Low-altitude aircraft take-off and landing platform site selection optimization method

Abstract

The invention discloses a low-altitude aircraft take-off and landing platform site selection optimization method. The method comprises the steps that real-time dynamic data and static GIS data including urban traffic flow data, meteorological data, landform data, environment data and POI data are acquired; constructing an urban three-dimensional digital model according to the static GIS data, and constructing a digital twin model according to the three-dimensional digital model and the real-time dynamic data; constructing environment constraint conditions and safety constraint conditions of candidate take-off and landing platform positions in the digital twin model; performing multi-objective optimization on the digital twin model through a particle swarm optimization algorithm, and generating an optimal candidate take-off and landing platform site selection scheme set meeting environment constraint conditions and safety constraint conditions; and dynamically updating the digital twin model according to real-time data feedback, and dynamically adjusting the site selection scheme of the take-off and landing platform. According to the method, the virtual city model is constructed through the digital twin, an accurate simulation environment and real-time feedback are provided for site selection optimization, and the accuracy and feasibility of a site selection scheme are improved.

Description

Technical Field

[0001] The present invention relates to the field of management and optimization of unmanned aerial vehicles (UAVs), and particularly to a method for optimizing the location selection of a take-off and landing platform for low-altitude aircraft. Background Art

[0002] With the rapid development of UAV technology, especially its wide application in Urban Air Mobility (UAM), the usage frequency and density of UAVs in the low-altitude airspace have increased significantly. However, this has also brought many problems, including the efficient utilization of airspace resources, the guarantee of flight safety, and the management of multi-UAV cooperative operations.

[0003] The existing methods for optimizing the location selection of low-altitude aircraft take-off and landing platforms have the following main deficiencies when facing high-density flight environments and dynamic airspace changes: The existing systems lag in integrating multi-source data such as traffic, meteorology, geography, and environment, and cannot comprehensively reflect the dynamic changes of the city, affecting the accuracy and real-time nature of location selection optimization; Traditional optimization algorithms are inefficient in dealing with multi-objectives and complex constraint conditions and are difficult to meet the requirements of efficient and flexible location selection; They cannot respond in real time to the rapid changes in the urban environment, resulting in the difficulty of dynamically adjusting the location selection plan and reducing the adaptability and stability of the system; As an advanced simulation and prediction tool, digital twins are not yet widely used in the optimization of the location selection of low-altitude aircraft take-off and landing platforms, and their simulation and real-time update capabilities cannot be fully utilized.

[0004] To solve the above problems, the present invention proposes a method for optimizing the location selection of a low-altitude aircraft take-off and landing platform. By constructing a virtual city model through digital twins, it provides an accurate simulation environment and real-time feedback for location selection optimization, so as to improve the accuracy and feasibility of the location selection plan, and further improve the safety and operation efficiency of UAV flights. Summary of the Invention

[0005] In view of the above problems, the present invention provides a method for optimizing the location selection of a low-altitude aircraft take-off and landing platform, including:

[0006] Step S1, obtaining real-time dynamic data including urban traffic flow data, meteorological data, topographic and geomorphic data, environmental data, and POI data, and static GIS data;

[0007] Step S2, constructing a three-dimensional digital model of the city according to the static GIS data, and constructing a digital twin model according to the three-dimensional digital model and the real-time dynamic data;

[0008] Step S3, construct the environmental constraint conditions and safety constraint conditions for the candidate takeoff and landing platform locations in the digital twin model; wherein, the environmental constraint conditions include terrain slope, building height, obstacle distribution, wind direction and speed, and noise impact; the safety constraint conditions include safety distance, route planning, and alternate landing points in case of emergencies;

[0009] Step S4, perform multi-objective optimization on the digital twin model through the particle swarm optimization algorithm to generate an optimal candidate takeoff and landing platform site selection plan set that meets the environmental constraint conditions and safety constraint conditions;

[0010] Step S5, dynamically update the digital twin model according to real-time data feedback and dynamically adjust the takeoff and landing platform site selection plan.

[0011] In an alternative manner, in the step S1:

[0012] Collect real-time road traffic flow and public transportation station data from the urban traffic monitoring system;

[0013] Collect real-time meteorological data of temperature, humidity, wind speed, and wind direction from a weather station or online weather service;

[0014] Obtain urban terrain, building distribution, and land use type information from the GIS database and perform 3D modeling to obtain urban 3D spatial information data;

[0015] Collect real-time noise and air quality environmental data from environmental monitoring stations;

[0016] Obtain POI data including hospitals, schools, commercial areas, and transportation stations in the city from public data sources or third-party services.

[0017] In an alternative manner, in the step S2, the further construction of the urban 3D digital model according to the static GIS data includes:

[0018] Construct a basic urban 3D model according to the static GIS data and access the real-time dynamic data through the API interface;

[0019] Map the real-time dynamic data into the urban 3D digital model and update the parameters of the urban 3D digital model in real time to reflect the dynamic changes of the urban environment.

[0020] In an alternative manner, in the step S4, the further multi-objective optimization of the digital twin model through the particle swarm optimization algorithm includes:

[0021] Generate a demand assessment model based on urban population density, traffic flow, aircraft takeoff and landing requirements, OD travel demand, and regional service demand;

[0022] According to the demand assessment model, the environmental constraint conditions, and the safety constraint conditions, multi-objective optimization is performed on the candidate siting locations in the digital twin model to generate an optional takeoff and landing platform siting scheme that meets the demand assessment model, the environmental constraint conditions, and the safety constraint conditions.

[0023] In an alternative manner, the generating of the demand assessment model according to urban population density, traffic flow, aircraft takeoff and landing requirements, OD travel requirements, and regional service requirements further includes:

[0024] Evaluating the takeoff and landing requirements of high-end communities based on population density and income level data;

[0025] Analyzing the demand fluctuations during peak hours in the business district based on the traffic flow prediction model;

[0026] Evaluating the emergency service requirements around hospitals based on historical first aid data;

[0027] Optimizing the platform location of the airport transportation hub according to airspace restrictions and traffic demands to maximize service efficiency;

[0028] Optimizing the accessibility of the platform near the subway station according to the ground transportation hub data.

[0029] In an alternative manner, the environmental constraint conditions further include:

[0030] Dynamically setting noise buffer zones according to the noise propagation model and environmental monitoring data; optimizing the visibility of the platform through the visibility calculation model to ensure the safe takeoff and landing of aircraft;

[0031] Combining terrain and building data and using spatial analysis tools to set obstacle avoidance areas;

[0032] Excluding siting points within no-fly zones according to the legal and policy database;

[0033] Automatically excluding siting points within no-fly zones according to the flight altitude limit database;

[0034] Performing slope analysis based on the digital elevation model to ensure the physical conditions of the siting area.

[0035] In an alternative manner, the generating of the optimal candidate takeoff and landing platform siting scheme set that meets the environmental constraint conditions and the safety constraint conditions further includes:

[0036] Combining the demand weights of each region with the environmental constraint conditions, and using a weighted algorithm to score all candidate points to generate a preliminary siting scheme;

[0037] Use the particle swarm optimization algorithm to evaluate the demand and environmental adaptability of each candidate site, combine the demand weighting with the environmental constraint conditions, search for suitable site locations and dynamically adjust the positions of the particles, and find the optimal site selection plan that meets all conditions; among them, impose a penalty weight on the candidate points that do not meet the constraint conditions to avoid selecting inappropriate areas into the final plan;

[0038] Dynamically adjust the boundary of the search space during the iteration process. Among them, when the selected site does not meet the constraint conditions, the selected site is removed from the search space or the feasible region of the search space is redefined as the region that does not contain the default points, and the candidate platform positions that meet the requirements are screened.

[0039] In an alternative way, the method further includes evaluating the candidate platform positions, specifically including:

[0040] Evaluate the demand coverage of each candidate platform and calculate its coverage ratio for high-demand areas;

[0041] Evaluate the adaptability of the site selection plan in terms of noise, flight altitude, field of view, and obstacle avoidance through simulation analysis;

[0042] Combined with the no-fly zone and flight altitude restrictions of the city, conduct a legal compliance assessment of the site selection plan;

[0043] Evaluate the economic benefits of the candidate platform positions according to the construction cost, maintenance cost, and expected usage benefits of the selected site area.

[0044] In an alternative way, the method further includes:

[0045] Perform weighted calculations on the evaluation results of demand coverage, environmental adaptability, legal compliance, and cost-benefit to obtain a comprehensive score;

[0046] Sort all the site selection plans according to the level of the comprehensive score to determine the best site selection plan for the low-altitude aircraft takeoff and landing platform.

[0047] In an alternative way, the method further includes:

[0048] Visually present the best site selection plan for the low-altitude aircraft takeoff and landing platform in the digital twin model and generate a site selection report including the selected site location, evaluation results, and constraint conditions.

[0049] According to the solution provided by the present invention, it includes: Step S1, obtaining real-time dynamic data and static GIS data including urban traffic flow data, meteorological data, topographic and geomorphic data, environmental data, and POI data; Step S2, constructing a three-dimensional digital model of the city based on the static GIS data, and constructing a digital twin model based on the three-dimensional digital model and the real-time dynamic data; Step S3, constructing environmental constraint conditions and safety constraint conditions for candidate takeoff and landing platform positions in the digital twin model; wherein, the environmental constraint conditions include terrain slope, building height, obstacle distribution, wind direction and speed, and noise impact; the safety constraint conditions include safety distance, route planning, and alternate landing points in case of emergency; Step S4, performing multi-objective optimization on the digital twin model through a particle swarm optimization algorithm to generate an optimal candidate takeoff and landing platform site selection solution set that meets the environmental constraint conditions and safety constraint conditions; Step S5, dynamically updating the digital twin model according to real-time data feedback, and dynamically adjusting the takeoff and landing platform site selection solution. The present invention constructs a virtual city model through a digital twin, provides an accurate simulation environment and real-time feedback for site selection optimization, and improves the accuracy and feasibility of the site selection solution.

[0050] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the following specifically enumerates the specific embodiments of the present invention. Brief Description of the Drawings

[0051] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0052] Figure 1 It shows a schematic flow chart of the method for optimizing the site selection of a low-altitude aircraft takeoff and landing platform according to an embodiment of the present invention;

[0053] Figure 2 It shows a schematic flow chart of the data collection process according to an embodiment of the present invention;

[0054] Figure 3 It shows a schematic flow chart of the data preprocessing process according to an embodiment of the present invention;

[0055] Figure 4 It shows a schematic flow chart of the dynamic adjustment process of the virtual model according to an embodiment of the present invention;

[0056] Figure 5 It shows a schematic flow chart of the process of selecting a low-altitude aircraft takeoff and landing platform according to an embodiment of the present invention;

[0057] Figure 6 The figure shows a schematic diagram of the evaluation process of the platform selection solution according to an embodiment of the present invention. Detailed implementation manners

[0058] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be completely conveyed to those skilled in the art.

[0059] Figure 1 The figure shows a schematic diagram of the process of the method for optimizing the location selection of the takeoff and landing platform of a low-altitude aircraft according to an embodiment of the present invention. Specifically, as Figure 1 shown, the method includes the following steps:

[0060] Step S1: Obtain real-time dynamic data including urban traffic flow data, meteorological data, topographic and geomorphic data, environmental data, and POI data, and static GIS data.

[0061] In this embodiment, by integrating real-time dynamic data, meteorological changes, traffic conditions, environmental pollution, etc. can be sensed in a timely manner, the flight plan can be adjusted in a timely manner, and the accident risk can be reduced. Combining topographic and geomorphic data to plan the flight route in advance, avoiding obstacles, and ensuring flight safety. Dynamically adjusting the flight path according to traffic conditions and meteorological conditions. Utilizing the favorable wind direction to reduce flight energy consumption and improve energy utilization efficiency. Selecting the most convenient takeoff and landing location in combination with POI data. Reducing the impact of UAM operation on the environment through environmental monitoring data and enhancing public acceptance.

[0062] In an alternative manner, in the step S1:

[0063] Real-time collect road traffic flow and public transportation station data from the urban traffic monitoring system;

[0064] Real-time collect meteorological data such as temperature, humidity, wind speed, and wind direction from a weather station or an online weather service;

[0065] Obtain information on urban topographic and geomorphic features, building distribution, and land use types from the GIS database, and perform three-dimensional modeling to obtain urban three-dimensional space information data;

[0066] Real-time collect noise and air quality environmental data from environmental monitoring stations;

[0067] Obtain POI data including hospitals, schools, commercial areas, and transportation stations in the city from public data sources or third-party services.

[0068] In this embodiment, asFigure 2 As shown, real-time data such as road traffic flow, bus stops, subway stations and other transportation hubs are obtained through the urban traffic monitoring system, and multi-dimensional analysis is carried out on the traffic data, such as traffic density, average vehicle speed, traffic congestion degree, etc., to provide traffic condition data required for the optimization model.

[0069]

[0070] Among them, D traffic is the traffic density score, T vehicle is the number of vehicles passing through per unit time, and A is the area of the monitoring area.

[0071] Collect real-time meteorological data such as temperature, humidity, wind speed, and wind direction through a weather station or online weather service, compare the meteorological change trend with historical data, identify potential extreme weather patterns, and predict the impact on aircraft takeoff and landing.

[0072] W Weather = f(T1, H, V, D)

[0073] Among them, W Weather is the meteorological score, and T1, H, V, and D are temperature, humidity, wind speed, and wind direction respectively.

[0074] Use Geographic Information System (GIS) technology to obtain information such as the topography and landforms, building distribution, and land use types of the city, and combine 3D modeling technology to provide high-precision 3D spatial data of the city.

[0075] G Geography = GIS(L, E, U)

[0076] Among them, G Geography is the geographic score, L is the topographic data, E is the building distribution data, and U is the land use type data.

[0077] Therefore, the further description is as follows:

[0078] L (topographic data): includes Digital Elevation Model (DEM) data, which is used to describe topographic features such as the slope and elevation of the area.

[0079] E (building distribution data): includes the height, density, and distribution of buildings, usually obtained through vector or point cloud data.

[0080] U (land use type): reflects the land use status of different regions (such as residential, commercial, industrial, etc.), generally from land use planning or GIS databases.

[0081] The "GIS" function is not a single mathematical function. Instead, through existing GIS software or development libraries (such as ArcGIS, QGIS, GeoPandas, etc.), it uses data overlay and spatial analysis methods to perform normalization processing and weighted fusion on data such as terrain, building distribution, and land use. To improve accuracy, the following weighted model can be used:

[0082] G Geography = w L × f L (L) + w E × f E (E) + W U × f U (U)

[0083] Where:

[0084] f L (L), f E (E) and f U (U) respectively perform normalization (or use exponential mapping functions) on the original data;

[0085] w L , w E and w U are the weights of f L (L), f E (E) and f U (U) respectively, and are determined through expert calibration or the Analytic Hierarchy Process (AHP) according to the actual situation of the region (such as terrain undulation, importance of building density, etc.).

[0086] Collect environmental data such as noise and air quality through environmental monitoring stations, and combine with the urban environmental noise map to evaluate the impact of different regions on the takeoff and landing of low-altitude aircraft.

[0087] E Environment = α × Noise + β × AirQuality

[0088] Where α and β are weight coefficients, Noise (noise) and AirQuality (air quality) are environmental scoring indicators respectively, and the coefficients satisfy α + β = 1.

[0089] Noise (noise): Represents the regional environmental noise level, and the data is sourced from urban environmental noise monitoring or noise maps.

[0090] AirQuality (air quality): Reflects the air quality situation of the region, and the data is sourced from environmental monitoring stations or relevant public data.

[0091] α and β (weight coefficients): They are the relative weights of noise and air quality in the overall environmental score, and their specific values are determined based on actual regional characteristics, historical data statistics, and expert evaluations. For example, in densely populated areas, the impact of noise may be more significant, so α can be set to a higher value than β, such as α = 0.6 and β = 0.4; in areas with prominent air quality problems, the weights can be adjusted accordingly.

[0092] Obtain POI data such as hospitals, schools, commercial areas, and transportation stations in the city from public data sources or third-party services, and establish a spatial database of urban key points to provide a basis for platform site selection.

[0093] POI database = {hospital, school, commercial area, transportation station}

[0094] Then, as Figure 3 shown, preprocess the above data, including:

[0095] Data deduplication: Deduplicate the collected data to avoid the influence of duplicate data on subsequent analysis. Use hash tables or database deduplication algorithms to ensure data uniqueness.

[0096] Null value filling: Use mean imputation, nearest neighbor imputation, or machine learning algorithms (such as K-nearest neighbor) to fill in the missing data, and select an appropriate filling strategy according to the data characteristics.

[0097] Outlier detection: Detect and remove outliers through statistical analysis and machine learning methods (such as Isolation Forest, Support Vector Machine (SVM)) to ensure data accuracy and validity.

[0098] Data standardization: Adopt Z-score standardization or Min-Max standardization methods to standardize different data sources, ensure that the data meets the requirements of subsequent processing and modeling, unify the scale and range, and avoid analysis biases caused by different dimensions.

[0099] As Figure 4 shown, integrate the Geographic Information System (GIS) data of the city into the digital twin, construct a basic model of the city, including three-dimensional data of terrain, buildings, and road networks, and fuse it with the data of other modules.

[0100] Access real-time traffic, meteorological, environmental monitoring and other dynamic data through API interfaces, and adopt efficient data stream processing technologies to ensure the real-time and stability of data access.

[0101] Step S2: Construct a three-dimensional digital model of the city based on the static GIS data, and construct a digital twin model based on the three-dimensional digital model and the real-time dynamic data.

[0102] In this embodiment, the static GIS data and the three-dimensional digital model provide high-precision urban geographic information, accurately reflecting the detailed information of urban buildings and infrastructure. The digital twin model of real-time dynamic data reflects the operating state of the city in real time.

[0103] Specifically, high-precision remote sensing equipment (such as LiDAR) is used to collect data on urban terrain and buildings, generating high-precision terrain models and building models. 3D modeling software is used to fuse the terrain model and the building model to generate a three-dimensional digital model of the city. The three-dimensional digital model is fused with real-time dynamic data to generate a digital twin model.

[0104] In an alternative manner, in step S2, the constructing of the three-dimensional digital model of the city based on the static GIS data further includes:

[0105] Construct a basic three-dimensional model of the city based on the static GIS data, and access the real-time dynamic data through the API interface;

[0106] Map the real-time dynamic data into the three-dimensional digital model of the city, and update the parameters of the three-dimensional digital model of the city in real time to reflect the dynamic changes of the urban environment.

[0107] In this embodiment, static GIS data (such as terrain and building outlines) is used to construct a basic three-dimensional model of the city (such as 3D modeling software or GIS software like CityEngine, Cesium, Unreal Engine, etc.). It does not need to include all details and only focuses on the basic framework.

[0108] Step S3, construct the environmental constraint conditions and safety constraint conditions for the candidate takeoff and landing platform positions in the digital twin model; wherein, the environmental constraint conditions include terrain slope, building height, obstacle distribution, wind direction and speed, and noise impact; the safety constraint conditions include safety distance, route planning, and alternate landing points in case of emergency.

[0109] In this embodiment, mark the safety distance range in the three-dimensional digital model, map the safety distance range into the three-dimensional digital model, and display the safety distance distribution. Use GPS and route planning algorithms to generate the route of the candidate takeoff and landing platform, and integrate the route data to generate a route planning map. Map the route planning map into the three-dimensional digital model and display the route path. Use GIS data and on-site surveys to collect the location and environmental information of the alternate landing points. Integrate the alternate landing point data to generate an alternate landing point map. Map the alternate landing point map into the three-dimensional digital model and display the location and environmental information of the alternate landing points.

[0110] Step S4, perform multi-objective optimization on the digital twin model through the particle swarm optimization algorithm to generate an optimal candidate landing and takeoff platform location selection scheme set that meets the environmental constraint conditions and safety constraint conditions.

[0111] In this embodiment, as Figure 5 shown, the objective function includes minimizing terrain slope, building height impact, obstacle impact, wind speed impact, noise impact, maximizing safety distance, flight route feasibility, and alternate landing point feasibility. The decision variables include the longitude, latitude, and height of the landing and takeoff platform. A group of particles is randomly generated, and each particle represents a candidate landing and takeoff platform position and direction. The initial position and velocity of the particles are randomly generated within the search space. For each particle, map its position and direction into the digital twin model and calculate its corresponding objective function value. Integrate the data returned by the digital twin model to generate the environmental constraint value and safety constraint value (objective function value) of each particle. Calculate the fitness value of the particle according to the objective function value and constraint conditions. When updating the velocity and position of the particle based on the boundary constraints of the search space. In each iteration, record the global optimal position and the corresponding objective function value. At the same time, record the positions and corresponding objective function values of all particles in each iteration for generating the Pareto optimal solution set. After the iteration ends, select a set of non-dominated solutions from all particles according to the Pareto dominance relationship to form the Pareto optimal solution set, and output the Pareto optimal solution as the candidate landing and takeoff platform location selection scheme set.

[0112] Among them, the genetic algorithm, through the mechanism of natural selection, is suitable for dealing with complex constraint conditions and can optimize various constraints such as noise buffer zones, flight altitude restrictions, and no-fly zones. Specifically, the genetic algorithm simulates the fitness of multiple candidate location points and makes selections according to environmental conditions (such as noise, no-fly zones, flight altitude, etc.), retaining the eligible location areas, so as to effectively screen out the optimal solutions that meet the environmental requirements.

[0113]

[0114] Among them, Fitness is the fitness, ωi is the weight of each constraint condition, and fi(P) is the constraint condition score corresponding to the location point P.

[0115] Each fi(P) represents the score of the location point P under the i-th constraint condition, such as terrain slope, building height, obstacles, wind speed, noise, safety distance, etc.

[0116] Weight coefficient ω iIt is used to adjust the contribution of each constraint condition to the overall fitness, which is determined according to the importance of each index. The specific value of the weight coefficient can be obtained through expert evaluation, statistical regression or sensitivity analysis to ensure that each constraint condition is reasonably reflected in the final optimization result. For example, if a certain area has particularly high requirements for safety distance, the ω value of the corresponding constraint condition will be larger.

[0117] In an alternative approach, in the step S4, the multi-objective optimization of the digital twin model by the particle swarm optimization algorithm further includes:

[0118] Generate a demand assessment model based on urban population density, traffic flow, aircraft takeoff and landing requirements, OD travel demand, and regional service demand;

[0119] Perform multi-objective optimization on the candidate location positions in the digital twin model according to the demand assessment model, the environmental constraint conditions, and the safety constraint conditions, and generate an optional takeoff and landing platform location selection plan that meets the demand assessment model, the environmental constraint conditions, and the safety constraint conditions.

[0120] In this embodiment, traditional location selection methods only consider a single factor (such as geographical location), while this application considers multiple dimensions such as urban population density, traffic flow, aircraft takeoff and landing requirements, travel demand, and regional service demand at the same time, making the location selection plan more scientific and reasonable. The introduction of environmental constraint conditions and safety constraint conditions ensures the reliability of the location selection plan and reduces potential risks. It can be adjusted according to different urban characteristics and demands and applied to different types of cities and scenarios.

[0121] In an alternative approach, the generating a demand assessment model based on urban population density, traffic flow, aircraft takeoff and landing requirements, OD travel demand, and regional service demand further includes:

[0122] Evaluate the takeoff and landing requirements of high-end communities based on population density and income level data;

[0123] Analyze the demand fluctuations during peak hours in the business district according to the traffic flow prediction model;

[0124] Evaluate the emergency service demand around hospitals based on historical first aid data;

[0125] Optimize the platform location of the airport transportation hub according to airspace restrictions and traffic demand to maximize service efficiency;

[0126] Optimize the accessibility of the platform near the subway station according to the ground transportation hub data.

[0127] Specifically, using a weighted analysis model based on population density and income level, higher weights are assigned to high-end communities based on data such as regional population and income collected by the data collection module. The site selection is preferably close to these high-demand areas to ensure that the platform can meet the travel needs of high-end communities.

[0128]

[0129] Among them, is the demand weight for high-end communities, P is the population density, I is the income level, and α + β = 1 is satisfied.

[0130] The weights α and β determine the relative influence of population density and income level on the demand of high-end communities, and their values can be determined according to the actual situation of the region or through statistical analysis (such as multiple regression or analytic hierarchy process).

[0131] Through the traffic flow prediction model, using the traffic flow data collected by the traffic monitoring module, the demand fluctuations during peak hours in the business district are identified. The optimization algorithm gives priority to the site selection around the business district to ensure that sufficient takeoff and landing platforms are provided during high-demand hours.

[0132] D CBD = f(Q, H)

[0133] Among them, D CBD is the demand score for the business district, Q is the traffic flow, and H is the demand fluctuation during peak hours.

[0134] H reflects the demand fluctuation situation in the region during peak hours. Using statistical methods such as standard deviation or rate of change to calculate, the volatility of traffic flow data during peak hours is quantified to obtain the index H; a higher value indicates that the travel demand in the region fluctuates violently during peak hours and the demand is unstable. During the site selection optimization process, the H value of the region will be incorporated into the demand assessment model as auxiliary information to guide the dynamic adjustment of the regional service capacity. Regions with higher values usually mean that higher dispatching flexibility and platform carrying capacity are required during peak hours to ensure that travel demands are fully met.

[0135] Based on historical emergency data, the takeoff and landing demands around hospitals are evaluated through an emergency service demand analysis model. Regions around hospitals are preferentially selected for site selection to meet the emergency medical service demands.

[0136] D hospital = γ × A aid

[0137] Among them, D hospital is the demand score around the hospital, A aid is the emergency demand index, and γ is the weight coefficient.

[0138] A aidThe emergency demand index is a comprehensive indicator A obtained by statistically analyzing data such as the number of emergency calls, the volume of emergency department visits, and the frequency of ambulance dispatches, and then through normalization and weighted averaging. aid The higher the value of, the more urgent the demand for emergency resources within the hospital and its surrounding areas. The weight coefficient γ reflects the importance of emergency demand in the overall site selection and is determined based on regional medical resources and historical data.

[0139] Combined with airspace restrictions and traffic demand analysis, optimize the platform location to maximize service efficiency. The platform should be as close as possible to airports and other transportation hubs for convenient transfer.

[0140]

[0141] Among them: D Hub is the demand score of the intercity hub. n is the number of transportation hubs considered (such as airports, subway stations, bus stops, etc.). δi is the weight coefficient of each transportation hub, reflecting the importance or priority of the hub. Pi is the demand intensity in the area where the hub is located, which can usually be measured by indicators such as population density and commercial activity intensity. Ti is the traffic flow, reflecting the traffic flow or commuting volume of the hub, such as the daily passenger flow or transfer frequency.

[0142] Combined with ground transportation hub data, optimize the accessibility of the platform settings. Prioritize areas near subway stations to improve the seamless connection between aircraft and ground transportation.

[0143]

[0144] Among them, D Subway is the demand score near the subway station. D Walking is the walking distance from the takeoff and landing platform to the subway station. T Transfer is the transfer time required from the platform to the subway station. is the traffic flow of the subway line (such as passenger flow). ∈ is the weight coefficient, reflecting the relative importance of the subway station. α, β, Y are the weight coefficients of walking distance, transfer time, and traffic flow.

[0145] By collecting and analyzing origin-destination (OD) travel data within the region, identify the main travel demand paths and key nodes. Combine the OD demand with the demand analysis results of existing key areas such as high-end communities, business districts, hospitals, airports, and subway stations, and screen out the most potential and demanding site selection areas to ensure that the platform layout not only meets the spatial optimization but also effectively covers the actual travel demand.

[0146]

[0147] Among them: D ODis the OD demand score. m is the number of OD pairs considered. λ j is the weight coefficient of the j-th OD pair, reflecting its importance. OD j is the travel demand volume of the j-th OD pair (such as the number of trips, the number of passengers, etc.), and φj is the comprehensive screening factor.

[0148] Comprehensive screening factor formula:

[0149]

[0150] Where: φj is the comprehensive screening factor of the j-th OD pair. Cj is the travel cost of the j-th OD pair, including direct costs such as ticket price, fuel cost, parking cost, etc., and indirect costs such as transfer cost. Tj is the travel time of the j-th OD pair, the total travel time from the starting point to the end point, including waiting, transfer, and flight time. Vj is the time value of the j-th OD pair. Based on the average wage rate and passenger survey data, a suitable k value is determined. Cmax, Tmax, and Vmax are the maximum values of travel cost, travel time, and time value respectively, for normalization. α, β, and γ are the weight coefficients of each screening factor, satisfying α + β + γ = 1.

[0151] In an alternative manner, the environmental constraint conditions further include:

[0152] According to the noise propagation model and environmental monitoring data, dynamically set the noise buffer zone; optimize the visibility of the platform through the visibility calculation model to ensure the safe takeoff and landing of the aircraft;

[0153] Combined with terrain and building data, use spatial analysis tools to set the obstacle avoidance area;

[0154] According to the law and policy database, exclude the site selection points within the no-fly zone;

[0155] According to the flight altitude limit database, automatically exclude the site selection points within the no-fly zone;

[0156] Conduct slope analysis based on the digital elevation model to ensure the physical conditions of the site selection area.

[0157] In this embodiment, use the noise propagation model, combined with the data of urban environmental monitoring stations, to analyze the noise impact range and set the noise buffer zone. The optimization algorithm excludes high-noise areas to ensure that the platform site selection meets the noise standards.

[0158] N buffer = NoiseModel(L, M)

[0159] Where, N buffer is the noise buffer zone, L is the noise source location, and M is the noise propagation parameter.

[0160] Optimize the visibility of the platform through 3D visual analysis tools (such as the field of view calculation model). Ensure that the platform is unobstructed in the urban environment, facilitating users to locate and identify the platform position.

[0161] Combine urban terrain and building height data, and use spatial analysis tools to set obstacle avoidance areas. The optimization algorithm ensures that the selected site area is far from buildings and other obstacles, avoiding potential safety hazards during aircraft takeoff and landing.

[0162] According to the legal and policy database, automatically exclude the selected site points within the no-fly zone. Ensure that the platform is not located within the no-fly zone and complies with local aviation regulations.

[0163]

[0164] Among them, P Optional is the optional platform location, P Total is all the candidate points, and is the point within the no-fly zone.

[0165] According to the urban flight altitude limit database, the optimization algorithm preferentially selects areas with relatively loose flight altitudes. Avoid selecting restricted areas to ensure that the aircraft takes off and lands within the compliance range.

[0166] Use the Digital Elevation Model (DEM) for slope analysis to ensure that the selected site area meets the physical conditions for platform construction. The selected area of the platform should meet the diameter and slope requirements to ensure the safe takeoff and landing of the aircraft.

[0167] In an optional manner, the generation of the optimal candidate takeoff and landing platform site selection scheme set that meets the environmental constraint conditions and safety constraint conditions further includes:

[0168] Combine the demand weights of each region with the environmental constraint conditions, and use a weighted algorithm to score all candidate points to generate a preliminary site selection scheme;

[0169] Use the particle swarm optimization algorithm to evaluate the demand and environmental adaptability of each candidate site selection point, combine the demand weighting with the environmental constraint conditions, search for suitable site selection positions and dynamically adjust the positions of the particles to find the optimal site selection scheme that meets all conditions; among them, impose a penalty weight on the candidate points that do not meet the constraint conditions to avoid selecting inappropriate regions into the final scheme;

[0170] Dynamically adjust the boundary of the search space during the iteration process. Among them, when the site selection point does not meet the constraint conditions, the site selection point is removed from the search space or the feasible domain of the search space is redefined as the area that does not contain the default points, and the candidate platform positions that meet the requirements are screened.

[0171] In this embodiment, the genetic algorithm, through the mechanism of natural selection, is applicable to dealing with complex constraint conditions and can optimize various constraints such as noise buffer zones, flight altitude limits, and no-fly zones. Specifically, the genetic algorithm can simulate the fitness of multiple candidate site selection points and make selections according to environmental conditions (such as noise, no-fly zones, flight altitude, etc.), retaining the site selection areas that meet the conditions, so as to effectively screen out the optimal solution that meets the environmental requirements.

[0172]

[0173] Among them, Fitness is the fitness, ωi is the weight of each constraint condition, and fi(P) is the constraint condition score corresponding to the site selection point P.

[0174] Each fi(P) represents the score of the site selection point P under the i-th constraint condition, such as terrain slope, building height, obstacles, wind speed, noise, safety distance, etc.

[0175] The weight coefficient ω i is used to adjust the contribution of each constraint condition to the overall fitness and is determined based on the importance of each index. The specific value of the weight coefficient can be obtained through expert evaluation, statistical regression, or sensitivity analysis to ensure that each constraint condition is reasonably reflected in the final optimization result. For example, if a certain area has a particularly high flight altitude limit, the ω value of the corresponding constraint condition will be larger.

[0176] Based on the results of demand analysis and environmental constraint analysis, a multi-objective optimization algorithm is applied to generate a set of site selection plans to ensure that the site selection plans achieve the best balance in terms of demand coverage, environmental adaptability, legal compliance, and cost-effectiveness.

[0177] Combine the demand weights of each region (such as high-end communities, business districts, hospitals, airports, etc.) with environmental constraint conditions (such as noise, no-fly zones, visibility, etc.), and use a weighted algorithm to score all candidate points to generate a preliminary site selection plan. The scoring criteria are adjusted according to the priority of the demand and the strictness of the constraint conditions.

[0178]

[0179] Among them, γj is the demand weight, Dj(P) is the demand score, λk is the constraint condition weight, and Ck(P) is the constraint score.

[0180] Demand weight γj:

[0181] is used to adjust the contribution of each demand index (such as high-end communities, business districts, hospitals, airports, etc.). The weights of each index can be determined through expert evaluation, historical data statistics, or normalization processing, satisfying

[0182] Particle Swarm Optimization (PSO) conducts global search in multi-dimensional space by simulating the flight process of "particles" and can quickly converge to the optimal solution. In the generation of site selection plans, the PSO algorithm combines demand weighting and environmental constraints by evaluating the demand and environmental adaptability of each candidate site, and searches for suitable site locations. PSO can effectively handle optimization problems with multiple objectives and constraints, and dynamically adjust the positions of particles to find the optimal site selection plan that meets all conditions.

[0183]

[0184] Among them, is the velocity of particle i at iteration k, is the position of particle i, pi is the individual best position of particle i, g is the global best position, w is the inertia weight, c1 and c2 are acceleration constants, and r1 and r2 are random numbers.

[0185] Apply penalty weights to candidate points that do not meet the constraint conditions (such as noise exceeding the standard, being located in a no-fly zone, and flight altitude not meeting the regulations, etc.). During the optimization process, the fitness values of these candidate points will decrease, so these non-compliant site selection areas can be preferentially excluded during the search process. By gradually increasing the penalty value, the algorithm is prevented from selecting inappropriate areas into the final plan.

[0186]

[0187] During the iterative process of the algorithm, dynamically adjust the boundaries of the search space. When a site selection point does not meet a certain constraint condition (for example, being located within the three-dimensional noise buffer zone), this point will be removed from the search space, or the feasible region of the search space will be redefined as the region that does not contain the default point. In this way, the optimization algorithm can automatically adjust the positions of candidate points and avoid repeatedly evaluating the excluded invalid regions.

[0188] Based on the scoring results and environmental restrictions, a batch of candidate platform positions that meet the requirements are screened out. These candidate platforms should have high demand adaptability and be able to meet all environmental and physical constraint requirements.

[0189] P canndidate ={P∈P optional |Score(P)>θ}.

[0190] In an alternative manner, the method further includes evaluating the candidate platform positions, specifically including:

[0191] Evaluate the demand coverage of each candidate platform and calculate its coverage ratio for high-demand areas;

[0192] Evaluate the adaptability of the site selection plan in terms of noise, flight altitude, field of view, and obstacle avoidance through simulation analysis;

[0193] Combined with the no-fly zones and flight altitude restrictions in the city, conduct a legal compliance assessment of the site selection plan;

[0194] Evaluate the economic benefits of the candidate platform locations based on the construction costs, maintenance costs, and expected usage revenues in the selected areas.

[0195] In this embodiment, evaluate the demand coverage of each candidate platform, calculate its coverage ratio for high-demand areas (such as high-end communities, business districts, hospitals, etc.), and ensure that the platform site selection can effectively cover the main demand areas.

[0196]

[0197] Among them, C covering (P) is the coverage of platform P, φj is the coverage weight of high-demand area j, and δj(P) is the coverage ratio of platform P to area j.

[0198] Through simulation analysis, evaluate the adaptability of the site selection plan in aspects such as noise, flight altitude, field of view, and obstacle avoidance. Ensure that the construction of the platform does not violate environmental protection requirements and can ensure the safe takeoff and landing of the aircraft in actual operation.

[0199]

[0200] Among them, A Adapt (P) is the environmental adaptability score of platform P, ψk is the weight of the environmental adaptability factor, ηk(P) is the score of platform P on environmental adaptability factor k, k is the index of the environmental adaptability factor (starting from 1), and l is the total number of environmental adaptability factors.

[0201] ψk represents the relative importance of the kth environmental adaptability factor in evaluating the environmental adaptability of the platform. These weights are usually determined through expert judgment, historical data analysis, or sensitivity testing, and are normalized to ensure that the contribution of each environmental factor to the final score can reflect its actual impact.

[0202] Combined with the no-fly zones and flight altitude restrictions in the city, conduct a legal compliance assessment of the site selection plan. Ensure that all selected areas comply with the laws and regulations of the local aviation administration department and do not involve any no-fly areas.

[0203]

[0204] Among them, L Compliance (P) is the legal compliance score of platform P, H(P) is the flight altitude of platform P, and H limit is the flight altitude restriction, It is a no-fly zone.

[0205] Evaluate the economic benefits of the site selection plan based on the construction cost, maintenance cost, and expected usage benefits of the selected area. Ensure that the site selection plan has a reasonable input-output ratio and can achieve economic sustainability.

[0206]

[0207] Among them, C benefit (P) is the cost-benefit score of platform P, R(P) is the expected revenue of platform P, and C total (P) is the total cost of platform P.

[0208] C Synthesize (P)=α1×C cover (P)+α2×A fitness (P)+α3×L compliance (P)+α4

[0209] ×C bene几t (P)

[0210] Among them, α1 + α2 + α3 + α4 = 1, which is used to balance the contributions of demand coverage, environmental adaptability, legal compliance, and cost-benefit in the final score.

[0211] In an alternative approach, the method further includes:

[0212] Perform a weighted calculation on the evaluation results of demand coverage, environmental adaptability, legal compliance, and cost-benefit to obtain a comprehensive score.

[0213] Rank all the site selection plans according to the level of the comprehensive score to determine the best site selection plan for the low-altitude aircraft takeoff and landing platform.

[0214] In an alternative approach, the method further includes:

[0215] Visually present the best site selection plan for the low-altitude aircraft takeoff and landing platform in the digital twin model and generate a site selection report including the selected location, evaluation results, and constraint conditions.

[0216] In this embodiment, the demand weights of each area (such as high-end communities, business districts, hospitals, airports, etc.) are combined with the environmental constraint conditions (such as noise, no-fly zones, visibility, etc.), and all candidate points are scored using a weighted algorithm to generate a preliminary site selection plan. The scoring criteria are adjusted according to the priority of the demand and the strictness of the constraint conditions.

[0217]

[0218] Among them, γj is the demand weight, Dj(P) is the demand score, λk is the constraint weight, and Ck(P) is the constraint score.

[0219] Step S5: Dynamically update the digital twin model according to real-time data feedback, and dynamically adjust the siting scheme of the takeoff and landing platform.

[0220] In this embodiment, as Figure 6 shown, obtain the latest data in real time from traffic monitoring, weather stations, environmental monitoring equipment, etc., and use efficient data acquisition protocols (such as MQTT, WebSocket) to obtain data to ensure the timeliness of the data. Update and optimize the input parameters in the model according to the real-time data, and use a data-driven method to dynamically adjust the weights and parameters in the algorithm model to ensure real-time performance and adaptability.

[0221] According to the feedback real-time data, the optimization algorithm recalculates and adjusts the siting scheme. Combining incremental calculation and local adjustment strategies, the optimization process can respond to environmental changes in real time. Continuously monitor the effect of the adjusted siting scheme. By comparing the simulation results with the actual effects, use performance evaluation indicators (such as return on investment, quality of service, operating cost) to verify the effectiveness of the scheme, and ensure the stability and continuous optimization ability of the system in actual applications. Performance indicators = {return on investment, quality of service, operating cost}, where each performance indicator is used to evaluate the effectiveness and optimization effect of the siting scheme.

[0222] The solution provided by the present invention includes: Step S1, obtaining real-time dynamic data and static GIS data including urban traffic flow data, meteorological data, topographic and geomorphic data, environmental data, and POI data; Step S2, constructing a three-dimensional digital model of the city according to the static GIS data, and constructing a digital twin model according to the three-dimensional digital model and the real-time dynamic data; Step S3, constructing environmental constraint conditions and safety constraint conditions for the candidate takeoff and landing platform positions in the digital twin model; among them, the environmental constraint conditions include terrain slope, building height, obstacle distribution, wind direction and wind speed, and noise impact; the safety constraint conditions include safety distance, route planning, and alternate landing points in case of emergency; Step S4, performing multi-objective optimization on the digital twin model through a particle swarm optimization algorithm to generate an optimal candidate takeoff and landing platform siting scheme set that meets the environmental constraint conditions and safety constraint conditions; Step S5, dynamically updating the digital twin model according to real-time data feedback, and dynamically adjusting the siting scheme of the takeoff and landing platform. The present invention constructs a virtual city model through a digital twin, provides an accurate simulation environment and real-time feedback for siting optimization, and improves the accuracy and feasibility of the siting scheme.

[0223] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and set in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise explicitly stated, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose. In addition, those skilled in the art can understand that although some of the embodiments herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices can be embodied by the same hardware item. The steps in the above embodiments, unless otherwise specified, should not be construed as a limitation on the execution order.

Claims

1. A method for optimizing the site selection of a low-altitude aircraft take-off and landing platform, characterized in that: include: Step S1, obtaining real-time dynamic data and static GIS data including urban traffic flow data, meteorological data, topographic data, environmental data, and POI data; Step S2, constructing a three-dimensional digital model of the city according to the static GIS data, and constructing a digital twin model according to the three-dimensional digital model and the real-time dynamic data; Step S3, constructing environmental constraints and safety constraints of the candidate take-off and landing platform locations in the digital twin model; wherein the environmental constraints include terrain slope, building height, obstacle distribution, wind direction and speed, and noise impact; the safety constraints include safety distance, route planning, and alternate landing points in emergency situations; Step S4, performing multi-objective optimization on the digital twin model by using a particle swarm optimization algorithm to generate a set of optimal candidate landing and take-off platform site selection solutions that meet the environmental constraints and safety constraints; Step S5: dynamically update the digital twin model according to real-time data feedback, and dynamically adjust the site selection plan of the take-off and landing platform.

2. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 1, characterized in that: In step S1: Collect road traffic flow and public transportation station data in real time from the urban traffic monitoring system; Collect temperature, humidity, wind speed and direction weather data in real time from weather stations or online weather services; Obtain information on urban topography, building distribution and land use types from the GIS database, and perform 3D modeling to obtain 3D spatial information data of the city; Collect noise and air quality environmental data in real time from environmental monitoring sites; Get POI data including hospitals, schools, commercial areas, and transportation stations in the city from public data sources or third-party services.

3. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 1, characterized in that: In step S2, constructing a three-dimensional digital model of the city based on the static GIS data further includes: Construct a basic three-dimensional model of the city based on the static GIS data, and access the real-time dynamic data in real time through the API interface; The real-time dynamic data is mapped into the three-dimensional digital model of the city, and the parameters of the three-dimensional digital model of the city are updated in real time to reflect the dynamic changes of the urban environment.

4. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 1, characterized in that: In step S4, the multi-objective optimization of the digital twin model by using a particle swarm optimization algorithm further includes: Generate a demand assessment model based on urban population density, traffic flow, aircraft take-off and landing demand, OD travel demand, and regional service demand; According to the demand assessment model and the environmental constraints and safety constraints, multi-objective optimization is performed on the candidate site selection locations in the digital twin model to generate an optional take-off and landing platform site selection plan that meets the demand assessment model, the environmental constraints and safety constraints.

5. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 4, characterized in that: The demand assessment model generated according to urban population density, traffic flow, aircraft take-off and landing demand, OD travel demand and regional service demand further includes: Assessing takeoff and landing demand in high-end communities based on population density and income level data; Analyze demand fluctuations during peak hours in business districts based on traffic flow forecasting models; Assess the demand for emergency services around hospitals based on historical emergency data; Optimize platform locations at airport transportation hubs based on airspace restrictions and traffic demand to maximize service efficiency; Optimize accessibility of platforms near subway stations based on ground transportation hub data.

6. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 4, characterized in that: The environmental constraints further include: Dynamically set noise buffer zones based on noise propagation models and environmental monitoring data; optimize platform visibility through viewshed calculation models to ensure safe takeoff and landing of aircraft; Combine terrain and building data to set obstacle avoidance areas using spatial analysis tools; Eliminate site selection within no-fly zones based on legal and policy databases; Automatically exclude site selection points within no-fly zones based on the flight altitude restriction database; Slope analysis is performed based on the digital elevation model to ensure the physical conditions of the site selection area.

7. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 1, characterized in that: The generating of the optimal candidate landing and take-off platform site selection scheme set that meets the environmental constraints and safety constraints further includes: Combine the demand weights of each region with the environmental constraints, use a weighted algorithm to score all candidate points, and generate a preliminary site selection plan; The particle swarm optimization algorithm is used to evaluate the demand and environmental adaptability of each candidate site, combine the demand weighting with the environmental constraints, search for suitable site locations and dynamically adjust the positions of particles to find the optimal site solution that meets all conditions; among them, penalty weights are imposed on candidate points that do not meet the constraints to avoid selecting inappropriate areas into the final solution; The boundaries of the search space are dynamically adjusted during the iteration process. When a site selection point does not meet the constraints, the site selection point is removed from the search space or the feasible domain of the search space is redefined as an area that does not contain the default point, thereby screening candidate platform locations that meet the requirements.

8. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 7, characterized in that: The method further includes evaluating the candidate platform position, specifically including: Evaluate the demand coverage of each candidate platform and calculate its coverage ratio of high-demand areas; Evaluate the adaptability of the site selection scheme in terms of noise, flight altitude, field of view, and obstacle avoidance through simulation analysis; Conduct legal compliance assessments on site selection options in light of the city’s no-fly zones and flight altitude restrictions; Evaluate the economic benefits of candidate platform locations based on the construction cost, maintenance cost and expected usage benefits of the site selection area.

9. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 8, characterized in that: The method further comprises: The evaluation results of demand coverage, environmental adaptability, legal compliance, and cost-effectiveness are weighted to obtain a comprehensive score; All site selection options are ranked according to the comprehensive scores to determine the best site selection option for the low-altitude aircraft take-off and landing platform.

10. The method for optimizing the site selection of a low altitude aircraft take-off and landing platform according to claim 9, characterized in that: The method further comprises: The optimal low-altitude aircraft take-off and landing platform site selection plan is visualized in the digital twin model, and a site selection report including the site location, evaluation results and constraints is generated.

Images