Rural power system digital twinborn three-dimensional point cloud acquisition and modeling method and system
By combining point cloud data collection from drones and deep learning models with GIS information, the problem of data collection for power lines and facilities in rural power systems was solved, enabling efficient 3D modeling and accurate power system construction.
Patent Information
- Application Number
- CN202510830549.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-20
- Publication Date
- 2025-11-18
AI Technical Summary
Rural power systems have scattered power lines and facilities with overlapping equipment, making data collection and analysis difficult. Existing automatic modeling methods cannot effectively identify individual power lines and facilities.
UAVs are used to collect point cloud data. Through data noise reduction, adaptive clustering and label classification, combined with GIS information and deep learning models, point cloud data collection routes for different areas are planned to generate 3D models.
This technology enables efficient 3D point cloud acquisition and modeling of rural power systems, improving modeling accuracy and reducing data redundancy and computational load.
Smart Images
Figure CN120976407A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of digital twin technology, specifically to a method and system for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems. Background Technology
[0002] In recent years, with the development of drones and 3D reconstruction technology, using drones to achieve aerial inspection and 3D modeling of power lines to create digital twins has become a new technological direction. Digital twins serve as a bridge between the physical world and the digital virtual world of the power grid. Introducing digital twin technology into the power grid allows for the synchronous mapping of the physical grid. During long-term operation, power lines are subjected to complex and diverse loads and environmental influences, making it difficult to detect potential safety hazards. By collecting data from sensors deployed on power grid equipment and visualizing the collected data, maintenance personnel can analyze the operational data to obtain the final evaluation results of the power grid equipment. Based on the identified equipment problems, maintenance personnel can optimize the equipment status and remind other maintenance personnel to increase monitoring or arrange planned emergency repairs. Digital twin models that combine sensors to reflect the real-time operating status of power lines are of great significance for solving the problem of monitoring the operating status of power grid equipment.
[0003] However, rural power systems differ significantly from substations and urban power systems. Rural power systems encompass various facilities, including residential power systems in densely populated areas, agricultural power systems and power lines for residential use located in open rural areas, high-voltage transmission lines in open rural areas, and substations near densely populated areas. These facilities are geographically dispersed, with overlapping equipment, making data collection and analysis difficult. Typical automated modeling methods are unable to effectively identify the individual power lines and facilities within a rural power system. Summary of the Invention
[0004] The purpose of this invention is to provide a method and system for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems, so as to solve the above-mentioned technical problems.
[0005] This invention provides a method for 3D point cloud acquisition and modeling of digital twins for rural power systems, including the following steps: S1, point cloud data is collected based on drones, and the data is denoised to obtain initial sampling data; S2, Adaptive clustering is performed on the initial sampled data, and position encoding is introduced to describe the point cloud coordinate information and construct the point cloud vector; S3, perform label classification on point clouds: S31, based on the height information in the point cloud coordinate information, the area where the high-voltage tower is located in the point cloud is assigned a first label and classified as a high-voltage line; S32, based on preset GIS or geographic information, assign a second label to different areas in the point cloud to classify them as rural open areas and a third label to classify them as residential areas; S33, perform preliminary fitting on the points clustered as power lines in the point cloud coordinate information to obtain a preliminary power line model; S4: Based on different label classifications, 3D point cloud data is collected using different preset acquisition methods, and a 3D model is generated. S41, based on the first label classification and the preliminary power line model, plan the UAV secondary point cloud data acquisition route for all regions corresponding to the first label classification and the power lines intersecting with the region, and perform secondary point cloud data acquisition. The acquired secondary point cloud data is fused with the initial sampling data to obtain fused point cloud data. Three-dimensional modeling of high-voltage towers and high-voltage power lines is performed based on the fused point cloud data. S42, based on the second label classification of rural open fields, for the area corresponding to the second label classification, plan the secondary point cloud data collection route of the UAV low-altitude flight, according to the secondary point cloud data collected by the video low-altitude flight, perform feature extraction of the three-dimensional point cloud according to the deep learning model pre-trained through the low-voltage power distribution network facility image, and model the power system of the rural open fields based on the extracted feature parameters. S43, based on the third label classification of the residential area, construct a three-dimensional model of the power system of the residential area corresponding to the third label classification.
[0006] Preferably, the low-voltage power distribution network facilities include low-voltage power poles and substations.
[0007] Preferably, in step S1, outliers in the point cloud data are determined using a nearest neighbor search algorithm, including: dividing the data space into three dimensions using a kd-tree, extracting each sample point in the point cloud data sequentially, and based on the sample point and a set radius R, collecting all data points in the data set whose distance to the sample point is less than R. When the number of points in the neighborhood of a sample point is less than a set threshold X, it is determined to be an outlier; deleting the outlier to obtain the initial sampled data after noise reduction.
[0008] Preferably, in step S2, the step of constructing point cloud vectors includes: based on point cloud coordinate data, reflection intensity data, and position encoding, using the Self-Attention mechanism based on the Transformer model, determining the query, key, and value, and calculating the attention relationship vector between point clouds.
[0009] Preferably, in step S31, points with coordinates greater than a preset height are extracted from the initial point cloud data, and morphological analysis is performed on these points to determine whether they are high-voltage towers. If so, the area where the high-voltage tower is located is assigned a first label classification.
[0010] Preferably, step S32 specifically includes: Based on the preset GIS or geographic information, collect the required geographic and environmental data, import them into the geographic information system software, create map layers, and establish corresponding layers for each data type; The geographic information system software is used to analyze geographic and environmental data, identify rural open areas and residential areas, and assign coordinate information. Based on the coordinate information of rural open areas and residential areas, the corresponding regions in the point cloud are assigned a second label classification and a third label classification.
[0011] Preferably, step S42 includes: Based on the second label classification of rural open areas, a secondary point cloud data collection route for low-altitude drone flight is planned for the area corresponding to the second label classification. Point cloud data is collected according to the described route, and after data noise reduction, secondary point cloud data is obtained. Feature extraction and feature fusion are performed on the secondary point cloud data to obtain the foreground region and category containing power targets; A deep learning model pre-trained using images of low-voltage distribution network facilities; A trained deep learning model is used to perform secondary identification and classification of the foreground region and category containing power targets, extract the feature parameters of each power target, and model the power system in rural open areas based on the extracted feature parameters.
[0012] Preferably, in step S43, a three-dimensional model of the power system of the residential area is automatically constructed by acquiring ground images, or a building model generated from a two-dimensional or three-dimensional map of the residential area is used to input the tags of the target in order to construct a three-dimensional model of the power system of the residential area.
[0013] The present invention also provides a three-dimensional point cloud acquisition and modeling system for a digital twin of a rural power system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the three-dimensional point cloud acquisition and modeling method for a digital twin of a rural power system as described in any of the preceding claims.
[0014] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the three-dimensional point cloud acquisition and modeling method for digital twins of rural power systems as described in any of the preceding claims.
[0015] In this application, the following steps are adopted: S1, point cloud data is collected based on UAVs, and after data denoising, initial sampling data is obtained; S2, adaptive clustering is performed on the initial sampling data, and position coding is introduced to describe the point cloud coordinate information and construct point cloud vectors; S3, point cloud is labeled and classified: S31, based on the height information in the point cloud coordinate information, the area where the high-voltage towers are located in the point cloud is assigned a first label and classified as a high-voltage line; S32, based on preset GIS or geographic information, different areas in the point cloud are assigned a second label and classified as rural open fields and a third label and classified as residential areas; S33, based on the point cloud coordinate information, the points clustered as power lines are preliminarily fitted to obtain a preliminary power line model; S4, based on different label classifications, three-dimensional point cloud data is collected according to different preset collection methods, and a three-dimensional model is generated: S41, based on the first label classification and the preliminary power line model... The process involves: S41, planning a secondary point cloud data acquisition route for all regions corresponding to the first label classification and the power lines intersecting with those regions using UAVs; S42, fusing the acquired secondary point cloud data with the initial sampling data to obtain fused point cloud data; and S43, modeling the high-voltage towers and high-voltage power lines using the fused point cloud data; S44, based on the second label classification for rural open areas, planning a secondary point cloud data acquisition route for UAVs flying at low altitudes for the regions corresponding to the second label classification; S45, extracting features from the 3D point cloud using a deep learning model pre-trained with low-voltage power distribution network facility images based on the extracted feature parameters; and S46, constructing a 3D model of the power system for residential areas based on the third label classification for the regions corresponding to the third label classification.
[0016] First, the point cloud data is categorized by label. The areas where high-voltage power towers are located in the point cloud are categorized as high-voltage lines, rural open areas, and residential areas. Then, different 3D modeling methods are adopted for different categories to meet the 3D point cloud acquisition and modeling requirements of different areas. High-voltage power lines are acquired through secondary point cloud data collection by UAVs, rural open areas are acquired through secondary point cloud data collection by UAVs flying at low altitudes, and residential areas are modeled using ground cameras or by directly importing building maps. Attached Figure Description
[0017] The accompanying drawings, as part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention, but do not constitute an undue limitation of the invention. Obviously, the drawings described below are merely some embodiments, and those skilled in the art can obtain other drawings based on these drawings without creative effort. In the drawings: Figure 1 This is a flowchart illustrating a method for acquiring and modeling three-dimensional point clouds of a digital twin of a rural power system according to an embodiment of the present invention.
[0018] Figure 2 This is a schematic diagram of the hardware structure of a system that runs a three-dimensional point cloud acquisition and modeling method for digital twins of rural power systems, according to one embodiment of the present invention.
[0019] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0020] The technical problems solved by the embodiments of the present invention, the technical solutions adopted, and the technical effects achieved will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other equivalent or obvious variations of embodiments obtained by those skilled in the art without creative effort fall within the protection scope of the present invention. The embodiments of the present invention can be embodied in various different ways as defined and covered by the claims.
[0021] It should be noted that many specific details are given in the following description for ease of understanding. However, it is obvious that the present invention may be implemented without these specific details.
[0022] It should be noted that, in the absence of explicit limitations or conflicts, the various embodiments and their technical features in this invention can be combined with each other to form a technical solution.
[0023] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0024] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.
[0025] The invention will now be described in further detail with reference to the accompanying drawings.
[0026] Please combine Figure 1 and Figure 2 , Figure 1 A method for 3D point cloud acquisition and modeling of a rural power system digital twin according to an embodiment of the present invention includes the following steps: S1, point cloud data is collected based on drones, and the data is denoised to obtain initial sampling data; S2, Adaptive clustering is performed on the initial sampled data, and position encoding is introduced to describe the point cloud coordinate information and construct the point cloud vector; S3, perform label classification on point clouds: S31, based on the height information in the point cloud coordinate information, the area where the high-voltage tower is located in the point cloud is assigned a first label and classified as a high-voltage line; S32, based on preset GIS or geographic information, assign a second label to different areas in the point cloud to classify them as rural open areas and a third label to classify them as residential areas; S33, perform preliminary fitting on the points clustered as power lines in the point cloud coordinate information to obtain a preliminary power line model; S4: Based on different label classifications, 3D point cloud data is collected using different preset acquisition methods, and a 3D model is generated. S41, based on the first label classification and the preliminary power line model, plan the UAV secondary point cloud data acquisition route for all regions corresponding to the first label classification and the power lines intersecting with the region, and perform secondary point cloud data acquisition. The acquired secondary point cloud data is fused with the initial sampling data to obtain fused point cloud data. Three-dimensional modeling of high-voltage towers and high-voltage power lines is performed based on the fused point cloud data. S42, based on the second label classification of rural open fields, for the area corresponding to the second label classification, plan the secondary point cloud data collection route of the UAV low-altitude flight, according to the secondary point cloud data collected by the video low-altitude flight, perform feature extraction of the three-dimensional point cloud according to the deep learning model pre-trained through the low-voltage power distribution network facility image, and model the power system of the rural open fields based on the extracted feature parameters. S43, based on the third label classification of the residential area, construct a three-dimensional model of the power system of the residential area corresponding to the third label classification.
[0027] Preferably, the low-voltage power distribution network facilities include low-voltage power poles and substations.
[0028] Preferably, in step S1, outliers in the point cloud data are determined using a nearest neighbor search algorithm, including: dividing the data space into three dimensions using a kd-tree, extracting each sample point in the point cloud data sequentially, and based on the sample point and a set radius R, collecting all data points in the data set whose distance to the sample point is less than R. When the number of points in the neighborhood of a sample point is less than a set threshold X, it is determined to be an outlier; deleting the outlier to obtain the initial sampled data after noise reduction.
[0029] Preferably, in step S2, the step of constructing point cloud vectors includes: based on point cloud coordinate data, reflection intensity data, and position encoding, using the Self-Attention mechanism based on the Transformer model, determining the query, key, and value, and calculating the attention relationship vector between point clouds.
[0030] Preferably, in step S31, points with coordinates greater than a preset height are extracted from the initial point cloud data, and morphological analysis is performed on these points to determine whether they are high-voltage towers. If so, the area where the high-voltage tower is located is assigned a first label classification.
[0031] Preferably, step S32 specifically includes: Based on the preset GIS or geographic information, collect the required geographic and environmental data, import them into the geographic information system software, create map layers, and establish corresponding layers for each data type; The geographic information system software is used to analyze geographic and environmental data, identify rural open areas and residential areas, and assign coordinate information. Based on the coordinate information of rural open areas and residential areas, the corresponding regions in the point cloud are assigned a second label classification and a third label classification.
[0032] Preferably, step S42 includes: Based on the second label classification of rural open areas, a secondary point cloud data collection route for low-altitude drone flight is planned for the area corresponding to the second label classification. Point cloud data is collected according to the described route, and after data noise reduction, secondary point cloud data is obtained. Feature extraction and feature fusion are performed on the secondary point cloud data to obtain the foreground region and category containing power targets; A deep learning model pre-trained using images of low-voltage distribution network facilities; A trained deep learning model is used to perform secondary identification and classification of the foreground region and category containing power targets, extract the feature parameters of each power target, and model the power system in rural open areas based on the extracted feature parameters.
[0033] Preferably, in step S43, a three-dimensional model of the power system of the residential area is automatically constructed by acquiring ground images, or a building model generated from a two-dimensional or three-dimensional map of the residential area is used to input the tags of the target in order to construct a three-dimensional model of the power system of the residential area.
[0034] In this application, the following steps are adopted: S1, point cloud data is collected based on UAVs, and after data denoising, initial sampling data is obtained; S2, adaptive clustering is performed on the initial sampling data, and position coding is introduced to describe the point cloud coordinate information and construct point cloud vectors; S3, point cloud is labeled and classified: S31, based on the height information in the point cloud coordinate information, the area where the high-voltage towers are located in the point cloud is assigned a first label and classified as a high-voltage line; S32, based on preset GIS or geographic information, different areas in the point cloud are assigned a second label and classified as rural open fields and a third label and classified as residential areas; S33, based on the point cloud coordinate information, the points clustered as power lines are preliminarily fitted to obtain a preliminary power line model; S4, based on different label classifications, three-dimensional point cloud data is collected according to different preset collection methods, and a three-dimensional model is generated: S41, based on the first label classification and the preliminary power line model... The process involves: S41, planning a secondary point cloud data acquisition route for all regions corresponding to the first label classification and the power lines intersecting with those regions using UAVs; S42, fusing the acquired secondary point cloud data with the initial sampling data to obtain fused point cloud data; and S43, modeling the high-voltage towers and high-voltage power lines using the fused point cloud data; S44, based on the second label classification for rural open areas, planning a secondary point cloud data acquisition route for UAVs flying at low altitudes for the regions corresponding to the second label classification; S45, extracting features from the 3D point cloud using a deep learning model pre-trained with low-voltage power distribution network facility images based on the extracted feature parameters; and S46, constructing a 3D model of the power system for residential areas based on the third label classification for the regions corresponding to the third label classification.
[0035] First, the point cloud data is categorized by label. The areas where high-voltage power towers are located are categorized as high-voltage lines, rural open areas, and residential areas. Then, different 3D modeling methods are adopted for different categories to meet the 3D point cloud acquisition and modeling requirements of different areas, which improves the accuracy of modeling. High-voltage power lines are acquired through secondary point cloud data collection by UAVs, rural open areas are acquired through secondary point cloud data collection by UAVs at low altitudes, and residential areas are modeled by ground cameras or by directly importing building maps, which reduces data redundancy and unnecessary computation.
[0036] This invention also provides a three-dimensional point cloud acquisition and modeling system for a digital twin of a rural power system. The three-dimensional point cloud acquisition and modeling system for a digital twin of a rural power system is built on a computer system and runs on the basis of a computer system. Specifically, it includes a memory 61, a processor 62, and a computer program 63 stored in the memory 61 and executable on the processor 62. When the processor 62 executes the computer program 63, it implements the steps of the three-dimensional point cloud acquisition and modeling method for a digital twin of a rural power system as described in any of the above claims.
[0037] This embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the three-dimensional point cloud acquisition and modeling method for digital twins of rural power systems as described in any of the preceding embodiments.
[0038] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments 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. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0039] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0040] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0041] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or 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 interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0042] 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.
[0043] Furthermore, the functional units in the various embodiments of the present invention 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.
[0044] If the integrated module / 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 medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.
[0045] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.
[0046] In the description of this specification, references to terms such as "one embodiment," "another embodiment," "other embodiments," or "first embodiment to Xth embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, method steps, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0047] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0048] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.
Claims
1. A method for 3D point cloud acquisition and modeling of digital twins for rural power systems, characterized in that, Including the following steps: S1, point cloud data is collected based on drones, and the data is denoised to obtain initial sampling data; S2, Adaptive clustering is performed on the initial sampled data, and position encoding is introduced to describe the point cloud coordinate information and construct the point cloud vector; S3, perform label classification on point clouds: S31, based on the height information in the point cloud coordinate information, the area where the high-voltage tower is located in the point cloud is assigned a first label and classified as a high-voltage line; S32, based on preset GIS or geographic information, assign a second label to different areas in the point cloud to classify them as rural open areas and a third label to classify them as residential areas; S33, perform preliminary fitting on the points clustered as power lines in the point cloud coordinate information to obtain a preliminary power line model; S4: Based on different label classifications, 3D point cloud data is collected using different preset acquisition methods, and a 3D model is generated. S41, based on the first label classification and the preliminary power line model, plan the UAV secondary point cloud data acquisition route for all regions corresponding to the first label classification and the power lines intersecting with the region, and perform secondary point cloud data acquisition. The acquired secondary point cloud data is fused with the initial sampling data to obtain fused point cloud data. Three-dimensional modeling of high-voltage towers and high-voltage power lines is performed based on the fused point cloud data. S42, based on the second label classification of rural open fields, for the area corresponding to the second label classification, plan the secondary point cloud data collection route of the UAV low-altitude flight, according to the secondary point cloud data collected by the video low-altitude flight, perform feature extraction of the three-dimensional point cloud according to the deep learning model pre-trained through the low-voltage power distribution network facility image, and model the power system of the rural open fields based on the extracted feature parameters. S43, based on the third label classification of the residential area, construct a three-dimensional model of the power system of the residential area corresponding to the third label classification.
2. The method for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems according to claim 1, characterized in that, The low-voltage power distribution network facilities include low-voltage power poles and substations.
3. The method for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems according to claim 1, characterized in that, In step S1, outliers in the point cloud data are determined using a nearest neighbor search algorithm, including: dividing the data space into three dimensions using a kd-tree, extracting each sample point in the point cloud data sequentially, and based on the sample point and a set radius R, collecting all data points in the data set whose distance to the sample point is less than R. When the number of points in the neighborhood of a sample point is less than a set threshold X, it is determined to be an outlier; deleting the outlier yields the initial sampled data after noise reduction.
4. The method for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems according to claim 1, characterized in that, In step S2, the step of constructing point cloud vectors includes: based on point cloud coordinate data, reflection intensity data, and position encoding, using the Self-Attention mechanism based on the Transformer model, determining the query, key, and value, and calculating the attention relationship vector between point clouds.
5. The method for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems according to claim 1, characterized in that, In step S31, points with coordinates greater than a preset height are extracted from the initial point cloud data, and morphological analysis is performed on these points to determine whether they are high-voltage towers. If so, the area where the high-voltage tower is located is assigned a first label classification.
6. The method for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems according to claim 1, characterized in that, Step S32 specifically includes: Based on the preset GIS or geographic information, collect the required geographic and environmental data, import them into the geographic information system software, create map layers, and establish corresponding layers for each data type; The geographic information system software is used to analyze geographic and environmental data, identify rural open areas and residential areas, and assign coordinate information. Based on the coordinate information of rural open areas and residential areas, the corresponding regions in the point cloud are assigned a second label classification and a third label classification.
7. The method for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems according to claim 2, characterized in that, Step S42 includes: Based on the second label classification of rural open areas, a secondary point cloud data collection route for low-altitude drone flight is planned for the area corresponding to the second label classification. Point cloud data is collected according to the described route, and after data noise reduction, secondary point cloud data is obtained. Feature extraction and feature fusion are performed on the secondary point cloud data to obtain the foreground region and category containing power targets; A deep learning model pre-trained using images of low-voltage distribution network facilities; A trained deep learning model is used to perform secondary identification and classification of the foreground region and category containing power targets, extract the feature parameters of each power target, and model the power system in rural open areas based on the extracted feature parameters.
8. The method for three-dimensional point cloud acquisition and modeling of digital twins for rural power systems according to claim 6, characterized in that, In step S43, a three-dimensional model of the power system of the residential area is automatically constructed by acquiring ground images, or a building model generated from a two-dimensional or three-dimensional map of the residential area is used to input the tags of the target in order to construct a three-dimensional model of the power system of the residential area.
9. A three-dimensional point cloud acquisition and modeling system for digital twins of rural power systems, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for three-dimensional point cloud acquisition and modeling of digital twins of rural power systems as described in any one of claims 1-8.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the three-dimensional point cloud acquisition and modeling method for digital twins of rural power systems as described in any one of claims 1 to 8.