Ultra-low orbit guarantee method, system and equipment for near-earth satellite

Abstract

The invention discloses an ultra-low orbit guarantee method, system and equipment for a near-earth satellite. Comprising the following steps: determining a satellite orbit element at the current moment based on an atmospheric resistance perturbation item, a conventional perturbation item and a small thrust perturbation item, and inputting the satellite orbit element at the current moment into an orbit mechanical model; based on the orbit mechanical model and the satellite orbit elements, determining a first velocity position parameter of the satellite at the prediction moment under the ICRS coordinate system, and converting the first velocity position parameter into an ECEF coordinate system to obtain a second velocity position parameter at the prediction moment; inputting the time characteristic, the satellite state characteristic, the space environment characteristic and the second speed position parameter of the current moment into an orbit correction model to obtain a target error prediction value; adjusting the second speed position parameter based on the target error prediction value to obtain a target speed position parameter of the satellite at the prediction moment; and performing orbit attenuation risk early warning based on the target speed and position parameters of the satellite at the prediction moment.

Description

Technical Field

[0001] The present application relates to the field of space environment detection technology, in particular to the field of satellite detection technology, and in particular to an ultra-low orbit support method, system and equipment for near-Earth satellites. Background Art

[0002] Ultra-low-orbit satellites (also known as near-Earth satellites) operate in orbits between 150km and 300km from the Earth's surface. Due to the large number of satellites and the increased influence of the atmospheric environment, ultra-low-orbit satellites now face challenges such as rapid orbital decay, increased collision risk, and increased difficulty in attitude control.

[0003] Usually, due to the drag of the Earth's atmosphere, the orbit of an ultra-low-orbit satellite will gradually decay, eventually causing the satellite to re-enter the Earth's atmosphere and burn up, which will not only result in the loss of expensive satellite equipment, but may also pose a threat to ground facilities and personnel safety. At present, the orbit management of most satellites adopts a "post-response" strategy, that is, orbit raising operations are performed after the satellite orbit decays to a certain extent.

[0004] However, when encountering extreme space weather such as solar flares and geomagnetic explosions, the atmospheric density will change significantly. In this scenario, when the satellite is at a lower position, it will not be able to propel for a long time due to large air resistance, small ion thrust, or insufficient power on board, which will cause the satellite to face a greater risk of crashing. Therefore, if the atmospheric density and the speed and position of the satellite cannot be accurately predicted in advance, in extreme space weather, after the satellite orbit decays to a certain extent, it will not be able to smoothly raise the orbit due to large air resistance and will eventually crash. Based on this, it is crucial to build a complete ultra-low orbit support plan and system to ensure that the satellite can operate stably in orbit and reduce the occurrence of crashes. Summary of the invention

[0005] In view of this, the embodiments of the present application provide an ultra-low orbit protection method, system, equipment, medium and product for near-Earth satellites, which can accurately predict the atmospheric density and the speed and position of the satellite in advance, and perform orbital decay risk warning based on the target speed and position parameters of the satellite at the prediction time, so as to avoid the satellite orbit from falling to a lower position after a significant decay.

[0006] In a first aspect, an embodiment of the present application provides an ultra-low orbit guarantee method for a near-Earth satellite, the method comprising: inputting historical environmental parameters and M target prediction values ​​corresponding to a target prediction period into a first metamodel, assigning M first weight values ​​to the M target prediction values ​​through the first metamodel, wherein the M target prediction values ​​are output by M basic prediction models based on the historical environmental parameters corresponding to the target prediction period; performing weighted summation on the M target prediction values ​​using the M first weight values ​​to determine the atmospheric density of the target prediction period; determining the atmospheric resistance perturbation term of the satellite at the current moment based on the real-time windward surface mass ratio, drag coefficient, atmospheric density, and the velocity scalar and velocity vector of the satellite relative to the atmosphere, wherein the current moment is in the target prediction period; determining the atmospheric resistance perturbation term of the satellite at the current moment based on the atmospheric resistance perturbation term, the conventional perturbation term, and the small thrust perturbation term. The satellite orbital elements at the moment are determined, and the satellite orbital elements at the current moment are input into the orbital mechanics model; based on the orbital mechanics model and the satellite orbital elements, the velocity and position parameters of the satellite at the prediction moment in the geocentric inertial rectangular ICRS coordinate system are determined to obtain the first velocity and position parameters, and the first velocity and position parameters are converted into the earth-fixed rectangular ECEF coordinate system to obtain the second velocity and position parameters at the prediction moment; the time characteristics, satellite state characteristics, space environment characteristics, and the second velocity and position parameters at the current moment are input into the orbit correction model, so that the orbit correction model evaluates the error of the second velocity and position parameters to obtain the target error prediction value; the second velocity and position parameters are adjusted based on the target error prediction value to obtain the target velocity and position parameters of the satellite at the prediction moment; and an orbital attenuation risk warning is performed based on the target velocity and position parameters of the satellite at the prediction moment.

[0007] In a second aspect, an embodiment of the present application provides an ultra-low orbit support system for a near-Earth satellite, the system comprising: a weight allocation module, for inputting historical environmental parameters and M target prediction values ​​corresponding to a target prediction period into a first metamodel, and for assigning M first weight values ​​to the M target prediction values ​​through the first metamodel, wherein the M target prediction values ​​are output by M basic prediction models based on the historical environmental parameters corresponding to the target prediction period; a determination module, for performing weighted summation on the M target prediction values ​​using the M first weight values ​​to determine the atmospheric density of the target prediction period; the determination module is also used to determine the atmospheric resistance perturbation term of the satellite at the current moment based on the satellite's real-time windward surface mass ratio, drag coefficient, atmospheric density, and the satellite's velocity scalar and velocity vector relative to the atmosphere at the current moment, wherein the current moment is in the target prediction period; the determination module is also used to determine the current atmospheric resistance perturbation term based on the atmospheric resistance perturbation term, the conventional perturbation term, and the small thrust perturbation term. The invention relates to a method for determining the satellite orbital elements at the predicted moment and inputting the satellite orbital elements at the current moment into the orbital mechanics model; a coordinate system conversion module, which is used to determine the velocity and position parameters of the satellite at the predicted moment in the geocentric inertial rectangular ICRS coordinate system based on the orbital mechanics model, obtain the first velocity and position parameters, and convert the first velocity and position parameters into the earth-fixed rectangular ECEF coordinate system to obtain the second velocity and position parameters at the predicted moment; an error evaluation module, which is used to input the time characteristics, satellite state characteristics, space environment characteristics, and the second velocity and position parameters at the current moment into the orbit correction model, so that the orbit correction model evaluates the error of the second velocity and position parameters and obtains the target error prediction value; an orbit correction module, which is used to adjust the second velocity and position parameters based on the target error prediction value to obtain the target velocity and position parameters of the satellite at the predicted moment; and a risk warning module, which is used to carry out orbit attenuation risk warning based on the target velocity and position parameters of the satellite at the predicted moment.

[0008] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the steps of the ultra-low orbit guarantee method for a near-Earth satellite as in the first aspect are implemented.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the steps of the ultra-low orbit assurance method for a near-Earth satellite as in the first aspect are implemented.

[0010] In a fifth aspect, an embodiment of the present application provides a computer program product, which is stored in a non-volatile storage medium. When the computer program product is executed by a processor, it implements the steps of the ultra-low orbit guarantee method for a near-Earth satellite as in the first aspect.

[0011] In a sixth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the steps of the ultra-low orbit support method for near-Earth satellites as in the first aspect.

[0012] The present application provides an ultra-low orbit guarantee method, system, equipment, medium and product for near-Earth satellites. Accurate atmospheric density is a prerequisite for accurately predicting satellite velocity and position parameters. Therefore, the present application can combine the prediction results of multiple basic prediction models to improve the overall prediction performance of the first element model, make up for the shortcomings of using a single basic prediction model to predict atmospheric density, and reduce the overall prediction error when predicting atmospheric density when facing different environmental conditions, so that a more accurate atmospheric density can be obtained. Based on this, when the atmospheric resistance perturbation term is determined using the atmospheric density, the accuracy of the atmospheric resistance perturbation term can be improved, and then when the satellite orbit elements are determined using the atmospheric resistance perturbation term, the calculation accuracy of the satellite orbit elements can be improved. In addition, the small thrust perturbation term, the atmospheric resistance perturbation term and the conventional perturbation term are combined to more comprehensively reflect the actual force conditions of the satellite orbit, so that the orbital mechanics model can analyze the orbital changes of the satellite under the action of various forces based on the actual force conditions, and further improve the accuracy of the satellite orbit elements. Afterwards, considering the accuracy of the predicted value output by the orbital mechanics model, affected by the satellite state and the satellite space environment, the present application designs a multivariate and reasonable learning feature for the orbit correction model, including time features, satellite state features and space environment features. By integrating the multivariate features, the input information of the model is enhanced, the generalization ability of the orbit correction model for orbit error prediction is improved, and the target error prediction value for the satellite velocity position parameter is obtained. The second velocity position parameter (i.e., the predicted value) output by the orbital mechanics model is corrected using the target error prediction value to obtain a more accurate target velocity position parameter, thereby improving the prediction accuracy of the satellite position at the prediction time. Therefore, combined with the accurate prediction of the atmospheric density by the first element model, the influence of the small thrust perturbation term on the change of the satellite orbital position, and the accurate evaluation of the error value of the velocity position parameter output by the orbital mechanics model by the orbit correction model, the present application can effectively improve the accuracy of the satellite velocity position parameter at the prediction time, and then use the predicted accurate satellite velocity position parameter to perform orbit decay risk analysis and early warning in advance, so as to avoid the satellite orbit from falling to a lower position and crashing after a large decay, reduce the occurrence of crashes, and provide guarantee for the stable operation of the satellite in orbit. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical application of the embodiments of the present application, the drawings in the embodiments of the present application are briefly introduced below.

[0014] Figure 1 It is a flowchart of an ultra-low orbit guarantee method for a near-Earth satellite provided in one embodiment of the present application; Figure 2 is a flow chart of an ultra-low orbit assurance method for a near-Earth satellite provided by another embodiment of the present application; Figure 3 It is a flowchart of an ultra-low orbit guarantee method for a near-Earth satellite provided by yet another embodiment of the present application; Figure 4 It is a flowchart of an ultra-low orbit guarantee method for a near-Earth satellite provided by yet another embodiment of the present application; Figure 5 is a schematic diagram of an exemplary structure of an ultra-low orbit support system for a near-Earth satellite provided in one embodiment of the present application; Figure 6 is an exemplary schematic diagram of an atmospheric density forecasting process provided by an embodiment of the present application; Figure 7 is an exemplary schematic diagram of a trajectory calculation process provided by an embodiment of the present application; Figure 8 It is a structural schematic diagram of an ultra-low orbit support system for a near-Earth satellite provided in an embodiment of the present application; Fig. 9 It is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0015] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that the purpose of providing these embodiments is to make the principles and spirit of the present application clearer and more thorough, so that those skilled in the art can better understand and implement the principles and spirit of the present application. The exemplary embodiments provided herein are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments herein, all other embodiments obtained by ordinary technicians of the art without creative work are within the scope of protection of this application.

[0016] In this document, terms such as first, second, third, etc. are only used to distinguish one entity (or operation) from another entity (or operation), but not to require or imply any order or relationship between these entities (or operations).

[0017] The following is a brief description of the concepts and technical terms that may be involved in the embodiments of the present application.

[0018] Orbital mechanics model: A high-precision orbit propagation model is established by considering the various real physical forces (perturbations, such as atmospheric drag perturbations) that the satellite is subject to. It is used to predict the position and velocity of low-orbit satellites. Common orbital mechanics models include the Simplified General Perturbation Model 4 (SGP4), the High Precision Orbit Propagator (HPOP), etc.

[0019] Atmospheric drag perturbation: refers to the drag perturbation caused by the interaction between the satellite and the atmospheric molecules when the satellite is orbiting. This perturbation will affect the satellite's orbital parameters, such as orbital altitude, orbital inclination and period. For low-orbit satellites, atmospheric drag is the largest non-conservative force, so its impact on the satellite orbit must be considered.

[0020] Feature Fusion: It is the process of combining data features from different sources to enhance the input information of the model. This can be achieved through simple concatenation, weighted combination or more complex methods such as dimensionality reduction, aiming to improve the model's understanding and prediction ability of the task.

[0021] Model fusion technology: Model fusion technology is an integrated learning method that improves the overall prediction performance by combining the prediction results of multiple models. This method can make up for the shortcomings of a single model and improve the accuracy and robustness of the model.

[0022] Basic prediction model: referred to as base model, each basic prediction model is trained and predicted independently of other models, and generates its own prediction results based on different learning algorithms or different data subsets. Different basic prediction models have different learning biases and capabilities, and they capture different patterns or features in the data.

[0023] ECI: Earth-Centered Inertial (ECI) coordinate system, which does not rotate with the Earth.

[0024] ICRS coordinate system: International Celestial Reference System, is the celestial reference system standard adopted by the International Astronomical Union (IAU). It is a geocentric inertial rectangular coordinate system with coordinate axes defined based on the background of the distant starry sky. This coordinate system is not affected by the rotation or revolution of the earth and is mainly used in astronomy and satellite orbit calculations.

[0025] ECEF coordinate system: Earth-Centered, Earth-Fixed coordinate system, is an Earth-fixed rectangular coordinate system with the origin at the center of the Earth and the coordinate axes pointing to fixed positions on the Earth. The X-axis of the coordinate system usually points to the Greenwich astronomical meridian, the Y-axis points to 90 degrees east longitude, and the Z-axis is consistent with the Earth's rotation axis. This coordinate system changes with the Earth's rotation and is fixed relative to the Earth.

[0026] Geodetic Coordinate System (WGS84): It is a geocentric coordinate system widely used internationally. Its full name is WorldGeodetic System 1984 Coordinate System. It is a geocentric coordinate system with its origin at the center of mass of the earth. It uses longitude and latitude to represent the position and is defined based on the reference ellipsoid (WGS84 ellipsoid). It also changes with the rotation of the earth and is fixed relative to the earth.

[0027] Solar radiation parameters: Solar Indices, including F10.7, S10.7, M10.7, and Y10.7. F10.7 data is daily frequency, and its historical value can be obtained from NOAA (or the Atmospheric Density Forecast Center). The forecast value for the next 40 days can be obtained from NOAA, or it can be predicted using the F10.7 forecast model; S10.7, Y10.7, and M10.7 are daily frequency, and the forecast value for the next 40 days can be obtained using the corresponding forecast model; M10.7 is data with an update frequency of 3h, and its historical value can be obtained using an algorithm, and the forecast value can be obtained using the corresponding forecast model.

[0028] F10.7 (i.e. F107): is an indicator used to describe the intensity of solar radiation. It represents the solar radio flux at a wavelength of 10.7 cm, and therefore can reflect the intensity of solar activity. F10.7 is used as a good representative of solar ultraviolet radiation. The measurement of F10.7 is the average value of the intensity of solar radio radiation measured within one hour on the ground at a 100 MHz frequency band centered at 2800 MHz, and a value is updated daily. F10.7 is closely related to the activity on the surface of the sun, and also has a long and short periodic variation law of 11 years and 27 days. It is an important index to characterize solar activity, and there is a strong correlation between geomagnetic field disturbances and the activity level of the sun.

[0029] S10.7 (EUV): This is the solar radiation parameter in the extreme ultraviolet band, representing the solar radiation in the 26-34 nanometer band. This radiation mainly comes from solar active regions.

[0030] M10.7: This is the solar radiation parameter in the far ultraviolet band, representing the solar radiation around 280 nm, which includes the photospheric continuum and chromospheric line radiation. M10.7 is an index used to describe solar activity, which is calculated by the ratio of the core to the wing of the spectral line of the Mg II 280 nm band. This ratio reflects the emission of the solar active region in the chromosphere and is an index that is theoretically independent of changes in instrument sensitivity. The M10.7 index is used as a good representative of the solar Far Ultraviolet (FUV) and Extreme Ultraviolet (EUV) radiation, which have a significant impact on the Earth's atmosphere, especially the thermosphere (located between about 85 km and 600 km above the Earth's surface).

[0031] Y10.7: This is a mixed solar index representing mainly solar X-rays and Lyman-alpha radiation. X-rays come mainly from the solar canopy, while Lyman-alpha radiation is produced in the upper chromosphere and transition region of the sun.

[0032] Geomagnetic parameters: Geomagnetic parameters, including ap, Ap, Ap* and Dst indexes. The ap index is predicted by the deep learning model with 24 steps (each step is 3 days); Ap is the daily geomagnetic parameter, which is obtained by averaging the 8 ap values ​​of the day; Ap* is the sliding geomagnetic parameter, which is obtained by averaging the ap values ​​of the first 8 prediction periods of the target prediction period; Dst is a geomagnetic parameter with an hourly frequency.

[0033] ap index: also known as the equivalent planetary amplitude of geomagnetic disturbance, the unit is 2nT, a new ap value is generated every 3 hours, and 8 ap indexes are generated every day in chronological order. According to relevant standards, an ap value greater than 39 corresponds to a magnetic storm period. The maximum value of the ap index is 400.

[0034] Ap index: It is an index of the global daily geomagnetic disturbance intensity, also known as the planetary equivalent daily amplitude. It is an indicator to measure the level of geomagnetic activity. A new Ap value is generated every day, which is the average of 8 AP values ​​every day. Therefore, the Ap index can only reflect the overall situation of geomagnetic disturbance throughout the day.

[0035] Ap* index: It is an index of the intensity of geomagnetic disturbances in a predicted period. It is a real-time indicator for measuring the level of geomagnetic activity. Compared with the Ap index, it is more real-time and can therefore more accurately evaluate the overall situation of geomagnetic disturbances in a certain predicted period.

[0036] Dst Index: This is the Disturbance Storm Time (Dst) index, which is used to indicate the strength of the ring current during a magnetospheric storm. The Dst index is determined from hourly measurements of the magnetic field at four points around the Earth's equator and is used to simulate global density changes during geomagnetic storms.

[0037] The time and space parameters include altitude, longitude and latitude, universal time, DOY, month, and local time (or mean solar time, which cancels the whole hour restriction).

[0038] The ultra-low orbit guarantee method for a near-Earth satellite provided in the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0039] Figure 1 It is a flow chart of an ultra-low orbit guarantee method for a near-Earth satellite provided in one embodiment of the present application. The executor of the ultra-low orbit guarantee method for a near-Earth satellite may be an ultra-low orbit guarantee system.

[0040] The following takes the ultra-low orbit guarantee method of the near-Earth satellite as an example, in which the execution subject is the ultra-low orbit guarantee system, to illustrate the ultra-low orbit guarantee method of the near-Earth satellite of the present application. It should be noted that the above execution subjects and application scenarios do not constitute a limitation on the present application.

[0041] like Figure 1 As shown, the ultra-low orbit guarantee method for a near-Earth satellite provided in an embodiment of the present application may include steps 110 to 180.

[0042] Step 110, inputting historical environment parameters corresponding to the target prediction period and M target prediction values ​​into the first metamodel, and assigning M first weight values ​​to the M target prediction values ​​through the first metamodel; Step 120, performing weighted summation on the M target prediction values ​​using the M first weight values ​​to determine the atmospheric density of the target prediction period; Step 130, determining the atmospheric drag perturbation term of the satellite at the current moment based on the real-time windward surface mass ratio, drag coefficient, atmospheric density, and the velocity scalar and velocity vector of the satellite relative to the atmosphere at the current moment; Step 140, determining the satellite orbital elements at the current moment based on the atmospheric drag perturbation term, the conventional perturbation term and the small thrust perturbation term, and inputting the satellite orbital elements at the current moment into the orbital mechanics model; Step 150, based on the orbital mechanics model and the satellite orbit elements, determine the velocity and position parameters of the satellite at the prediction time in the Earth-centered inertial rectangular ICRS coordinate system to obtain the first velocity and position parameters, and convert the first velocity and position parameters into the Earth-fixed rectangular ECEF coordinate system to obtain the second velocity and position parameters at the prediction time; Step 160, inputting the time characteristics, satellite state characteristics, space environment characteristics, and second velocity position parameters at the current moment into the orbit correction model, so that the orbit correction model evaluates the error of the second velocity position parameter to obtain a target error prediction value; Step 170, adjusting the second speed position parameter based on the target error prediction value to obtain the target speed position parameter of the satellite at the prediction time; Step 180, providing an orbital decay risk warning based on the target velocity position parameters of the satellite at the prediction time.

[0043] The ultra-low orbit assurance method for near-Earth satellites provided in the embodiments of the present application, combined with the accurate prediction of atmospheric density by the first element model, the influence of small thrust perturbation terms on the change of satellite orbital position, and the accurate evaluation of the error value of the velocity and position parameters output by the orbital mechanics model by the orbit correction model, can effectively improve the accuracy of the satellite velocity and position parameters at the prediction time, and then use the predicted accurate satellite velocity and position parameters to perform orbital decay risk analysis and early warning in advance, avoid the satellite orbit from falling to a lower position and crashing after a large attenuation, reduce the occurrence of crashes, and provide assurance for the stable on-orbit operation of the satellite.

[0044] The specific implementation of the above steps will be described in detail below in conjunction with specific embodiments.

[0045] Involving step 110, historical environment parameters corresponding to the target prediction period and M target prediction values ​​are input into the first metamodel, and M first weight values ​​are assigned to the M target prediction values ​​through the first metamodel.

[0046] In step 110, M target prediction values ​​are obtained by respectively inputting historical environmental parameters corresponding to the target prediction period into M basic prediction models. The M target prediction values ​​are output by the M basic prediction models based on the historical environmental parameters corresponding to the target prediction period. The basic prediction models are basic atmospheric forecast models, including but not limited to JB series models (Jacchia-Bowman), MSIS series models (Mass Spectrometer Incoherent Scatter), and DTM series models (Drag Temperature Model), and M is a positive integer.

[0047] Historical environmental parameters include geomagnetic parameters, solar radiation parameters and spatiotemporal parameters. Geomagnetic parameters and solar radiation parameters are time series characteristics, including ap, Ap*, F10.7, M10.7, S10.7, Y10.7, etc., while spatiotemporal parameters are non-time series characteristics. , including longitude, latitude, altitude, DOY, month, and mean solar time.

[0048] The first meta-model is a fusion model for fusing the prediction results of M basic prediction models. The first weight value is used to characterize the prediction accuracy of each basic prediction model under the historical environmental parameters corresponding to the target prediction period. The higher the prediction accuracy, the higher the first weight value. Therefore, through the weight model of the first meta-model, the historical environmental parameters of the target prediction period can be analyzed, and M first weight values ​​can be assigned to the M target prediction values, so that the weight assignment can meet the spatial environmental conditions corresponding to the target prediction period.

[0049] Involving step 120, M first weight values ​​are used to perform weighted summation on M target prediction values ​​to determine the atmospheric density of the target prediction period.

[0050] Involving step 130, based on the real-time windward surface mass ratio, drag coefficient, atmospheric density of the satellite at the current moment, and the velocity scalar and velocity vector of the satellite relative to the atmosphere, the atmospheric drag perturbation term of the satellite at the current moment is determined.

[0051] In step 130, the current moment is in the target prediction period, and the atmospheric drag perturbation term can be calculated by the second acceleration To express, , is the second acceleration, C is the drag coefficient, A is the real-time frontal area of ​​the satellite, and m is the mass of the satellite. represents the atmospheric density, v and Represents the velocity scalar and velocity vector of the satellite relative to the atmosphere.

[0052] In an embodiment of the present application, based on the satellite mass and real-time windward area in the atmospheric drag perturbation term, the real-time windward surface mass ratio of the satellite can be determined, which can more accurately reflect the change in the windward area of ​​the satellite under different attitudes. Then, based on the real-time windward surface mass ratio, the second acceleration corresponding to the atmospheric drag perturbation term is determined, which can improve the calculation accuracy of the second acceleration in the satellite orbital mechanics model, and then improve the accuracy of the satellite orbital elements based on the second acceleration.

[0053] Involving step 140, based on the atmospheric drag perturbation term, the conventional perturbation term and the small thrust perturbation term, the satellite orbital elements at the current moment are determined, and the satellite orbital elements at the current moment are input into the orbital mechanics model.

[0054] In step 140, the ultra-low orbit satellite has the characteristics of high maneuvering frequency, long continuous maneuvering time, and small engine thrust. In order to maintain the continuity of orbit prediction, the present application adds a small thrust perturbation term that was not previously available to the orbital mechanics model to calculate the acceleration generated by the ion engine thrust, so as to consider the effect of the acceleration on the satellite when determining the satellite orbit elements. Conventional perturbation terms may include third body gravitational perturbation terms, earth non-spherical perturbation terms, solid tidal force perturbation terms, solar radiation pressure perturbation terms, and other perturbation terms.

[0055] Involving step 150, based on the orbital mechanics model and the satellite orbit elements, the velocity and position parameters of the satellite at the predicted time in the Earth-centered inertial rectangular ICRS coordinate system are determined to obtain the first velocity and position parameters, and the first velocity and position parameters are converted into the Earth-fixed rectangular ECEF coordinate system to obtain the second velocity and position parameters at the predicted time.

[0056] In step 150, the orbital mechanics model may be SGP4, HPOP, SGT4 or other models, which are not specifically limited in this application. The prediction time is a future time, after the current time, and there may be a prediction period between the current time and the prediction time. The period length of the prediction period may be preset according to specific needs, which is not specifically limited in this application. The prediction frequencies of the orbital mechanics model and the orbital correction model are consistent, and both are predicted once every prediction period.

[0057] The speed and position parameters of the present application include speed parameters and position parameters. By inputting the satellite orbit elements at the current moment into the orbital mechanics model, the orbital mechanics model can predict the speed and position parameters at future moments based on the satellite orbit elements, and represent the predicted speed and position parameters in the ICRS coordinate system to obtain the first speed and position parameters.

[0058] This application can use professional mathematical libraries or Geographic Information System (GIS) software (such as PROJ, GDAL or MATLAB's Geographic Toolbox) to achieve coordinate system conversion of velocity position parameters. The conversion process may also need to consider parameters such as the earth's flattening and reference ellipsoid model. Among them, PROJ is applied to the fields of Geographic Information System (GIS) and map projection, and usually refers to an open source library for coordinate conversion and map projection, supporting conversion between multiple map projection methods and coordinate reference systems (CRS). GDAL (Geospatial Data Abstraction Library) is an open source library for reading and writing raster and vector geospatial data formats. MATLAB (Matrix Laboratory) is a high-level programming language and environment for numerical and scientific computing.

[0059] Involving step 160, the time characteristics, satellite state characteristics, space environment characteristics, and second velocity position parameters of the current moment are input into the orbit correction model, so that the orbit correction model evaluates the error of the second velocity position parameter to obtain a target error prediction value.

[0060] In step 160, the satellite state feature is represented in the ECEF coordinate system, and the space environment feature is represented in the geodetic coordinate system wgs84. Both the wgs84 and ECEF coordinate systems change with the rotation of the earth and are fixed relative to the earth. Therefore, the two are relatively stationary and belong to the earth-fixed coordinate system. The feature fusion technology can be used to perform feature splicing on the time features, satellite state features, space environment features, and second velocity position parameters at the current moment to obtain input features, and then input them into the orbit correction model. The orbit correction model is pre-trained. The orbit correction model is used to evaluate the error of the predicted value of the velocity position parameter output by the orbital mechanics model. The error is relative to the true value. In the process of training the orbit correction model based on historical training data, the true value can be obtained by actually detecting the satellite through the satellite detection system. The above-mentioned first velocity position parameter and the second velocity position parameter are both output by the orbital mechanics model. The predicted value of the velocity position parameter at the predicted moment is different from the difference between the two in that they are represented in different coordinate systems.

[0061] This application designs multiple and reasonable learning features for the orbit correction model, including time features, satellite state features, and space environment features. By integrating multiple features, the input information of the model is enhanced, and the generalization ability of the orbit correction model for orbit error prediction is improved. In addition, the input features and output labels of the orbit correction model are uniformly represented in the earth-fixed coordinate system, which can fit the error between the predicted value and the true value output by the orbital mechanics model for different satellite states and different space environment states, analyze the performance of the predicted value output by the orbital mechanics model in different prediction scenarios, and realize global analysis and modeling of the prediction error of the orbital mechanics model, obtain the target error prediction value for the predicted value, and use the target error prediction value to correct the second velocity position parameter (i.e., the predicted value) output by the orbital mechanics model, and obtain a target velocity position parameter with higher accuracy, thereby improving the prediction accuracy of the satellite position at the prediction time.

[0062] It should be noted that the present application can input the input features after feature fusion into the orbit correction model, or can input the time features, satellite status features, space environment features, and second velocity position parameters of the current moment into the orbit correction model respectively, and perform feature fusion of various features through the orbit correction model.

[0063] The current time is , the prediction time is , , The time feature corresponding to the current time may include the current month, DOY (day of year), and the mean solar time of the satellite's longitude at the current time. DOY refers to the day of the year at the current time.

[0064] In some embodiments of the present application, satellite status characteristics may include the mass of the satellite, the windward area, and the velocity and position parameters of the satellite at the current moment in the ECEF coordinate system, and space environment characteristics may include the satellite position at the current moment in the geodetic coordinate system, the relative position of major celestial bodies and the satellite, and the satellite's solar radiation parameters and geomagnetic parameters.

[0065] Specifically, the satellite status characteristics may include the satellite's mass m, the windward area , and the velocity position parameters of the satellite in the ECEF coordinate system at the current moment. For the convenience of distinction, the velocity position can be the third velocity position parameter, which can specifically include three position component parameters ( , , ) and three velocity component parameters ( , , ).

[0066] In an embodiment of the present application, by converting the velocity position parameters of the satellite at the current moment in the input features into the ECEF coordinate system, the input features and output features of the orbit correction model can be unified to the earth-fixed coordinate system relatively fixed to the earth, reducing the difficulty of training the orbit correction model and enhancing the interpretability of the orbit correction model. In addition to time features and satellite state features, the input features can also include the relative positions of major celestial bodies (earth, sun, moon), solar radiation parameters and geomagnetic parameters, and all kinds of position features, time features and model prediction results are uniformly represented in the earth-fixed system, so that the orbit correction model can directly learn the relationship between the earth position, sun position, moon position and the prediction error of the orbital mechanics model. In this way, by inputting multivariate features into the orbit correction model, the orbit correction model can analyze and evaluate the prediction error of the orbital mechanics model under the influence of the current satellite state and the satellite space environment, and obtain the target error prediction value that can accurately correct the output prediction value of the orbital mechanics model.

[0067] In some embodiments of the present application, in addition to being represented in ECEF (Earth-fixed rectangular coordinate system), there is an alternative scheme for the second velocity position parameter, the third velocity position parameter, the predicted result of the orbital mechanics model, and the prediction error of the orbital correction model in the present application, that is, performing a coordinate transformation on the above parameters and converting them into the Earth-fixed polar coordinate system, so that they are all represented in the Earth-fixed polar coordinate system. The position velocity expression in the Earth-fixed polar coordinate system has a more direct correlation with other features represented in the geodetic coordinate system.

[0068] In some embodiments of the present application, the satellite position may include the longitude, latitude and altitude of the satellite, and the relative position of the main celestial body and the satellite includes the longitude and latitude of the point where the sun is directly above the earth, the relative longitude and latitude difference between the satellite and the sun, the longitude and latitude of the point where the moon is directly above the earth, and the relative longitude and latitude difference between the satellite and the moon.

[0069] Specifically, the space environment characteristics can include the following: the longitude of the satellite ,latitude and altitude; the longitude of the point where the sun shines directly on the earth and latitude , and the relative longitude and latitude difference between the satellite and the sun and ; The longitude of the point where the moon shines directly on the earth and latitude , and the relative longitude and latitude differences between the satellite and the moon and ; Solar radiation parameters F10.7, M10.7, S10.7, Y10.7; Geomagnetic parameters ap, Ap*.

[0070] The longitude and latitude of the satellite can be calculated from the satellite orbital roots. The longitude and latitude of the sun and moon at a specific time can also be directly calculated using professional astronomical software. The relative longitude and latitude difference calculation formulas (1), (2), (3), and (4) can be shown as follows: (1) (2) (3) (4) In some embodiments, the astronomical software may be, for example, Astropy, which is a Python software package for astronomical data analysis and processing. It is an open source project jointly promoted by the community and aims to provide a powerful astronomy and astrophysics core toolkit for the Python programming environment.

[0071] In some embodiments of the present application, in order to train an orbit correction model that can accurately evaluate the prediction error of the orbital mechanics model based on the current satellite status and the satellite space environment status, before the above-mentioned step 160, the following steps may also be included: obtaining time characteristics, satellite status characteristics, space environment characteristics and satellite orbit elements of multiple first moments; inputting the satellite orbit elements of the first moment into the orbital mechanics model to obtain the predicted value of the velocity and position parameters for the second moment output by the orbital mechanics model, wherein the first moment and the second moment are separated by a preset period; combining the time characteristics, satellite status characteristics, space environment characteristics of each first moment, and the predicted value and true value of the velocity and position parameters for the second moment to construct historical training data; training the preset model based on the historical training data to obtain an orbit correction model associated with the orbital mechanics model.

[0072] Specifically, the first moment and the second moment are two adjacent historical prediction moments, and the second moment is after the first moment. The true value of the velocity position parameter at the second moment can be obtained by actually detecting the satellite through the satellite detection system. The mean square error can be used as the loss function during model training, and the back propagation algorithm is used for training. The orbit correction model is associated with the orbital mechanics model. The preset model can be set according to specific needs, and this application does not make specific limitations on this.

[0073] The above-mentioned training of the preset model based on historical training data may specifically include: taking the time characteristics of the first moment, the satellite status characteristics, the space environment characteristics, and the predicted value of the speed and position parameters at the second moment as input training data, and taking the difference between the predicted value and the true value of the speed and position parameters at the second moment as output training data (i.e., output label) for training.

[0074] Among them, the difference between the predicted value and the true value of the speed position parameter at the second moment can be the true error value. The mean square error between the training error prediction value output by the preset model and the true error value is calculated to obtain the loss function value.

[0075] It should be noted that in the historical training data, the satellite state characteristics are in the ECEF coordinate system, the space environment characteristics are in the geodetic coordinate system, and the predicted value and true value of the velocity and position parameters at the second moment are both in the ECEF coordinate system, ensuring that the historical training data are uniformly represented in the earth-fixed coordinate system.

[0076] In the embodiment of the present application, during the training process of the orbit correction model, the training data used is derived from the predicted value actually output by the orbital mechanics model. Based on this, during the training process, the orbit correction model can learn the deviation between the predicted value output by the orbital mechanics model under different time characteristics, different satellite state characteristics, and different space environment characteristics and the true value, so that the trained orbit correction model can have the ability to reasonably and accurately evaluate the error of the predicted value output by the orbital mechanics model in different satellite orbit prediction scenarios by combining time characteristics, satellite state characteristics and space environment characteristics, and obtain an orbit correction model adapted to the orbital mechanics model, so that the orbit correction model can have a better prediction error evaluation capability for the associated orbital mechanics model. In addition, for different orbital mechanics models, an associated orbit correction model can be trained for each orbital mechanics model. The correction capability of the orbit correction model trained for a specific orbital mechanics model is only effective for the orbital mechanics model. For example, the correction model of HPOP is basically ineffective for the error correction of SGP4. This can make the adaptability and correlation between the orbital mechanics model and the orbit correction model stronger, and further enhance the prediction error evaluation capability of the orbit correction model for the associated orbital mechanics model.

[0077] In step 170, the second speed position parameter is adjusted based on the target error prediction value to obtain the target speed position parameter of the satellite at the prediction time.

[0078] In step 170, the target error prediction value is also represented in the ECEF coordinate system, and the target error prediction value can be added to the second speed position parameter to obtain the target speed position parameter at the prediction time. The target error prediction value can include a speed error prediction value and a position error prediction value.

[0079] Exemplarily, the second speed position parameter includes a speed parameter and positional parameters The orbit correction model outputs the predicted value of the satellite's velocity error in the ECEF coordinate system and the predicted position error , then the second speed position parameter and the prediction result of the correction model are combined to calculate the corrected target speed position parameter according to formulas (5) and (6). The target speed position parameter includes the speed parameter and positional parameters : (5) (6) Finally and Converted to the final forecast value in ICRS coordinate system and Make a report.

[0080] In some embodiments of the present application, the second speed position parameter and the target speed position parameter both include position parameters and speed parameters, the position parameter includes three position component parameters on the x, y, and z axes, and the speed parameter includes three speed component parameters on the x, y, and z axes. Accordingly, the speed error prediction value includes three speed component error prediction values ​​on the x, y, and z axes, and the position error prediction value includes three position component error prediction values ​​on the x, y, and z axes.

[0081] Based on this, the second speed position parameter and the target speed position parameter both contain three position component parameters and three speed component parameters. The orbit correction model is constructed by six sub-fusion models, each of which is composed of multiple base models and a target fusion model. Each base model is used to evaluate the deviation between the predicted value and the true value of the corresponding component parameter in the speed position parameter at the prediction moment, and obtain the predicted component error associated with the corresponding component parameter. The target fusion model is used to fuse multiple predicted component errors output by multiple base models to obtain the component error prediction value output by the sub-fusion model. Specifically, the six sub-fusion models have the same structure, and the multiple base models include at least two of lightGBM, random forest algorithm, support vector machine SVM algorithm, long short-term memory network LSTM, and encoder transformer encoder.

[0082] Multiple base models are trained based on historical training data. Specifically, the time characteristics, satellite state characteristics, space environment characteristics, and predicted values ​​of velocity position parameters at the first moment are used as input training data, and the difference between the predicted value and the true value of the corresponding component parameters of the velocity position parameters at the second moment are used as output training data (i.e., output labels). The target fusion model is used to fuse the output results of multiple base models. For example, a linear regression algorithm can be used to perform weighted summation on the output results of multiple base models to obtain the target velocity position parameters.

[0083] The above step 160 may specifically include: based on the six sub-fusion models, respectively evaluating the errors of the six component parameters in the second speed position parameter to obtain a target error prediction value including six component error prediction values. Among them, the six component error prediction values ​​include three speed component error prediction values ​​and three position component error prediction values, and the six component error prediction values ​​are used to adjust the six component parameters in the second speed position parameter respectively to obtain the target speed position parameter.

[0084] For example, the prediction time is , the current time is , the satellite is The third position parameter of the moment contains three position component parameters ( , , ) and three velocity component parameters ( , , ); Satellite in The second velocity position parameter at the moment contains three position component parameters , and the three velocity component parameters .

[0085] In this way, the present application trains a sub-fusion model for each component parameter in a targeted manner, so that the sub-fusion model has the ability to perform error evaluation on a single component parameter, and is more targeted and adaptable. Therefore, the accuracy of the orbit correction model's error evaluation of the predicted value output by the orbit mechanics model can be improved.

[0086] Involving step 180, an orbital decay risk warning is performed based on the target velocity position parameters of the satellite at the prediction time.

[0087] In step 180, the predicted attenuation altitude of the satellite can be determined based on the target speed and position parameters of the satellite at the predicted time, and the active orbit raising strategy is initiated when the predicted attenuation altitude reaches a preset level threshold. That is, when the risk of satellite orbit attenuation is detected in advance, the satellite engine is controlled to continue to thrust, and the orbit raising operation is actively performed on the satellite before the satellite orbit decays to a lower altitude, thereby reducing the risk of falling.

[0088] It should be noted that the present application can set an orbital decay period, which is a period used to predict the attenuation height of the satellite and adjust the real-time operating height of the satellite based on the attenuation height. The orbital decay period can include at least one prediction period. Exemplarily, if the orbital decay period and the prediction period are both 3 hours in duration, the predicted attenuation height of the satellite within the orbital decay period can be determined based on the speed position parameters of the satellite at the current moment and the target speed position parameters at the prediction moment; if the orbital decay period is 24 hours and the prediction period is 3 hours, the target speed position parameters are the speed position parameters 3 hours after the current moment. On this basis, it is necessary to continue to use the target speed position parameters to predict the speed position parameters 6 hours after the current moment. After multiple predictions, the speed position parameters 24 hours after the current moment are predicted based on the speed position parameters (predicted values) 21 hours after the current moment, and the predicted attenuation height of the satellite within the orbital decay period is determined by combining the two speed position parameters with an interval of 24 hours.

[0089] In some embodiments of the present application, in order to improve the accuracy and robustness of the first element model so as to reduce the overall prediction error when predicting the atmospheric density when facing different environmental conditions, before the above-mentioned step 110, the method may further include steps 210-230.

[0090] Step 210, obtain target training data, the target training data includes historical environmental parameters, measured values ​​and M predicted values ​​corresponding to each prediction period in multiple prediction periods, the measured values ​​are the actually detected atmospheric density of each prediction period, and the M predicted values ​​are obtained by predicting the atmospheric density of each prediction period based on the historical environmental parameters of each prediction period by M basic prediction models.

[0091] The measured value is the actual detected atmospheric density of each prediction period. For example, the actual satellite telemetry data at a large number of historical moments can be combined, and the detection value of the atmospheric density detector carried by the low-orbit satellite can be used as the measured value. The M predicted values ​​are obtained by predicting the atmospheric density of each prediction period based on the historical environmental parameters of each prediction period by M basic prediction models.

[0092] Exemplarily, the historical prediction periods include period 1, period 2, and period 3. Taking period 1 as an example, the target training data includes historical environmental parameters, measured values, and M predicted values ​​corresponding to period 1. The measured values ​​are the actually detected atmospheric density of period 1, and the M predicted values ​​are obtained by predicting the atmospheric density of period 1 based on the historical environmental parameters of period 1 by M basic prediction models.

[0093] Step 220 , training the first meta-model using the target training data, so that the first meta-model assigns corresponding M first weight values ​​to the M prediction values ​​of each prediction period based on the historical environment parameters corresponding to each prediction period.

[0094] In step 220, feature extraction is performed on the geomagnetic parameters and solar radiation parameters of N consecutive steps before each prediction period to obtain time series features, and feature extraction is performed on the spatiotemporal parameters of the prediction period to obtain non-time series features. The time series features, non-time series features, and M predicted values ​​corresponding to each prediction period are used as input features, and the M measured values ​​are used as labels to train the first meta-model. N is a positive integer and can be set according to specific needs, for example, it is set to 40.

[0095] The first meta-model obtains M prediction values ​​for each prediction period, and based on all the prediction values ​​under multiple prediction periods, learns how to adjust the weight values ​​of each basic prediction model under different environmental conditions, and assigns the first weight value to the M prediction values, that is, assigns the first weight value to the M basic prediction models.

[0096] For example, the M basic prediction models include the MSIS20 model, the MSIS00 model, the DTM2020 model, and the JB2008 model. The four basic prediction models can predict the atmospheric density of each prediction period based on the historical environmental parameters of the prediction period, and obtain the four prediction values ​​corresponding to each prediction period. , where the JB2008 prediction values ​​for three consecutive hours are averaged and used as the prediction value with a step length of 3 hours The first meta-model may assign four first weight values ​​to the fourth prediction value based on the historical environmental parameters corresponding to the Nth prediction period, perform weighted summation on the four prediction values ​​based on the four first weight values, and output the fused atmospheric density prediction value of the Nth period.

[0097] Step 230, when the first loss function value of the first metamodel satisfies the first preset condition, it is determined that the training of the first metamodel is completed, the first loss function value is the mean square error between the first predicted value corresponding to each prediction period in multiple prediction periods and the measured value, and the first predicted value is obtained by weighted summing up the M predicted values ​​corresponding to each prediction period using the M first weight values ​​assigned by the first metamodel in each prediction period.

[0098] In step 230, the first loss function value is the mean square error between the first predicted value and the measured value corresponding to each prediction period in multiple prediction periods, and the first predicted value is obtained by weighted summing the M predicted values ​​corresponding to each prediction period using the M first weight values ​​assigned by the first metamodel in each prediction period. The present application uses the stacking method to fuse the models.

[0099] The first meta-model is a fusion model for fusing the prediction results of M basic prediction models, and the first prediction value is the fusion result obtained by weighted summing the prediction results of the M basic prediction models by the first meta-model. Therefore, the mean square error between the first prediction value and the measured value of multiple prediction cycles is calculated. When the mean square error is less than the first preset error threshold, it is determined that the first loss function value of the first meta-model meets the first preset condition, and the training of the first meta-model is completed.

[0100] In some embodiments of the present application, the first meta-model includes a weight model and a fusion layer. The network structure of the weight model is transformer encoder or Lstm. The weight model is used to assign corresponding M first weight values ​​to M prediction values ​​of different prediction periods. The fusion layer is used to perform weighted summation of the M prediction values ​​using the M first weight values. Therefore, the fusion layer can also be a weighted summation layer.

[0101] Specifically, when the network structure of the weight model is transformer encoder, transformer encoder is used as a learner to train the weight model. When the network structure of the weight model is Lstm, Lstm is used as a learner to train the weight model. The weights of each basic prediction model are dynamically calculated according to the environmental characteristics corresponding to the historical environmental parameters. Finally, the prediction values ​​of each basic prediction model are weighted and summed to obtain the prediction result of the first meta-model.

[0102] The input features of the weight model include the features corresponding to the geomagnetic parameters, solar radiation parameters, and spatiotemporal parameters; the output of the weight model is the first weight value of each basic prediction model (the number of output weights is the same as the number of models). In addition to the input of the weight model, the input features of the first meta-model also include the prediction results of the basic prediction models, that is, M prediction values; the output of the first meta-model is the final result of this fusion.

[0103] In an example, for example, there are 4 basic prediction models, and the prediction values ​​of the basic prediction models of the prediction period are [pred1, pred2, pred3, pred4] respectively. At the same time, the weight vector W=[w1, w2, w3, w4, b] output by the weight model, where w1, w2, w3, w4 are the 4 first weight values, and b is the bias term, then the prediction result of the fusion layer of the first meta-model at this moment is As shown in formula (7): (7) In an embodiment of the present application, various atmospheric density forecast models are used as basic prediction models to make preliminary predictions on atmospheric density, and the weight model and the final weighted sum layer are connected together to form a first meta-model that is fused together. The input of the first meta-model includes the input features of the weight model and the prediction results of each basic prediction model. The first meta-model is trained using a mature machine learning algorithm transformer encoder or LSTM, so that the first meta-model can analyze the performance of each basic prediction model under different spatial environmental conditions, and combine the prediction accuracy of each basic prediction model for atmospheric density under different spatial environmental conditions. Different first weight values ​​are assigned to each basic prediction model under different spatial environmental conditions, so that the prediction results of each basic prediction model after fusion are more accurate, and more accurate atmospheric density prediction results are output.

[0104] In some embodiments of the present application, when the network structure of the weight model is Lstm, the above step 220 uses the target training data to train the first meta-model, which may specifically include the following steps: Extracting features of the geomagnetic parameters and solar radiation parameters of N consecutive steps before each prediction period to obtain time series features , and extract the features of the spatiotemporal parameters of each prediction period to obtain non-time series features ; For timing characteristics After normalization, the high-order features H of the last hidden layer of the weight model in round N are obtained. ; Merge H with non-time series features, input into a fully connected layer (FC), and then connect to a softmax layer, output a weight vector W, which contains M first weight values; Based on the weight vector, perform weighted summation on the predicted values ​​of the M basic prediction models to obtain the first predicted value; Use the measured value of atmospheric density as the label, use the mean square error between the measured value and the first predicted value as the loss function, and use the back propagation algorithm to train the first meta-model.

[0105] Specifically, geomagnetic parameters and solar radiation parameters are time series characteristics , including ap, Ap*, F10.7, M10.7, S10.7, and Y10.7. The update frequency of ap, Ap*, and M10.7 is 3 hours, and the update frequency of F10.7, S10.7, and Y10.7 is 1 day. The time series features take 3 hours as the step length. Time series features Before inputting into Lstm, normalization operation is required. Spatiotemporal parameters are non-sequential features. , including longitude, latitude, altitude, DOY, month, and mean solar time. The Lstm sequence length can be 40 or other values, the hidden layer depth can be 1, 2 or other values, and the hidden layer dimension can be 32, 64 or other values, which are not specifically limited in this application.

[0106] In some embodiments of the present application, before the above-mentioned step 130 determines the atmospheric resistance perturbation term of the satellite at the current moment, steps 310-330 may also be included: Step 310, when it is determined that the speed direction of the satellite is the windward direction, obtain the wind direction unit vector of the satellite in the on-board coordinate system, the area of ​​the satellite solar panel, and the unit normal vector of the plane where the satellite solar panel is located in the satellite body coordinate system; Step 320, convert the wind direction unit vector of the on-board coordinate system to the satellite body coordinate system; Step 330, determine the real-time windward area of ​​the satellite based on the satellite solar panel area, and the wind direction unit vector and unit normal vector in the satellite body coordinate system.

[0107] Specifically, if the windward direction is the satellite's velocity direction, then the wind direction unit vector in the satellite coordinate system is On this basis, the wind direction unit vector can be transformed from the on-board coordinate system to the satellite body coordinate system using the rotation matrix.

[0108] In the embodiment of the present application, the real-time windward area of ​​the satellite is determined based on the area of ​​the satellite solar panel, and the wind direction unit vector and unit normal vector in the satellite body coordinate system, and the fixed windward area in the atmospheric resistance perturbation term is updated to the real-time windward area. Compared with the fixed constant, the real-time windward area can be dynamically calculated when the attitude, orbital altitude and the movement of components such as solar panels cause the windward area to change, so the accuracy of the real-time windward area is higher. In this way, the present application optimizes and upgrades the atmospheric resistance perturbation term. When determining the satellite orbital elements, the acceleration generated by the atmospheric resistance perturbation term can be determined based on the more accurate real-time windward area, thereby improving the accuracy of the calculation of the satellite orbital elements.

[0109] In some embodiments of the present application, the above-mentioned step 320 converts the wind direction unit vector of the on-board coordinate system to the satellite body coordinate system, which may specifically include: obtaining a second rotation matrix of the satellite attitude angle relative to the satellite body coordinate system; and converting the wind direction unit vector from the on-board coordinate system to the satellite body coordinate system based on the second rotation matrix.

[0110] Specifically, the satellite attitude angle includes the roll angle , Pitch angle , yaw angle , the second rotation matrix from the on-board coordinate system to the satellite body coordinate system It can be calculated by method (8): (8) in, They represent the rotation matrices around the z-axis, y-axis, and x-axis of the on-satellite coordinate system, respectively:

[0111] Convert the wind direction unit vector from the on-board coordinate system to the satellite body coordinate system. , after calculation, we can get .

[0112] In this way, after obtaining the second rotation matrix, the wind direction unit vector can be successfully converted from the on-board coordinate system to the satellite body coordinate system using the second rotation matrix, thereby obtaining an effective expression of the wind direction unit vector in the satellite body coordinate system.

[0113] In some embodiments of the present application, in order to accurately calculate the real-time windward area of ​​the satellite, the above-mentioned step 330 determines the real-time windward area of ​​the satellite based on the area of ​​the satellite solar panel, and the wind direction unit vector and the unit normal vector in the satellite body coordinate system, which may specifically include: calculating the absolute value of the product of the wind direction unit vector and the unit normal vector in the satellite body coordinate system; multiplying the satellite solar panel area by the absolute value to obtain the real-time windward area of ​​the satellite.

[0114] Specifically, the satellite's windward area can be calculated using formula (9): : (9) Where S is the area of ​​the solar panel, and the unit normal vector of the plane where the satellite's solar panel is located in the satellite's body coordinate system is (The general satellite configuration is [0,0,1]), the satellite body can be approximately regarded as a sphere, s is the area of ​​the satellite sphere, and the real-time windward area of ​​the satellite is finally obtained by calculation .

[0115] In the embodiment of the present application, the absolute value of the product of the wind direction unit vector and the unit normal vector in the satellite body coordinate system is calculated, and the satellite solar panel area is multiplied by the absolute value, so that the real-time windward area of ​​the satellite can be effectively calculated. In this way, in the scenario where the satellite changes its attitude due to factors such as orbit adjustment and rotation of solar panels, by calculating the windward area in real time, these complex attitude changes can be effectively adapted to avoid the calculation error of the windward area caused by attitude changes.

[0116] In some embodiments of the present application, in order to obtain a small thrust perturbation term, Figure 4 is a flow chart of an ultra-low orbit guarantee method for a near-Earth satellite provided by another embodiment of the present application. Before the above step 140 determines the satellite orbit elements at the current moment based on the atmospheric drag perturbation term, the conventional perturbation term and the small thrust perturbation term, it may also include Figure 4 Steps 410 - 430 are shown.

[0117] Step 410, when the thrust of the satellite's ion thruster is constant, obtain the thrust vector of the satellite engine in the satellite's body coordinate system.

[0118] Specifically, the thrust generated by ion thrusters is small, and this low thrust is considered a perturbation term in orbital dynamics because it produces continuous small disturbances to the orbit of the spacecraft. Although the small thrust is small in magnitude, it can accumulate significant velocity increments over a long period of time. The continuous effect of small thrust will cause slow changes in the orbit, which may lead to the accumulation of orbital prediction errors if not taken into account.

[0119] Step 420, obtain the first rotation matrix of the satellite attitude angle relative to the geocentric inertial coordinate system, and based on the first rotation matrix, convert the thrust vector of the satellite engine in the satellite body coordinate system to the geocentric inertial coordinate system to obtain the thrust components of the thrust vector on the three coordinate axes of the geocentric inertial coordinate system.

[0120] Specifically, the conversion of the same vector between different coordinate systems can be completed by the rotation matrix. The satellite attitude is usually described relative to the ECI coordinate system. Therefore, the present application can obtain the satellite attitude angle through the satellite attitude sensor, and then use the satellite attitude angle to determine the first rotation matrix .

[0121] Rotation matrix from three-dimensional coordinate system A to coordinate system B is a 3×3 matrix that defines how to transform a vector from the coordinate system A to Transformed to coordinate system B The vector can be transformed in the AB coordinate system using formula (10): (10) Rotation Matrix , in the matrix It represents the projection of the unit vector in the first axis direction of the A coordinate system onto the various coordinate axis directions in the B coordinate system, and so on for the other elements.

[0122] Based on this, the thrust vector of the engine is , the thrust direction of the engine points directly behind the satellite, then The representation in the satellite body coordinate system (BFC) is , T is the thrust generated by the engine.

[0123] Using the first rotation matrix right After coordinate system transformation, we get Representation in the ECI coordinate system , the components of T on the three coordinate axes of ECI can be obtained by calculation:

[0124] Step 430, combining the satellite mass, the real-time on / off status of the engine, and the thrust components on the three coordinate axes to obtain a small thrust perturbation term.

[0125] Specifically, after the small thrust perturbation term is input into the orbital mechanics model, the orbital mechanics model can calculate the acceleration generated by the small thrust perturbation term based on the satellite mass, the real-time on / off status of the engine, and the thrust components on the three coordinate axes.

[0126] In some embodiments of the present application, the above-mentioned step 140 determines the satellite orbit elements based on the atmospheric drag perturbation term, the conventional perturbation term and the small thrust perturbation term, and may specifically include: determining the first acceleration corresponding to the small thrust perturbation term based on the satellite mass, the real-time on / off status of the engine and the thrust components on the three coordinate axes; determining the acceleration generated by the non-conservative force based on the first acceleration corresponding to the small thrust perturbation term and the second acceleration corresponding to the atmospheric drag perturbation term; determining the satellite orbit elements based on the acceleration generated by the non-conservative force, the earth's gravitational acceleration and the third celestial body's gravitational acceleration, wherein the earth's gravitational acceleration and the third celestial body's gravitational acceleration are calculated by the conventional perturbation terms.

[0127] Specifically, the engine can generate a small thrust when it is in the on state, and cannot generate a small thrust when it is in the off state, so the first acceleration determined is different in different on / off states. The gravitational acceleration of the earth and the gravitational acceleration of the third celestial body are calculated by conventional perturbation terms.

[0128] In addition to the small thrust perturbation term and the atmospheric drag perturbation term, the non-conservative force may also include other non-conservative force perturbation terms. Therefore, the acceleration generated by the non-conservative force can be obtained by adding the first acceleration, the second acceleration, and the acceleration generated by other non-conservative force perturbation terms.

[0129] For example, the orbital mechanics model is HPOP, and the dynamic equation of HPOP can be described by Newton's second law of motion in formula (11): (11) in, represents the second-order derivative of the position vector with respect to time, is the Earth's gravitational acceleration, , represents the gravitational acceleration of the third celestial body. The atmospheric drag and the small thrust generated by the engine are both non-conservative forces, and are represented by and to represent the acceleration produced by these two forces.

[0130] In the embodiment of the present application, a small thrust perturbation term is added on the basis of the atmospheric drag perturbation term and the conventional perturbation term. Based on this, when the satellite orbit elements are calculated by the subsequent orbital mechanics model, the first acceleration corresponding to the small thrust perturbation term and the second acceleration corresponding to the atmospheric drag perturbation term can be determined, and then the acceleration generated by the non-conservative force is determined by combining the first acceleration and the second acceleration. The small thrust perturbation term that was previously ignored is taken into account, so the calculated acceleration generated by the non-conservative force will be more accurate. By comprehensively considering these perturbation factors in the model, the dynamic changes of the satellite orbit can be analyzed more comprehensively, thereby improving the accuracy and reliability of the orbit prediction.

[0131] In some embodiments of the present application, in order to improve the accuracy of the first acceleration, the above-mentioned determination of the first acceleration corresponding to the small thrust perturbation term based on the satellite mass, the real-time on / off state of the engine and the thrust components on the three coordinate axes may include the following steps: substituting the real-time on / off state of the engine into the working state function to obtain the function value, wherein the on state and the off state correspond to different function values; determining the first acceleration corresponding to the small thrust perturbation term based on the function value, the satellite mass and the thrust components on the three coordinate axes.

[0132] Specifically, the acceleration expression of the small thrust perturbation term can be shown as formula (12): (12) in, is the first acceleration, I represents the working state function of the engine, I=1 when it is turned on, and I=0 when it is turned off. The small thrust perturbation term is connected to the satellite simulation module to obtain the satellite mass m, the real-time on / off state of the satellite engine, and the thrust size in each direction, so as to calculate .

[0133] In an embodiment of the present application, the thrust of the ion thruster is constant, so the thrust vector of the engine is constant. Based on this, the present application can use the thrust vector of the engine, the mass of the satellite, and the real-time on / off status of the satellite engine to effectively and accurately calculate the first acceleration generated by the small thrust perturbation term.

[0134] As a specific example, Figure 5 FIG. 1 is a schematic diagram of an exemplary structure of an ultra-low orbit support system for a near-Earth satellite provided in an embodiment of the present application. Figure 5 As shown, the ultra-low orbit support system includes a data collection and management module, a space environment prediction module, an atmospheric density prediction module, an atmospheric density correction module, a satellite simulation module, an orbit calculation module, an orbit correction module, and satellite situation and risk warning modules.

[0135] Among them, the functions of the data collection and management module include: real-time collection and storage of various historical data including measured values ​​and predicted values ​​of the space environment, satellite measured values ​​and model predicted values ​​of atmospheric density, measured values ​​and algorithm predicted values ​​of satellite orbital elements, platform parameters of different types of satellites, and satellite telemetry data; providing data support for the current reporting and prediction of the space environment, atmospheric density, satellite orbit, satellite risks and other situations; providing data support for the training and upgrading of AI correction models such as data correlation analysis, atmospheric density and orbit calculation.

[0136] The space environment forecast module mainly includes two models, namely the F107 forecast model and the Ap forecast model. F107 and Ap correspond to the intensity of solar radiation to the earth and the degree of geomagnetic disturbance caused by solar wind, respectively, and are the input parameters of common atmospheric density models. Figure 6 In the atmospheric density prediction process shown, the space environment prediction module extracts the historical values ​​of relevant space environment characteristics (such as Ap, F107, solar wind, X-rays, solar active areas, etc.) required to predict the atmospheric density from the data collection and management module, predicts F107 and Ap, and transmits the prediction results to the subsequent atmospheric density prediction module, and at the same time transmits them back to the data collection and management module for storage.

[0137] like Figure 6 As shown, the atmospheric density prediction module can be composed of multiple atmospheric models such as MSIS20, MSIS00, DTM, etc. Models can also be added. In practical applications, one output result can be selected from multiple atmospheric model output results as the final forecast result of atmospheric density, or the output results of multiple atmospheric models can be selected as part of the input of the atmospheric density correction model. Finally, the density forecast values ​​of multiple models at a specified time and space are transmitted back to the data collection and management module for storage. Figure 6 In the atmospheric density forecasting process shown, the atmospheric density forecasting module can receive the predicted values ​​of AP and F107 at a certain time in the next three days output by the space environment forecasting module and the spatial position of the satellite at the same time output by the orbit calculation module as input, and output the forecast results of multiple models, combined with the input time and spatial position, as part of the input of the atmospheric density correction model.

[0138] The atmospheric density correction model is an AI model that aims to integrate the output results of multiple models in the atmospheric density forecast module to further improve the prediction accuracy of atmospheric density. Figure 6 As shown in , the modified model is an integrated model that can be formed by integrating other AIs such as neural network LSTM, lightGBM, Xgboost, SVM, etc. The training data of this modified model comes from the historical data collected by the data collection management module. Figure 6 As shown in the figure, the inputs required for prediction by the correction model come from the data collection management module and the atmospheric density prediction model. The data collection management module provides the historical values ​​and prediction values ​​of the space environment indexes such as F107 and Ap, and the atmospheric density prediction module provides the prediction results of the spatiotemporal position and multiple atmospheric models. The correction model calculates the prediction results of the space environment index and multiple models, outputs a more accurate atmospheric density correction value as the final prediction value of the atmospheric density, transmits it back to the data collection management module for storage, and outputs it to the orbit calculation module for satellite orbit calculation.

[0139] The satellite simulation module can obtain various parameters of the satellite platform from the data collection and management module, such as satellite mass, volume, solar panel area, attitude, remaining power, engine thrust and other data. Through the satellite simulation algorithm, the satellite's real-time windward surface mass ratio, maneuvering acceleration and other data can be obtained, thereby providing data support for the accurate calculation of satellite orbits and situation display. Figure 7 In the orbit calculation process shown, the satellite simulation module obtains the specified satellite model, attitude strategy and maneuvering strategy from the data collection management module, calculates the satellite's drag coefficient and real-time windward surface mass ratio (dynamic surface mass ratio) through the simulation algorithm, and transmits the atmospheric perturbation item to the orbit calculation module, thereby improving the orbit calculation accuracy; obtains the satellite model, engine model and maneuvering strategy from the data collection management module, obtains the satellite's engine parameters (engine thrust size, direction), (on / off) status and other information through the simulation algorithm, and transmits the small thrust perturbation item to the orbit calculation module. In this way, the atmospheric drag perturbation item, small thrust perturbation item and conventional perturbation items (third body gravity perturbation item, earth non-spherical perturbation item, solid tidal force perturbation item, solar radiation pressure perturbation item and other perturbation items) are combined to achieve accurate calculation of the satellite orbit in the maneuvering state and obtain the orbital element calculation value.

[0140] The orbit calculation module has been optimized and upgraded based on HPOP (High Precision Orbit Algorithm). Figure 7 As can be seen from the orbit calculation process shown, the main optimization points are as follows: in view of the significant increase in the influence of atmospheric density on ultra-low orbits, the drag coefficient, satellite mass, windward area and other parameters in the atmospheric drag perturbation term are opened, and the calculation accuracy of the orbit algorithm on the influence of atmospheric density is improved by externally connecting the atmospheric density correction module and the satellite simulation module; in view of the characteristics of ultra-low orbit satellites with high maneuvering frequency, long continuous maneuvering time and very small engine thrust, a small thrust perturbation term that HPOP does not have is added, and the small thrust perturbation term is connected to the satellite simulation module externally to obtain the real-time status of the satellite engine, so as to calculate the influence of satellite maneuvers on the orbit, and realize the orbit calculation of the orbit algorithm for the satellite in maneuver.

[0141] The track correction module integrates neural network models such as LSTM and Transformers and machine learning models such as SVM and lightGBM. The training data of the model comes from the historical data collected by the data collection and management module. Figure 7As shown in the figure, this module obtains historical values ​​or predicted values ​​such as space environment data, satellite dynamics data, spatiotemporal position data, and telemetry data from the data collection and management module, and obtains predicted values ​​of orbital elements from the orbit calculation module. After joint calculation by multiple models, a more accurate orbital element correction value is obtained, and the correction value is used as the final orbit calculation result, which is returned to the data collection and management module for storage, and output to subsequent satellite situation, risk warning and other modules for display or analysis.

[0142] In this way, the orbit correction module integrates multiple AI models, and based on the calculation results of the orbit calculation module, combined with space environment data, satellite dynamics data, spatiotemporal position data, telemetry data, etc., it corrects the satellite's orbital parameters to further improve the calculation accuracy of the orbital roots.

[0143] Corresponding to the method embodiment of the present application, the present application also provides an ultra-low orbit support system for near-Earth satellites.

[0144] Figure 8 Schematic diagram of the structure of an ultra-low orbit support system for a near-Earth satellite provided in an embodiment of the present application. Figure 8 As shown, the ultra-low orbit guarantee system 800 of the near-Earth satellite may include: a weight allocation module 810, a determination module 820, a coordinate system conversion module 830, an error assessment module 840, an orbit correction module 850, and a risk warning module 860.

[0145] Among them, the weight allocation module 810 is used to input the historical environmental parameters and M target prediction values ​​corresponding to the target prediction period into the first metamodel, and allocate M first weight values ​​to the M target prediction values ​​through the first metamodel, wherein the M target prediction values ​​are output by the M basic prediction models based on the historical environmental parameters corresponding to the target prediction period; the determination module 820 is used to perform weighted summation on the M target prediction values ​​using the M first weight values ​​to determine the atmospheric density of the target prediction period; the determination module 820 is also used to determine the atmospheric resistance perturbation term of the satellite at the current moment based on the real-time windward surface mass ratio, drag coefficient, atmospheric density, and the velocity scalar and velocity vector of the satellite relative to the atmosphere at the current moment, wherein the current moment is in the target prediction period; the determination module 820 is also used to determine the satellite orbital roots at the current moment based on the atmospheric resistance perturbation term, the conventional perturbation term and the small thrust perturbation term, and send it to the orbital mechanics The model inputs the satellite orbital roots at the current moment; the coordinate system conversion module 830 is used to determine the speed and position parameters of the satellite at the predicted moment in the Earth-centered inertial rectangular ICRS coordinate system based on the orbital mechanics model, obtain the first speed and position parameters, and convert the first speed and position parameters into the Earth-fixed rectangular ECEF coordinate system to obtain the second speed and position parameters at the predicted moment; the error evaluation module 840 is used to input the time characteristics, satellite state characteristics, space environment characteristics, and the second speed and position parameters at the current moment into the orbit correction model, so that the orbit correction model evaluates the error of the second speed and position parameters to obtain the target error prediction value; the orbit correction module 850 is used to adjust the second speed and position parameters based on the target error prediction value to obtain the target speed and position parameters of the satellite at the predicted moment; the risk warning module 860 is used to issue an orbit attenuation risk warning based on the target speed and position parameters of the satellite at the predicted moment.

[0146] In some embodiments of the present application, the system also includes: an acquisition module, which is used to obtain the wind direction unit vector of the satellite in the on-board coordinate system, the area of ​​the satellite solar panel, and the unit normal vector of the plane where the satellite solar panel is located in the satellite body coordinate system before determining the atmospheric resistance perturbation term of the satellite at the current moment, when it is determined that the speed direction of the satellite is the windward direction; the coordinate system conversion module is also used to convert the wind direction unit vector of the on-board coordinate system to the satellite body coordinate system; the determination module is also used to determine the real-time windward area of ​​the satellite based on the satellite solar panel area, and the wind direction unit vector and unit normal vector in the satellite body coordinate system.

[0147] In some embodiments of the present application, the determination module is specifically used to: calculate the absolute value of the product of the wind direction unit vector and the unit normal vector in the satellite body coordinate system; multiply the satellite solar panel area by the absolute value to obtain the real-time windward area of ​​the satellite.

[0148] In some embodiments of the present application, it also includes: an acquisition module, which is also used to obtain the thrust vector of the satellite engine in the satellite body coordinate system when the thrust of the satellite's ion thruster is constant before determining the satellite orbital elements at the current moment based on the atmospheric drag perturbation term, the conventional perturbation term and the small thrust perturbation term; a coordinate system conversion module, which is also used to obtain the first rotation matrix of the satellite attitude angle relative to the geocentric inertial coordinate system, and based on the first rotation matrix, convert the thrust vector of the satellite engine in the satellite body coordinate system to the geocentric inertial coordinate system to obtain the thrust components of the thrust vector on the three coordinate axes of the geocentric inertial coordinate system; a combination module, which is used to combine the satellite mass, the real-time on / off status of the engine, and the thrust components on the three coordinate axes to obtain the small thrust perturbation term.

[0149] In some embodiments of the present application, the determination module includes: a first determination unit, used to determine the first acceleration corresponding to the small thrust perturbation term based on the satellite mass, the real-time on / off status of the engine, and the thrust components on the three coordinate axes; a second determination unit, used to determine the acceleration generated by the non-conservative force based on the first acceleration corresponding to the small thrust perturbation term and the second acceleration corresponding to the atmospheric drag perturbation term; a third determination unit, used to determine the satellite orbital elements based on the acceleration generated by the non-conservative force, the earth's gravitational acceleration, and the third celestial body's gravitational acceleration, wherein the earth's gravitational acceleration and the third celestial body's gravitational acceleration are calculated by conventional perturbation terms.

[0150] In some embodiments of the present application, the first determination unit is specifically used to: substitute the real-time on / off state of the engine into the working state function to obtain a function value, wherein the on state and the off state correspond to different function values; based on the function value, the satellite mass and the thrust components on the three coordinate axes, determine the first acceleration corresponding to the small thrust perturbation term.

[0151] In some embodiments of the present application, it also includes: an acquisition module, which is used to acquire target training data before inputting historical environmental parameters and M target prediction values ​​corresponding to the target prediction period into the first metamodel, wherein the target training data includes historical environmental parameters, measured values ​​and M prediction values ​​corresponding to each prediction period in multiple prediction periods, the measured value is the atmospheric density of each prediction period actually detected, and the M prediction values ​​are obtained by predicting the atmospheric density of each prediction period by M basic prediction models based on the historical environmental parameters of each prediction period; a model training module, which is used to train the first metamodel using the target training data so that the first metamodel assigns corresponding M first weight values ​​to the M prediction values ​​of each prediction period based on the historical environmental parameters corresponding to each prediction period; a determination module, which is used to determine that the training of the first metamodel is completed when the first loss function value of the first metamodel meets the first preset condition, wherein the first loss function value is the mean square error between the first prediction value corresponding to each prediction period in multiple prediction periods and the measured value, and the first prediction value is obtained by weighted summing the M prediction values ​​corresponding to each prediction period using the M first weight values ​​assigned by the first metamodel in each prediction period.

[0152] In some embodiments of the present application, the second speed position parameter and the target speed position parameter both include three position component parameters and three speed component parameters, the track correction model is constructed by six sub-fusion models, each sub-fusion model is composed of multiple base models and a target fusion model, each base model is used to evaluate the deviation between the predicted value and the true value of the corresponding component parameter in the speed position parameter at the prediction moment, and obtain the predicted component error associated with the corresponding component parameter, the target fusion model is used to fuse multiple predicted component errors output by multiple base models to obtain the component error prediction value output by the sub-fusion model; the multiple base models include at least two of lightGBM, random forest algorithm, support vector machine SVM algorithm, long short-term memory network LSTM, and encoder transformer encoder.

[0153] The ultra-low orbit support system for near-Earth satellites provided in the embodiments of the present application can achieve Figure 1-7 The various processes implemented by the service platform in the method embodiment can achieve the same technical effect. To avoid repetition, they will not be described here.

[0154] Fig. 9 It is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application.

[0155] like Fig. 9 As shown, the electronic device 900 includes a memory 901 , a processor 902 , and a computer program stored in the memory 901 and executable on the processor 902 .

[0156] In an example, the processor 902 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0157] The memory 901 may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it can be operated to perform the operations described with reference to the card opening method in the embodiment according to the first aspect of the present application.

[0158] The processor 902 runs a computer program corresponding to the executable program code by reading the executable program code stored in the memory 901, so as to implement the card activation method in the embodiment of the first aspect.

[0159] In some examples, the electronic device 900 may further include a communication interface 903 and a bus 910. Fig. 9 As shown, the memory 901, the processor 902, and the communication interface 903 are connected via a bus 910 and communicate with each other.

[0160] The communication interface 903 is mainly used to realize the communication between the modules, systems, units and / or devices in the embodiment of the present application. The input device and / or output device can also be accessed through the communication interface 903.

[0161] The bus 910 includes hardware, software, or both, coupling the components of the electronic device 900 to each other. By way of example and not limitation, the bus 910 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a Memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-E) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 910 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0162] The electronic device provided in the embodiment of the present application can realize Figure 1-7 The various processes implemented by the electronic device in the method embodiment can achieve the same technical effect, and to avoid repetition, they will not be described here.

[0163] In combination with the ultra-low orbit guarantee method for a near-Earth satellite in the above embodiments, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, the steps of any one of the ultra-low orbit guarantee methods for a near-Earth satellite in the above embodiments are implemented.

[0164] In combination with the ultra-low orbit guarantee method for a near-Earth satellite in the above embodiment, the embodiment of the present application can provide a computer program product for implementation. The (computer) program product is stored in a non-volatile storage medium, and when the program product is executed by at least one processor, the steps of any one of the ultra-low orbit guarantee methods for a near-Earth satellite in the above embodiment are implemented.

[0165] The embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, the processor is used to run programs or instructions, implement the various processes of the above-mentioned ultra-low orbit guarantee method embodiment of the near-Earth satellite, and can achieve the same technical effect. To avoid repetition, it will not be repeated here. It should be understood that the chip mentioned in the embodiment of the present application can also be called a system-level chip, a system chip, a chip system, or a system-on-chip chip, etc.

[0166] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0167] The functional blocks shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0168] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or systems. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0169] Aspects of the present disclosure are described above with reference to the flowcharts and / or block diagrams of the methods, systems (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing system to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing system enable the implementation of the functions / actions specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0170] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for ultra-low orbit support of a near-Earth satellite, characterized in that: include: Inputting historical environment parameters corresponding to the target prediction period and M target prediction values ​​into the first meta-model, and assigning M first weight values ​​to the M target prediction values ​​through the first meta-model, wherein the M target prediction values ​​are output by the M basic prediction models based on the historical environment parameters corresponding to the target prediction period; Using the M first weight values ​​to perform weighted summation on the M target prediction values, to determine the atmospheric density of the target prediction period; Based on the satellite's real-time windward surface mass ratio, drag coefficient, atmospheric density, and the satellite's velocity scalar and velocity vector relative to the atmosphere at the current moment, determine the satellite's atmospheric drag perturbation term at the current moment, where the current moment is in the target prediction period; Based on the atmospheric drag perturbation term, the conventional perturbation term and the small thrust perturbation term, the satellite orbital elements at the current moment are determined, and the satellite orbital elements at the current moment are input into the orbital mechanics model; Based on the orbital mechanics model and the satellite orbit elements, the velocity and position parameters of the satellite at the prediction time are determined in the Earth-centered inertial rectangular ICRS coordinate system to obtain the first velocity and position parameters, and the first velocity and position parameters are converted into the Earth-fixed rectangular ECEF coordinate system to obtain the second velocity and position parameters at the prediction time; Inputting the time characteristics, satellite state characteristics, space environment characteristics, and the second velocity position parameter at the current moment into the orbit correction model, so that the orbit correction model evaluates the error of the second velocity position parameter to obtain a target error prediction value; Adjusting the second speed position parameter based on the target error prediction value to obtain the target speed position parameter of the satellite at the prediction time; Orbital decay risk warning is carried out based on the target speed and position parameters of the satellite at the predicted time.

2. The method according to claim 1, characterized in that Before determining the atmospheric drag perturbation term of the satellite at the current moment, it also includes: When it is determined that the speed direction of the satellite is the windward direction, the wind direction unit vector of the satellite in the on-board coordinate system, the area of ​​the satellite solar panel, and the unit normal vector of the plane where the satellite solar panel is located in the satellite body coordinate system are obtained; Converting the wind direction unit vector of the on-satellite coordinate system to the satellite body coordinate system; Based on the satellite solar panel area, and the wind direction unit vector and unit normal vector in the satellite body coordinate system, the real-time windward area of ​​the satellite is determined.

3. The method according to claim 2, characterized in that Based on the satellite solar panel area, and the wind direction unit vector and unit normal vector on the satellite body coordinate system, the real-time windward area of ​​the satellite is determined, including: Calculate the absolute value of the product of the wind direction unit vector and the unit normal vector in the satellite body coordinate system; The satellite solar panel area is multiplied by the absolute value to obtain the real-time windward area of ​​the satellite.

4. The method according to claim 1, characterized in that: Before determining the satellite orbit elements at the current moment based on the atmospheric drag perturbation term, the conventional perturbation term and the small thrust perturbation term, it also includes: When the thrust of the satellite's ion thruster is constant, the thrust vector of the satellite engine in the satellite's body coordinate system is obtained; Acquire a first rotation matrix of the satellite attitude angle relative to the geocentric inertial coordinate system, and based on the first rotation matrix, convert the thrust vector of the satellite engine in the satellite body coordinate system to the geocentric inertial coordinate system to obtain the thrust components of the thrust vector on the three coordinate axes of the geocentric inertial coordinate system; The satellite mass, the real-time on / off status of the engine, and the thrust components on the three coordinate axes are combined to obtain a small thrust perturbation term.

5. The method according to claim 4, characterized in that Based on the atmospheric drag perturbation, conventional perturbation and small thrust perturbation, the satellite orbit elements are determined, including: Determining a first acceleration corresponding to a small thrust perturbation term based on the mass of the satellite, the real-time on / off state of the engine, and the thrust components on the three coordinate axes; Determining the acceleration generated by the non-conservative force based on the first acceleration corresponding to the small thrust perturbation term and the second acceleration corresponding to the atmospheric drag perturbation term; The satellite orbit elements are determined based on the acceleration generated by the non-conservative force, the earth's gravitational acceleration and the third celestial body's gravitational acceleration, wherein the earth's gravitational acceleration and the third celestial body's gravitational acceleration are calculated by conventional perturbation terms.

6. The method according to claim 5, characterized in that Based on the mass of the satellite, the real-time on / off state of the engine and the thrust components on the three coordinate axes, determining a first acceleration corresponding to the small thrust perturbation term includes: Substitute the real-time on / off state of the engine into the working state function to obtain the function value, wherein the on state and the off state correspond to different function values; A first acceleration corresponding to the small thrust perturbation term is determined based on the function value, the satellite mass and the thrust components on the three coordinate axes.

7. The method according to claim 1, characterized in that Before inputting the historical environment parameters corresponding to the target prediction period and the M target prediction values ​​into the first meta-model, it also includes: Obtain target training data, wherein the target training data includes historical environmental parameters, measured values, and M predicted values ​​corresponding to each prediction period in multiple prediction periods, wherein the measured values ​​are actually detected atmospheric density of each prediction period, and the M predicted values ​​are obtained by predicting the atmospheric density of each prediction period by M basic prediction models based on the historical environmental parameters of each prediction period; Using the target training data to train the first meta-model, so that the first meta-model assigns corresponding M first weight values ​​to the M prediction values ​​of each prediction period based on the historical environment parameters corresponding to each prediction period; When the first loss function value of the first meta-model satisfies the first preset condition, it is determined that the training of the first meta-model is completed, wherein the first loss function value is the mean square error between the first predicted value and the measured value corresponding to each prediction period in multiple prediction periods, and the first predicted value is obtained by weighted summing up the M predicted values ​​corresponding to each prediction period using the M first weight values ​​assigned by the first meta-model in each prediction period.

8. The method according to claim 1, characterized in that The second speed position parameter and the target speed position parameter both include three position component parameters and three speed component parameters. The track correction model is constructed by six sub-fusion models, each of which is composed of multiple base models and a target fusion model. Each base model is used to evaluate the deviation between the predicted value and the true value of the corresponding component parameter in the speed position parameter at the prediction moment to obtain the predicted component error associated with the corresponding component parameter. The target fusion model is used to fuse multiple predicted component errors output by multiple base models to obtain the component error prediction value output by the sub-fusion model. The multiple base models include at least two of lightGBM, random forest algorithm, support vector machine SVM algorithm, long short-term memory network LSTM, and encoder transformer encoder.

9. An ultra-low orbit support system for a near-Earth satellite, characterized in that: include: A weight assignment module, used for inputting historical environment parameters corresponding to the target prediction period and M target prediction values ​​into the first meta-model, and assigning M first weight values ​​to the M target prediction values ​​through the first meta-model, wherein the M target prediction values ​​are output by the M basic prediction models based on the historical environment parameters corresponding to the target prediction period; A determination module, configured to perform weighted summation on the M target prediction values ​​using the M first weight values ​​to determine the atmospheric density of the target prediction period; The determination module is further used to determine the atmospheric drag perturbation term of the satellite at the current moment based on the real-time windward surface mass ratio, drag coefficient, atmospheric density, and the velocity scalar and velocity vector of the satellite relative to the atmosphere at the current moment, wherein the current moment is in the target prediction period; The determination module is further used to determine the satellite orbital elements at the current moment based on the atmospheric drag perturbation term, the conventional perturbation term and the small thrust perturbation term, and input the satellite orbital elements at the current moment into the orbital mechanics model; A coordinate system conversion module is used to determine the velocity position parameters of the satellite at the prediction time in the Earth-centered inertial rectangular ICRS coordinate system based on the orbital mechanics model, obtain the first velocity position parameters, and convert the first velocity position parameters into the Earth-fixed rectangular ECEF coordinate system to obtain the second velocity position parameters at the prediction time; an error evaluation module, for inputting the time characteristics, satellite state characteristics, space environment characteristics, and the second velocity position parameter at the current moment into the orbit correction model, so that the orbit correction model evaluates the error of the second velocity position parameter to obtain a target error prediction value; An orbit correction module, used to adjust the second speed position parameter based on the target error prediction value to obtain the target speed position parameter of the satellite at the prediction time; The risk warning module is used to provide orbital decay risk warning based on the target speed position parameters of the satellite at the prediction time.

10. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; when the electronic device executes the computer program instructions, the method according to any one of claims 1 to 8 is implemented.

Images