Grid code-based inspection data acquisition optimization method and system, and electronic equipment

Abstract

The invention provides an inspection data acquisition optimization method and system based on a grid code, and electronic equipment, and relates to the technical field of data processing, and the method comprises the steps: traversing parts of a target substation, carrying out the grid code layout, and constructing a digital twin three-dimensional model; obtaining a target inspection point set and a target grid code set in the inspection task, and planning an inspection route; routing inspection is carried out according to the routing inspection route, when any target routing inspection point is reached, positioning is carried out through the grid codes, and acquisition parameters are determined; and adjusting a holder camera according to the collection parameter set, carrying out inspection data collection, carrying out verification by using a digital twin three-dimensional model, and carrying out feedback adjustment based on a verification result. The technical problem that in the prior art, due to inaccurate positioning, the collected data quality is not high, and the inspection efficiency is affected is solved, inspection is conducted through grid code mark positioning and parameter adjustment, it is ensured that the inspection collected data can meet the inspection target, and the inspection efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for optimizing inspection data collection based on grid codes, and electronic equipment. Background Art

[0002] In the operation of critical infrastructure such as power systems and substations, regular inspections and maintenance are crucial for ensuring the proper functioning and safety of equipment. Currently, existing inspection methods often rely on simple positioning to determine the location of inspection equipment. In complex or large facilities, such as substations, positioning inaccuracies can easily occur, directly leading to reduced data quality. Inspection equipment often relies on GPS-based positioning or visual recognition technology to determine the location of inspection points, but these positioning methods suffer from poor accuracy and stability in complex environments. Due to environmental factors (such as signal obstruction and complex terrain), positioning errors often occur, preventing inspection equipment from accurately reaching the designated inspection points, thus impacting the comprehensiveness and accuracy of inspection tasks. Inaccurate positioning prevents inspection equipment from accurately aligning with the target inspection point, further compromising the quality of data collection.

[0003] In summary, the prior art has a technical problem in that the quality of collected data is low due to inaccurate positioning, thereby affecting inspection efficiency. Summary of the Invention

[0004] The purpose of this application is to provide a grid code-based inspection data collection optimization method and system, and electronic equipment to solve the technical problem in the prior art that inaccurate positioning leads to low quality of collected data, thereby affecting inspection efficiency.

[0005] In view of the above problems, the present application provides a method and system for optimizing inspection data collection based on grid codes, and electronic equipment.

[0006] In the first aspect, the present application provides a patrol data collection optimization method based on a grid code, which is implemented by a patrol data collection optimization system based on a grid code, wherein the patrol data collection optimization method based on a grid code comprises: traversing the components of the target substation to lay out the grid code, obtaining a set of grid codes and a set of patrol points that have been laid out, using a simulation platform to perform spatial topology on the patrol point set of the target substation, and introducing the grid code set as an index to construct a digital twin three-dimensional model, wherein each patrol point corresponds to a grid code; obtaining a target patrol point set and a target grid code set in the patrol task, based on An inspection route is planned based on the target grid code set to obtain an inspection route; the inspection equipment inspects according to the inspection route, and when it arrives at any target inspection point in the target inspection point set, it locates the target inspection point through the grid code and the grid code of the pan-tilt camera arranged on the inspection equipment, determines the acquisition parameters of the pan-tilt camera, and obtains an acquisition parameter set; the pan-tilt camera is adjusted according to the acquisition parameter set, and the adjusted pan-tilt camera is used to collect inspection data to obtain an inspection data set, and the digital twin three-dimensional model is used to verify the inspection data set, and the acquisition parameter set is feedback-adjusted based on the verification result.

[0007] Optionally, a reference point of the target substation is selected, and a three-dimensional coordinate system is constructed with the reference point as the origin; the components of the target substation are three-dimensionally positioned based on the three-dimensional coordinate system to obtain a grid code set, and the grid code set is mapped one-to-one with the corresponding components to obtain the inspection point set.

[0008] Optionally, the inspection point set is traversed to collect images, and the collected images are processed into point clouds. A three-dimensional simulation is performed based on the processed point clouds using a three-dimensional visualization component to construct a three-dimensional visualization model. The grid code set is introduced to bind the three-dimensional visualization model to obtain the digital twin three-dimensional model.

[0009] Optionally, the grid code of the pan-tilt camera is determined by the sensing device of the inspection equipment; the direction vector and the inspection distance are identified based on the grid code of the target inspection point and the grid code of the pan-tilt camera to obtain the inspection direction vector and the inspection distance; the direction angle is calculated based on the inspection direction vector to determine the pitch angle and the yaw angle; the basic information of the pan-tilt camera is obtained, and the focusing focal length is obtained in combination with the inspection distance; the pitch angle, yaw angle and focusing focal length are used as the initial acquisition parameter set; the initial acquisition parameter set is adjusted and optimized in combination with the deviation scale set of the pan-tilt camera to obtain the acquisition parameter set.

[0010] Optionally, M historical initial acquisition parameter sets and M historical application acquisition parameter sets of the pan-tilt camera are obtained, where M is a positive integer; a one-to-one mapping deviation difference calculation is performed on the M historical initial acquisition parameter sets and the M historical application acquisition parameter sets to determine M historical deviation difference sets; the M historical deviation difference sets are traversed to perform deviation concentration analysis to determine the deviation scale set.

[0011] Optionally, M first historical deviation differences of the same type are extracted from the M historical deviation difference sets; the mean of the M first historical deviation differences is calculated as the first analysis center, the first analysis center is iteratively updated in the M first historical deviation differences according to the meanshift algorithm to obtain a first deviation centralized analysis center, and the first historical deviation difference corresponding to the first deviation centralized analysis center is used as a first deviation scale; deviation centralized analysis of the same type of data is performed on the M historical deviation difference sets respectively to obtain the deviation scale set.

[0012] Optionally, based on the grid code of the target inspection point corresponding to the inspection data set, the digital twin three-dimensional model is retrieved to obtain the digital twin three-dimensional sub-model of the target inspection point; the digital twin three-dimensional sub-model is used to verify the data feasibility of the inspection data set to obtain the inspection verification deviation data set; it is judged whether the inspection verification deviation data set meets the requirements, and if not, the acquisition parameter set is feedback-adjusted based on the inspection verification deviation data set to obtain a feedback acquisition parameter set; the feedback acquisition parameters are used to adjust the pan-tilt camera to re-acquire inspection data.

[0013] Optionally, a feasibility comparison and verification device is pre-built; the digital twin three-dimensional sub-model and the inspection data set are compared using the feasibility comparison and verification device to obtain an inspection verification deviation data set.

[0014] In the second aspect, the present application also provides a grid code-based inspection data acquisition optimization system for executing the grid code-based inspection data acquisition optimization method as described in the first aspect, wherein the grid code-based inspection data acquisition optimization system includes: a three-dimensional model construction module for traversing the components of the target substation to lay out the grid code, obtaining the laid-out grid code set and inspection point set, using the simulation platform to perform spatial topology on the inspection point set of the target substation, and introducing the grid code set as an index to construct a digital twin three-dimensional model, wherein each inspection point corresponds to a grid code; an inspection route planning module for obtaining the target inspection point set and target grid code set in the inspection task, based on the target A grid code set is used to plan the inspection route and obtain the inspection route; an acquisition parameter determination module is used for the inspection equipment to carry out inspections according to the inspection route. When arriving at any target inspection point in the target inspection point set, the grid code of the target inspection point and the grid code of the pan-tilt camera arranged on the inspection equipment are used for positioning, and the acquisition parameters of the pan-tilt camera are determined to obtain the acquisition parameter set; an acquisition parameter adjustment module is used to adjust the pan-tilt camera according to the acquisition parameter set, and use the adjusted pan-tilt camera to collect inspection data to obtain the inspection data set, and use the digital twin three-dimensional model to verify the inspection data set, and feedback-adjust the acquisition parameter set based on the verification result.

[0015] In a third aspect, the present application also provides an electronic device comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the grid code-based inspection data collection optimization method described in any one of the above-mentioned first aspects.

[0016] One or more technical solutions provided in this application have at least the following beneficial effects: By traversing the components of the target substation to lay out the grid code, a laid-out grid code set and a patrol point set are obtained, the patrol point set of the target substation is spatially topologically performed using a simulation platform, and the grid code set is introduced as an index to construct a digital twin three-dimensional model, wherein each patrol point corresponds to a grid code; the target patrol point set and the target grid code set in the patrol task are obtained, and the patrol route is planned based on the target grid code set to obtain the patrol route; the patrol equipment conducts patrol according to the patrol route, and when it reaches any target patrol point in the target patrol point set, it locates the target patrol point through the grid code and the grid code of the pan-tilt camera arranged on the patrol equipment, determines the acquisition parameters of the pan-tilt camera, and obtains the acquisition parameter set; the pan-tilt camera is adjusted according to the acquisition parameter set, and the adjusted pan-tilt camera is used to collect patrol data to obtain the patrol data set, and the patrol data set is verified using the digital twin three-dimensional model, and the acquisition parameter set is feedback-adjusted based on the verification result. That is to say, the components and inspection points of the substation are marked with grid codes, a digital twin model is constructed, the target inspection point set and the corresponding grid code set are obtained, the inspection route is planned, and the inspection equipment conducts inspections according to the planned route. When a target inspection point is reached, it is positioned according to the grid code of the target inspection point and the grid code of the pan-tilt camera installed on the inspection equipment, the acquisition parameters of the pan-tilt camera are adjusted and the inspection is carried out. The digital twin model is used to verify and calibrate the pan-tilt adjustment parameters, and the acquisition parameters are adjusted based on the verification result feedback to ensure that the inspection collection data can meet the inspection goals and improve the inspection efficiency.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0019] Figure 1 This is a flow chart of the inspection data collection optimization method based on grid codes in this application.

[0020] Figure 2 This is a structural diagram of the inspection data collection and optimization system based on grid codes in this application.

[0021] Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of this application.

[0022] Explanation of the accompanying symbols: three-dimensional model construction module 11, inspection route planning module 12, acquisition parameter determination module 13, acquisition parameter adjustment module 14, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0023] This application solves the technical problem in the prior art that the quality of collected data is low due to inaccurate positioning, thereby affecting the efficiency of inspection by providing an inspection data collection optimization method and system and electronic equipment based on grid codes. By marking the components and inspection points of the substation with grid codes, a digital twin model is constructed, the target inspection point set and the corresponding grid code set are obtained, and the inspection route is planned. The inspection equipment inspects according to the planned route. When a target inspection point is reached, it is positioned according to the grid code of the target inspection point and the grid code of the pan-tilt camera installed on the inspection equipment. The acquisition parameters of the pan-tilt camera are adjusted and the inspection is carried out. The digital twin model is used to verify and calibrate the pan-tilt adjustment parameters, and the acquisition parameters are adjusted through feedback from the verification results to ensure that the inspection collection data can meet the inspection goals and improve the inspection efficiency.

[0024] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0025] For example, see the attached Figure 1 The present application provides a method for optimizing patrol data collection based on a grid code, wherein the method is executed by a patrol data collection optimization system based on a grid code, and the method specifically includes the following steps: S100: Traverse the components of the target substation to deploy grid codes, obtain the deployed grid code set and inspection point set, use the simulation platform to perform spatial topology on the inspection point set of the target substation, and introduce the grid code set as an index to construct a digital twin three-dimensional model, where each inspection point corresponds to a grid code.

[0026] Furthermore, the present application S100 includes: A reference point of the target substation is selected and a three-dimensional coordinate system is constructed with the reference point as the origin; three-dimensional coordinate positioning of the components of the target substation is performed based on the three-dimensional coordinate system to obtain a grid code set, and the grid code set is mapped one-to-one with the corresponding components to obtain the inspection point set.

[0027] Furthermore, the present application further comprises the following steps: The inspection point set is traversed to collect images, and the collected images are processed into point clouds. A three-dimensional simulation is performed based on the processed point clouds using a three-dimensional visualization component to construct a three-dimensional visualization model. The grid code set is introduced to bind the three-dimensional visualization model to obtain the digital twin three-dimensional model.

[0028] Specifically, a specific reference point is selected within the target substation. This reference point is typically a prominent fixed component or location within the facility (such as the substation's central control room or important electrical equipment). This reference point serves as the origin of the three-dimensional coordinate system, and the positions of all other components are described relative to this point. In a three-dimensional coordinate system, the reference point is used to determine the starting position (origin) of the coordinate system. The reference point serves as the reference point, and the coordinates of all other locations are calculated and expressed relative to this point. A three-dimensional coordinate system is composed of three mutually perpendicular coordinate axes (X, Y, and Z) and is used to represent the position of any point in space.

[0029] Based on the set three-dimensional coordinate system, each component in the substation (such as transformers, switchgear, cables, lines, etc.) is accurately positioned in three dimensions. Each component is assigned a unique grid code. The grid code is used to identify each component and corresponds one-to-one with the physical location of the component. The grid code is a coding method, and each grid code represents an area or component in space. In the substation, the grid code can be used to uniquely identify the inspection target. The grid code set is composed of multiple independent grid codes, and each grid code in the set corresponds to an inspection point or device. A one-to-one mapping relationship is established between each grid code and the corresponding component to obtain the inspection point set of the entire substation. Each inspection point corresponds to a grid code, and each grid code uniquely identifies a component or device.

[0030] The inspection point set includes all key equipment or areas requiring inspection and data collection. All inspection points within the substation that require inspection are traversed. At each inspection point, installed cameras or other visual devices are used to capture images, including the equipment's appearance, status, and operating environment. LiDAR or depth cameras (such as LiDAR or structured light sensors) can directly generate 3D point cloud data. Point cloud processing of other collected data typically involves removing noise, filling blank areas, and increasing data density. Point cloud processing software is used to convert the collected image data into point cloud data, resulting in the 3D coordinates of each inspection point.

[0031] Utilizing 3D visualization components, 3D simulation is performed based on the processed point cloud. 3D visualization components are tools or technologies used to convert processed data into visual 3D models, rendering the point cloud data in space and presenting a realistic 3D effect on the computer screen. 3D simulation is the process of constructing a virtual scene based on a 3D model, allowing users to simulate the physical environment, operational behaviors, or interactions in space through a computer. 3D visualization models constructed through 3D simulation not only demonstrate the location and form of equipment but also enable interactive observation and analysis.

[0032] Bind the grid code collection to the 3D visualization model to associate the model with the inspection point collection. Specifically, each grid code represents a inspection point. After binding, the grid code is used to locate the corresponding inspection location in the 3D model. When the inspection equipment arrives at a particular inspection point, it can accurately locate the target by reading the grid code information. Through point cloud processing and 3D simulation modeling, the location of the inspection point and the status of the equipment are accurately restored, reflecting the actual structure and component locations of the substation. Binding the grid code collection to the 3D model allows each inspection point to be accurately found in the model using its grid code, thereby improving the accuracy and efficiency of inspections.

[0033] S200: Obtain a target inspection point set and a target grid code set in an inspection task, perform inspection route planning based on the target grid code set, and obtain an inspection route.

[0034] Specifically, a pre-planned inspection task generates a set of target inspection points and a set of target grid codes. Each target inspection point is assigned a unique grid code that identifies its location and the equipment it corresponds to. The target grid code set is the collection of these grid codes. The target inspection point set is the specific location or component set that needs to be inspected during the inspection task, including different equipment, components, or areas, requiring regular inspection and data collection.

[0035] Inspection routes are planned based on the target grid code set. Taking into account factors such as the location of each inspection point, their distances from each other, and their importance (priority), an efficient and accurate path is determined, enabling the inspection equipment to reach all target inspection points in sequence. A heuristic function is used to estimate the cost from the current node to the target node, and the path with the lowest cost is selected during the search process. Based on the target grid code set, the inspection route's starting point (usually the first inspection point) and ending point (usually the last inspection point) are initialized. The open list (containing nodes to be expanded, with the starting point initially added to the open list) and closed list (containing expanded nodes) are also initialized. The total cost of each node is composed of the actual cost from the starting point to the current node and the heuristically estimated cost from the node to the ending point (usually the straight-line distance between the two points, calculated using the Euclidean distance formula). The node with the lowest cost is selected for expansion. From the current node, neighboring nodes are expanded, and the costs of these nodes are calculated. If a neighboring node is not in the open list, or if the path to it via the current node has a lower cost, its cost is updated and it is added to the open list. Once the target node (end point) is found, the search ends and the path is returned. If the open list is empty, it means that no path could be found.

[0036] Paths are generated sequentially based on the shortest path from the entrance to each inspection point, taking into account the distances and connections between all devices and inspection points to ultimately arrive at an inspection route. Using the target grid code set and inspection route planning, inspection routes are mapped out for inspection equipment. Inspection equipment is precisely positioned using grid codes, avoiding positioning errors and path duplication, thus ensuring the accuracy of inspection tasks.

[0037] S300: The inspection device performs inspection along the inspection route. When it reaches any target inspection point in the target inspection point set, it locates the target inspection point through the grid code and the grid code of the pan-tilt camera deployed on the inspection device, determines the acquisition parameters of the pan-tilt camera, and obtains the acquisition parameter set.

[0038] Furthermore, the present application S300 includes: The grid code of the pan-tilt camera is determined by the sensing device of the inspection equipment; the direction vector and the inspection distance are identified based on the grid code of the target inspection point and the grid code of the pan-tilt camera to obtain the inspection direction vector and the inspection distance; the direction angle is calculated based on the inspection direction vector to determine the pitch angle and the yaw angle; the basic information of the pan-tilt camera is obtained, and the focusing focal length is obtained in combination with the inspection distance; the pitch angle, yaw angle and focusing focal length are used as the initial acquisition parameter set; the initial acquisition parameter set is adjusted and optimized in combination with the deviation scale set of the pan-tilt camera to obtain the acquisition parameter set.

[0039] Specifically, when the inspection equipment arrives at any target inspection point along a predetermined inspection route, it uses its sensors (such as lidar, ultrasonic sensors, and GPS) to determine the current position of the PTZ camera and obtain its grid code. The PTZ camera is mounted on the inspection equipment and can adjust its viewing angle, including pitch and yaw.

[0040] The direction vector and inspection distance are identified based on the grid code of the target inspection point and the grid code of the PTZ camera. Specifically, using the PTZ camera's grid code as the starting point and the grid code of the target inspection point as the end point, the target direction vector is calculated using a three-dimensional coordinate system. This is the difference between the camera's coordinates and the target inspection point's coordinates. The inspection distance is then calculated by calculating the Euclidean distance between the inspection device and the target inspection point, which is the straight-line distance between the two points.

[0041] The azimuth angle is calculated based on the inspection direction vector to obtain the pitch and yaw angles. The pitch angle is the vertical angle of the PTZ camera relative to the horizontal plane and is determined by calculating the angular difference between the target point's change in the Z-axis and its projection on the XY plane (horizontal plane). The yaw angle represents the horizontal rotation of the PTZ camera relative to the vertical axis (Z-axis). It is determined by calculating the difference between the target point's projection on the XY plane (horizontal plane) and the camera's XY coordinates. For example, assuming the PTZ camera is at (10, 5, 2) and the inspection point is at (15, 10, 8), the pitch angle is calculated as follows: the change in the Z-axis is 8 - 2 = 6, the horizontal distance (i.e., the XY plane distance) is 7.1 calculated using Euclidean distance, and the pitch angle is atan²(6, 7.1) = 40.2°. The calculation process of the yaw angle is as follows: the XY coordinate differences between the projection of the target point on the XY plane (horizontal plane) and the camera position are 10-5=5, 15-10=5 respectively, and the yaw angle is atan2(5,5)=45°.

[0042] Obtain basic information about the PTZ camera, including the lens's minimum and maximum focal lengths, focal range, and more. Based on the inspection distance from the target inspection point to the PTZ camera, use the camera's optical characteristics to calculate the appropriate focal length. For example, the longer the distance, the larger the focal length required to ensure a clear target. Focus adjustment is the process of adjusting the focal length of the camera lens so that the target object appears clearly in the camera's field of view. This adjustment typically changes the camera's clarity. Use the pitch angle, yaw angle, and focus adjustment as the initial collection parameter set to control the PTZ camera, ensuring the device accurately aligns with the target inspection point and collects clear data.

[0043] By analyzing the historical initial acquisition parameter sets and historical application acquisition parameter sets of the PTZ camera, we obtain a set of deviation scales for the PTZ camera. These scales represent the degree to which various acquisition parameters (such as pitch angle and focal length) deviate from their optimal values ​​or analysis center during different inspection tasks. These deviation scales can be used to guide the optimization of acquisition parameters for the current inspection task, as they indicate which parameters experience significant adjustments in real-world applications and which remain relatively stable.

[0044] Based on the deviation scale set, the initial acquisition parameter set is adjusted to compensate for any deviations, resulting in a final acquisition parameter set. For example, if the historical deviation scale indicates significant deviation in the pitch angle, the pitch tolerance is increased, and the adjustment ranges for focal length and yaw angle are optimized. By leveraging historical data feedback, the error in camera configuration parameters during each inspection mission is reduced, improving the accuracy and stability of data acquisition. After these adjustments and optimizations, the resulting acquisition parameter set more accurately meets the needs of the current inspection mission, ensuring data acquisition quality.

[0045] The camera's grid code determines the camera's position, significantly improving positioning accuracy. By calculating the inspection direction vector and inspection distance, and optimizing based on a set of deviation scales, the camera's pitch, yaw, and focal length are automatically adjusted to ensure optimal image quality. Automatically adjusting acquisition parameters reduces manual intervention, improves inspection efficiency and accuracy, and avoids inspection data issues caused by inaccurate manual settings.

[0046] Furthermore, the present application further comprises the following steps: Obtain M historical initial acquisition parameter sets and M historical application acquisition parameter sets of the pan-tilt camera, where M is a positive integer; perform a one-to-one mapping deviation difference calculation on the M historical initial acquisition parameter sets and the M historical application acquisition parameter sets to determine M historical deviation difference sets; traverse the M historical deviation difference sets to perform deviation concentration analysis to determine the deviation scale set.

[0047] Extract M first historical deviation differences of the same type from the M historical deviation difference sets; calculate the mean of the M first historical deviation differences as the first analysis center, iteratively update the first analysis center in the M first historical deviation differences according to the meanshift algorithm to obtain a first deviation centralized analysis center, and use the first historical deviation difference corresponding to the first deviation centralized analysis center as the first deviation scale; perform deviation centralized analysis of the same type of data on the M historical deviation difference sets respectively to obtain the deviation scale set.

[0048] Specifically, M historical initial acquisition parameter sets and M historical application acquisition parameter sets are obtained for the PTZ camera. M is a positive integer representing the number of historically collected data points. It reflects the set of parameters used for the PTZ camera at different points in time, as well as the set of parameters adjusted based on actual inspection needs. The historical initial acquisition parameter set refers to the initial acquisition parameters (such as the PTZ camera's angle and focal length) set during actual inspection tasks, without any adjustments to the actual application. The historical application acquisition parameter set refers to the set of acquisition parameters adjusted to meet data collection quality requirements during actual inspection tasks, including parameters continuously adjusted and optimized during field practice. For example, the initial parameters for the PTZ camera are: pitch angle = 30°, yaw angle = 45°, and focal length = 50mm. During actual inspections, the adjusted parameters are: pitch angle = 35°, yaw angle = 40°, and focal length = 55mm. This yields an initial acquisition parameter set and a corresponding application acquisition parameter set.

[0049] For each pair of historical initial acquisition parameter sets and historical application acquisition parameter sets, the difference between the two (i.e., the deviation difference) is calculated. This represents the parameter adjustment range in actual application. In other words, for each parameter (such as pitch angle, yaw angle, and focal length), the deviation difference is calculated separately. For example, the pitch deviation difference is 35° - 30° = 5°, the yaw deviation difference is 40° - 45° = -5°, and the focal length deviation difference is 55mm - 50mm = 5mm.

[0050] From each of the M historical deviation difference sets, a set of deviation differences of the same type (such as pitch angle, yaw angle, and focal length) is extracted to obtain M first historical deviation difference sets. The first historical deviation difference represents the difference between the initial setting and the actual adjustment of a parameter (such as pitch angle or focal length) under the same or similar operating conditions. The mean of these M first historical deviation differences is calculated as the first analysis center, representing the average deviation level. The meanshift algorithm is a density-based clustering algorithm used to identify central trends in data. The analysis center is iteratively updated to converge to the area with the highest density in the dataset. The meanshift algorithm is used to perform deviation concentration analysis, iteratively updating the first analysis center until the density center is found. Essentially, the meanshift algorithm searches for concentrated areas in the data and continuously adjusts the analysis center until it converges to the point with the highest density in that area, which serves as the first deviation concentration analysis center. Specifically, the first analysis center is initialized to the mean. The position of the center point is then gradually updated based on the data density distribution. Iterate continuously until the analysis center no longer changes significantly and converges to the point with the highest density in the data set, which is the deviation from the centralized analysis center.

[0051] The first deviation concentration analysis center represents the center of the deviation region for that type of acquisition parameter. The first historical deviation difference corresponding to the first deviation concentration analysis center is used as the first deviation scale. The first deviation scale indicates the degree of deviation from the analysis center and is used to describe the degree of deviation of a data point relative to the concentration region. A deviation concentration analysis of the same type of data is performed on each of the M sets of historical deviation differences. This involves performing the same steps above, clustering the deviation differences for each type of parameter (such as angle, focal length, etc.) to identify the concentrated region of deviation and obtain a set of deviation scales.

[0052] By analyzing the deviation difference between the historical initial acquisition parameters and the actual application acquisition parameters, and using the meanshift algorithm to determine the deviation centralized analysis center, the deviation of the camera in actual application is determined, which is used to optimize future inspection tasks, improve the accuracy and consistency of data collection, and help identify and correct errors in camera settings, thereby improving the quality and reliability of inspection data.

[0053] S400: Adjust the pan-tilt camera according to the acquisition parameter set, use the adjusted pan-tilt camera to collect inspection data, obtain the inspection data set, and use the digital twin three-dimensional model to verify the inspection data set, and feedback adjust the acquisition parameter set based on the verification result.

[0054] Furthermore, the present application S400 includes: Based on the grid code of the target inspection point corresponding to the inspection data set, the digital twin three-dimensional model is retrieved to obtain the digital twin three-dimensional sub-model of the target inspection point; the digital twin three-dimensional sub-model is used to verify the data feasibility of the inspection data set to obtain the inspection verification deviation data set; it is judged whether the inspection verification deviation data set meets the requirements, and if not, the acquisition parameter set is feedback-adjusted based on the inspection verification deviation data set to obtain a feedback acquisition parameter set; the feedback acquisition parameters are used to adjust the pan-tilt camera to re-acquire inspection data.

[0055] Furthermore, the present application further comprises the following steps: A feasibility comparison and verification device is pre-built; the digital twin three-dimensional sub-model and the inspection data set are compared using the feasibility comparison and verification device to obtain an inspection verification deviation data set.

[0056] Specifically, the PTZ camera is adjusted based on a defined set of acquisition parameters. The camera's angle and focal length are adjusted based on the pitch, yaw, and focal length parameters in the acquisition parameter set. Once the adjustment is complete, the camera begins collecting inspection data, including image capture and sensor data acquisition, to generate an inspection data set. Adjusting the PTZ camera involves adjusting its angle (pitch and yaw) and focal length based on the pre-defined acquisition parameter set to ensure it can effectively capture images of the target inspection point. The inspection data set refers to all data (including images, videos, sensor data, etc.) obtained after the camera is adjusted and an inspection is performed.

[0057] During the inspection process, the grid code corresponding to the inspection data set collected by the PTZ camera is determined. Each inspection point has a unique grid code, which is directly associated with its spatial location. By analyzing the inspection data set and combining it with the grid code of the target inspection point, the grid code of the target inspection point is accurately located, and a search operation is performed based on the grid code information. Based on the grid code of the target inspection point, a search is performed from the existing digital twin 3D model database to obtain the digital twin 3D sub-model corresponding to the grid code. The digital twin 3D sub-model is a virtual model of the target inspection point, which can reflect the actual physical state, geometry, structural information, etc. of the point.

[0058] The digital twin 3D sub-model is used to verify the feasibility of the inspection data set, checking whether the actual collected data meets the expected standards for space, size, shape, and other aspects to ensure data accuracy. If the collected data meets the expected requirements, the inspection data is considered feasible; if not, an inspection verification deviation data set is generated to indicate data deviation. Data feasibility verification involves comparing the collected inspection data using the digital twin 3D sub-model to determine the validity and rationality of the data, confirming whether the data meets the expected goals and accurately reflects the actual situation. The inspection verification deviation data set refers to the data deviation set obtained after comparing the inspection data using the digital twin 3D sub-model, that is, data with poor identification results.

[0059] A pre-built feasibility comparison verifier verifies whether inspection data matches the digital twin's 3D sub-model. This comparison primarily checks the consistency between inspection data (such as images and sensor data) and the virtual data recorded in the digital twin model, confirming whether the data is within predetermined ranges and operational. The feasibility comparison verifier must support different types of data comparisons, including images, videos, and sensor data. For example, the image comparison module compares inspection images with virtual images in the digital twin model to ensure geometric position and appearance consistency. The sensor data comparison module compares sensor data such as temperature, pressure, and vibration with pre-set data in the 3D model to verify that the data is within normal ranges. The deviation calculation module calculates the deviation or error between inspection data and model data during data comparison. This process requires a deviation calculation module to quantify the error and generate a deviation data set. During the pre-build phase, comparison rules and standards must be configured. Different types of data comparisons require different algorithms, such as image processing, error detection, and data fitting. The appropriate algorithm should be selected based on actual needs. When pre-building a feasibility comparison and validator, data input and output interfaces must be designed so that the data collected by inspection equipment and the digital twin model can be correctly input into the validator and the comparison results can be clearly output, facilitating subsequent analysis and adjustments. After the design is completed in the pre-build phase, the validator needs to be developed and tested. The purpose of this testing is to verify that the comparison and validator can accurately compare data in various scenarios and promptly detect data deviations, ensuring its reliability and practicality during actual inspections.

[0060] Specifically, design and implement the basic functional modules of the feasibility comparison verifier to ensure that it can handle various types of data comparison tasks. Each module must be specially optimized according to the different data types. According to the characteristics of the inspection data, select the appropriate comparison algorithm, adopt feature matching or similarity calculation methods, and sensor data comparison can use error analysis and regression algorithms. Set comparison rules, such as error tolerance range, image matching accuracy requirements, etc. Ensure that the comparison rules can be appropriately adjusted according to different inspection tasks. Develop the comparison verifier and test it with the actual collected inspection data and digital twin model to verify its comparison accuracy and stability. Deploy the pre-built feasibility comparison verifier and use it in actual inspection tasks. The verifier will automatically compare the inspection data with the digital twin 3D sub-model and output the comparison results.

[0061] The feasibility comparison verifier is used to compare the digital twin 3D sub-model and the inspection data set to obtain the inspection verification deviation data set, including the matching degree between the image and the 3D model, the deviation between the sensor data and the model preset value, and whether there are missing or abnormal values ​​in the inspection data. During the comparison process, all detected deviations are recorded to generate an inspection verification deviation data set, including all problems that arise in the comparison between the inspection data and the model, such as data errors, missing data, and measurement results that deviate from normal values. The inspection verification deviation data set refers to the data set generated during the comparison process, which represents the comparison results between the inspection data and the digital twin 3D sub-model, including the differences between the inspection data and the 3D model, such as position errors, image distortion, and deviations between the sensor data and the expected values ​​of the model.

[0062] Determine whether the inspection and verification deviation data set meets the requirements, that is, whether it is within an acceptable range. For example, set a tolerance range for deviation based on the task requirements. If the deviation exceeds the set threshold, the inspection data is considered to be non-compliant. If the deviation data set does not meet the requirements, adjust the acquisition parameters based on the nature of the deviation. For example, if there is a position error in the image, adjust the pitch and yaw angles of the gimbal camera; if the image is blurry or the focus is inappropriate, adjust the focus; if the sensor data deviates from the normal range, adjust the sensor sensitivity. Feedback adjustment is performed based on the specific deviation value in the inspection and verification deviation data set to ensure that the inspection equipment can better align with the target during the next acquisition.

[0063] After feedback adjustment, the acquisition parameters are updated and fed back to the PTZ camera. The PTZ camera then re-collects data based on these feedback parameters, improving data accuracy and consistency. The PTZ camera realigns the transformer according to the newly set angle and focal length, ensuring more accurate images and more accurate sensor data. By comparing inspection data with the digital twin 3D sub-model in real time, deviations are quickly identified and acquisition parameters adjusted to ensure the accuracy and reliability of inspection data. Adaptive adjustment of acquisition parameters based on deviations in inspection data reduces the number of re-inspections required due to unqualified data, saving time and resources. Furthermore, optimized inspection data is easier to analyze and process, improving the efficiency and quality of inspection tasks.

[0064] In summary, the inspection data collection optimization method based on grid code provided in this application has the following beneficial effects: By traversing the components of the target substation to lay out the grid code, a laid-out grid code set and a patrol point set are obtained, the patrol point set of the target substation is spatially topologically performed using a simulation platform, and the grid code set is introduced as an index to construct a digital twin three-dimensional model, wherein each patrol point corresponds to a grid code; the target patrol point set and the target grid code set in the patrol task are obtained, and the patrol route is planned based on the target grid code set to obtain the patrol route; the patrol equipment conducts patrol according to the patrol route, and when it reaches any target patrol point in the target patrol point set, it locates the target patrol point through the grid code and the grid code of the pan-tilt camera arranged on the patrol equipment, determines the acquisition parameters of the pan-tilt camera, and obtains the acquisition parameter set; the pan-tilt camera is adjusted according to the acquisition parameter set, and the adjusted pan-tilt camera is used to collect patrol data to obtain the patrol data set, and the patrol data set is verified using the digital twin three-dimensional model, and the acquisition parameter set is feedback-adjusted based on the verification result. That is to say, the components and inspection points of the substation are marked with grid codes, a digital twin model is constructed, the target inspection point set and the corresponding grid code set are obtained, the inspection route is planned, and the inspection equipment conducts inspections according to the planned route. When a target inspection point is reached, it is positioned according to the grid code of the target inspection point and the grid code of the pan-tilt camera installed on the inspection equipment, the acquisition parameters of the pan-tilt camera are adjusted and the inspection is carried out. The digital twin model is used to verify and calibrate the pan-tilt adjustment parameters, and the acquisition parameters are adjusted based on the verification result feedback to ensure that the inspection collection data can meet the inspection goals and improve the inspection efficiency.

[0065] In the second embodiment, based on the same inventive concept as the inspection data collection optimization method based on grid code in the above-mentioned embodiment, the present application also provides an inspection data collection optimization system based on grid code, please refer to the attached Figure 2 The grid code-based inspection data collection and optimization system includes: The three-dimensional model construction module 11 is used to traverse the components of the target substation to lay out the grid code, obtain the laid-out grid code set and inspection point set, use the simulation platform to perform spatial topology on the inspection point set of the target substation, and introduce the grid code set as an index to build a digital twin three-dimensional model, where each inspection point corresponds to a grid code; the inspection route planning module 12 is used to obtain the target inspection point set and target grid code set in the inspection task, and plan the inspection route based on the target grid code set to obtain the inspection route; the acquisition parameter determination module 13 is used to determine the inspection equipment according to the target grid code set. The inspection route is inspected. When any target inspection point in the target inspection point set is reached, positioning is performed through the grid code of the target inspection point and the grid code of the pan-tilt camera arranged on the inspection equipment, the acquisition parameters of the pan-tilt camera are determined, and the acquisition parameter set is obtained; the acquisition parameter adjustment module 14 is used to adjust the pan-tilt camera according to the acquisition parameter set, use the adjusted pan-tilt camera to collect inspection data, obtain the inspection data set, and use the digital twin three-dimensional model to verify the inspection data set, and feedback adjust the acquisition parameter set based on the verification result.

[0066] Furthermore, the three-dimensional model construction module 11 in the inspection data acquisition optimization system based on grid codes is also used for: A reference point of the target substation is selected and a three-dimensional coordinate system is constructed with the reference point as the origin; three-dimensional coordinate positioning of the components of the target substation is performed based on the three-dimensional coordinate system to obtain a grid code set, and the grid code set is mapped one-to-one with the corresponding components to obtain the inspection point set.

[0067] Furthermore, the three-dimensional model construction module 11 in the inspection data acquisition optimization system based on grid codes is also used for: The inspection point set is traversed to collect images, and the collected images are processed into point clouds. A three-dimensional simulation is performed based on the processed point clouds using a three-dimensional visualization component to construct a three-dimensional visualization model. The grid code set is introduced to bind the three-dimensional visualization model to obtain the digital twin three-dimensional model.

[0068] Furthermore, the acquisition parameter determination module 13 in the inspection data acquisition optimization system based on grid codes is further configured to: The grid code of the pan-tilt camera is determined by the sensing device of the inspection equipment; the direction vector and the inspection distance are identified based on the grid code of the target inspection point and the grid code of the pan-tilt camera to obtain the inspection direction vector and the inspection distance; the direction angle is calculated based on the inspection direction vector to determine the pitch angle and the yaw angle; the basic information of the pan-tilt camera is obtained, and the focusing focal length is obtained in combination with the inspection distance; the pitch angle, yaw angle and focusing focal length are used as the initial acquisition parameter set; the initial acquisition parameter set is adjusted and optimized in combination with the deviation scale set of the pan-tilt camera to obtain the acquisition parameter set.

[0069] Furthermore, the acquisition parameter determination module 13 in the inspection data acquisition optimization system based on grid codes is further configured to: Obtain M historical initial acquisition parameter sets and M historical application acquisition parameter sets of the pan-tilt camera, where M is a positive integer; perform a one-to-one mapping deviation difference calculation on the M historical initial acquisition parameter sets and the M historical application acquisition parameter sets to determine M historical deviation difference sets; traverse the M historical deviation difference sets to perform deviation concentration analysis to determine the deviation scale set.

[0070] Furthermore, the acquisition parameter determination module 13 in the inspection data acquisition optimization system based on grid codes is further configured to: Extract M first historical deviation differences of the same type from the M historical deviation difference sets; calculate the mean of the M first historical deviation differences as the first analysis center, iteratively update the first analysis center in the M first historical deviation differences according to the meanshift algorithm to obtain a first deviation centralized analysis center, and use the first historical deviation difference corresponding to the first deviation centralized analysis center as the first deviation scale; perform deviation centralized analysis of the same type of data on the M historical deviation difference sets respectively to obtain the deviation scale set.

[0071] Furthermore, the acquisition parameter adjustment module 14 in the inspection data acquisition optimization system based on grid codes is further configured to: Based on the grid code of the target inspection point corresponding to the inspection data set, the digital twin three-dimensional model is retrieved to obtain the digital twin three-dimensional sub-model of the target inspection point; the digital twin three-dimensional sub-model is used to verify the data feasibility of the inspection data set to obtain the inspection verification deviation data set; it is judged whether the inspection verification deviation data set meets the requirements, and if not, the acquisition parameter set is feedback-adjusted based on the inspection verification deviation data set to obtain a feedback acquisition parameter set; the feedback acquisition parameters are used to adjust the pan-tilt camera to re-acquire inspection data.

[0072] Furthermore, the acquisition parameter adjustment module 14 in the inspection data acquisition optimization system based on grid codes is further configured to: A feasibility comparison and verification device is pre-built; the digital twin three-dimensional sub-model and the inspection data set are compared using the feasibility comparison and verification device to obtain an inspection verification deviation data set.

[0073] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The grid code-based inspection data collection optimization method and specific examples in Example 1 are also applicable to the grid code-based inspection data collection optimization system in this embodiment. Through the above detailed description of the grid code-based inspection data collection optimization method, those skilled in the art can clearly understand the grid code-based inspection data collection optimization system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0074] Example three, based on the same inventive concept as the inspection data collection optimization method based on grid code in the aforementioned Example one, the present application also provides an electronic device, comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the inspection data collection optimization method based on grid code in any one of the aforementioned Example one.

[0075] Attachment Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of this application. Figure 3 In the figure, the bus architecture is represented by bus 300, which can include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are all well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 when performing operations.

[0076] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0077] Obviously, for those skilled in the art, several improvements and modifications can be made to the present application without departing from the principles of the present application, and these improvements and modifications also fall within the scope of protection of the present application.

Claims

1. The inspection data collection optimization method based on grid code is characterized by: include: Traverse the components of the target substation to deploy grid codes, obtain the completed grid code set and inspection point set, use the simulation platform to perform spatial topology on the inspection point set of the target substation, and introduce the grid code set as an index to build a digital twin 3D model, where each inspection point corresponds to a grid code; Obtaining a target inspection point set and a target grid code set in the inspection task, performing inspection route planning based on the target grid code set, and obtaining an inspection route; The inspection device performs inspections along the inspection route. When it reaches any target inspection point in the target inspection point set, it locates the target inspection point by using the grid code of the target inspection point and the grid code of the pan-tilt camera deployed on the inspection device, determines the acquisition parameters of the pan-tilt camera, and obtains the acquisition parameter set. The pan-tilt camera is adjusted according to the acquisition parameter set, and the adjusted pan-tilt camera is used to collect inspection data to obtain an inspection data set. The inspection data set is verified using the digital twin three-dimensional model, and the acquisition parameter set is feedback-adjusted based on the verification result.

2. The inspection data collection optimization method based on grid code according to claim 1 is characterized in that: The inspection device performs inspections along the inspection route. When arriving at any target inspection point in the target inspection point set, the inspection device locates the target inspection point by using the grid code of the target inspection point and the grid code of the pan-tilt camera deployed on the inspection device, determines the acquisition parameters of the pan-tilt camera, and obtains the acquisition parameter set, including: Determine the grid code of the pan-tilt camera by a sensing device of the inspection equipment; Identify the direction vector and inspection distance based on the grid code of the target inspection point and the grid code of the pan-tilt camera to obtain the inspection direction vector and inspection distance; Calculate the direction angle based on the inspection direction vector to determine the pitch angle and yaw angle; Obtain basic information of the pan-tilt camera, and obtain the focus focal length based on the inspection distance; Using the pitch angle, yaw angle and focus focal length as an initial acquisition parameter set; The initial acquisition parameter set is adjusted and optimized in combination with the deviation scale set of the pan-tilt camera to obtain the acquisition parameter set.

3. The inspection data collection optimization method based on grid code according to claim 2 is characterized in that: The initial acquisition parameter set is adjusted and optimized based on the deviation scale set of the pan-tilt camera to obtain the acquisition parameter set, including: Obtain M historical initial acquisition parameter sets and M historical application acquisition parameter sets of the PTZ camera, where M is a positive integer; Performing a one-to-one mapping deviation difference calculation on the M historical initial acquisition parameter sets and the M historical application acquisition parameter sets to determine M historical deviation difference sets; The M historical deviation difference value sets are traversed to perform deviation concentration analysis to determine the deviation scale set.

4. The inspection data collection optimization method based on grid code according to claim 3 is characterized in that: Traversing the M historical deviation difference sets to perform deviation concentration analysis and determine the deviation scale set, including: Extracting M first historical deviation differences of the same type from the M historical deviation difference sets; Calculating the mean of the M first historical deviation differences as a first analysis center, iteratively updating the first analysis center among the M first historical deviation differences according to a meanshift algorithm to obtain a first deviation concentrated analysis center, and using the first historical deviation difference corresponding to the first deviation concentrated analysis center as a first deviation scale; A deviation concentration analysis of the same type of data is performed on each of the M historical deviation difference sets to obtain the deviation scale set.

5. The inspection data collection optimization method based on grid code according to claim 1 is characterized in that: Traverse the components of the target substation to lay out the grid code, obtain the laid-out grid code set and inspection point set, use the simulation platform to perform spatial topology on the inspection point set of the target substation, and introduce the grid code set as an index to build a digital twin 3D model, including: Select the reference point of the target substation and construct a three-dimensional coordinate system with the reference point as the origin; The components of the target substation are positioned in three-dimensional coordinates based on the three-dimensional coordinate system to obtain a grid code set, and the grid code set is mapped one-to-one with the corresponding components to obtain the inspection point set.

6. The inspection data collection optimization method based on grid code according to claim 5, characterized in that: include: Traversing the inspection point set to collect images, performing point cloud processing on the collected images, performing three-dimensional simulation based on the processed point cloud using a three-dimensional visualization component, and constructing a three-dimensional visualization model; The grid code set is introduced to bind the three-dimensional visualization model to obtain the digital twin three-dimensional model.

7. The inspection data collection optimization method based on grid code according to claim 1 is characterized in that: Adjusting the pan-tilt camera according to the acquisition parameter set, using the adjusted pan-tilt camera to collect inspection data to obtain an inspection data set, verifying the inspection data set using the digital twin three-dimensional model, and performing feedback adjustment on the acquisition parameter set based on the verification result, including: Based on the grid code of the target inspection point corresponding to the inspection data set, the digital twin three-dimensional model is searched to obtain the digital twin three-dimensional sub-model of the target inspection point; Performing data feasibility verification on the inspection data set using the digital twin three-dimensional sub-model to obtain an inspection verification deviation data set; Determine whether the inspection verification deviation data set meets the requirements, and if not, perform feedback adjustment on the acquisition parameter set based on the inspection verification deviation data set to obtain a feedback acquisition parameter set; The feedback acquisition parameters are used to adjust the pan-tilt camera to re-acquire inspection data.

8. The inspection data collection optimization method based on grid code according to claim 1 is characterized in that: include: Pre-built feasibility comparison verifier; The feasibility comparison verifier is used to compare the digital twin three-dimensional sub-model and the inspection data set to obtain the inspection verification deviation data set.

9. The inspection data collection and optimization system based on grid code is characterized by: The steps for implementing the inspection data collection optimization method based on grid codes according to any one of claims 1 to 8, wherein the inspection data collection optimization system based on grid codes comprises: A 3D model construction module is used to traverse the components of the target substation to deploy grid codes, obtain the deployed grid code set and inspection point set, use the simulation platform to perform spatial topology on the inspection point set of the target substation, and introduce the grid code set as an index to construct a digital twin 3D model, where each inspection point corresponds to a grid code; An inspection route planning module is used to obtain a target inspection point set and a target grid code set in an inspection task, and perform inspection route planning based on the target grid code set to obtain an inspection route; An acquisition parameter determination module is used for the inspection equipment to perform inspections along the inspection route. When arriving at any target inspection point in the target inspection point set, the module locates the target inspection point by using the grid code of the target inspection point and the grid code of the pan-tilt camera deployed on the inspection equipment, determines the acquisition parameters of the pan-tilt camera, and obtains the acquisition parameter set; An acquisition parameter adjustment module is used to adjust the pan-tilt camera according to the acquisition parameter set, use the adjusted pan-tilt camera to collect inspection data, obtain an inspection data set, and use the digital twin three-dimensional model to verify the inspection data set, and feedback adjust the acquisition parameter set based on the verification results.

10. An electronic device, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; In which, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the grid code-based inspection data collection optimization method as described in any one of claims 1 to 8.

Images