Unmanned equipment situation awareness system, construction method, electronic equipment and storage medium

Abstract

The application discloses an unmanned equipment situation awareness system, a construction method, electronic equipment and a storage medium, and belongs to the technical field of intelligent situation awareness of space equipment. The construction method comprises the following steps: mapping physical parameters of a space environment, equipment state parameters and task target parameters to a multidimensional space and a unified time axis; realizing situation awareness through four steps of calculation, extrapolation, statistics and prediction; converting a situation spectrum into a visual dynamic situation graph spectrum according to a result of four-order progressive modeling processing; and intuitively presenting a current situation state and a future situation change trend. The application unifies situation information data in a situation spectrum for management through situation calculation, extrapolation, statistics and prediction, visually expresses a cooperative relationship of a state of the application, a state of a target and an environment state and the like by using a graph structure, makes a relationship network more intuitive and clear, and significantly improves situation awareness capability and decision efficiency of the space unmanned equipment in a complex environment.

Description

Technical Field

[0001] This invention relates to the field of intelligent situational awareness technology for aerospace equipment, and more specifically to a situational awareness system for unmanned equipment, its construction method, electronic equipment, and storage medium. This system is applicable to various types of unmanned space equipment and can provide data support for subsequent autonomous decision-making by equipment and command by commanders in various scenarios, including single-equipment, multi-equipment collaboration, and even system-wide command. Background Technology

[0002] Currently, with the rapid development of aerospace technology, space missions are becoming increasingly complex, placing unprecedented demands on the autonomy, coordination, and reliability of equipment. However, the multi-source and heterogeneous data from various equipment in space missions are fragmented in terms of data storage and processing. Commanders and unmanned equipment struggle to obtain a comprehensive and unified view of the environmental status or mission situation, leading to insufficient decision-making basis and a high risk of misjudgment.

[0003] For high-orbit equipment, communication delays can easily reach tens of minutes, making the centralized ground-based decision-making model extremely slow and unable to cope with emergencies. Even in low Earth orbit, decision-making for complex missions heavily relies on the commander's personal experience, lacking data-driven quantitative analysis and support, making it difficult to guarantee decision-making efficiency and accuracy. For multi-equipment missions such as constellations and formations, the coordinated scheduling between platforms often requires tedious manual planning, which is time-consuming and prone to errors. However, in the space environment, the situation changes rapidly, requiring efficient situational assessment to cope with the ever-changing space environment.

[0004] Therefore, an integrated solution is needed that can combine comprehensive information and dynamic situational awareness to enhance the situational awareness capabilities of unmanned equipment and commanders in complex environments. Summary of the Invention

[0005] In view of this, the present invention aims to solve the above-mentioned technical problems and provides an unmanned equipment situation awareness system, a construction method, an electronic device and a storage medium. The construction method constructs a unified situation spectrum through a four-order progressive modeling method to achieve comprehensive and multi-level situation awareness.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide a method for constructing an unmanned equipment situational awareness system, comprising the following steps:

[0008] (1) Data processing: Map the physical parameters of the space environment, equipment status parameters and mission target parameters into a unified multi-dimensional space and a unified time axis;

[0009] (2) Four-order progressive modeling: Based on the data processing results, the situation spectrum is constructed through four steps: calculation, extrapolation, statistics and prediction to realize situation cognition;

[0010] (3) Situation visualization: Based on the results of the four-order progressive modeling process, the situation data is transformed into a visualized dynamic situation map; the dynamic situation map is used to intuitively present the current situation status and future situation change trends.

[0011] Furthermore, the data processing in step (1) specifically includes:

[0012] Quantify various situational factors that are collected, calculated, processed, and analyzed;

[0013] Transformed into parameters or metrics with different dimensions;

[0014] Record all parameters or indicators on a unified timeline.

[0015] Furthermore, the fourth-order progressive modeling in step (2) includes:

[0016] Calculation steps: Calculate the current state of each node, its relative state with respect to the target, and its relationship with the environment using mathematical calculation methods;

[0017] Extrapolation steps: Extrapolate the state of each node at a future time period, its relative state with the target, its relationship with the environment, and its equipment capabilities using mathematical calculation methods.

[0018] Statistical steps: Statistically analyze the actions, interactions, and task execution processes of both oneself and the target;

[0019] Prediction steps: Based on calculated, extrapolated, and statistical data, perform trend prediction, capability prediction, and intent recognition for each node.

[0020] Furthermore, the calculation steps include:

[0021] Self-state calculation: Based on carrier sensor data and inherent equipment parameters, real-time position, attitude, motion parameters, and equipment health status are calculated through Kalman filtering or federated Kalman filtering.

[0022] Relative state calculation: Calculate the relative distance, relative velocity, and relative attitude with respect to the target based on target detection data and the user's real-time state data;

[0023] Environmental status calculation: Based on environmental perception data, its own real-time position and motion parameters, calculate the degree of impact of the environment on itself and its own safety margin in the environment.

[0024] Furthermore, the extrapolation step includes:

[0025] Self-state extrapolation: extrapolate future predicted location, speed, remaining fuel / electricity, and equipment health status trends based on current self-state data, equipment performance constraint parameters, and environmental prediction data;

[0026] Relative state extrapolation: extrapolate future predictions of relative distance, relative speed, and rendezvous patterns based on current relative state data, historical target motion patterns, and environmental constraints;

[0027] Equipment capability extrapolation: extrapolating future equipment performance degradation curves, equipment availability, and remaining lifespan based on current equipment performance data and equipment loss models;

[0028] Statistical extrapolation: Based on time series characteristics, time series analysis methods are used to extrapolate the predicted values ​​of statistical indicators for future time periods; the time series analysis methods include Fourier transform, linear regression, or nonlinear regression.

[0029] Furthermore, the statistical steps include:

[0030] Self-motion statistics: Collects self-movement and operation actions, and records the trigger time, duration, and action parameters of each action;

[0031] Target motion statistics: Collect target motion actions and interactions with itself, and record the time and characteristics of the actions.

[0032] Rendezvous process statistics: Collect rendezvous events between itself and the target, and record the rendezvous time, rendezvous location, relative state at the time of rendezvous, and rendezvous result;

[0033] Task execution statistics: Collect data on task start time, stage objectives, execution progress, completion status, and abnormal events;

[0034] Action pattern statistics: The frequency of each action of the self and the target is calculated using frequency statistics; association rule mining is used to analyze the relationship between actions and generate an action association map.

[0035] Intersection pattern statistics: Clustering algorithms are used to classify intersection processes. Intersection patterns at different distances are divided based on intersection distance, speed, and result characteristics. The occurrence probability and pattern characteristic parameters of each pattern are calculated.

[0036] Furthermore, the prediction step includes:

[0037] Trend prediction: Based on extrapolated data and statistical data, we identify future threat events, key time windows and vulnerable areas through time series similarity matching and grid risk assessment.

[0038] Capability prediction: Based on statistical data, extrapolated data, and computational data, the system uses grey prediction models, multiplicative models, or Bayesian estimation to assess the endurance, maneuverability, perception capabilities, and mission execution capabilities of itself and the target over a future time period.

[0039] Intent recognition: Based on statistical data, extrapolated data, and computational data, the target intent is determined by matching the target behavior feature vector with a predefined intent template based on similarity and combining it with Bayesian inference.

[0040] Secondly, embodiments of the present invention also provide an unmanned equipment situational awareness system, constructed based on any one of the methods in the first aspect of the embodiments, including:

[0041] Data processing module: used to fuse multi-source heterogeneous data and map it to a unified multi-dimensional situation space;

[0042] The situation spectrum construction module is used to perform fourth-order progressive modeling processing.

[0043] Visualization module: Used to generate visual situation maps and threat analysis results.

[0044] Thirdly, embodiments of the present invention provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method as described in any one of the first aspects.

[0045] Fourthly, embodiments of the present invention also provide a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of the first aspects.

[0046] The descriptions of the second and third aspects of this invention can be referred to the detailed description of the first aspect; and the beneficial effects described in the second and third aspects can be referred to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0047] As can be seen from the above technical solution, compared with the prior art, the present invention has the following technical advantages:

[0048] 1. Intuitive presentation of relationship networks: Through situation calculation, extrapolation, statistics, and prediction, situation information data is managed in a unified situation spectrum. The spectrum structure is used to visually express the state of itself, the state of the target, and the state of the environment, making the relationship network more intuitive and clear.

[0049] 2. Comprehensive situational awareness: It can integrate multi-source heterogeneous data to form a unified situational view, solving the problem of data fragmentation and providing commanders with a comprehensive and unified view of the environmental status or mission situation.

[0050] 3. Efficient decision support: Through a four-level progressive modeling method, a comprehensive understanding of the current state and future trends is achieved, which greatly improves decision-making efficiency and accuracy.

[0051] 4. Strong adaptability: The system can adaptively adjust its situational awareness strategy according to changes in the environment and mission requirements, and is suitable for various deployment methods such as single-equipment independent deployment, multi-equipment collaborative deployment, and all-domain integrated deployment.

[0052] 5. Precise prediction capability: Through algorithmic models, it achieves accurate prediction of threats, capabilities, and intentions, providing a valuable time window for responding to emergencies. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0054] Figure 1 A flowchart illustrating the construction method of the unmanned equipment situation awareness system provided by this invention.

[0055] Figure 2 This is a schematic diagram of the situation spectrum structure provided by the present invention.

[0056] Figure 3 The flowchart for situation calculation provided by this invention.

[0057] Figure 4 A block diagram of the situation awareness system for unmanned space equipment based on situation spectrum provided by the present invention.

[0058] Figure 5 This is a structural diagram of the electronic device provided by the present invention. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] Example 1:

[0061] Commanders typically make judgments and decisions based on the intentions of superiors, the situation, and their own resources. However, due to the large number of factors to consider, they need to manually integrate dozens of independent reports such as "early warning, environmental status, and equipment status" to judge the threat and the target's intentions and make effective response plans. This process is time-consuming and prone to misjudgment due to data omissions.

[0062] Therefore, commanders need to use "map" tools to comprehensively describe the situation information when making decisions, enabling them to make decisions based on this "map." However, in the space environment, commanders lack such a "map" to clearly understand the situation. The present invention provides a method for constructing a situation awareness system for unmanned space equipment based on a situation spectrum. In this method, the "situation spectrum" is this map. Various parameters or indicators are recorded on a unified timeline, and these parameters or indicators together constitute the situation spectrum. Discrete data is transformed into a "visualized situation heatmap," and "core threat points + related logic" are automatically generated. Commanders do not need to analyze raw data; the "situation spectrum" provides a clear and intuitive understanding of the overall situation, historical processes, and future trends, offering complete and clear situation information. Commanders can quickly grasp "who the core threat is, where the threat is, and how to respond," effectively improving the efficiency of situation assessment.

[0063] Reference Figure 1 As shown in the figure, this invention discloses a method for constructing an unmanned equipment situational awareness system, including the following steps:

[0064] (1) Data processing: Map the physical parameters of the space environment, equipment status parameters and mission target parameters into a unified multi-dimensional space and a unified time axis;

[0065] (2) Four-order progressive modeling: Based on the data processing results, the situation spectrum is constructed through four steps: calculation, extrapolation, statistics and prediction to realize situation cognition;

[0066] The four steps are as follows:

[0067] 1) Calculation: The current state of each node, its relative state with respect to the target, and its relationship with the environment are calculated using mathematical calculation methods to grasp the current situation and provide data support for forming a complete real-time situational awareness. The calculation should be performed under a unified spatiotemporal reference, with a unified coordinate system, time, and unit.

[0068] 2) Extrapolation: Through mathematical calculation methods, extrapolate the state of each node in a future time period, its relative state with the target, its relationship with the environment, and its equipment capabilities to grasp the future situation and provide a basis for trend prediction and intention recognition in situation cognition. At the same time, extrapolate the statistical content based on the statistical results to provide a basis for prediction.

[0069] 3) Statistics: Statistical analysis of the actions, encounters, and task execution processes of both oneself and the target is conducted to extract reusable patterns and provide a basis for situational awareness capability prediction and extrapolation.

[0070] 4) Prediction: Based on calculated, extrapolated, and statistical data, perform trend prediction, capability prediction, and intent identification for each node to form a complete situational awareness result.

[0071] (3) Situation visualization: Based on the results of the four-order progressive modeling process, the situation data is transformed into a visualized dynamic situation map; the dynamic situation map is used to intuitively present the current situation status and future situation change trends.

[0072] Before issuing commands, commanders need to analyze and assess the situation. However, the space environment contains a variety of dynamic targets, and the situational awareness data of equipment is often multi-source and heterogeneous, making correlation difficult. This invention integrates situational information based on the situational spectrum, and performs a series of operations such as calculation, extrapolation, statistics, and prediction on its own state, relative state with the target, and relative state with the environment to form a "situational map". This results in a complete situational cognition and reasoning, providing reliable and complete data for mission planning.

[0073] This invention maps the physical parameters of the space environment, equipment status parameters, and mission objective parameters into a unified multi-dimensional space. Through intelligent algorithms, it analyzes and predicts in real time, generating a visualized situation map. This map not only intuitively presents the current state but also predicts future trends, providing commanders or autonomous control systems with interpretable and quantifiable decision-making support.

[0074] The three steps of the construction method of this invention are described in detail below:

[0075] Step (1): Data processing;

[0076] A situational awareness spectrum quantifies various collected, calculated, processed, and analyzed situational elements, transforming them into parameters or indicators with different dimensions. These parameters or indicators are then recorded on a unified timeline. After subsequent modeling and processing, these parameters or indicators collectively constitute the situational awareness spectrum, providing a clear picture of the overall situation, historical processes, and future trends. The situational awareness spectrum provides data support for situational awareness, mission planning, and mission strategy.

[0077] For each unmanned equipment, a situation spectrum based on itself must be formed to create a "situation map" centered on itself. Decision-makers only need to look at this map to understand the current situation and the threats they face, so as to formulate corresponding response strategies.

[0078] Situation spectrum can be used for cognitive reasoning analysis of the situation, such as Figure 2 As shown, the time domain (left <—> right) of the situation spectrum allows you to view historical and extrapolated states in different dimensions, and predict future trends. The element domain (top <—> bottom) allows you to see the reasons for changes in the state or the formation of threats, enabling decision-makers to have a more comprehensive understanding and analysis of the entire situation.

[0079] Step (2): Four-order progressive modeling;

[0080] The underlying process of cognitive reasoning can be described as a "situation spectrum" that covers all situational information, generating real-time and future situations through "calculation-statistics-extrapolation-prediction".

[0081] 1) Calculation: The current state of each node, its relative state with respect to the target, and its relationship with the environment are calculated using mathematical calculation methods to grasp the current situation and provide data support for forming a complete real-time situational awareness. The calculation should be performed under a unified spatiotemporal reference, with a unified coordinate system, time, and unit.

[0082] Self-state calculation:

[0083] Real-time position, attitude, motion parameters, and equipment health status are calculated based on inherent parameters such as carrier sensor data, equipment mass, dimensions, maximum speed, and endurance. The calculation method employs Kalman filtering to fuse sensor data, addressing attitude drift issues arising from sensor signal loss. For multi-sensor redundancy scenarios, federated Kalman filtering is used, allocating data weights according to sensor accuracy to improve position calculation accuracy.

[0084] Calculation of relative state with respect to the target:

[0085] The relative distance, relative velocity, and relative attitude with the target are calculated based on target detection data and the user's real-time status data. The calculation method uses spatial analytical geometry to calculate the relative distance and a finite difference method to calculate the relative velocity by subtracting the target velocity from the user's velocity over two consecutive frames.

[0086] Calculation of the relationship status with the environment:

[0087] Based on environmental perception data such as illumination angle, visibility, obstacle distribution, no-fly zone range, electromagnetic interference intensity, and frequency distribution, as well as its own real-time position and motion parameters, the degree of influence of the environment on itself and its own safety margin in the environment are calculated.

[0088] 2) Extrapolation: Through mathematical calculation methods, extrapolate the state of each node in a future time period, its relative state with the target, its relationship with the environment, and its equipment capabilities to grasp the future situation and provide a basis for trend prediction and intention recognition in situation cognition. At the same time, extrapolate the statistical content based on the statistical results to provide a basis for prediction.

[0089] Extrapolation of one's own state:

[0090] Based on the current self-state data, equipment performance constraint parameters, and environmental prediction data output from the above calculation step 1), the predicted position, speed, remaining fuel / electricity, and equipment health status change trends for each future time node are extrapolated. The calculation method adopts linear extrapolation; for complex motion scenarios, support vector regression is used, with historical motion data as training samples to establish a nonlinear motion model, and the extrapolation error is controlled within 10%.

[0091] Relative state extrapolation to the target:

[0092] Based on the current relative state data output from step 1) above, the target's historical motion patterns, and environmental constraints, the predicted relative distance, relative speed, and intersection probability for each future time node are extrapolated. The calculation method uses Markov chains to predict the target's motion patterns, classifying the target's motion state into "normal," "maneuvering," and other states. The state transition probability is calculated using historical data, and the future motion state of the target is extrapolated based on the probability model. Combined with Monte Carlo simulation, multiple sets of possible target trajectories are generated, and the intersection probability and danger coefficient are statistically analyzed to improve the reliability of the extrapolation results.

[0093] Equipment capability extrapolation:

[0094] Based on the calculation methods of current equipment performance data, equipment loss model extrapolation of equipment performance degradation curves at future time points, equipment availability, and remaining life, an equipment reliability model based on Weibull distribution is constructed, the equipment failure probability curve is fitted, and the equipment performance is corrected using the attenuation coefficient method to generate performance degradation curves.

[0095] Furthermore, it also includes extrapolating statistical data:

[0096] Based on the statistical data such as historical intersection frequency and task execution success rate output from the subsequent step 3), and the time series characteristics of the statistical indicators such as periodicity and trend, the predicted values ​​of statistical indicators for future time periods are extrapolated. For periodic statistical data, Fourier transform is used to extract periodic features, and periodic extrapolation is combined to predict future statistical values; for statistical data with linear trends, linear regression model extrapolation is used; for nonlinear data, nonlinear regression model extrapolation is used.

[0097] 3) Statistics: Statistical analysis of the actions, encounters, and task execution processes of both oneself and the target is conducted to extract reusable patterns and provide a basis for situational awareness capability prediction and extrapolation.

[0098] Self-motion statistics: Collects self-movement and operation actions, and records the trigger time, duration and action parameters of each action.

[0099] Target motion statistics: Collect target motion actions and interactions with itself, and record the time and characteristics of the actions.

[0100] Intersection process statistics: Collect the intersection events between itself and the target, and record the intersection time, intersection location, relative state at the time of intersection, and intersection result.

[0101] Task execution statistics: Collect data at each stage, including task start time, stage goals, execution progress, completion status, and abnormal events, and record task execution time, resource consumption, and task success rate.

[0102] Movement pattern statistics:

[0103] Analysis methods: Frequency statistics are used to calculate the frequency of each action of the self and the target; association rule mining is used to analyze the relationship between actions and generate an action association map.

[0104] Meeting pattern statistics:

[0105] Clustering algorithms are used to classify the intersection process. Based on features such as intersection distance, speed, and result, the process is divided into modes such as "short-range intersection", "medium-range intersection", and "long-range intersection". The occurrence probability and feature parameters of each mode are calculated.

[0106] 4) Prediction: Based on calculated, extrapolated, and statistical data, perform trend prediction, capability prediction, and intent identification for each node to form a complete situational awareness result.

[0107] Trend (threat) prediction: Through extrapolated data analysis and the intersection patterns with targets, key time windows, and vulnerable areas.

[0108] Capability prediction: Based on statistical data, predict the endurance, maneuverability, perception, and mission execution capabilities of oneself and the target.

[0109] Intent recognition: Match the statistical behavioral patterns and extrapolated states of the current target with the "intent templates" in the rule base to determine the target's intent.

[0110] ① Trend (Threat) Prediction:

[0111] Based on the target's future position / velocity, relative state extrapolation results from the extrapolation step, intersection pattern data from the statistical step, and threat determination rules from the rule base, we can identify potential future threat events and determine key time windows and vulnerable areas.

[0112] Extrapolation data analysis: Time series similarity matching is used to compare the similarity between the target's future trajectory and the historical threat trajectory. If the similarity exceeds a certain range, it is marked as a potential threat.

[0113] Intercourse pattern analysis: Based on the statistical intercourse pattern library, if the extrapolated intercourse process matches the "long-distance threat intercourse" pattern and the intercourse time window overlaps with its own vulnerability time, it is judged as a high-risk threat.

[0114] Vulnerability zone identification: Using a grid-based risk assessment method, combining the target's extrapolated trajectory with its own defense capabilities, the threat risk value of each grid is calculated. Grids with risk values ​​exceeding a certain range are marked as vulnerable zones.

[0115] ② Ability prediction:

[0116] Based on historical capability data from the statistical step, extrapolation results of equipment capabilities from the extrapolation step, and current equipment health status from the calculation step, we can assess our own and the target's basic capabilities such as endurance and maneuverability, perception capabilities, and mission execution capabilities over a future time period, providing capability matching basis for situational decision-making.

[0117] Basic capability prediction: A grey prediction model is adopted, which is built based on historical endurance and maneuver data to predict the endurance of future missions, with the prediction error controlled within a certain range; combined with the remaining life curve extrapolated from equipment capabilities, the prediction results of basic capabilities such as remaining life and maneuverability are corrected.

[0118] Perception capability prediction: Based on the statistical performance patterns of sensing devices and combined with extrapolated environmental parameters, a multiplicative model is used to calculate the perception capability. For target perception capability, Bayesian estimation is used to correct the perception capability parameters by using historical interaction data such as the distance and time when the target detected itself in the past, thereby improving the prediction accuracy.

[0119] Task execution capability prediction: Construct a task execution capability assessment matrix, decompose task types into multiple capability indicators, and predict the equipment's task execution capability based on the historical compliance rate of each indicator and the extrapolated equipment status.

[0120] ③ Intent recognition:

[0121] The current and future intent of the target are determined based on the target behavior pattern data from the statistical module, the target future state data from the extrapolation step, the "intent template" from the rule base, and the target's current relative state from the calculation step.

[0122] Template matching: Construct an intent template library and define core features for each intent; use cosine similarity to calculate the similarity between the target behavior feature vector and the feature vector of each intent template. The intent corresponding to the template with the highest similarity and exceeding the threshold is initially determined to be the target intent; if there are multiple templates with close similarity, Bayesian inference is introduced, and the posterior probability is calculated by combining the historical intent probability. The intent with the highest posterior probability is taken as the final determination result.

[0123] Step (3): Situation visualization;

[0124] By unifying situational information data into a situational spectrum through situational calculation, extrapolation, statistics, and prediction, the situational information data is managed in a unified manner. The spectrum structure is used to visually express the state of itself, the state of the target, and the state of the environment, etc. The situational data is transformed into a visual dynamic situational spectrum, which can intuitively present the current situational state and future situational change trends, thereby making the relationship network more intuitive and clear.

[0125] like Figure 3 As shown, this invention, through the input of multi-source heterogeneous sensing data, performs four-stage processing of calculation, statistics, extrapolation, and prediction, and finally realizes the generation of dynamic situation spectrum. It solves the problems of data fragmentation, decision delay and lack of unified situation view in the prior art, and significantly improves the situation awareness and decision-making efficiency of unmanned space equipment in complex environments.

[0126] Example 2:

[0127] Reference Figure 4 As shown, this embodiment of the invention provides a situational awareness system for unmanned space equipment that implements the method of Embodiment 1, comprising:

[0128] Data processing module: used to fuse multi-source heterogeneous data and map it to a unified multi-dimensional situation space;

[0129] The situation spectrum construction module is used to perform fourth-order progressive modeling processing.

[0130] Visualization module: Used to generate visual situation maps and threat analysis results.

[0131] This system can be deployed in various ways, including single-equipment independent deployment, multi-equipment collaborative deployment, and integrated deployment across the entire domain.

[0132] The independent capability of individual equipment enhances its independent situational awareness. When ground communication is delayed or interrupted, the equipment can autonomously perceive and assess emergencies based on the local situational awareness spectrum, without relying on ground command support.

[0133] Multi-equipment collaboration can improve the efficiency of situational awareness among multiple equipment. In multi-equipment scenarios such as satellite constellations and formations, each piece of equipment can share situational information, forming an overall situational awareness network. Even if one piece of equipment malfunctions, the system can still quickly grasp the status of surrounding equipment and the environmental conditions through shared situational information, laying the cognitive foundation for subsequent collaborative actions.

[0134] The integrated, all-domain approach can significantly enhance commanders' overall situational awareness. This approach integrates multi-dimensional situational parameters through a "situational spectrum" to generate a dynamic situational map in real time, allowing command to intuitively and comprehensively grasp the overall situation. Simultaneously, combined with intelligent prediction algorithms, it can anticipate enemy target intentions, providing command with visualized situational materials containing "threat level + prediction basis," helping commanders accurately grasp changes in the situation.

[0135] By leveraging a "situation spectrum" to fuse and analyze massive amounts of sensor data, the system can comprehensively and dynamically perceive and understand the space environment. Simultaneously, relying on algorithms such as machine learning, the system can predict situational changes, enabling commanders to quickly identify potential threats and providing strong support for subsequent decision-making.

[0136] Example 3:

[0137] Based on the same inventive concept, the present invention also provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0138] Memory, used to store computer programs;

[0139] When the processor executes the program stored in the memory, it is able to implement the method for constructing a situational awareness system for unmanned space equipment based on the situational spectrum as described in any one of Embodiments 1.

[0140] like Figure 5 As shown, the electronic device may include: a processor 10, a communication interface 20, a memory 30, and a communication bus 40, wherein the processor 10, the communication interface 20, and the memory 30 communicate with each other via the communication bus 40. The processor 10 can call logical instructions in the memory 30 to execute the construction of a situational awareness system for unmanned space equipment based on the situational spectrum. The method includes:

[0141] (1) Data processing: Map the physical parameters of the space environment, equipment status parameters and mission target parameters into a unified multi-dimensional space and a unified time axis;

[0142] (2) Four-order progressive modeling: Based on the data processing results, the situation spectrum is constructed through four steps: calculation, extrapolation, statistics and prediction to realize situation cognition;

[0143] (3) Situation visualization: Based on the results of the four-order progressive modeling process, the situation data is transformed into a visualized dynamic situation map; the dynamic situation map is used to intuitively present the current situation status and future situation change trends.

[0144] Example 4:

[0145] This invention also provides a storage medium in which a program stored in the computer-readable storage medium is used to execute the situation awareness system construction method for unmanned space equipment based on situation spectrum of Embodiment 1 described above. The program can be executed on a processor.

[0146] Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0147] The program stored on this medium is loaded into the processor's memory and executed to perform various functions. This storage medium, connected to hardware devices, enables the computer to perform the steps of Embodiment 1 described above.

[0148] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0149] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for constructing an unmanned equipment situation awareness system, characterized in that, The method comprises the following steps: (1) data processing: mapping physical parameters of space environment, equipment state parameters and task target parameters to a multi-dimensional space and a unified time axis; (2) four-step progressive modeling: based on the data processing result, constructing a situation spectrum through calculation, extrapolation, statistics and prediction to realize situation awareness; wherein, the calculation step: calculating the current self state, relative state with the target and relationship state with the environment of each node through mathematical calculation method; the extrapolation step: extrapolating and calculating the self state, relative state with the target, relationship state with the environment and equipment capability of each node in a future time period through mathematical calculation method; the statistics step: statistically analyzing the actions, conjunctions and task execution processes of both the self and the target; the prediction step: based on the data of calculation, extrapolation and statistics, predicting the trend, capability and intention of each node; The calculation step comprises: self state calculation: fusing and calculating real-time position, attitude, motion parameter and equipment health state through Kalman filtering or federated Kalman filtering based on carrier sensor data and equipment inherent parameters; relative state calculation: calculating relative distance, relative speed and relative attitude with the target based on target detection data and real-time state data of the self; environment state calculation: calculating the influence degree of the environment on the self and the safety margin of the self in the environment based on environment perception data and real-time position and motion parameter of the self; The extrapolation step comprises: self state extrapolation: extrapolating future predicted position, speed, residual fuel / electricity and equipment health state change trend based on current self state data, equipment performance constraint parameter and environment prediction data; relative state extrapolation: extrapolating future predicted relative distance, relative speed and conjunction mode based on current relative state data, target historical motion mode and environment constraint; equipment capability extrapolation: extrapolating future equipment performance decay curve, equipment available capability and residual life based on current equipment performance data and equipment wear-out model; statistical content extrapolation: extrapolating statistical index prediction value in a future time period based on time sequence characteristics and using time sequence analysis method; the time sequence analysis method comprises Fourier transform, linear regression or nonlinear regression; (3) situation visualization: converting situation data into a visual dynamic situation spectrum according to the result of the four-step progressive modeling; the dynamic situation spectrum is used for intuitively presenting current situation state and future situation change trend.

2. The method of claim 1, wherein, The data processing in step (1) specifically comprises: quantifying various collected, calculated, processed and analyzed situation elements; converting into parameters or indexes with different dimensions; recording each parameter or index on a unified time axis.

3. The method of claim 1, wherein, The statistics step comprises: self action statistics: collecting self motion action and operation action, and recording trigger time, duration and action parameter of each action; target action statistics: collecting target motion action and self interaction action, and recording action occurrence time and action characteristics; conjunction process statistics: collecting conjunction events of the self and the target, and recording conjunction time, conjunction position, relative state at the time of conjunction and conjunction result; Task execution statistics: collect task start time, phase target, execution progress, completion, and abnormal event data; Action rule statistics: calculate the frequency of each action using frequency statistics; use association rule mining to analyze the association between actions and generate an action association graph; Intersection mode statistics: use clustering algorithms to classify intersection processes, divide intersection modes based on intersection distance, speed, and result characteristics, and calculate the occurrence probability and mode characteristic parameters of each mode.

4. The method of claim 1, wherein, The prediction step includes: Trend prediction: identify future threat events, critical time windows, and vulnerability areas based on extrapolated data and statistical data using time series similarity matching and grid risk assessment; Capability prediction: assess the endurance, mobility, perception, and task execution capabilities of the target in the future time period based on statistical data, extrapolated data, and calculated data using gray prediction models, multiplication models, or Bayesian estimation; Intention recognition: determine the target's intention by matching the target's behavior feature vector with predefined intention templates and combining Bayesian inference based on statistical data, extrapolated data, and calculated data.

5. An unmanned equipment situation awareness system implementing the method of any one of claims 1-4, characterized by It includes: Data processing module: used to fuse and map multi-source heterogeneous data to a unified multi-dimensional situation space; Situational spectrum construction module: used to perform four-order progressive modeling processing; Visualization module: used to generate visual situation spectrum and threat analysis results.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the method of any one of claims 1-4.

7. A storage medium having stored thereon a computer program, characterized in that The program is executed by the processor to implement the method of any one of claims 1-4.

Images