A low-altitude flying target recognition method and system based on three-dimensional digital earth

Abstract

The present invention relates to the field of flight target identification technology, and in particular to a method and system for low-altitude flight target identification based on a three-dimensional digital earth. The method comprises the following steps: marking low-altitude monitoring range data with high-rise surface elements to obtain high-rise surface element marking data; calculating spatial relative distances on the high-rise surface element marking data to obtain flight target-surface element spatial relative distance data; estimating the probability of flight loss of control based on the flight target-surface element spatial relative distance data to obtain flight loss of control probability data; constructing a flight target state recognition model based on the flight loss of control probability data to obtain a flight target state recognition model; and predicting the risk flight intention of low-altitude flight targets based on the flight target state recognition model to obtain target risk flight intention data. The present invention improves flight target recognition technology by optimizing the flight target recognition technology.

Description

Technical Field

[0001] The present invention relates to the technical field of flight target recognition, and in particular to a method and system for recognizing low-altitude flight targets based on a three-dimensional digital globe. Background Art

[0002] With the widespread use of low-altitude targets such as drones and low-altitude aircraft in military, commercial, and civilian applications, efficient and accurate identification of low-altitude targets has become a critical issue. Traditional radar and optoelectronic monitoring methods are susceptible to interference from factors such as terrain obstruction and meteorological conditions in complex terrain, making accurate identification of low-altitude targets difficult. Low-altitude target recognition methods based on three-dimensional digital Earth technology leverage the advantages of global positioning, real-time monitoring, and dynamic analysis. By constructing high-precision geographic information and environmental models, they achieve comprehensive target perception and intelligent identification. Three-dimensional digital Earth technology integrates multiple spatial information technologies, including geographic information systems (GIS), remote sensing (RS), and global navigation satellite systems (GNSS), enabling real-time collection and analysis of multidimensional data such as the trajectory, attitude, and velocity of low-altitude targets. Furthermore, by integrating the target's appearance, motion, and behavior patterns, a more refined recognition model is constructed, enabling automated and intelligent monitoring and analysis of low-altitude targets. This method not only improves low-altitude target recognition accuracy but also reduces false alarms and missed detections, particularly in complex environments and adverse weather conditions. Its application scenarios cover a wide range of areas, including urban security, border monitoring, aviation regulation, and drone swarm management. It helps enhance airspace safety management capabilities and provides technical support for the safe operation and standardized management of low-altitude aircraft. With the continuous development of three-dimensional digital Earth technology, this method will play an even more important role in future airspace management and target identification. However, traditional low-altitude target identification methods based on three-dimensional digital Earth suffer from inaccurate analysis of the probability of loss of control of low-altitude targets and inaccurate assessment of their flight risk intentions. Summary of the Invention

[0003] Based on this, it is necessary to provide a low-altitude flying target identification method and system based on three-dimensional digital earth to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for identifying low-altitude flying targets based on a three-dimensional digital globe is provided, the method comprising the following steps:

[0005] Step S1: Acquire low-altitude monitoring range data; perform high-altitude surface element marking on the low-altitude monitoring range data to obtain high-altitude surface element marking data;

[0006] Step S2: Calculating the spatial relative distance of the towering surface element marker data to obtain flight target-surface element spatial relative distance data; performing near-surface airflow disturbance analysis based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data; and estimating the flight loss-of-control probability based on the near-surface airflow disturbance data to obtain flight loss-of-control probability data.

[0007] Step S3: constructing a flight target state recognition model based on the flight loss of control probability data based on the Q-Learning algorithm to obtain a flight target state recognition model;

[0008] Step S4: predict the risky flight intention of the low-altitude flying target based on the flight target state recognition model, obtain the target risky flight intention data, and feed back the target risky flight intention data to the terminal.

[0009] By acquiring low-altitude monitoring range data and marking tall surface elements, the present invention can accurately identify and record tall objects on the surface that could impact aircraft. This process helps construct a detailed map of the flight environment, providing important foundational data for subsequent flight safety analysis. The tall surface element marking data can help identify potential obstacles in the flight path, enabling these obstacles to be avoided during flight planning and operations, reducing the occurrence of flight accidents. By calculating the relative spatial distances between the flight target and tall surface elements, a detailed understanding of the actual spatial relationship between the aircraft and surface obstacles can be obtained. This process enables the assessment of the aircraft's relative position to obstacles during low-altitude flight and further analyzes the impact of near-surface airflow disturbances. Through in-depth analysis of these disturbances, potential areas of airflow interference can be identified, and the impact of airflow on aircraft stability can be predicted, allowing appropriate control measures to be taken during flight. Estimating the probability of flight loss of control based on near-surface airflow disturbance data is of great significance. By analyzing the impact of airflow disturbances on the aircraft, the risk of aircraft loss of control can be quantified, providing a scientific basis for flight operations. This estimation helps pilots or automated flight systems better manage airflow disturbances during flight, improving flight safety and reducing the incidence of accidents. A flight target state recognition model constructed using the Q-Learning algorithm effectively processes flight loss of control probability data and learns the risk characteristics of different flight states. This model is continuously optimized through reinforcement learning, enabling it to accurately identify and predict the aircraft's state under various environmental conditions. This model not only helps understand the potential safety impacts of different flight states but also provides information on how to adjust flight strategies under specific flight states, thereby enhancing the aircraft's adaptability and safety in complex environments. Through a dynamically updated learning mechanism, the model continuously improves recognition accuracy and provides customized safety measures for different flight environments. Risky flight intention prediction based on the flight target state recognition model provides real-time early warning of potential risks. By predicting the target's risky flight intention, the flight system can proactively adjust flight strategies or alert the pilot to prevent flight hazards. This prediction information is transmitted through a terminal feedback mechanism, ensuring that the pilot or automated flight system has timely access to the latest risk assessment data and can make necessary safety adjustments. This not only improves flight safety but also enhances emergency response capabilities and significantly reduces flight risks. Through real-time feedback and adjustments, a high level of safety can be maintained during the flight.Therefore, the present invention is an optimization process for a traditional low-altitude flight target identification method based on three-dimensional digital earth, which solves the problems of inaccurate analysis of the probability of low-altitude flight target loss of control and inaccurate judgment of its flight risk intention in the traditional low-altitude flight target identification method based on three-dimensional digital earth, improves the accuracy of analysis of the probability of low-altitude flight target loss of control and improves the accuracy of judgment of flight risk intention.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Acquire low-altitude monitoring range data;

[0012] Step S12: collecting monitoring range environment data from the low-altitude monitoring range data to obtain monitoring range environment data;

[0013] Step S13: marking the high-altitude surface elements on the low-altitude monitoring range data according to the monitoring range environment data to obtain high-altitude surface element marking data.

[0014] The present invention's acquisition of low-altitude monitoring range data lays the foundation for subsequent analysis. This step forms a low-altitude flight monitoring framework by collecting basic geographic data and environmental information about the area where the aircraft is located. Accurately acquiring data within this range provides a comprehensive understanding of the aircraft's spatial environment, ensuring that all areas that may impact flight are covered in subsequent analysis. Acquiring this data is crucial for developing a comprehensive monitoring system and provides raw data support for subsequent high-altitude surface element labeling and airflow analysis. By collecting environmental data for the low-altitude monitoring range data, a detailed understanding of the environmental characteristics and surface conditions within the monitoring range can be obtained. This step, by collecting information on environmental factors such as climate, topography, and buildings, provides the necessary background data for high-altitude surface element labeling. This environmental data collection helps accurately identify and label high-altitude surface elements that may impact the aircraft, ensuring comprehensiveness and accuracy of the analysis, thereby improving the reliability of subsequent safety assessments. By labeling low-altitude monitoring range data with high-altitude surface elements based on the monitoring range environmental data, surface obstacles that pose a threat to the aircraft can be systematically identified and recorded. This labeling process not only facilitates the creation of a detailed obstacle map but also provides critical information for aircraft path planning and flight safety analysis. By accurately marking towering surface elements, the risk of aircraft colliding with these obstacles during low-altitude flight can be effectively reduced, flight safety can be improved, and accurate basic data can be provided for subsequent airflow disturbance analysis and flight loss of control probability estimation.

[0015] Preferably, step S2 includes the following steps:

[0016] Step S21: Real-time monitoring of low-altitude flight targets in the low-altitude monitoring range data is performed by radar to obtain real-time monitoring data of low-altitude flight targets;

[0017] Step S22: performing spatial relative distance calculation on the high-rise surface element marker data based on the real-time monitoring data of the low-altitude flight target to obtain the flight target-surface element spatial relative distance data;

[0018] Step S23: performing near-surface airflow disturbance analysis on the real-time monitoring data of the low-altitude flying target based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data;

[0019] Step S24: Estimating the probability of flight loss of control based on the near-surface airflow disturbance data and the real-time monitoring data of the low-altitude flight target to obtain flight loss of control probability data.

[0020] The present invention uses radar to monitor flying targets within a low-altitude monitoring range in real time, accurately capturing the dynamic state and position of an aircraft. This process provides continuous, real-time data updates, enabling timely monitoring of the aircraft's trajectory, speed, and spatial position. This real-time monitoring is crucial for ensuring flight safety, as it tracks changes in the flying target, helps detect and respond to anomalies, enhances comprehensive understanding of the aircraft's status, and provides key data support for subsequent spatial distance calculations and airflow analysis. By calculating spatial relative distances between high-altitude surface element marker data and real-time low-altitude flying target monitoring data, the relative position between the flying target and high-altitude surface obstacles can be accurately assessed. This calculation reveals the actual distance between the aircraft and ground obstacles, thereby identifying any spatial conflicts. This data is crucial for aircraft path planning and safe obstacle avoidance, as it provides information on the distance between the aircraft and obstacles in specific environments, enabling timely adjustments and avoidance during flight, reducing the risk of accidents. Analyzing near-surface airflow disturbances for low-altitude flying targets based on the flying target-surface element spatial relative distance data provides a deeper understanding of the impact of airflow disturbances on the aircraft. This analysis process identifies the areas and intensities of airflow disturbances by evaluating the airflow disturbances of the flight target at different spatial distances. This near-surface airflow disturbance data provides crucial environmental information for the aircraft, helping to understand and predict the impact of airflow changes on flight stability. This allows for the adoption of appropriate flight strategies to address airflow disturbances and ensure flight safety. Estimating the probability of loss of control of low-altitude flight targets based on near-surface airflow disturbance data quantifies the risk of loss of control of the aircraft in the current airflow environment. This estimate, by comprehensively considering the potential impact of airflow disturbances on the aircraft, provides a scientific assessment of the likelihood of loss of control. This risk assessment is of great significance to pilots or automated flight systems, as it can provide early warning information during flight, enabling pilots to adjust their flight strategies in a timely manner, reduce the probability of loss of control, improve flight safety, and ensure the successful completion of the mission.

[0021] Preferably, step S23 includes the following steps:

[0022] Step S231: extracting the flight speed of the low-altitude flying target real-time monitoring data to obtain the target flight speed data;

[0023] Step S232: Decomposing the multi-directional airflow interference vector during the flight path based on the target flight speed data and the flight target-surface element spatial relative distance data to obtain multi-directional airflow interference vector data;

[0024] Step S233: performing interference airflow manifold feature recognition on the multi-directional airflow interference vector data to obtain interference airflow manifold feature data;

[0025] Step S234: performing near-surface airflow disturbance analysis on the real-time monitoring data of the low-altitude flight target according to the interfering airflow manifold characteristic data to obtain near-surface airflow disturbance data.

[0026] By extracting flight speed from real-time monitoring data of low-altitude flight targets, the present invention can provide aircraft speed information at specific moments. This speed data is crucial for accurately analyzing aircraft behavior in low-altitude environments, as it directly affects the extent of airflow disturbances affecting the aircraft. By acquiring target flight speed data, the dynamic state of the aircraft can be precisely understood, providing basic data for subsequent airflow disturbance analysis and enabling a more detailed and reliable assessment of the aircraft's performance in complex airflow environments. Multidirectional airflow disturbance vector decomposition during the flight path, based on target flight speed data and target-surface element spatial relative distance data, can identify the direction and intensity of airflow disturbances experienced by the aircraft during the flight path. This process, by decomposing multidirectional airflow disturbance vectors, reveals the impact of airflow on the aircraft in different directions, providing important data for accurately predicting aircraft performance in complex airflow environments. This decomposition capability helps better understand the characteristics of airflow disturbances and provides a scientific basis for adjusting aircraft flight strategies, thereby improving flight stability and safety. Identifying the manifold features of the disturbed airflow using multidirectional airflow disturbance vector data enables in-depth analysis of the manifold characteristics of the airflow disturbances. This process can identify the pattern, intensity, and variation of airflow disturbances, thereby providing a comprehensive understanding of the structural characteristics of airflow disturbances. By obtaining the manifold characteristic data of the disturbing airflow, the impact of airflow disturbances on the aircraft can be more accurately described, helping pilots or automatic flight systems identify potential areas of airflow disturbance and formulate appropriate flight adjustment strategies to ensure flight safety. By analyzing near-surface airflow disturbances based on real-time monitoring data of low-altitude flight targets based on the manifold characteristic data of the disturbing airflow, the impact of airflow manifold characteristics on the aircraft can be comprehensively considered. This analysis process provides a comprehensive assessment of near-surface airflow disturbances by combining manifold characteristic data with real-time aircraft monitoring data. This assessment can reveal the actual impact of airflow disturbances, predict airflow problems encountered by the aircraft, and provide timely adjustment recommendations to pilots or automatic flight systems, thereby improving the stability and safety of the aircraft during low-altitude flight.

[0027] Preferably, step S24 includes the following steps:

[0028] Step S241: identifying wind notch behavior during the flight path of the low-altitude flight target real-time monitoring data based on the near-surface airflow disturbance data to obtain wind notch behavior identification data;

[0029] Step S242: performing flight airflow load simulation calculation on the low-altitude flight target real-time monitoring data based on the wind cut behavior recognition data to obtain target flight airflow load data;

[0030] Step S243: performing load intensity distribution analysis on the target flight airflow load data to obtain load intensity distribution data;

[0031] Step S244: performing pre-identification of the out-of-control behavior of the low-altitude flying target based on the load intensity distribution data and the wind notch behavior identification data to obtain pre-identification data of the out-of-control behavior;

[0032] Step S245: Estimating the flight out-of-control probability of the low-altitude flight target real-time monitoring data based on the out-of-control behavior pre-identification data, the load intensity distribution data, and the wind notch behavior identification data to obtain flight out-of-control probability data.

[0033] This invention uses near-surface airflow disturbance data to identify wind notch behavior in real-time monitoring data of low-altitude flight targets, accurately identifying wind notch phenomena encountered by an aircraft during its flight path. This process, by analyzing airflow disturbance data, can detect whether significant wind speed variations or wind notch effects exist in the area the aircraft passes through. Wind notch behavior identification reveals the impact of sudden airflow changes on the aircraft, providing critical data for subsequent load calculations and loss of control predictions. This helps to promptly address flight risks associated with airflow fluctuations and ensure aircraft stability and safety. Using wind notch behavior identification data, flight airflow load simulation calculations based on real-time monitoring data of low-altitude flight targets can quantify the specific airflow loads imposed on the aircraft by wind notches and other airflow disturbances. This simulation, combined with actual wind notch identification data, calculates the loads borne by the aircraft under different airflow conditions, providing basic data for subsequent load intensity analysis. Accurate simulation of airflow load data can help predict aircraft performance in different airflow environments and provide valuable insights for aircraft design and operation. Load intensity distribution analysis of target flight airflow load data provides a detailed understanding of the intensity distribution of airflow loads on the aircraft. This analysis, by mapping and evaluating the spatial distribution of airflow loads, reveals the load intensity and distribution patterns experienced by various aircraft components. Obtaining load intensity distribution data helps identify the forces acting on the aircraft during different flight phases and airflow conditions, providing crucial information for assessing the aircraft's load-carrying capacity and safety, enabling appropriate improvements during design and maintenance. Pre-emptive identification of low-altitude flight target loss of control, based on load intensity distribution data and wind-cut behavior recognition data, can predict the risk of loss of control. This pre-emptive identification process combines load intensity and wind-cut behavior information to assess the probability of loss of control under airflow disturbances. Pre-emptive identification of loss of control behavior can identify potential loss of control risks in advance, providing early warning to the pilot or automated flight system, enabling appropriate preventive measures to mitigate loss of control and ensure flight safety. Estimating the probability of flight loss of control based on pre-emptive identification of loss of control behavior, load intensity distribution data, and wind-cut behavior recognition data, combined with real-time low-altitude flight target monitoring data, provides a comprehensive assessment of the actual probability of loss of control. This estimation process integrates information from multiple data sources to provide a comprehensive loss of control risk assessment. By accurately calculating the probability of flight loss of control, strong data support can be provided to pilots or automatic control systems, enabling them to adjust and respond based on actual risks, optimize flight strategies, and significantly improve the safety and stability of flight missions.

[0034] Preferably, pre-identifying the out-of-control behavior of a low-altitude flying target based on the load intensity distribution data and the wind notch behavior identification data includes the following steps:

[0035] Perform airflow directionality analysis on the wind cutout behavior recognition data to obtain wind cutout airflow directionality data;

[0036] The air pressure intensity of the three-dimensional cross section of the wind cut behavior identification data is calculated based on the airflow directionality data of the wind cut to obtain the air pressure intensity data of the three-dimensional cross section of the space;

[0037] Based on the air pressure intensity data of the three-dimensional space section and the airflow directionality data of the wind cut, the maximum flight elevation angle of the airflow impact of the low-altitude flying target is calculated to obtain the maximum flight elevation angle data of the airflow impact;

[0038] Based on the air pressure intensity data of the three-dimensional space section and the airflow directionality data of the wind cut, the maximum lateral / longitudinal deviation angle of the airflow impact of the low-altitude flying target is calculated to obtain the maximum lateral / longitudinal deviation angle data of the airflow impact;

[0039] According to the maximum flight elevation angle data of airflow impact and the maximum lateral / longitudinal deviation angle data of airflow impact, the out-of-control behavior pre-identification of the low-altitude flying target is performed to obtain the out-of-control behavior pre-identification data.

[0040] The present invention can clarify the flow direction of the airflow in the wind cut area and its changing patterns by performing directional analysis on the wind cut behavior. This analysis process can reveal the specific direction of the airflow in the wind cut area and its impact on the aircraft. Accurate wind cut airflow directional data provides a key basis for further pressure intensity calculation and aircraft airflow impact assessment. This helps to understand the direction of the airflow on the aircraft, thereby providing data support for subsequent prediction of out-of-control behavior and formulation of adjustment strategies, and improving flight safety. By calculating the air pressure intensity of three-dimensional spatial cross-sections, the pressure distribution of the airflow in the wind cut area can be understood in detail. This process involves accurately calculating the pressure intensity of the airflow on different spatial cross-sections, thereby revealing the actual pressure impact of the airflow on the aircraft. Accurate air pressure intensity data helps to evaluate the specific effect of the airflow on the aircraft, and provides a scientific basis for further analysis of airflow impact and aircraft out-of-control risks, enhances the understanding of the aircraft's airflow load, and thus provides a strong guarantee for flight safety. By calculating the maximum flight elevation angle of the airflow impact, the maximum elevation angle impact that the aircraft can withstand in the wind cut area can be predicted. This data reflects the maximum acceptable pitch angle of the aircraft under specific airflow conditions, thereby assessing the aircraft's control limits under airflow shock. Understanding the maximum pitch angle helps the pilot or the automatic control system adjust the flight attitude, avoid the risk of loss of control due to airflow shock, and improve the aircraft's stability and safety in complex airflow environments. By calculating the maximum lateral and longitudinal deviation angles due to airflow shock, the aircraft's lateral and longitudinal stability under airflow disturbances can be assessed. This data reveals the maximum lateral and longitudinal deviations of the aircraft under specific airflow conditions, thereby predicting the impact of airflow on the flight path. Accurate deviation angle data is crucial for trajectory control and safe operation of the aircraft, helping to maintain flight stability in complex airflow environments and prevent deviation and loss of control due to airflow shock. By integrating the maximum pitch angle and maximum lateral / longitudinal deviation angle data due to airflow shock, a comprehensive assessment of the aircraft's potential loss of control behavior can be made. This pre-identification process combines multiple airflow shock factors to predict the risk of loss of control under complex airflow conditions. Accurate pre-identification data for loss of control behavior provides timely warnings to the pilot or the automatic flight system, enabling the development of effective flight strategies and adjustments, thereby effectively mitigating the risk of loss of control and improving mission safety and reliability.

[0041] Preferably, step S3 includes the following steps:

[0042] Step S31: Predicting the flight target deviation trajectory based on the near-surface airflow disturbance data and the flight loss of control probability data to obtain flight target deviation trajectory prediction data;

[0043] Step S32: performing trajectory smoothing analysis on the flight target deviation trajectory estimation data to obtain deviation trajectory smoothing data;

[0044] Step S33: constructing a flight target state recognition model based on the flight loss of control probability data and the deviation trajectory smoothing data based on the Q-Learning algorithm to obtain a flight target state recognition model.

[0045] The present invention uses near-surface airflow disturbance data to predict flight target deviation trajectories based on flight loss-of-control probability data, enabling accurate prediction of a target's trajectory in complex airflow environments. This step analyzes the impact of airflow disturbances on the aircraft to generate an estimate of the future flight path, revealing the aircraft's motion trends in a loss-of-control scenario. Such predictions are crucial for developing response strategies and optimizing flight plans, helping to identify potential deviation risks in advance and ensure timely adjustments during flight to maintain flight stability. Trajectory smoothing analysis of the estimated flight target deviation trajectory data helps reduce trajectory fluctuations caused by airflow disturbances. Trajectory smoothing analysis applies smoothing techniques to process the estimated trajectory data to eliminate or reduce the effects of noise and irregular disturbances. This process generates more consistent and stable deviation trajectory data, providing more accurate trajectory predictions, helping the flight control system make more effective decisions, and improving the aircraft's trajectory tracking capability and flight safety. A flight target state recognition model is constructed based on the flight loss-of-control probability data and deviation trajectory smoothing data using the Q-Learning algorithm, resulting in an intelligent flight target state recognition system. Through continuous learning and optimization, the Q-Learning algorithm constructs an efficient state recognition model based on flight loss probability and trajectory data. This model can identify the state of a flying target in real time, predict aircraft behavior, and provide decision support. Application of this model effectively improves the ability to accurately assess aircraft state, optimizes flight control strategies, reduces the risk of flight loss, and enhances overall flight safety.

[0046] Preferably, step S32 includes the following steps:

[0047] Step S321: performing trajectory offset time series difference calculation on the flight target offset trajectory estimation data to obtain trajectory offset time series difference data;

[0048] Step S322: performing a displacement discontinuity analysis on the flight target displacement trajectory estimation data based on the trajectory displacement time series difference data to obtain trajectory displacement discontinuity data;

[0049] Step S323: performing trajectory smoothing analysis on the flight target deviation trajectory estimation data according to the trajectory deviation discontinuity data to obtain deviation trajectory smoothing data.

[0050] The present invention calculates trajectory deviation time-series differences on estimated trajectory data to quantify the magnitude of trajectory change at different time points. This process, by calculating trajectory deviation differences between each time point, reveals the rate and magnitude of trajectory change, providing information about the dynamic temporal changes of the target. Understanding this difference data is crucial for identifying and analyzing abnormal fluctuations and sudden changes in the flight trajectory. Using this data, the flight control system can more accurately predict future trajectory changes and make targeted adjustments, improving flight path prediction accuracy and stability. Discontinuity analysis of estimated trajectory data based on trajectory deviation time-series difference data assesses the consistency and stability of trajectory changes. Discontinuity analysis detects discontinuities or sudden shifts in trajectory changes, helping to identify potential anomalies or instability. This analysis provides information on trajectory continuity and stability, revealing breaks and irregular fluctuations that may occur during flight. This is crucial for developing smooth and stable flight control strategies, helping to prevent the risk of loss of control due to discontinuous deviations and ensuring flight path consistency and flight safety. Trajectory smoothing analysis of the target's estimated trajectory data based on trajectory deviation discontinuity data optimizes the smoothness of the trajectory data. Trajectory smoothing analysis processes the discontinuity data to make the target's trajectory smoother and more continuous. This process helps eliminate trajectory fluctuations caused by noise and discontinuity, making the trajectory data more stable and reliable. The smoothed trajectory data more accurately reflects the target's actual flight path, providing clearer reference information for the flight control system. By reducing irregularities and sudden changes in the trajectory, the aircraft can be controlled based on a more stable trajectory, further improving flight safety and control accuracy.

[0051] Preferably, step S33 includes the following steps:

[0052] Step S331: Calculating the local risk flight curvature based on the flight out of control probability data and the deviation trajectory smoothing data to obtain local risk flight curvature data;

[0053] Step S332: dividing the local risk flight curvature data into a training set and a test set to obtain a local risk flight curvature training set and a local risk flight curvature test set;

[0054] Step S333: constructing an initial flight target state recognition model for the local risk flight curvature training set based on the Q-Learning algorithm to obtain the initial flight target state recognition model;

[0055] Step S334: Performing model optimization testing on the initial flight target state recognition model using the local risk flight curvature test set to obtain a flight target state recognition model.

[0056] The present invention can identify and evaluate local risk points within a flight trajectory by calculating local risk flight curvature based on flight loss of control probability data and offset trajectory smoothing data. Local risk flight curvature data can reveal the curvature and rate of change of the flight trajectory, thereby helping to identify flight risk areas. This data allows for more accurate analysis of the risk profile of a flight target within a specific area, providing valuable reference for subsequent flight target state identification. This helps provide early warning of potential risks during flight, thereby improving flight safety and stability. Dividing the local risk flight curvature data into a training set and a test set provides effective data support for model training and evaluation. This partitioning allows the training set to be used to construct and optimize an initial flight target state identification model, while the test set is used to evaluate the model's performance and generalization capabilities. This data partitioning method ensures that the model learns comprehensive features during training while also enabling verification of its actual effectiveness and predictive capabilities using the test set, thereby improving the model's reliability and accuracy. By constructing an initial flight target state identification model based on the local risk flight curvature training set using the Q-Learning algorithm, an intelligent state recognition system can be established. By continuously learning from local risk flight curvature data, the Q-Learning algorithm gradually optimizes the model's recognition capabilities, thereby constructing an initial model capable of accurately identifying flight target states. This process facilitates efficient flight state recognition, provides a scientific basis for flight control and decision-making, and enhances the intelligent level of flight safety management. Model optimization testing of the initial flight target state recognition model using a local risk flight curvature test set allows for evaluation and improvement of model performance. By examining the model's predictive capabilities on an independent test dataset, optimization testing can identify deficiencies in the model's practical application and enable appropriate adjustments and improvements. This process ensures that the resulting flight target state recognition model possesses good generalization and accuracy, enabling more effective real-time flight state recognition and risk assessment, thereby improving overall flight safety.

[0057] Preferably, the present invention further provides a low-altitude flying target recognition system based on a three-dimensional digital globe, for executing the low-altitude flying target recognition method based on a three-dimensional digital globe as described above. The low-altitude flying target recognition system based on a three-dimensional digital globe comprises:

[0058] The surface element marking module is used to obtain low-altitude monitoring range data; the low-altitude monitoring range data is marked with high-altitude surface elements to obtain high-altitude surface element marking data;

[0059] The flight loss control probability estimation module is used to calculate the spatial relative distance of the towering surface element marker data to obtain the flight target-surface element spatial relative distance data; perform near-surface airflow disturbance analysis based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data; and estimate the flight loss control probability based on the near-surface airflow disturbance data to obtain the flight loss control probability data;

[0060] The flight target state recognition model construction module is used to construct a flight target state recognition model based on the flight loss of control probability data based on the Q-Learning algorithm to obtain a flight target state recognition model;

[0061] The risk flight intention prediction module is used to predict the risk flight intention of low-altitude flying targets based on the flight target state recognition model, obtain the target risk flight intention data, and feed back the target risk flight intention data to the terminal.

[0062] The present invention has the beneficial effect of accurately identifying and recording tall objects on the surface that could impact an aircraft by acquiring low-altitude monitoring range data and marking tall surface elements. This process facilitates the construction of a detailed map of the flight environment, providing important foundational data for subsequent flight safety analysis. The tall surface element marking data can help identify potential obstacles in the flight path, enabling these obstacles to be avoided during flight planning and operations, thus reducing the occurrence of flight accidents. By calculating the relative spatial distances between the flight target and tall surface elements, a detailed understanding of the actual spatial relationship between the aircraft and surface obstacles can be obtained. This process enables the assessment of the aircraft's relative position to obstacles during low-altitude flight and further analyzes the impact of near-surface airflow disturbances. Through in-depth analysis of these disturbances, potential areas of airflow interference can be identified, and the impact of airflow on aircraft stability can be predicted, allowing appropriate control measures to be taken during flight. Estimating the probability of flight loss of control based on near-surface airflow disturbance data is of great significance. By analyzing the impact of airflow disturbances on the aircraft, the risk of aircraft loss of control can be quantified, providing a scientific basis for flight operations. This estimation helps pilots or automated flight systems better manage airflow disturbances during flight, improving flight safety and reducing the incidence of accidents. A flight target state recognition model constructed using the Q-Learning algorithm effectively processes flight loss of control probability data and learns the risk characteristics of different flight states. This model is continuously optimized through reinforcement learning, enabling it to accurately identify and predict the aircraft's state under various environmental conditions. This model not only helps understand the potential safety impacts of different flight states but also provides information on how to adjust flight strategies under specific flight states, thereby enhancing the aircraft's adaptability and safety in complex environments. Through a dynamically updated learning mechanism, the model continuously improves recognition accuracy and provides customized safety measures for different flight environments. Risky flight intention prediction based on the flight target state recognition model provides real-time early warning of potential risks. By predicting the target's risky flight intention, the flight system can proactively adjust flight strategies or alert the pilot to prevent flight hazards. This prediction information is transmitted through a terminal feedback mechanism, ensuring that the pilot or automated flight system has timely access to the latest risk assessment data and can make necessary safety adjustments. This not only improves flight safety but also enhances emergency response capabilities and significantly reduces flight risks. Through real-time feedback and adjustments, a high level of safety can be maintained during the flight.Therefore, the present invention is an optimization process for a traditional low-altitude flight target identification method based on three-dimensional digital earth, which solves the problems of inaccurate analysis of the probability of low-altitude flight target loss of control and inaccurate judgment of its flight risk intention in the traditional low-altitude flight target identification method based on three-dimensional digital earth, improves the accuracy of analysis of the probability of low-altitude flight target loss of control and improves the accuracy of judgment of flight risk intention. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 The figure is a flowchart of a method for identifying low-altitude flying targets based on a three-dimensional digital globe;

[0064] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0065] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0066] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0067] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0068] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0069] To achieve this, please refer to Figures 1 to 2A method for identifying low-altitude flying targets based on a three-dimensional digital globe comprises the following steps:

[0070] Step S1: Acquire low-altitude monitoring range data; perform high-altitude surface element marking on the low-altitude monitoring range data to obtain high-altitude surface element marking data;

[0071] Step S2: Calculating the spatial relative distance of the towering surface element marker data to obtain flight target-surface element spatial relative distance data; performing near-surface airflow disturbance analysis based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data; and estimating the flight loss-of-control probability based on the near-surface airflow disturbance data to obtain flight loss-of-control probability data.

[0072] Step S3: constructing a flight target state recognition model based on the flight loss of control probability data based on the Q-Learning algorithm to obtain a flight target state recognition model;

[0073] Step S4: predict the risky flight intention of the low-altitude flying target based on the flight target state recognition model, obtain the target risky flight intention data, and feed back the target risky flight intention data to the terminal.

[0074] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for identifying low-altitude flying targets based on a three-dimensional digital globe according to the present invention. In this example, the method for identifying low-altitude flying targets based on a three-dimensional digital globe includes the following steps:

[0075] Step S1: Acquire low-altitude monitoring range data; perform high-altitude surface element marking on the low-altitude monitoring range data to obtain high-altitude surface element marking data;

[0076] In this embodiment of the present invention, detailed surface elevation measurements are performed using LiDAR and Synthetic Aperture Radar (SAR) systems. These measurements cover altitude variations in low-altitude areas, forming a three-dimensional digital Earth model. Data processing software then analyzes the acquired three-dimensional terrain data to identify all tall surface features, such as towers, buildings, or mountains. The outlines and locations of these tall surface features are labeled as tall surface feature marker data for further processing.

[0077] Step S2: Calculating the spatial relative distance of the towering surface element marker data to obtain flight target-surface element spatial relative distance data; performing near-surface airflow disturbance analysis based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data; and estimating the flight loss-of-control probability based on the near-surface airflow disturbance data to obtain flight loss-of-control probability data.

[0078] In an embodiment of the present invention, spatial relative distance calculation is performed on the marked towering surface element data. First, the current position of the flight target in the three-dimensional digital earth model is used to calculate the distance between it and all towering surface elements. This calculation is based on straight-line distance or surface elevation difference, and is accurately measured using spatial geometry algorithms. Subsequently, based on these distance data, near-surface airflow disturbance analysis is performed. Using meteorological data and aerodynamic theory, near-surface airflow disturbance data is generated by simulating the air flow around the flight target. Finally, combining the airflow disturbance data and the dynamic response characteristics of the flight target, statistical methods are applied to estimate the probability of flight loss of control to form flight loss of control probability data. All data processing and calculations are completed using dedicated analysis tools to ensure the accuracy and reliability of the results.

[0079] Step S3: constructing a flight target state recognition model based on the flight loss of control probability data based on the Q-Learning algorithm to obtain a flight target state recognition model;

[0080] In an embodiment of the present invention, a flight target state recognition model is constructed based on the Q-Learning algorithm. First, the previously obtained flight loss of control probability data is used as the input of the Q-Learning algorithm, where the state of the flight target is represented as the state of the environment. Each state is paired with its corresponding flight loss of control probability as the initial data for training the Q-Learning algorithm. By defining the state space, action space and reward function, the Q-Learning model is trained to optimize the strategy, thereby identifying the risks of the flight target in different states. During the training process, the method of iteratively updating the Q value table is used to gradually improve the model's ability to accurately identify the flight target state. After the model training is completed, a Q-Learning model that can predict the flight target state is obtained, which can evaluate the flight risk according to different flight states and environmental conditions.

[0081] Step S4: predict the risky flight intention of the low-altitude flying target based on the flight target state recognition model, obtain the target risky flight intention data, and feed back the target risky flight intention data to the terminal.

[0082] In an embodiment of the present invention, a flight target state recognition model is constructed to predict risky flight intentions. First, real-time flight target data is input into the recognition model. The model analyzes the current state of the flight target based on the input data, and predicts future flight intentions in combination with flight environment information. The model predicts the risky flight intentions of the flight target based on its state and behavior, such as approaching an obstacle or deviating from the planned route. The prediction results are used to generate target risk flight intention data, which specifically includes the predicted risk type and probability of occurrence. Finally, the target risk flight intention data is fed back to the terminal in real time through the wireless communication system for subsequent processing or alarm triggering. All prediction and feedback operations must ensure the timeliness and accuracy of data transmission.

[0083] Preferably, step S1 includes the following steps:

[0084] Step S11: Acquire low-altitude monitoring range data;

[0085] Step S12: collecting monitoring range environment data from the low-altitude monitoring range data to obtain monitoring range environment data;

[0086] Step S13: marking the high-altitude surface elements on the low-altitude monitoring range data according to the monitoring range environment data to obtain high-altitude surface element marking data.

[0087] In an embodiment of the present invention, multiple remote sensing technologies are used to collect surface elevation data for a designated area. The target area is scanned to collect high-precision three-dimensional terrain data. Simultaneously, synthetic aperture radar (SAR) is used to detect the surface, supplementing the limitations of lidar under certain conditions. All collected data is transmitted via a data storage device to a processing system to form a comprehensive low-altitude monitoring range data set. This data set contains detailed information on surface elevation changes, object distribution, and their three-dimensional spatial distribution, providing foundational data for subsequent processing. Monitoring range environmental data is then collected for the low-altitude monitoring range data. First, the low-altitude monitoring range data is input into an environmental data collection system, which includes meteorological sensors and environmental monitoring equipment. These devices provide real-time meteorological information, such as wind speed, temperature, and humidity, as well as other environmental factors, such as vegetation cover and surface material type, which all affect environmental conditions for low-altitude flight. Using this information, data fusion technology combines the environmental data with terrain data to form monitoring range environmental data. This environmental data covers all factors affecting low-altitude flight, providing comprehensive background information for further analysis. The low-altitude monitoring range data is then labeled with elevated surface elements based on the monitoring range environmental data. First, using surface material and environmental characteristics from environmental data, tall surface elements within the low-altitude monitoring range are identified and labeled. Using a terrain analysis algorithm, areas of unusual surface height are extracted and labeled as tall surface elements. A feature recognition algorithm based on environmental data is then applied to categorize these tall areas as buildings, towers, or natural terrain. Ultimately, tall surface element labeling data is generated, containing the specific locations and attributes of all identified tall surface elements, providing essential data for flight target identification and risk assessment.

[0088] Preferably, step S2 includes the following steps:

[0089] Step S21: Real-time monitoring of low-altitude flight targets in the low-altitude monitoring range data is performed by radar to obtain real-time monitoring data of low-altitude flight targets;

[0090] Step S22: performing spatial relative distance calculation on the high-rise surface element marker data based on the real-time monitoring data of the low-altitude flight target to obtain the flight target-surface element spatial relative distance data;

[0091] Step S23: performing near-surface airflow disturbance analysis on the real-time monitoring data of the low-altitude flying target based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data;

[0092] Step S24: Estimating the probability of flight loss of control based on the near-surface airflow disturbance data and the real-time monitoring data of the low-altitude flight target to obtain flight loss of control probability data.

[0093] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0094] Step S21: Real-time monitoring of low-altitude flight targets in the low-altitude monitoring range data is performed by radar to obtain real-time monitoring data of low-altitude flight targets;

[0095] In an embodiment of the present invention, radar is used to monitor low-altitude flying targets in low-altitude monitoring range data in real time. A radar system installed on a ground-based monitoring platform continuously scans the low-altitude area. These radar systems are capable of detecting and tracking flying targets within the monitoring range in real time, and obtaining information such as their position, speed, and altitude. The radar system transmits electromagnetic wave signals and receives echo signals reflected from the flying targets. Based on the time delay and frequency variation of the signals, the spatial coordinates and dynamic parameters of the targets are calculated. All acquired real-time data is recorded and stored to form real-time monitoring data for low-altitude flying targets.

[0096] Step S22: performing spatial relative distance calculation on the high-rise surface element marker data based on the real-time monitoring data of the low-altitude flight target to obtain the flight target-surface element spatial relative distance data;

[0097] In an embodiment of the present invention, spatial relative distance calculations are performed on the tall surface element marking data based on the real-time monitoring data of low-altitude flight targets. The flight target position coordinates in the real-time monitoring data of low-altitude flight targets are compared with the element position coordinates in the tall surface element marking data. In a specific implementation, the straight-line distance between each flight target and the ground feature marked as a tall surface element is calculated. Distance calculations are performed using a three-dimensional coordinate system, taking into account the height changes of the terrain, to obtain spatial relative distance data between the flight target and each tall surface element. This data will be used for subsequent airflow disturbance analysis and flight risk assessment.

[0098] Step S23: performing near-surface airflow disturbance analysis on the real-time monitoring data of the low-altitude flying target based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data;

[0099] In an embodiment of the present invention, near-surface airflow disturbance analysis is performed on real-time monitoring data of low-altitude flight targets based on the spatial relative distance data between the flight target and the surface elements. First, the spatial relative distance data between the flight target and the surface elements is input into an airflow disturbance analysis model. The model uses computational fluid dynamics (CFD) technology or wind tunnel test data to simulate the disturbance of near-surface airflow, considering the influence of the relative position and relative motion between the flight target and the surrounding towering surface elements on the airflow. By analyzing the changes in the airflow field around the flight target, near-surface airflow disturbance data is generated. This data reflects the impact of airflow instability caused by terrain features on the flight target.

[0100] Step S24: Estimating the probability of flight loss of control based on the near-surface airflow disturbance data and the real-time monitoring data of the low-altitude flight target to obtain flight loss of control probability data.

[0101] In an embodiment of the present invention, the probability of flight loss of control is estimated based on real-time monitoring data of low-altitude flight targets based on near-surface airflow disturbance data. Combined with the near-surface airflow disturbance data, the stability of the flight target in the current airflow environment is assessed. The specific method includes applying a flight mechanics model to quantify the impact of airflow disturbances on the flight target and calculate the risk of loss of control of the flight target under different airflow conditions. The generated loss of control probability data reflects the likelihood of the flight target losing control under the current environment. This data will be used for risk warning and flight safety management, helping to take necessary flight adjustments or safety measures.

[0102] Preferably, step S23 includes the following steps:

[0103] Step S231: extracting the flight speed of the low-altitude flying target real-time monitoring data to obtain the target flight speed data;

[0104] Step S232: Decomposing the multi-directional airflow interference vector during the flight path based on the target flight speed data and the flight target-surface element spatial relative distance data to obtain multi-directional airflow interference vector data;

[0105] Step S233: performing interference airflow manifold feature recognition on the multi-directional airflow interference vector data to obtain interference airflow manifold feature data;

[0106] Step S234: performing near-surface airflow disturbance analysis on the real-time monitoring data of the low-altitude flight target according to the interfering airflow manifold characteristic data to obtain near-surface airflow disturbance data.

[0107] In one embodiment of the present invention, flight velocity is extracted from real-time monitoring data of low-altitude flying targets. First, the target's linear velocity components in three-dimensional space are extracted from the velocity information in the real-time monitoring data acquired by a radar system. The target's velocity is measured using the Doppler effect, utilizing the frequency shift of the radar signal. These velocity components are then integrated to calculate the target's overall flight velocity data. This data provides essential dynamic information for subsequent airflow disturbance analysis. Multidirectional airflow disturbance vector decomposition is performed during the flight path based on the target's flight velocity data and the spatial relative distance between the target and ground elements. First, a flight path model is constructed based on the target's velocity data and its spatial relative distance to ground elements. Using an airflow disturbance vector decomposition method, the multidirectional airflow disturbances encountered by the target during its flight path are decomposed to obtain airflow disturbance components in different directions. This method provides a detailed understanding of the impact of airflow disturbances on the target and generates multidirectional airflow disturbance vector data. The multidirectional airflow disturbance vector data is then used to identify the manifold features of the disturbances. Fluid dynamics analysis methods are used to process the multidirectional airflow disturbance vector data and identify the manifold features of the airflow disturbances. Specifically, it includes analyzing the pattern and shape of airflow disturbances, such as vortex, laminar flow or turbulence. By identifying the manifold characteristics of the interfering airflow, the manifold characteristic data of the interfering airflow is obtained, which describes the specific flow pattern of the airflow disturbance and its impact on the flight target. According to the manifold characteristic data of the interfering airflow, the real-time monitoring data of the low-altitude flight target is analyzed for near-surface airflow disturbances. Combined with the manifold characteristic data of the interfering airflow, the stability of the flight target in the current airflow environment is evaluated. The actual impact of the airflow manifold characteristics on the flight target is analyzed, and the degree of interference of the airflow disturbance on the flight path is calculated using the airflow disturbance model. The generated near-surface airflow disturbance data reflects the airflow instability encountered by the flight target under the current environmental conditions, providing a basis for further flight safety assessment.

[0108] Preferably, step S24 includes the following steps:

[0109] Step S241: identifying wind notch behavior during the flight path of the low-altitude flight target real-time monitoring data based on the near-surface airflow disturbance data to obtain wind notch behavior identification data;

[0110] Step S242: performing flight airflow load simulation calculation on the low-altitude flight target real-time monitoring data based on the wind cut behavior recognition data to obtain target flight airflow load data;

[0111] Step S243: performing load intensity distribution analysis on the target flight airflow load data to obtain load intensity distribution data;

[0112] Step S244: performing pre-identification of the out-of-control behavior of the low-altitude flying target based on the load intensity distribution data and the wind notch behavior identification data to obtain pre-identification data of the out-of-control behavior;

[0113] Step S245: Estimating the flight out-of-control probability of the low-altitude flight target real-time monitoring data based on the out-of-control behavior pre-identification data, the load intensity distribution data, and the wind notch behavior identification data to obtain flight out-of-control probability data.

[0114] In one embodiment of the present invention, wind notch behavior identification is performed on real-time monitoring data of low-altitude flight targets based on near-surface airflow disturbance data, thereby generating wind notch behavior identification data. Specifically, a laser radar array and high-frequency ultrasonic airflow detection devices are deployed to collect wind speed, direction, and airflow disturbance characteristics around the low-altitude flight path. This data is processed using optical interferometry to identify sudden changes in velocity gradients and directional differences in the airflow, thereby locating the presence of wind notches. Data parsing and vortex feature extraction techniques are used to refine and analyze abnormal airflow patterns in the monitoring data, determining the intensity, location, and spread of wind notch behavior along the target's flight path. To improve identification accuracy, real-time data cross-validation techniques are used to spatially overlay data from multiple sensors to eliminate false positives and false negatives. The resulting wind notch behavior identification data provides detailed wind notch characteristics, including intensity, location, and impact. Based on the wind notch behavior identification data, flight airflow load simulation is performed on the real-time monitoring data of the low-altitude flight target to generate target flight airflow load data. First, combined with the characteristic information from wind notch identification, the identified wind shear area is input into a high-precision airflow load simulation system. This system uses sophisticated aerodynamic calculation methods to perform point-by-point calculations of the airflow pressure, shear force, and lateral disturbances experienced by the target. During the simulation, fluid dynamics equations and large eddy simulation (LES) are used to calculate the distribution of dynamic loads imposed on the aircraft surface by the airflow within the wind shear region, with particular attention paid to the transient effects of the airflow on the wings, tail, and fuselage. After analysis and calculation, the load data is presented as a three-dimensional spatial distribution diagram, detailing the load intensity and direction at each key component, providing input for subsequent intensity distribution analysis. Load intensity distribution analysis is performed on the target flight airflow load data to generate load intensity distribution data. In specific implementation, high-resolution load distribution imaging technology is used to visualize the dynamic loads on the aircraft in the wind shear region. First, the airflow load data is sampled at high frequency and converted into a load time series. Fourier transforms are used to analyze the load intensity characteristics at different frequencies, identifying peak load intensity regions and durations. Next, an automatic load distribution segmentation algorithm is used to identify high-intensity load regions, and the stress concentration and diffusion patterns at each load point are analyzed. During the analysis process, load distribution errors are corrected by comparing historical load data to ensure the accuracy and practicality of the data. The resulting load intensity distribution data provides a detailed description of the load concentration at each location and the dynamic evolution trend of the load, laying the data foundation for pre-identification of out-of-control behavior. Based on the load intensity distribution data and wind cut behavior identification data, pre-identification of the out-of-control behavior of low-altitude flying targets is performed to obtain pre-identification data for out-of-control behavior. The specific operation includes first jointly analyzing the load intensity distribution data and wind cut behavior data, and using the stress-strain correspondence to evaluate the force response of the aircraft in the key disturbance area.Using stress concentration and strain deviation, the system identifies hazardous areas that could lead to structural overload or reduced controllability. Using a critical stress threshold identification algorithm, the system assesses the aircraft's controllability under different load scenarios, identifying critical points along the flight path that could lead to loss of control. During the identification process, the system pays special attention to subtle deviations in the aircraft's attitude and trajectory to proactively assess potential loss of control. This system then outputs pre-identification data for loss of control behavior, including the specific loss of control area, time period, and triggering conditions. Using pre-identification data for loss of control behavior, load intensity distribution data, and wind shear behavior identification data, the system estimates the probability of flight loss of control based on real-time monitoring data of low-altitude flight targets, generating flight loss of control probability data. First, the pre-identification data is overlaid with the real-time monitoring data, and spatial risk mapping technology is used to align each loss of control risk point with the flight path. Next, using a loss of control probability calculation formula, the triggering conditions for each risk point are quantified. By combining key parameters such as load intensity, wind shear intensity, and flight attitude deviation, the loss of control probability value at each location is calculated. Multi-dimensional data fusion generates a flight loss of control probability map, providing a comprehensive assessment of the aircraft's dynamic stability in wind shear environments. The final flight out-of-control probability data includes a detailed probability distribution diagram, risk level classification, and warning time of out-of-control, providing a decision-making basis for flight safety control.

[0115] Preferably, pre-identifying the out-of-control behavior of a low-altitude flying target based on the load intensity distribution data and the wind notch behavior identification data includes the following steps:

[0116] Perform airflow directionality analysis on the wind cutout behavior recognition data to obtain wind cutout airflow directionality data;

[0117] The air pressure intensity of the three-dimensional cross section of the wind cut behavior identification data is calculated based on the airflow directionality data of the wind cut to obtain the air pressure intensity data of the three-dimensional cross section of the space;

[0118] Based on the air pressure intensity data of the three-dimensional space section and the airflow directionality data of the wind cut, the maximum flight elevation angle of the airflow impact of the low-altitude flying target is calculated to obtain the maximum flight elevation angle data of the airflow impact;

[0119] Based on the air pressure intensity data of the three-dimensional space section and the airflow directionality data of the wind cut, the maximum lateral / longitudinal deviation angle of the airflow impact of the low-altitude flying target is calculated to obtain the maximum lateral / longitudinal deviation angle data of the airflow impact;

[0120] According to the maximum flight elevation angle data of airflow impact and the maximum lateral / longitudinal deviation angle data of airflow impact, the out-of-control behavior pre-identification of the low-altitude flying target is performed to obtain the out-of-control behavior pre-identification data.

[0121] In this embodiment of the present invention, a high-frequency vector wind speed sensor and a laser Doppler velocimeter are used to precisely measure airflow directionality. First, the monitored wind speed and direction data are time-synchronized to ensure consistency across all data points. Then, using vector decomposition, the airflow directionality is divided into multiple components. By analyzing the dominant direction, velocity variations, and distribution of vortex regions section by section, the dynamic evolution of the airflow is captured. This process specifically targets areas of rapid wind shear changes to identify the primary directional characteristics of wind shear behavior. The resulting output is wind shear airflow directionality data, which includes the primary flow direction, rotational direction, and velocity variation patterns of the airflow. Based on this wind shear airflow directionality data, the air pressure intensity of the three-dimensional cross-sections of the wind shear behavior identification data is calculated. First, a three-dimensional spatial gridding technique is used to decompose the flight area into multiple cross-sections to precisely locate wind shear regions. Subsequently, a network of high-precision pressure sensors collects real-time pressure data for each cross-section. Combined with the airflow directionality data, the pressure intensity of each cross-section is calculated using a numerical integration method. Particularly in areas of severe wind shear, refined meshing and multiple measurements are employed to ensure data accuracy. Section-by-section analysis generates a pressure intensity distribution map for each section. All section data is integrated to produce a complete three-dimensional spatial pressure intensity data set, providing the basis for subsequent elevation and deflection angle calculations. By combining this three-dimensional spatial pressure intensity data with wind shear airflow directionality data, the maximum elevation angle of a low-altitude target subjected to airflow impact is calculated. A dynamic fluid dynamics simulation device inputs pressure and directionality data to simulate the target's response to airflow impact in various wind shear zones. By analyzing the pressure and shear forces acting on each part of the aircraft's windward surface point by point, the target's maximum elevation angle under specific airflow conditions is calculated. Nonlinear simulation methods are used to gradually approximate the critical elevation angle, ensuring the accuracy of the measured results. The output maximum elevation angle data details the maximum safe elevation angle achievable by the target under wind shear, identifying the boundary conditions for flight control. Using the air pressure intensity data of three-dimensional spatial cross-sections and the airflow directionality data of wind cuts, the maximum lateral and longitudinal deviation angles of low-altitude flying targets due to airflow impact are calculated. Using the equilibrium moment analysis method, the lateral and longitudinal force states of the aircraft are modeled and calculated using the airflow intensity and directionality. For areas with large changes in air pressure intensity, the moment calculation process is further refined to capture the aircraft's deviation angle under extreme conditions. Through iterative numerical solution, the maximum lateral and longitudinal deviation angles of the aircraft in a specific airflow environment are calculated, and the output result is the maximum lateral / longitudinal deviation angle data of airflow impact. The data details the critical deviation angle value and related airflow impact parameters, laying a data foundation for the pre-assessment of loss of control risks. Based on the maximum flight elevation angle data of airflow impact and the maximum lateral / longitudinal deviation angle data of airflow impact, the loss of control behavior of low-altitude flying targets can be pre-identified.By establishing a dynamic correlation matrix between pitch and deflection angles, the aircraft's stability under different pitch and deflection conditions is analyzed. This data is compared with the aircraft's design limit parameters to identify critical conditions that could trigger a loss of control. Through continuous risk assessment and critical state identification, the aircraft's safe flight envelope under varying wind shear conditions is determined. The resulting pre-identification data for loss of control behavior includes potential trigger points, risk levels, and response strategies, providing critical data support for flight control system optimization and early warning systems.

[0122] Preferably, step S3 includes the following steps:

[0123] Step S31: Predicting the flight target deviation trajectory based on the near-surface airflow disturbance data and the flight loss of control probability data to obtain flight target deviation trajectory prediction data;

[0124] Step S32: performing trajectory smoothing analysis on the flight target deviation trajectory estimation data to obtain deviation trajectory smoothing data;

[0125] Step S33: constructing a flight target state recognition model based on the flight loss of control probability data and the deviation trajectory smoothing data based on the Q-Learning algorithm to obtain a flight target state recognition model.

[0126] In one embodiment of the present invention, a multidimensional space vector calculation method is used to estimate the target's trajectory. First, near-surface airflow disturbance data is matched with loss-of-control probability data, and an eddy current characteristic extraction algorithm is applied to analyze the real-time impact of airflow on the aircraft. Subsequently, a trajectory deduction formula is used to dynamically simulate the aircraft's trajectory under various airflow disturbances, combining the target's velocity, angle, and inertial parameters. This method outputs a coordinate sequence of continuous trajectory points. High-frequency data interpolation and numerical differentiation are used to analyze the target's trajectory deviation trends and velocity changes in areas of sudden airflow changes. The resulting estimated trajectory data includes the target's trajectory coordinates, velocity variation characteristics, and directionality, providing a detailed picture of the target's predicted trajectory in complex airflow environments. The estimated trajectory data undergoes trajectory smoothing analysis. The estimated trajectory is processed using a weighted moving average algorithm and Kalman filtering techniques to eliminate abnormal jitter and noise caused by sudden airflow changes. First, a continuity analysis is performed on the trajectory point set to determine the trajectory's coherence and rationality. A smoothing window is then used to adjust the velocity and direction of the deflected trajectory. Multi-scale piecewise smoothing ensures trajectory stability and accuracy, and corrects for significant deviations. Quadratic spline interpolation is then used to fit the smoothed trajectory to generate a smoothed trajectory line. The output, smoothed deviation trajectory data, contains an optimized sequence of trajectory points, eliminating bias caused by random perturbations. It demonstrates the actual deviation trend of the target under airflow disturbances, providing a more accurate trajectory basis for subsequent flight state identification. A flight target state identification model is constructed using the Q-Learning algorithm. First, the flight loss probability data and the smoothed deviation trajectory data are input into the state space of the Q-Learning algorithm to define the aircraft's states under different combinations of trajectory and loss probability. Based on the algorithm's reinforcement learning mechanism, state-action pairs are set and trained with the goal of maximizing flight stability, gradually optimizing the response strategy under each state. Through multiple rounds of simulation, the reward function is repeatedly adjusted, with particular attention paid to identifying and improving the response behavior of pre-loss states. During training, adaptive step-size control and dynamic exploration rate adjustment are employed to ensure the model's generalization under various airflow disturbance conditions. The resulting flight target state recognition model can identify the stability of an aircraft in different disturbance environments in real time and provide corresponding adjustment recommendations. The model includes a state mapping matrix, an optimal response strategy set, and a real-time decision-making feedback mechanism, providing reliable data support for low-altitude target identification and risk control.

[0127] Preferably, step S32 includes the following steps:

[0128] Step S321: performing trajectory offset time series difference calculation on the flight target offset trajectory estimation data to obtain trajectory offset time series difference data;

[0129] Step S322: performing a displacement discontinuity analysis on the flight target displacement trajectory estimation data based on the trajectory displacement time series difference data to obtain trajectory displacement discontinuity data;

[0130] Step S323: performing trajectory smoothing analysis on the flight target deviation trajectory estimation data according to the trajectory deviation discontinuity data to obtain deviation trajectory smoothing data.

[0131] In one embodiment of the present invention, trajectory deviation time-series difference calculations are performed on estimated target trajectory data to identify the trajectory change rate and trend at different time points. First, the coordinate information for each time point is extracted from the estimated trajectory data, and the offset between adjacent time points is calculated using the time-series difference method. This operation involves performing coordinate axis difference calculations on consecutive coordinate points in the trajectory. By calculating the displacement difference within each time interval, the changing characteristics of the target deviation rate are analyzed. Subsequently, the time-series difference data is normalized to ensure comparability of deviation characteristics across different time periods, generating a set of trajectory deviation time-series difference data containing time points, offsets, and rate changes. This data provides the basis for subsequent trajectory discontinuity analysis, with a particular focus on identifying abnormal deviation behavior and sudden change points. Using this trajectory deviation time-series difference data, discontinuity analysis is performed on the estimated target trajectory data to assess trajectory continuity and stability. First, the time-series difference data is checked for smoothness to identify sudden deviation points and their temporal locations. By defining a critical deviation threshold, deviation points that exceed the threshold are marked as discontinuity anomalies. Subsequently, a time window segmentation method was used to segment the trajectory data into time segments, and the deviation consistency and fluctuation characteristics within each segment were calculated. Regions with large fluctuations or prominent intermittent deviations were subjected to in-depth analysis to assess the impact of discontinuities on vehicle stability. The output trajectory deviation discontinuity data, including the location, amplitude, and frequency of the discontinuity points, revealed potential discontinuities during the deviation process, providing a basis for subsequent smoothing. The estimated target deviation trajectory data was smoothed based on the trajectory deviation discontinuity data to minimize the impact of discontinuities on the overall trajectory. First, a local regression smoothing method (LOWESS) was used to correct the data for the marked discontinuous deviation points and refine the smoothing of the discontinuous regions. For continuous regions of the trajectory, a weighted average method was applied to balance the trajectory trends between different points. In particular, interpolation points were added to areas with strong discontinuities to supplement the detailed information lost during the smoothing process. A quadratic fit was performed on the overall trajectory to eliminate irregular fluctuations, ultimately generating an optimized trajectory path. The output offset trajectory smoothing data includes a smoothed trajectory point set, optimized trajectory lines, and smoothness evaluation indicators, providing a more stable trajectory basis for the state recognition of low-altitude flying targets.

[0132] Preferably, step S33 includes the following steps:

[0133] Step S331: Calculating the local risk flight curvature based on the flight out of control probability data and the deviation trajectory smoothing data to obtain local risk flight curvature data;

[0134] Step S332: dividing the local risk flight curvature data into a training set and a test set to obtain a local risk flight curvature training set and a local risk flight curvature test set;

[0135] Step S333: constructing an initial flight target state recognition model for the local risk flight curvature training set based on the Q-Learning algorithm to obtain the initial flight target state recognition model;

[0136] Step S334: Performing model optimization testing on the initial flight target state recognition model using the local risk flight curvature test set to obtain a flight target state recognition model.

[0137] In an embodiment of the present invention, local risk flight curvature is calculated based on flight loss probability data and offset trajectory smoothing data to identify the risk level of low-altitude flight targets in different path segments. First, the second-order derivative of the offset trajectory smoothing data is calculated to extract the curvature information of each trajectory segment. This information is then combined with the flight loss probability data to quantify the local risk curvature value of the trajectory point. During the operation, the curvature calculation involves quantitatively evaluating the degree of curvature of the trajectory line. Each trajectory segment is analyzed using the arc fitting method to obtain the curvature radius of each segment and calculate the correlation between the risk factor and the curvature. Comparative analysis shows that areas with greater curvature tend to indicate a higher risk of loss of control. Finally, by combining the various local curvatures and corresponding loss of control probability values, local risk flight curvature data is generated. This data is used to identify key points in high-risk flight paths and provide a reference for subsequent model construction. The local risk flight curvature data is partitioned to establish training and test sets for model construction and verification. First, all curvature data were arranged in chronological order. Using random splitting or time series segmentation, the data was divided into a training set and a test set. The training set was used for model construction, while the test set was used for subsequent model validation. Specifically, the local risk flight curvature data was randomly shuffled in an 80:20 ratio and divided into training and test sets, ensuring a balanced data distribution between the two sets. After partitioning, descriptive statistics were performed on the data characteristics of the training and test sets to ensure that both sets contained sufficient representative risk curvature features. This partitioned dataset provided the foundation for model construction and optimization testing of the Q-Learning algorithm. A Q-Learning algorithm was used to construct a model on the local risk flight curvature training set to initially identify the state of low-altitude flying targets. The steps involved: first, initializing the Q-Learning state space, action space, and reward mechanism. State transition conditions and reward functions were set based on the data characteristics of the local risk flight curvature training set. Next, through algorithm iteration, the correlation between local curvature and flight state was learned, and the Q-value matrix was updated. In each training round, the algorithm simulates decisions based on the input curvature data, adjusts the recognition strategy, and outputs the optimal state recognition strategy until the Q value converges. During training, key features of the trajectory data, such as curvature mutation points and loss of control risk values, are used as input to continuously optimize the recognition accuracy of the Q-Learning algorithm. The resulting initial recognition model for the flight target state provides a preliminary analytical framework for accurate flight state determination. The initial recognition model for the flight target state is optimized and tested using a local risk flight curvature test set to verify and adjust the model's recognition capabilities. First, the data in the test set is input into the initial recognition model, and the model's recognition results are evaluated for accuracy, recall, and false positive rate to quantify the model's recognition performance under different risk curvatures.In response to errors discovered during testing, the model was refined by adjusting model parameters, optimizing the reward mechanism, and incrementally updating the Q-value table. Particular attention was paid to recognition accuracy in high-curvature areas, and the Q-value update strategy was refined to improve the model's responsiveness to extreme excursions and loss of control. Following testing and optimization, the resulting flight target state recognition model boasts increased accuracy and robustness, ensuring the desired dynamic state recognition of low-altitude targets.

[0138] Preferably, the present invention further provides a low-altitude flying target recognition system based on a three-dimensional digital globe, for executing the low-altitude flying target recognition method based on a three-dimensional digital globe as described above. The low-altitude flying target recognition system based on a three-dimensional digital globe comprises:

[0139] The surface element marking module is used to obtain low-altitude monitoring range data; the low-altitude monitoring range data is marked with high-altitude surface elements to obtain high-altitude surface element marking data;

[0140] The flight loss control probability estimation module is used to calculate the spatial relative distance of the towering surface element marker data to obtain the flight target-surface element spatial relative distance data; perform near-surface airflow disturbance analysis based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data; and estimate the flight loss control probability based on the near-surface airflow disturbance data to obtain the flight loss control probability data;

[0141] The flight target state recognition model construction module is used to construct a flight target state recognition model based on the flight loss of control probability data based on the Q-Learning algorithm to obtain a flight target state recognition model;

[0142] The risk flight intention prediction module is used to predict the risk flight intention of low-altitude flying targets based on the flight target state recognition model, obtain the target risk flight intention data, and feed back the target risk flight intention data to the terminal.

[0143] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0144] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present 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 present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A low-altitude flying target recognition method based on three-dimensional digital earth, characterized in that: The following steps are involved: Step S1: Acquire low-altitude monitoring range data; perform high-altitude surface element marking on the low-altitude monitoring range data to obtain high-altitude surface element marking data; Step S2: Calculating the spatial relative distance of the towering surface element marker data to obtain flight target-surface element spatial relative distance data; performing near-surface airflow disturbance analysis based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data; and estimating the flight loss-of-control probability based on the near-surface airflow disturbance data to obtain flight loss-of-control probability data. Step S3: constructing a flight target state recognition model based on the flight loss of control probability data based on the Q-Learning algorithm to obtain a flight target state recognition model; wherein step S3 includes the following steps: Step S31: Predicting the flight target deviation trajectory based on the near-surface airflow disturbance data and the flight loss of control probability data to obtain flight target deviation trajectory prediction data; Step S32: performing trajectory smoothing analysis on the flight target deviation trajectory estimation data to obtain deviation trajectory smoothing data; wherein step S32 includes the following steps: Step S321: performing trajectory offset time series difference calculation on the flight target offset trajectory estimation data to obtain trajectory offset time series difference data; Step S322: performing a displacement discontinuity analysis on the flight target displacement trajectory estimation data based on the trajectory displacement time series difference data to obtain trajectory displacement discontinuity data; Step S323: performing trajectory smoothing analysis on the flight target deviation trajectory estimation data according to the trajectory deviation discontinuity data to obtain deviation trajectory smoothing data; Step S33: constructing a flight target state recognition model based on the flight loss of control probability data and the deviation trajectory smoothing data based on the Q-Learning algorithm to obtain a flight target state recognition model; Step S4: predict the risky flight intention of the low-altitude flying target based on the flight target state recognition model, obtain the target risky flight intention data, and feed back the target risky flight intention data to the terminal.

2. The low-altitude flying target recognition method based on three-dimensional digital earth according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire low-altitude monitoring range data; Step S12: collecting monitoring range environment data from the low-altitude monitoring range data to obtain monitoring range environment data; Step S13: marking the high-altitude surface elements on the low-altitude monitoring range data according to the monitoring range environment data to obtain high-altitude surface element marking data.

3. The low-altitude flying target recognition method based on three-dimensional digital earth according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Real-time monitoring of low-altitude flight targets in the low-altitude monitoring range data is performed by radar to obtain real-time monitoring data of low-altitude flight targets; Step S22: performing spatial relative distance calculation on the high-rise surface element marker data based on the real-time monitoring data of the low-altitude flight target to obtain the flight target-surface element spatial relative distance data; Step S23: performing near-surface airflow disturbance analysis on the real-time monitoring data of the low-altitude flying target based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data; Step S24: Estimating the probability of flight loss of control based on the near-surface airflow disturbance data and the real-time monitoring data of the low-altitude flight target to obtain flight loss of control probability data.

4. The low-altitude flying target recognition method based on three-dimensional digital earth according to claim 3 is characterized in that: Step S23 includes the following steps: Step S231: extracting the flight speed of the low-altitude flying target real-time monitoring data to obtain the target flight speed data; Step S232: Decomposing the multi-directional airflow interference vector during the flight path based on the target flight speed data and the flight target-surface element spatial relative distance data to obtain multi-directional airflow interference vector data; Step S233: performing interference airflow manifold feature recognition on the multi-directional airflow interference vector data to obtain interference airflow manifold feature data; Step S234: performing near-surface airflow disturbance analysis on the real-time monitoring data of the low-altitude flight target according to the interfering airflow manifold characteristic data to obtain near-surface airflow disturbance data.

5. The low-altitude flying target recognition method based on three-dimensional digital earth according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: identifying wind notch behavior during the flight path of the low-altitude flight target real-time monitoring data based on the near-surface airflow disturbance data to obtain wind notch behavior identification data; Step S242: performing flight airflow load simulation calculation on the low-altitude flight target real-time monitoring data based on the wind cut behavior recognition data to obtain target flight airflow load data; Step S243: performing load intensity distribution analysis on the target flight airflow load data to obtain load intensity distribution data; Step S244: performing pre-identification of the out-of-control behavior of the low-altitude flying target based on the load intensity distribution data and the wind notch behavior identification data to obtain pre-identification data of the out-of-control behavior; Step S245: Estimating the flight out-of-control probability of the low-altitude flight target real-time monitoring data based on the out-of-control behavior pre-identification data, the load intensity distribution data, and the wind notch behavior identification data to obtain flight out-of-control probability data.

6. The low-altitude flying target recognition method based on three-dimensional digital earth according to claim 4 is characterized in that: The pre-identification of the out-of-control behavior of low-altitude flying targets based on load intensity distribution data and wind cut behavior identification data includes the following steps: Perform airflow directionality analysis on the wind cutout behavior recognition data to obtain wind cutout airflow directionality data; The air pressure intensity of the three-dimensional cross section of the wind cut behavior identification data is calculated based on the airflow directionality data of the wind cut to obtain the air pressure intensity data of the three-dimensional cross section of the space; Based on the air pressure intensity data of the three-dimensional space section and the airflow directionality data of the wind cut, the maximum flight elevation angle of the airflow impact of the low-altitude flying target is calculated to obtain the maximum flight elevation angle data of the airflow impact; Based on the air pressure intensity data of the three-dimensional space section and the airflow directionality data of the wind cut, the maximum lateral / longitudinal deviation angle of the airflow impact of the low-altitude flying target is calculated to obtain the maximum lateral / longitudinal deviation angle data of the airflow impact; According to the maximum flight elevation angle data of airflow impact and the maximum lateral / longitudinal deviation angle data of airflow impact, the out-of-control behavior pre-identification of the low-altitude flying target is performed to obtain the out-of-control behavior pre-identification data.

7. The low-altitude flying target recognition method based on three-dimensional digital earth according to claim 1 is characterized in that: Step S33 includes the following steps: Step S331: Calculating the local risk flight curvature based on the flight out of control probability data and the deviation trajectory smoothing data to obtain local risk flight curvature data; Step S332: dividing the local risk flight curvature data into a training set and a test set to obtain a local risk flight curvature training set and a local risk flight curvature test set; Step S333: constructing an initial flight target state recognition model for the local risk flight curvature training set based on the Q-Learning algorithm to obtain the initial flight target state recognition model; Step S334: Performing model optimization testing on the initial flight target state recognition model using the local risk flight curvature test set to obtain a flight target state recognition model.

8. A low-altitude flying target recognition system based on three-dimensional digital earth, characterized in that: For executing the low-altitude flying target recognition method based on the three-dimensional digital earth as claimed in claim 1, the low-altitude flying target recognition system based on the three-dimensional digital earth comprises: The surface element marking module is used to obtain low-altitude monitoring range data; the low-altitude monitoring range data is marked with high-altitude surface elements to obtain high-altitude surface element marking data; The flight loss control probability estimation module is used to calculate the spatial relative distance of the towering surface element marker data to obtain the flight target-surface element spatial relative distance data; perform near-surface airflow disturbance analysis based on the flight target-surface element spatial relative distance data to obtain near-surface airflow disturbance data; and estimate the flight loss control probability based on the near-surface airflow disturbance data to obtain the flight loss control probability data; The flight target state recognition model construction module is used to construct a flight target state recognition model based on the flight loss of control probability data based on the Q-Learning algorithm to obtain a flight target state recognition model; The risk flight intention prediction module is used to predict the risk flight intention of low-altitude flying targets based on the flight target state recognition model, obtain the target risk flight intention data, and feed back the target risk flight intention data to the terminal.

Images