Return position prediction method and device suitable for spacecraft and computer equipment

Abstract

This invention provides a method, apparatus, and computer device for predicting the return position of spacecraft. The invention calculates the deviation direction and distance between the real-time position information and the nominal orbit at the corresponding altitude level. By detecting whether the deviation distance exceeds the orbital deviation threshold at the corresponding altitude level, it quickly determines whether the spacecraft is abnormal, thus rapidly detecting abnormal flight conditions. Finally, the deviation distance (not exceeding the orbital deviation threshold), the corresponding altitude level, and the corresponding deviation direction are input into a preset deviation landing point mapping model. Based on the model output, the predicted return position of the spacecraft is determined. By using the model only for non-abnormal spacecraft to predict the return position, the prediction accuracy is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of aerospace telemetry and control technology, and in particular to a method, device and computer equipment for predicting the return position of a spacecraft. Background Technology

[0002] Accurate prediction of a spacecraft's return position is a critical aspect of the mission, directly impacting recovery efficiency and the safety of search and rescue personnel. Existing return position prediction methods primarily rely on orbital dynamics models and control law derivations, combined with position and velocity data acquired from ground-based telemetry and control equipment. However, these methods suffer from the following technical limitations: atmospheric density disturbances and aerodynamic parameter uncertainties during reentry can lead to accumulated orbital deviations; furthermore, the control law is adjusted in real-time during the reentry process, making it difficult for traditional dynamics models to cover these nonlinear disturbances. Consequently, the accuracy of the prediction results falls short of the requirements for search and rescue operations. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a method, device, and computer equipment for predicting the return position of spacecraft. It solves the technical problems in existing technologies, such as atmospheric density disturbances and aerodynamic parameter uncertainties during the return process leading to the accumulation of orbital deviations, and the real-time adjustment of the spacecraft's control law during the return process, which makes it difficult for traditional dynamic models to cover these nonlinear disturbances, resulting in prediction accuracy that is still somewhat lacking to meet search and rescue requirements.

[0004] According to an embodiment of the present invention, a method for predicting the return position of a spacecraft is provided. The method includes: constructing a preset standard orbit for the return trajectory based on Monte Carlo simulation; wherein the preset standard orbit includes nominal orbits at each altitude level and orbit deviation thresholds at each altitude level; acquiring real-time position information of the spacecraft based on preset telemetry and control equipment; wherein the real-time position information includes the altitude and three-dimensional position information of the corresponding altitude level; calculating the deviation direction and deviation distance between the real-time position information and the nominal orbit at the corresponding altitude level, and detecting whether the deviation distance exceeds the orbit deviation threshold at the corresponding altitude level; inputting the deviation distance (if it does not exceed the orbit deviation threshold at the corresponding altitude level), the corresponding altitude, and the corresponding deviation direction into a preset deviation landing point mapping model, and determining the target predicted return position of the spacecraft based on the output of the deviation landing point mapping model.

[0005] In some embodiments, the step of constructing a preset standard orbit for the return orbit based on Monte Carlo simulation further includes: constructing sample data of the spacecraft's reentry orbit based on Monte Carlo simulation; wherein the sample data includes return orbit data under different initial deviations, atmospheric disturbances, and aerodynamic parameter fluctuations; determining orbit deviation thresholds for each altitude level based on the sample data; and obtaining a preset standard orbit based on the orbit deviation thresholds for each altitude level and the preset nominal orbits for each altitude level.

[0006] In some embodiments, after the step of detecting whether the deviation distance exceeds the orbital deviation threshold of the corresponding altitude layer, the method further includes: if the deviation distance is detected to exceed the orbital deviation threshold of the corresponding altitude layer, issuing a return-to-home anomaly warning notification and stopping prediction.

[0007] In some embodiments, before the step of acquiring the spacecraft's real-time position information based on preset telemetry and control equipment, the method further includes: deploying multiple telemetry and control equipment according to the preset standard orbit, so that in the area where the preset standard orbit is located at an altitude layer below 50km, any location in the area is covered by at least 3 of the preset telemetry and control equipment.

[0008] In some embodiments, the step of acquiring the spacecraft's real-time position information based on preset telemetry and control equipment further includes: collecting the spacecraft's real-time position data based on various preset telemetry and control equipment to obtain multi-source raw data; wherein the number of sources of the multi-source raw data is determined by the number of telemetry and control equipment; performing fusion processing on the multi-source raw data to obtain multi-source fused data; and performing noise reduction processing on the multi-source fused data to obtain real-time position information.

[0009] In some embodiments, the step of calculating the deviation direction and deviation distance between the real-time position information and the nominal orbit of the corresponding height layer further includes: projecting and connecting the nadir point of the marked orbit of the corresponding height layer with the nadir point of the real-time position information, and using the obtained geodetic azimuth as the deviation direction; and calculating the deviation distance based on the nominal orbit of the corresponding height layer and the three-dimensional position information of the real-time position information.

[0010] In some embodiments, before the step of inputting the deviation distance (not exceeding the orbital deviation threshold of the corresponding altitude layer), the corresponding altitude, and the corresponding deviation direction into a preset deviation landing point mapping model, the method further includes: constructing an initial model; wherein the input of the initial model is each altitude layer in the spacecraft's historical return data, and the historical deviation direction and historical deviation distance corresponding to each altitude layer, and the output of the initial model is the historical actual direction deviation and historical actual deviation distance corresponding to the actual landing position in the spacecraft's historical return data; training and testing the initial model using a training set and a test set to obtain a deviation landing point mapping model; wherein both the training set and the test set are composed of the spacecraft's historical return data.

[0011] In some embodiments, the step of determining the predicted return position of the spacecraft based on the output of the deviation landing point mapping model further includes: obtaining the predicted target direction deviation and the predicted target deviation distance output by the deviation landing point mapping model; and calculating the predicted return position of the spacecraft based on the predicted target direction deviation, the predicted target deviation distance, and the nominal orbit.

[0012] On the other hand, according to embodiments of the present invention, a spacecraft return position prediction device is also provided. The device includes: a standard orbit calculation module, used to construct a preset standard orbit for the return orbit based on Monte Carlo simulation; wherein the preset standard orbit includes nominal orbits at each altitude level and orbit deviation thresholds at each altitude level; a real-time position measurement and control module, used to acquire real-time position information of the spacecraft based on preset measurement and control equipment; wherein the real-time position information includes the altitude and three-dimensional position information of the corresponding altitude level; a deviation calculation and detection module, used to calculate the deviation direction and deviation distance between the real-time position information and the nominal orbit at the corresponding altitude level, and detect whether the deviation distance exceeds the orbit deviation threshold at the corresponding altitude level; and a return position prediction module, used to input the deviation distance (which does not exceed the orbit deviation threshold at the corresponding altitude level), the corresponding altitude, and the corresponding deviation direction into a preset deviation landing point mapping model, and determine the target predicted return position of the spacecraft based on the output of the deviation landing point mapping model.

[0013] In some embodiments, a computer device is provided, including: a controller; and a memory for storing one or more programs, which, when executed by the controller, perform the applicable spacecraft return position prediction method mentioned in any of the above embodiments.

[0014] The technical principle of this invention is as follows: a preset standard orbit for the return trajectory is constructed based on Monte Carlo simulation, and the real-time position information of the spacecraft is obtained based on preset telemetry and control equipment. Then, the deviation direction and deviation distance between the real-time position information and the nominal orbit at the corresponding altitude layer are calculated. By detecting whether the deviation distance exceeds the orbit deviation threshold of the corresponding altitude layer, it is determined whether the spacecraft is abnormal. Finally, the deviation distance that does not exceed the orbit deviation threshold of the corresponding altitude layer, the corresponding altitude layer, and the corresponding deviation direction are input into a preset deviation landing point mapping model, and the target predicted return position of the spacecraft is determined based on the model output.

[0015] Compared with existing technologies, this invention has the following advantages: By calculating the deviation direction and distance between the real-time position information and the nominal orbit of the corresponding altitude layer, and by detecting whether the deviation distance exceeds the orbit deviation threshold of the corresponding altitude layer, it quickly determines whether the spacecraft is abnormal, thereby quickly detecting abnormal flight conditions; finally, the deviation distance that does not exceed the orbit deviation threshold of the corresponding altitude layer, the corresponding altitude layer, and the corresponding deviation direction are input into a preset deviation landing point mapping model, and the target predicted return position of the spacecraft is determined according to the model output. By using the model to predict the return position only for non-abnormal spacecraft, the prediction accuracy is greatly improved.

[0016] It solves the technical problems that factors such as atmospheric density disturbances and aerodynamic parameter uncertainties during the reentry process can lead to the accumulation of orbital deviations, and that the control law of the spacecraft is adjusted in real time during the reentry process. Traditional dynamic models are difficult to cover these nonlinear disturbances, and the accuracy of the prediction results is still somewhat different from the search and rescue requirements. Thus, it has the technical effect of improving the accuracy of the reentry position prediction.

[0017] Preferably, in this invention, the deviation distance, corresponding height, and corresponding deviation direction of the input model are quickly calculated by calculating the positional deviation at the same height. This allows for the rapid determination of the target's predicted return position, which greatly improves the prediction rate compared to the complex motion prediction calculation process in the prior art. Attached Figure Description

[0018] Figure 1 This is a flowchart of a method for predicting the return position of a spacecraft, as described in an embodiment of the present invention.

[0019] Figure 2 This is a flowchart of a method for predicting the return position of a spacecraft, according to another embodiment of the present invention.

[0020] Figure 3 This is a flowchart of a method for predicting the return position of a spacecraft, as described in another embodiment of the present invention.

[0021] Figure 4This is a flowchart of a method for predicting the return position of a spacecraft in another embodiment of the present invention.

[0022] Figure 5 This is a flowchart of a method for predicting the return position of a spacecraft, according to another embodiment of the present invention.

[0023] Figure 6 This is a flowchart of a method for predicting the return position of a spacecraft, as described in another embodiment of the present invention.

[0024] Figure 7 This is a structural block diagram of a spacecraft return position prediction device according to an embodiment of the present invention.

[0025] Figure 8 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0026] The technical solutions of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0027] Due to constraints in telemetry and control resources, the deployed radar, optical, and S-band unified telemetry and control equipment cannot achieve multiple coverages of the spacecraft's return orbit. Measurement data from a single device is susceptible to environmental interference, making it difficult to provide stable, high-precision real-time position information. Furthermore, existing methods do not fully utilize measured data from historical return missions, do not statistically summarize actual deviation patterns, and cannot correct prediction results through deviation mapping relationships. Consequently, landing point sensing results are not stable enough, and convergence performance is poor.

[0028] Therefore, this invention provides a method, apparatus, and computer device for predicting the return position of spacecraft. By combining orbital constraints, multi-source telemetry and control fusion, and historical data mapping, it achieves real-time prediction of the spacecraft's return position, solving the problems of large prediction errors and limited applicability in existing technologies, and improving the efficiency of spacecraft return and recovery while enhancing the safety of search and rescue personnel. To illustrate the solution provided by this invention in detail, the following embodiments are used for further explanation.

[0029] like Figure 1 As shown in the figure, this invention proposes a method for predicting the return position of a spacecraft, including the following steps:

[0030] Step S110: Construct a preset standard orbit for the return orbit based on Monte Carlo simulation.

[0031] The preset standard track includes the nominal track for each altitude level and the track deviation threshold for each altitude level.

[0032] Specifically, for any altitude during the spacecraft's return journey... ( ), the geocentric position deviation of the spacecraft ,in The maximum permissible deviation threshold for this altitude level is the orbital deviation threshold, specifically determined by the simulation sample data mentioned in subsequent embodiments. The principle is defined. The nominal orbit is the ideal orbit for the planned spacecraft. The nominal orbit consists of three-dimensional position information at each altitude level. .

[0033] Step S120: Obtain the spacecraft's real-time position information based on the preset telemetry and control equipment.

[0034] The real-time location information includes the height of the corresponding height layer and the three-dimensional location information;

[0035] Specifically, the three-dimensional location information of the real-time location information is as follows: Measurement and control equipment, including radar, optical, and S-band unified measurement and control equipment.

[0036] Step S130: Calculate the deviation direction and deviation distance between the real-time location information and the nominal orbit of the corresponding height layer, and detect whether the deviation distance exceeds the orbit deviation threshold of the corresponding height layer.

[0037] Specifically, the actual position of each altitude layer (each 1 km is one layer) is compared with the theoretical data corresponding to the nominal return orbit, and the direction of position deviation for each altitude layer is calculated. and deviation distance .

[0038] Step S140: Input the deviation distance (which does not exceed the orbital deviation threshold of the corresponding altitude layer), the corresponding altitude, and the corresponding deviation direction into the preset deviation landing point mapping model, and determine the predicted return position of the spacecraft based on the output of the deviation landing point mapping model.

[0039] Specifically, the altitude of the spacecraft's real-time return position obtained in the previous step... Deviation direction and deviation distance The data input deviation landing point mapping model allows the model to quickly output the landing position orientation deviation within the landing area. and deviation distance The predicted value. Finally, based on the direction deviation. and deviation distance The predicted value, along with the final landing point on the nominal orbit, allows for the calculation of the spacecraft's predicted return position.

[0040] The detailed working process of this embodiment is as follows: a preset standard orbit for the return trajectory is constructed based on Monte Carlo simulation, and the real-time position information of the spacecraft is obtained based on preset telemetry and control equipment. Then, the deviation direction and deviation distance between the real-time position information and the nominal orbit of the corresponding altitude layer are calculated. By detecting whether the deviation distance exceeds the orbit deviation threshold of the corresponding altitude layer, it is determined whether the spacecraft is abnormal. Finally, the deviation distance that does not exceed the orbit deviation threshold of the corresponding altitude layer, the corresponding altitude layer, and the corresponding deviation direction are input into a preset deviation landing point mapping model, and the target predicted return position of the spacecraft is determined according to the model output.

[0041] Technical Effects: By calculating the deviation direction and distance between real-time position information and the nominal orbit at the corresponding altitude layer, and detecting whether the deviation distance exceeds the orbital deviation threshold at the corresponding altitude layer, the system quickly determines whether the spacecraft is abnormal, thus rapidly detecting abnormal flight conditions. Finally, the deviation distance (within the orbital deviation threshold), the corresponding altitude layer, and the corresponding deviation direction are input into a preset deviation landing point mapping model. Based on the model output, the predicted return position of the spacecraft is determined. By using the model to predict the return position only for non-abnormal spacecraft, the prediction accuracy is greatly improved. This solves the technical problem that atmospheric density disturbances and aerodynamic parameter uncertainties during reentry can lead to accumulated orbital deviations, and that the control law is adjusted in real time during the spacecraft's reentry process, making it difficult for traditional dynamic models to cover these nonlinear disturbances, resulting in prediction accuracy that still falls short of search and rescue requirements. Therefore, this system achieves the technical effect of improving the accuracy of return position prediction.

[0042] Preferably, this invention uses only positional deviation calculations at the same altitude to quickly calculate the deviation distance, corresponding altitude, and corresponding deviation direction required for input to the model. This allows for rapid determination of the target's predicted return position, significantly improving the prediction rate compared to the complex motion prediction calculations in existing technologies. In practical applications, existing technologies require phased prediction time, with a time of 6.67 seconds required to predict from an altitude of 10km, and another 0.32 seconds required when the spacecraft reaches an altitude of 1km. In contrast, the prediction time required for each altitude phase in this invention is fixed at approximately 0.2 seconds. Compared to existing technologies, the prediction speed changes from a stepped progression to a fixed duration, and the greatly simplified calculation significantly increases the prediction speed, thereby improving the prediction rate of this invention.

[0043] In some embodiments, such as Figure 2 As shown, step S110 further includes:

[0044] Step S111: Construct sample data for spacecraft reentry orbit based on Monte Carlo simulation.

[0045] The sample data includes return orbit data under different initial deviations, atmospheric disturbances, and aerodynamic parameter fluctuations.

[0046] Specifically, Monte Carlo simulation was used to obtain sample data of the spacecraft's reentry orbit. The sample data included return orbit data under different initial deviations, atmospheric disturbances, and aerodynamic parameter fluctuations.

[0047] Step S112: Determine the orbital deviation threshold for each altitude layer based on the sample data.

[0048] Specifically, statistical analysis is performed on the sample data to extract the positional deviation values ​​corresponding to each altitude level. A three-dimensional return trajectory constraint pipeline (i.e., the "preset standard track") is constructed centered on the nominal track. The track deviation threshold is set for any altitude during reentry. ( ), the geocentric position deviation of the spacecraft ,in The maximum permissible deviation threshold for this altitude level is the orbital deviation threshold, which is specifically determined by the simulation sample data. The principles have been established. The principle is the Laida criterion, a data processing method based on normal distribution, primarily used to identify and remove outliers (gross errors). Its core idea is that, given a set of data that follows a normal distribution, the vast majority of data points will cluster around the mean μ; specifically, the values ​​will fall within the interval [missing value]. The probability of data points falling within this range is as high as approximately 99.73%, therefore data points outside this range are considered outliers and should be removed or corrected.

[0049] Step S113: Obtain the preset standard track based on the track deviation threshold of each altitude layer and the preset nominal track of each altitude layer.

[0050] Specifically, the nominal track is taken as the center, and the track deviation threshold of each altitude layer is used as the left and right ranges to obtain the preset standard track, which is a continuous track range.

[0051] Beneficial effects: The steps for constructing a preset standard orbit for the return orbit based on Monte Carlo simulation have been further refined. Sample data of the spacecraft's reentry orbit is constructed through Monte Carlo simulation, and then orbit deviation thresholds are generated based on the sample data. Finally, a preset standard orbit is obtained based on the nominal orbit, which can provide a basis for subsequent detection of whether the spacecraft is abnormal and the location of telemetry and control equipment.

[0052] In some embodiments, before step S120, the method further includes: deploying multiple telemetry and control (TT&C) devices according to a preset standard orbit, so that in the region where the preset standard orbit is located at an altitude of less than 50 km, any location in the region is covered by at least three preset TT&C devices. Specifically, in the region below the nominal orbit of the spacecraft, TT&C devices are deployed according to the principle of "multiple coverage," including radar, optical, and S-band unified TT&C devices, with a deployment density that ensures that in the region below an altitude of 50 km, any location is simultaneously covered by at least three devices.

[0053] In some embodiments, such as Figure 3 As shown, step S120 further includes:

[0054] Step S121: Collect real-time position data of the spacecraft based on various preset telemetry and control devices to obtain multi-source raw data.

[0055] The number of sources of multi-source raw data is determined by the number of measurement and control devices.

[0056] Specifically, each telemetry and control device that receives real-time location data will generate corresponding raw data, and the raw data obtained by multiple telemetry and control devices constitutes multi-source raw data.

[0057] Step S122: Perform fusion processing on the original data from multiple sources to obtain multi-source fused data.

[0058] Specifically, the collected raw data from multiple sources are fused to obtain multi-source fused data, where fusion refers to existing fusion technologies.

[0059] Step S123: Denoise the multi-source fused data to obtain real-time location information.

[0060] Specifically, methods such as smoothing data processing or Kalman filtering are used to eliminate measurement noise and obtain actual position data.

[0061] Beneficial effects: The steps for acquiring the spacecraft's real-time position information based on preset telemetry and control equipment are further refined. By fusing and denoising data collected from multiple telemetry and control devices, more accurate real-time position information is obtained, improving the accuracy of the target prediction return position subsequently obtained based on the real-time position information. This further enriches the scope of this invention application.

[0062] In some embodiments, after step S130 of detecting whether the deviation distance exceeds the orbital deviation threshold of the corresponding altitude layer, the method further includes: if the deviation distance is detected to exceed the orbital deviation threshold of the corresponding altitude layer, issuing a return-to-home anomaly warning notification and stopping prediction.

[0063] Specifically, if the detected deviation distance exceeds the orbital deviation threshold of the corresponding altitude layer, it indicates that the corresponding spacecraft's flight trajectory has exceeded the preset standard orbit and is in an abnormal state. An abnormal warning and prediction stop processing are issued in this case. Since it is already abnormal, continuing to predict is meaningless, so it is stopped directly to reduce unnecessary calculation costs.

[0064] In some embodiments, such as Figure 4 As shown, step S130, which involves calculating the deviation direction and deviation distance between the real-time location information and the nominal orbit at the corresponding altitude layer, further includes:

[0065] Step S131: Project and connect the nadir point of the marked orbit at the corresponding altitude layer with the nadir point of the real-time position information, and use the resulting geodetic azimuth as the deviation direction.

[0066] Specifically, the deviation direction The corresponding altitude position on the nominal return orbit Real-time position of the return capsule The azimuth angle of the line connecting the projections of the sub-satellite points.

[0067] Step S132: Calculate the deviation distance based on the nominal track of the corresponding height layer and the three-dimensional position information of the real-time position information.

[0068] Specifically, the three-dimensional position information of the nominal orbit is Deviation distance The calculation formula is as follows:

[0069]

[0070] Beneficial effects: The steps for calculating the deviation direction and distance between real-time position information and the nominal orbit at the corresponding altitude layer are further refined. By projecting the sub-satellite point and performing three-dimensional position calculations, the deviation direction and distance can be obtained quickly, improving the overall computational efficiency of this invention.

[0071] In some embodiments, such as Figure 5 As shown, before step 140, which involves inputting the deviation distance (not exceeding the orbital deviation threshold of the corresponding altitude layer), the corresponding altitude layer, and the corresponding deviation direction into the preset deviation landing point mapping model, the following steps are also included:

[0072] Step S210: Construct the initial model.

[0073] The input to the initial model is the historical altitude from the spacecraft's historical return data, as well as the historical deviation direction and historical deviation distance corresponding to the historical altitude. The output of the initial model is the historical actual direction deviation and historical actual deviation distance corresponding to the actual landing position from the spacecraft's historical return data.

[0074] Specifically, historical data on previous spacecraft returns will be collected, including historical directional deviations of the actual landing positions of each spacecraft return. Distance from historical deviation ( (This refers to the sequence number of each return activity) and the corresponding historical altitude during the reentry process. , location historical deviation direction and historical deviation distance ( (Assigning a hierarchical sequence number to each return activity). Based on historical heights. Historical deviation direction Distance from historical deviation The independent variable is the historical directional deviation of the actual landing position. Distance from historical deviation Construct a mapping model with the dependent variable as the dependent variable: , .

[0075] Step S220: Train and test the initial model using the training set and test set to obtain the deviation landing point mapping model.

[0076] Both the training set and the test set consist of historical return data from spacecraft.

[0077] Specifically, historical return data is divided into training and testing sets according to a certain ratio to train and test the model. The deviation landing point mapping model can be fitted using multiple linear regression to ensure the convergence and stability of the prediction results. The multiple linear regression fitting method used in the deviation landing point mapping model can be replaced by alternative methods such as decision trees and gradient boosting trees to adapt to historical data that does not meet the linear correlation analysis. Decision trees and gradient boosting trees replace the "mapping model construction" step in the patented "track pipe constraint - deviation calculation - landing point prediction" process, also with a high degree of... Deviation direction and deviation distance The independent variable is the deviation of the actual landing position. and deviation distance As the dependent variable, it can be perfectly adapted.

[0078] Beneficial effects: Constructing an altitude using historical return data Deviation direction and deviation distance The deviation landing point mapping model takes the direction deviation and deviation distance as inputs and outputs as outputs. It makes full use of historical return data to improve the accuracy of the deviation landing point mapping model, thereby improving the accuracy of target prediction return position.

[0079] In some embodiments, such as Figure 6 As shown, step S140, which involves determining the predicted return position of the spacecraft based on the output of the deviation landing point mapping model, further includes:

[0080] Step S141: Obtain the target prediction direction deviation and target prediction deviation distance output by the deviation landing point mapping model.

[0081] Specifically, the altitude at which the spacecraft returns to its real-time position, obtained in step S130, does not exceed the orbital deviation threshold of the corresponding altitude level. Deviation direction and deviation distance The data input deviation landing point mapping model is used to determine the landing position orientation deviation output by the deviation landing point mapping model. and deviation distance The predicted values ​​are respectively used as the target prediction direction deviation. Distance from target prediction .

[0082] Step S142: Calculate the predicted return position of the spacecraft based on the predicted target direction deviation, the predicted target deviation distance, and the nominal orbit.

[0083] Specifically, based on the target prediction direction deviation Distance from target prediction The system uses the nominal orbit as a standard to determine the corresponding target preset return position. Since the spacecraft will collect more than one position information during its return orbit, if there are multiple inputs, there will also be multiple corresponding outputs. Therefore, it is necessary to perform weighted fusion of the prediction results at different altitude levels (the lower the altitude, the greater the weight, and the weight below 5km should not be less than 50%) to finally output the high-precision return position of the spacecraft.

[0084] Beneficial effects: The steps for determining the predicted return position of the spacecraft based on the output of the deviation landing point mapping model are further refined, enriching the solution of this invention.

[0085] On the other hand, such as Figure 7 As shown, this embodiment of the invention also provides a spacecraft return position prediction device, the device 300 comprising:

[0086] The standard orbit calculation module 310 is used to construct a preset standard orbit for the return orbit based on Monte Carlo simulation; wherein, the preset standard orbit includes the nominal orbit of each altitude layer and the orbit deviation threshold of each altitude layer;

[0087] The real-time position measurement and control module 320 is used to acquire the spacecraft's real-time position information based on preset measurement and control equipment; wherein, the real-time position information includes the altitude of the corresponding altitude layer and three-dimensional position information;

[0088] The deviation calculation and detection module 330 is used to calculate the deviation direction and deviation distance between the real-time position information and the nominal track of the corresponding height layer, and to detect whether the deviation distance exceeds the track deviation threshold of the corresponding height layer.

[0089] The return position prediction module 340 is used to input the deviation distance (which does not exceed the orbital deviation threshold of the corresponding altitude layer), the corresponding altitude, and the corresponding deviation direction into a preset deviation landing point mapping model, and determine the target predicted return position of the spacecraft based on the output of the deviation landing point mapping model.

[0090] The detailed working process of this embodiment is as follows: a preset standard orbit for the return trajectory is constructed based on Monte Carlo simulation, and the real-time position information of the spacecraft is obtained based on preset telemetry and control equipment. Then, the deviation direction and deviation distance between the real-time position information and the nominal orbit of the corresponding altitude layer are calculated. By detecting whether the deviation distance exceeds the orbit deviation threshold of the corresponding altitude layer, it is determined whether the spacecraft is abnormal. Finally, the deviation distance that does not exceed the orbit deviation threshold of the corresponding altitude layer, the corresponding altitude layer, and the corresponding deviation direction are input into a preset deviation landing point mapping model, and the target predicted return position of the spacecraft is determined according to the model output.

[0091] Technical Effects: By calculating the deviation direction and distance between real-time position information and the nominal orbit at the corresponding altitude layer, and detecting whether the deviation distance exceeds the orbital deviation threshold at the corresponding altitude layer, the system quickly determines whether the spacecraft is abnormal, thus rapidly detecting abnormal flight conditions. Finally, the deviation distance (within the orbital deviation threshold), the corresponding altitude layer, and the corresponding deviation direction are input into a preset deviation landing point mapping model. Based on the model output, the predicted return position of the spacecraft is determined. By using the model to predict the return position only for non-abnormal spacecraft, the prediction accuracy is greatly improved. This solves the technical problem that atmospheric density disturbances and aerodynamic parameter uncertainties during reentry can lead to accumulated orbital deviations, and that the control law is adjusted in real time during the spacecraft's reentry process, making it difficult for traditional dynamic models to cover these nonlinear disturbances, resulting in prediction accuracy that still falls short of search and rescue requirements. Therefore, this system achieves the technical effect of improving the accuracy of return position prediction.

[0092] Preferably, in this invention, the deviation distance, corresponding height, and corresponding deviation direction of the input model are quickly calculated by calculating the positional deviation at the same height. This allows for the rapid determination of the target's predicted return position, which greatly improves the prediction rate compared to the complex motion prediction calculation process in the prior art.

[0093] Figure 8 The diagram illustrates a structural schematic of an embodiment of the computer device of the present invention, which shows a structural schematic of a computer system suitable for implementing the computer device of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computer device.

[0094] Please see Figure 8 As shown, the computer device includes: a controller; and a memory for storing one or more programs, which, when executed by the controller, perform the aforementioned method for predicting the return position of an applicable spacecraft.

[0095] Please continue reading. Figure 8 As shown, the computer system 400 of this computer device includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 402 or programs loaded from storage portion 408 into Random Access Memory (RAM) 403. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0096] The following components are connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to I / O interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 410 as needed so that computer programs read from it can be installed into storage section 408 as needed.

[0097] In particular, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs various functions defined in the system of the present invention.

[0098] Another aspect of the present invention provides a computer-readable storage medium storing at least one executable instruction that, when executed on a computer device / equipment, causes the computer device / equipment to perform a spacecraft return position prediction method as described in any of the above embodiments.

[0099] Beneficial Effects: By calculating the deviation direction and distance between real-time position information and the nominal orbit at the corresponding altitude layer, and detecting whether the deviation distance exceeds the orbital deviation threshold at the corresponding altitude layer, the system can quickly determine whether the spacecraft is abnormal, thus rapidly detecting abnormal flight conditions. Finally, the deviation distance that does not exceed the orbital deviation threshold at the corresponding altitude layer, the corresponding altitude layer, and the corresponding deviation direction are input into a preset deviation landing point mapping model. Based on the model output, the predicted return position of the spacecraft is determined. By using the model to predict the return position only for non-abnormal spacecraft, the prediction accuracy is greatly improved. This solves the technical problem that factors such as atmospheric density disturbances and aerodynamic parameter uncertainties during the return process can lead to the accumulation of orbital deviations, and that the control law of the spacecraft is adjusted in real time during the return process. Traditional dynamic models are unable to cover these nonlinear disturbances, and the prediction accuracy is still somewhat different from the search and rescue requirements. This results in a technical effect of improving the accuracy of return position prediction.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for predicting the return position of a spacecraft, characterized in that, The method includes: A preset standard track for the return trajectory is constructed based on Monte Carlo simulation; wherein, the preset standard track includes the nominal track for each altitude level and the track deviation threshold for each altitude level; The spacecraft's real-time position information is acquired based on preset telemetry and control equipment; wherein, the real-time position information includes the altitude of the corresponding altitude layer and three-dimensional position information; Calculate the deviation direction and deviation distance between the real-time location information and the nominal orbit of the corresponding height layer, and detect whether the deviation distance exceeds the orbit deviation threshold of the corresponding height layer; The deviation distance (which does not exceed the orbital deviation threshold of the corresponding altitude layer), the corresponding altitude, and the corresponding deviation direction are input into a preset deviation landing point mapping model, and the target predicted return position of the spacecraft is determined based on the output of the deviation landing point mapping model.

2. The method according to claim 1, characterized in that, The step of constructing a preset standard orbit for the return orbit based on Monte Carlo simulation further includes: Sample data for the spacecraft's reentry orbit was constructed based on Monte Carlo simulation; wherein, the sample data includes return orbit data under different initial deviations, atmospheric disturbances, and aerodynamic parameter fluctuations. Based on the sample data, determine the orbital deviation threshold for each altitude level; Based on the track deviation threshold of each altitude level and the preset nominal track of each altitude level, a preset standard track is obtained.

3. The method according to claim 1, characterized in that, After the step of detecting whether the deviation distance exceeds the orbital deviation threshold of the corresponding altitude layer, the method further includes: If the detected deviation distance exceeds the orbital deviation threshold of the corresponding altitude layer, a return-to-home anomaly warning notification is issued, and prediction is stopped.

4. The method according to claim 1, characterized in that, Before the step of acquiring the spacecraft's real-time position information based on preset telemetry and control equipment, the method further includes: According to the preset standard track, multiple measurement and control devices are deployed so that in the area where the preset standard track is located at an altitude of less than 50km, any location in the area is covered by at least 3 of the preset measurement and control devices.

5. The method according to claim 4, characterized in that, The step of acquiring the spacecraft's real-time position information based on preset telemetry and control equipment further includes: The spacecraft's real-time position data is collected based on various preset telemetry and control devices to obtain multi-source raw data; wherein, the number of sources of the multi-source raw data is determined by the number of telemetry and control devices. The multi-source raw data is fused to obtain multi-source fused data; The multi-source fused data is denoised to obtain real-time location information.

6. The method according to claim 1, characterized in that, The step of calculating the deviation direction and deviation distance between the real-time location information and the nominal orbit at the corresponding altitude layer further includes: The nadir angle obtained by projecting the nadir point of the marked orbit at the corresponding altitude layer and the nadir point of the real-time position information is used as the deviation direction. The deviation distance is calculated based on the nominal track of the corresponding height layer and the three-dimensional position information of the real-time position information.

7. The method according to claim 1, characterized in that, Before the step of inputting the deviation distance (which does not exceed the orbital deviation threshold of the corresponding height layer), the corresponding height, and the corresponding deviation direction into the preset deviation landing point mapping model, the method further includes: Construct an initial model; wherein the input of the initial model is the historical altitude of the spacecraft in its historical return data, as well as the historical deviation direction and historical deviation distance corresponding to the historical altitude, and the output of the initial model is the historical actual direction deviation and historical actual deviation distance corresponding to the actual landing position in the spacecraft's historical return data; The initial model is trained and tested using a training set and a test set to obtain a deviation landing point mapping model; wherein, both the training set and the test set consist of the spacecraft's historical return data.

8. The method according to claim 7, characterized in that, The step of determining the predicted return position of the spacecraft based on the output of the deviation landing point mapping model further includes: Obtain the target prediction direction deviation and target prediction deviation distance output by the deviation landing point mapping model; The predicted return position of the spacecraft is calculated based on the predicted target direction deviation, the predicted target deviation distance, and the nominal orbit.

9. A spacecraft return position prediction device, characterized in that, The device includes: A standard orbit calculation module is used to construct a preset standard orbit for the return orbit based on Monte Carlo simulation; wherein, the preset standard orbit includes the nominal orbit of each altitude layer and the orbit deviation threshold of each altitude layer; A real-time position measurement and control module is used to acquire the real-time position information of a spacecraft based on preset measurement and control equipment; wherein, the real-time position information includes the altitude of the corresponding altitude layer and three-dimensional position information; The deviation calculation and detection module is used to calculate the deviation direction and deviation distance between the real-time position information and the nominal track of the corresponding height layer, and to detect whether the deviation distance exceeds the track deviation threshold of the corresponding height layer; The return position prediction module is used to input the deviation distance (which does not exceed the orbital deviation threshold of the corresponding altitude layer), the corresponding altitude, and the corresponding deviation direction into a preset deviation landing point mapping model, and determine the target predicted return position of the spacecraft based on the output of the deviation landing point mapping model.

10. A computer device, characterized in that, include: Controller; A memory for storing one or more programs, which, when executed by the controller, perform the applicable spacecraft return position prediction method according to any one of claims 1-8.

Images