Method and system for evaluating collision risk of on-orbit spacecraft based on elastic expansion mechanism

Abstract

The invention discloses a method and system for evaluating an on-orbit spacecraft collision risk based on an elastic expansion mechanism, and belongs to the field of satellite operation safety evaluation. The invention discloses a method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism. The method comprises the following steps: selecting a corresponding observation assembly, a dynamic model and a space collision model; obtaining space-time big data of the flyer through an observation assembly; performing data processing on the time-space big data of the flyer to form a data set of which the data format is matched with the dynamic model; importing the data set into a kinetic model, and extracting features and modes of a specific flyer influencing the flight of the target spacecraft through convolutional network calculation; according to the characteristics and modes of the specific flyer, the relative proximity of the specific flyer and the target spacecraft is evaluated in real time through a space collision model; and according to the relative proximity, generating evaluation information and early warning information. The system for evaluating the collision risk of the on-orbit spacecraft based on the elastic expansion mechanism can dynamically adjust the resource quota, and is high in efficiency and response speed.

Description

Technical Field

[0001] This application belongs to the technical field of satellite operation safety assessment, and particularly relates to a method and system for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism. Background Art

[0002] With the development of space activities in various countries, the number of space targets in the Earth's orbit has been continuously accelerating. On-orbit spacecraft are constantly facing the risk of approaching or even colliding with other space targets. The issue of space traffic safety has received close attention from all space-faring countries and agencies. Therefore, ensuring the safe operation of spacecraft within their service life is an extremely important task.

[0003] In related technologies, in order to ensure the safety and sustainable development of space activities, the method of adjusting the satellite orbit through traditional information technology to passively avoid collisions, although providing support for the collision avoidance decision-making and collision avoidance orbit planning of spacecraft to a certain extent, the technical limitations are becoming increasingly prominent. On the one hand, the computing power of existing systems applying traditional methods is limited, and it is difficult to meet the high standards of real-time monitoring and early warning when processing and analyzing massive satellite telemetry data. On the other hand, the low efficiency of data processing leads to early warnings being issued only when a collision is approaching, leaving extremely limited reaction time for the staff and being unable to respond in real time to various dynamic changes in space. Summary of the Invention

[0004] In view of this, the first object of this application is to provide a method for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism to solve the problems of insufficient computing power and untimely early warning existing in traditional methods.

[0005] The second object of this application is to provide a system for implementing the above method.

[0006] To achieve the above technical objectives, the first aspect of this application provides a method for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism, and the method includes the following steps: Select corresponding observation components, dynamic models, and space collision models; Obtain the spatio-temporal big data of the flying object through the observation components; Process the spatio-temporal big data of the flying object to form a data set with a data format adapted to the dynamic model; Import the data set into the dynamic model, and through convolutional network calculation, extract the characteristics and patterns of specific flying objects affecting the flight of the target spacecraft; According to the characteristics and patterns of the specific flying objects, use the space collision model to real-time evaluate the relative proximity of the specific flying objects to the target spacecraft; Generate evaluation information and early warning information according to the relative proximity.

[0007] In one embodiment, it further includes: receiving indication information, where the indication information includes the target spacecraft ID, time range, and accuracy requirement.

[0008] In one embodiment, it further includes: setting the load threshold and resource quota of a specific cloud cluster according to the indication information.

[0009] In one embodiment, the spatio-temporal big data of the flying object includes space object tracking data, space environment data, and collision history data.

[0010] In one embodiment, when the resource amount required for data processing exceeds the total resources currently available in a specific cloud cluster, judge the availability and scalability of the physical server cluster; If the physical server cluster is available and supports expansion, deploy virtual machine instances for data processing on the physical server cluster.

[0011] In one embodiment, the data processing includes noise removal and data smoothing, outlier detection and correction, missing data supplementation, and data format standardization.

[0012] In one embodiment, the characteristics of the specific flying object include the flying object ID, name, orbital altitude, working frequency band, overflight time, and flying speed, and the mode of the specific flying object includes the flight mode and attitude control mode.

[0013] In one embodiment, the relative proximity includes relative distance, relative speed, and relative direction.

[0014] In one embodiment, if the relative proximity is less than or equal to a preset threshold, generate evaluation information and early warning information for requesting adjustment of the target spacecraft; If the relative proximity is greater than the preset threshold, do not generate evaluation information and early warning information for requesting adjustment of the target spacecraft.

[0015] The second aspect of the present application provides a system for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism. The system includes a processor and a memory communicatively connected to the processor. The memory stores an evaluation program executable by the processor. When the evaluation program stored in the memory is executed by the processor, the processor executes the method for evaluating the collision risk of on-orbit spacecraft based on the elastic expansion mechanism as described in the first aspect above.

[0016] By adopting the above technical solutions, the present application has the following beneficial effects: This application first selects the corresponding observation components, dynamic models, and space collision models, then obtains the spatio-temporal big data of the flying object through the observation components, and then processes the spatio-temporal big data of the flying object to form a data set with a data format adapted to the dynamic model. After that, the data set is imported into the dynamic model, and through convolutional network calculation, the characteristics and patterns of specific flying objects that affect the flight of the target spacecraft are extracted. Then, according to the characteristics and patterns of the specific flying objects, the relative proximity of the specific flying object to the target spacecraft is evaluated in real time through the space collision model. Finally, according to the relative proximity, evaluation information and warning information are generated. It can not only solve the problems of insufficient computing power and untimely warning existing in traditional methods, but also help to provide support for the collision avoidance decision-making and collision avoidance orbit planning of the target spacecraft, ensuring the safety and sustainable development of space activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of this application, the drawings required for the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can also be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of a method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to an embodiment of this application.

[0019] Figure 2 is Figure 1 The schematic diagram of the principle of the method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism as shown.

[0020] Figure 3 It is a schematic structural diagram of a system for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to an embodiment of this application.

[0021] Description of the reference numerals: C1, flight trajectory of the target spacecraft; C2, motion simulation trajectory of the specific flying object; P1, first intersection point; P2, second intersection point; 11, memory; 12, processor; 13, network interface; 14, bus system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The specific embodiments of this application will be described in detail below with reference to the drawings. Obviously, the described embodiments are only some embodiments of this application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the description of this application without creative efforts belong to the scope protected by this application.

[0023] In the description of this application, unless otherwise specified or limited, the terms "disposed," "installed," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; and direct or indirect connections through an intermediary. Those skilled in the art will understand the specific meanings of these terms based on the specific circumstances.

[0024] The directions or positional relationships indicated by terms such as "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inside" and "outside" are based on the directions or positional relationships shown in the accompanying drawings, or are the directions or positional relationships in which the invented product is usually placed when in use. They are only for the convenience and simplification of description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limitations on this application.

[0025] The terms "first," "second," "third," etc. are merely used to distinguish between elements of similar nature and do not indicate or imply relative importance or a particular order.

[0026] The terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than the listed elements and may also include additional elements not specifically listed.

[0027] With the rapid development of the aerospace industry, the space sector has entered an unprecedented period of activity. This is reflected not only in the dense deployment of various satellite constellations for communications, navigation, Earth observation, and other purposes, but also in the diversified efforts to develop and utilize space resources. However, this series of advances has also exacerbated the complexity of the space environment, leading to unprecedented challenges for space traffic management.

[0028] In the Low Earth Orbit (LEO) region, the surge in the number of spacecraft in orbit has significantly increased the risk of close encounters and potential collisions between satellites. This, coupled with the long-term accumulation of space debris, has created a dynamic and uncertain space environment, posing a serious threat to spacecraft safety. According to the inventors' understanding, while traditional information technology has provided some support for spacecraft collision avoidance decisions and trajectory planning, existing systems applying these methods have increasingly significant technical limitations. On the one hand, existing systems employing these methods have limited computing power, making it difficult to meet the high standards required for real-time monitoring and early warning when processing and analyzing massive amounts of satellite telemetry data. On the other hand, their inefficient data processing results in warnings only being issued when a collision is imminent, leaving operators with extremely limited time to react and unable to respond to dynamic changes in space in real time.

[0029] In view of this, in order to solve the problems of insufficient computing power and untimely warning existing in the traditional methods, it is necessary to improve or optimize the current technical solutions to provide sufficient warning time and feasible collision avoidance strategies for the spacecraft management team, and ensure the safety and sustainable development of space activities.

[0030] Embodiment 1 Please refer to Figure 1 , an embodiment of the first aspect of the present application provides a method for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism. The method for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism is applied to an information system built based on a cloud computing architecture, such as a cloud computing platform with the ability to process ultra-large-scale data. It should be noted that the ultra-large-scale data mentioned here refers to the stored information with a data magnitude above the terabyte (TB) level, such as the petabyte (PB) level, exabyte (EB) level, zettabyte (ZB) level, etc. The so-called cloud computing platform is a computing service platform based on cloud computing technology, which has higher availability, lower cost, and faster response time. It not only allows users to process data and applications distributedly over the network, but also can provide users with flexible, scalable, and shareable computing resources and system services.

[0031] In this Embodiment 1, the method for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism includes the following steps: Step S101: Select corresponding observation components, dynamic models, and space collision models.

[0032] Specifically, the observation components mentioned here include ground-based measurement devices and space-based measurement devices for sensing the space situation. Among them, the ground-based measurement devices include, but are not limited to, radars (range measurement, speed measurement, and angle measurement), lasers (range measurement), and optical telescopes (angle measurement), etc. The space-based measurement devices include, but are not limited to, optical sensors, lidars (LiDAR), and passive infrared detectors (PIR), etc.

[0033] The kinetic model mentioned here is a Convolutional Neural Networks (CNN) model used to describe the motion laws of space objects (such as satellites) in space, for predicting the orbital parameters of space objects. Specifically, the convolutional neural network model is a deep neural network model designed specifically for processing data with grid structures (such as images, audio, etc.). It combines big data analysis and machine learning algorithms to enable the constructed model to deeply mine and perform pattern recognition on massive amounts of data, so as to capture the dynamic change trends between orbital parameters and many variables (such as solar activities, geomagnetic indices, and atmospheric conditions, etc.). Then, convolutional neural network training is adopted to deeply understand the complex interactions between these variables, such as the real-time parameter relationships of multiple satellites in different orbital planes, or the real-time parameter relationships of multiple satellites in the same orbital plane, etc., to automatically extract data, achieve efficient processing and accurate recognition of complex data, and is widely used in tasks such as image recognition, object detection, and natural language processing.

[0034] The space collision model mentioned here is used to describe the probability of two space objects (such as spacecraft, space debris) colliding under specific conditions, and it includes physical models and mathematical formulas. It should be noted that during the calculation process of the collision probability, the balance between calculation accuracy and calculation efficiency needs to be considered.

[0035] Furthermore, step S101 also includes: receiving indication information.

[0036] Specifically, the indication information mentioned here can be sent to the receiver through system messages (such as network broadcasts) or specific control signals (such as dedicated communication channels), and it includes but is not limited to the target spacecraft ID, time range, and accuracy requirements, etc. Among them, the target spacecraft ID refers to the unique identifier used to identify and track the target spacecraft, the time range refers to the time period experienced by a certain event or process, and the accuracy requirement can refer to meter (m)-level accuracy, centimeter (cm)-level accuracy, etc.

[0037] Furthermore, to solve the problem of insufficient computing power existing in traditional methods, step S101 also includes: setting the load threshold and resource quota of a specific cloud cluster according to the indication information.

[0038] Specifically, the cloud cluster mentioned here refers to servers connected together through a network, such as cloud servers, which form a unified virtual server set by combining multiple servers (such as physical servers, virtual machines) to jointly provide services such as high availability, load balancing, and fault recovery. The load threshold mentioned refers to that under specific conditions, the load reaches a critical point or limit value, triggering corresponding operations or alarms, and is used to determine whether a certain indicator or variable reaches or exceeds the set limit value. The resource quota is a means of resource control. By allocating and restricting server resources (such as CPU, memory, disk space, etc.), it ensures that each user or application can only use the allocated amount of resources, preventing individual users or applications from occupying too many resources and avoiding problems such as server crashes and outages caused by resource abuse. Preferably, the setting of the load threshold and resource quota for the cloud cluster can be achieved through a cloud management platform (Cloud Management Platform, CMP). The cloud management platform mentioned is an information system for unified management and scheduling of cloud computing resources, aiming to centrally manage multiple cloud computing resource pools (including computing, storage, network, etc.) and realize automated deployment, monitoring, management, and optimization of resources.

[0039] Step S102: Obtain the spatio-temporal big data of the flying object through the observation component.

[0040] Specifically, the flying object mentioned here refers to an object flying in the air, including but not limited to spacecraft (such as satellites, rockets, etc.), space debris (such as the rocket body after mission completion, the satellite body after mission completion, and the ejecta of the rocket, etc.), and other objects that may collide with the target spacecraft. The spatio-temporal big data refers to a data set that simultaneously has time attributes and space attributes, and has the characteristics of multi-scale correlation, dynamic change, and multi-source and massive. Among them, multi-scale correlation means that spatio-temporal data shows multi-type and multi-dimensional correlation characteristics in the spatio-temporal evolution at different scales; dynamic change means that spatio-temporal data changes with time and space, and has time-varying and non-linear characteristics; multi-source and massive means that spatio-temporal data comes from various devices (such as drones, satellites, social media, Internet of Things devices, and mobile devices, etc.) and various sensors (such as optical sensors, radar sensors, and microwave sensors, etc.), and the data volume is huge.

[0041] Further, in step S102, in order to ensure the richness of the acquired data and be able to extract useful information through analysis and mining, specifically, the spatio-temporal big data includes spatial object tracking historical data, spatial environment data, and collision historical data. Among them, the spatial object tracking historical data can be information about the status and position of a satellite obtained through a satellite TT&C system, and this information includes but is not limited to the orbital parameters, attitude information, telemetry data, etc. of the satellite; the spatial environment data can be spatial physical environment data detected and collected by a satellite, and this data includes but is not limited to solar activity, the Earth's magnetic field, atmospheric conditions, high-energy particles, etc.; the collision historical data can be various measurement data and statistical information related to satellite collision events, and this information includes but is not limited to the orbital parameters, relative position, velocity, acceleration of the satellites involved in the collision, as well as the causes and impacts of the satellite collision, etc.

[0042] In some embodiments, for the acquisition of spatio-temporal big data of a flying object, subject to the requirements of relevant laws and regulations, it can also be automatically crawled from various websites by a web robot (such as a web crawler, etc.).

[0043] Step S103: Process the spatio-temporal big data of the flying object to form a data set with a data format adapted to the dynamic model.

[0044] Specifically, the data processing mentioned here includes but is not limited to noise removal and data smoothing, outlier detection and correction, missing data supplementation, and data format standardization, etc., and it can be implemented based on a big data processing framework (such as Apache Hadoop, Apache Spark, etc.).

[0045] For example, in the process of processing ground data obtained by ground-based measurement equipment, in order to improve the accuracy of ground data, noise should first be removed through filtering methods such as Kalman filtering and particle filtering. Among them, Kalman filtering is used to remove noise caused by environmental interference and sensor errors, while particle filtering is suitable for environments with non-linear and non-Gaussian noise to obtain more accurate orbit estimates in complex orbits and dynamic changes. Then, outlier detection is performed on the ground-based measurement data based on statistical analysis methods (such as Z-Score, IQR method) or machine learning methods (such as Isolation Forest), and the detected outliers are corrected or removed according to preset rules. For example, if the ground-based measurement data is outside the prediction range of the physical model, it can be marked as an outlier and corrected or resampled to reduce outliers caused by sensor failures or external interferences (such as orbit parameters that do not conform to physical laws). After that, based on interpolation methods (such as linear interpolation, Lagrange interpolation) and prediction methods of regression models (such as Autoregressive Integrated Moving Average Model ARIMA), missing values in the ground-based measurement data are filled to reduce the impact of sensor failures, environmental obstacles, or communication interruptions on the ground-based measurement data. Finally, the data of each monitoring station is standardized, including but not limited to unifying the coordinate system (such as WGS-84 coordinate system), time format (such as UTC time), and dimension of measurement units of the data. For example, the angular units (degrees, radians) and distance units (kilometers, meters) used by different ground stations are unified into standard units to overcome the problem of inconsistent data formats caused by differences in equipment and technical standards of different ground monitoring stations and ensure that the data format of the formed data set is compatible with the dynamic model.

[0046] Further, to solve the problems of limited resources and slow processing speed of traditional information systems, step S103 further includes: when the resource amount required for data processing exceeds the total resources currently available in a specific cloud cluster, judging the availability and scalability of the physical server cluster; if the physical server cluster is available and supports expansion, deploying virtual machine instances for data processing on the physical server cluster.

[0047] It should be noted that this step is based on the utilization of virtualization technology in the cloud computing platform. By centrally managing and scheduling computing resources (including servers, storage devices, network resources, etc.), such as abstracting physical server resources into computable units that can be allocated on demand, the resource quota can be dynamically adjusted according to real-time data processing requirements, realizing the elastic expansion of computing resources and solving the problem of insufficient computing power in traditional methods.

[0048] Specifically, in the design of the elastic scaling strategy, there are three scaling modes: horizontal scaling, vertical scaling, and hybrid scaling. Among them, horizontal scaling is based on a stateless computing node pool (such as Kubernetes Pod), and realizes the expansion of parallel computing capabilities by dynamically increasing or decreasing the number of nodes; vertical scaling relies on virtual machine live migration technology (such as QEMU / KVM) to adjust the resource quota of a single node online, and is suitable for tasks that rely on high throughput of a single node (such as Kalman filter iteration); hybrid scaling combines the high fault tolerance of horizontal scaling and the low latency advantage of vertical scaling, and uses reinforcement learning (such as Q-Learning) to dynamically select the optimal scaling path.

[0049] It should be noted that in this embodiment, the implementation of the elastic scaling mechanism is based on the real-time collection of CPU utilization rate (U CPU ), memory occupancy rate (U Mem ), and network transmission time (T Net ), as well as the quantification of the change in the amount of resources required for data processing needs. For example, the indicators are collected in real time through a distributed monitoring system (such as Prometheus), and the load change is quantified through the weighted comprehensive indicator L, so as to respond flexibly when the resource requirements change. Specifically, the weighted comprehensive indicator L can be determined according to formula (1) as: L = α ⋅ U CPU + β ⋅ U Mem + γ ⋅ T Net (1) Among them, the weight coefficients α, β, and γ are determined through historical data regression analysis.

[0050] In some embodiments, through multiple regression analysis of historical data, α is 0.6, β is 0.3, and γ is 0.1.

[0051] In this way, when the information system (such as a cloud computing information system, etc.) to which the method for evaluating the collision risk of on-orbit spacecraft based on the elastic scaling mechanism is applied faces constellation data above a large scale, it can not only automatically detect the load situation of computing resources and immediately call more computing nodes to join the processing, but also quickly deploy new virtual machine instances on a physical server cluster with sufficient computing resources to form a supplementary virtual cluster, ensuring that even when the data volume surges or the computing demand changes suddenly, the information system can also respond to the non-steady computing demand in data processing with an efficient and stable operating state and complete the task of evaluating the collision risk of on-orbit spacecraft.

[0052] In some embodiments, in the dynamic resource allocation algorithm, the elastic scaling trigger mechanism sets a dynamic threshold based on statistical process control (SPC). For example, when the CPU utilization rate exceeds the set threshold (such as μ + 3σ, where μ is the historical mean and σ is the standard deviation), the system applying the method disclosed in this application will trigger an expansion operation. Specifically, in terms of the design of the load threshold and the elastic scaling boundary, first, the system needs to be constrained according to the service level agreement (SLA), and then the upper limit of resource utilization is inversely deduced to ensure that a specified proportion of tasks can be completed within the specified time. For example, if the service level agreement requires that 99% of the tasks be completed within 10 seconds, then the resource allocation and threshold setting of the system will be optimized around this requirement. In addition, to avoid latency problems caused by cold starts, a predictive scaling strategy using long short-term memory networks (LSTM) can also be adopted to predict future load trends, thereby preheating resources in advance (Pre-warming) to improve the system response ability.

[0053] Step S104: Import the data set into the kinetic model, and through convolutional network calculation, extract the characteristics and patterns of specific flying objects that affect the flight of the target spacecraft.

[0054] It should be noted that the characteristics of the specific flying objects mentioned here include but are not limited to the flying object ID, name, orbital altitude, working frequency band, overflight time, flight speed, etc., and the patterns of the specific flying objects include but are not limited to flight patterns and attitude control patterns, etc.

[0055] Step S105: According to the characteristics and patterns of the specific flying objects, use the space collision model to real-time evaluate the relative proximity between the specific flying object and the target spacecraft.

[0056] It should be noted that the relative proximity mentioned here includes relative distance, relative speed, and relative direction.

[0057] Step S106: Generate evaluation information and warning information according to the relative proximity.

[0058] Specifically, in step S106, if the relative proximity is less than or equal to the preset threshold, evaluation information and warning information for requesting adjustment of the target spacecraft are generated; if the relative proximity is greater than the preset threshold, evaluation information and warning information for requesting adjustment of the target spacecraft are not generated.

[0059] For the convenience of understanding the inventive concept of this application, for the evaluation of the relative proximity between a specific flying object and a target spacecraft through the space collision model, please refer to Figure 2In this model, the target spacecraft's flight trajectory is C1, and the simulated trajectory of the specific object's motion is C2. P1 and P2 are the two intersection points of the specific object and the target spacecraft during rendezvous. P1 can be denoted as the first intersection point of C1 and C2, and P2 can be denoted as the second intersection point of C1 and C2. C2 is derived through computer simulation based on the characteristics and patterns of the specific object. Thus, when personnel, using the spatial collision model, know in advance that the target spacecraft and the specific object are in a conflicting or colliding path, they calculate the target spacecraft's adjustment time and position based on the time and position of the rendezvous between C1 and C2. Then, through radio remote control, the collision avoidance engine on the target spacecraft is activated or deactivated, allowing the target spacecraft to quickly adjust its orbit or change its attitude to avoid a collision with the specific object. It should be noted that the time mentioned here refers to ephemeris time, such as Coordinated Universal Time (UTC). Specifically, according to what the inventors have learned, when using a more complex non-Gaussian spatial collision model, setting the collision threshold to 10 meters, the number of random experiments to 1,000, and interpolating and extrapolating the collision probability field, the average error of collision warning can be reduced to below 1% and the accuracy can be increased by more than 6 percentage points.

[0060] Embodiment 2 Based on the same inventive concept as the above embodiments, please refer to Figure 3 The embodiment of the second aspect of the present application provides a system for assessing the collision risk of on-orbit spacecraft based on an elastic expansion mechanism, which can be implemented in the form of hardware and / or software and can be integrated into an electronic device that carries the real-time assessment and warning functions of on-orbit spacecraft collision risk. Specifically, the system for assessing the collision risk of on-orbit spacecraft based on an elastic expansion mechanism includes a processor 12 and a memory 11 storing a computer program (such as an on-orbit spacecraft collision risk assessment program), wherein: Figure 3 The processor 12 shown in the figure is not used to indicate that the number of processors 12 is one, but is only used to indicate the positional relationship of the processor 12 relative to other devices. In actual applications, the number of processors 12 can be one or more; similarly, Figure 3 The memory 11 shown in the figure has the same meaning, that is, it is used only to refer to the positional relationship of the memory 11 relative to other devices. In actual applications, the number of memories 11 can be one or more. When the processor 12 executes the computer program, the steps of the method for assessing the collision risk of an on-orbit spacecraft based on the elastic expansion mechanism are implemented.

[0061] Specifically, the memory 11 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The memory 11 described in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memories.

[0062] The memory 11 in the embodiments of the present application is used to store various types of data to support the operation of the system for evaluating the collision risk of on-orbit spacecraft based on the elastic expansion mechanism. Examples of such data include: any computer programs for operating on the system for evaluating the collision risk of on-orbit spacecraft based on the elastic expansion mechanism, such as operating systems and application programs; contact data; phone book data; messages; pictures; videos, etc. Among them, the operating system contains various system programs, such as the framework layer, the core library layer, the driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application programs can include various application programs, such as a Media Player, a Browser, etc., for implementing various application services. Here, the program for implementing the method of the embodiments of the present application can be included in the application programs.

[0063] The system for evaluating the collision risk of on-orbit spacecraft based on the elastic expansion mechanism may further include: at least one network interface 13. Each component in the system for evaluating the collision risk of on-orbit spacecraft based on the elastic expansion mechanism is coupled together through a bus system 14. The bus system 14 is used to realize the connection and communication between these components. In addition to including a data bus, the bus system 14 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clear illustration, in Figure 3 all kinds of buses are labeled as the bus system 14.

[0064] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. As long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification. Specifically, each step and module of the method and system disclosed in the present application can be implemented by hardware, software, or a combination thereof. If implemented in hardware, the various illustrative steps, modules, and circuits described in conjunction with the present application can be implemented or executed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic components, hardware components, or any combination thereof. The general-purpose processor can be a processor, a microprocessor, a controller, a microcontroller, or a state machine, etc. If implemented in software, the various illustrative steps and modules described in conjunction with the present application can be stored on a computer-readable medium or transmitted as one or more instructions or codes.

[0065] As described above, it is only the specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed by the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism, characterized in that The method includes the following steps: Select corresponding observation components, dynamic models, and space collision models; Obtain the spatio-temporal big data of the flying object through the observation components; Perform data processing on the spatio-temporal big data of the flying object to form a data set with a data format adapted to the dynamic model; Import the data set into the dynamic model, and through convolutional network calculation, extract the characteristics and patterns of specific flying objects that affect the flight of the target spacecraft; According to the characteristics and patterns of the specific flying object, use the space collision model to real-time evaluate the relative proximity of the specific flying object to the target spacecraft; Generate evaluation information and warning information according to the relative proximity; 2. The method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to claim 1, characterized in that, It further includes: Receive indication information, where the indication information includes the target spacecraft ID, time range, and accuracy requirements.

3. The method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to claim 2, wherein It further includes: Set the load threshold and resource quota of a specific cloud cluster according to the indication information.

4. The method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to claim 1, wherein The spatio-temporal big data of the flying object includes space object tracking data, space environment data, and collision history data.

5. The method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to claim 1, wherein When the resource amount required for data processing exceeds the total resources currently available in a specific cloud cluster, judge the availability and scalability of the physical server cluster; If the physical server cluster is available and supports expansion, deploy virtual machine instances for data processing on the physical server cluster.

6. The method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism as claimed in claim 1, wherein The data processing includes noise removal and data smoothing, outlier detection and correction, missing data supplementation, and data format standardization.

7. The method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to claim 1, wherein The characteristics of the specific flying object include the flying object ID, name, orbital altitude, working frequency band, overflight time, and flying speed, and the pattern of the specific flying object includes the flight pattern and attitude control pattern.

8. The method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to claim 1, characterized in that, The relative proximity includes relative distance, relative speed, and relative direction.

9. The method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism according to claim 1, wherein If the relative proximity is less than or equal to a preset threshold, generate evaluation information and warning information for requesting adjustment of the target spacecraft; If the relative proximity is greater than the preset threshold, do not generate evaluation information and warning information for requesting adjustment of the target spacecraft.

10. A system for evaluating the collision risk of on-orbit spacecraft based on an elastic expansion mechanism, characterized in that, The system includes a processor and a memory communicatively connected to the processor. The memory stores an evaluation program executable by the processor. When the evaluation program stored in the memory is executed by the processor, the processor executes the method for evaluating the collision risk of an on-orbit spacecraft based on an elastic expansion mechanism as described in any one of claims 1 to 9.

Images