Node satellite simulation method and device and storage medium

Abstract

The invention relates to a nodal satellite simulation method and device and a storage medium, and the method comprises the steps: obtaining a satellite simulation demand; analyzing and processing the satellite simulation demand to obtain structured scene information; the structured scene information comprises finite function blocks for realizing satellite simulation requirements; obtaining a plurality of preset simulation process nodes, and obtaining node strategy subsets corresponding to the simulation process nodes; aiming at each simulation process node, searching a target node strategy matched with the structured scene information from each node strategy subset in sequence, and generating a target simulation model based on the target node strategy; and inputting simulation parameters corresponding to the satellite simulation requirements into the target simulation model, performing satellite simulation processing, and generating a satellite simulation result. According to the method and the device, the problems of poor scene expansibility and low repeated configuration efficiency in satellite digital twinborn simulation are solved, and the scene expansibility and the configuration efficiency of the satellite digital twinborn simulation are remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of satellite simulation digital twins, and in particular to a node-based satellite simulation method, device and storage medium. Background Art

[0002] With the continuous development of aerospace technology, the complexity and functionality of satellite systems are increasing, and the demand for simulation and simulation of satellite systems is becoming more and more urgent. Traditional satellite simulation methods often rely on specific scenarios and models, and are difficult to adapt to complex and changing simulation needs, especially when facing large-scale constellation simulation, traditional methods seem to be unable to cope with it.

[0003] With the rise of digital twin technology, new opportunities have been brought to the field of satellite simulation. By building a digital mirror of the satellite system, digital twin technology can reflect the physical state and behavior of the satellite in real time and accurately, and predict its future change trend. This technology not only provides strong support for the design, manufacturing, testing and maintenance of satellite systems, but also provides new ideas and methods for constellation simulation. However, we still face many challenges when applying digital twin technology to constellation simulation. Constellation simulation involves the collaborative work of multiple satellites, and the interactions between them are complex and changeable. It is difficult for traditional methods to fully and accurately simulate these interactions. In addition, with the expansion of the constellation scale and the continuous increase in simulation scenarios, it is difficult for traditional methods to enumerate all possible scenarios, and it is impossible to quickly adapt to the emergence of new scenarios, which greatly limits the efficiency and accuracy of simulation.

[0004] At present, no effective solution has been proposed to the problems of poor scene scalability and low efficiency of repeated configuration in satellite digital twin simulation of related technologies. Summary of the invention

[0005] The embodiments of the present application provide a node-based satellite simulation method, device and storage medium to at least solve the problems of poor scene scalability and low efficiency of repeated configuration in satellite digital twin simulation in related technologies.

[0006] In a first aspect, an embodiment of the present application provides a node-based satellite simulation method, including: Obtain satellite simulation requirements; The satellite simulation requirement is parsed and processed to obtain structured scene information; the structured scene information includes limited function blocks for realizing the satellite simulation requirement; Acquire multiple preset simulation process nodes, and acquire node strategy subsets corresponding to each of the simulation process nodes; For each of the simulation process nodes, sequentially retrieving a target node strategy that matches the structured scenario information from each of the node strategy subsets, and generating a target simulation model based on the target node strategy; The obtained simulation parameters corresponding to the satellite simulation requirements are input into the target simulation model, satellite simulation processing is performed, and satellite simulation results are generated.

[0007] In some embodiments, for each simulation process node, sequentially retrieving a target node strategy matching the structured scenario information from each node strategy subset, and generating a target simulation model based on the target node strategy, includes: Acquire a preset simulation model set, and based on the satellite simulation requirement, retrieve a preset simulation model corresponding to the satellite simulation requirement from the simulation model set; If the predetermined simulation model is retrieved, the predetermined simulation model is determined as the target simulation model; If the retrieval of the predetermined simulation model fails, then for each simulation process node, a target node strategy matching the structured scenario information is retrieved from each node strategy subset in turn, and the target simulation model is generated based on the target node strategy.

[0008] In some embodiments, the method further comprises: In the case where the target simulation model is generated based on the target node strategy, the target simulation model is dynamically updated to the simulation model set to generate a new simulation model set.

[0009] In some embodiments, for each simulation process node, sequentially retrieving a target node strategy that matches the structured scenario information from each node strategy subset includes: Acquire historical simulation data, and establish a strategy allocation model based on the historical simulation data; The structured scenario information is input into the strategy allocation model for matching processing, and the target node strategy for each simulation process node is output.

[0010] In some embodiments, for each simulation process node, sequentially retrieving a target node strategy that matches the structured scenario information from each node strategy subset includes: Based on the structured scenario information, determining a retention node from each of the process nodes, and determining a retention strategy subset corresponding to the retention node in each of the node strategy subsets; For each of the retained nodes, the target node strategy matching the structured scenario information is retrieved from the retained strategy subset in turn.

[0011] In some embodiments, the method further comprises: Using a preset process manager, detecting the satellite simulation result; If the satellite simulation result is detected, it is confirmed that the satellite simulation process has been completed, and the operating resources of each simulation process node are released; and / or, During the satellite simulation process, if a process termination instruction is received, the process manager is used to execute termination processing on any simulation process node in the target simulation model.

[0012] In some embodiments, the step of inputting the obtained simulation parameters corresponding to the satellite simulation requirements into the target simulation model, performing satellite simulation processing, and generating satellite simulation results includes: Using the target simulation model and based on the simulation parameters, running a plurality of the target node strategies in parallel, and storing the simulation process data generated in the process of running each of the target node strategies in a simulation database; The simulation process data in the simulation database are called to generate the satellite simulation result.

[0013] In some embodiments, calling each of the simulation process data in the simulation database to generate the satellite simulation result includes: According to the execution order information of each of the target node strategies, determining, among the target node strategies, a first node strategy at a first call priority and a second node strategy at a second call priority; the second call priority is higher than the first call priority; storing first simulation process data generated in the process of running each of the first node strategies in a first simulation database; When the second node strategy is run in parallel, second simulation process data is generated based on the called first simulation process data of the first simulation database, and the second simulation process data is stored in the second simulation database.

[0014] In a second aspect, an embodiment of the present application provides a node-based satellite simulation device, including: Requirements parsing module, used to obtain satellite simulation requirements; The requirement parsing module is further used to parse the satellite simulation requirement to obtain structured scenario information; the structured scenario information is used to indicate limited functional blocks that realize the satellite simulation requirement; A model generation module, used to obtain a plurality of preset simulation process nodes, and obtain a node strategy subset corresponding to each of the simulation process nodes; The model generation module is also used to retrieve, for each simulation process node, a target node strategy that matches the structured scenario information from each node strategy subset in turn, and generate a target simulation model based on the target node strategy; The simulation operation module is used to input simulation parameters corresponding to the satellite simulation requirements into the target simulation model, perform satellite simulation processing, and generate satellite simulation results.

[0015] In a third aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the node-based satellite simulation method as described in the first aspect above.

[0016] Compared with the related art, the node-based satellite simulation method, device and storage medium provided in the embodiments of the present application solve the problems of poor scene scalability and low efficiency of repeated configuration in satellite digital twin simulation through node-based simulation process and strategic configuration, and significantly improve the scene scalability and configuration efficiency of satellite digital twin simulation. The details of one or more embodiments of the present application are presented in the following drawings and descriptions to make other features, purposes and advantages of the present application more concise and easy to understand. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 It is a hardware structure block diagram of a terminal of the node-based satellite simulation method of an embodiment of the present application; Figure 2 is a flow chart of a node-based satellite simulation method according to an embodiment of the present application; Figure 3 is a preferred flow chart of a node-based satellite simulation method according to an embodiment of the present application; Figure 4 is an example process node flow chart of a node-based satellite simulation method according to an embodiment of the present application; Figure 5 It is a simulation model configuration flow diagram of the node-based satellite simulation method according to an embodiment of the present application; Figure 6 is a schematic diagram of a common simulation task of a node-based satellite simulation method according to an embodiment of the present application; Figure 7 It is a schematic diagram of a pure instruction simulation task of a node-based satellite simulation method according to an embodiment of the present application; Figure 8 It is a schematic diagram of a common simulation task operation flow of a node-based satellite simulation method according to an embodiment of the present application; Fig. 9 It is a structural block diagram of a node-based satellite simulation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

[0019] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0020] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation, and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application means greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in the present application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0021] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 1 1 is a hardware structure diagram of a terminal of the node-based satellite simulation method of an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0022] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the noded satellite simulation method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0023] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0024] This embodiment provides a node-based satellite simulation method. Figure 2 is a flowchart of a node-based satellite simulation method according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps: Step S201, obtaining satellite simulation requirements; Among them, satellite simulation requirements submitted by users can be received through a user interface or interface. The satellite simulation requirements may include detailed information about the purpose of simulation, required accuracy, specific scenarios, etc. The system records and stores these requirements in the form of data for use in subsequent steps.

[0025] Step S202, parsing the satellite simulation requirements to obtain structured scene information; the structured scene information includes limited function blocks for realizing the satellite simulation requirements; Among them, the obtained satellite simulation requirements are carefully analyzed by using analytical algorithm models or manual processing, and the finite function blocks required to realize the requirements are extracted. Each finite function block corresponds to a specific step or module to realize the requirements. Each finite function block is defined in detail, including its function, input, output and interface relationship with other function blocks, and the extracted function blocks are organized according to logical relationships and sequence to form structured scene information.

[0026] For example, a satellite simulation requirement is "synchronous operation task of the three-body constellation, reproduction of the constellation operation during 24:00 on February 26 to February 28, reproduction of the orbit, topology and instruction execution status of the constellation in the historical mission for fault analysis". The satellite simulation requirement information is automatically or manually decomposed to obtain a finite number of functional blocks for realizing the satellite simulation requirement, which are: Functional block one, high-precision orbit data; Functional description: Import historical orbit data to ensure data accuracy and completeness; Input: Historical orbit data file; Output: Orbital data model after import; Interface relationship: Data transfer with subsequent functional blocks. Functional block two, topology restoration; Functional description: Generate a historical topology map by timestamp to show the relative position and relationship of each satellite in the constellation; Input: Orbital data model after import; Output: Historical topology map sequence; Interface relationship: Receive the output of function block one and provide input for function block three. Function block three, instruction playback; Function description: issue instructions according to the historical time series, simulate the instruction execution process in the historical task; Input: historical instruction data and time series information; Output: instruction execution results and state changes; Interface relationship: receive the output of function block two as background information, and interact with other system modules to execute instructions; Function block four: data synchronization; Function description: compare historical telemetry data to verify consistency and ensure that the simulation results are consistent with the actual situation; Input: real-time telemetry data and historical telemetry data during the simulation process; Output: data consistency verification report; Interface relationship: receive real-time data of the simulation system and compare and verify it with historical data. By organizing the information of each limited function block analyzed above, structured scenario information can be generated: "high-precision orbit data, import historical orbit data; topology restoration, generate historical topology map according to timestamp; instruction playback, issue instructions according to historical time series; data synchronization, compare historical telemetry data to verify consistency".

[0027] Structured scenario information is a structured decomposition of satellite simulation requirements, which is used to clarify the specific technical implementation requirements of simulation tasks. Structured scenario information is a bridge between user requirements and node-based simulation processes. By breaking down complex requirements into limited functional modules and configurable policy constraints, it provides standardized input for the matching of subsequent process node strategies. Satellite simulation requirements are endless, but the scenarios in these requirements are limited. This step breaks down complex requirements into limited and specific functional blocks, simplifies the subsequent policy matching process, and improves the flexibility and configurability of the simulation, enabling the system to cope with diverse simulation requirements.

[0028] Step S203, obtaining a plurality of preset simulation process nodes, and obtaining a node strategy subset corresponding to each simulation process node; Among them, the simulation process node is a unit with independent functions and can run in parallel during the satellite simulation process. Each node is responsible for completing specific functions and works together through strategic configuration and asynchronous communication mechanisms to cover the entire simulation life cycle. Multiple simulation process nodes are pre-defined in the system, such as satellite orbit generation nodes, satellite-to-ground link nodes, inter-satellite link nodes, topology generation nodes, control instruction parsing nodes, constellation initialization nodes, control instruction issuance nodes, telemetry data processing nodes, etc.

[0029] The node strategy subset is a collection of specific implementation strategies that can be selected for each simulation process node during the simulation process, which is used to meet the needs of different simulation scenarios. Each node strategy subset contains several node strategies. For example, the node strategy subset corresponding to the satellite orbit generation node includes no orbit strategy (no orbit data generation), predicted orbit strategy (simulation model generates orbit), and orbit planning strategy (import external orbit data); the node strategy subset corresponding to the topology generation node includes no topology strategy (no topology generation), simulated topology strategy (dynamic generation based on model), and real-time topology strategy (import historical topology data). This step provides a rich selection of nodes and strategies, allowing the system to flexibly respond to different simulation scenarios.

[0030] Step S204, for each simulation process node, sequentially retrieving a target node strategy that matches the structured scenario information from each node strategy subset, and generating a target simulation model based on the target node strategy; Among them, according to the structured scene information obtained in the above steps, each simulation process node is traversed in turn. For each simulation process node, the target node strategy that matches the structured scene information is retrieved from its corresponding node strategy subset. Then, according to these target node strategies, a complete target simulation model is generated. For example, the structured scene information includes "high-precision orbit data, importing historical orbit data; topology restoration, generating historical topology maps according to timestamps; instruction playback, issuing instructions according to historical time series; data synchronization, comparing historical telemetry data to verify consistency", then the matching target node strategies are orbit planning strategy, simulation topology strategy, time loop strategy, and live synchronization strategy. Specifically, the satellite orbit generation node selects the orbit planning strategy (importing historical orbit data); the topology generation node selects the simulation topology strategy (generating historical topology maps according to timestamps); the control instruction parsing node selects the time loop strategy (issuing instructions according to historical time series); the telemetry data processing node selects the live synchronization strategy (comparing historical telemetry data to verify consistency).

[0031] The target simulation model is a node strategy combination of multiple target node strategies that match the structured scenario information. This step of building the target simulation model implements on-demand strategy combination and dynamic construction of the simulation model, so that the system can generate appropriate models according to specific simulation requirements and quickly respond to new scenario requirements.

[0032] Step S205 , inputting the obtained simulation parameters corresponding to the satellite simulation requirements into the target simulation model, performing satellite simulation processing, and generating satellite simulation results.

[0033] The obtained simulation parameters corresponding to the satellite simulation requirements (such as simulation task number, constellation information, simulation task type, etc.) are input into the target simulation model. Then, the simulation process is started, the target simulation model (combination of target node strategies) is run, and the satellite simulation results are generated. The satellite simulation results may include orbital data, topological data, simulation events, control instructions and their execution, telemetry data, etc. This step uses the target simulation model to start complex simulation tasks with one click, realizes the automation and intelligence of satellite simulation, improves the efficiency and accuracy of simulation, and the generated satellite simulation results provide users with valuable reference information, which helps users to make subsequent analysis and decisions.

[0034] Through the above steps, compared with the traditional technology that relies on fixed simulation processes and configurations, it is difficult to adapt to the ever-changing simulation needs, and each simulation needs to be reconfigured, which is inefficient. This application divides the simulation process into multiple independent simulation process nodes and provides a variety of optional strategies for each node. Flexible expansion of simulation scenarios; after obtaining the satellite simulation requirements, structured scene information is obtained through parsing and processing, and matching target node strategies are retrieved from a preset node strategy subset based on this information, so as to quickly generate a target simulation model that meets specific requirements. In this process, there is no need to make large-scale modifications to the entire simulation system, and only the strategies of the relevant nodes need to be adjusted to adapt to the new scenario. In addition, since multiple node strategies are preset, repeated configuration work is avoided during each simulation, which greatly improves the simulation efficiency. Therefore, this application effectively solves the problems of poor scene scalability and low efficiency of repeated configuration in satellite digital twin simulation, and significantly improves the scene scalability and configuration efficiency of satellite digital twin simulation.

[0035] In some of the embodiments, for each simulation process node, a target node strategy matching the structured scenario information is retrieved from each node strategy subset in turn, and a target simulation model is generated based on the target node strategy, including: Obtain a preset simulation model set, and based on the satellite simulation requirement, retrieve a preset simulation model corresponding to the satellite simulation requirement from the simulation model set; If a predetermined simulation model is retrieved, the predetermined simulation model is determined as a target simulation model; If the retrieval of the established simulation model fails, for each simulation process node, the target node strategy matching the structured scenario information is retrieved from each node strategy subset in turn, and the target simulation model is generated based on the target node strategy.

[0036] Among them, according to known satellite simulation requirements and scenarios, a set of simulation model collections are pre-built. These simulation models are composed of different simulation process nodes and their strategies. The simulation models in the simulation model collection can solve some known satellite simulation requirements.

[0037] When a new satellite simulation requirement is received, the requirement is parsed, key structured scene information is extracted, and the parsed structured scene information is matched with each simulation model in the simulation model set. The matching process is mainly based on the similarity of the scene information and the scope of application of the model. If a simulation model that highly matches the simulation requirement is retrieved, it will be determined as the established simulation model corresponding to this satellite simulation requirement; if a simulation model that highly matches the simulation requirement is not retrieved, then based on the structured scene information, for each simulation process node, the target node strategy that matches the target scene information will be retrieved from the corresponding node strategy subset, and by combining these target node strategies, a target simulation model that meets specific simulation requirements is dynamically generated.

[0038] This step can significantly reduce the simulation preparation time by presetting a simulation model set and retrieving an established simulation model from it. Once the established simulation model is retrieved, it can be directly used for simulation without reconfiguration, which greatly improves the simulation efficiency. When the established simulation model cannot meet the simulation requirements, the target simulation model can be flexibly generated through the dynamic combination of node strategies to adapt to new simulation scenarios. This method enhances the scenario adaptability of the simulation system, enabling it to better cope with complex and changeable satellite simulation requirements. In addition, the complexity of the simulation configuration is reduced through the node-based and strategy-based simulation process design. Users do not need to have an in-depth understanding of the underlying implementation of the simulation system, but only need to select the appropriate node strategy according to the simulation requirements, thereby lowering the usage threshold and improving the ease of use of the simulation system.

[0039] In some embodiments, the method further comprises: When the target simulation model is generated based on the target node strategy, the target simulation model is dynamically updated to the simulation model set to generate a new simulation model set.

[0040] Among them, when the established simulation model cannot meet the simulation requirements, according to the simulation requirements, for each simulation process node, the target node strategy that matches the structured scenario information is matched from each node strategy subset in turn, and the target node strategy is combined into a target simulation model. After the new target simulation model is generated, it is dynamically updated to the simulation model set through the programming interface or data management module to generate a new simulation model set. In this step, by dynamically updating the simulation model set, the system can quickly respond to new simulation requirements without large-scale reconstruction or upgrading of the entire system, thereby improving the flexibility and response speed of the simulation; the dynamic update mechanism enables the system to continuously iterate and optimize the simulation model. With the continuous advancement of technology and the continuous changes in simulation requirements, the system can continuously introduce new node strategies and simulation models to adapt to new challenges and requirements.

[0041] In some of the embodiments, for each simulation process node, a target node strategy matching the structured scenario information is retrieved from each node strategy subset in turn, including: Obtain historical simulation data and establish a strategy allocation model based on the historical simulation data; The structured scenario information is input into the strategy allocation model for matching processing, and the target node strategy for each simulation process node is output.

[0042] Among them, the above-mentioned strategy allocation model is used to provide a mapping relationship between structured scenario information and node strategy, and can automatically or manually achieve node strategy matching. For this strategy allocation model, the establishment process can be: extract historical simulation data from the database of the simulation system. These data should contain information such as operation records, parameter settings, output results, etc. of each simulation process node under different simulation scenarios, and preprocess the historical simulation data, including data cleaning, formatting, normalization, etc., for subsequent analysis and use. Then, based on the historical simulation data, select a suitable machine learning or statistical learning method (such as neural network, etc.) to establish a strategy allocation model. For example, construct a neural network model, input layer: determine the input features of the neural network according to the description information of the simulation scenario, and the input features may include the number of satellites, orbit type, communication requirements, etc.; hidden layer: set multiple hidden layers, each layer contains a certain number of neurons, and the number of neurons and the number of layers can be adjusted according to the complexity of the data and the performance of the model; output layer: the number of neurons in the output layer is the same as the number of simulation process nodes, and each neuron corresponds to the target node strategy of a node. Then divide the preprocessed historical simulation data into training set and test set, use the training set to train the neural network model, adjust the weight and bias of the model through the back propagation algorithm, so that the output of the model is as close as possible to the actual target node strategy; during the training process, you can use cross-validation and other methods to evaluate the performance of the model to prevent overfitting. Use the test set to evaluate the trained neural network model, calculate the model's accuracy, recall rate, F1 value and other indicators; based on the evaluation results, judge whether the model meets the requirements. If the model performance is not good, you can adjust and optimize the model. The specific optimization options are as follows: adjust the structure of the neural network, such as increasing or decreasing the number of hidden layers, the number of neurons, etc.; try different activation functions, optimization algorithms, etc. to improve the performance of the model; use more historical simulation data for training to improve the generalization ability of the model.

[0043] After the strategy allocation model is established, the node strategy matching of the above-mentioned structured scenario information can be performed based on the strategy allocation model. Specifically, in the matching process, the input features of the strategy allocation model can include the description information of the simulation scenario (such as the number of satellites, orbit type, communication requirements, etc.), and the output is the target node strategy for each simulation process node. The strategy allocation model obtained through training enables it to accurately predict the best node strategy combination based on the input structured scenario information. When there is a new simulation requirement, the structured scenario information (such as specific satellite configuration, mission requirements, etc.) is input into the strategy allocation model. The model performs matching processing based on the input scenario information through the internal algorithm, and outputs the target node strategy for each simulation process node. The target node strategy output by the model is subsequently applied to the simulation process to generate a target simulation model. By establishing a strategy allocation model in this step, the best node strategy combination can be selected for the new simulation scenario quickly and accurately, avoiding the tedious process of manual selection and configuration, and improving the simulation efficiency; the strategy allocation model established based on historical simulation data can learn the optimal combination of node strategies in different scenarios, thereby optimizing the simulation results and making them closer to the real situation.

[0044] In some of the embodiments, for each simulation process node, a target node strategy matching the structured scenario information is retrieved from each node strategy subset in turn, including: Based on the structured scenario information, determine the retention nodes from each process node, and determine the retention strategy subset corresponding to the retention node in each node strategy subset; For each retained node, the target node strategy that matches the structured scenario information is retrieved from the retained strategy subset in turn.

[0045] Among them, according to the structured scenario information, the nodes that need to be run in the current scenario are selected from the predefined process nodes, that is, the retained nodes. These nodes are usually necessary to complete the simulation task and may be different in different simulation scenarios. For example, in the pure instruction simulation task scenario, it does not need to generate orbits, nor does it need satellite-to-ground links and inter-satellite links. At this time, the retained nodes are control instruction parsing nodes and constellation initialization nodes, and the corresponding target node strategies are no orbit strategy, no satellite-to-ground link node strategy, no inter-satellite link node strategy, only support time instruction parsing strategy, and pure instruction simulation initialization strategy. For each retained node, there is a corresponding retained strategy subset, and each retained strategy subset also contains several node strategies. These node strategies can cope with different types of simulation scenarios. For each retained node, the target node strategy that matches the structured scenario information is retrieved from the corresponding retained strategy subset in turn. The retrieved target node strategy will be the best strategy that each retained node should adopt in the current scenario. This step dynamically determines the retention nodes and retrieval target node strategies based on the structured scenario information, modularizes the node strategy, and selects the node strategy that best suits the current simulation scenario. This can optimize the simulation performance, reduce unnecessary computing overhead and resource waste, improve the efficiency and accuracy of the simulation, and can flexibly respond to different types of simulation requirements.

[0046] In some embodiments, the method further comprises: Use the preset process manager to check satellite simulation results; If the satellite simulation result is detected, it is confirmed that the satellite simulation process has been completed and the operating resources of each simulation process node are released; and / or, During the satellite simulation process, if a process termination instruction is received, the process manager is used to execute termination processing on any simulation process node in the target simulation model.

[0047] Among them, the preset process manager is responsible for monitoring the running status of each simulation process node. When all nodes complete their preset tasks and output the corresponding simulation results, the process manager will detect the status of each simulation process node by checking the status flag or output data of each node. The process manager can be an independent software module that communicates with each simulation process node and receives status updates from the nodes through polling, event triggering or message queue. Once the process manager confirms that all simulation process nodes have completed their tasks, it will trigger the resource release mechanism. The resource release mechanism can be implemented by calling the API provided by the operating system to close no longer needed processes, release memory, disconnect network connections, etc., to ensure the effective use of system resources. At the same time, the process manager can also record the completion status of the simulation task for subsequent query or statistics. During the satellite simulation process, if a process termination instruction is received from the user or other system, the process manager will immediately perform termination processing on any simulation process node in the target simulation model, which includes stopping the calculation of the node, saving the current state (if possible), and notifying other related nodes or systems. The abort process can be implemented by sending an abort signal to the node, setting an interrupt flag, or calling a specific abort function. The process manager ensures that all nodes can correctly respond to the abort instruction and release related resources after the abort. This step can avoid resource waste and improve the resource utilization of the overall system by timely releasing system resources that are no longer needed through the process manager; and the process manager can monitor the running status of the simulation process and take abort measures in time when an exception or error occurs, thereby enhancing the reliability of the system. Users can abort the simulation task at any time as needed without having to wait for the entire task to be completed, which improves the flexibility and satisfaction of users. In addition, the process manager can support the simultaneous execution of multiple simulation tasks, and ensure that each task has sufficient resources through effective resource management and task scheduling.

[0048] In some of the embodiments, simulation parameters corresponding to the satellite simulation requirements are input into the target simulation model, satellite simulation processing is performed, and satellite simulation results are generated, including: Using the target simulation model, based on simulation parameters, multiple target node strategies are run in parallel, and the simulation process data generated in the process of running each target node strategy is stored in the simulation database; Call each simulation process data in the simulation database to generate satellite simulation results.

[0049] Before the simulation starts, the simulation parameters (such as simulation task number, constellation information, simulation task type, etc.) are input into the target simulation model so that each node strategy can perform corresponding calculations and simulations according to these parameters. Each node strategy is executed independently, and data exchange and synchronization with other nodes are achieved through a preset simulation database, and multi-threading, multi-process or distributed computing technologies are used to achieve parallel operation of each node strategy. In addition, other communication mechanisms such as message queues and shared memory can also be used to achieve data exchange and synchronization between simulation process nodes.

[0050] In the process of running each node strategy, the generated simulation process data is stored in the simulation database in real time or periodically. According to the preset algorithm and model, the called simulation process data is processed and analyzed to generate the final satellite simulation results, which may include orbit trajectory diagrams, communication status diagrams, control instruction execution status reports, etc. This step can make full use of the system's computing resources, improve the parallelism and efficiency of the simulation, and shorten the simulation cycle by running multiple node strategies in parallel; storing the simulation process data in the database can realize centralized management and unified access of the data, and ensure the consistency and integrity of the data. At the same time, the database also provides a data backup and recovery mechanism to improve data security.

[0051] In some of the embodiments, calling various simulation process data in the simulation database to generate satellite simulation results includes: According to the execution order information of each target node strategy, determine, among the target node strategies, a first node strategy with a first call priority and a second node strategy with a second call priority; the second call priority is higher than the first call priority; storing first simulation process data generated in the process of running each first node strategy in a first simulation database; When the second node strategy is run in parallel, second simulation process data is generated based on the first simulation process data of the called first simulation database, and the second simulation process data is stored in the second simulation database.

[0052] Among them, in order to determine the execution order of the node strategy, the execution order of each node can be clarified in the design stage of the simulation process, which can be achieved by defining the node dependencies and preconditions. For example, some nodes (such as satellite-to-ground link nodes, intersatellite link nodes, and topology generation nodes) depend on orbital data, so these nodes need to be executed after the satellite orbit generation node. At the beginning of the simulation, a suitable simulation model is selected according to the simulation requirements, and then according to the determined execution order, the first node strategy with the first call priority is first run. In the process of running these node strategies, corresponding simulation process data, such as orbital data, topology data, etc., will be generated. These first simulation process data are stored in the first simulation database so that subsequent node strategies can access and use them when needed. After the first node strategy is completed, according to the execution order information, the second node strategy with the second call priority is run in parallel. When these second node strategies are running, they may need to access the first simulation process data generated by the first node strategy. At this time, the required data can be obtained by calling the first simulation database. Based on the acquired first simulation process data, the second node strategy will generate new simulation process data (second simulation process data) and store these data in the second simulation database. This step can more effectively utilize computing resources by reasonably dividing nodes and defining the execution order. For example, when running node strategies in parallel, the parallel computing capabilities of multi-core processors can be fully utilized. By running node strategies in parallel, the execution time of simulation tasks can be significantly reduced. In particular, when the data dependencies between certain node strategies are properly handled, the simulation efficiency can be further improved.

[0053] The embodiments of the present application are described and illustrated below through preferred embodiments.

[0054] Figure 3 is a preferred flow chart of the node-based satellite simulation method according to an embodiment of the present application, such as Figure 3 As shown, the node-based satellite simulation method includes the following steps: Step S301, building a process that covers the entire life cycle of digital twin constellation simulation; Among them, the process framework can support all currently known digital twin simulation requirements, and will start and manage corresponding nodes as needed. The process covers the entire life cycle of digital twin constellation simulation tasks.

[0055] Step S302, defining each node in the process, these nodes reasonably divide the constellation simulation life cycle, and each node completes a specified function; The process clearly divides multiple nodes. For example, Figure 4 is an example process node flow chart of the node-based satellite simulation method according to an embodiment of the present application, such as Figure 4As shown, an example process is defined, in which the following eight nodes are defined: satellite orbit generation node, satellite-to-ground link node, inter-satellite link node, topology generation node, control instruction parsing node, constellation initialization node, control instruction issuing node, and telemetry data processing node. Each node completes a relatively independent task.

[0056] The satellite orbit generation node is responsible for generating orbit data for each satellite in the constellation. The orbit data contains the location information of the satellite at each moment. The satellite-to-ground link node uses the satellite-to-ground communication model to determine whether a satellite can establish a satellite-to-ground link node with a ground station when it is at a specific position. The inter-satellite link node uses the inter-satellite communication model to determine whether the satellite can communicate based on the positions of the two satellites. The topology generation node is responsible for generating the topology map of the entire constellation at a specified moment. The control instruction parsing node is used to refine the user's control instruction requirements to which instructions are executed at which moments in the entire simulation life cycle. The constellation initialization node refers to resetting the constellation state at the beginning of the simulation to make the constellation state more in line with the actual situation, such as satellite startup, device power-on, device communication, system version, etc. The control instruction issuing node refers to issuing instructions to satellite equipment through simulation. The telemetry data processing node is responsible for receiving and formatting the telemetry data returned by the satellite equipment.

[0057] Step S303, each node of the process has at least one node strategy; Among them, process nodes can run in parallel and communicate with each other. Each node runs independently to reduce coupling. The dependent parties are notified through asynchronous methods such as messages and database data that the resources are ready, and the business that was suspended due to resource waiting can continue to execute.

[0058] Although the functions of multiple nodes in the process are independent of each other, they have data dependencies. For example, in the example process, the satellite-to-ground link node, intersatellite link node, and topology generation node depend on orbit data; in the example process, the constellation initialization node and control instruction parsing node depend on the topology generation node. Although serial execution of each node can solve the data dependency very well, the coupling between the nodes will be very high and the mutual influence will be great. In addition, the efficiency of the simulation will be very low. Therefore, the independence of the functions of each node provides a good foundation for parallel operation, which can reduce mutual influence and greatly improve efficiency. In order to deal with data dependencies, the process needs to provide a communication mechanism, which can be achieved through messages or database data changes.

[0059] Step S304, providing a process solution management mechanism, and configuring multiple process solutions according to known requirements, the solution is a simulation model; in, Figure 5 FIG. 1 is a schematic diagram of a simulation model configuration process of a node-based satellite simulation method according to an embodiment of the present application. Figure 5As shown in the figure, each node in the process has at least one implementation strategy. Different node strategies respond to different scenario requirements, and the selection of node strategies supports complex constellation simulation requirements. The constellation simulation requirements are endless, but the scenarios in these requirements are limited and can be exhaustively enumerated, so the node strategies are also limited. The efficient support of constellation simulation is achieved through high reuse of node strategies; when new scenarios appear, they can also be transformed into node strategy changes through scenario decomposition, and node strategy adjustment is faster and more efficient, such as Figure 4 As shown: ① In the example process, there are three strategies for the satellite orbit generation node: no orbit strategy, predicted orbit, and orbit plan. Among them, the no orbit strategy does not involve the satellite orbit generation node, and satellite orbits are not required in some simulation services. The predicted orbit is the orbit data generated by the simulation prediction model. The orbit plan is the satellite orbit plan provided externally.

[0060] ② In the example process, there are three strategies for the satellite-to-ground link node: no connection strategy, model one strategy, and model two strategy.

[0061] ③ There are multiple strategies for the control instruction parsing nodes in the example process: no instruction strategy, time loop, event trigger, first occurrence of an event, every occurrence of an event, before an event occurs, after an event occurs, specified time, specified number of loops, etc.

[0062] ④ There are multiple strategies for constellation initialization nodes in the example process: normal simulation, pure instruction simulation, software testing, etc.

[0063] Step S305, when receiving the digital twin simulation requirement, select a process solution that matches the simulation requirement; Among them, a suitable node strategy is selected according to the simulation requirements to form a process solution, and the solution here is the simulation model mentioned above.

[0064] There are 6 mature process solutions in the example process: general simulation tasks, pure instruction simulation, basic software testing, distributed software testing, constellation reproduction, and constellation synchronization.

[0065] Figure 6 is a schematic diagram of a common simulation task of a node-based satellite simulation method according to an embodiment of the present application, such as Figure 6 As shown, in the example process, the common simulation tasks select the following strategies: orbit prediction, satellite-ground link model 1, inter-satellite link model 1, events and time all support instruction parsing, and common simulation initialization.

[0066] Figure 7 is a schematic diagram of a pure instruction simulation task of a node-based satellite simulation method according to an embodiment of the present application, such as Figure 7As shown, the pure instruction simulation task in the example process selects the following strategies: no track strategy, no satellite-ground link strategy, no inter-satellite link strategy, only supports time instruction parsing, and pure instruction simulation initialization.

[0067] Step S306, after inputting the simulation parameters, the process starts to run, and during the process running, simulation related data is generated: track data, topology data, simulation events, control instructions and their execution status, and telemetry data; in, Figure 8 FIG. 1 is a schematic diagram of a common simulation task operation flow of a node-based satellite simulation method according to an embodiment of the present application, such as Figure 8 As shown, when receiving the digital twin simulation requirements, a process solution (i.e., simulation model) that matches the simulation requirements is selected. Each simulation requirement has its own unique scenario requirements. Different process solutions support different scenarios. The appropriate process solution is selected based on the scenario support. If there is no solution that meets the expectations, a new solution that meets the simulation requirements can be configured through step S304.

[0068] Step S307: the process can be terminated. After the process is terminated, all nodes will receive the termination signal and stop running, ending the simulation task and reclaiming related resources. Among them, the simulation parameters include: simulation task number, constellation information, simulation task type, simulation start time, simulation end time, application software information, and constellation step size.

[0069] The following data are generated during the simulation: track data, topology data, simulation events, control instructions and their execution status, and telemetry data, all of which define unique data structures and data processing solutions.

[0070] In step S308, the process will automatically determine whether the simulation task has been completed. When the simulation task is completed, the simulation task will be terminated and related resources will be recycled.

[0071] The process can be terminated, that is, the simulation task can be terminated at any time. The method provides a process manager, which is responsible for the process and closes all related matters and releases resources after the process is terminated to prevent resource waste. At the same time, the process will automatically determine whether the simulation task has been completed. There is a separate module in the process manager to determine whether the simulation task has been completed. If it has been completed, the process will be closed and resources will be released.

[0072] The present application provides a node-based constellation simulation method based on digital twins, establishes clear processes and nodes, clearly explains what needs to be done in each constellation simulation, divides the nodes, clarifies the scope of responsibilities of each node, and is easy to understand; by defining different node strategies, different capabilities are strategized, allowing users to dynamically select strategies when running simulation requirements, greatly improving the flexibility, scalability, and maintainability of digital twin services; the present application provides a digital twin simulation requirement solution management platform, users can customize digital twin simulation requirement solutions, and can also precipitate mature solutions for users to choose. Any special scenario only needs to be configured once and can be reused continuously, reducing a lot of repetitive work; the node strategy defined in the present application is plug-in-based, and can be easily added or removed. When new capability requirements arise, only special strategies need to be developed to support them. Changes are easy to make and the impact of changes is small, and faster iterations can be achieved; the present application provides a ready-made example and a mature solution for example use, which can be quickly applied based on this mature example.

[0073] The present embodiment also provides a node-based satellite simulation device, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module", "unit", "subunit", etc. can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0074] Fig. 9 is a structural block diagram of a node-based satellite simulation device according to an embodiment of the present application, such as Fig. 9 As shown, the device comprises: The requirement analysis module 10 is used to obtain satellite simulation requirements; The requirement analysis module 10 is also used to analyze and process the satellite simulation requirements to obtain structured scene information; the structured scene information is used to indicate the limited functional blocks that realize the satellite simulation requirements; The model generation module 20 is used to obtain a plurality of preset simulation process nodes and obtain a node strategy subset corresponding to each simulation process node; The model generation module 20 is also used to retrieve the target node strategy matching the structured scenario information from each node strategy subset for each simulation process node, and generate a target simulation model based on the target node strategy; The simulation operation module 30 is used to input simulation parameters corresponding to satellite simulation requirements into a target simulation model, perform satellite simulation processing, and generate satellite simulation results.

[0075] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0076] In addition, in combination with the node-based satellite simulation method in the above embodiment, the embodiment of the present application can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any node-based satellite simulation method in the above embodiment is implemented.

[0077] Those skilled in the art should understand that the technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0078] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A node-based satellite simulation method, characterized in that: include: Obtain satellite simulation requirements; Analyzing and processing the satellite simulation requirements to obtain structured scene information; The structured scenario information includes limited functional blocks for realizing the satellite simulation requirements; Acquire multiple preset simulation process nodes, and acquire node strategy subsets corresponding to each of the simulation process nodes; For each of the simulation process nodes, sequentially retrieving a target node strategy that matches the structured scenario information from each of the node strategy subsets, and generating a target simulation model based on the target node strategy; The obtained simulation parameters corresponding to the satellite simulation requirements are input into the target simulation model, satellite simulation processing is performed, and satellite simulation results are generated.

2. The node-based satellite simulation method according to claim 1, characterized in that: The step of retrieving, for each simulation process node, a target node strategy matching the structured scenario information from each node strategy subset in turn, and generating a target simulation model based on the target node strategy, including: Acquire a preset simulation model set, and based on the satellite simulation requirement, retrieve a preset simulation model corresponding to the satellite simulation requirement from the simulation model set; If the predetermined simulation model is retrieved, the predetermined simulation model is determined as the target simulation model; If the retrieval of the predetermined simulation model fails, then for each simulation process node, a target node strategy matching the structured scenario information is retrieved from each node strategy subset in turn, and the target simulation model is generated based on the target node strategy.

3. The node-based satellite simulation method according to claim 2, characterized in that: The method further comprises: In the case where the target simulation model is generated based on the target node strategy, the target simulation model is dynamically updated to the simulation model set to generate a new simulation model set.

4. The node-based satellite simulation method according to claim 1, characterized in that: For each simulation process node, sequentially retrieving a target node strategy matching the structured scenario information from each node strategy subset, including: Acquire historical simulation data, and establish a strategy allocation model based on the historical simulation data; The structured scenario information is input into the strategy allocation model for matching processing, and the target node strategy for each simulation process node is output.

5. The node-based satellite simulation method according to claim 1, characterized in that: For each simulation process node, sequentially retrieving a target node strategy matching the structured scenario information from each node strategy subset, including: Based on the structured scenario information, determining a retention node from each of the process nodes, and determining a retention strategy subset corresponding to the retention node in each of the node strategy subsets; For each of the retained nodes, the target node strategy matching the structured scenario information is retrieved from the retained strategy subset in turn.

6. The node-based satellite simulation method according to claim 1, characterized in that: The method further comprises: Using a preset process manager, detecting the satellite simulation result; If the satellite simulation result is detected, it is confirmed that the satellite simulation process has been completed, and the operating resources of each simulation process node are released; and / or, During the satellite simulation process, if a process termination instruction is received, the process manager is used to execute termination processing on any simulation process node in the target simulation model.

7. The node-based satellite simulation method according to claim 1, characterized in that: The step of inputting the obtained simulation parameters corresponding to the satellite simulation requirements into the target simulation model, performing satellite simulation processing, and generating satellite simulation results includes: Using the target simulation model and based on the simulation parameters, running a plurality of the target node strategies in parallel, and storing the simulation process data generated in the process of running each of the target node strategies in a simulation database; The simulation process data in the simulation database are called to generate the satellite simulation result.

8. The node-based satellite simulation method according to claim 7, characterized in that: The calling of each simulation process data in the simulation database to generate the satellite simulation result includes: According to the execution order information of each of the target node strategies, determining, among the target node strategies, a first node strategy at a first call priority and a second node strategy at a second call priority; the second call priority is higher than the first call priority; storing first simulation process data generated in the process of running each of the first node strategies in a first simulation database; When the second node strategy is run in parallel, second simulation process data is generated based on the called first simulation process data of the first simulation database, and the second simulation process data is stored in the second simulation database.

9. A node-based satellite simulation device, characterized in that: include: Requirements parsing module, used to obtain satellite simulation requirements; The demand analysis module is also used to analyze and process the satellite simulation demand to obtain structured scene information; The structured scenario information is used to indicate limited functional blocks for realizing the satellite simulation requirements; A model generation module, used to obtain a plurality of preset simulation process nodes, and obtain a node strategy subset corresponding to each of the simulation process nodes; The model generation module is also used to retrieve, for each simulation process node, a target node strategy that matches the structured scenario information from each node strategy subset in turn, and generate a target simulation model based on the target node strategy; The simulation operation module is used to input simulation parameters corresponding to the satellite simulation requirements into the target simulation model, perform satellite simulation processing, and generate satellite simulation results.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the noded satellite simulation method according to any one of claims 1 to 8 when running.

Images