A substation vehicle operation scheme verification method and device

By combining 3D point cloud models and parametric models, the spatial distance between vehicles and equipment is calculated in real time, risk points are automatically marked, and verification reports are generated. This solves the accuracy and efficiency problems of vehicle maintenance plans in substations, and achieves efficient risk prediction and plan optimization.

CN122490790APending Publication Date: 2026-07-31HUBEI CENT CHINA TECH DEV OF ELECTRIC POWER
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HUBEI CENT CHINA TECH DEV OF ELECTRIC POWER
Filing Date
2026-04-30
Publication Date
2026-07-31

AI Technical Summary

Technical Problem

In existing technologies, the preparation of substation vehicle maintenance plans relies on manual surveys and visual inspections, which results in limited accuracy of distance data between vehicles and energized equipment, making it impossible to effectively conduct pre-tests and verifications, and making it difficult to detect risks of proximity to electricity or collisions in advance, thus leading to low verification efficiency.

Method used

By acquiring a 3D point cloud model of the substation, individual power equipment is modeled, and combined with a 3D parametric model of the target vehicle, the spatial distance between the vehicle and the equipment is calculated in real time, risk points are automatically marked, and a visualized solution verification report is generated.

Benefits of technology

It has enabled the digital preparation and dynamic simulation verification of substation maintenance plans, significantly reducing the risks of proximity to electricity and collisions, improving the efficiency and accuracy of plan preparation, and ensuring operational safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122490790A_ABST
    Figure CN122490790A_ABST
Patent Text Reader

Abstract

A method and apparatus for verifying substation vehicle operation schemes are disclosed, relating to the field of substation scheme verification. The method includes: acquiring a 3D point cloud model of the substation to obtain individual equipment models; constructing a 3D parametric model of the target vehicle; obtaining maintenance scheme data from the 3D point cloud model based on the individual equipment models and the 3D parametric model; inputting the maintenance scheme data into a vehicle kinematics simulation engine to drive the 3D parametric model in simulated motion and calculating the spatial distance between the vehicle's spatial coordinates and the individual equipment models in real time; when the spatial distance is less than the safety distance threshold corresponding to the voltage level, marking risk points and recording risk information in the 3D point cloud model; generating a scheme verification report based on the risk points and risk information, and displaying the scheme verification report to the user. Implementing the technical solution provided in this application can solve the problem of low verification efficiency for the rationality of substation maintenance schemes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of power plant scheme verification, specifically to a method and apparatus for verifying vehicle operation schemes in substations. Background Technology

[0002] In power substations, specialized vehicles such as cranes and aerial work platforms are frequently used for equipment inspection, installation, and maintenance. When these vehicles operate near energized equipment, they must maintain a prescribed safe distance from live conductors; otherwise, it can easily lead to equipment discharge tripping or even personal injury accidents. Therefore, a detailed maintenance plan must be prepared before work begins, clearly defining the vehicle's travel route, parking location, and boom's range of motion to ensure operational safety.

[0003] Currently, maintenance plans are mainly developed through manual on-site surveys and written records. The distance data between vehicles and energized equipment in these plans are often based on visual inspection or simple measurements, resulting in limited accuracy. Furthermore, once the plans are finalized, effective pre-testing and verification are not possible, making it difficult to detect potential risks of near-electricity or collisions during vehicle movement or boom extension. This traditional approach, relying on experience and static drawings, leads to low efficiency in verifying the rationality of substation maintenance plans.

[0004] Therefore, there is an urgent need for a method and device for verifying substation vehicle operation schemes. Summary of the Invention

[0005] This application provides a method and apparatus for verifying substation vehicle operation schemes, which solves the problem of low verification efficiency for the rationality of substation maintenance schemes.

[0006] This application provides a method for verifying a vehicle operation plan in a substation in its first aspect. The method includes: acquiring a three-dimensional point cloud model of the substation, and performing individual modeling of the power equipment in the three-dimensional point cloud model to obtain individual equipment models, each carrying equipment identification, voltage level, and energized status label; acquiring the structural parameters and kinematic parameters of the target vehicle, constructing a three-dimensional parametric model of the target vehicle, and determining the local coordinates of vehicle parts in the three-dimensional parametric model according to preset part extraction rules; and acquiring maintenance plan data in the three-dimensional point cloud model based on the individual equipment models and the three-dimensional parametric model, the maintenance plan data including the target vehicle's travel path, parking position, boom movement... The system generates a sequence and establishes the spatial coordinates of vehicle parts. These coordinates are obtained by transforming the local coordinates of the vehicle parts into a coordinate system within the 3D point cloud model. The maintenance plan data is then input into the vehicle kinematics simulation engine, driving the 3D parametric model to simulate motion within the 3D point cloud model according to the maintenance plan data. The system also calculates the spatial distance between the vehicle parts and the individual equipment models in real time. When the spatial distance is less than the safety distance threshold corresponding to the voltage level, risk points are marked and risk information is recorded in the 3D point cloud model. This risk information includes the current time point, the spatial coordinates of the risk point, and the equipment identifier. Based on the risk points and risk information, a solution verification report is generated and displayed to the user.

[0007] By adopting the above technical solution, a high-precision operation scenario and vehicle model were established in a virtual environment. Based on this, maintenance plan data was acquired, driving a 3D parametric model to simulate movement within a 3D point cloud model according to the plan. The spatial distance between key vehicle components and individual equipment models was calculated in real time, risk points were automatically marked and detailed information was recorded, ultimately generating a visualized plan verification report for the user. Compared to traditional plan preparation methods relying on manual surveys, visual estimations, and static drawings, this method achieves digital preparation and dynamic simulation verification of maintenance plans, transforming plan rationality assessment from post-event discovery to pre-event verification. This significantly reduces the risks of near-electrical hazards and collisions during on-site operations, while simultaneously improving the efficiency and accuracy of plan preparation.

[0008] Optionally, a 3D point cloud model of the substation is acquired, and individual power equipment in the 3D point cloud model is modeled to obtain individual equipment models. Specifically, this includes: acquiring global point cloud data of the substation, performing denoising, registration, and segmentation processing on the global point cloud data to construct a 3D point cloud model; extracting point cloud clusters corresponding to the power equipment from the 3D point cloud model, and establishing individual equipment models based on the point cloud clusters. The individual equipment models include the 3D geometry of the power equipment and the spatial coordinates of the equipment; and in response to user configuration operations, associating equipment identifiers, voltage levels, and energized status labels with the individual equipment models.

[0009] By employing the above technical solution, point cloud clusters of power equipment are extracted from global point cloud data, and individual equipment models containing three-dimensional geometry and spatial coordinates are established. This allows users to configure equipment identifiers, voltage levels, and energized status labels. This solution achieves digital modeling of the substation environment and association of equipment attributes, providing accurate spatial references and semantic information for subsequent safety distance calculations.

[0010] Optionally, according to preset part extraction rules, the local coordinates of the vehicle parts are determined in the three-dimensional parametric model. Specifically, this includes: parsing the component hierarchy of the three-dimensional parametric model, and obtaining the local coordinates of the vehicle parts in the three-dimensional parametric model coordinate system of the target vehicle's body box vertices, the centers of each rotation joint of the boom, and the center of the boom end effector according to preset part extraction rules.

[0011] By employing the above technical solution, and through analyzing the component hierarchy of the 3D parametric model, the local coordinates of key components such as the vehicle's body box vertices, the center of the boom rotation joint, and the center of the end effector are automatically extracted in the model coordinate system. This solution eliminates the need for manual annotation, providing accurate input for spatial distance calculations by obtaining the coordinates of the parts of the vehicle most likely to be near electrical equipment.

[0012] Optionally, in the 3D point cloud model, maintenance plan data is obtained based on the individual equipment model and the 3D parametric model. Specifically, this includes: generating a travel path composed of a sequence of spatial coordinate points in response to the user's path drawing operation in the 3D point cloud model; determining the spatial coordinate point selected by the user as the parking position in response to the user's parking point selection operation in the 3D point cloud model; generating a boom action sequence based on the boom pitch angle, horizontal rotation angle, and extension length sequence set by the user in response to the user's boom attitude adjustment operation in the 3D parametric model; obtaining the spatial transformation matrix between the coordinate system of the 3D parametric model and the coordinate system of the 3D point cloud model, and multiplying the local coordinates of the vehicle part by the spatial transformation matrix to obtain the spatial coordinates of the vehicle part.

[0013] By adopting the above technical solution, users can generate travel paths, parking positions, and boom motion sequences through interactive operations in a 3D point cloud model, and convert the local coordinates of vehicle parts into global spatial coordinates using coordinate system transformation. This solution organically combines the user's scheme design intention with the 3D scene, ensuring both the flexibility of scheme design and the consistency of data in subsequent simulation calculations.

[0014] Optionally, the spatial distance between the spatial coordinates of the vehicle parts and the individual equipment model is calculated in real time. Specifically, this includes: during the simulation motion, acquiring the spatial coordinates of the vehicle parts at a preset frequency. The vehicle parts corresponding to the spatial coordinates include at least one of the following: the apex of the body box, the center of each rotation joint of the boom, and the center of the end effector of the boom; calculating the Euclidean distance between the spatial coordinates of each vehicle part and the surface of the individual equipment model, and selecting the minimum value as the spatial distance.

[0015] By employing the above technical solution, the spatial coordinates of vehicle parts are acquired at a preset frequency during the simulated motion. The Euclidean distance between each coordinate and the surface of the individual equipment model is calculated, and the minimum value is taken as the spatial distance. This solution, through multi-part, high-frequency, and precise distance calculations, can accurately capture the minimum distance between the vehicle and the energized equipment at any moment during operation, providing reliable data support for risk assessment.

[0016] Optionally, when determining that the spatial distance is less than the safety distance threshold corresponding to the voltage level, before marking the risk point and recording the risk information in the 3D point cloud model, the method further includes: matching the reference distance threshold corresponding to the voltage level from a preset safety distance rule library, wherein the preset safety distance rule library contains at least the reference distance thresholds corresponding to 10kV, 110kV, and 220kV voltages respectively; determining whether the current energized status label of the individual equipment model is energized; if the energized status label is energized, then the reference distance threshold is corrected using a first preset correction value to obtain the safety distance threshold; if the energized status label is not energized, then the reference distance threshold is corrected using a second preset correction value to obtain the safety distance threshold.

[0017] By adopting the above technical solution, a baseline distance threshold is matched from the rule base based on the equipment voltage level, and different correction values ​​are applied according to the equipment's energized status label to obtain the final safe distance threshold. This solution achieves dynamic adaptation of the safe distance: a larger proximity safety threshold is used for energized equipment, and a smaller anti-collision threshold is used for non-energized equipment, which ensures the safety of working near electricity while avoiding unnecessary false alarms.

[0018] Optionally, after generating a scheme verification report based on risk points and risk information, the method further includes: responding to the user's modification operation on the maintenance scheme data, inputting the re-acquired maintenance scheme data into the vehicle kinematics simulation engine to determine whether any risk points have been marked; when no risk points have been marked, outputting the re-acquired maintenance scheme data as an executable power plant maintenance scheme, constructing the correspondence between the power plant maintenance scheme, the 3D point cloud model, and the 3D parametric model, and storing it in the experience base.

[0019] By adopting the above technical solution, users can modify the maintenance plan data based on the verification report and re-simulate until there are no risk points, at which point an executable solution is output. Simultaneously, the solution and the 3D model are linked and stored in an experience database. This ensures the reliability of the final solution while also enabling the accumulation and reuse of experience from successful solutions.

[0020] In a second aspect, this application provides a substation vehicle operation scheme verification device, the device including an acquisition unit and a processing unit;

[0021] The acquisition unit is used to acquire the three-dimensional point cloud model of the substation and perform individual modeling of the power equipment in the three-dimensional point cloud model to obtain individual equipment models. The individual equipment models carry equipment identification, voltage level and energized status labels. It is also used to acquire the structural parameters and kinematic parameters of the target vehicle, construct the three-dimensional parametric model of the target vehicle, and determine the local coordinates of the vehicle parts in the three-dimensional parametric model according to the preset part extraction rules.

[0022] The processing unit is used to acquire maintenance plan data in the 3D point cloud model based on the equipment unit model and the 3D parametric model. The maintenance plan data includes the target vehicle's travel path, parking position, boom movement sequence, and vehicle part spatial coordinates. The vehicle part spatial coordinates are obtained by transforming the local coordinates of the vehicle part in the 3D point cloud model. It is also used to input the maintenance plan data into the vehicle kinematics simulation engine, driving the 3D parametric model to simulate motion in the 3D point cloud model according to the maintenance plan data, and to calculate the spatial distance between the vehicle part spatial coordinates and the equipment unit model in real time. Furthermore, when the spatial distance is less than the safety distance threshold corresponding to the voltage level, it marks risk points and records risk information in the 3D point cloud model, including the current time point, the risk point's spatial coordinates, and the equipment identifier. Finally, it generates a plan verification report based on the risk points and risk information, and displays the plan verification report to the user.

[0023] Optionally, the acquisition unit is used to acquire the full-domain point cloud data of the substation, perform denoising, registration and segmentation processing on the full-domain point cloud data, and construct a three-dimensional point cloud model; the processing unit is used to extract the point cloud clusters corresponding to the power equipment from the three-dimensional point cloud model, establish a single equipment model based on the point cloud clusters, and the single equipment model includes the three-dimensional geometry of the power equipment and the spatial coordinates of the equipment; it is also used to respond to the user's configuration operation and associate the equipment identifier, voltage level and energized status label with the single equipment model.

[0024] Optionally, the processing unit is used to parse the component hierarchy of the three-dimensional parametric model and obtain the local coordinates of the vehicle parts in the three-dimensional parametric model coordinate system, including the vertices of the vehicle body box, the centers of each rotation joint of the boom, and the center of the end effector of the boom, according to preset part extraction rules.

[0025] Optionally, the processing unit is used to generate a travel path composed of a sequence of spatial coordinate points in response to the user's path drawing operation in the 3D point cloud model; to determine the spatial coordinate point selected by the user as the parking position in response to the user's parking point selection operation in the 3D point cloud model; to generate a boom action sequence based on the boom pitch angle, horizontal rotation angle and extension length sequence set by the user in response to the user's boom attitude adjustment operation on the 3D parametric model; and to obtain the spatial transformation matrix between the coordinate system of the 3D parametric model and the coordinate system of the 3D point cloud model, and multiply the local coordinates of the vehicle part by the spatial transformation matrix to obtain the spatial coordinates of the vehicle part.

[0026] Optionally, the processing unit is used to acquire the spatial coordinates of vehicle parts at a preset frequency during the simulation motion. The vehicle parts corresponding to the spatial coordinates include at least one of the top of the body box, the center of each rotation joint of the boom, and the center of the end effector of the boom. The processing unit calculates the Euclidean distance between the spatial coordinates of each vehicle part and the surface of the device unit model, and selects the minimum value as the spatial distance.

[0027] Optionally, the processing unit is used to match the reference distance threshold corresponding to the voltage level from a preset safety distance rule library. The preset safety distance rule library includes at least the reference distance thresholds corresponding to 10kV, 110kV, and 220kV voltages, respectively. It then determines whether the current energized status label of the individual device model is energized. If the energized status label is energized, the reference distance threshold is corrected using a first preset correction value to obtain the safety distance threshold. If the energized status label is not energized, the reference distance threshold is corrected using a second preset correction value to obtain the safety distance threshold.

[0028] Optionally, the processing unit is used to respond to the user's modification operation on the maintenance plan data, input the re-acquired maintenance plan data into the vehicle kinematics simulation engine, and determine whether any risk points have been marked; when no risk points have been marked, the re-acquired maintenance plan data is output as an executable power plant maintenance plan, and the correspondence between the power plant maintenance plan, the 3D point cloud model and the 3D parametric model is constructed and stored in the experience base.

[0029] In a third aspect, this application provides an electronic device including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the first aspect or any possible implementation of the first aspect.

[0030] In a fourth aspect, this application provides a computer-readable storage medium storing a computer program, which is executed by a processor as described in the first aspect or any possible implementation thereof.

[0031] In summary, one or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. A high-precision work scenario and vehicle model were established in a virtual environment. Based on this, maintenance plan data was acquired, and a 3D parametric model was driven to simulate the movement of the plan within a 3D point cloud model. The spatial distance between key vehicle components and individual equipment models was calculated in real time, risk points were automatically marked and detailed information was recorded, and a visualized plan verification report was generated and presented to the user. Compared to traditional plan preparation methods that rely on manual surveys, visual estimations, and static drawings, this method achieves digital preparation and dynamic simulation verification of maintenance plans, transforming plan rationality assessment from post-event discovery to pre-event verification. This significantly reduces the risks of near-electrical hazards and collisions during on-site operations, while improving the efficiency and accuracy of plan preparation.

[0032] 2. By analyzing the component hierarchy of the 3D parametric model, the local coordinates of key components such as the vehicle's body box vertices, the center of the boom rotation joint, and the center of the end effector are automatically extracted in the model coordinate system. This method eliminates the need for manual annotation and obtains the coordinates of the parts of the vehicle most likely to be near electrical equipment, providing accurate input for spatial distance calculations.

[0033] 3. Based on the equipment voltage level, a baseline distance threshold is matched from the rule base, and different correction values ​​are applied according to the equipment's energized status label to obtain the final safe distance threshold. This scheme achieves dynamic adaptation of the safe distance: a larger proximity safety threshold is used for energized equipment, and a smaller anti-collision threshold is used for non-energized equipment, which ensures the safety of working near electricity while avoiding unnecessary false alarms. Attached Figure Description

[0034] Figure 1 This is a flowchart illustrating a method for verifying a substation vehicle operation scheme provided in an embodiment of this application.

[0035] Figure 2 This is a schematic diagram of the structure of a substation vehicle operation scheme verification device provided in an embodiment of this application.

[0036] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0037] Explanation of reference numerals in the attached drawings: 201, acquisition unit; 202, processing unit; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Implementation

[0038] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0039] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0040] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0041] The preparation of maintenance plans mainly relies on manual on-site surveys and written records. The distance data between vehicles and energized equipment in the plans are mostly based on visual inspection or simple measurements, which have limited accuracy. Moreover, after the plans are formulated, effective pre-run verification is not possible, making it difficult to detect potential risks of near-electricity or collisions during vehicle movement or boom extension. This traditional method, which relies on experience and static drawings, results in low efficiency in verifying the rationality of substation maintenance plans. Therefore, this embodiment provides a method and device for verifying substation vehicle operation plans.

[0042] The substation vehicle operation scheme verification method provided in this application can be referenced. Figure 1 , Figure 1 This is a flowchart illustrating a method for verifying a substation vehicle operation plan, provided in an embodiment of this application, and applied to a server. The method includes steps S101 to S106.

[0043] S101. Obtain the three-dimensional point cloud model of the substation, and perform individual modeling of the power equipment in the three-dimensional point cloud model to obtain individual equipment models. The individual equipment models carry equipment identification, voltage level and energized status labels.

[0044] In the above steps, the server first acquires 3D point cloud data of the substation, which can be obtained through UAV oblique photography or ground laser scanning. The server performs denoising, registration, and segmentation processing on the raw point cloud data to construct a high-precision 3D point cloud model. Then, the server extracts the point cloud clusters corresponding to each power device from the 3D point cloud model and establishes an independent individual model for each point cloud cluster, namely, the device individual model. Each device individual model not only contains the device's 3D geometry and spatial coordinate information, but is also assigned a device identifier, voltage level, and energized status label through association operations. For example, the server labels a 220kV circuit breaker individual model as "Circuit Breaker_220kV", with a voltage level of 220kV and an energized status label of "energized", thus providing a basis for subsequent safety distance calculations.

[0045] In one possible implementation, a three-dimensional point cloud model of the substation is acquired, and individual power equipment in the three-dimensional point cloud model is modeled to obtain individual equipment models. Specifically, this includes: acquiring global point cloud data of the substation, performing denoising, registration, and segmentation processing on the global point cloud data to construct a three-dimensional point cloud model; extracting point cloud clusters corresponding to the power equipment from the three-dimensional point cloud model, and establishing individual equipment models based on the point cloud clusters. The individual equipment models include the three-dimensional geometry of the power equipment and the spatial coordinates of the equipment; and in response to user configuration operations, associating equipment identifiers, voltage levels, and energized status labels with the individual equipment models.

[0046] Specifically, the server first acquires raw point cloud data of the entire substation area, denoises the data to remove outliers and noise, aligns the point clouds scanned from multiple stations to a unified coordinate system using a registration algorithm, and then divides the point cloud into different equipment instances using a segmentation algorithm based on Euclidean clustering or region growing. For each segmented equipment point cloud cluster, the server triangulates it to generate a single-unit model containing the equipment's three-dimensional geometry and spatial coordinates. Finally, users can manually configure equipment identification, voltage level, and energized status labels for each single-unit model based on the actual ledger information of the substation. For example, if a user clicks on a single-unit model and enters "No. 1 Main Transformer_110kV" in the pop-up dialog box, selects "110kV" for the voltage level, and selects "Energized" for the energized status, the server will associate this information with the single-unit model.

[0047] S102. Obtain the structural and kinematic parameters of the target vehicle, construct a three-dimensional parametric model of the target vehicle, and determine the local coordinates of the vehicle parts in the three-dimensional parametric model according to the preset part extraction rules.

[0048] In the above steps, the server receives user input or reads the structural parameters of the target vehicle from the database, including vehicle length, width, height, wheelbase, number of boom sections and length of each section, boom pitch and rotation angle range, and kinematic parameters, such as motion constraints and transmission ratios of each joint. Based on these parameters, the server constructs a 3D parametric model of the vehicle, which reflects the vehicle's geometry and joint positions in different postures. Subsequently, the server automatically parses the component hierarchy of the 3D parametric model according to preset part extraction rules, and calculates the local coordinates of key parts of the vehicle in the model's own coordinate system. These key parts include the eight vertices of the body box, the centers of the rotational joints between each boom section, and the tool center point of the boom end effector.

[0049] In one possible implementation, the local coordinates of the vehicle parts are determined in the three-dimensional parametric model according to preset part extraction rules. Specifically, this includes: parsing the component hierarchy of the three-dimensional parametric model, and obtaining the local coordinates of the vehicle parts in the three-dimensional parametric model coordinate system of the target vehicle's body box vertices, the centers of each rotation joint of the boom, and the center of the boom end effector according to preset part extraction rules.

[0050] Specifically, the server parses the component hierarchy of the 3D parametric model. This structure records the parent-child relationships and relative positions between components such as the body, boom sections, rotary joints, and end effectors in a tree-like manner. Based on preset part extraction rules, the server automatically traverses the component tree: for body components, the server calculates the coordinates of the eight vertices of their bounding box; for rotary joint components, the server reads the coordinates of their center point in the model's local coordinate system; for end effector components, the server reads the coordinates of their tool center point. These coordinate values ​​constitute the local coordinates of the vehicle parts. For example, the server calculates the vertex coordinates of a crane's body bounding box as (±2.5, ±1.8, ±0.5), the center coordinates of the boom rotary joint as (0, 0, 1.2), and the center point of the boom end effector as (0, 0, 6.0).

[0051] S103. In the three-dimensional point cloud model, maintenance plan data is obtained based on the equipment unit model and the three-dimensional parametric model. The maintenance plan data includes the target vehicle's travel path, parking position, boom action sequence, and vehicle part spatial coordinates. The vehicle part spatial coordinates are obtained by performing coordinate system transformation on the local coordinates of the vehicle part in the three-dimensional point cloud model.

[0052] In the above steps, the server provides an interactive interface within the 3D point cloud model scene. Users can draw the vehicle's travel path from the entrance to the work point using a mouse or touchscreen, select the vehicle's parking position, and set the boom's pitch, rotation, and extension / retraction sequence. The server generates the travel path, parking position, and boom movement sequence based on these user actions. Simultaneously, the server calculates the spatial transformation matrix between the 3D parametric model coordinate system and the 3D point cloud model coordinate system. This matrix includes rotation and translation components. The server multiplies the obtained local coordinates of the vehicle parts by this transformation matrix to obtain the spatial coordinates of the vehicle parts in the global coordinate system of the 3D point cloud model. The travel path, parking position, boom movement sequence, and the transformed spatial coordinates of the vehicle parts together constitute the maintenance plan data.

[0053] In one possible implementation, maintenance plan data is obtained in the 3D point cloud model based on the individual equipment model and the 3D parametric model. Specifically, this includes: generating a travel path composed of a sequence of spatial coordinate points in response to the user's path drawing operation in the 3D point cloud model; determining the spatial coordinate point selected by the user as the parking position in response to the user's parking point selection operation in the 3D point cloud model; generating a boom action sequence based on the boom pitch angle, horizontal rotation angle, and extension length sequence set by the user in response to the user's boom attitude adjustment operation in the 3D parametric model; obtaining the spatial transformation matrix between the coordinate system of the 3D parametric model and the coordinate system of the 3D point cloud model, and multiplying the local coordinates of the vehicle part by the spatial transformation matrix to obtain the spatial coordinates of the vehicle part.

[0054] Specifically, in a 3D point cloud model scene, the user clicks on multiple spatial points sequentially with the mouse. The server connects these points in order to form a smooth curve, which serves as the vehicle's travel path. When the user clicks on a location in the scene, the server determines the vehicle's parking position based on the spatial coordinates of that point. The user adjusts the boom's pitch angle, horizontal rotation angle, and extension length using a virtual joystick or slider. The server records the adjustment values ​​at each moment, forming a boom motion sequence. Simultaneously, the server calculates the transformation matrix from the 3D parametric model coordinate system to the 3D point cloud model coordinate system. This matrix includes rotation and translation components. Multiplying the previously determined local coordinates of the vehicle part by this matrix yields the vehicle's spatial coordinates in the global scene. For example, if the local coordinates are (1, 0, 0), and the transformation matrix includes a 90-degree rotation around the Z-axis and a translation of (10, 20, 0), the transformed spatial coordinates are (10, 21, 0).

[0055] S104. Input the maintenance plan data into the vehicle kinematics simulation engine, drive the three-dimensional parametric model to perform simulation motion in the three-dimensional point cloud model according to the maintenance plan data, and calculate the spatial distance between the spatial coordinates of the vehicle parts and the individual equipment models in real time.

[0056] In the above steps, the server inputs the travel path, parking position, and boom movement sequence from the maintenance plan data into the built-in vehicle kinematics simulation engine. The simulation engine drives the 3D parametric model to move the vehicle, rotate the boom, and extend / retract the boom sections within the 3D point cloud model in chronological order, completely simulating the operation process. Simultaneously with the motion simulation, the server acquires the current spatial coordinates of each vehicle component at a preset frequency and calculates the shortest Euclidean distance between each coordinate point and the surfaces of all individual equipment models. The preset frequency can be set according to user requirements. For line segments between boom joints, the server also calculates the shortest distance from the line segment to the surface of the equipment model. Finally, the server uses the minimum value among all calculated distances as the spatial distance at the current moment.

[0057] In one possible implementation, the spatial distance between the spatial coordinates of the vehicle parts and the individual equipment model is calculated in real time. Specifically, this includes: during the simulation motion, acquiring the spatial coordinates of the vehicle parts at a preset frequency. The vehicle parts corresponding to the spatial coordinates include at least one of the apex of the body box, the center of each rotation joint of the boom, and the center of the end effector of the boom; calculating the Euclidean distance between the spatial coordinates of each vehicle part and the surface of the individual equipment model, and selecting the minimum value as the spatial distance.

[0058] Specifically, during the simulation, the server reads the current values ​​of the spatial coordinates of each vehicle part at a preset frequency. These parts include the eight vertices of the vehicle body box, the rotational joint centers of each boom section, and the tool center point at the boom end. For each spatial coordinate point, the server calculates the shortest Euclidean distance from it to the triangular mesh on the surface of each individual device model, obtaining the point-to-surface distance. For line segments between adjacent joint center points, the server uses discrete sampling or analytical algorithms to calculate the shortest distance from the line segment to the surface of the device model, obtaining the line-to-surface distance. The server uses the minimum of all point-to-surface and line-to-surface distances as the spatial distance at the current moment. For example, if the distance from the vehicle body vertex to the device is 4 meters, the distance from the boom midpoint to the device is 2 meters, and the distance from the boom end to the device is 1.5 meters, then the server selects 1.5 meters as the spatial distance.

[0059] S105. When the spatial distance is less than the safe distance threshold corresponding to the voltage level, mark the risk point in the three-dimensional point cloud model and record the risk information, including the current time point, the spatial coordinates of the risk point, and the equipment identifier.

[0060] In the above steps, the server compares the current spatial distance with the safety distance threshold corresponding to the voltage level of the individual device model in real time. For example, the safety distance threshold for 220kV live equipment is typically 3 meters. If the end of the vehicle's boom is only 2.5 meters away from the equipment, the server determines that a risk has been triggered. The server generates a visual risk point marker, such as a red dot or warning icon, at the location of the risk in the 3D point cloud model and records the risk information, including the current simulation time, the precise spatial coordinates of the risk point, and the identification of the involved equipment. All risk information is stored in a risk list for subsequent report generation.

[0061] In one possible implementation, before marking risk points and recording risk information in the 3D point cloud model when determining that the spatial distance is less than the safety distance threshold corresponding to the voltage level, the method further includes: matching the reference distance threshold corresponding to the voltage level from a preset safety distance rule library, wherein the preset safety distance rule library contains at least the reference distance thresholds corresponding to 10kV, 110kV, and 220kV voltages respectively; determining whether the current energized status label of the individual equipment model is energized; if the energized status label is energized, then the reference distance threshold is corrected using a first preset correction value to obtain the safety distance threshold; if the energized status label is not energized, then the reference distance threshold is corrected using a second preset correction value to obtain the safety distance threshold.

[0062] Specifically, the server has a built-in safety distance rule base that stores baseline distance thresholds corresponding to different voltage levels, such as 0.7 meters for 10kV, 1.5 meters for 110kV, and 3 meters for 220kV. Before the simulation begins, the server matches the baseline distance threshold from the rule base based on the voltage level of the individual device model. Then, the server checks the device's energized status label: if the label is "energized," the baseline distance threshold is corrected using a first preset correction value, such as multiplying the baseline distance by 1.0 without additional amplification, or multiplying it by a coefficient of 1.2 based on weather conditions; if the label is "de-energized," a second preset correction value is used, such as multiplying the baseline distance by 0.2 or directly using a fixed physical collision safety distance, such as 0.5 meters. The corrected value is the final safety distance threshold. For example, for a 110kV live equipment, the reference distance is 1.5 meters. If the weather is good and a correction factor of 1.0 is used, the safe distance threshold is 1.5 meters. If the equipment is de-energized, the safe distance threshold can be reduced to 0.5 meters. The first preset correction value and the second preset correction value can be set according to actual needs.

[0063] S106. Generate a solution verification report based on the risk points and risk information, and display the solution verification report to the user.

[0064] In the steps described above, after the simulation is complete, the server aggregates all marked risk points and their corresponding risk information, generating a structured solution verification report. The report, using a combination of lists and 3D views, details the time, location, involved equipment, and deviation between the actual distance and the safety threshold for each risk. Users can click on any risk point in the 3D point cloud model, and the server automatically focuses the view on that location, highlighting the relative positional relationship between the vehicle and the equipment. This report allows users to quickly locate safety hazards in the maintenance plan and adjust the travel path, parking position, or boom movement sequence accordingly.

[0065] In one possible implementation, after generating a scheme verification report based on risk points and risk information, the method further includes: responding to the user's modification operation on the maintenance scheme data, inputting the reacquired maintenance scheme data into the vehicle kinematics simulation engine, and determining whether any risk points have been marked; when no risk points have been marked, outputting the reacquired maintenance scheme data as an executable power plant maintenance scheme, constructing the correspondence between the power plant maintenance scheme, the 3D point cloud model, and the 3D parametric model, and storing it in the experience base.

[0066] Specifically, after reviewing the solution verification report, users can modify the travel path, parking position, or boom movement sequence based on the original maintenance solution data. The server responds to the user's modifications by re-acquiring the modified maintenance solution data and re-driving the simulation engine for verification. If no risk points are marked after the re-simulation (i.e., all spatial distances exceed the corresponding safe distance thresholds), the server outputs the current maintenance solution data as an executable substation maintenance solution. This solution includes all verified paths, locations, and action commands. Simultaneously, the server establishes a correspondence between the maintenance solution, the used 3D point cloud model, and the vehicle's 3D parametric model, storing them all in the experience database. When encountering subsequent work tasks involving the same substation, equipment type, or vehicle model, the server can directly retrieve historical solutions from the experience database for reference or reuse them directly, thereby reducing the workload of repeated verification.

[0067] This application also provides a substation vehicle operation scheme verification device, referring to... Figure 2 The device is a server, which includes an acquisition unit 201 and a processing unit 202.

[0068] The acquisition unit 201 is used to acquire the three-dimensional point cloud model of the substation and perform individual modeling of the power equipment in the three-dimensional point cloud model to obtain individual equipment models. The individual equipment models carry equipment identification, voltage level and energized status labels. It is also used to acquire the structural parameters and kinematic parameters of the target vehicle, construct the three-dimensional parametric model of the target vehicle, and determine the local coordinates of the vehicle parts in the three-dimensional parametric model according to the preset part extraction rules.

[0069] The processing unit 202 is used to acquire maintenance plan data in the 3D point cloud model based on the equipment unit model and the 3D parametric model. The maintenance plan data includes the target vehicle's travel path, parking position, boom action sequence, and vehicle part spatial coordinates. The vehicle part spatial coordinates are obtained by transforming the local coordinates of the vehicle part in the 3D point cloud model. It is also used to input the maintenance plan data into the vehicle kinematics simulation engine, driving the 3D parametric model to simulate motion in the 3D point cloud model according to the maintenance plan data, and to calculate the spatial distance between the vehicle part spatial coordinates and the equipment unit model in real time. Furthermore, when the spatial distance is less than the safety distance threshold corresponding to the voltage level, it marks risk points and records risk information in the 3D point cloud model, including the current time point, the risk point's spatial coordinates, and the equipment identifier. Finally, it generates a plan verification report based on the risk points and risk information, and displays the plan verification report to the user.

[0070] In one possible implementation, the acquisition unit 201 is used to acquire the full-domain point cloud data of the substation, perform denoising, registration and segmentation processing on the full-domain point cloud data, and construct a three-dimensional point cloud model; the processing unit 202 is used to extract the point cloud clusters corresponding to the power equipment from the three-dimensional point cloud model, establish a single equipment model based on the point cloud clusters, the single equipment model including the three-dimensional geometry of the power equipment and the spatial coordinates of the equipment; it is also used to associate equipment identifiers, voltage levels and energized status labels with the single equipment model in response to the user's configuration operation.

[0071] In one possible implementation, the processing unit 202 is used to parse the component hierarchy of the three-dimensional parametric model and obtain the local coordinates of the vehicle parts in the three-dimensional parametric model coordinate system, including the vertices of the vehicle body box, the centers of each rotation joint of the boom, and the center of the end effector of the boom, according to preset part extraction rules.

[0072] In one possible implementation, the processing unit 202 is used to generate a travel path consisting of a sequence of spatial coordinate points in response to a user's path drawing operation in the 3D point cloud model; to determine the spatial coordinate point selected by the user as the parking position in response to a user's parking point selection operation in the 3D point cloud model; and to generate a boom action sequence based on the boom pitch angle, horizontal rotation angle, and extension length sequence set by the user in response to a user's boom attitude adjustment operation on the 3D parametric model. The acquisition unit 201 is used to acquire the spatial transformation matrix between the coordinate system of the 3D parametric model and the coordinate system of the 3D point cloud model, and to multiply the local coordinates of the vehicle part by the spatial transformation matrix to obtain the spatial coordinates of the vehicle part.

[0073] In one possible implementation, the processing unit 202 is used to acquire the spatial coordinates of vehicle parts at a preset frequency during the simulation motion. The vehicle parts corresponding to the spatial coordinates include at least one of the top of the body box, the center of each rotation joint of the boom, and the center of the end effector of the boom. The processing unit 202 calculates the Euclidean distance between the spatial coordinates of each vehicle part and the surface of the device unit model, and selects the minimum value as the spatial distance.

[0074] In one possible implementation, the processing unit 202 is used to match a reference distance threshold corresponding to a voltage level from a preset safety distance rule library. The preset safety distance rule library includes reference distance thresholds corresponding to 10kV, 110kV, and 220kV voltages, respectively. It then determines whether the current energized status label of the individual device model is energized. If the energized status label is energized, the reference distance threshold is corrected using a first preset correction value to obtain a safety distance threshold. If the energized status label is not energized, the reference distance threshold is corrected using a second preset correction value to obtain a safety distance threshold.

[0075] In one possible implementation, the processing unit 202 is used to respond to the user's modification operation on the maintenance plan data, input the reacquired maintenance plan data into the vehicle kinematics simulation engine, determine whether any risk points are marked; when no risk points are marked, output the reacquired maintenance plan data as an executable power plant maintenance plan, construct the correspondence between the power plant maintenance plan, the three-dimensional point cloud model and the three-dimensional parametric model and store it in the experience base.

[0076] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0077] This application also provides an electronic device. (See reference...) Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one communication bus 302, at least one user interface 303, a network interface 304, and a memory 305.

[0078] The communication bus 302 is used to enable communication between these components.

[0079] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0080] The network interface 304 may include standard wired interfaces and wireless interfaces (such as Wi-Fi interfaces).

[0081] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0082] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. The memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for verifying a substation vehicle operation scheme.

[0083] exist Figure 3 In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 301 can be used to call an application program of a substation vehicle operation scheme verification method stored in the memory 305. When executed by one or more processors 301, the electronic device 300 performs one or more methods as described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0084] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0085] This application also provides a computer-readable storage medium storing instructions. When executed by one or more processors, these instructions cause an electronic device to perform one or more of the methods described in the above embodiments.

[0086] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0087] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0088] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0089] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0090] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification disclosure.

[0091] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for verifying a vehicle operation plan in a substation, characterized in that, The method includes: A three-dimensional point cloud model of the substation is obtained, and the power equipment in the three-dimensional point cloud model is individually modeled to obtain individual equipment models. The individual equipment models carry equipment identification, voltage level and energized status labels. Obtain the structural and kinematic parameters of the target vehicle, construct a three-dimensional parametric model of the target vehicle, and determine the local coordinates of the vehicle parts in the three-dimensional parametric model according to the preset part extraction rules. In the three-dimensional point cloud model, maintenance plan data is obtained based on the equipment unit model and the three-dimensional parametric model. The maintenance plan data includes the target vehicle's travel path, parking position, boom action sequence, and vehicle part spatial coordinates. The vehicle part spatial coordinates are obtained by performing coordinate system transformation on the local coordinates of the vehicle part in the three-dimensional point cloud model. The maintenance plan data is input into the vehicle kinematics simulation engine, which drives the three-dimensional parametric model to perform simulated motion in the three-dimensional point cloud model according to the maintenance plan data, and calculates the spatial distance between the spatial coordinates of the vehicle parts and the individual equipment model in real time. When the spatial distance is less than the safety distance threshold corresponding to the voltage level, risk points are marked and risk information is recorded in the three-dimensional point cloud model. The risk information includes the current time point, the spatial coordinates of the risk point, and the device identifier. A solution verification report is generated based on the risk points and risk information, and the solution verification report is displayed to the user.

2. The method according to claim 1, characterized in that, The process of acquiring a 3D point cloud model of the substation and performing individual modeling of the power equipment within the 3D point cloud model to obtain individual equipment models specifically includes: The full-area point cloud data of the substation is acquired, and the full-area point cloud data is subjected to denoising, registration and segmentation processing to construct the three-dimensional point cloud model. Extract the point cloud clusters corresponding to the power equipment from the three-dimensional point cloud model, and establish the equipment unit model based on the point cloud clusters. The equipment unit model includes the three-dimensional geometry of the power equipment and the equipment spatial coordinates. In response to the user's configuration operation, the device identifier, the voltage level, and the power status label are associated with the device unit model.

3. The method according to claim 1, characterized in that, The step of determining the local coordinates of vehicle parts in the three-dimensional parametric model according to preset part extraction rules specifically includes: The component hierarchy of the three-dimensional parametric model is analyzed, and the local coordinates of the vehicle parts in the three-dimensional parametric model coordinate system are obtained according to the preset part extraction rules, including the vertices of the vehicle body box, the centers of each rotation joint of the boom, and the center of the end effector of the boom.

4. The method according to claim 1, characterized in that, In the three-dimensional point cloud model, maintenance plan data is obtained based on the individual equipment model and the three-dimensional parametric model, specifically including: In response to the user's path drawing operation in the 3D point cloud model, the travel path consisting of a sequence of spatial coordinate points is generated; In response to the user's operation of selecting a parking point in the 3D point cloud model, the spatial coordinate point selected by the user is determined as the parking position; In response to the user's operation to adjust the arm posture of the three-dimensional parametric model, the arm motion sequence is generated according to the user's set arm pitch angle, horizontal rotation angle and extension length sequence; Obtain the spatial transformation matrix between the coordinate system of the three-dimensional parametric model and the coordinate system of the three-dimensional point cloud model, and multiply the local coordinates of the vehicle part by the spatial transformation matrix to obtain the spatial coordinates of the vehicle part.

5. The method according to claim 1, characterized in that, The real-time calculation of the spatial distance between the vehicle's spatial coordinates and the individual device model specifically includes: During the simulated motion, the spatial coordinates of the vehicle parts are acquired at a preset frequency. The vehicle parts corresponding to the spatial coordinates of the vehicle parts include at least one of the apex of the body box, the center of each rotation joint of the arm, and the center of the end effector of the arm. Calculate the Euclidean distance between the spatial coordinates of each vehicle part and the surface of the device unit model, and select the minimum value as the spatial distance.

6. The method according to claim 1, characterized in that, Before marking risk points and recording risk information in the three-dimensional point cloud model when determining that the spatial distance is less than the safety distance threshold corresponding to the voltage level, the method further includes: The reference distance threshold corresponding to the voltage level is obtained by matching from a preset safety distance rule library. The preset safety distance rule library contains at least the reference distance thresholds corresponding to 10kV voltage, 110kV voltage and 220kV voltage respectively. Determine whether the current power status label of the device unit model is powered. If the power status label is powered, then use the first preset correction value to correct the reference distance threshold to obtain the safe distance threshold. If the charged status tag is not charged, the reference distance threshold is corrected using a second preset correction value to obtain the safe distance threshold.

7. The method according to claim 1, characterized in that, After generating a solution verification report based on the risk points and the risk information, the method further includes: In response to the user's modification operation on the maintenance plan data, the newly acquired maintenance plan data is input into the vehicle kinematics simulation engine to determine whether any risk points have been marked. When no risk points are marked, the reacquired maintenance plan data is output as an executable power plant maintenance plan, and the correspondence between the power plant maintenance plan, the three-dimensional point cloud model, and the three-dimensional parametric model is constructed and stored in the experience base.

8. A substation vehicle operation scheme verification device, characterized in that, The device includes an acquisition unit (201) and a processing unit (202): The acquisition unit (201) is used to acquire a three-dimensional point cloud model of the substation and perform individual modeling of the power equipment in the three-dimensional point cloud model to obtain an individual equipment model. The individual equipment model carries equipment identification, voltage level and energized status label. The acquisition unit (201) is also used to acquire the structural parameters and kinematic parameters of the target vehicle, construct a three-dimensional parametric model of the target vehicle, and determine the local coordinates of the vehicle parts in the three-dimensional parametric model according to the preset part extraction rules. The processing unit (202) is used to obtain maintenance plan data in the three-dimensional point cloud model based on the equipment unit model and the three-dimensional parametric model. The maintenance plan data includes the target vehicle's travel path, parking position, boom action sequence, and vehicle part spatial coordinates. The vehicle part spatial coordinates are obtained by performing coordinate system transformation on the vehicle part local coordinates in the three-dimensional point cloud model. The processing unit (202) is also used to input the maintenance plan data into the vehicle kinematics simulation engine, drive the three-dimensional parametric model to perform simulation motion in the three-dimensional point cloud model according to the maintenance plan data, and calculate the spatial distance between the spatial coordinates of the vehicle part and the single equipment model in real time. The processing unit (202) is further configured to mark risk points and record risk information in the three-dimensional point cloud model when the spatial distance is less than the safety distance threshold corresponding to the voltage level. The risk information includes the current time point, the spatial coordinates of the risk point, and the device identifier. The processing unit (202) is also used to generate a solution verification report based on the risk points and the risk information, and to display the solution verification report to the user.

9. An electronic device, characterized in that, The device includes a processor (301), a memory (305), a user interface (303), and a network interface (304). The memory (305) is used to store instructions. The user interface (303) and the network interface (304) are used to communicate with other devices. The processor (301) is used to execute the instructions stored in the memory (305) to cause the electronic device (300) to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7 above.