Method, apparatus and electronic device for determining safety fence

Abstract

The application provides a safety fence determination method, device and electronic equipment. It can be applied to the field of unmanned aerial vehicle technology. The safety fence determination method is characterized in that: in response to receiving an inspection task, an inspection path is obtained from task data of the inspection task, wherein the inspection task represents a task of inspecting a target substation by an unmanned aerial vehicle; based on a space region corresponding to the inspection path, a plurality of channel voxel units are determined in a plurality of voxel units included in a voxel space of a three-dimensional model of the target substation; based on initial passing states of the plurality of channel voxel units, self-adjustment of passable states is performed to obtain target passing states of the plurality of channel voxel units; according to the plurality of target passing states, the plurality of channel voxel units are divided into fence boundaries to determine a plurality of safety fences corresponding to the inspection task; different safety fences in the plurality of safety fences correspond to different upper limits of unmanned aerial vehicle movement speed.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) technology, and more specifically, to a method, apparatus, and electronic device for determining a fence. Background Technology

[0002] With the construction of ultra-high voltage power transmission projects and the large-scale integration of new energy sources, the number and scale of substations continue to grow. The equipment within these substations is characterized by high density, three-dimensionality, and complex structures. Simultaneously, the operating environment commonly suffers from strong electromagnetic interference and dense reflections from metal components. To improve operation and maintenance efficiency and safety, the power industry is gradually promoting the use of drones for visible light inspection, infrared thermography, and partial discharge detection. However, in infrastructure scenarios such as substations, drone flight space is limited and obstacles are dense. A collision could damage critical equipment such as busbars, bushings, and structures, leading to significant safety hazards and economic losses. Therefore, higher requirements are placed on the spatial constraints and safety boundaries within the substation during drone operations.

[0003] In the process of realizing the concept of this application, it was found that in substation environments with dense equipment and complex structures, the determined safety constraints have obvious usability and accuracy problems. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus and electronic device for determining a safety fence.

[0005] One aspect of this application provides a method for determining a safety fence, comprising: in response to receiving an inspection task, obtaining an inspection path from the task data of the inspection task, wherein the inspection task represents a task for a UAV to inspect a target substation; determining multiple channel voxel units in the voxel space of the substation's three-dimensional model, based on the spatial region corresponding to the inspection path; performing self-adjustment of the passability state based on the initial passability state of each of the multiple channel voxel units to obtain the target passability state of each of the multiple channel voxel units; dividing the multiple channel voxel units into fence boundaries according to the multiple target passability states to determine a multi-layer safety fence corresponding to the inspection task; different safety fences in the multi-layer safety fence correspond to different upper limits of UAV movement speed.

[0006] According to an embodiment of this application, the determination method further includes: obtaining a three-dimensional model of the target substation; the three-dimensional model of the substation is composed of three-dimensional models of multiple electrical equipment in the target substation; performing voxelization processing on the spatial region where the three-dimensional model of the substation is located to obtain a voxel space; for multiple voxel units in the voxel space, determining the initial passage state of the voxel unit according to the equipment attributes of each electrical equipment and the distance between the voxel unit and each electrical equipment.

[0007] According to an embodiment of this application, for multiple voxel units in a voxel space, the initial passage state of the voxel unit is determined based on the device attributes and the distance between the voxel unit and each of the multiple power equipment, including: determining multiple initial risk values ​​based on the device attributes of the power equipment and the distance between the voxel unit in the space where the power equipment is located and each of the multiple power equipment; determining a first risk value of the voxel unit from the multiple initial risk values; and determining the initial passage state of the voxel unit based on the first risk value. Wherein, conditionally flyable means that the speed limit of the UAV is 2 meters per second.

[0008] According to an embodiment of this application, the determination method further includes: for multiple voxel units, adjusting a first risk value based on the model confidence of the device 3D model corresponding to the voxel unit to obtain an adjusted first risk value for the voxel unit; wherein, determining the initial passage state of the voxel unit based on the first risk value includes: determining the initial passage state of the voxel unit based on the adjusted first risk value.

[0009] According to an embodiment of this application, the determination method further includes: upon receiving updated data of the target substation, determining a second risk value of the voxel unit based on the updated data and the distance between the voxel unit and the target substation; and determining the initial passage state of the voxel unit based on the larger of the first risk value and the second risk value.

[0010] According to an embodiment of this application, obtaining the three-dimensional model of the target substation and the equipment attributes of the multiple electrical equipment included in the target substation includes: obtaining the three-dimensional models and equipment attributes of the multiple electrical equipment included in the target substation; and, based on the layout of the electrical equipment in the target substation, spatially aligning the three-dimensional models of the multiple electrical equipment in the substation coordinate system to obtain the three-dimensional model of the target substation.

[0011] According to embodiments of this application, the initial access state includes prohibited flight, conditionally flyable, and safe flight; based on the initial access state of each of the multiple channel voxel units, self-adjustment of the passability state is performed to obtain the target access state of each of the multiple channel voxel units, including: when the initial access state of the multiple channel voxel units is prohibited flight, adjusting the state type of the initial access state of the multiple channel voxel units to conditionally flyable to obtain the target access state of the channel voxel units; when the state type of the initial access state of the multiple channel voxel units is conditionally flyable or safe flight, the initial access state of the channel voxel units is taken as the target access state.

[0012] According to an embodiment of this application, multiple channel voxel units are divided into fence boundaries based on multiple target passage states to determine a multi-layer safety fence corresponding to the inspection task, including: dividing multiple channel voxel units into multiple voxel sets based on the state type to which the target passage states belong; and determining a multi-layer safety fence corresponding to the inspection task based on the area boundaries of the spatial regions corresponding to each of the multiple voxel sets.

[0013] Another aspect of this application provides a safety fence determination device, comprising: an acquisition module, configured to acquire an inspection path from task data of an inspection task in response to receiving an inspection task, wherein the inspection task represents a task for a UAV to inspect a target substation; a determination module, configured to determine multiple channel voxel units in a voxel space containing multiple voxel units of the substation's 3D model based on the spatial region corresponding to the inspection path; an adjustment module, configured to self-adjust the passability state based on the initial passability state of each of the multiple channel voxel units to obtain the target passability state of each of the multiple channel voxel units; and a division module, configured to divide the multiple channel voxel units into fence boundaries according to the multiple target passability states to determine a multi-layer safety fence corresponding to the inspection task; wherein different safety fences in the multi-layer safety fence correspond to different upper limits of UAV movement speed.

[0014] Another aspect of this application provides an electronic device comprising:

[0015] One or more processors;

[0016] Memory, used to store one or more programs.

[0017] Specifically, when one or more programs are executed by one or more processors, the one or more processors implement the above method.

[0018] Another aspect of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0019] Another aspect of this application provides a computer program product including computer-executable instructions that, when executed, are used to implement the methods described above.

[0020] According to embodiments of this application, mapping the inspection path to voxel space and performing self-adjustment of channel voxel units can alleviate the problem of disrupting the connectivity of critical inspection channels during voxelization and safety expansion. This maintains the integrity of the UAV's flight space while ensuring the safety protection of substation equipment, avoiding inspection path interruptions caused by overly conservative safety fences. Furthermore, multi-layered safety fences constructed based on target traffic status allow the UAV to automatically adjust its flight speed according to its real-time location, meeting the protection requirements of high-safety-level areas while ensuring efficient passage in low-risk areas, thereby improving inspection efficiency while ensuring the safe operation of the substation. By coupling the inspection path with voxel space, a refined safety fence can be determined, enhancing the safety and inspection efficiency of UAV operations within the substation. Attached Figure Description

[0021] The above and other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0022] Figure 1 An exemplary system architecture for determining a security fence that can be applied according to embodiments of this application is illustrated.

[0023] Figure 2 A flowchart illustrating a method for determining a security fence according to an embodiment of this application is shown schematically.

[0024] Figure 3 A data flow diagram illustrating the initial passage state determination method according to an embodiment of this application is shown schematically.

[0025] Figure 4 The diagram illustrates a voxel-based passage state diagram with self-adjustment and model confidence adjustment for passable states.

[0026] Figure 5 A block diagram schematically illustrates a security fence determining device according to an embodiment of this application; and

[0027] Figure 6 A block diagram of an electronic device suitable for implementing a method for determining a security fence according to an embodiment of this application is shown schematically. Detailed Implementation

[0028] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0029] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0030] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0031] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0032] Currently, the main methods for constraining the flight safety boundaries of drones are as follows: One method is based on the concept of electronic fences or geofencing, abstracting no-fly zones, height-restricted zones, or safety corridors into regular geometric shapes such as polygons, boxes, cylinders, or convex polyhedra, and performing boundary violation judgment and alarms on the flight control or host computer side; the other method is based on 3D maps such as point clouds, grids, or voxel maps for collision detection or path planning, achieving safety constraints through local obstacle avoidance or replanning. However, while these methods have certain applicability in open or relatively simple scenarios, they still have significant shortcomings in the environment of substations with dense equipment and complex structures. First, the 3D scene models of substations come from diverse sources, making unified processing difficult. In actual engineering, the models within the station may come from LiDAR scanned point clouds, 3D reconstructed meshes, BIM / CAD models, or asset library models, etc. These multi-source models differ significantly in terms of coordinate systems, scale units, attitude references, accuracy density, and topology. Existing methods often rely on manual alignment and empirical parameters for processing, resulting in low modeling efficiency, poor reusability, and difficulty in supporting rapid deployment and continuous maintenance at the station level. Secondly, existing fencing methods generally focus on geometric boundaries, resulting in a coarse-grained representation that struggles to accommodate the numerous irregular structures and narrow passages within substations, such as structural gaps, equipment room passages, and areas near cable trays. In practical applications, this often necessitates the addition of numerous geometric fencing elements, leading to high maintenance costs and the potential for excessive fencing expansion that encroaches on flyable space, or insufficient fencing coverage that misses high-risk areas.

[0033] Meanwhile, if the differences in model accuracy and the complexity of local structures are not fully considered during the generation of safety fences, details such as wires, slender components or gaps between equipment may be oversimplified, thereby destroying the connectivity of free space, making the safety boundary too conservative, and affecting the operability and inspection efficiency of drones in confined spaces.

[0034] In view of this, embodiments of this application provide a method for determining a safety fence, comprising: in response to receiving an inspection task, obtaining an inspection path from the task data of the inspection task, wherein the inspection task represents a task for a UAV to inspect a target substation; determining multiple channel voxel units in the voxel space of the substation's three-dimensional model, based on the spatial region corresponding to the inspection path; performing self-adjustment of the passability state based on the initial passability state of each of the multiple channel voxel units to obtain the target passability state of each of the multiple channel voxel units; dividing the multiple channel voxel units into fence boundaries according to the multiple target passability states to determine a multi-layer safety fence corresponding to the inspection task; different safety fences in the multi-layer safety fence correspond to different upper limits of UAV movement speed.

[0035] Figure 1This illustration schematically depicts an exemplary system architecture 100 for determining a security fence according to embodiments of this application. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this application, in order to help those skilled in the art understand the technical content of this application, but do not mean that the embodiments of this application cannot be used in other devices, systems, environments or scenarios.

[0036] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a drone device 101, a network 102, and a server 103. The network 102 serves as a medium for providing a communication link between the drone device 101 and the server 103. The network 102 may include various connection types, such as wired and / or wireless communication links, etc.

[0037] Users can interact with the drone device 101 through the server 103 to control the drone device 101 to perform inspection tasks on the target substation.

[0038] The drone device 101 can be a drone capable of performing inspection tasks for substations. This drone can inspect key equipment in the target substation by taking photos.

[0039] Server 103 can be a server that provides various services, such as using the above-mentioned method for determining a safety fence to generate a safety fence for motion constraints on the UAV device 101 by processing the three-dimensional model of the target substation and the preset inspection path.

[0040] It should be noted that the method for determining the security fence provided in this application embodiment can generally be executed by the server 103. Accordingly, the security fence determination system provided in this application embodiment can generally be set in the server 103.

[0041] It should be understood that Figure 1 The number of drones, networks, and servers shown is merely illustrative. Any number of drones, networks, and servers can be included depending on implementation needs.

[0042] Figure 2 A flowchart illustrating a method for determining a security fence according to an embodiment of this application is shown schematically.

[0043] like Figure 2 As shown, the method includes operations S210~S240.

[0044] In operation S210, in response to receiving the inspection task, the inspection path is obtained from the task data of the inspection task, where the inspection task represents the task of the UAV to inspect the target substation.

[0045] According to an embodiment of this application, upon receiving an inspection task for a target substation, the task data can first be parsed to extract pre-planned or specified inspection path information. This inspection path can consist of a series of ordered spatial coordinate points or voxel sequences, representing the flight trajectory that the UAV should follow when performing inspection operations within the substation. Its generation can be determined based on equipment inspection requirements, shooting angle requirements, or historical optimized paths.

[0046] In operation S220, based on the spatial region corresponding to the inspection path, multiple channel voxel units are determined in the voxel space of the target substation's three-dimensional model.

[0047] According to an embodiment of this application, after obtaining the inspection path, the spatial area occupied by the inspection path can be determined. This spatial area can be obtained by three-dimensionally buffering and expanding the inspection path, that is, using discrete points on the path as a reference, extending radially by the distance corresponding to the safe airspace of the UAV, thereby forming a tubular spatial area with a certain cross-sectional area. Subsequently, within the intersection range of this tubular spatial area and the voxel space of the target substation's three-dimensional model, voxel units related to the inspection path space are selected as a channel voxel set. The aforementioned voxel space can be obtained by voxelizing the spatial area where the target substation's three-dimensional model is located. Through voxelization, the spatial area where the inspection path is located can be represented in the form of channel voxel units, enabling precise positioning of the inspection path in space.

[0048] In operation S230, the passable state is self-adjusted based on the initial passable state of each of the multiple channel voxel units to obtain the target passable state of each of the multiple channel voxel units.

[0049] According to embodiments of this application, for a channel voxel unit, the aforementioned initial passage state can indicate the motion state of the UAV when it is located at that voxel position. The initial passage state can include constraint types such as restricted access, speed limit, buffer, or free passage. Then, in order to ensure the channel connectivity of the channel voxel unit for the UAV, the initial passage state can be adaptively adjusted to release voxel constraints that might otherwise block the channel, ultimately forming a target passage state that balances safety and passability.

[0050] During operation of S240, fence boundaries are defined for multiple channel voxel units based on the passage status of multiple targets, and multi-layer safety fences corresponding to the inspection task are determined; different safety fences in the multi-layer safety fences correspond to different upper limits of UAV movement speed.

[0051] According to embodiments of this application, based on the target passage state determined by each channel voxel unit after self-adjustment, voxels with the same passage state can be spatially aggregated and their boundaries extracted to form a safety fence area with a clear geometric boundary. The target passage state includes various types such as prohibited entry, speed limit, buffer zone, and free passage, allowing for the creation of multiple layers of safety fences. These multiple layers of safety fences are spatially nested or adjacent, and different safety fences correspond to different upper limits for UAV movement speed, thus enabling the implementation of different UAV motion control strategies.

[0052] According to embodiments of this application, furthermore, each layer of the multi-layered safety fence establishes a mapping relationship with the upper speed limit of the drone. For example, the no-entry fence corresponds to an absolutely prohibited area with a speed limit of zero; the speed-limited fence corresponds to a restricted passage area below the cruising speed, and its speed limit can be set according to the risk level of nearby power equipment; the buffer fence corresponds to a warning area slightly below the normal cruising speed; and the free passage area corresponds to an unrestricted flight space at the standard cruising speed. This layered mechanism allows the drone to automatically match the corresponding speed constraints based on its real-time location during inspection.

[0053] According to embodiments of this application, mapping the inspection path to voxel space and performing self-adjustment of channel voxel units can alleviate the problem of disrupting the connectivity of critical inspection channels during voxelization and safety expansion. This maintains the integrity of the UAV's flight space while ensuring the safety protection of substation equipment, avoiding inspection path interruptions caused by overly conservative safety fences. Furthermore, a multi-layered safety fence constructed based on the target's passage status allows the UAV to automatically adjust its flight speed according to its real-time location, meeting the protection requirements of high-safety-level areas while ensuring efficient passage in low-risk areas, thereby improving inspection efficiency while ensuring the safe operation of the substation. By coupling the inspection path with voxel space, a refined safety fence can be determined, enhancing the safety and inspection efficiency of UAV operations within the substation.

[0054] According to an embodiment of this application, a three-dimensional model of the target substation is obtained; the three-dimensional model of the substation is composed of three-dimensional models of multiple electrical equipment in the target substation; the spatial region where the three-dimensional model of the substation is located is voxelized to obtain a voxel space; for multiple voxel units in the voxel space, the initial passage state of the voxel unit is determined according to the equipment attributes of each electrical equipment and the distance between the voxel unit and each electrical equipment.

[0055] According to an embodiment of this application, firstly, a three-dimensional model of the target substation is obtained. This model is composed of fused three-dimensional models of multiple electrical equipment within the substation. Electrical equipment may include transformers, circuit breakers, etc. Subsequently, the spatial area occupied by the aforementioned three-dimensional substation model can be discretized into voxels. The continuous space is divided into a set of regularly arranged voxel units according to a preset voxel resolution, thus obtaining a voxel space containing multiple voxel units. After the voxel space is constructed, the initial passage state of each voxel unit can be determined. Specifically, firstly, the distance relationship between the spatial location of the corresponding voxel unit and the geometric model of each electrical equipment is considered, which can be the shortest Euclidean distance from the voxel center point to the equipment surface; secondly, the equipment attributes of each electrical equipment are considered. Equipment attributes may include equipment category, voltage level, operating status, and risk level required by safety regulations. Based on the joint analysis of the above distances and attributes, voxel units can be classified and marked as initial passage states such as prohibited, speed-limited, buffer, or free passage.

[0056] According to an embodiment of this application, obtaining the three-dimensional model of the target substation and the equipment attributes of the multiple electrical equipment included in the target substation includes: obtaining the three-dimensional models and equipment attributes of the multiple electrical equipment included in the target substation; and, based on the layout of the electrical equipment in the target substation, spatially aligning the three-dimensional models of the multiple electrical equipment in the substation coordinate system to obtain the three-dimensional model of the target substation.

[0057] According to embodiments of this application, the aforementioned 3D model of the substation equipment can originate from different data sources such as LiDAR scan point clouds, oblique photogrammetry reconstruction meshes, BIM / CAD models from the design phase, or asset library models. Equipment attributes can include information such as equipment category, voltage level, rated parameters, operating status, and corresponding safety regulations. During alignment, a unified coordinate transformation function maps equipment models from different sources and coordinate systems to a preset substation coordinate system, eliminating differences in the original coordinate reference, scale units, and orientation directions between different models. This ensures that each equipment model maintains a geometrical positional relationship consistent with the actual physical layout within a unified spatial reference frame. By performing the above registration and fusion on all equipment models, a 3D model of the substation is obtained.

[0058] According to embodiments of this application, the 3D models of each substation device and their associated attribute information are obtained, and spatial alignment is performed based on the actual device layout. This allows heterogeneous models from different data sources to maintain a geometrical positional relationship consistent with the actual physical layout under a unified coordinate system, forming a complete 3D scene representation of the substation. This provides a reliable data foundation for subsequent voxelization processing and refined safety constraint calculations. The above method, through the unified fusion and standardization of multi-source heterogeneous device models, can alleviate the problems of diverse data sources and inconsistent coordinate references in substation 3D modeling. This further improves the accuracy of subsequent safety fence determination.

[0059] According to an embodiment of this application, for multiple voxel units in a voxel space, determining the initial passage state of a voxel unit based on its device attributes and the distances between the voxel unit and each of the multiple power equipment includes: determining multiple initial risk values ​​based on the device attributes of the power equipment and the distances between the voxel unit in the space where the power equipment is located and each of the multiple power equipment; determining a first risk value of the voxel unit from the multiple initial risk values; and determining the initial passage state of the voxel unit based on the first risk value.

[0060] According to embodiments of this application, a mapping relationship between spatial distance and equipment risk level can first be established, allowing voxel units to obtain different risk values ​​for different devices. Then, a first risk value for the voxel unit is determined from the multiple initial risk values. This determination process typically employs a maximization operation, selecting the maximum value among the multiple initial risk values ​​as the first risk value for the voxel unit. Finally, based on the determined first risk value, the voxel unit is mapped to a specific initial passage state according to a preset risk classification threshold.

[0061] According to an embodiment of this application, the first risk value is compared with the threshold range corresponding to states such as restricted access, speed limit, buffer zone, and free passage to determine the initial constraint type of the voxel unit. This initial passage state serves as the basis for subsequent adaptive adjustments in conjunction with inspection tasks, and can accurately reflect the static safety requirements under the combined effect of equipment attributes and spatial distance.

[0062] According to embodiments of this application, to achieve unified fusion of multi-source models of substation equipment, Unreal Engine 4 can be used as a unified 3D scene platform to import model data from different sources and convert them into a unified scene object representation. The set of multi-source 3D models obtained in the substation scene can be represented as follows: Among them, different models These can be derived from LiDAR point clouds, 3D reconstruction meshes, BIM / CAD models, or asset library models, etc. It can represent the serial number of electrical equipment. This represents the total number of power equipment. Since the models differ in coordinate system, scale unit, and orientation reference, spatial alignment of the multi-source 3D models can be performed first, using a unified coordinate transformation function. Map each model to the same station-level spatial coordinate system: .in, This represents the multi-source 3D model after conversion. By performing the above processing on all multi-source 3D models and completing unified loading, spatial alignment and scene organization in the 3D scene carrying platform, the fused substation 3D scene model is obtained, as shown in Equation (1).

[0063] (1)

[0064] in, This can represent a fused 3D scene model of a substation constructed under a unified world coordinate system. It can represent fusion Operators for a transformer equipment model.

[0065] After fusing the multi-source models, the space containing the fused 3D model is voxelized, discretizing the continuous space into a regular voxel mesh. The voxel resolution can be... voxel space It can be represented as Among them, voxel units A minimal discrete unit in the space of a strain gauge power station. These represent the continuous world coordinate values ​​in the three-dimensional space of the substation.

[0066] The above voxel resolution The resolution can be set according to the equipment density and inspection accuracy requirements of the substation. A higher resolution is used in areas with dense equipment or complex structures, while a lower resolution is used in open areas, balancing spatial representation accuracy and computational efficiency. Through the above processing, a voxelized basic spatial model covering the entire substation operating space is constructed, providing a unified data foundation for the subsequent generation of semantic voxel safety fences.

[0067] For any voxel unit Its corresponding voxel cubic region in three-dimensional space can be denoted as , Based on the above voxel index mapping and resolution The only certainty, It can represent the number of a voxel unit.

[0068] Figure 3 A data flow diagram illustrating the initial passage state determination method according to an embodiment of this application is shown schematically.

[0069] After completing the voxel-based basic space construction of the substation scene, refer to Figure 3 Furthermore, by jointly modeling the device semantic information and operational risk information at the voxel unit level, the initial passage status of the voxel unit can be determined.

[0070] Voxel space can be represented as ,in, It can represent the total number of voxel units, and each voxel unit A minimum discrete voxel element in the three-dimensional space of a strain gauge power station. By analyzing the spatial overlap between the voxel element and the equipment geometric model, the semantic category of the power equipment corresponding to the voxel element can be determined.

[0071] The semantic category set of power equipment can be ,in, It can represent the first Device semantics, It can represent the total number of categories of electrical equipment. It can represent semantic categories The equipment area in the three-dimensional space of a substation. For any voxel element. The semantic category of its power equipment is determined by the spatial region corresponding to the voxel. The overlapping volume with each semantic category spatial region is determined, so the voxel semantic mapping function can be as shown in equation (2).

[0072] (2)

[0073] in, This indicates the semantic category of the voxel, used to determine which power equipment's influence range the voxel unit belongs to based on its distance from the power equipment. This represents spatial region volume operations, and argmax represents the optimization operator.

[0074] After determining the voxel semantic category of a voxel unit, risk derivation can be performed based on the safety procedures in the device attributes, mapping the voxel semantic category of the voxel unit to different initial risk values. Specifically, this relates to the voxel semantic category... The related set of security procedures and operation and maintenance rules is as follows , This can be determined through the equipment attributes of different power transmission devices. The first risk value of the voxel unit. It can be determined by equation (3).

[0075] (3)

[0076] in, It can represent operating condition parameters related to voxels. Determined based on the equipment attributes of different power transmission equipment. Including but not limited to equipment voltage level, operating status, and safety distance requirements, functions Used to translate procedural constraints into risk intensity at the voxel level.

[0077] Furthermore, based on the first risk value and the preset security constraint judgment criteria, the voxels are mapped to different passage states. The communication state determination can be shown in equation (4).

[0078] (4)

[0079] in, It can represent the initial passage state of a voxel unit. Thresholds for different risk levels. It can indicate a restricted area. It can indicate a speed-limited zone. It can represent a buffer. This can represent a free passage zone. Furthermore, the areas corresponding to speed-limited zones and buffer zones can represent conditional flight, the areas corresponding to free passage zones can represent safe flight, and the areas corresponding to restricted areas can represent prohibited flight.

[0080] According to embodiments of this application, by voxelizing the space containing the fused 3D substation model, the continuous space is transformed into a set of regularly arranged voxel units, reducing the computational complexity in large-scale substation scenarios. Furthermore, by comprehensively considering the equipment attributes of the substation equipment, the spatial distances between voxel units and equipment to determine the initial passage state, a mapping between safety constraints and equipment risk levels and spatial locations is achieved. A stricter safety zone is formed around high-risk equipment, while a larger flight area is retained in low-risk areas. This ensures that the generated initial passage state not only meets the differentiated requirements of power safety regulations but also provides a reasonable constraint benchmark for subsequent dynamic optimization combined with inspection tasks.

[0081] According to an embodiment of this application, the method for determining a safety fence further includes: for multiple voxel units, adjusting a first risk value based on the model confidence of the device 3D model corresponding to the voxel unit to obtain an adjusted first risk value for the voxel unit; wherein, determining the initial passage state of the voxel unit based on the first risk value includes: determining the initial passage state of the voxel unit based on the adjusted first risk value.

[0082] According to embodiments of this application, for multiple voxel units in voxel space, the model confidence level of the corresponding 3D device model can be determined. This confidence level can be comprehensively determined by factors such as model source reliability, local point cloud density, registration residuals, or reconstruction accuracy, and can be used to quantify the accuracy and reliability of the 3D device model in a specific spatial region. Subsequently, the previously determined first risk value is dynamically adjusted based on the model confidence level to obtain an adjusted first risk value. The above adjustment process can follow the uncertainty adaptive principle: for regions with low model confidence, the first risk value is moderately increased to increase the safety margin and form a more conservative safety protection; for regions with high model confidence, the first risk value is maintained or moderately decreased to reduce unnecessary safety inflation and retain more usable flight space. This adjustment mechanism enables the risk value to reflect the spatial distribution differences in model data quality.

[0083] According to embodiments of this application, when determining the initial passage status, the adjusted first risk value can be used as the criterion to map voxel units to initial constraint types such as restricted entry, speed limit, buffer, or free passage according to a preset risk classification threshold. This processing method ensures that the generation of the initial passage status considers both the objective risk level determined by equipment attributes and spatial distance, and the uncertainty factors introduced by model data quality, thereby achieving a dynamic balance between security and available space that is compatible with data reliability.

[0084] Figure 4 The diagram illustrates a voxel-based passage state diagram with self-adjustment and model confidence adjustment for passable states.

[0085] According to the embodiments of this application, considering the differences in source, accuracy and registration error of multi-source 3D models, the risk value of voxel units can be evaluated using model uncertainty index. The model uncertainty index can be determined by a combination of factors such as model source reliability, local structural complexity, point cloud density or registration residual. Based on the above uncertainty index, the safety margin corresponding to the voxel unit can be dynamically calculated, as shown in Equation (5).

[0086] (5)

[0087] in, Can represent voxel units Safety margin, and These represent the minimum and maximum values ​​of the safety margin, respectively. Can represent voxel units Model uncertainty index . refer to Figure 4In the model confidence adjustment section, the first risk value obtained in the above steps can be adjusted based on the safety margin, so that the safety boundary is automatically increased in areas with high model uncertainty, and the safety inflation is correspondingly reduced in areas with high model confidence.

[0088] According to embodiments of this application, the first risk value is dynamically adjusted based on the model confidence level of the equipment's 3D model. This allows safety constraints to reflect differences in model data quality across different areas, thereby avoiding excessive encroachment on available flight space due to a uniformly conservative strategy while considering the individual 3D models of multiple equipment sources. The adjusted first risk value simultaneously considers both the equipment's objective risk level and data reliability information. The initial passage state determined accordingly can match local data quality, reducing the risk of insufficient safety protection or inspection efficiency loss caused by 3D model errors. This improves the reliability and economy of the safety fence generated in subsequent steps in engineering practice.

[0089] According to an embodiment of this application, the method for determining a safety fence further includes: upon receiving updated data of the target substation, determining a second risk value of the voxel unit based on the updated data and the distance between the voxel unit and the target substation; and determining the initial passage state of the voxel unit based on the larger of the first risk value and the second risk value.

[0090] The updated data mentioned above may include changes to the equipment model, adjustments to the operating status, inspection and renovation information, or higher-precision scan data.

[0091] After receiving updated data from the target substation, the distance between the voxel unit and the target substation is recalculated based on the updated data, and a second risk value for the voxel unit is determined based on the updated equipment attributes. This second risk value reflects the safety constraints on the surrounding space imposed by the substation in its latest state. Then, the first risk value determined based on the original data and the second risk value determined based on the updated data are fused, and the larger of the two values ​​is selected as the final risk assessment criterion for the voxel unit. This maximization fusion strategy embodies the principle of conservative safety constraints, ensuring that the risk level of the voxel unit covers the most stringent safety requirements regardless of whether the equipment is in its original or updated state, avoiding momentary loss of safety protection due to data update timing or state switching. The initial passage state of the voxel unit is determined based on the larger of the fused risk values.

[0092] To ensure the reliability and stability of safety fences during long-term operation of substations, rules can be added to each voxel unit. By managing voxel units in a structured manner, the fence generation process can be made interpretable, auditable, and maintainable.

[0093] Specifically, power safety regulations, operation and maintenance management systems, and equipment attributes can be abstracted into a set of structured rules. , Each structured rule in the system includes the semantic category of the equipment to which the rule applies, the constraints, and the corresponding security constraint level. The rule set can be configured and expanded according to different substation levels, voltage levels, or operation and maintenance strategies.

[0094] At the voxel unit level, when voxel units semantic categories When matched with the applicable conditions of structured rules, structured rules can participate in the derivation of voxel risk levels and safety constraints. To achieve traceability of fence constraints, each voxel unit can be extended to represent as follows: ;in, This represents a set of structured rules that affect voxel unit constraints, used to record the rule basis for the safety status of voxel units. Through this method, when a voxel unit is determined to be in an initial passage state such as prohibited, speed-limited, or buffered, the specific procedural clauses or operational rules corresponding to its constraint source can be clearly traced, thereby improving the interpretability of the safety fence generation process.

[0095] Furthermore, when the substation equipment layout or operation and maintenance procedures change, only the affected voxel units need to be updated, without regenerating the entire safety fence. The rule update set can be... The affected set of voxels can be represented as By comparing the first risk value of the affected voxel with the changed second risk value, the initial passage status of the affected voxel can be determined.

[0096] According to the embodiments of this application, by comparing the first risk value and the second risk value, it can be ensured that the risk assessment of the voxel unit always covers the safety requirements after the equipment status changes. This avoids the instantaneous loss of safety constraints or gaps in protection caused by equipment maintenance, modification, or model refinement, thus improving the reliability and stability of the safety fence during the long-term operation of the substation. Furthermore, by updating the risk value, it is not necessary to completely rebuild the entire substation voxel space, which reduces the consumption of computing resources and maintenance time costs in large and complex scenarios. This allows the safety fence to respond promptly to actual operation and maintenance needs such as changes in equipment ledgers and adjustments to operating modes. Incremental maintenance and continuous protection of the safety fence are achieved in scenarios with dynamic updates of equipment data.

[0097] According to embodiments of this application, the initial access state includes prohibited flight, conditionally flyable, and safe flight; based on the initial access state of each of the multiple channel voxel units, the access state is self-adjusted to obtain the target access state of each of the multiple channel voxel units, including: when the initial access state of the multiple channel voxel units is prohibited flight, adjusting the state type of the initial access state of the multiple channel voxel units to conditionally flyable to obtain the target access state of the channel voxel units; when the state type of the initial access state of the multiple channel voxel units is conditionally flyable or safe flight, the initial access state of the channel voxel units is taken as the target access state, wherein conditionally flyable indicates that the speed limit of the UAV is 2 m / s.

[0098] According to embodiments of this application, a no-fly zone corresponds to a restricted area where drones are absolutely prohibited from entering. Conditional flight permitting may include speed-limited flight and buffered flight, where drones can pass under specific conditions, such as a speed limit of 2 meters per second. Safe flight corresponds to a free passage zone where humans and drones can pass at normal speeds. During the self-adjustment process, when the initial passage state of a channel voxel unit is detected as no-fly, resulting in impaired connectivity of the inspection channel, the initial passage state of that voxel unit is forcibly adjusted to a conditionally flight permitting state, i.e., downgraded from no-entry to restricted passage, thereby restoring the connectivity of the inspection channel. Since the preset inspection channel is a preset path where drone inspection is guaranteed, the above self-adjustment does not cancel safety constraints, but rather transforms rigid prohibition into flexible restriction, allowing drones to safely pass through the original blocked area even under conditions such as reduced speed and enhanced obstacle avoidance perception.

[0099] For channel voxel units whose initial passage status is conditionally flyable or safe to fly, their original status is maintained and directly output as the target passage status. This selective adjustment mechanism ensures that only necessary areas are constrained and downgraded during the passage maintenance process, avoiding weakening of safety protection due to over-adjustment, and preserving the constraint effectiveness of the original safety fence while maintaining the passability of critical inspection paths.

[0100] According to embodiments of this application, during the self-adjustment of the voxel communicable state, the following steps can also be taken: for each voxel unit in the space where the substation is located, non-forbidden voxels can be used to form a free space voxel set. .in, Represents a set of voxel spaces, a set This represents all voxel regions accessible to the drone. Voxel adjacency relationships are constructed on this set of accessible voxels to form a free-space connected graph. Among them, the edge set This represents the spatial adjacency relationship between voxel units. When two voxels satisfy a preset adjacency relationship in three-dimensional space, such as six-adjacency, eighteen-adjacency, or twenty-six-adjacency, a corresponding edge is established in the graph. This connected graph... It can characterize the overall passable structure in voxelized space and be used to analyze the connectivity of free space after fence generation.

[0101] According to embodiments of this application, in order to determine the inspection path, it is necessary to pre-determine the equivalent safe airspace requirements for the drone. ;in, This indicates the equivalent outer dimensions of the drone. This represents the minimum safe area when the drone passes through the passage. The passage voxel unit can be determined based on the inspection path; the passage voxel unit can be represented as... .

[0102] Then, in the connected graph The above-mentioned channel voxel unit Perform connectivity testing. For any channel origin voxel... With endpoint voxel If a flight path exists And the local minimum clearance on this path satisfy If the corresponding inspection channel remains airworthy, then it can be assumed that the path remains open to air traffic; if no such path exists, or if a path exists but its local minimum clearance is less than [a certain value], then [the path is considered to be open to air traffic]. If the fence constraint results in impaired accessibility of the critical inspection passage, it will be determined that the fence constraint has caused the passage to be impaired.

[0103] When a flyability impairment is detected in a critical inspection channel, the target channel voxel unit causing the impairment can be identified. The target channel voxel is defined as shown in equation (6).

[0104] } (6)

[0105] in, This represents the set of potential passage paths in the passage area. For the target passage voxel unit, its passability state can be self-adjusted, and the adjusted target passability state diagram is shown in (7).

[0106] (7)

[0107] in, Voxel representation The adjusted target traffic status This can indicate the priority of the corresponding inspection channel. This indicates the channel priority threshold. Through the aforementioned self-adjustment mechanism, under the premise of meeting the basic requirements of safety procedures, some speed-up units that cause critical channel blockages are adjusted to speed-limiting voxels or buffer voxels, thereby restoring the spatial connectivity of critical inspection channels and avoiding damage to the original passable inspection paths during voxelization and fence generation.

[0108] refer to Figure 4 After self-adjustment, the originally blocked connectivity becomes passable, allowing the UAV to complete its inspection mission. Furthermore, connectivity verification can be performed on the self-adjustment results. Specifically, after constraint adjustment, the channel voxel unit set is reconstructed based on the updated target passability. And re-establish the updated free-space connected graph. Further verification is needed to determine whether the critical inspection channels have been restored to connectivity. For any critical channel starting voxel... With endpoint voxel If satisfied ,and , The updated flight path indicates that the corresponding passage has been restored to flyable connectivity after fence optimization. Through the above flyable connectivity detection, self-adjustment, and flyable connectivity verification, the actual passable structure of key inspection passages can be maintained while ensuring safety constraints.

[0109] According to embodiments of this application, the initial prohibited-flight state of a channel voxel unit is selectively adjusted to conditionally flyable, restoring channel connectivity without removing safety constraints. This allows the drone to safely pass through the original blocked area in a restricted manner, avoiding the predicament of inspection path interruption or mission failure due to overly conservative safety expansion. Furthermore, this self-adjusting mechanism limits the state adjustment to only channel voxel units initially prohibited from flight, maintaining the original state for voxels with conditionally flyable or safe flight conditions, ensuring the accuracy and necessity of constraint degradation. This improves the practicality and mission success rate of voxel-based safety fences in substation drone inspection projects.

[0110] According to an embodiment of this application, multiple channel voxel units are divided into fence boundaries based on multiple target passage states to determine a multi-layer safety fence corresponding to the inspection task, including: dividing multiple channel voxel units into multiple voxel sets based on the state type to which the target passage states belong; and determining a multi-layer safety fence corresponding to the inspection task based on the area boundaries of the spatial regions corresponding to each of the multiple voxel sets.

[0111] According to embodiments of this application, voxel units with the same target passage status are spatially clustered into multiple voxel sets. Voxels within the same set are adjacent to each other in three-dimensional space, forming continuous regions with clearly defined spatial boundaries. Different sets correspond to different security constraint levels. The extracted boundaries of these multiple regions can then be defined as multi-layered safety fences corresponding to the inspection task. Each fence layer exhibits a gradient distribution from the inside out: the innermost layer is a no-fly fence, corresponding to an absolutely prohibited area; the middle layer is a conditionally permitted fly fence, corresponding to speed-limited or buffer-restricted areas; and the outermost layer is a safe fly fence, corresponding to a free-passage area. (Reference) Figure 4 The first layer of safety fencing can be the safety fencing between the no-fly zone buffer zone and the second layer of safety fencing can be the safety fencing between the buffer zone and the free passage zone. Correspondingly, there can also be a safety fencing between the buffer zone and the speed limit zone.

[0112] According to embodiments of this application, voxel sets are partitioned and region boundaries are extracted based on the target traffic status. This transforms the safety constraints, originally based on discrete voxels, into a continuous fence surface with clear geometric boundaries, facilitating direct integration with collision detection, path planning, and real-time obstacle avoidance algorithms of UAV flight control systems. Furthermore, this layered fence structure possesses clear semantic components and a visualized spatial hierarchy, enabling maintenance personnel to review fence rationality, identify conflict areas, and make dynamic adjustment decisions, thereby improving the interpretability and maintainability of safety fences in power production management.

[0113] Figure 5 A block diagram of a security fence determination device according to an embodiment of this application is shown schematically.

[0114] like Figure 5 As shown, the safety fence determining device 500 includes an acquisition module 510, a determining module 520, an adjustment module 530, and a dividing module 540.

[0115] The acquisition module 510 is used to receive the inspection task and obtain the inspection path from the task data of the inspection task, wherein the inspection task represents the task of the UAV to inspect the target substation.

[0116] The determination module 520 is used to determine multiple channel voxel units in the voxel space of the target substation's three-dimensional model, based on the spatial region corresponding to the inspection path.

[0117] The adjustment module 530 is used to self-adjust the passable state based on the initial passable state of each of the multiple channel voxel units, so as to obtain the target passable state of each of the multiple channel voxel units.

[0118] The partitioning module 540 is used to partition the fence boundaries of multiple channel voxel units according to the passage status of multiple targets, and determine the multi-layer safety fence corresponding to the inspection task; different safety fences in the multi-layer safety fence correspond to different upper limits of UAV movement speed.

[0119] Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be at least partially implemented as hardware circuits, such as field-programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems-on-a-chip, systems-on-a-substrate, systems-on-package, application-specific integrated circuits (ASICs), or implemented by hardware or firmware in any other reasonable manner by integrating or packaging circuits, or implemented in any one of software, hardware, and firmware, or in a suitable combination of any of these. Alternatively, one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0120] For example, any plurality of the acquisition module 510, determination module 520, adjustment module 530, and partitioning module 540 can be combined into one module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits can be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of this application, at least one of the acquisition module 510, determination module 520, adjustment module 530, and partitioning module 540 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the acquisition module 510, determination module 520, adjustment module 530 and division module 540 may be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0121] It should be noted that the data processing system part in the embodiments of this application corresponds to the data processing method part in the embodiments of this application. The specific description of the data processing system part is referred to in the data processing method part, and will not be repeated here.

[0122] Figure 6 A block diagram of an electronic device suitable for implementing the methods described above, according to an embodiment of this application, is illustrated schematically. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0123] like Figure 6 As shown, an electronic device 600 according to an embodiment of this application includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0124] RAM 603 stores various programs and data required for the operation of electronic device 600. Processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Processor 601 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0125] According to embodiments of this application, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to a bus 604. The electronic device 600 may also include one or more of the following components connected to the input / output (I / O) interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 610 as needed so that computer programs read from it can be installed into the storage section 608 as needed.

[0126] According to embodiments of this application, the method flow according to embodiments of this application can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by processor 601, it performs the functions defined in the system of embodiments of this application. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0127] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0128] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0129] For example, according to embodiments of this application, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0130] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this application. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the method for determining a security fence provided in the embodiments of this application.

[0131] When the computer program is executed by the processor 601, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0132] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and / or installed from the removable medium 611. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0133] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0134] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations are not explicitly described in this application. In particular, without departing from the spirit and teachings of this application, the features described in the various embodiments of this application can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of this application.

[0135] The embodiments of this application have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of this application. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Without departing from the scope of this application, those skilled in the art can make various substitutions and modifications, all of which should fall within the scope of this application.

Claims

1. A method of determining a secure enclosure, characterized by, include: In response to receiving an inspection task, the inspection path is obtained from the task data of the inspection task, wherein the inspection task represents the task of the UAV to inspect the target substation. Based on the spatial region corresponding to the inspection path, multiple channel voxel units are determined in the voxel space of the three-dimensional model of the target substation. Based on the initial passage states of each of the multiple channel voxel units, the passable state is self-adjusted to obtain the target passage states of each of the multiple channel voxel units. Based on the multiple target passage states, multiple channel voxel units are divided into fence boundaries to determine multi-layer safety fences corresponding to the inspection task; different safety fences in the multi-layer safety fences correspond to different upper limits of UAV movement speed.

2. The method for determining a safety fence according to claim 1, characterized in that, The determination method further includes: Obtain a 3D model of the target substation; the 3D model of the substation consists of 3D models of multiple power equipment in the target substation; The spatial region where the three-dimensional model of the substation is located is voxelized to obtain voxel space; For multiple voxel units in the voxel space, the initial passage state of the voxel unit is determined based on the equipment attributes of each of the substations and the distance between the voxel unit and each of the substations.

3. The method for determining a safety fence according to claim 2, characterized in that, For multiple voxel units in the voxel space, determining the initial passage state of the voxel unit based on the device attributes and the distances between the voxel unit and the various power equipment includes: Based on the equipment attributes of the substation, multiple initial risk values ​​are determined according to the distances between the voxel units in the space where the substation is located and the respective substations. A first risk value for the voxel unit is determined from a plurality of initial risk values; The initial passage state of the voxel unit is determined based on the first risk value.

4. The method for determining a safety fence according to claim 3, characterized in that, The determination method further includes: For multiple voxel units, the first risk value is adjusted according to the model confidence of the device 3D model corresponding to the voxel unit to obtain the adjusted first risk value of the voxel unit. The step of determining the initial passage state of the voxel unit based on the first risk value includes: The initial passage state of the voxel unit is determined based on the adjusted first risk value.

5. The method for determining a safety fence according to claim 3, characterized in that, The determination method further includes: Upon receiving updated data from the target substation, a second risk value for the voxel unit is determined based on the updated data and the distance between the voxel unit and the target substation. The initial passage state of the voxel unit is determined based on the larger of the first risk value and the second risk value.

6. The method for determining a safety fence according to claim 2, characterized in that, The process of obtaining the three-dimensional model of the target substation and the equipment attributes of the various power equipment included in the target substation includes: Obtain the 3D models and equipment attributes of each of the multiple power equipment contained in the target substation; Based on the layout of the power equipment in the target substation, the three-dimensional models of each of the multiple power equipment are spatially aligned in the substation coordinate system to obtain the three-dimensional model of the target substation.

7. The method for determining a safety fence according to claim 2, characterized in that, The initial passage status includes no flight, conditional flight, and safe flight; The self-adjustment of the passable state based on the initial passable state of each of the multiple channel voxel units to obtain the target passable state of each of the multiple channel voxel units includes: When the initial passage state of multiple channel voxel units is prohibited from flying, the state type of the initial passage state of multiple channel voxel units is adjusted to conditionally flyable, thereby obtaining the target passage state of the channel voxel units. If the initial passage state of multiple channel voxel units belongs to the state type of conditionally flyable or safe flight, the initial passage state of the channel voxel unit is taken as the target passage state. The conditionally flyable drone has a maximum speed of 2 meters per second.

8. The method for determining a safety fence according to claim 7, characterized in that, The step of dividing multiple channel voxel units into fence boundaries based on multiple target passage states to determine a multi-layered safety fence corresponding to the inspection task includes: Based on the state type to which the target passage state belongs, multiple channel voxel units are divided into multiple voxel sets; Based on the regional boundaries of the spatial regions corresponding to each of the multiple voxel sets, a multi-layered safety fence corresponding to the inspection task is determined.

9. A device for determining a safety fence, characterized in that, include: The acquisition module is used to obtain the inspection path from the task data of the inspection task in response to receiving the inspection task, wherein the inspection task represents the task of the UAV to inspect the target substation. The determination module is used to determine multiple channel voxel units in the voxel space of the three-dimensional model of the target substation based on the spatial region corresponding to the inspection path. An adjustment module is configured to self-adjust the passability state based on the initial passability state of each of the multiple channel voxel units, thereby obtaining the target passability state of each of the multiple channel voxel units; and The partitioning module is used to partition the boundaries of multiple channel voxel units according to the multiple target passage states, and determine the multi-layer safety fence corresponding to the inspection task; different safety fences in the multi-layer safety fence correspond to different upper limits of UAV movement speed.

10. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 8.

Images