-time LSTM submodel, b f Representing a predetermined first offset vector, σ (U) f x t +W f h t-1 +b f ) Represents a pair of U f x t +W f h t-1 +b f Is activated by a sigmoid activation function, f t Representing the forgetting matrix;
the input matrix is calculated by the following formula:
g t =σ(U g x t +W g h t-1 +b g )
wherein, U g Representing a predetermined second input weight matrix, x t Represents the characteristic value, W g Representing a predetermined second forgetting gate weight matrix, h t-1 Representing the output value of the last-time LSTM submodel, b g Representing a predetermined second offset vector, σ (U) g x t +W g h t-1 +b g ) Represents to U g x t +W g h t-1 +b g Is activated by a sigmoid activation function, g t Representing the input matrix;
the internal state matrix is calculated by the following formula:
c t =f t c t-1 +g t tanh(Ux t +Wh t-1 +b)
wherein, f t Representing said forgetting matrix, c t-1 Said internal state matrix, g, representing the last moment in time t Representing said input matrix, U representing a predetermined third input weight matrix, x t Representing said characteristic value, W representing a predetermined third forgetting gate weight matrix, h t-1 Indicating the output value of the last time LSTM submodel, b indicating a predetermined second timeThree offset vectors, tanh (Ux) t +Wh t-1 + b) denotes the pair Ux t +Wh t-1 The result of + b is activated by the tanh activation function, c t Representing the internal state matrix;
calculating an output value by the following formula:
q t =σ(U q x t +W q h t-1 +b q )
wherein, U q Representing a predetermined fourth input weight matrix, x t Represents the characteristic value, W q Representing a predetermined fourth forgetting-gate weight matrix, h t-1 Representing said output value at the previous moment, b q Representing a predetermined fourth offset vector, σ (U) q x t +W q h t-1 +b q ) Represents U q x t +W q h t-1 +b q The result of (a) is activated by a sigmoid activation function, q t Representing the output value;
calculating the feature vector by the following formula:
h t =tanh(c t )q t
wherein, c t Representing said internal state matrix, q t Represents the output value, tanh (c) t ) Represent pair c t Activation by sigmoid activation function, h t Representing the feature vector;
obtaining the predicted pitch angle deviation and the predicted azimuth angle deviation at the next moment through the FNN model according to the feature vectors, wherein the method comprises the following steps:
obtaining the pitch angle deviation and the azimuth angle deviation at the current moment according to the feature vector;
obtaining the predicted pitch angle deviation and the predicted azimuth angle deviation at the next moment by the following calculation formulas:
[Δα ’ t+1 ，Δβ ’ t+1 ]=f FNN ([Δα ’ t ，Δβ ’ t ],[Δα ’ t-1 ，Δβ ’ t-1 ],…,[Δα ’ t-l+2 ，Δβ ’ t-l+2 ],[Δα ’ t-l+1 ，Δβ ’ t-l+1 ])
wherein, delta alpha ’ t Representing said pitch angle deviation, Δ α, at the current moment ’ t-1 ,…,Δα ’ t-l+2 ,Δα ’ t-l+1 Representing said pitch angle deviation, Δ β, at a historical moment ’ t Represents said azimuth deviation, Δ β, at the current time ’ t-1 ,…,Δβ ’ t-l+2 ,Δβ ’ t-l+1 Representing said azimuth deviation at historical time, f FNN ([Δα ’ t ，Δβ ’ t ],[Δα ’ t-1 ，Δβ ’ t-1 ],…,[Δα ’ t-l+2 ，Δβ ’ t-l+2 ],[Δα ’ t-l+1 ，Δβ ’ t-l+1 ]) Represents the calculation of said pitch and azimuth deviations at the current and historical times by means of a FNN model, delta alpha ’ t+1 Representing said predicted pitch angle deviation, Δ β, at the next moment in time ’ t+1 Representing the predicted azimuth deviation at the next time instant.
2. The method for calibrating a ground beam for a GEO satellite of claim 1, wherein the obtaining of the measurement power value of the satellite calibration beam includes:
and acquiring measurement power values of east, west, south and north calibration beams transmitted by the satellite in response to the fact that the central visual axis of the satellite antenna points to the receiving antenna of the ground calibration station.
3. The method for calibrating a ground beam for a GEO satellite according to claim 1, wherein the obtaining of the pitch angle deviation and the azimuth angle deviation of the satellite antenna pointing direction according to the measurement power value includes:
obtaining the pitch angle deviation and the azimuth angle deviation pointed by the satellite antenna by utilizing a normalized differential pointing error measurement method according to the measurement power value;
the pitch angle deviation is the north-south pointing deviation of the satellite antenna; the azimuth deviation is the satellite antenna east-west pointing deviation.
4. The method for calibrating a ground beam for a GEO satellite of claim 1, wherein the training process of the deep neural network model includes:
acquiring pitch angle deviation and azimuth angle deviation data pointed by a training satellite antenna;
determining a plurality of data sets for training according to the pitch angle deviation and the azimuth angle deviation data, and determining a target result corresponding to each data set;
constructing a training set according to the data set for training and the target result;
and training a deviation prediction model according to the training set.
5. The method for calibrating a ground beam for a GEO satellite of claim 4, wherein the training a bias prediction model from the training set comprises:
and verifying the predicted pitch angle deviation and the predicted azimuth angle deviation based on the target result, and if the accuracy of the predicted pitch angle deviation and the predicted azimuth angle deviation is smaller than a threshold value, retraining the deep neural network model.
6. A device for calibrating a beam to ground for a GEO satellite, comprising:
an acquisition module configured to acquire a measurement power value of a satellite calibration beam;
the measurement module is configured to obtain a pitch angle deviation and an azimuth angle deviation pointed by the satellite antenna according to the measurement power value;
the preprocessing module is configured to obtain a characteristic value through normalization processing according to the pitch angle deviation and the azimuth angle deviation;
the LSTM neural network module is configured to obtain a feature vector with predicted value information through an LSTM model according to the feature value;
the FNN neural network module is configured to obtain predicted pitch angle deviation and predicted azimuth angle deviation at the next moment through an FNN model according to the feature vectors;
a transmission module configured to transmit the predicted pitch angle deviation and predicted azimuth angle deviation to a satellite;
wherein the LSTM neural network module is configured to:
the forgetting matrix is calculated by the following formula:
f t =σ(U f x t +W f h t-1 +b f )
wherein, U f Representing a predetermined first input weight matrix, x t Represents the characteristic value, W f Representing a predetermined first forgetting-gate weight matrix, h t-1 Represents the output value of the last time LSTM submodel, b f Representing a predetermined first offset vector, σ (U) f x t +W f h t-1 +b f ) Represents to U f x t +W f h t-1 +b f Is activated by a sigmoid activation function, f t Representing the forgetting matrix;
the input matrix is calculated by the following formula:
g t =σ(U g x t +W g h t-1 +b g )
wherein, U g Representing a predetermined second input weight matrix, x t Represents the characteristic value, W g Representing a predetermined second forgetting-gate weight matrix, h t-1 Representing the output value of the last-time LSTM submodel, b g Representing a predetermined second offset vector, σ (U) g x t +W g h t-1 +b g ) Represents a pair of U g x t +W g h t-1 +b g Is activated by a sigmoid activation function, g t Representing the input matrix;
the internal state matrix is calculated by the following formula:
c t =f t c t-1 +g t tanh(Ux t +Wh t-1 +b)
wherein f is t Representing said forgetting matrix, c t-1 Said internal state matrix, g, representing the last moment in time t Representing said input matrix, U representing a predetermined third input weight matrix, x t Representing said characteristic value, W representing a predetermined third forgetting gate weight matrix, h t-1 Represents the output value of the last time LSTM submodel, b represents a predetermined third offset vector, tanh (Ux) t +Wh t-1 + b) denotes the pair Ux t +Wh t-1 The result of + b is activated by the tanh activation function, c t Representing the internal state matrix;
the output value is calculated by the following formula:
q t =σ(U q x t +W q h t-1 +b q )
wherein, U q Representing a predetermined fourth input weight matrix, x t Represents the characteristic value, W q Representing a predetermined fourth forgetting-gate weight matrix, h t-1 Representing said output value at the previous moment, b q Representing a predetermined fourth offset vector, σ (U) q x t +W q h t-1 +b q ) Represents that U is q x t +W q h t-1 +b q The result of (a) is activated by a sigmoid activation function, q t Representing the output value;
calculating the feature vector by the following formula:
h t =tanh(c t )q t
wherein, c t Representing said internal state matrix, q t Represents said output value, tanh (c) t ) Represents a pair c t Activation by sigmoid activation function, h t Representing the feature vector;
wherein the FNN neural network module is configured to:
obtaining the pitch angle deviation and the azimuth angle deviation at the current moment according to the feature vector;
obtaining the predicted pitch angle deviation and the predicted azimuth angle deviation at the next moment by the following calculation formulas:
[Δα ’ t+1 ，Δβ ’ t+1 ]=f FNN ([Δα ’ t ，Δβ ’ t ],[Δα ’ t-1 ，Δβ ’ t-1 ],…,[Δα ’ t-l+2 ，Δβ ’ t-l+2 ],[Δα ’ t-l+1 ，Δβ ’ t-l+1 ])
wherein, delta alpha ’ t Representing said pitch angle deviation, Δ α, at the current time ’ t-1 ,…,Δα ’ t-l+2 ,Δα ’ t-l+1 Representing said pitch angle deviation, Δ β, at a historical moment ’ t Represents said azimuth deviation, Δ β, of the current time instant ’ t-1 ,…,Δβ ’ t-l+2 ,Δβ ’ t-l+1 Representing said azimuth deviation at historical time, f FNN ([Δα ’ t ，Δβ ’ t ],[Δα ’ t-1 ，Δβ ’ t-1 ],…,[Δα ’ t-l+2 ，Δβ ’ t-l+2 ],[Δα ’ t-l+1 ，Δβ ’ t-l+1 ]) Represents the calculation of the pitch angle deviation and the azimuth angle deviation at the current time and the historical time by a FNN model, delta alpha ’ t+1 Representing said predicted pitch angle deviation, Δ β, at the next moment in time ’ t+1 Representing the predicted azimuth deviation at the next time instant.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 5 when executing the program.
8. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111544788.9A CN114430294B (en) | 2021-12-16 | 2021-12-16 | Method and device for calibrating ground beams of GEO satellite, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111544788.9A CN114430294B (en) | 2021-12-16 | 2021-12-16 | Method and device for calibrating ground beams of GEO satellite, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114430294A CN114430294A (en) | 2022-05-03 |
| CN114430294B true CN114430294B (en) | 2022-12-13 |
Family
ID=81311402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111544788.9A Active CN114430294B (en) | 2021-12-16 | 2021-12-16 | Method and device for calibrating ground beams of GEO satellite, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114430294B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114879227B (en) * | 2022-05-05 | 2023-03-10 | 中国电子科技集团公司第五十四研究所 | Satellite multi-beam antenna pointing high-precision measurement method |
| CN114944878B (en) * | 2022-05-16 | 2024-02-13 | 中国人民解放军32039部队 | Combined calibration method and device for mobile communication satellite and electronic equipment |
| CN117094371A (en) * | 2023-10-17 | 2023-11-21 | 北京航天驭星科技有限公司 | Training method, calibration system and parameter generation method for antenna pointing calibration model |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110737948A (en) * | 2019-10-15 | 2020-01-31 | 南京航空航天大学 | method for predicting residual life of aero-engine based on deep FNN-LSTM hybrid network |
| EP3712651A1 (en) * | 2019-03-21 | 2020-09-23 | Koninklijke Philips N.V. | Method and system for adaptive beamforming of ultrasound signals |
| CN112013833A (en) * | 2020-07-23 | 2020-12-01 | 中国人民解放军战略支援部队信息工程大学 | VICTS antenna satellite-to-satellite tracking method based on deep neural network |
| CN112193439A (en) * | 2020-10-08 | 2021-01-08 | 军事科学院系统工程研究院网络信息研究所 | Satellite-ground integrated high-precision satellite multi-beam calibration method |
| WO2021068194A1 (en) * | 2019-10-11 | 2021-04-15 | 深圳信息职业技术学院 | Training method and apparatus for antenna signal processing model, and antenna and storage medium |
| WO2021246546A1 (en) * | 2020-06-03 | 2021-12-09 | 엘지전자 주식회사 | Intelligent beam prediction method |
-
2021
- 2021-12-16 CN CN202111544788.9A patent/CN114430294B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3712651A1 (en) * | 2019-03-21 | 2020-09-23 | Koninklijke Philips N.V. | Method and system for adaptive beamforming of ultrasound signals |
| WO2021068194A1 (en) * | 2019-10-11 | 2021-04-15 | 深圳信息职业技术学院 | Training method and apparatus for antenna signal processing model, and antenna and storage medium |
| CN110737948A (en) * | 2019-10-15 | 2020-01-31 | 南京航空航天大学 | method for predicting residual life of aero-engine based on deep FNN-LSTM hybrid network |
| WO2021246546A1 (en) * | 2020-06-03 | 2021-12-09 | 엘지전자 주식회사 | Intelligent beam prediction method |
| CN112013833A (en) * | 2020-07-23 | 2020-12-01 | 中国人民解放军战略支援部队信息工程大学 | VICTS antenna satellite-to-satellite tracking method based on deep neural network |
| CN112193439A (en) * | 2020-10-08 | 2021-01-08 | 军事科学院系统工程研究院网络信息研究所 | Satellite-ground integrated high-precision satellite multi-beam calibration method |
Non-Patent Citations (6)
| Title |
|---|
| Deep Learning Assisted Calibrated Beam Training for Millimeter-Wave Communication Systems;Ke Ma 等;《IEEE Transactions on Communications》;20210721;第69卷(第10期);第6706-6721页 * |
| FC-BET: A Fast Consecutive Beam Tracking Scheme for MmWave Vehicular Communications;Chen Wang 等;《2021 IEEE Wireless Communications and Networking Conference (WCNC)》;20210505;第1-6页 * |
| Modeling and Calibrating the Ground-Surface Beam Pointing of GEO Satellite;Chenhua Sun等;《IEEE Access》;20190729;第121897-121906页 * |
| Recurrent Neural Network Based Beam Prediction for Millimeter-Wave 5G Systems;Shubham Khunteta 等;《2021 IEEE Wireless Communications and Networking Conference (WCNC)》;20210505;第1-6页 * |
| 一种用于卫导站间卫星通信的天线跟踪与自校准方法;熊帅 等;《现代导航》;20160430(第02期);第113-116页 * |
| 星载多波束天线校正技术研究;朱丽;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20080515;第26-47页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114430294A (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114430294B (en) | Method and device for calibrating ground beams of GEO satellite, electronic equipment and storage medium | |
| CN109163721B (en) | Attitude measurement method and terminal equipment | |
| CN111045046B (en) | Short-term ionosphere forecasting method and device based on NARX | |
| Chang et al. | Strapdown inertial navigation system alignment based on marginalised unscented Kalman filter | |
| CN112577521B (en) | Combined navigation error calibration method and electronic equipment | |
| TR201801964A2 (en) | ||
| JP2016114603A (en) | Method and system for processing gps drifting | |
| US11573329B2 (en) | Modeling effects of structures on global-positioning system localization | |
| CN114528978A (en) | Ionized layer TEC prediction method, ionized layer TEC prediction device, ionized layer TEC prediction equipment and storage medium | |
| CN114779297A (en) | Terminal positioning method and related device | |
| US11139569B2 (en) | Antenna system, method and computer program product, with real time axial ratio polarization correction | |
| CN113532428A (en) | Data processing method and device, communication-in-motion terminal and computer readable storage medium | |
| RU137394U1 (en) | DEVICE FOR PROCESSING INFORMATION OF NETWORK DISTANCED IN THE SPACE OF PELENGATION POST | |
| CN114399587B (en) | Three-dimensional lane line generation method and device, electronic device and computer readable medium | |
| CN110445557A (en) | Deep space TT&C interferometry large aperture antenna is directed toward Calibration Method and device | |
| US11977175B2 (en) | Method and apparatus for estimating position of signal source | |
| CN115685202A (en) | Baseline estimation method and device of space-borne distributed interferometric synthetic aperture radar | |
| CN114501615A (en) | Terminal positioning method, device, computer equipment, storage medium and program product | |
| CN110207699B (en) | Positioning method and device | |
| CN115817163B (en) | Method, apparatus, electronic device and computer readable medium for adjusting wheel speed of vehicle | |
| US20240046146A1 (en) | Method for teaching an electronic computing device, a computer program product, a computer-readable storage medium as well as an electronic computing device | |
| CN113137975B (en) | Inertial correction method and device for astronomical inertial integrated navigation and electronic equipment | |
| CN117146802B (en) | Base posture measurement method and device and satellite communication terminal | |
| CN115829879B (en) | Attitude quaternion processing method, device and equipment for agile satellite | |
| CN116886178B (en) | Track forecast correction method and device |
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 |