A method, device and equipment for predicting the orbital state of low-earth orbit satellites

Abstract

The present application discloses a method, device and equipment for predicting the orbital state of a low-earth orbit satellite. The method includes: defining a pseudo-drag coefficient according to the atmospheric drag perturbation formula; performing a decomposition operation on the space environment parameters based on the correlation analysis of the pseudo-drag coefficient according to the VMD algorithm to obtain space environment characteristic parameters, where the space environment parameters include the solar radiation flux index and the geomagnetic index; using the space environment characteristic parameters and a preset equivalent drag coefficient to perform pseudo-drag coefficient prediction training on an initial SVM model to obtain an optimized SVM model; predicting the pseudo-drag coefficient at a future moment through the optimized SVM model to obtain a pseudo-drag prediction value; and performing a prediction calculation on the orbital state of the low-earth orbit satellite according to the pseudo-drag prediction value to obtain a state prediction result. The present application can solve the technical problem in the prior art that it is difficult to ensure the influence degree of the change of the space environment, resulting in poor accuracy of the orbital state prediction of the low-earth orbit satellite.

Description

Technical Field

[0001] The present application relates to the field of satellite technology, and in particular, to a method, device and equipment for predicting the orbital state of low-earth orbit satellites. Background Art

[0002] In the context of the rapid development of space technology, more and more satellites are deployed into orbits. Precise and efficient orbit prediction has become particularly crucial, which not only supports rendezvous analysis and collision avoidance, but is also vital for the safe operation of space targets. The current orbit prediction method for space targets is based on the framework of orbit determination and prediction. In the orbit determination process, observational data is used to obtain accurate historical orbit data and estimate relevant parameters. However, in the orbit prediction stage, observational data is unavailable, and the same physical model as that in the orbit determination process and the estimated atmospheric drag coefficient must be used to achieve orbit prediction. For low-earth orbit satellites, although conservative forces (including the earth's gravity and third-body perturbation) can be modeled with good accuracy, non-conservative perturbations (i.e., atmospheric drag) may have higher uncertainties, manifested as the complexity and inaccuracy of atmospheric density modeling and space environment prediction.

[0003] In traditional methods, the accuracy of orbit prediction depends on the prediction accuracy of the space environment during the prediction time period, and the accurate prediction of the space environment remains a difficult problem; although it has little impact in short-term orbit prediction or when the space environment is stable. However, in the case of medium- and long-term orbit prediction or when the space environment changes significantly, it is difficult to accurately estimate the atmospheric density, and at the same time, it will cause the value of the atmospheric drag coefficient solved in the orbit determination stage to be unable to adapt to the error absorption in the prediction stage, resulting in a rapid decline in the prediction accuracy and a rapid increase in errors. Summary of the Invention

[0004] The present application provides a method, device and equipment for predicting the orbital state of low-earth orbit satellites, which are used to solve the technical problem that it is difficult to ensure the influence degree of space environment changes in the prior art, resulting in poor accuracy of the orbital state prediction of low-earth orbit satellites.

[0005] In view of this, the first aspect of the present application provides a method for predicting the orbital state of low-earth orbit satellites, including:

[0006] Defining a pseudo-drag coefficient according to the atmospheric drag perturbation formula;

[0007] Performing a decomposition operation on the space environment parameters based on the correlation analysis of the pseudo-drag coefficient according to the VMD algorithm to obtain space environment characteristic parameters, where the space environment parameters include solar radiation flux index and geomagnetic index;

[0008] Using the space environment characteristic parameters and a preset equivalent drag coefficient to perform pseudo-drag coefficient prediction training on an initial SVM model to obtain an optimized SVM model;

[0009] Predict the pseudo drag coefficient at a future moment through the optimized SVM model to obtain a pseudo drag prediction value;

[0010] Predict and calculate the orbital state of the low-earth orbit satellite based on the pseudo drag prediction value to obtain a state prediction result.

[0011] Preferably, the decomposition operation of the space environment parameters based on the correlation analysis of the pseudo drag coefficient is performed according to the VMD algorithm to obtain space environment characteristic parameters, including:

[0012] Normalize the solar radiation flux index and the geomagnetic index respectively and then merge them to obtain a space environment processing parameter;

[0013] Perform a decomposition operation of the space environment processing parameter based on the correlation analysis of the pseudo drag coefficient by using the VMD algorithm to obtain space environment characteristic parameters.

[0014] Preferably, the training of the initial SVM model for pseudo drag coefficient prediction by using the space environment characteristic parameters and the preset equivalent drag coefficient to obtain an optimized SVM model includes:

[0015] Concatenate the space environment characteristic parameters and the preset equivalent drag coefficient into an input feature vector, use the historical value of the pseudo drag as the target variable, and generate a training set;

[0016] Use a preset optimization algorithm and the training set to perform coefficient prediction training on the initial SVM model to obtain an optimized SVM model.

[0017] Preferably, before the training of the initial SVM model for pseudo drag coefficient prediction by using the space environment characteristic parameters and the preset equivalent drag coefficient to obtain an optimized SVM model, it further includes:

[0018] Predict the orbital state of the low-earth orbit satellite by using numerical integration to obtain a predicted ephemeris;

[0019] Calculate the traditional prediction error based on the orbit dynamics model and the predicted ephemeris;

[0020] Perform iterative optimization analysis according to the traditional prediction error through the golden section search algorithm to obtain a preset equivalent drag coefficient.

[0021] Preferably, the prediction and calculation of the orbital state of the low-earth orbit satellite based on the pseudo drag prediction value to obtain a state prediction result includes:

[0022] Calculate the atmospheric drag perturbation value based on the pseudo drag prediction value;

[0023] Substitute the atmospheric drag perturbation value into the formula of the orbit dynamics model to predict and calculate the orbital state of the low-earth orbit satellite to obtain a state prediction result.

[0024] The second aspect of this application provides a low-earth orbit satellite orbit state prediction device, including:

[0025] A coefficient definition unit for defining a pseudo-drag coefficient according to the atmospheric drag perturbation formula;

[0026] An association decomposition unit for performing a decomposition operation on space environment parameters based on the correlation analysis of the pseudo-drag coefficient according to the VMD algorithm to obtain space environment characteristic parameters, where the space environment parameters include solar radiation flux index and geomagnetic index;

[0027] A model training unit for performing pseudo-drag coefficient prediction training on an initial SVM model using the space environment characteristic parameters and a preset equivalent drag coefficient to obtain an optimized SVM model;

[0028] A coefficient prediction unit for predicting the pseudo-drag coefficient at a future moment through the optimized SVM model to obtain a pseudo-drag prediction value;

[0029] An orbit prediction unit for performing prediction calculations on the low-earth orbit satellite orbit state based on the pseudo-drag prediction value to obtain a state prediction result.

[0030] Preferably, the association decomposition unit is specifically used for:

[0031] Normalize the solar radiation flux index and the geomagnetic index respectively and then merge them to obtain space environment processing parameters;

[0032] Perform a decomposition operation on the space environment processing parameters based on the correlation analysis of the pseudo-drag coefficient using the VMD algorithm to obtain space environment characteristic parameters.

[0033] Preferably, the model training unit is specifically used for:

[0034] Concatenate the space environment characteristic parameters and the preset equivalent drag coefficient into an input feature vector, use the pseudo-drag historical value as the target variable, and generate a training set;

[0035] Perform coefficient prediction training on the initial SVM model using a preset optimization algorithm and the training set to obtain an optimized SVM model.

[0036] Preferably, it further includes:

[0037] A traditional prediction unit for predicting the low-earth orbit satellite orbit state by means of numerical integration to obtain a predicted ephemeris;

[0038] An error calculation unit for calculating the traditional prediction error based on the orbit dynamics model and the predicted ephemeris;

[0039] An optimization calculation unit is used to perform iterative optimization analysis based on the traditional prediction error through the golden section search algorithm to obtain a preset equivalent drag coefficient.

[0040] In the third aspect of the present application, a low-orbit satellite orbit state prediction device is provided. The device includes a processor and a memory.

[0041] The memory is used to store program codes and transmit the program codes to the processor.

[0042] The processor is used to execute the low-orbit satellite orbit state prediction method described in the first aspect according to the instructions in the program codes.

[0043] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0044] In the present application, a low-orbit satellite orbit state prediction method is provided, including: defining a pseudo drag coefficient according to the atmospheric drag perturbation formula; performing a decomposition operation on the space environment parameters based on the correlation analysis of the pseudo drag coefficient according to the VMD algorithm to obtain space environment characteristic parameters, where the space environment parameters include the solar radiation flux index and the geomagnetic index; using the space environment characteristic parameters and the preset equivalent drag coefficient to perform pseudo drag coefficient prediction training on the initial SVM model to obtain an optimized SVM model; predicting the pseudo drag coefficient at a future moment through the optimized SVM model to obtain a pseudo drag prediction value; and performing prediction calculation on the low-orbit satellite orbit state according to the pseudo drag prediction value to obtain a state prediction result.

[0045] The low-orbit satellite orbit state prediction method provided by the present application defines the concept of the pseudo drag coefficient, associates the space environment parameters with the pseudo drag coefficient through the VMD algorithm, and transforms the low-orbit satellite orbit state prediction problem into a pseudo drag coefficient prediction problem; and on this basis, a pseudo drag coefficient prediction model is constructed, which can ensure obtaining an accurate pseudo drag coefficient considering the changes in the space environment, and further ensure the accuracy and reliability of the low-orbit satellite orbit state prediction result based on this; this process specifically analyzes the quantitative impact of the space environment changes on the pseudo drag coefficient, which is more in line with the actual situation and can meet the current technical requirements of low-orbit satellite orbit prediction. Therefore, the present application can solve the technical problem that it is difficult to ensure the influence degree of the space environment changes in the prior art, resulting in poor accuracy of the low-orbit satellite orbit state prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic flow chart of a low-orbit satellite orbit state prediction method provided by an embodiment of the present application;

[0047] Figure 2 It is a schematic structural diagram of a low-orbit satellite orbit state prediction device provided by an embodiment of the present application;

[0048] Figure 3 Schematic diagram of the normalized correlation analysis between the space environment parameters and the pseudo-drag coefficient provided by the embodiment of the present application;

[0049] Figure 4 Schematic diagram of the solution process of the space environment characteristic parameters based on the VMD algorithm provided by the embodiment of the present application;

[0050] Figure 5 Curve graph of the correlation relationship between the space environment characteristic parameters and the pseudo-drag coefficient provided by the embodiment of the present application;

[0051] Figure 6 Schematic diagram of the comparison of the radial errors of the low-earth orbit satellite orbit prediction based on three different methods provided by the embodiment of the present application;

[0052] Figure 7 Schematic diagram of the comparison of the along-track errors of the low-earth orbit satellite orbit prediction based on three different methods provided by the embodiment of the present application;

[0053] Figure 8 Schematic diagram of the comparison of the cross-track errors of the low-earth orbit satellite orbit prediction based on three different methods provided by the embodiment of the present application;

[0054] Figure 9 Schematic diagram of the comparison of the radial prediction errors between the solution provided by the present application and the traditional prediction solution provided by the application example of the present application;

[0055] Figure 10 Schematic diagram of the comparison of the along-track prediction errors between the solution provided by the present application and the traditional prediction solution provided by the application example of the present application;

[0056] Figure 11 Schematic diagram of the comparison of the cross-track prediction errors between the solution provided by the present application and the traditional prediction solution provided by the application example of the present application. Detailed implementation manners

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0058] For ease of understanding, please refer to Figure 1 , an embodiment of a method for predicting the orbit state of a low-earth orbit satellite provided by the present application includes:

[0059] Step 101, define the pseudo-drag coefficient according to the atmospheric drag perturbation formula.

[0060] The atmospheric drag perturbation formula is expressed as:

[0061]

[0062] Wherein, represents the atmospheric drag perturbation, which refers to the acceleration caused by the atmospheric drag, is the mass of the current satellite, is the windward area, is the area-to-mass ratio, is the atmospheric drag coefficient, is the atmospheric density, which is related to the orbital altitude, represents the magnitude of v e , and v e represents the velocity vector of the spacecraft relative to the atmosphere. All parameters on the right side of the equation have uncertainties, and most studies focus on the modeling of the atmospheric density , which has a complex dependence relationship with space environment parameters such as geomagnetic indices and solar radiation flux indices. The atmospheric drag coefficient is estimated together with the state variables of the spacecraft in traditional precise orbit determination and prediction, and is used to absorb the errors of the atmospheric density model, satellite area-to-mass ratio, and satellite attitude change. The partial derivative of the atmospheric drag perturbation with respect to is expressed as:

[0063]

[0064] According to the above two formulas, it can be seen that the change of space environment parameters will affect the calculation of the atmospheric density , and further affect the calculation of the atmospheric drag coefficient . Moreover, in the case of medium- and long-term orbit prediction or obvious changes in the space environment, the atmospheric density is difficult to accurately estimate, which further affects the calculation of the atmospheric drag coefficient , resulting in a decrease in the accuracy of orbit prediction and an increase in errors.

[0065] Therefore, in this embodiment, a pseudo-drag coefficient is defined. Since the change of the space environment will ultimately be reflected in the orbital state of the satellite, in this embodiment, the change of the space environment is introduced into the atmospheric drag coefficient using the real orbit data. At this time, the space environment parameters used to calculate the atmospheric density are set to fixed values. Then, the atmospheric drag coefficient at this time does not need to be solved by orbit determination, and at the same time, it loses its original physical meaning and is defined as the pseudo-drag coefficient .

[0066] Step 102: Decompose the space environment parameters based on the correlation analysis of the pseudo-drag coefficient using the VMD algorithm to obtain the space environment characteristic parameters. The space environment parameters include the solar radiation flux index and the geomagnetic index.

[0067] Further, step 102 includes:

[0068] Normalize the solar radiation flux index and the geomagnetic index respectively and then merge them to obtain the space environment processing parameters;

[0069] Use the VMD algorithm to perform a decomposition operation on the space environment processing parameters based on the correlation analysis of the pseudo-drag coefficient to obtain the space environment characteristic parameters.

[0070] Through analysis, it is found that the space environment parameters are the key parameters affecting the atmospheric drag coefficient. Therefore, in this embodiment, the VMD algorithm is used to associate the changes in the space environment with the pseudo-drag coefficient. To confirm the strong correlation between the two, the solar radiation flux index and the geomagnetic index within the same time period can be normalized and analyzed with the pseudo-drag coefficient. Please refer to Figure 3 , the pseudo-drag coefficient and the solar radiation flux index The overall trend is relatively close, and the low-frequency characteristics are dominant. The Pearson correlation coefficient between the two is calculated to be 0.622; the geomagnetic index has a certain local influence on the pseudo-drag coefficient, manifested as the influence of some high-frequency characteristics. The Pearson correlation coefficient between the two is calculated to be 0.178.

[0071] The VMD algorithm is the variational mode decomposition algorithm, which is an adaptive signal decomposition method and can effectively process non-stationary and non-linear signals. The basic decomposition mechanism is to define each intrinsic mode function (IMF) component as a non-smooth component with amplitude modulation-frequency modulation characteristics; then perform the Hilbert transform, extract the unilateral spectrum to obtain the IMF spectrum; modulate the exponential term of the center frequency of the mixed spectrum response to the base frequency band of the response; then, on this basis, use the Gaussian smoothing algorithm to construct the objective function and solve it under the constraint conditions to obtain the optimal solution, that is, the target decomposition result.

[0072] It can be seen from the working principle of the VMD algorithm that this method has obvious advantages in extracting the frequency characteristics of signals. Therefore, in this embodiment, the VMD algorithm is used to perform a fusion decomposition process on the solar radiation flux index and the geomagnetic index to generate the space environment characteristic parameters. Specifically, first, the solar radiation flux index and the geomagnetic index Perform normalization to normalize the time-domain amplitude effects of the two under the same scale; then merge the normalized results to obtain the spatial environment processing parameters; finally, use the VMD algorithm to decompose the spatial environment processing parameters, filter out the high-frequency components, and obtain the spatial environment characteristic parameters , and the specific process can be referred to Figure 4 . By performing normalization and comparative analysis on the obtained spatial environment characteristic parameters and the pseudo-drag coefficient, we can obtain Figure 5 the results shown in the figure. It can be found that the spatial environment characteristic parameters are strongly correlated with the pseudo-drag coefficient, and the Pearson coefficient calculated for the two is 0.897. Therefore, in this embodiment, the changes in the spatial environment have been correlated with the pseudo-drag coefficient, and it is a strongly correlated relationship. Therefore, the pseudo-drag coefficient can be predicted based on the spatial environment parameters in the future; the decomposition operation based on the correlation analysis of the pseudo-drag coefficient mentioned in this embodiment refers to establishing a correlation relationship between the spatial environment parameters and the pseudo-drag coefficient to ensure the scientificity and rationality of subsequent prediction operations.

[0073] Step 103: Use the spatial environment characteristic parameters and the preset equivalent drag coefficient to perform pseudo-drag coefficient prediction training on the initial SVM model to obtain an optimized SVM model.

[0074] Further, step 103 includes:[[]]

[0075] Concatenate the spatial environment characteristic parameters and the preset equivalent drag coefficient into an input feature vector, use the historical pseudo-drag values as the target variables, and generate a training set;

[0076] Use the preset optimization algorithm and the training set to perform pseudo-drag coefficient prediction training on the initial SVM model to obtain an optimized SVM model.

[0077] Since there is a strong correlation between the spatial environment characteristic parameters and the pseudo-drag coefficient, this embodiment can construct a prediction model to predict the pseudo-drag coefficient based on the spatial environment characteristic parameters; the spatial environment characteristic parameters can be used as the input feature vector of the model, while the pseudo-drag coefficient is the output target variable.

[0078] To prove the advantages of the pseudo-drag coefficient determination method in this embodiment, the preset equivalent drag coefficient calculated based on the traditional method is used as a reference, and achieving a level better than this indicates an improvement in accuracy. After constructing the initial SVM model in this embodiment, a training set is constructed based on the spatial environment characteristic parameters and the preset equivalent drag coefficient. Concatenating the two can obtain an input feature vector, and using the historical pseudo-drag values as the corresponding labels, that is, the target variables, to obtain the model training set, which can be specifically expressed as , where represents the preset equivalent drag coefficient; the input feature vector is X, the output target vector is Y, and the learning objective of the model is to achieve mapping.

[0079] The pseudo drag history value in the training set can be calculated based on the concept definition. In this embodiment, the changes in the space environment are introduced into the atmospheric drag coefficient by using real orbit data. At this time, the space environment parameters for calculating the atmospheric density are fixed, and the pseudo drag coefficient can be calculated. . And the pseudo drag coefficient requires a high-precision orbit dynamics model and real satellite orbit data for solution; the orbit dynamics model adopted in this embodiment is in the geocentric inertial ECI coordinate system:

[0080]

[0081] Among them, and represent the position and velocity of the space target in the inertial system respectively, , represents the Euclidean norm of the vector; is the gravitational constant of the earth; represents the perturbation acceleration vector, which consists of non-spherical perturbation , three-body gravitational perturbation , atmospheric drag perturbation , solar radiation pressure perturbation and other unmodeled perturbations and so on. Except for the atmospheric drag perturbation, the modeling of the remaining perturbation models is accurate enough or has little impact on low-earth orbit satellites, so the details will not be discussed.

[0082] Set the space environment parameters for calculating the atmospheric density as fixed values, and given the initial epoch and the initial orbit state of the low-earth orbit satellite , , the orbit state at any future epoch can be regarded as a univariate function of the pseudo drag coefficient , specifically the following formula:

[0083]

[0084] can be solved by numerical integration calculation using the above orbit dynamics model.

[0085] Using satellite measurement data as real satellite orbit data, which is called precise ephemeris. Based on the precise ephemeris and with the principle of minimizing the prediction error e(t), the objective function for minimizing the prediction error can be constructed:

[0086]

[0087] Among them, x true$(t)$ is the precise ephemeris data in the inertial system, and $e(t)$ is the error value in the orbital coordinate system along the track direction, normal direction, and radial direction.

[0088] Pseudo-drag coefficient The optimization calculation process of can be regarded as finding the minimum value of a univariate function within a certain interval. The golden-section search is to search within the known interval through the golden ratio, continuously narrowing the maximum and minimum values within the known interval of the function, and finding the extreme value of the function. Therefore, in this embodiment, the golden-section search algorithm is selected to perform iterative optimization calculation according to the objective function of the prediction error, and the pseudo-drag coefficient when the prediction error is the smallest is obtained. It can be understood that all the pseudo-drag historical values required to construct the training set can be calculated by the above method; the initial SVM model can be optimized and trained by using the training set and the preset optimization method to obtain the optimized SVM model.

[0089] Further, before step 103, it also includes:

[0090] The orbital state of the low-earth orbit satellite is predicted by numerical integration to obtain the predicted ephemeris.

[0091] The traditional prediction error is calculated based on the orbital dynamics model and the predicted ephemeris.

[0092] The preset equivalent drag coefficient is obtained through iterative optimization analysis according to the traditional prediction error by the golden-section search algorithm.

[0093] It can be seen from the calculation of the pseudo-drag historical value above that the calculation process of the preset equivalent drag coefficient is basically the same as that of the pseudo-drag historical value. The only difference is that the predicted ephemeris obtained by the traditional method is used in the calculation process of the preset equivalent drag coefficient, while the precise ephemeris is used in the calculation process of the pseudo-drag historical value. Using the prediction result obtained by the traditional method, that is, the predicted ephemeris, as the benchmark to calculate the preset equivalent drag coefficient can represent a new prediction accuracy.

[0094] In view of the fact that the preset equivalent drag coefficient can be solved , then the orbital prediction accuracies based on the preset equivalent drag coefficient and the pseudo-drag coefficient can be compared. Please refer to Figure 6 , Figure 7 and Figure 8, taking a certain low-earth orbit satellite as an example, with an orbital altitude of about 400 km, under the same conditions, pseudo-drag coefficient prediction, preset equivalent drag coefficient prediction, and pure traditional method prediction are respectively carried out, and the orbital prediction errors in the RTN coordinate system can be obtained respectively. By comparison, it can be found that the prediction based on the pseudo-drag coefficient has obvious improvement in the total position error compared with the traditional prediction, mainly in the along-track direction. The prediction based on the preset equivalent drag coefficient is relatively consistent compared with the traditional prediction.

[0095] The prediction error comparison in this embodiment is carried out with unified normalization scaling, taking the maximum prediction error of the pseudo-drag coefficient as the unit quantity, and the scaled error is expressed as:

[0096]

[0097] Among them, is the scaled error, is the selected prediction error of the pseudo-drag coefficient , is the prediction error of other forms, respectively represent the radial, along-track, and normal directions.

[0098] Through comparative analysis, it can be found that the low-earth orbit satellite orbital prediction error is mainly manifested in the along-track direction, and the order of magnitude of the along-track error far exceeds that of the radial and normal directions; the pseudo-drag coefficient can effectively absorb the orbital prediction error, mainly affecting the along-track error. The order of magnitude of the radial error is less than that of the along-track but can still be improved, and the normal error has basically no influence; the prediction of the preset equivalent drag coefficient can approximately represent the prediction result of the traditional method, and at the same time, it also shows the scientificity and rationality of the pseudo-drag coefficient concept proposed in this embodiment.

[0099] Step 104: Predict the pseudo-drag coefficient at a future moment by optimizing the SVM model to obtain the pseudo-drag prediction value.

[0100] The optimized SVM model obtained after training can predict the pseudo-drag coefficient at a future moment according to the current space environment characteristic parameters and the current preset equivalent drag coefficient, which is called the pseudo-drag prediction value. The current parameters can refer to the latest parameter information at the current moment, or the recently calculated ones, which can be determined according to the actual situation.

[0101] Step 105: Predict and calculate the orbital state of the low-earth orbit satellite based on the pseudo-drag prediction value to obtain the state prediction result.

[0102] Further, step 105 includes:

[0103] Calculate the atmospheric drag perturbation value based on the pseudo-drag prediction value;

[0104] Substitute the atmospheric drag perturbation value into the formula of the orbital dynamics model to predict and calculate the orbital state of the low-earth orbit satellite, and obtain the state prediction result.

[0105] The atmospheric drag perturbation value can be calculated according to the atmospheric drag perturbation formula. Substitute the obtained atmospheric drag perturbation value into the formula of the orbital dynamics model, calculate the specific position and velocity of the satellite in the orbit, and then the state prediction result of the satellite orbit can be obtained.

[0106] For the sake of easy understanding, this application also provides an experimental measurement and calculation case. A low-earth orbit satellite with an orbital altitude of 400 km is selected for a 10-day orbit prediction. The pseudo-drag historical values are established using the precise ephemeris data of the first 70 days for the training stage of machine learning. In the prediction stage, the starting epoch starts from the 70th day, and the pseudo-drag coefficient required for the predicted starting epoch is predicted, thereby realizing intelligent orbit prediction. The normalized orbit prediction results are as Figures 9 - 11 shown. It can be seen from Figures 9 - 11 that the along-track error is the main error source of the low-earth orbit satellite, which comes from the uncertainty of the atmospheric drag. The solution of this application has achieved good performance in the actual orbit prediction application.

[0107] The method for predicting the orbital state of a low-earth orbit satellite provided by the embodiment of this application defines the concept of the pseudo-drag coefficient, associates the space environment parameters with the pseudo-drag coefficient through the VMD algorithm, and transforms the problem of predicting the orbital state of the low-earth orbit satellite into the problem of predicting the pseudo-drag coefficient; and on this basis, a pseudo-drag coefficient prediction model is constructed, which can ensure obtaining accurate pseudo-drag coefficients considering the changes in the space environment, and further guarantee the accuracy and reliability of the prediction results of the orbital state of the low-earth orbit satellite based on this; this process specifically analyzes the quantitative impact of the changes in the space environment on the pseudo-drag coefficient, which is more in line with the actual situation and can meet the current technical requirements for predicting the orbital state of low-earth orbit satellites. Therefore, the embodiment of this application can solve the technical problem that it is difficult to ensure the influence degree of the changes in the space environment in the prior art, resulting in poor accuracy of predicting the orbital state of low-earth orbit satellites.

[0108] For the sake of easy understanding, please refer to Figure 2 , this application provides an embodiment of a device for predicting the orbital state of a low-earth orbit satellite, including:

[0109] A coefficient definition unit 201, configured to define a pseudo-drag coefficient according to the atmospheric drag perturbation formula;

[0110] An association decomposition unit 202, configured to perform a decomposition operation on the space environment parameters based on the correlation analysis of the pseudo-drag coefficient according to the VMD algorithm to obtain space environment characteristic parameters, and the space environment parameters include the solar radiation flux index and the geomagnetic index;

[0111] The model training unit 203 is configured to perform pseudo drag coefficient prediction training on the initial SVM model by using the space environment characteristic parameters and the preset equivalent drag coefficient to obtain an optimized SVM model;

[0112] The coefficient prediction unit 204 is configured to predict the pseudo drag coefficient at a future moment through the optimized SVM model to obtain a pseudo drag prediction value;

[0113] The orbit prediction unit 205 is configured to perform prediction calculation on the orbit state of the low-earth orbit satellite according to the pseudo drag prediction value to obtain a state prediction result.

[0114] Further, the correlation decomposition unit 202 is specifically configured to:

[0115] Normalize the solar radiation flux index and the geomagnetic index respectively and then merge them to obtain space environment processing parameters;

[0116] Perform a decomposition operation on the space environment processing parameters based on the correlation analysis of the pseudo drag coefficient by using the VMD algorithm to obtain space environment characteristic parameters.

[0117] Further, the model training unit 203 is specifically configured to:

[0118] Concatenate the space environment characteristic parameters and the preset equivalent drag coefficient into an input feature vector, use the pseudo drag historical value as the target variable, and generate a training set;

[0119] Perform pseudo drag coefficient prediction training on the initial SVM model by using a preset optimization algorithm and the training set to obtain an optimized SVM model.

[0120] Further, it further includes:

[0121] The traditional prediction unit 206 is configured to predict the orbit state of the low-earth orbit satellite by using numerical integration to obtain a predicted ephemeris;

[0122] The error calculation unit 207 is configured to calculate the traditional prediction error based on the orbit dynamics model and the predicted ephemeris;

[0123] The optimization calculation unit 208 is configured to perform iterative optimization analysis according to the traditional prediction error through the golden section search algorithm to obtain the preset equivalent drag coefficient.

[0124] This application also provides a low-earth orbit satellite orbit state prediction device, which includes a processor and a memory;

[0125] The memory is used to store program codes and transmit the program codes to the processor;

[0126] The processor is configured to execute the low-earth orbit satellite orbit state prediction method in the above method embodiment according to the instructions in the program code.

[0127] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0130] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. And the aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (English full name: Read-Only Memory, English abbreviation: ROM), random access memories (English full name: Random Access Memory, English abbreviation: RAM), magnetic disks or optical discs that can store program codes.

[0131] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting the orbital state of a low-orbit satellite, characterized in that: include: The pseudo drag coefficient is defined according to the atmospheric drag perturbation formula. The pseudo drag coefficient is defined as follows: The space environment parameters are set to fixed values. At this time, the atmospheric drag coefficient does not need to be solved for orbit determination and also loses its original physical meaning. It is defined as the pseudo drag coefficient. According to the VMD algorithm, the space environment parameters are decomposed based on the pseudo resistance coefficient correlation analysis to obtain the space environment characteristic parameters, wherein the space environment parameters include the solar radiation flux index and the geomagnetic index. The decomposition operation process is as follows: The solar radiation flux index and the geomagnetic index are normalized and then merged to obtain the spatial environment processing parameters; Using a VMD algorithm to perform a decomposition operation on the space environment processing parameters based on the pseudo drag coefficient correlation analysis to obtain space environment characteristic parameters; The orbit state of low-orbit satellites is predicted by numerical integration to obtain the predicted ephemeris; Calculating a traditional prediction error based on the orbital dynamics model and the predicted ephemeris; An iterative optimization analysis is performed according to the traditional prediction error through a golden section search algorithm to obtain a preset equivalent resistance coefficient; The spatial environment characteristic parameters and the preset equivalent drag coefficient are used to perform pseudo drag coefficient prediction training on the initial SVM model to obtain an optimized SVM model. The prediction training process is as follows: The spatial environment characteristic parameters and the preset equivalent resistance coefficient are spliced ​​into an input feature vector, and the pseudo resistance historical value is used as a target variable to generate a training set; Using a preset optimization algorithm and the training set to perform pseudo drag coefficient prediction training on the initial SVM model to obtain an optimized SVM model; Predicting the pseudo resistance coefficient at a future moment by using the optimized SVM model to obtain a pseudo resistance prediction value; The orbit state of the low-orbit satellite is predicted and calculated according to the pseudo-resistance prediction value to obtain a state prediction result.

2. The method for predicting the orbital state of a low-orbit satellite according to claim 1, characterized in that: The step of predicting and calculating the orbital state of the low-orbit satellite according to the pseudo-resistance prediction value to obtain a state prediction result includes: Calculating an atmospheric resistance perturbation value according to the pseudo resistance prediction value; The atmospheric drag perturbation value is substituted into the orbital dynamics model formula to perform prediction calculation on the orbital state of the low-orbit satellite to obtain a state prediction result.

3. A low-orbit satellite orbit state prediction device, characterized in that: include: The coefficient definition unit is used to define the pseudo drag coefficient according to the atmospheric drag perturbation formula. The pseudo drag coefficient definition process is: The space environment parameters are set to fixed values. At this time, the atmospheric drag coefficient does not need to be solved for orbit determination and also loses its original physical meaning. It is defined as the pseudo drag coefficient. The correlation decomposition unit is used to perform a decomposition operation on the space environment parameters based on the pseudo resistance coefficient correlation analysis according to the VMD algorithm to obtain space environment characteristic parameters, wherein the space environment parameters include a solar radiation flow index and a geomagnetic index. The correlation decomposition unit is specifically used to: The solar radiation flux index and the geomagnetic index are normalized and then merged to obtain the spatial environment processing parameters; Using a VMD algorithm to perform a decomposition operation on the space environment processing parameters based on the pseudo drag coefficient correlation analysis to obtain space environment characteristic parameters; The traditional prediction unit is used to predict the orbit state of the low-orbit satellite by numerical integration to obtain the predicted ephemeris; An error calculation unit, used for calculating a traditional prediction error based on an orbital dynamics model and the predicted ephemeris; An optimization calculation unit, used for performing iterative optimization analysis according to the traditional prediction error by using a golden section search algorithm to obtain a preset equivalent resistance coefficient; The model training unit is used to perform pseudo drag coefficient prediction training on the initial SVM model using the spatial environment characteristic parameters and the preset equivalent drag coefficient to obtain an optimized SVM model. The model training unit is specifically used to: The spatial environment characteristic parameters and the preset equivalent resistance coefficient are spliced ​​into an input feature vector, and the pseudo resistance historical value is used as a target variable to generate a training set; Using a preset optimization algorithm and the training set to perform pseudo drag coefficient prediction training on the initial SVM model to obtain an optimized SVM model; A coefficient prediction unit, used to predict the pseudo resistance coefficient at a future moment by using the optimized SVM model to obtain a pseudo resistance prediction value; The orbit prediction unit is used to predict and calculate the orbit state of the low-orbit satellite according to the pseudo-drag prediction value to obtain a state prediction result.

4. A low-orbit satellite orbit state prediction device, characterized in that: The device comprises a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the low-orbit satellite orbit state prediction method described in any one of claims 1-2 according to the instructions in the program code.

Images