Low-altitude traffic flow characteristic analysis and airspace capacity dynamic evaluation method and system

Abstract

The invention discloses a low-altitude traffic flow characteristic analysis and airspace capacity dynamic evaluation method and system. The method comprises the following steps: S1, acquiring and preprocessing low-altitude traffic flow data; s2, constructing a multi-element low-altitude three-dimensional road resistance function; s3, constructing a multi-dimensional low-altitude airspace bearing capacity model; s4, constructing a dynamic updating mechanism of a low-altitude traffic flow path resistance function and a bearing capacity model; and S5, carrying out traffic flow characteristic analysis and airspace capacity dynamic evaluation on the low-altitude aircraft by using the obtained model. The method disclosed by the invention is suitable for a three-dimensional low-altitude traffic environment, is particularly suitable for traffic flow characteristic analysis and airspace capacity dynamic evaluation of low-altitude aircrafts such as a logistics unmanned aerial vehicle, a manned vertical take-off and landing aircraft (eVTOL) and an environment monitoring unmanned aerial vehicle, and can adapt to complex meteorological conditions, electromagnetic interference and dynamic airspace management requirements; and technical support is provided for fine management of low-altitude traffic and efficient utilization of airspace resources.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of low-altitude traffic management, and particularly relates to a road resistance function and bearing capacity model construction method suitable for a three-dimensional low-altitude traffic environment. BACKGROUND

[0002] With the promotion of low-altitude airspace opening policy and the large-scale application of low-altitude aircraft such as unmanned aerial vehicles and urban air vehicles (eVTOL), efficient management of low-altitude traffic flow and accurate assessment of airspace bearing capacity have become key problems to be solved. However, the existing traffic flow analysis and bearing capacity assessment methods are mainly designed for ground traffic and are difficult to adapt to the three-dimensional dynamic characteristics of low-altitude traffic, and have the following limitations:

[0003] 1. Dimensional limitation: Traditional road resistance functions (such as BPR function and Davidson function) are designed only for two-dimensional plane traffic flow, and do not consider the three-dimensional airspace characteristics of low-altitude traffic such as vertical stratification flight and dynamic obstacle avoidance, resulting in the inability of the model to accurately represent the distribution and conflict risk of aircraft in the height direction.

[0004] 2. Insufficient environmental sensitivity: Compared with the ground traffic environment, the low-altitude traffic environment is significantly affected by meteorological conditions, terrain building group shielding, electromagnetic interference and other factors, and the existing model does not systematically quantify the comprehensive influence of these dynamic factors on traffic flow efficiency and safety. For example, the document "Modeling of Air Traffic Road Resistance Function" (Lu Zhaoyang, Guo Yushuai, Hao Enlei. Modeling of Air Traffic Road Resistance Function [J]. Aviation Computing Technology, 2018, 48(02): 18-21.) introduces a flight route load differentiation factor Finally, the air traffic road resistance function is formed, but this research does not consider obstacle avoidance in low-altitude traffic and ignores environmental impact, resulting in a large limitation of the road resistance function model, which is only suitable for simple high-altitude airspace traffic.

[0005] 3. Defects of static model: The existing bearing capacity models rely on static parameters and offline data, and are difficult to respond to sudden events or dynamic traffic demand changes in real time, and cannot support minute-level dynamic allocation of airspace resources.

[0006] In addition, the dynamic characteristics of low-altitude traffic flow (such as aircraft heterogeneity and task diversity) further increase the complexity of model construction. For example, the differences in safety interval and communication reliability requirements between logistics unmanned aerial vehicles and manned eVTOLs are significant, and the traditional model does not design differentiated parameters for such heterogeneous scenarios, resulting in insufficient universality.

[0007] To address the above issues, it is urgent to propose a method for constructing a low-altitude traffic flow path resistance function and carrying capacity model that integrates three-dimensional airspace characteristics, dynamic correction of multiple environmental factors, and multi-dimensional comprehensive evaluation to support the refined management of low-altitude traffic and the efficient use of airspace resources. Summary of the Invention

[0008] The technical problem to be solved by the present invention: The present invention aims to solve the technical problem of the imperfect existing low-altitude traffic flow path resistance function and carrying capacity model, and provide a method for constructing a low-altitude traffic flow path resistance function and carrying capacity model to achieve accurate characterization of low-altitude traffic flow characteristics and scientific evaluation of airspace carrying capacity.

[0009] In order to solve the technical problems raised by the present invention, the present invention adopts the following technical solutions:

[0010] First, the present invention proposes a method for analyzing low-altitude traffic flow characteristics and dynamically evaluating airspace capacity, comprising the following steps:

[0011] S1. Collect multi-source data of low-altitude traffic flow to form a multi-source heterogeneous raw data set and perform preprocessing.

[0012] S2. Integrate environmental impact factors into the basic road resistance function framework to construct a multi-factor low-altitude three-dimensional road resistance function;

[0013] S3. First, a multi-dimensional indicator system is constructed based on the road resistance function and environmental impact factors. Then, the analytic hierarchy process is applied to determine the weights of each indicator and construct a multi-criteria comprehensive evaluation model. Finally, the dynamic threshold of carrying capacity under the road resistance constraint is determined to obtain a multi-dimensional low-altitude airspace carrying capacity model.

[0014] S4. Coordinated optimization of the parameters of the road resistance function and the carrying capacity model, introducing a real-time response mechanism to environmental changes and a dynamic update strategy at multiple time scales, and constructing a dynamic update mechanism for the road resistance function and carrying capacity model of low-altitude traffic flow;

[0015] S5. Use the real-time updated low-altitude traffic flow resistance function and carrying capacity model to analyze the traffic flow characteristics of low-altitude aircraft and dynamically evaluate the airspace capacity.

[0016] Furthermore, step S1 of the present invention includes:

[0017] S101. Collect real-time trajectory data, flight status data, and meteorological environment data of low-altitude aircraft to form a multi-source heterogeneous raw data set;

[0018] S102, Data Cleaning and Fusion: Pre-process the collected raw data sets, implement spatiotemporal fusion of multi-source data based on the Kalman filter algorithm, and construct a unified standard format for low-altitude traffic flow data;

[0019] S103, data partitioning and feature extraction: according to the spatial height layering, the data is vertically partitioned, and the traffic Q in each region is extracted based on the spatio-temporal clustering method x,y,z (t), environmental impact factor F x,y,z (t) key feature parameters, wherein (x, y, z) represents three-dimensional grid coordinates, and t represents time.

[0020] Further, step S2 includes the following sub-steps:

[0021] S201, construction of basic road resistance function framework: based on the nonlinear flow-density relationship, a three-dimensional spatial basic road resistance function framework is constructed:

[0022] Wherein, T x,y,z (t) represents the actual flight time of the coordinate (x, y, z) grid unit at t time, T f,x,y,z (t) represents the ideal flight time under free flow state, Q x,y,z (t) represents the flow in each region, C x,y,z (t) represents the basic traffic capacity of the grid unit, and the parameters α=0.15 and β=4.0.

[0023] S202, construction of environmental impact factor: introduce meteorological impact factor W x,y,z (t), obstacle avoidance factor D x,y,z (t), communication delay factor L x,y,z (t), and construct the comprehensive environmental impact factor:

[0024] F x,y,z (t) = λ1W x,y,z (t) + λ2D x,y,z (t) + λ3L x,y,z (t),

[0025] Wherein, λ1, λ2, λ3 are weight coefficients, and satisfy λ1+λ2+λ3=1.

[0026] S203, construction of three-dimensional road resistance function in low altitude: the environmental impact factor is integrated into the basic road resistance function framework, and a comprehensive three-dimensional road resistance function model in low altitude is constructed:

[0027]

[0028] Wherein, γ is an environmental sensitivity coefficient, which is used to adjust the influence strength of environmental factors on the road resistance function.

[0029] Further, the step S3 of the present application specifically includes:

[0030] S301, construction of multi-dimensional index system based on road resistance function: using the road resistance function T x,y,z(t) and its environmental impact factor F x,y,z (t), construct the efficiency index E x,y,z (t), safety index S x,y,z (t), Environmental adaptability index A x,y,z (t) a multi-dimensional evaluation index system, in which:

[0031] Efficiency Index That is, 1 minus the ratio of actual delay to maximum acceptable delay to represent the degree of closeness between actual flight time and ideal flight time;

[0032] Safety indicators Where η is the adjustment coefficient, which controls the rate at which safety decreases as the derivative increases, and the rate of change of the road resistance function is used to evaluate the potential conflict risk;

[0033] Environmental adaptability index Where μ is the adjustment coefficient, and the environmental impact factors in S2 are used to evaluate environmental adaptability. As the environmental impact increases, the environmental adaptability index decreases nonlinearly;

[0034] S302. Construction of hierarchical multi-criteria evaluation model: Apply the analytic hierarchy process to determine the weights of each indicator and construct a multi-criteria comprehensive evaluation model: P x,y,z (t) = ω1E x,y,z (t)+ω2S x,y,z (t)+ω3A x,y,z (t), where ω1, ω2, and ω3 are the weights of the indicators of each dimension, satisfying ω1+ω2+ω3=1;

[0035] S303, Determination of dynamic threshold of carrying capacity under road resistance constraint: Based on historical data analysis and expert knowledge, determine the critical performance threshold P critical and the maximum acceptable resistance T max , by solving the system of equations: Reverse calculation of the maximum acceptable flow value Q max,x,y,z (t), is the dynamic bearing capacity value of the (x, y, z) grid cell at time t.

[0036] Furthermore, step S4 of the present invention specifically includes:

[0037] S401. Collaborative parameter optimization of the road resistance function and the carrying capacity model: A joint parameter optimization framework based on a hybrid of gradient descent and genetic algorithms is constructed. By minimizing the error between measured traffic flow data and model predictions, adaptive optimization of key parameters such as α, β, and γ in the road resistance function and weight coefficients ω1, ω2, and ω3 in the carrying capacity model is simultaneously achieved:

[0038]

[0039] in, Indicates the measured value of road resistance. Represents the predicted value of road resistance, Indicates the flow reference value, Indicates the traffic forecast value;

[0040] S402, Real-time response mechanism for environmental changes: Establish a deep learning-based environmental change detection and response mechanism. When significant changes in meteorological conditions, obstacle distribution, or electromagnetic environment are detected, the environmental impact factor F is automatically triggered. x,y,z (t) updated calculation;

[0041] S403. Multi-time-scale dynamic update strategy: Design a multi-time-scale update strategy that includes short-term, medium-term, and long-term, and set different update frequencies for different parameters to ensure that the model can adapt to dynamic changes in traffic flow characteristics while maintaining computational efficiency.

[0042] In addition, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed, the steps of the method of the present invention are implemented.

[0043] Finally, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method of the present invention when executed by a processor.

[0044] The present invention adopts the above technical solution, which has the following technical effects compared with the prior art:

[0045] The present invention innovatively constructs a road resistance function model that adapts to the characteristics of low-altitude three-dimensional airspace, effectively depicts the traffic flow characteristics of low-altitude aircraft in the vertical and horizontal directions, and improves the matching degree between the model and the actual low-altitude traffic environment; by introducing environmental influencing factors such as weather, obstacles, and communication interference, it realizes the refined characterization of complex low-altitude environments, and significantly improves the adaptability of the model to environmental changes; based on data-driven parameter optimization and multi-time scale update strategies, the model can respond to changes in traffic flow characteristics in real time and support dynamic management decisions of low-altitude traffic; a multi-dimensional evaluation index system including safety, efficiency and environmental adaptability is constructed to comprehensively evaluate the carrying capacity of low-altitude airspace and provide a basis for the scientific allocation of airspace resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is the flow chart for low-altitude traffic flow data collection and preprocessing.

[0047] Figure 2 Construct a framework diagram for the multi-element low-altitude three-dimensional road resistance function.

[0048] Figure 3 A flow chart for multi-dimensional low-altitude airspace carrying capacity evaluation model construction.

[0049] Figure 4 A dynamic updating mechanism architecture diagram for low-altitude traffic flow path resistance function and carrying capacity model.

[0050] Figure 5 A certain city low-altitude traffic corridor airspace capacity dynamic evaluation result example diagram. DETAILED DESCRIPTION

[0051] The application will be further described below in conjunction with the drawings, and it should be understood that these embodiments are only used to illustrate the application and not to limit the scope of the application. After reading the application, those skilled in the art can modify various equivalent forms of the application, which fall within the scope defined by the claims attached hereto.

[0052] The application relates to a low-altitude traffic flow path resistance function and carrying capacity model construction method, in particular to traffic flow characteristic analysis and airspace capacity dynamic evaluation of low-altitude aircraft such as logistics unmanned aircraft, manned vertical take-off and landing aircraft (eVTOL), environmental monitoring unmanned aircraft, etc., which can adapt to complex weather conditions, electromagnetic interference and dynamic airspace management requirements.

[0053] The model method of the application comprises the following four steps: S1: low-altitude traffic flow data acquisition and preprocessing; S2: multi-element low-altitude three-dimensional path resistance function construction; S3: multi-dimensional low-altitude airspace carrying capacity model construction; and S4: dynamic updating mechanism construction of low-altitude traffic flow path resistance function and carrying capacity model.

[0054] As a preferred technical solution of the application, step S1 is divided into three steps.

[0055] S1.1, multi-source data acquisition: as shown in the figure, real-time trajectory data, flight state data and meteorological environment data of low-altitude aircraft are collected by using ground monitoring equipment (such as low-altitude monitoring radar, ADS-B receiving equipment), airborne data downlink system and low-altitude meteorological sensing network, forming a multi-source heterogeneous original data set. Figure 1

[0056] S1.2, data cleaning and fusion: the collected original data is preprocessed, such as time-space registration, outlier elimination and missing value completion, the time-space fusion of multi-source data is realized based on Kalman filtering algorithm, and a unified data standard format of low-altitude traffic flow is constructed.

[0057] S1.3, data partitioning and feature extraction: the data is vertically partitioned according to airspace height stratification (0-120m, 120-300m, 300-1000m), and the traffic flow density ρ x,y,z (t) and average flight speed v​x,y,z (t), flow rate Q x,y,z (t) and other key characteristic parameters, where (x, y, z) represent the three-dimensional grid coordinates and t represents time.

[0058] As a preferred technical solution of the present invention, Figure 2 As shown, step S2 is divided into three steps:

[0059] S2.1. Construction of basic road resistance function framework: Based on the nonlinear flow-density relationship, a three-dimensional airspace basic road resistance function framework is constructed: Among them, T x,y,z (t) represents the actual flight time of the grid cell with coordinates (x, y, z) at time t, T f,x,y,z (t) represents the ideal flight time in free flow state, C x,y,z (t) represents the basic capacity of the grid unit, with parameters α = 0.15 and β = 4.0.

[0060] S2.2. Construction of environmental impact factors: Introducing meteorological impact factors W x,y,z (t), obstacle avoidance factor D x,y,z (t), communication delay (electromagnetic interference) factor L x,y,z (t), construct comprehensive environmental impact factor: F x,y,z (t)=λ1W x,y,z (t)+λ2D x,y,z (t)+λ3L x,y,z (t) Wherein, λ1, λ2, and λ3 are weight coefficients, satisfying λ1+λ2+λ3=1.

[0061] S2.3. Construction of low-altitude three-dimensional road resistance function: Integrate environmental impact factors into the basic road resistance function framework to construct a comprehensive low-altitude three-dimensional road resistance function model: Among them, γ is the environmental sensitivity coefficient, which is used to adjust the influence of environmental factors on the road resistance function.

[0062] As a preferred technical solution of the present invention, Figure 3 As shown, step S3 is divided into three steps:

[0063] S3.1. Construction of a multi-dimensional indicator system based on road resistance function: Using the road resistance function T constructed in S2 x,y,z (t) and its environmental impact factor F x,y,z (t), construct the efficiency index E x,y,z (t), safety index S x,y,z (t), Environmental adaptability index A x,y,z (t) a multi-dimensional evaluation index system, in which:

[0064] Efficiency Index That is, 1 minus the ratio of actual delay to maximum acceptable delay to represent the degree of closeness between actual flight time and ideal flight time;

[0065] Safety indicators Where η is the adjustment coefficient, which controls the rate at which safety decreases as the derivative increases, and the rate of change of the road resistance function is used to evaluate the potential conflict risk;

[0066] Environmental adaptability index Where μ is the adjustment coefficient, and the environmental impact factors in S2 are used to evaluate environmental adaptability. As the environmental impact increases, the environmental adaptability index decreases nonlinearly.

[0067] S3.2. Construction of hierarchical multi-criteria evaluation model: Apply the analytic hierarchy process to determine the weights of each indicator and construct a multi-criteria comprehensive evaluation model: P x,y,z (t) = ω1E x,y,z (t)+ω2S x,y,z (t)+ω3A x,y,z (t), where ω1, ω2, and ω3 are the weights of the indicators in each dimension, satisfying ω1+ω2+ω3=1.

[0068] S3.3 Determination of dynamic threshold of carrying capacity under road resistance constraint: Based on historical data analysis and expert knowledge, the critical performance threshold P is determined. critical and the maximum acceptable resistance T max , by solving the system of equations: Reverse calculation of the maximum acceptable flow value Q max,x,y,z (t), is the dynamic bearing capacity value of the (x, y, z) grid element at time t. The solution process adopts the bisection method or Newton iteration method to ensure computational efficiency and convergence stability.

[0069] As a preferred technical solution of the present invention, Figure 4 As shown, step S4 is divided into three steps:

[0070] S4.1. Collaborative parameter optimization of the road resistance function and the carrying capacity model: A joint parameter optimization framework based on a hybrid of gradient descent and genetic algorithms is constructed. By minimizing the error between measured traffic flow data and model predictions, adaptive optimization of key parameters such as α, β, and γ in the road resistance function and weight coefficients ω1, ω2, and ω3 in the carrying capacity model is simultaneously achieved:

[0071]

[0072] Among them, λ is the trade-off coefficient for balancing the two optimization objectives, and its value range is usually 0.1-10.

[0073] S4.2. Cascade response mechanism for environmental changes: Establish an environmental change detection and response mechanism based on the CNN-LSTM deep learning network. When significant changes in meteorological conditions, obstacle distribution, or electromagnetic environment are detected, the environmental impact factor F is automatically triggered in the cascade order of "road resistance function update → bearing capacity model update". x,y,z (t) is updated and the carrying capacity assessment results are subsequently updated. The criteria for determining the significance of environmental changes are: changes in meteorological conditions exceeding 20%, changes in obstacle distribution density exceeding 15%, or changes in electromagnetic interference intensity exceeding 25%.

[0074] S4.3. Multi-timescale collaborative update strategy: Design a multi-timescale collaborative update strategy encompassing short-term (5-minute), medium-term (hourly), and long-term (daily) updates. Implement differentiated but coordinated update frequencies for the resistance function and carrying capacity model to ensure mathematical consistency and causal relevance between the two models. This ensures that the two models maintain mathematical consistency and causal relevance while optimizing computing resource utilization. Implement differentiated but coordinated updates according to the following rules:

[0075] Short-term update (5 minutes): only update the environmental impact factor F in the road resistance function x,y,z (t), and the maximum acceptable flow value Q calculated based on the updated road resistance function max,x,y,z (t), keep the basic parameters unchanged;

[0076] Mid-term update (hourly): Update the γ parameter in the road resistance function and the weight coefficients ω1, ω2, and ω3 in the carrying capacity model to adapt to changes in traffic flow conditions;

[0077] Long-term update (daily): Comprehensively optimize all parameters α, β, γ in the road resistance function and the complete calculation logic of the carrying capacity model to ensure the model's adaptability to long-term changes in traffic flow characteristics.

[0078] Finally, the traffic flow characteristics of low-altitude aircraft and the dynamic evaluation of airspace capacity are carried out using the real-time updated low-altitude traffic flow resistance function and carrying capacity model.

[0079] Example 1: The method of the present invention was applied to construct a low-altitude traffic flow resistance function and carrying capacity model for a low-altitude logistics distribution corridor in a certain city (east-west, 10 km long, 2 km wide, and with an altitude range of 0-300 m). First, based on the five low-altitude surveillance radars and 20 ADS-B ground stations deployed in the area, a total of 74,582 low-altitude aircraft trajectory data were collected from March 15, 2024, to April 15, 2024. Meteorological data and electromagnetic environment data were also collected during the same period.

[0080] The data preprocessing method in S1 of the application divides the airspace into a 10*2*3 three-dimensional grid (1km*1km in the horizontal direction, and divided into three layers of 0-120m, 120-200m, and 200-300m in the vertical direction), and extracts the traffic flow density, average flight speed, and flow of each grid unit as characteristic parameters.

[0081] The S2 step of the application is used to construct a multi-element low-altitude three-dimensional road resistance function. For the environmental influence factor, the weight coefficients λ1=0.5, λ2=0.2, and λ3=0.3 are determined based on expert experience, and the environmental sensitivity coefficient γ=0.8.

[0082] Then, the S3 step of the application is used to construct a multi-dimensional low-altitude airspace carrying capacity model based on the constructed road resistance function. The efficiency index is directly calculated according to the formula , wherein T max is set as 2.5 times the free flow time. The safety index is calculated by the formula . The environmental adaptability index is calculated by the formula . The weights of the safety, efficiency, and environmental adaptability indexes are determined by the analytic hierarchy process to be ω1=0.6, ω2=0.3, and ω3=0.1, and the critical performance threshold P critical =0.75.

[0083] Finally, the S4 step of the application is used to construct a collaborative dynamic updating mechanism for the road resistance function and the carrying capacity model, with a trade-off coefficient λ=2.0, to realize joint optimization of the two model parameters. The cascading response mechanism is set to trigger updating when the weather condition changes by more than 20%. The collaborative updating strategy is set to a short-term updating period of 5 minutes, a medium-term updating period of 1 hour, and a long-term updating period of 1 day.

[0084] As shown in Figure 5 , in the actual operation during 7:00-19:00 on April 20, 2025, the system successfully captured the airspace carrying capacity decline (about 35% decline) caused by local strong convective weather from 10:30 to 11:30 in the morning and the airspace capacity fluctuation caused by temporary flight restrictions for large-scale activities from 15:00 to 16:00 in the afternoon. The automatic adjustment of the road resistance function parameters triggered the corresponding update of the carrying capacity model, and the system accurately predicted the traffic flow operation state, with an average prediction error of only 8.7%, which is much lower than the error level of 23.5% of the traditional static model and the error level of 15.3% of the model without the collaborative updating strategy.

[0085] Embodiment 2: This embodiment provides an electronic system, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method steps of the present application.

[0086] Embodiment 3: This embodiment provides a computer-readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the steps of the method of the present application, which will not be described here again.

[0087] It should be noted that the processing procedures of embodiments 2-3 correspond to the specific steps of the method provided by the embodiments of the present application, have the corresponding function modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment can be referred to the method provided by the embodiments of the present application.

[0088] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program codes can be executed entirely on a machine, partially on a machine, partially on a machine as a separate software package, and partially on a remote machine, or entirely on a remote machine or server.

[0089] In the context of the present application, the machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of machine-readable storage media can include one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0090] The above embodiments only illustrate the technical idea of the present application, and cannot limit the protection scope of the present application. Any modification made according to the technical idea of the present application on the basis of the technical solution falls within the protection scope of the present application.

Claims

1. A method for analyzing low-altitude traffic flow characteristics and dynamically evaluating airspace capacity, characterized by: include: S1. Collect multi-source data of low-altitude traffic flow to form a multi-source heterogeneous raw data set and perform preprocessing. S2. Integrate environmental impact factors into the basic road resistance function framework to construct a multi-factor low-altitude three-dimensional road resistance function; S3. First, a multi-dimensional indicator system is constructed based on the road resistance function and environmental impact factors. Then, the analytic hierarchy process is applied to determine the weights of each indicator and construct a multi-criteria comprehensive evaluation model. Finally, the dynamic threshold of carrying capacity under the road resistance constraint is determined to obtain a multi-dimensional low-altitude airspace carrying capacity model. S4. Coordinated optimization of the parameters of the road resistance function and the carrying capacity model, introducing a real-time response mechanism to environmental changes and a dynamic update strategy at multiple time scales, and constructing a dynamic update mechanism for the road resistance function and carrying capacity model of low-altitude traffic flow; S5. Use the real-time updated low-altitude traffic flow resistance function and carrying capacity model to analyze the traffic flow characteristics of low-altitude aircraft and dynamically evaluate the airspace capacity.

2. The method according to claim 1, wherein: Step S1 includes: S101. Collect real-time trajectory data, flight status data, and meteorological environment data of low-altitude aircraft to form a multi-source heterogeneous raw data set; S102, Data Cleaning and Fusion: Pre-process the collected raw data sets, implement spatiotemporal fusion of multi-source data based on the Kalman filter algorithm, and construct a unified standard format for low-altitude traffic flow data; S103, data partitioning and feature extraction: vertically partition the data according to the spatial height layer, and extract the flow Q in each area based on the spatiotemporal clustering method x,y,z (t), environmental impact factor F x,y,z (t) Key feature parameters, where (x, y, z) represents the three-dimensional grid coordinates and t represents time.

3. The method according to claim 1, characterized in that Step S1 is to collect multi-source data of low-altitude traffic flow using ground-based monitoring equipment, airborne data downlink system and low-altitude meteorological perception network. The ground-based monitoring equipment includes low-altitude surveillance radar and ADS-B receiving equipment.

4. The method according to claim 2, characterized in that The preprocessing described in step S102 includes spatiotemporal registration, outlier removal, and missing value completion.

5. The method according to claim 2, characterized in that The airspace altitude layers described in step S103 are specifically divided into 0-120m, 120-300m, and 300-1000m.

6. The method according to claim 1, wherein: Step S2 specifically includes the following sub-steps: S201. Construction of basic road resistance function framework: Based on the nonlinear flow-density relationship, a three-dimensional airspace basic road resistance function framework is constructed: Among them, T x,y,z (t) represents the actual flight time of the grid cell with coordinates (x, y, z) at time t, T f,x,y,z (t) represents the ideal flight time in free flow state, Q x,y,z (t) represents the flow rate in each area, C x,y,z (t) represents the basic capacity of the grid cell, with parameters α = 0.15 and β = 4.0; S202, Construction of environmental impact factors: Introducing meteorological impact factor W x,y,z (t), obstacle avoidance factor D x,y,z (t), communication delay factor L x,y,z (t), construct comprehensive environmental impact factors: F x,y,z (t)=λ1W x,y,z (t)+λ2D x,y,z (t)+λ3L x,y,z (t), Among them, λ1, λ2, and λ3 are weight coefficients, satisfying λ1+λ2+λ3=1; S203, Construction of low-altitude three-dimensional road resistance function: Integrate environmental impact factors into the basic road resistance function framework to construct a comprehensive low-altitude three-dimensional road resistance function model: Among them, γ is the environmental sensitivity coefficient, which is used to adjust the influence of environmental factors on the road resistance function.

7. The method according to claim 6, characterized in that: Step S3 specifically includes: S301. Construction of a multi-dimensional indicator system based on road resistance function: Using the road resistance function T constructed in S2 x,y,z (t) and its environmental impact factor F x,y,z (t), construct the efficiency index E x,y,z (t), safety index S x,y,z (t), Environmental adaptability index A x,y,z (t) a multi-dimensional evaluation index system, in which: Efficiency indicators That is, 1 minus the ratio of actual delay to maximum acceptable delay to represent the degree of closeness between actual flight time and ideal flight time; Safety indicators Where η is the adjustment coefficient, which controls the rate at which safety decreases as the derivative increases, and the rate of change of the road resistance function is used to evaluate the potential conflict risk; Environmental adaptability index Where μ is the adjustment coefficient, and the environmental impact factors in S2 are used to evaluate environmental adaptability. As the environmental impact increases, the environmental adaptability index decreases nonlinearly; S302. Construction of hierarchical multi-criteria evaluation model: Apply the analytic hierarchy process to determine the weights of each indicator and construct a multi-criteria comprehensive evaluation model: P x,y,z (t) = ω1E x,y,z (t)+ω2S x,y,z (t)+ω3A x,y,z (t), where ω1, ω2, and ω3 are the weights of the indicators of each dimension, satisfying ω1+ω2+ω3=1; S303, Determine the dynamic threshold of carrying capacity under road resistance constraints: Based on historical data analysis and expert knowledge, determine the critical performance threshold P critical and the maximum acceptable resistance T max , by solving the system of equations: Reverse calculation of the maximum acceptable flow value Q max,x,y,z (t), is the dynamic bearing capacity value of the (x, y, z) grid cell at time t.

8. The method according to claim 7, wherein: Step S4 specifically includes: S401. Collaborative parameter optimization of the road resistance function and the carrying capacity model: A joint parameter optimization framework based on a hybrid of gradient descent and genetic algorithms is constructed. By minimizing the error between measured traffic flow data and model predictions, adaptive optimization of the key parameters α, β, and γ in the road resistance function and the weight coefficients ω1, ω2, and ω3 in the carrying capacity model is simultaneously achieved: in, Indicates the measured value of road resistance. Represents the predicted value of road resistance, Indicates the flow reference value, Indicates the traffic forecast value; S402, Real-time response mechanism for environmental changes: Establish a deep learning-based environmental change detection and response mechanism. When significant changes in meteorological conditions, obstacle distribution, or electromagnetic environment are detected, the environmental impact factor F is automatically triggered. x,y,z (t) updated calculation; S403. Multi-time-scale dynamic update strategy: Design a multi-time-scale update strategy that includes short-term, medium-term, and long-term, and set different update frequencies for different parameters to ensure that the model can adapt to dynamic changes in traffic flow characteristics while maintaining computational efficiency.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the program implements the steps of the method according to any one of claims 1 to 8.

Images