Low-altitude safety facility layout method based on voxelized risk field and facility capacity

Abstract

This invention discloses a method for low-altitude safety facility layout based on voxelized risk field and facility capabilities. The method includes: constructing a three-dimensional voxel space corresponding to the study area; semantically labeling each voxel unit in the three-dimensional voxel space and determining the voxel index corresponding to the candidate low-altitude safety facility installation points; fusing multi-source risk factors to quantify the safety risk of each voxel unit in the three-dimensional voxel space and constructing a voxelized low-altitude risk field covering the study area; determining occlusion entities based on the semantic attribute labeling of voxel units; calculating the coverage intensity after deploying different types of low-altitude safety facilities at each candidate low-altitude safety facility installation point using a ray tracing algorithm; generating a perception-defense capability matrix; constructing a multi-objective optimization model for low-altitude safety infrastructure layout based on the voxelized low-altitude risk field and the perception-defense capability matrix; and solving the multi-objective optimization model using a multi-objective evolutionary algorithm to obtain the optimal facility deployment scheme set.

Description

Technical Field

[0001] This invention belongs to the field of low-altitude safety technology and relates to a method for optimizing the layout of low-altitude safety facilities based on voxelized risk field and facility capability modeling. Background Technology

[0002] With the rapid development of the low-altitude economy and the continuous expansion of low-altitude airspace openness, the urban low-altitude environment exhibits significant altitude stratification and three-dimensional interweaving characteristics. Low-altitude activities show differentiated spatial distribution and operational patterns at different altitude levels. At the same time, low-altitude security threats are becoming increasingly complex and diversified. "Low, slow, and small" targets such as unauthorized drone flights and illegally intruding airborne objects pose serious challenges to the security of key protection areas, civil aviation airports, and urban core areas. As a crucial support for ensuring the safe operation of low-altitude airspace, the scientific layout and optimized allocation of low-altitude security infrastructure have become an important prerequisite for the high-quality development of the low-altitude economy.

[0003] However, current planning and deployment of low-altitude safety facilities still largely rely on traditional, static layout methods based on two-dimensional planar projection or empirical point placement. This simplifies the complex urban low-altitude environment into a flat map for analysis, failing to characterize the differences in risk levels and facility coverage capabilities at different altitudes and spatial locations. Existing empirical point placement methods lack quantitative spatial coverage assessment tools, leading to a mismatch between facility deployment density and risk distribution, potentially resulting in insufficient coverage in high-risk areas or over-construction in low-risk areas. Furthermore, most studies focus on simple superposition of single risk indicators, failing to fully consider the systematic integration of multi-dimensional risk factors such as airspace restriction levels, terrain constraints, and regulations and policies, making it difficult to accurately assess the spatial heterogeneity of low-altitude safety risks in three-dimensional space. In addition, existing research often optimizes the deployment of sensing and defense facilities as independent problems, easily leading to misalignment between sensing and defense blind spots, and failing to form a closed-loop capability of detection-tracking-response.

[0004] Therefore, this invention aims to construct a method for optimizing the layout of low-altitude security facilities based on three-dimensional voxel space modeling, multi-source risk factor fusion, low-altitude security facility capability calculation, and multi-objective optimization algorithms. This method is designed for real three-dimensional low-altitude environments, promotes collaborative perception and defense, and balances multiple objectives. It can not only effectively guide the refined three-dimensional deployment of urban low-altitude security systems, resolve potential conflicts arising from misaligned perception and defense blind spots, and optimize spatial layout, but also provide crucial scientific basis and decision support for promoting the sustainable development of low-altitude economic security. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method for optimizing the layout of low-altitude safety facilities based on voxelized risk field and facility capability modeling.

[0006] The objective of this invention is achieved through the following technical solution: A method for optimizing the layout of low-altitude safety facilities based on voxelized risk field and facility capability modeling includes: S1. Construct a three-dimensional voxel space corresponding to the study area, perform semantic attribute annotation on each voxel unit in the three-dimensional voxel space, and determine the voxel index corresponding to the candidate low-altitude safety facility installation point. S2. Integrate multi-source risk factors, quantify the safety risk of each voxel unit in the three-dimensional voxel space, and construct a voxelized low-altitude risk field covering the study area. S3. Based on the semantic attribute annotation of the voxel unit, determine the occlusion entity, calculate the coverage intensity of each candidate low-altitude security facility installation point after deploying different types of low-altitude security facilities using the ray tracing algorithm, and generate a perception-defense capability matrix. S4. Based on the voxelized low-altitude risk field and the perception-defense capability matrix, and with the facility deployment scheme as the decision variable, construct a multi-objective optimization model for the layout of low-altitude safety infrastructure, which includes the optimization objectives of maximizing perception risk coverage, maximizing defense risk coverage, minimizing total life-cycle cost, and maximizing perception-defense collaborative coverage. S5. Use a multi-objective evolutionary algorithm to solve the multi-objective optimization model and obtain the optimal facility deployment scheme set.

[0007] Furthermore, in step S1, semantic attribute annotation is performed on each voxel unit, specifically including: using the 3D model and surface data in the study area, defining a voxel type indicator function, dividing the voxel unit into a set containing free voxels and multiple types of occluded entity voxels, wherein the voxel units marked as occluded entity voxels constitute the occluded entity voxel set in the ray tracing algorithm; the surface data includes terrain elevation model and surface cover data.

[0008] Furthermore, in step S2, a voxelized low-altitude risk field is constructed by fusing multi-source risk factors. Specifically, this includes: collecting data on key protection targets, airspace restricted areas, and the spatial distribution data of historical safety events; calculating the key protection target factor, airspace restriction level factor, and historical event density factor for each voxel unit; and linearly weighting and superimposing the above three types of factors to obtain the risk value corresponding to the voxel unit, thereby constructing the voxelized low-altitude risk field.

[0009] Furthermore, the key protection target factor for each voxel unit is calculated using a Gaussian decay function; The calculation of the spatial restriction level factor for each voxel unit specifically includes: calculating the spatial intersection volume ratio between the voxel unit and the spatial restriction region; using the spatial intersection volume ratio as a weight, combined with the restriction level corresponding to the spatial restriction region, to calculate the spatial restriction level factor, wherein for a voxel unit located at the overlap of multiple spatial restriction regions, the highest restriction level among all spatial restriction regions covering the voxel unit is taken. The calculation of the historical event density factor includes: using the three-dimensional kernel density estimation method to calculate the historical event density distribution function in three-dimensional space, substituting the center coordinates of each voxel unit into the above historical event density distribution function to obtain the corresponding historical event density factor.

[0010] Furthermore, in step S3, the coverage intensity is calculated using a ray tracing algorithm to generate a perception-defense capability matrix. Specifically, this includes: generating ray clusters for each type of facility based on its effective pitch and azimuth ranges; traversing the set of voxels of the obstructing entities and calculating the shortest intersection distance between each ray in the ray cluster and the voxel of the obstructing entity to determine the line-of-sight relationship between the installation point of the candidate low-altitude safety facility and each voxel unit; based on the line-of-sight relationship determination result, selecting the corresponding physical propagation model according to the facility type to calculate the coverage intensity of the voxel unit, and summarizing all calculation results to generate the perception-defense capability matrix.

[0011] Furthermore, the physical propagation model includes: for electromagnetic sensing facilities, the signal-to-noise ratio at the voxel unit location is calculated using radar equations as the coverage strength; for photoelectric sensing facilities, the imaging signal-to-noise ratio at the voxel unit location is calculated using an illumination propagation model as the coverage strength; and for defensive facilities, the defensive effectiveness at the voxel unit location is calculated using a piecewise nonlinear attenuation model as the coverage strength.

[0012] Furthermore, the multi-objective optimization model for the layout of low-altitude safety infrastructure described in step S4 also includes constraints, which include: Total budget constraint: The total lifecycle cost of the facility deployment plan shall not exceed the preset budget limit; Single-point mutual exclusion constraint: Each candidate low-altitude safety facility installation site may deploy at most one type of facility; Coverage redundancy constraints: For critical risk voxel sets whose risk values ​​exceed a preset threshold and are located within key coverage areas, the minimum facility coverage quantity requirement must be met; for sensing facilities, the critical risk voxel set is defined as the set of voxels whose risk values ​​exceed a preset threshold and are located within key coverage areas, with the preset threshold being the upper quartile of the risk field after normalization; for defense facilities, the critical risk voxel set is defined as the set of voxels whose risk values ​​exceed a preset threshold and are located in areas with high-density clustering of historical events, with the preset threshold being the upper quartile of the kernel density estimation result; In step S5, a multi-objective evolutionary algorithm based on reference points is used to solve the multi-objective optimization model for the layout of low-altitude safety infrastructure. The iteration is terminated when the set maximum number of iterations is reached or the optimal objective function value is not improved after a certain number of iterations, and a Pareto optimal layout scheme set is obtained. The most satisfactory facility deployment scheme is selected from the Pareto optimal layout scheme set according to actual needs.

[0013] This invention also provides a low-altitude safety facility layout optimization device based on voxelized risk field and facility capability modeling, comprising: A three-dimensional voxel space construction unit is used to construct a three-dimensional voxel space corresponding to the study area. Semantic attributes are labeled for each voxel unit in the three-dimensional voxel space, and the voxel index corresponding to the candidate low-altitude safety facility installation point is determined. A voxelized low-altitude risk field construction unit is used to fuse multi-source risk factors, quantify the safety risk of each voxel unit in the three-dimensional voxel space, and construct a voxelized low-altitude risk field covering the study area. The perception-defense capability matrix generation unit is used to determine the occlusion entity based on the semantic attribute annotation of the voxel unit, calculate the coverage intensity after deploying different types of low-altitude security facilities at each candidate low-altitude security facility installation point using a ray tracing algorithm, and generate the perception-defense capability matrix. The multi-objective optimization model construction unit is used to construct a multi-objective optimization model for low-altitude safety infrastructure layout based on the voxelized low-altitude risk field and the perception-defense capability matrix, with facility deployment scheme as the decision variable. The model includes the optimization objectives of maximizing perception risk coverage, maximizing defense risk coverage, minimizing total life cycle cost, and maximizing perception-defense collaborative coverage. The solution unit is used to solve the multi-objective optimization model using a multi-objective evolutionary algorithm to obtain the optimal facility deployment scheme set.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the low-altitude safety facility layout optimization method.

[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the low-altitude safety facility layout optimization method described above.

[0016] Compared with the prior art, the beneficial effects of the technical solution of the present invention are: 1. By employing the technical feature of "constructing a three-dimensional voxel space and using a three-dimensional model to define voxel type indicator functions to annotate semantic attributes," the highly layered low-altitude environment is uniformly divided into three-dimensional meshes and its coordinates transformed, thus providing a basis for consistently assessing risks and occlusion in three-dimensional space. This solves the problems of spatial dimension loss, unstable results, and difficulty in reproduction caused by existing technologies relying on two-dimensional planar projection or empirical point placement, achieving accurate quantification of three-dimensional space and rapid cross-regional reproduction.

[0017] 2. Based on the three-dimensional voxel space, a voxelized low-altitude risk field is constructed by integrating key protection target factors, airspace restriction level factors, and historical event density factors. This field accurately depicts the risk differences at different altitudes and spatial locations through multi-source data fusion. By introducing the spatial intersection volume ratio between voxel units and airspace restriction areas as a weight, the risk quantification error caused by the traditional binary judgment of "either inside or outside" is avoided, achieving a smooth and accurate transition of the restriction level of boundary voxel units. This makes the identification of high-risk areas more accurate and the deployment of facilities more targeted.

[0018] 3. A combined weighting method was adopted to determine the target value weights, which integrates objective data such as the resident population density and economic asset density of the target area with expert experience. This makes the quantification of the risk contribution of key protection targets both objective and reproducible, avoiding the weight bias and cross-regional non-reproducibility issues caused by purely subjective scoring.

[0019] 4. Based on the ray tracing algorithm, the intersection distance between the ray and the voxel of the obstructing entity is accurately calculated. After determining the visibility, the coverage intensity of various facilities is calculated using the radar equation, the light propagation model, and the piecewise nonlinear attenuation model. This objectively and realistically reflects the actual blocking effect and attenuation law of ground objects such as buildings, vegetation, and bridges on the detection and defense rays, making the coverage assessment results close to the real physical environment and effectively avoiding significant deviations between the theoretical coverage range and the actual reachability of the planning scheme.

[0020] 5. Due to the adoption of the Amanatides-Woo algorithm to adapt to cuboid meshes and differentiate the angular resolution of ray clusters, the coverage intensity is calculated using radar equations, illumination propagation models, and piecewise nonlinear attenuation models after determining visibility. This technical feature enables ray tracing to directly support non-cubic voxel spaces with differentiated horizontal and vertical resolutions, thus balancing the need for high-precision modeling in the vertical direction with overall computational efficiency, and effectively avoiding significant deviations between the theoretical coverage of the planning scheme and its actual achievable capability.

[0021] 6. Construct a multi-objective optimization model with the optimization objectives of maximizing the coverage of perceived risks, maximizing the coverage of defensive risks, minimizing the total cost throughout the life cycle, and maximizing the coverage of perception-defense collaboration, and with constraints such as budget constraints, single-point mutual exclusion constraints, and redundancy coverage constraints in key areas. This expands the traditional single-objective model into a four-dimensional multi-objective framework, forcing the multi-objective optimization algorithm to consider the closed loop of detection capability, response capability, and budget ceiling when selecting solutions. This results in a Pareto optimal solution that meets the needs of actual combat, resolving the misalignment between perception blind spots and defense blind spots. The optimization results can achieve a balance between coverage effectiveness, economic input, and system reliability, which is more in line with the actual decision-making needs of engineering.

[0022] 7. The entire process is based on a unified three-dimensional voxel space framework. From spatial modeling, risk quantification, capacity calculation to optimization solution, the spatial indexes, calculation rules and parameter specifications of each step are strictly corresponding. Key parameters such as voxel resolution, risk weight, facility performance parameters and constraint thresholds are explicitly defined, which facilitates model adjustment and engineering application in different research areas and scenarios. Attached Figure Description

[0023] Figure 1 This is a flowchart of the low-altitude safety facility layout optimization method based on voxelized risk field and facility capability modeling of the present invention.

[0024] Figure 2 This is a voxelized three-dimensional spatial schematic diagram of the present invention.

[0025] Figure 3 This is a schematic diagram of the three-dimensional coverage of the facility based on ray tracing according to the present invention. Detailed Implementation

[0026] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention.

[0027] Example 1 This embodiment provides a method for optimizing the layout of low-altitude safety facilities based on voxelized risk field and facility capability modeling. (See...) Figure 1 Specifically, it includes the following steps: S1. Taking the core business district of a certain city as an example, the research area... The study area is defined as a three-dimensional space of 2km × 2km × 200m. The corresponding three-dimensional voxel space Semantic attribute annotation is performed on each voxel unit to determine candidate installation sites for low-altitude safety facilities. Corresponding voxel index; S101, 3D voxel mesh construction, see Figure 2Specifically, based on the study area spatial range and preset voxel resolution ,along The space is divided equally in three directions to form A regular voxel unit, denoted as subscript These correspond to voxel indices in three directions, respectively. , , ,symbol This indicates rounding up. The study area in this embodiment... The spatial range is Preset voxel resolution , in meters.

[0028] Each voxel unit The center coordinates are determined by the following formula: ; in, , , Voxel resolution The value of is determined comprehensively based on the scale of the study area, the complexity of the terrain, and the required computational accuracy. In the horizontal direction, and They are usually taken to have the same value; in the vertical direction, Different settings can be made based on the altitude stratification characteristics of low-altitude activities; Specifically, in engineering applications, The recommended value range is 5~50m. For densely built-up areas, complex terrain, or key protected areas, 5~10m is preferable to ensure accuracy; for open and flat areas, the range can be relaxed to 30~50m to reduce computational load. Vertical resolution The recommended value range is 2~20m, and in the dense layer of drone logistics routes of 60~120m, it should be refined to 2~5m.

[0029] S102. Semantic attribute annotation of voxel units. After constructing the 3D voxel mesh, using the 3D building model, terrain elevation model, and land cover data of the study area, semantic attribute annotation is performed on each voxel unit. Perform semantic attribute annotation and define voxel type indicator functions. ,in This indicates that the voxel unit is an empty voxel and does not contain occluding entities. ( This indicates that the voxel unit belongs to the first... Occlusion-like entities, This represents the total number of entity types that are occluded. Specific categories include, but are not limited to: For housing construction, For trees and vegetation, For bridge structure, This includes terrain and surface features. Voxel units marked as non-zero are collectively referred to as occlusion entity voxels, forming the occlusion entity voxel set in the S3 step ray tracing algorithm. : ; S103. Determination of the voxel element to which the candidate low-altitude safety facility installation sites belong. Candidate low-altitude safety facility installation sites The three-dimensional spatial coordinates are , , This represents the total number of candidate low-altitude safety facility installation sites. The voxel unit to which it belongs is denoted as... voxel index The calculation is as follows: ; ; ; Candidate installation sites for low-altitude safety facilities are typically building rooftops with excellent visibility, locations of existing municipal facilities such as communication towers, surveillance poles, and streetlights, as well as planned locations for dedicated security poles. This embodiment extracts a total of candidate installation sites, including building rooftops, communication towers, and streetlights, within the study area. indivual.

[0030] S2. Construction of a voxelized low-altitude risk field based on multi-source risk factors. This involves constructing a three-dimensional voxel space in S1. Based on this, key protection target factors are integrated. Airspace restriction level factor and historical event density factor Three types of risk factors are used to quantitatively assess the low-altitude safety risk of each voxel unit, ultimately constructing a voxelized low-altitude risk field covering the study area. ; S201. Multi-source risk factor data collection. This includes data on the location of key protected targets, airspace restricted areas, and the spatial distribution of historical security incidents. The parameters for each data type are as follows: Key protection target data parameters. This includes the spatial coordinates of each target and its value weight. and protection radius .in, , The total number of key protection targets. Reflecting the importance of this target for low-altitude safety protection, it is a dimensionless normalized parameter with a value range of [value range missing]. ; Defined as the radius of the space centered on the target that requires safety protection, in meters.

[0031] Airspace restricted area data parameters. This includes the spatial boundary polygons of each restricted area and their corresponding restriction levels. Each airspace restricted area Defined as a vertical prism in three-dimensional space with a horizontally projected polygon as its base and a height range as its edge height. , This represents the total number of spatially restricted regions. The horizontally projected polygons are composed of... Ordered vertices Define, where each vertex For horizontal coordinates, The height range is Restriction Level This is a dimensionless parameter reflecting the constraint strength of this airspace on the deployment and operation of low-altitude safety facilities; a larger value indicates stricter restrictions. (One voxel unit) center lie in Within the horizontal projection of point, if and only if point Located inside the aforementioned horizontally projected polygon, and .

[0032] Spatial distribution data parameters of historical security incidents, including the three-dimensional spatial coordinates of each historical security incident. Information such as event type and timestamp, among which , This represents the total number of historical security incidents.

[0033] S202, Key Protection Target Factor Calculation. A voxel element is defined as having a higher security risk value the closer it is to a critical protected target; this risk contribution decreases with increasing distance. For voxel elements... Its key protection target factor Calculations were performed using the Gaussian decay function, taking into account the spatial distribution and attribute parameters of all key protected targets: ; in, Let be the distance attenuation coefficient, a dimensionless positive parameter that controls the rate attenuation of risk with distance. A higher value indicates a faster rate of risk decay. voxel unit center coordinates To the The three-dimensional Euclidean distance of each key protected target, i.e. Target value weight The combined weighting method is used to determine the weighting. , This is the subjective preference coefficient, with a default value of 0.5. Subjective weight. Based on expert scoring and normalization, the following weightings are assigned: 0.9-1.0 for top-tier protection targets such as administrative centers and nuclear power plants; 0.6-0.8 for first-tier targets such as transportation hubs and substations; and 0.3-0.5 for second-tier targets such as commercial complexes and schools. (Objective weighting) Based on the normalization of data such as the resident population density and economic asset density of the target area of ​​key protection targets, the entropy weight method is used to calculate the data. For specific calculations, please refer to CN202610545614.0.

[0034] S203, Airspace Restriction Level Factor Calculation. The airspace restriction level factor characterizes the degree to which a voxel's location is constrained by airspace management policies. Voxel units located within strictly restricted airspace, because this area typically corresponds to key control areas such as airport clear zones and low-altitude airspace for major events, experience a correspondingly higher severity of potential security threats and security requirements, thus increasing their risk level factor value. To accurately handle voxels located at the boundaries of restricted airspace areas, the spatial intersection volume ratio between the voxel and the restricted airspace area is introduced. Definition of voxel unit. airspace restricted areas The ratio of the spatially intersecting volumes is: ; in, voxel unit The volume of the intersection. Estimated through Monte Carlo sampling, in each voxel Random sampling is performed according to a three-dimensional independent uniform distribution. =300~500 points, the sampling points emit rays in their horizontal plane, and the interaction between the rays and... within The number of intersection points of each side of the horizontally projected polygon is used. If the number of intersection points is odd, the sampling point is determined to be inside; if the number of intersection points is even, the sampling point is determined to be outside. The points falling into the polygon are counted. Number of sampling points within Then the ratio of intersecting volumes is estimated as follows: For those completely located Internal voxels, For those who are completely in External voxels, For boundary voxels, .

[0035] For a voxel located in an area where multiple airspace restriction zones overlap, take the highest level among all airspace restriction zones covering that voxel. Values ​​are assigned based on the stringency of regulations: 1.0 for the airport core airspace, 0.9-1.0 for temporary no-fly zones during major events, 0.5-0.8 for height-restricted zones, and 0.1-0.3 for general surveillance zones. The intersection volume ratio is used as the weighting factor for the airspace restriction level. The calculation formula is: ; S204, Historical Event Density Factor The historical event density factor is calculated based on the statistical regularity of the three-dimensional spatial distribution of historical security events, characterizing the historical security risk level of each voxel location. This factor uses the three-dimensional kernel density estimation method to calculate the density distribution of historical events in three-dimensional space. : ; in, It is a three-dimensional kernel function, using a three-dimensional Gaussian kernel function; They are respectively The bandwidth parameters in three directions are used to control the smoothness of the density estimation. When the event distribution is sparse, the following parameters are used: When the event distribution is dense, take ; For the first The three-dimensional spatial coordinates of a historical security event.

[0036] voxels Substituting the center coordinates into the density function above, the historical event density factor of the voxel can be obtained. : ; S205. Construct a low-altitude voxel-based risk field. Linearly weighted superposition of the three types of risk factors mentioned above is used to construct a voxel-based low-altitude risk field covering the study area. : ; in, For the first The weighting coefficients of risk factors satisfy the following conditions: and The weight configuration can take the following values: Political Core Area , , Transportation hub area , , General urban areas , , .

[0037] S3. Quantify the coverage of sensing and defense capabilities that can be provided by deploying sensing and defense-type low-altitude safety facilities at each candidate installation site. Using a ray tracing algorithm, calculate the occlusion effect based on the voxel set of occluding entities to generate a sensing-defense capability matrix. This is applied to a study area of ​​1–4 km. 2 For medium-scale scenes with voxel resolution of 5~10m, the hardware and software environment required for algorithm execution is: a 64-bit Linux operating system, a processor with no less than 16 physical cores and a main frequency of no less than 2.5GHz, an ECC-verified random access memory with a capacity of no less than 64GB, and an NVMe solid-state storage device with a capacity of no less than 500GB. S301, Definition of inherent static parameters of facilities. For the set of facility types. Each type of facility Define its inherent set of static parameters. It should include at least the following parameters: maximum effective range. Effective pitch angle range Effective azimuth range Coverage intensity attenuation model parameters and capability assessment thresholds Set of facility types Classified into a collection of sensing facilities and defensive facilities ,satisfy For facilities with dynamic parameter adjustment capabilities, their effective range and field of view are included in the inherent static parameter set according to their parameter boundaries in the farthest detection mode or maximum power mode. The set is used for calculation.

[0038] The typical inherent static parameter values ​​for various facilities are shown in Table 1 below: Table 1 Typical inherent static parameter values ​​for various facilities The type of low-altitude safety facility used in this embodiment is: S302. Three-dimensional coverage calculation of facility perception and defense capabilities based on ray tracing. This step is for each candidate low-altitude security facility installation location. and each type of facility The coverage intensity distribution of the facility in three-dimensional voxel space was calculated using a ray tracing algorithm, see [link / reference]. Figure 3 .

[0039] Furthermore, step S302 includes the following steps: S3021, ray cluster generation, with candidate low-altitude safety facility installation locations. Origin of the ray According to the preset pitch angle resolution and azimuth resolution Within the effective pitch angle range of the facility and azimuth range Internally generated, regularly distributed ray clusters. Elevation angle resolution. and azimuth resolution The angle is determined based on a trade-off between facility detection accuracy and computational efficiency. For key protection areas requiring precise coverage assessment, a range of 1°–2° is recommended around the perimeter; for large-scale scans in the preliminary planning stage, 3°–5° can be used. Each ray within a ray cluster is composed of… Characterization, ,in and These are the elevation angle and the azimuth angle, respectively. S3022. Find the intersection of a ray and an occluding entity voxel. For each ray in the ray cluster, traverse the set of occluding entity voxels. For the occluded entity voxels, the Amanatides-Woo algorithm is used to calculate the intersection distance between the ray and each occluded entity voxel. For the cuboid mesh environment, the algorithm initialization and step parameters are as follows: The three-dimensional spatial coordinates of the ray origin are The normalized direction vector is The current voxel index is voxel resolution is The distance parameters of the ray reaching the three opposite mesh faces of the current voxel: , , .like Then the parameter ,like ,but ,like ,but Similarly, if Then the parameter ,like ,but ,like ,but ;like ,but ,like Then the parameter ,like ,but Algorithm step parameters: , , If a certain component is 0, the corresponding .

[0040] Record the minimum distance among all valid intersection points as the nearest occlusion distance for that ray. If the ray does not intersect with any solid voxel, then it is recorded as... ; S3023, Voxel visibility determination. Based on the ray tracing intersection results, determine the candidate point... Each ray originating from the point of origin and each voxel unit in the three-dimensional voxel space The visual relationship between them.

[0041] Specifically, regarding the candidate low-altitude safety facility installation sites Corresponding ray origin Starting in the direction Rays, if voxel units Located on the propagation path of the ray, and at the origin To voxel unit Distance from the center satisfy Then determine the direction of the ray. voxel unit Visibility, defining the directional visibility indicator function. Otherwise, it is determined that the direction is blocked. .

[0042] Based on the visibility results in all directions within the ray cluster, candidate installation sites for low-altitude safety facilities are defined. To voxel unit Overall visibility indicator function: ; That is, when at least one ray in the ray cluster is in contact with a voxel unit When viewing through, ;otherwise This overall visibility indicator function will be used for coverage strength calculations in S3024; S3024. Coverage Intensity Calculation. Based on the established visibility, select the appropriate physical propagation model according to the facility type to calculate the coverage intensity of each voxel unit. For occluded voxels, the coverage intensity is set to zero; for through voxel units, the following calculations are performed: For electromagnetic sensing facilities The signal-to-noise ratio at the voxel location is calculated using radar equations and used as an indicator of coverage strength. ; in, Transmission power, measured in watts; These are the gains of the transmitting and receiving antennas, respectively, and are dimensionless. The wavelength is the operating wavelength, expressed in meters. The radar cross section of a typical target is shown in square meters. Candidate installation sites for low-altitude safety facilities Corresponding ray origin To voxel unit Distance from the center The unit is meters; Boltzmann's constant; The system noise temperature is expressed in Kelvin. Receiver bandwidth, measured in Hertz; is the atmospheric loss factor, which is dimensionless; For visibility indication functions, when candidate low-altitude safety facility installation locations... To voxel unit The value is 1 if there is at least one line-of-sight ray, otherwise it is 0.

[0043] For photoelectric sensing facilities The signal-to-noise ratio at the voxel location is calculated using an illumination propagation model: ; in, For passive imaging devices, the equivalent target radiant flux represents the equivalent radiant intensity after ambient illuminance is reflected by the target or after the target's own thermal radiation. For active detection devices, it represents the echo energy after the emitted pulse is reflected by the target. The surface reflectivity of the target is dimensionless and ranges from 1 to 10. ; Let be a dimensionless atmospheric transmittance function that varies with distance, and its value range is . ; The effective receiving area of ​​the optical lens; This refers to the solid angle of the sensor's field of view; This is the noise equivalent irradiance; This is a visibility indicator function.

[0044] For defensive facilities, A piecewise nonlinear decay model is used to characterize the nonlinear decrease in defensive effectiveness with increasing distance: ; in, This refers to the maximum effective range of the defensive facilities. The decay exponent is a dimensionless positive parameter that controls the rate at which defensive effectiveness decreases with distance. This is a visibility indicator function.

[0045] S303. Sensing-Defense Capability Matrix Generation. This involves summarizing the coverage intensity calculation results for all candidate locations and all facility types to generate a complete sensing-defense capability matrix that describes the coverage intensity distribution of each candidate location in 3D voxel space after deploying various facilities. .

[0046] S4. Construction of a facility layout optimization model based on risk-capability joint optimization. Based on the voxelized low-altitude risk field generated in S2 and the voxelized perception-defense capability matrix generated in S3, a multi-objective optimization model for low-altitude safety infrastructure layout is constructed, using facility deployment schemes as decision variables, maximizing perception risk coverage, maximizing defense risk coverage, minimizing total lifecycle cost, and maximizing perception-defense collaborative coverage as optimization objectives, and using budget constraints, mutual exclusion constraints, and redundancy constraints as constraints.

[0047] S401. Definition of Decision Variables. Define binary decision variables. ( , (), indicating whether it is a candidate low-altitude safety facility installation site. Deployment of the first Type of facilities: Indicates deployment, This indicates no deployment. All decision variables constitute the facility deployment plan vector. .

[0048] S402, Construction of multi-objective optimization function.

[0049] First, maximize perceived risk coverage. The perceived risk coverage rate is defined as the proportion of perceived coverage-weighted voxel risk values ​​to the total risk value. It is used to measure the proportion of risk voxels that the deployment plan can effectively cover for sensing facilities. ; in, voxel unit The perception coverage indicator function is defined as: ; in, This is an indicator function that takes the value 1 when the condition is met, and 0 otherwise; The threshold for determining the capabilities of sensing facilities is the maximum value of the minimum detectable signal-to-noise ratio (electromagnetic) or minimum imaging signal-to-noise ratio (photoelectric) specified in the equipment specifications. Voxel representation It is effectively covered by at least one deployed sensing facility.

[0050] Secondly, maximize the coverage of defensive risks. The defense risk coverage rate is defined as the proportion of defense coverage-weighted voxel risk values ​​to the total risk value. It is used to measure the proportion of risk voxels that a deployment plan can effectively cover for defense-related facilities. ; in, To cover the voxelized low-altitude risk field of the study area; voxels The defense coverage indication function is defined as: ; in, The threshold for determining the capabilities of defensive facilities is determined by taking the minimum value of the nominal maximum effective distance specified in the technical specifications of the defensive facilities used, and replacing it with... The result of subsequent calculations Value as . Voxel unit It is effectively covered by at least one deployed defensive facility.

[0051] Secondly, minimize the total lifecycle cost. Total lifecycle cost includes facility acquisition cost, installation and deployment cost, and operation and maintenance cost: ; in, For the first The unit purchase cost of such facilities; For the first The unit installation and deployment cost of this type of facility; For the first The average annual operation and maintenance cost of such facilities; This refers to the entire lifespan of the facility.

[0052] Finally, maximizing the coverage of perception-defense synergy. The perception-defense coordinated coverage measure is the proportion of high-risk voxels that are effectively covered by both perception and defense facilities. ; S403, Constraints. These include: Total budget constraint. The total lifecycle cost of the deployment plan must not exceed the preset budget limit. : ; Single-point mutual exclusion constraint. Each candidate point... At most one type of facility can be deployed: ; Covering redundancy constraints. For sensing facilities, the set of key risk voxels. Defined as a risk value exceeding a preset threshold And a collection of voxels located within the protection radius of key protected targets, Take the upper quartile of the risk field after normalization. For defensive facilities, the set of key risk voxels. Defined as a risk value exceeding Furthermore, it is a collection of voxels located in a high-density cluster of historical events. Take the upper quartile of the nuclear density estimate. Such voxels should be at least... Each facility is covered to enhance system reliability: ; ; in, and These are sets of key risk voxels that require sensing coverage and defensive coverage, respectively.

[0053] S5. Model Solving and Optimal Layout Generation. The multi-objective optimization model constructed in S4 is solved using a reference-point-based multi-objective evolutionary algorithm (NSGA-III). The algorithm parameters can be set as follows: population size 200-500, maximum number of iterations... The number of chromosomes is 500-800, the crossover probability is 0.9, the mutation probability is 0.1, and the chromosomes are directly encoded in binary. Each chromosome corresponds to a facility deployment scheme vector. Gene locus sequence and candidate site-facility type pair One-to-one correspondence. When the set maximum number of iterations is reached... Or the objective function value during iteration If no improvement is made after this step, the iteration is terminated, ultimately yielding the Pareto optimal facility deployment scheme set. Decision-makers can choose the most suitable facility deployment plan on the Pareto frontier based on actual needs.

[0054] Preferably, the specific site selection scheme and the empirical site selection scheme provided in this embodiment are compared as follows: In this embodiment, X-band radar and electro-optical turntables are selected for sensing facilities, and radio jamming is selected for defensive facilities. An empirical deployment scheme is as follows: deployment is centered on key protected targets, with one set of electromagnetic sensing, one set of electro-optical sensing, and one set of defensive facilities fixed around each target, and evenly supplemented at road intersections. Ultimately, 20 locations are selected, deploying 10 sets of X-band radar, 4 sets of electro-optical turntables, and 6 sets of radio jamming. The deployment scheme of this invention uses NSGA-III for solving, with a population size of 300, a maximum number of iterations of 600, a crossover probability of 0.9, and a mutation probability of 0.1. An equilibrium scheme is selected from the Pareto front: deploying 8 sets of X-band radar, 6 sets of electro-optical turntables, and 4 sets of radio jamming at 18 candidate locations. The objective function values ​​corresponding to the two schemes are shown in Table 2. Table 2 Comparison of objective function values ​​for the two schemes The results show that, under the premise of completely identical facility types, the optimized deployment method of this invention reduces the total cost by 17.3% compared with empirical deployment, while improving the coverage of perceived risks by 27.9%, the coverage of defensive risks by 39.3%, and the coverage of perception-defense collaboration by 45.1%. These data demonstrate that this invention, through three-dimensional risk field quantification, ray-tracing line-of-sight calculation, and multi-target collaborative optimization, significantly outperforms traditional empirical deployment methods, exhibiting clear technical advantages in both coverage effectiveness and cost-effectiveness.

[0055] Example 2 Based on the same inventive concept, this application also provides a low-altitude safety facility layout optimization device based on voxelized risk field and facility capability modeling, which can be used to implement the method described in the above embodiments, specifically including the following: A three-dimensional voxel space construction unit is used to construct a three-dimensional voxel space corresponding to the study area. Semantic attributes are labeled for each voxel unit in the three-dimensional voxel space, and the voxel index corresponding to the candidate low-altitude safety facility installation point is determined. A voxelized low-altitude risk field construction unit is used to fuse multi-source risk factors, quantify the safety risk of each voxel unit in the three-dimensional voxel space, and construct a voxelized low-altitude risk field covering the study area. The perception-defense capability matrix generation unit is used to determine the occlusion entity based on the semantic attribute annotation of the voxel unit, calculate the coverage intensity after deploying different types of low-altitude security facilities at each candidate low-altitude security facility installation point using a ray tracing algorithm, and generate the perception-defense capability matrix. The multi-objective optimization model construction unit is used to construct a multi-objective optimization model for low-altitude safety infrastructure layout based on the voxelized low-altitude risk field and the perception-defense capability matrix, with facility deployment scheme as the decision variable. The model includes the optimization objectives of maximizing perception risk coverage, maximizing defense risk coverage, minimizing total life cycle cost, and maximizing perception-defense collaborative coverage. The solution unit is used to solve the multi-objective optimization model using a multi-objective evolutionary algorithm to obtain the optimal facility deployment scheme set.

[0056] Preferably, embodiments of this application also provide a specific implementation of an electronic device capable of implementing all steps in the low-altitude safety facility layout optimization method based on voxelized risk field and facility capability modeling in the above embodiments. The electronic device specifically includes the following: Processor, memory, communications interface, and bus; The processor, memory, and communication interface communicate with each other via a bus; the communication interface is used to realize information transmission between server-side devices, metering devices, and user-side devices.

[0057] The processor is used to call the computer program in the memory. When the processor executes the computer program, it implements all the steps in the low-altitude safety facility layout optimization method based on voxelized risk field and facility capability modeling in the above embodiments.

[0058] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the low-altitude safety facility layout optimization method based on voxelized risk field and facility capability modeling in the above embodiments. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements all steps of the low-altitude safety facility layout optimization method based on voxelized risk field and facility capability modeling in the above embodiments. The computer-readable storage medium may be a disk, optical disk, read-only memory, random access memory, flash memory, portable hard disk, solid-state drive, or other tangible storage medium capable of storing program code and being read and executed by a processor.

[0059] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0060] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0061] While this application provides method operation steps as shown in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the method can be executed in the order shown in the embodiments or drawings or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0062] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0064] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0065] This invention is not limited to the embodiments described above. The above description of specific embodiments is intended to illustrate and explain the technical solutions of this invention. The specific embodiments described above are merely illustrative and not restrictive. Without departing from the spirit and scope of the claims, those skilled in the art can make many specific modifications based on the teachings of this invention, and these modifications all fall within the scope of protection of this invention.

Claims

1. A method for optimizing the layout of low-altitude safety facilities based on voxelized risk field and facility capability modeling, characterized in that, include: S1. Construct a three-dimensional voxel space corresponding to the study area, perform semantic attribute annotation on each voxel unit in the three-dimensional voxel space, and determine the voxel index corresponding to the candidate low-altitude safety facility installation point. S2. Integrate multi-source risk factors, quantify the safety risk of each voxel unit in the three-dimensional voxel space, and construct a voxelized low-altitude risk field covering the study area. S3. Based on the semantic attribute annotations of the voxel units, determine the occlusion entities, calculate the coverage intensity of each candidate low-altitude security facility installation site after deploying different types of low-altitude security facilities using a ray tracing algorithm, and generate a perception-defense capability matrix; specifically including: For each type of facility, a ray cluster is generated based on its effective pitch and azimuth ranges; the set of obstructing entity voxels is traversed, and the shortest intersection distance between each ray in the ray cluster and the obstructing entity voxel is calculated to determine the line-of-sight relationship between the installation point of the candidate low-altitude safety facility and each voxel unit; based on the line-of-sight relationship determination result, the corresponding physical propagation model is selected according to the facility type to calculate the coverage intensity of the voxel unit, and all calculation results are summarized to generate the perception-defense capability matrix; S4. Based on the voxelized low-altitude risk field and the perception-defense capability matrix, and with the facility deployment scheme as the decision variable, construct a multi-objective optimization model for the layout of low-altitude safety infrastructure, which includes maximizing the perception risk coverage, maximizing the defense risk coverage, minimizing the total cost throughout the life cycle, and maximizing the perception-defense collaborative coverage as optimization objectives. S5. Use a multi-objective evolutionary algorithm to solve the multi-objective optimization model and obtain the optimal facility deployment scheme set.

2. The method for optimizing the layout of low-altitude safety facilities according to claim 1, characterized in that, Step S1 involves semantic attribute annotation for each voxel unit, specifically including: using the 3D model and surface data within the study area, defining a voxel type indicator function to divide the voxel unit into a set containing free voxels and multiple types of occluded entity voxels, wherein the voxel units marked as occluded entity voxels constitute the occluded entity voxel set in the ray tracing algorithm; the surface data includes the terrain elevation model and surface cover data.

3. The method for optimizing the layout of low-altitude safety facilities according to claim 1, characterized in that, Step S2 involves constructing a voxel-based low-altitude risk field by fusing multiple risk factors. Specifically, this includes: collecting data on key protected targets, airspace restricted areas, and the spatial distribution data of historical safety events; calculating the key protected target factor, airspace restriction level factor, and historical event density factor for each voxel unit; and linearly weighting and superimposing the above three types of factors to obtain the risk value corresponding to the voxel unit, thereby constructing the voxel-based low-altitude risk field.

4. The method for optimizing the layout of low-altitude safety facilities according to claim 3, characterized in that, The key protection target factor for each voxel unit is calculated using a Gaussian decay function; The calculation of the spatial restriction level factor for each voxel unit specifically includes: calculating the spatial intersection volume ratio between the voxel unit and the spatial restriction region; using the spatial intersection volume ratio as a weight, combined with the restriction level corresponding to the spatial restriction region, to calculate the spatial restriction level factor, wherein for a voxel unit located at the overlap of multiple spatial restriction regions, the highest restriction level among all spatial restriction regions covering the voxel unit is taken. The calculation of the historical event density factor includes: using the three-dimensional kernel density estimation method to calculate the historical event density distribution function in three-dimensional space, substituting the center coordinates of each voxel unit into the above historical event density distribution function to obtain the corresponding historical event density factor.

5. The method for optimizing the layout of low-altitude safety facilities according to claim 1, characterized in that, The physical propagation model includes: for electromagnetic sensing facilities, the signal-to-noise ratio at the voxel unit location is calculated using radar equations as the coverage strength; for photoelectric sensing facilities, the imaging signal-to-noise ratio at the voxel unit location is calculated using an illumination propagation model as the coverage strength; and for defensive facilities, the defensive effectiveness at the voxel unit location is calculated using a piecewise nonlinear attenuation model as the coverage strength.

6. The method for optimizing the layout of low-altitude safety facilities according to claim 1, characterized in that, The multi-objective optimization model for the layout of low-altitude safety infrastructure in step S4 also includes constraints, which include: Total budget constraint: The total lifecycle cost of the facility deployment plan shall not exceed the preset budget limit; Single-point mutual exclusion constraint: Each candidate low-altitude safety facility installation site may deploy at most one type of facility; Coverage redundancy constraints: For critical risk voxel sets whose risk values ​​exceed a preset threshold and are located within key coverage areas, the minimum facility coverage quantity requirement must be met; for sensing facilities, the critical risk voxel set is defined as the set of voxels whose risk values ​​exceed a preset threshold and are located within key coverage areas, with the preset threshold being the upper quartile of the risk field after normalization; for defense facilities, the critical risk voxel set is defined as the set of voxels whose risk values ​​exceed a preset threshold and are located in areas with high-density clustering of historical events, with the preset threshold being the upper quartile of the kernel density estimation result; In step S5, a multi-objective evolutionary algorithm based on reference points is used to solve the multi-objective optimization model for the layout of low-altitude safety infrastructure. The iteration is terminated when the set maximum number of iterations is reached or the optimal objective function value is not improved after a certain number of iterations, and a Pareto optimal layout scheme set is obtained. The most satisfactory facility deployment scheme is selected from the Pareto optimal layout scheme set according to actual needs.

7. A low-altitude safety facility layout optimization device based on voxelized risk field and facility capability modeling, characterized in that, include: A three-dimensional voxel space construction unit is used to construct a three-dimensional voxel space corresponding to the study area. Semantic attributes are labeled for each voxel unit in the three-dimensional voxel space, and the voxel index corresponding to the candidate low-altitude safety facility installation point is determined. A voxelized low-altitude risk field construction unit is used to fuse multi-source risk factors, quantify the safety risk of each voxel unit in the three-dimensional voxel space, and construct a voxelized low-altitude risk field covering the study area. The perception-defense capability matrix generation unit is used to determine the occlusion entity based on the semantic attribute annotation of the voxel unit, calculate the coverage intensity after deploying different types of low-altitude security facilities at each candidate low-altitude security facility installation point using a ray tracing algorithm, and generate the perception-defense capability matrix. The multi-objective optimization model construction unit is used to construct a multi-objective optimization model for low-altitude safety infrastructure layout based on the voxelized low-altitude risk field and the perception-defense capability matrix, with facility deployment scheme as the decision variable. The optimization objectives include maximizing perception risk coverage, maximizing defense risk coverage, minimizing total life cycle cost, and maximizing perception-defense collaborative coverage. The solution unit is used to solve the multi-objective optimization model using a multi-objective evolutionary algorithm to obtain the optimal facility deployment scheme set.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the low-altitude safety facility layout optimization method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the low-altitude safety facility layout optimization method according to any one of claims 1 to 6.

Images