Low-altitude airspace collaborative management method and system based on digital twinning

Abstract

The invention provides a low-altitude airspace collaborative management method and system based on digital twinning, and the method comprises the steps: analyzing the maneuvering characteristics and flight envelope characteristic parameters of an aircraft based on the obtained real-time state data of the aircraft, and calculating the maneuvering characteristics and flight envelope characteristic parameters of the aircraft by using kinematics and dynamics models, describing motion laws of different aircrafts; real-time flight data of the aircraft are combined, the motion track and attitude change of the aircraft are synchronized in real time in a virtual environment through a digital twin technology, the dynamic behavior of the aircraft is accurately reproduced, and a high-fidelity digital model is provided for flight conflict detection and flight path prediction; a multi-level and multi-granularity digital twin model is constructed according to the difference of the motion characteristics of the aircrafts, and the digital twin model comprises an airspace structure model of a macroscopic level, an aircraft group behavior model of a mesoscopic level and a single aircraft dynamic model of a microscopic level.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and in particular relates to a low-altitude airspace collaborative management method and system based on digital twins. Background Art

[0002] The construction of a digital twin model for low-altitude airspace faces many technical challenges. First, the low-altitude airspace environment is complex and changeable, and there are many types of aircraft. How to fully perceive and accurately map the real-time status of the aircraft is a major problem. Secondly, the dynamic characteristics of low-altitude aircraft are different. How to accurately depict and synchronize the dynamic behaviors of the aircraft such as motion trajectory and attitude changes in the digital twin model in real time is another technical obstacle. Furthermore, low-altitude airspace management involves many stakeholders. How to coordinate the demands of all parties, optimize resource allocation, and improve management efficiency in the digital twin system is also a major challenge. In addition, the low-altitude digital twin system has high computational complexity and strict real-time requirements. How to achieve efficient parallel computing and meet real-time response requirements is also a technical problem that needs to be overcome. Finally, the safety and robustness of the low-altitude digital twin system are crucial. How to build a stable, reliable, and well-protected digital twin system is another technical problem facing researchers. Summary of the invention

[0003] The present invention proposes a low-altitude airspace collaborative management method and system based on digital twins to solve the problems existing in the above-mentioned prior art.

[0004] To achieve the above object, the present invention provides a low-altitude airspace collaborative management method based on digital twin, comprising the following steps:

[0005] Collecting multimodal data of the aircraft, processing the multimodal data through a Kalman filter data fusion algorithm, and obtaining key parameters of the aircraft;

[0006] Constructing kinematic and dynamic models according to the aircraft model to process the key parameters and obtain the maneuverability performance and flight envelope characteristic parameters of the aircraft;

[0007] Through digital twin technology, the key parameters, maneuverability performance parameters and flight envelope characteristic parameters of the aircraft are synchronized into the virtual environment to obtain a digital model;

[0008] Construct a multi-level digital twin model based on the differences in aircraft motion characteristics in different digital models;

[0009] Introducing a particle swarm optimization algorithm into the multi-level digital twin model to comprehensively plan and dynamically schedule low-altitude resources;

[0010] The knowledge graph technology is introduced into the multi-level digital twin model to construct a virtual simulation environment for low-altitude airspace, and low-altitude airspace situation decisions are made through the semantic association of the knowledge graph.

[0011] Preferably, obtaining key parameters of the aircraft includes:

[0012] A multi-source heterogeneous sensor network is used for data collection to obtain multimodal data; the multimodal data is cleaned and standardized to eliminate noise and outliers in the data; feature extraction is performed on the standardized multimodal data to obtain parameters that can reflect the characteristics of different aircraft; the parameters reflecting the characteristics of different aircraft are input into a Kalman filter data fusion model to accurately sense and map the real-time status of the aircraft; and key parameters of the aircraft are obtained based on the output results of the Kalman filter data fusion model.

[0013] Preferably, obtaining the maneuverability performance and flight envelope characteristic parameters of the aircraft includes:

[0014] A kinematic and dynamic model is constructed based on the aircraft model. The model includes the mass, thrust and drag parameters of the aircraft. The key parameters of the aircraft are input into the kinematic and dynamic model, and the position, velocity and attitude state of the aircraft at the next moment are predicted through numerical integration methods. The flight envelope of the aircraft is determined based on the maneuverability parameters of the aircraft and the prediction results, where the flight envelope includes the characteristic parameters of maximum speed, maximum acceleration and minimum turning radius.

[0015] Preferably, building a multi-level digital twin model includes:

[0016] By analyzing the motion trajectory and formation changes of each aircraft group, an aircraft group behavior model is constructed; on the basis of the aircraft group behavior model, a single aircraft dynamic model is further established; the single aircraft dynamic model comprehensively considers the dynamic characteristics and environmental factors of the aircraft, and makes a refined description of the motion state of a single aircraft; on the upper layer of the single aircraft dynamic model, a macro airspace structure model is constructed; the airspace structure model describes the airspace environment in which the aircraft is located based on the topography, meteorological conditions and control rules of the airspace; the aircraft group behavior model, the single aircraft dynamic model and the airspace structure model are integrated to form a multi-level digital twin model.

[0017] Preferably, the overall planning and dynamic scheduling of low-altitude resources include:

[0018] Through the particle swarm optimization algorithm, low-altitude resources are comprehensively planned and dynamically scheduled in the multi-level digital twin model to generate the optimal resource allocation plan; in the iterative process of the particle swarm optimization algorithm, the demand weights of different stakeholders are introduced, and the interests of stakeholders are balanced by adjusting the weight coefficients; the feasibility analysis and risk assessment of the generated low-altitude resource allocation plan are carried out to determine whether the plan meets the constraints. If not, it is iteratively optimized until a feasible optimal plan is obtained; the optimized low-altitude resource allocation plan is sent to relevant aircraft operators and air traffic control departments for flight mission planning and scheduling, and the key parameters of the plan are fed back to the multi-level digital twin model in real time for dynamic updating and adjustment.

[0019] Preferably, making low-altitude airspace situation decisions through semantic association of knowledge graphs includes:

[0020] Knowledge graph technology is introduced into the multi-level digital twin model to build a low-altitude airspace management knowledge base and reasoning engine. The knowledge graph contains multi-dimensional information on airspace structure, flight rules and meteorological conditions, and realizes low-altitude airspace situation understanding and decision support through semantic association. Flight plans and airspace applications are automatically reviewed and conflicts are detected according to the rules and constraints of the knowledge graph.

[0021] The present invention also provides a low-altitude airspace collaborative management system based on digital twins, comprising:

[0022] A multi-source data fusion perception module is used to collect multi-modal data of the aircraft, process the multi-modal data through a Kalman filter data fusion algorithm, and obtain key parameters of the aircraft;

[0023] An aircraft motion characteristic acquisition module is used to construct a kinematic and dynamic model according to the aircraft model to process the key parameters and obtain the maneuverability and flight envelope characteristic parameters of the aircraft;

[0024] The aircraft digital twin synchronization module is used to synchronize the key parameters, maneuverability performance parameters and flight envelope characteristic parameters of the aircraft into the virtual environment through digital twin technology to obtain a digital model;

[0025] A multi-level digital twin model construction module is used to construct a multi-level digital twin model based on the differences in aircraft motion characteristics in different digital models;

[0026] A low-altitude resource management module based on particle swarm optimization is used to introduce a particle swarm optimization algorithm into the multi-level digital twin model to comprehensively plan and dynamically schedule low-altitude resources;

[0027] The intelligent airspace management module based on knowledge graph is used to introduce knowledge graph technology into the multi-level digital twin model, build a virtual simulation environment for low-altitude airspace, and make low-altitude airspace situation decisions through the semantic association of the knowledge graph.

[0028] The present invention also provides a computer device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0029] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method are implemented.

[0030] The present invention also provides a computer program product, comprising a computer program, which implements the steps of the method when executed by a processor.

[0031] Compared with the prior art, the present invention has the following advantages and technical effects:

[0032] The present invention discloses a method and system for collaborative management of low-altitude airspace based on digital twins. In view of the complex and changeable low-altitude environment and the wide variety of aircraft, a multi-source heterogeneous sensor network is deployed to collect multi-modal data, and the Kalman filter algorithm is used for data fusion to achieve accurate perception of the real-time status of the aircraft. Based on the acquired aircraft status data, its maneuverability and flight envelope characteristic parameters are analyzed to construct a motion model. Through the digital twin technology, the aircraft motion trajectory and attitude changes are synchronized in real time in a virtual environment to build a multi-level and multi-granular digital twin model. The particle swarm optimization algorithm is introduced into the digital twin model to coordinate and dynamically schedule low-altitude resources. At the same time, the knowledge graph technology is introduced to build a low-altitude airspace management knowledge base and reasoning engine to achieve situation understanding and decision support. The present invention realizes accurate perception, intelligent planning and collaborative management of low-altitude airspace through the organic combination of multi-source data fusion, digital twin modeling and knowledge graph reasoning, and improves the utilization efficiency and management level of low-altitude resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0034] Figure 1 The figure is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0036] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] Embodiment 1

[0038] like Figure 1 As shown, this embodiment provides a low-altitude airspace collaborative management method based on digital twins, including the following steps:

[0039] Collect multi-modal data of the aircraft, process the multi-modal data through the Kalman filter data fusion algorithm, and obtain the key parameters of the aircraft;

[0040] Construct kinematic and dynamic models according to the aircraft model to process key parameters and obtain the aircraft's maneuverability and flight envelope characteristic parameters;

[0041] Through digital twin technology, the key parameters, maneuverability performance parameters and flight envelope characteristic parameters of the aircraft are synchronized into the virtual environment to obtain a digital model;

[0042] Construct a multi-level digital twin model based on the differences in aircraft motion characteristics in different digital models;

[0043] Introducing particle swarm optimization algorithm into the multi-level digital twin model to coordinate planning and dynamically schedule low-altitude resources;

[0044] Knowledge graph technology is introduced into the multi-level digital twin model to build a virtual simulation environment for low-altitude airspace, and low-altitude airspace situation decisions are made through the semantic association of the knowledge graph.

[0045] The specific steps include:

[0046] S101. In view of the complex and changeable low-altitude airspace environment and the wide variety of aircraft, a multi-source heterogeneous sensor network is deployed to collect radar, ADS-B, and Beidou multi-modal data. The Kalman filter data fusion algorithm is used to accurately perceive and map the real-time status of the aircraft, obtain the key parameters of the aircraft's position, speed, and heading, and build a comprehensive and accurate low-altitude situational awareness capability.

[0047] Specifically, according to the complex and changeable characteristics of the low-altitude airspace environment, a multi-source heterogeneous sensor network is used for data collection to obtain multimodal data such as radar, ADS-B, and Beidou. For the collected multimodal data, preprocessing technology is used to clean and standardize the data, eliminate noise and outliers in the data, and improve data quality. According to the characteristics of the wide variety of aircraft, feature extraction is performed on the preprocessed multimodal data to obtain key parameters that can reflect the characteristics of different aircraft. The extracted key parameters of the aircraft are input into the Kalman filter data fusion model, and the accurate perception and mapping of the real-time status of the aircraft are achieved through model training and optimization. According to the output results of the Kalman filter data fusion model, the key parameters such as the position, speed, and heading of the aircraft are obtained to form a comprehensive description of the aircraft status. The obtained aircraft status information is visualized to generate an intuitive and easy-to-understand situation awareness map to provide decision-making support for relevant personnel. Continuously monitor changes in the low-altitude airspace environment and aircraft status, dynamically adjust the sensor network configuration and data fusion algorithm parameters according to the changes, and maintain the real-time and accuracy of situation awareness.

[0048] In this embodiment, due to the complex and changeable low-altitude airspace environment, a multi-source heterogeneous sensor network is required for data collection. For example, radar, ADS-B receiver, Beidou satellite receiver and other equipment can be deployed to form a comprehensive perception network. Radar can detect the position and speed of the aircraft, ADS-B can receive the identity and location information actively broadcast by the aircraft, and the Beidou system can provide an accurate time and space reference. This multi-source data collection method can complement each other's advantages and disadvantages and improve the comprehensiveness and reliability of perception. Preprocessing the collected multimodal data is a key step to improve data quality. Median filtering can be used to remove burst noise, Kalman filtering can be used to smooth trajectory data, and interpolation algorithms can be used to repair data loss. For example, the ADS-B position data of a drone suddenly jumps, and the data before and after can be used for interpolation correction to make the trajectory smoother and more reasonable. Feature extraction for different types of aircraft is the basis for accurate identification. Dynamic characteristics such as aircraft speed, acceleration, turning radius, climb rate, and electromagnetic characteristics such as radar cross section and ADS-B message format can be extracted. For example, there are obvious differences in the turning characteristics between fixed-wing aircraft and multi-rotor drones, which can be used as an important basis for differentiation. Kalman filtering is a classic data fusion algorithm that can effectively fuse observation data from different sensors. By establishing a kinematic model of the aircraft and combining it with the observation equation, the optimal estimate of the aircraft state can be obtained. For example, the radar observation data of a drone shows that its position is (x1, y1, z1), while the ADS-B data shows that the position is (x2, y2, z2). Kalman filtering can give a more reliable position estimate (x, y, z) based on the uncertainty of the two data.

[0049] S102: Based on the acquired real-time status data of the aircraft, analyze the maneuverability and flight envelope characteristic parameters of the aircraft, wherein the characteristic parameters include maximum speed, maximum acceleration, and minimum turning radius. Use kinematic and dynamic models to describe the motion laws of different aircraft.

[0050] Specifically, based on the key parameters obtained, the aircraft's instantaneous speed, acceleration, turning radius and other maneuverability parameters are calculated and compared with the preset threshold value to determine whether the aircraft's maneuverability is normal. For different types of aircraft, corresponding kinematic and dynamic models are established. The model contains parameters such as the aircraft's mass, thrust, and drag, which are used to describe the aircraft's motion law. The aircraft's real-time state data is input into the kinematic and dynamic models, and the aircraft's position, speed, attitude and other state quantities at the next moment are calculated by numerical integration and other methods to predict the aircraft's motion state. Based on the aircraft's maneuverability parameters and the prediction results of the motion model, the aircraft's flight envelope is determined, including characteristic parameters such as maximum speed, maximum acceleration, and minimum turning radius, which are used to evaluate the aircraft's maneuverability and flight performance.

[0051] Taking a fixed-wing aircraft as an example, its kinematic model includes state variables such as position, speed, and attitude, while the dynamic model involves forces such as thrust, lift, and drag. By substituting real-time state data into the model, the state of the aircraft at the next moment can be predicted using the numerical integration method. This prediction helps to discover potential risks in advance. The determination of the flight envelope can comprehensively evaluate the performance of the aircraft. Taking a certain type of fighter as an example, its flight envelope includes characteristic parameters such as the maximum speed of 1.8 Mach, the maximum overload of 9G, and the minimum turning radius of 300 meters. These parameters not only reflect the extreme performance of the aircraft, but also provide boundary conditions for safe flight. By real-time monitoring of the relationship between the flight status and the flight envelope, situations that exceed the safety range can be discovered in a timely manner.

[0052] S103. In combination with the real-time flight data of the aircraft, the motion trajectory and attitude changes of the aircraft are synchronized in real time in a virtual environment through digital twin technology, the dynamic behavior of the aircraft is accurately reproduced, and a high-fidelity digital model is provided for flight conflict detection and track prediction.

[0053] Specifically, a digital twin model of the aircraft is constructed in a virtual environment. The model is consistent with the physical and dynamic characteristics of the real aircraft and can accurately reproduce the motion trajectory and attitude changes of the aircraft. According to real-time flight data, the digital twin model is used to calculate and update the position and attitude of the aircraft in the virtual environment in real time, so as to achieve real-time synchronization of the dynamic behavior of the aircraft. Based on the digital twin model, a machine learning algorithm is used to predict the future motion trajectory of the aircraft, and whether there is a potential risk of flight conflict is determined based on the prediction results. If a potential risk of flight conflict is detected, different flight strategies and obstacle avoidance schemes are simulated through the digital twin model, the safety and feasibility of each scheme are evaluated, and the optimal scheme is selected as the trajectory adjustment strategy of the aircraft. The optimized trajectory adjustment strategy is transmitted to the real aircraft to guide the aircraft to perform corresponding flight actions to avoid actual flight conflicts. Throughout the process, the real-time flight data of the aircraft is continuously monitored, and the motion status of the aircraft is continuously updated through the real-time synchronization of the digital twin model and the real aircraft to ensure the high consistency between the digital twin model and the real aircraft.

[0054] In this embodiment, the collected data is transmitted to the virtual environment to construct a digital twin model. The model needs to accurately replicate the physical and dynamic characteristics of the aircraft. Taking a fixed-wing drone as an example, its digital twin model contains geometric parameters such as wingspan, fuselage length, center of gravity position, and dynamic parameters such as engine thrust and lift coefficient. Through these parameters, the model can accurately simulate the motion behavior of the aircraft. Based on real-time data, the digital twin model continuously updates the state of the aircraft in the virtual environment. For example, when the real drone flies north at a speed of 5 meters per second, the virtual model will also synchronously update its position and attitude to maintain consistency with the actual aircraft. This real-time synchronization lays the foundation for subsequent trajectory prediction and conflict detection. Machine learning algorithms, such as long short-term memory networks (LSTM), are used to predict the future trajectory of the aircraft. The algorithm analyzes historical flight data and learns the movement pattern of the aircraft to predict possible trajectories in the future. For example, the prediction system may find that the drone will have a potential collision risk with a nearby high-rise building in the next 5 minutes. Once a potential risk is detected, the system will use the digital twin model to simulate multiple obstacle avoidance solutions. For example, different strategies such as yaw 30 degrees to the left, yaw 30 degrees to the right, or climb 100 meters can be simulated to evaluate the safety and feasibility of each solution. Through simulation calculations, the system may find that yaw 30 degrees to the right is the best choice, which can effectively avoid obstacles and maintain the original route. After determining the optimal solution, the system transmits the track adjustment instruction to the real aircraft. After receiving the instruction, the flight control system performs the corresponding flight action, such as changing the yaw angle or adjusting the altitude, to avoid the occurrence of actual conflicts. Throughout the process, the digital twin model continues to keep pace with the real aircraft, constantly updating the flight status, and providing accurate basic data for the next round of predictions and decisions. This flight conflict detection and obstacle avoidance system based on digital twins has significant advantages. It can rehearse multiple possible situations in a virtual environment without the need for high-risk actual flight tests. At the same time, through continuous learning and optimization, the system can continuously improve the prediction accuracy and decision-making efficiency, providing a strong guarantee for the safe operation of the aircraft.

[0055] Furthermore, based on the digital twin model, a machine learning algorithm is used to predict the future motion trajectory of the aircraft, and whether there is a potential risk of flight conflict is determined based on the prediction results.

[0056] Based on the historical flight data of the aircraft and the real-time data collected by the sensors, a digital twin model of the aircraft is constructed. The model contains information such as the physical characteristics, dynamic characteristics and environmental factors of the aircraft. The long short-term memory neural network (LSTM) algorithm is used to train the historical motion trajectory data of the aircraft and establish a motion trajectory prediction model. The input of the model is the current state information and environmental information of the aircraft, and the output is the prediction result of the motion trajectory in the future. A large number of aircraft motion trajectory samples are generated by the Monte Carlo simulation method. The samples contain the movement of the aircraft under different environmental conditions. The generated sample data is used to further train and optimize the LSTM prediction model to improve the prediction accuracy and generalization ability of the model. The information of other aircraft is added to the digital twin model. The multi-agent reinforcement learning algorithm is used to simulate the interaction of multiple aircraft in the same airspace, and the distance, speed, direction and other parameters between the aircraft are analyzed to determine whether there is a potential conflict risk. When the distance between the predicted trajectory of the aircraft and the trajectory of other aircraft is less than the safety threshold, a conflict risk alarm is triggered, and corresponding disposal measures are taken according to the risk level, such as trajectory adjustment and speed control, to ensure the safety of the aircraft operation. The aircraft status and environmental information are updated in real time in the digital twin model. By comparing with the sensor data of the actual aircraft, the digital twin model is continuously optimized and corrected to improve the simulation accuracy and prediction ability of the model. According to the mission requirements and risk assessment results of the aircraft, the genetic algorithm is used to optimize the aircraft's motion trajectory, generate a safe and efficient flight path, and pass the optimized trajectory parameters to the flight control system to guide the actual movement of the aircraft.

[0057] S104. Construct a multi-level and multi-granularity digital twin model based on the differences in the motion characteristics of the aircraft. The digital twin model includes an airspace structure model at the macro level, an aircraft group behavior model at the meso level, and a single aircraft dynamic model at the micro level.

[0058] Specifically, based on the acquired aircraft motion characteristic data, a clustering algorithm is used to classify aircraft to obtain aircraft groups with similar motion characteristics. For each aircraft group, an aircraft group behavior model is constructed by analyzing its motion trajectory, formation changes, etc. to characterize the overall motion characteristics of the group. On the basis of the aircraft group behavior model, a single aircraft dynamic model is further established. This model comprehensively considers the dynamic characteristics of the aircraft, environmental factors, etc., and describes the motion state of a single aircraft in a refined manner. On the upper layer of the single aircraft dynamic model, a macroscopic airspace structure model is constructed. This model describes the airspace environment in which the aircraft is located based on the topography, meteorological conditions, and control rules of the airspace. The aircraft group behavior model, the single aircraft dynamic model, and the airspace structure model are integrated to form a multi-level and multi-granular aircraft digital twin model. Through this model, the motion characteristics of the aircraft at different levels can be fully reflected. The digital twin model is trained and optimized using a machine learning algorithm to improve the accuracy and prediction ability of the model. The recurrent neural network in deep learning can be used to learn the timing characteristics of aircraft motion; the reinforcement learning algorithm can be used to achieve autonomous optimization of aircraft motion strategies; the transfer learning method can be used to utilize existing aircraft model knowledge to accelerate the construction process of new aircraft models.

[0059] In this embodiment, the application of clustering algorithms can effectively identify groups of aircraft with similar motion characteristics. For example, by using the K-means clustering method to classify aircraft according to speed and altitude characteristics, several typical groups such as "low-altitude slow speed", "medium-altitude cruising", and "high-altitude fast speed" may be obtained. This classification is helpful for the subsequent targeted establishment of group behavior models. The construction of group behavior models requires analysis of the overall motion characteristics of aircraft. Taking military formation flight as an example, by observing the relative position changes of multiple fighters, typical formations such as "wedge" and "echelon" can be identified, and a mathematical model describing the formation transformation law can be established. This model can predict the future movement trend of the entire formation. The dynamic model of a single aircraft is more sophisticated and needs to consider the dynamic characteristics of the aircraft. For example, when modeling a helicopter, its unique vertical take-off and landing capability and hovering characteristics must be considered. The model may include parameters such as rotor lift and tail rotor anti-torque to accurately describe the movement performance of the helicopter under various flight conditions. The airspace structure model is a macroscopic description. Taking the airspace around an airport as an example, the model needs to include information such as runway direction, approach route, and no-fly zone. At the same time, local meteorological conditions, such as wind direction, wind speed, and visibility, must also be considered. These factors will affect the actual motion trajectory of the aircraft. The fusion of multi-level models is a complex process. Taking a swarm of drones as an example, a dynamic model of a single drone can be established first, and then a swarm model can be built based on swarm behavior rules (such as collision avoidance algorithms). Finally, it is placed in a specific airspace environment to form a complete digital twin model. This multi-granular model can simultaneously reflect the characteristics of a single drone and the swarm effect. Machine learning algorithms play an important role in model optimization. For example, the use of long short-term memory networks (LSTMs) can effectively capture the temporal characteristics of aircraft motion and predict its future trajectory. Reinforcement learning algorithms such as Q-learning can be used to optimize flight strategies, such as finding the optimal route under complex meteorological conditions. Transfer learning can use existing passenger aircraft model knowledge to quickly build a digital twin model of a new cargo aircraft, greatly improving modeling efficiency. This multi-level, multi-method digital twin model construction method can comprehensively and accurately describe the motion characteristics of the aircraft, providing strong support for flight safety management, air traffic control and other fields.

[0060] S105. Apply the optimized aircraft motion model to low-altitude resource management, introduce the particle swarm optimization algorithm into the digital twin model, coordinate the planning and dynamic scheduling of low-altitude resources, balance the needs of different stakeholders, improve the efficiency and coordination level of low-altitude airspace management, and achieve optimal configuration of low-altitude resources.

[0061] Specifically, based on the predicted trajectory and state parameters of the aircraft, combined with the real-time occupancy of low-altitude resources, the particle swarm optimization algorithm is used to carry out the overall planning and dynamic scheduling of low-altitude resources in the digital twin model to generate the optimal resource allocation plan. In the iterative process of the particle swarm optimization algorithm, the demand weights of different stakeholders are introduced, such as aircraft operators, air traffic control departments, ground facilities, etc., and the interests of all parties are balanced by adjusting the weight coefficients to ensure that the generated resource allocation plan takes into account both fairness and efficiency. The feasibility analysis and risk assessment of the generated low-altitude resource allocation plan are carried out to determine whether the plan meets the constraints such as safety and reliability. If not, it is returned and optimized and iterated again until a feasible optimal plan is obtained. The optimized low-altitude resource allocation plan is sent to the relevant aircraft operators and air traffic control departments to guide them in planning and scheduling flight missions. At the same time, the key parameters in the plan are fed back to the digital twin model in real time for dynamic updating and adjustment. In the process of low-altitude resource management, the real-time status of aircraft and the occupancy of low-altitude resources are continuously monitored, and data are analyzed and predicted through machine learning algorithms to identify potential conflict risks and resource bottlenecks, and timely adjust optimization strategies to improve the real-time and accuracy of management. A collaborative mechanism and data sharing platform for low-altitude resource management is established to promote information exchange and decision-making coordination among different stakeholders, improve the management efficiency and resource utilization of low-altitude airspace, and achieve the optimal configuration and sustainable development of low-altitude resources.

[0062] In this embodiment, the particle swarm optimization algorithm is used in this scenario. Each particle can represent a potential resource allocation scheme, and its position and speed correspond to the trajectory and state parameters of the aircraft. For example, a particle may represent a scheme such as "UAV A flies along a specific path at an altitude of 500 meters at a speed of 60km / h". The algorithm searches for the optimal resource allocation scheme by continuously iterating and adjusting the position and speed of the particles. The design of the fitness function is the key to the success of the algorithm. It can comprehensively consider multiple factors, such as flight safety, resource utilization efficiency, task completion time, etc. For example, a simple fitness function may be: f = w1*safety + w2*efficiency + w3*time, where w1, w2, and w3 are weight coefficients. Safety can be measured by the minimum distance between the aircraft and the obstacle, efficiency can be expressed by airspace utilization, and time directly uses the task completion time. The convergence process of the algorithm reflects the process of scheme optimization. Initially, particles may be distributed throughout the solution space, representing various possible resource allocation schemes. As the iteration proceeds, the particles will gradually move closer to the optimal solution. For example, in an urban delivery scenario, the initial plan may include some dangerous paths through high-rise buildings, but after optimization, these paths will be adjusted to safer and more efficient routes. The optimal solution output in the end needs to be applied in actual management. For example, for an urban logistics distribution network, the optimized plan may include multiple drone routes, each of which is carefully designed to avoid high-risk areas and maximize delivery efficiency. The ground control center can dynamically adjust the flight plans of each drone based on this plan to ensure the coordinated operation of the entire network. This low-altitude resource management method based on particle swarm optimization can not only improve resource utilization efficiency, but also significantly enhance flight safety. Through real-time adjustment and optimization, it can flexibly respond to complex and changeable low-altitude environments, laying the foundation for future smart city air traffic management.

[0063] S106. In the application of the digital twin model, the knowledge graph technology is introduced to build a low-altitude airspace management knowledge base and reasoning engine. The knowledge graph contains multi-dimensional information such as airspace structure, flight rules, and meteorological conditions, and realizes low-altitude airspace situation understanding and decision support through semantic association. According to the knowledge graph rules and constraints, flight plans and airspace applications are automatically reviewed and conflicts are detected to improve the level of intelligent management.

[0064] Specifically, based on the multi-dimensional information of low-altitude airspace, such as airspace structure, flight rules and meteorological conditions, a low-altitude airspace management knowledge graph is constructed, entities, attributes and relationships are established, and a semantic association network is formed. Through the knowledge graph reasoning engine, the semantic association information in the graph is used, combined with the real-time airspace situation data, to understand and analyze the low-altitude airspace situation and provide support for management decisions. According to the airspace management rules and constraints defined in the knowledge graph, the submitted flight plans and airspace applications are automatically reviewed to determine whether they meet the relevant regulations and requirements. In the process of flight plan and airspace application review, the semantic association and reasoning ability of the knowledge graph are used to detect conflicts and incompatibilities between different plans and applications to ensure the safety and rationality of airspace use. Digital twin technology is combined with knowledge graphs to build a virtual simulation environment for low-altitude airspace, and airspace management strategies and decision-making plans are optimized through simulation and analysis of virtual airspace. Machine learning algorithms, such as decision trees, support vector machines or neural networks, are used to train airspace management decision models based on the semantic association features of knowledge graphs to achieve intelligent management decision support. Through the visual display of the knowledge graph, managers are provided with intuitive airspace situation presentation and correlation analysis, assisting in manual decision-making and management optimization in complex airspace environments.

[0065] In this embodiment, the low-altitude airspace management knowledge graph is a semantic network structure used to represent airspace entities, attributes and relationships. For example, the airspace can be divided into different blocks, each of which contains attributes such as altitude, latitude and longitude range, and adjacency with surrounding blocks. Flight rules can be expressed as constraint relationships between entities, such as no-fly or restricted flight in certain areas. Meteorological conditions can be associated with airspace blocks as dynamic attributes. The knowledge graph reasoning engine can use the semantic associations in the graph for complex reasoning. For example, when severe convective weather is detected in a certain area, the reasoning engine can automatically infer the affected routes and flight plans, and give adjustment suggestions. This intelligent analysis greatly improves the efficiency and accuracy of airspace management. Knowledge graphs can play an important role in flight plan review. Suppose a drone applies to fly over a city, the system will automatically check the flight restriction rules, building height and other information in the area to determine whether it meets safety requirements. If there is a potential risk, the system will give specific reasons and provide alternatives. Conflict detection is a key link in airspace management. Through the association analysis of the knowledge graph, the system can quickly identify flight plans that overlap in time and space. For example, when the expected routes of two aircraft approach at a certain point in time, the system will automatically mark potential conflict points and give avoidance suggestions based on factors such as flight priority. The combination of digital twin technology and knowledge graphs can create a highly realistic virtual airspace environment. In this environment, managers can simulate different airspace division schemes and evaluate their impact on indicators such as traffic flow and safety. This visual simulation greatly improves the scientific nature and foresight of decision-making. Machine learning algorithms have broad application prospects in airspace management. For example, a neural network model can be trained using historical data to predict airspace congestion in a certain period of time in the future. The model can consider a variety of factors, such as weather and holidays, to provide a basis for the dynamic allocation of airspace resources. The visualization function of the knowledge graph provides managers with intuitive decision support tools. For example, when dealing with emergencies, the system can quickly present key information such as the airspace structure, aircraft distribution, and alternative routes in the affected area to help managers quickly formulate response strategies. This visual analysis greatly improves the efficiency and accuracy of decision-making in complex situations.

[0066] This embodiment also provides a low-altitude airspace collaborative management system based on digital twins, including:

[0067] A multi-source data fusion perception module is used to collect multi-modal data of the aircraft, process the multi-modal data through a Kalman filter data fusion algorithm, and obtain key parameters of the aircraft;

[0068] An aircraft motion characteristic acquisition module is used to construct a kinematic and dynamic model according to the aircraft model to process the key parameters and obtain the maneuverability and flight envelope characteristic parameters of the aircraft;

[0069] The aircraft digital twin synchronization module is used to synchronize the key parameters, maneuverability performance parameters and flight envelope characteristic parameters of the aircraft into the virtual environment through digital twin technology to obtain a digital model;

[0070] A multi-level digital twin model construction module is used to construct a multi-level digital twin model based on the differences in aircraft motion characteristics in different digital models;

[0071] A low-altitude resource management module based on particle swarm optimization is used to introduce a particle swarm optimization algorithm into the multi-level digital twin model to comprehensively plan and dynamically schedule low-altitude resources;

[0072] The intelligent airspace management module based on knowledge graph is used to introduce knowledge graph technology into the multi-level digital twin model, build a virtual simulation environment for low-altitude airspace, and make low-altitude airspace situation decisions through the semantic association of the knowledge graph.

[0073] This embodiment further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0074] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method are implemented.

[0075] This embodiment also provides a computer program product, including a computer program, which implements the steps of the method when executed by a processor.

[0076] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A low-altitude airspace collaborative management method based on digital twins, characterized in that: The following steps are involved: Collecting multimodal data of the aircraft, processing the multimodal data through a Kalman filter data fusion algorithm, and obtaining key parameters of the aircraft; Constructing kinematic and dynamic models according to the aircraft model to process the key parameters and obtain the maneuverability performance and flight envelope characteristic parameters of the aircraft; Through digital twin technology, the key parameters, maneuverability performance parameters and flight envelope characteristic parameters of the aircraft are synchronized into the virtual environment to obtain a digital model; Construct a multi-level digital twin model based on the differences in aircraft motion characteristics in different digital models; Introducing a particle swarm optimization algorithm into the multi-level digital twin model to comprehensively plan and dynamically schedule low-altitude resources; The knowledge graph technology is introduced into the multi-level digital twin model to construct a virtual simulation environment for low-altitude airspace, and low-altitude airspace situation decisions are made through the semantic association of the knowledge graph.

2. The method according to claim 1, characterized in that The key parameters of the aircraft include: A multi-source heterogeneous sensor network is used to collect data to obtain multimodal data; the multimodal data is cleaned and standardized to eliminate noise and outliers in the data; feature extraction is performed on the standardized multimodal data to obtain parameters that can reflect the characteristics of different aircraft; the parameters reflecting the characteristics of different aircraft are input into a Kalman filter data fusion model to sense and map the real-time status of the aircraft; and key aircraft parameters are obtained based on the output results of the Kalman filter data fusion model.

3. The method according to claim 1, characterized in that Obtaining the maneuverability and flight envelope characteristic parameters of the aircraft includes: A kinematic and dynamic model is constructed based on the aircraft model. The model includes the mass, thrust and drag parameters of the aircraft. The key parameters of the aircraft are input into the kinematic and dynamic model, and the position, velocity and attitude state of the aircraft at the next moment are predicted through numerical integration methods. The flight envelope of the aircraft is determined based on the maneuverability parameters of the aircraft and the prediction results, where the flight envelope includes the characteristic parameters of maximum speed, maximum acceleration and minimum turning radius.

4. The method according to claim 1, characterized in that Building a multi-level digital twin model includes: By analyzing the motion trajectory and formation changes of each aircraft group, an aircraft group behavior model is constructed; on the basis of the aircraft group behavior model, a single aircraft dynamic model is further established; the single aircraft dynamic model comprehensively considers the dynamic characteristics and environmental factors of the aircraft, and makes a refined description of the motion state of a single aircraft; on the upper layer of the single aircraft dynamic model, a macro airspace structure model is constructed; the airspace structure model describes the airspace environment in which the aircraft is located based on the topography, meteorological conditions and control rules of the airspace; the aircraft group behavior model, the single aircraft dynamic model and the airspace structure model are integrated to form a multi-level digital twin model.

5. The method according to claim 1, characterized in that Overall planning and dynamic scheduling of low-altitude resources include: Through the particle swarm optimization algorithm, low-altitude resources are comprehensively planned and dynamically scheduled in the multi-level digital twin model to generate the optimal resource allocation plan; in the iterative process of the particle swarm optimization algorithm, the demand weights of different stakeholders are introduced, and the interests of stakeholders are balanced by adjusting the weight coefficients; the feasibility analysis and risk assessment of the generated low-altitude resource allocation plan are carried out to determine whether the plan meets the constraints. If not, it is iteratively optimized until a feasible optimal plan is obtained; the optimized low-altitude resource allocation plan is sent to relevant aircraft operators and air traffic control departments for flight mission planning and scheduling, and the key parameters of the plan are fed back to the multi-level digital twin model in real time for dynamic updating and adjustment.

6. The method according to claim 1, characterized in that The semantic association of knowledge graphs is used to make low-altitude airspace situation decisions, including: Knowledge graph technology is introduced into the multi-level digital twin model to build a low-altitude airspace management knowledge base and reasoning engine. The knowledge graph contains multi-dimensional information on airspace structure, flight rules and meteorological conditions, and realizes low-altitude airspace situation understanding and decision support through semantic association. Flight plans and airspace applications are automatically reviewed and conflicts are detected according to the rules and constraints of the knowledge graph.

7. A low-altitude airspace collaborative management system based on digital twins, characterized in that: include: A multi-source data fusion perception module is used to collect multi-modal data of the aircraft, process the multi-modal data through a Kalman filter data fusion algorithm, and obtain key parameters of the aircraft; An aircraft motion characteristic acquisition module is used to construct a kinematic and dynamic model according to the aircraft model to process the key parameters and obtain the maneuverability and flight envelope characteristic parameters of the aircraft; The aircraft digital twin synchronization module is used to synchronize the key parameters, maneuverability performance parameters and flight envelope characteristic parameters of the aircraft into the virtual environment through digital twin technology to obtain a digital model; A multi-level digital twin model construction module is used to construct a multi-level digital twin model based on the differences in aircraft motion characteristics in different digital models; A low-altitude resource management module based on particle swarm optimization is used to introduce a particle swarm optimization algorithm into the multi-level digital twin model to comprehensively plan and dynamically schedule low-altitude resources; The intelligent airspace management module based on knowledge graph is used to introduce knowledge graph technology into the multi-level digital twin model, build a virtual simulation environment for low-altitude airspace, and make low-altitude airspace situation decisions through the semantic association of the knowledge graph.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images