Method for carrying out equipment modeling based on equipment parameters in distribution network line

By preprocessing and registering the point cloud data of power facilities, combined with the Delaunay triangulation algorithm, an accurate three-dimensional model of power towers and power lines was constructed, solving the problem of insufficient accuracy of three-dimensional modeling in the existing technology, and meeting the Safety distance requirements for high-voltage transmission lines when crossing and accurate identification requirements for circuit inspection.

CN119091080APending Publication Date: 2024-12-06STATE GRID ANHUI ELECTRIC POWER CO LTD ELECTRIC POWER SCI RES INST +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411030030.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing three-dimensional modeling method of laser point cloud based on power lines and power towers is still insufficient in terms of accuracy and reliability, and it is difficult to meet the safety distance requirements and circuit inspections of high-voltage or ultra-high voltage transmission lines when crossing rivers, highways, and railways. accuracy.

Method used

By acquiring point cloud data of power facilities, pre-processing is performed to remove noise and invalid data, point cloud registration is performed, data is aligned to a common coordinate system, and a three-dimensional model of power towers and power lines is constructed using the Delaunay triangulation algorithm.

Benefits of technology

The three-dimensional model of the power line and power tower is realized based on laser point cloud, which improves the accuracy and reliability of the three-dimensional modeling of power facilities, meets the precise identification needs of circuit inspections, and ensures compliance with safe distances.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091080A_ABST
    Figure CN119091080A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a method for carrying out equipment modeling based on equipment parameters in a distribution network line, and belongs to the technical field of distribution network line modeling. The method comprises the following steps: acquiring point cloud data about electric power facilities in a circuit inspection process in a distribution network line; preprocessing the point cloud data to remove noise, discrete points and invalid data in the point cloud data; performing point cloud registration on the preprocessed point cloud data so as to align the point cloud data into a common coordinate system; and performing three-dimensional reconstruction and modeling on the aligned point cloud data to construct a three-dimensional model about the power tower and the power line. According to the modeling method, the three-dimensional model about the power line and the power tower can be accurately constructed based on the laser point cloud.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network route modeling, and in particular to a method for performing equipment modeling based on equipment parameters in a distribution network line. Background Art

[0002] When high-voltage or ultra-high-voltage transmission lines cross over rivers, roads, and railways, a small safety distance can easily cause power accidents. Therefore, in order to meet the requirements for the horizontal safety distance of high-voltage and ultra-high-voltage transmission lines crossing rivers, roads, and railways and the accuracy required during the circuit inspection of distribution network routes, accurate identification of rivers, roads, and railways is particularly important.

[0003] At present, during the circuit inspection process, the method of three-dimensional modeling based on the laser point cloud of the existing power lines and power towers is still insufficient in accuracy and reliability, and the method of three-dimensional modeling based on the laser point cloud of the power lines and power towers still needs to be improved. Summary of the invention

[0004] The purpose of the embodiment of the present invention is to provide a method for equipment modeling based on equipment parameters in a distribution network line, which can accurately construct a three-dimensional model of power lines and power towers based on laser point clouds.

[0005] In order to achieve the above object, on the one hand, an embodiment of the present invention provides a method for device modeling based on device parameters in a distribution network line, the method comprising:

[0006] Obtain point cloud data about power facilities during circuit inspection in distribution network lines;

[0007] Preprocessing the point cloud data to remove noise, discrete points and invalid data in the point cloud data;

[0008] Performing point cloud registration on the preprocessed point cloud data to align the point cloud data into a common coordinate system;

[0009] The aligned point cloud data are three-dimensionally reconstructed and modeled to construct a three-dimensional model of the power tower and power lines.

[0010] Optionally, obtaining point cloud data about power facilities during circuit inspection in the distribution network includes:

[0011] The drone performs a laser radar scan on the power facilities to obtain data samples, wherein the power facilities include power lines and power towers;

[0012] Marking data of ground points in the data sample;

[0013] According to the feature that the power tower and the power line must be placed above the ground, data above the ground point are selected;

[0014] The data above the ground point is marked as point cloud data including the power tower and the power line.

[0015] Optionally, preprocessing the point cloud data to remove noise, discrete points and invalid data in the point cloud data includes:

[0016] Acquiring point cloud data about the power tower and power lines;

[0017] Marking the point cloud data to obtain a set of marked points in the point cloud data about the approximate directions of the power tower and the power line as a training point set;

[0018] Obtaining points in the point cloud data excluding the training point set as points to be divided;

[0019] Obtaining the distance between each of the points to be divided and each of the points in the training point set;

[0020] Arranging the distances between each of the points to be divided and the points in the training point set in ascending order;

[0021] Selecting a point in the training point set whose distance is within the preset distance;

[0022] Obtaining the category of the point with the highest frequency of occurrence in the training point set within the preset distance;

[0023] Classifying the points to be classified into the category of the points with the highest frequency of occurrence in the training point set;

[0024] The points that cannot be classified are removed from the points to be classified.

[0025] Optionally, preprocessing the point cloud data to remove noise, discrete points and invalid data in the point cloud data includes:

[0026] Acquire the classified point cloud data;

[0027] Dividing each category of the point cloud data into data sets corresponding to points in the training point set;

[0028] Determining the orientation of the point cloud in the data set;

[0029] Determining a span of the point cloud in the data set according to the direction of the point cloud in the data set, wherein the span includes a length of the span and a direction of the span;

[0030] Dividing the data set into intervals according to the orientation of the first point cloud in the data set and the span to obtain an interval point set;

[0031] Obtain all point cloud data in the interval point set and mark them;

[0032] Select any one point cloud data in the interval point set, and determine whether the number of the point cloud data in the interval point set whose distance to the selected point cloud data is less than a set distance is greater than a set number;

[0033] When the number of point cloud data whose distance from the selected point cloud data is less than a set distance among the remaining point cloud data in the interval point set is greater than a set number, determining the selected point cloud data as subsequent point cloud data;

[0034] When the number of the point cloud data whose distance from the selected point cloud data is less than a set distance among the remaining point cloud data in the interval point set is not greater than a set number, removing the point cloud data;

[0035] All the post-point cloud data are collected to obtain pre-processed point cloud data.

[0036] Optionally, performing point cloud registration on the preprocessed point cloud data to align the point cloud data into a common coordinate system includes:

[0037] Acquire the preprocessed point cloud data;

[0038] Acquire an initial point cloud corresponding to the point cloud data in a unified coordinate system, wherein the Euclidean distance between points in the initial point cloud and corresponding points in the point cloud data is the minimum;

[0039] Calculate a new transformation matrix based on the correspondence between the points in the point cloud data and the corresponding points in the initial point cloud;

[0040] Performing a rigid transformation on the initial point cloud according to the transformation matrix to obtain a new point cloud set;

[0041] Determining whether the initial point cloud meets the requirements according to the average distance between the new point cloud set and the corresponding points in the corresponding point cloud data;

[0042] When the average distance meets the requirement, an initial point cloud corresponding to the point cloud data is obtained.

[0043] Optionally, performing point cloud registration on the preprocessed point cloud data to align the point cloud data into a common coordinate system includes:

[0044] When the average distance does not meet the requirement, return to the step of obtaining an initial point cloud corresponding to the point cloud data in a unified coordinate system, wherein the Euclidean distance between points in the initial point cloud and corresponding points in the point cloud data is the smallest.

[0045] Optionally, performing three-dimensional reconstruction and modeling on the aligned point cloud data to construct a three-dimensional model of the power tower and the power line includes:

[0046] Acquire initial data corresponding to the point cloud data in a unified coordinate system;

[0047] Get the coordinate data of each point in the initial data;

[0048] Generate a triangular mesh according to the Delaunay triangulation algorithm and the coordinate data of the points in the initial data;

[0049] The triangular mesh is fitted to obtain a three-dimensional model.

[0050] Optionally, the three-dimensional model includes a three-dimensional model of the power tower and the power lines.

[0051] On the other hand, the present invention also provides a modeling system for electric power facilities, the modeling system comprising:

[0052] Data acquisition module, which acquires laser point clouds about power towers and power lines;

[0053] The data processing module obtains the laser point cloud and executes the method for device modeling based on device parameters in the distribution network line as described above.

[0054] On the other hand, the present invention further provides a machine-readable storage medium having instructions stored thereon, wherein the instructions are used to enable a machine to execute a method for performing device modeling based on device parameters in a distribution network line as described above.

[0055] Through the above technical solution, the present invention provides a method for equipment modeling based on equipment parameters in a distribution network line. By acquiring point cloud data about power towers and power lines, the point cloud data can be preprocessed to remove useless points such as noise, discrete points and invalid data in the point cloud data. After preprocessing the point cloud data, the preprocessed point cloud data can be point cloud registered to align the point cloud data to a common coordinate system for subsequent modeling. After aligning the point cloud data, the aligned point cloud data can be three-dimensionally reconstructed and modeled, so that a three-dimensional model of the power tower and power line can be constructed. This method can accurately construct a three-dimensional model of power lines and power towers based on laser point clouds.

[0056] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0058] Figure 1 is an overall flow chart of a method for performing device modeling based on device parameters in a distribution network line according to an embodiment of the present invention;

[0059] Figure 2 is a flowchart of obtaining point cloud data of a method for performing device modeling based on device parameters in a distribution network line according to an embodiment of the present invention;

[0060] Figure 3 is a first flow chart of preprocessing point cloud data according to a method for device modeling based on device parameters in a distribution network line according to an embodiment of the present invention;

[0061] Figure 4 is a second flow chart of preprocessing point cloud data according to a method for device modeling based on device parameters in a distribution network line according to an embodiment of the present invention;

[0062] Figure 5 is a flowchart of point cloud registration of a method for device modeling based on device parameters in a distribution network line according to an embodiment of the present invention;

[0063] Figure 6 It is a flowchart of constructing a three-dimensional model of a method for equipment modeling based on equipment parameters in a distribution network line according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0065] Figure 1 The overall flow chart of a method for device modeling based on device parameters in a distribution network line according to an embodiment of the present invention. In the present invention, the process of the method for device modeling based on device parameters in a distribution network line may include:

[0066] In step S1, point cloud data about power facilities during circuit inspection in a distribution network is obtained.

[0067] In step S2, the point cloud data is preprocessed to remove noise, discrete points and invalid data in the point cloud data.

[0068] In step S3, point cloud registration is performed on the pre-processed point cloud data to align the point cloud data into a common coordinate system.

[0069] In step S4, the aligned point cloud data is 3D reconstructed and modeled to construct a 3D model of the power tower and power lines.

[0070] In the present invention, during the circuit inspection process of the distribution network route, it may be necessary to perform three-dimensional modeling on the power equipment on the inspection route to mark it to avoid safety accidents such as collisions. When three-dimensional modeling is performed on the power tower and the power line, point cloud data about the power tower and the power line can be obtained, and then the point cloud data can be preprocessed so that the preprocessed point cloud data can more accurately reflect the power tower and the power line. After the point cloud data is preprocessed, the preprocessed point cloud data can be aligned, and then each point cloud data can be aligned to a common coordinate system to facilitate subsequent modeling processing. After the point cloud data is aligned, the aligned point cloud data can be three-dimensionally reconstructed and modeled to accurately construct a three-dimensional model of the power tower and the power line.

[0071] In one embodiment of the present invention, Figure 2 As shown, the process of obtaining point cloud data may include:

[0072] In step S5, the drone performs a lidar scan on the power tower and power lines to obtain data samples.

[0073] In step S6, the data of the ground points in the data sample are labeled.

[0074] In step S7, according to the feature that power towers and power lines must be placed above the ground, data above the ground point is selected.

[0075] In step S8, the data above the ground point is marked as point cloud data containing power towers and power lines.

[0076] In the present invention, when the drone performs a laser radar scan on the power tower and the power line to obtain a data sample. Because in the acquired data sample, the intervals between the power towers are large, and in the data up to one kilometer, the number of power towers does not exceed ten, when three-dimensional modeling is performed based on the laser point cloud of the acquired power tower and power line, the number of power towers is too small, which may affect the training of the network model. Therefore, in the acquired data sample, multiple point cloud data about the power tower can be included to facilitate subsequent three-dimensional modeling. When the data sample is obtained, the data of the ground point can be marked according to the characteristics of the power tower, power line and ground in the data sample. Because the power tower and power line must be placed above the ground, the data above the ground point can be selected according to the characteristics of the power tower and power line above the ground. After obtaining the data above the ground point, the data can contain the power tower and the power line, and the data can be marked as point cloud data containing the power tower and the power line.

[0077] In one embodiment of the present invention, Figure 3 As shown, the first process of preprocessing point cloud data may include:

[0078] In step S9 , point cloud data on power towers and power lines is acquired.

[0079] In step S10 , the point cloud data is marked to obtain a set of marked points on the power tower and the power line in the point cloud data as a training point set.

[0080] In step S11, points in the point cloud data excluding the training point set are calculated as points to be divided.

[0081] In step S12, the distance between the point to be classified and each point in the training point set is obtained.

[0082] In step S13, the distances between the points to be divided and the points in the training point set are arranged in ascending order.

[0083] In step S14, points in the training point set whose distance is within a preset distance are selected.

[0084] In step S15, the category of the point with the highest frequency in the training point set within the preset distance is obtained.

[0085] In step S16, the point to be classified is classified into the category of the point with the highest frequency in the training point set.

[0086] In step S17, the points that cannot be classified are removed from the points to be classified.

[0087] In the present invention, after obtaining the point cloud data about the power tower and the power line, the point cloud data may contain the remaining point cloud data irrelevant to the power tower and the power line. Therefore, the point cloud data can be preprocessed to eliminate the point cloud irrelevant to the power tower and the power line in the point cloud data to avoid affecting the subsequent modeling of the power line and the power tower. When preprocessing the point cloud data, part of the point cloud in the point cloud data can be marked as point cloud about the power tower and the power line, so that the marked point set of the part of the point cloud data about the power tower and the power line can be obtained, and then the marked point set can be used as a training point set. The training point set can represent the approximate direction and distribution of the power tower and the power line. After obtaining the training point set, the points in the point cloud data excluding the training point set can be obtained as points to be divided. After obtaining the points to be divided, the distance between each point to be divided and each point in the training point set can be obtained according to the distribution of each point to be divided and the distribution of the training point set, and then the distance between each point to be divided and each point in the training point set can be arranged in an increasing relationship. After obtaining the sorting of the distances between the point to be divided and each point in the training point set, the point in the training point set whose distance to the point to be divided is within a preset distance can be selected. The points in the training point set can be divided into different attributes and can represent different categories, including points representing power towers and power lines. After obtaining the points in the training point set within a certain range of the point to be divided, because there is more than one point in the training point set within a certain range of the divided point, the certain range can be a preset distance, and the category of the points in the training point set within the preset distance from the point to be divided can be obtained, and then the category of the point with the highest frequency of occurrence within the range can be selected, that is, the category with the highest frequency of occurrence within the range is selected, and then the divided point can be classified into the category of the point with the highest frequency of occurrence. The points in the training point set can represent different categories, and when representing different categories, they can be regarded as different points. Because the training point set can represent the general direction and distribution of the power tower and power line, when the remaining points are screened and classified, they are screened by the distance between each point and the points in the training point set. Then, the points representing the power tower will not be classified as representing the power line, and the remaining points that are too far away from the power tower and power line and have nothing to do with the power tower and power line will neither be classified as the power tower nor the power line, and can be removed to avoid affecting the subsequent modeling of the power tower and power line.

[0088] In one embodiment of the present invention, Figure 4 As shown, the second process of preprocessing the point cloud data may include:

[0089] In step S18, the classified point cloud data is obtained.

[0090] In step S19, each category of point cloud data is divided into data sets corresponding to points in the training point set.

[0091] In step S20 , the orientation of the point cloud in the data set is determined.

[0092] In step S21 , the span of the point cloud in the data set is determined according to the direction of the point cloud in the data set, where the span includes the length of the span and the direction of the span.

[0093] In step S22, the data set is divided into intervals according to the orientation and span of the first point cloud in the data set to obtain interval point sets.

[0094] In step S23, all point cloud data in the interval point set are obtained and marked.

[0095] In step S24, any point cloud data in the interval point set is selected, and it is determined whether the number of point cloud data whose distance to the selected point cloud data is less than a set distance among the remaining point cloud data in the interval point set is greater than a set number.

[0096] In step S25, when the number of point cloud data whose distance to the selected point cloud data is less than a set distance among the remaining point cloud data in the interval point set is greater than a set number, the selected point cloud data is determined to be the subsequent point cloud data.

[0097] In step S26, when the number of point cloud data whose distance to the selected point cloud data is less than a set distance among the remaining point cloud data in the interval point set is not greater than a set number, the point cloud data is removed.

[0098] In step S27, all post-point cloud data are collected to obtain pre-processed point cloud data.

[0099] In the present invention, after the point cloud data is classified, because the preset distance of the classification may be too large, some discrete points that do not belong to the power lines and power towers will be attributed to the point cloud data of the power lines or power towers. Therefore, the classified point cloud data can be further screened so that the pre-processed point cloud can correspond to the power lines and power towers more accurately. When screening, the classified point cloud data can be obtained first, and then each type of point cloud data can be divided into data sets corresponding to the points in the previous training point set. Each point in the training point set corresponds to a data set. After obtaining the data set, the direction of the point cloud in the data set can be determined according to the position of the points in the data set, and then the span of the point cloud in the data set can be determined according to the direction of the point cloud in the data set. The span can be a vector, including the length of the span and the direction of the span. After obtaining the span, the data set can be divided into intervals according to the orientation of the first point cloud in the data set and the span, so that multiple interval point sets can be obtained. If the point clouds in the same interval point set all represent the same power line or power tower, the distances between the interval point sets can be within a certain distance range. Therefore, after obtaining the interval point set, all the point cloud data in the interval point set can be obtained, and all the point cloud data in the interval point set can be marked. After obtaining the marked interval point set, any point cloud data in the interval point set can be selected, and it can be determined whether the number of point cloud data whose distance to the selected point cloud data is less than the set distance in the remaining point cloud data in the interval point set is greater than the set number, so that the point cloud that meets the requirements can be further screened according to the rule. When the number of point cloud data whose distance to the selected point cloud data is less than the set distance in the remaining point cloud data in the interval point set is greater than the set number, it can be determined that the selected point cloud data is the later point cloud data. When the number of point cloud data whose distance to the selected point cloud data is less than the set distance in the remaining point cloud data in the interval point set is not greater than the set number, the point cloud data can be removed. After all the post-point cloud data are obtained, they can be aggregated to obtain pre-processed point cloud data. The pre-processed point cloud data can more accurately screen the point cloud that meets the requirements, so that it is easier to build a three-dimensional model based on the point cloud.

[0100] In one embodiment of the present invention, Figure 5 As shown, the process of point cloud registration may include:

[0101] In step S28, the pre-processed point cloud data is obtained.

[0102] In step S29, an initial point cloud corresponding to the point cloud data is obtained in the unified coordinate system, and the Euclidean distance between the points in the initial point cloud and the corresponding points in the point cloud data is the minimum.

[0103] In step S30, a new transformation matrix is ​​calculated according to the correspondence between the points in the point cloud data and the corresponding points in the initial point cloud.

[0104] In step S31, a rigid transformation is performed on the initial point cloud according to the transformation matrix to obtain a new point cloud set.

[0105] In step S32, it is determined whether the initial point cloud meets the requirements based on the average distance between the new point cloud set and the corresponding points in the point cloud data.

[0106] In step S33, when the average distance meets the requirement, an initial point cloud corresponding to the point cloud data is obtained.

[0107] In the present invention, because the point cloud data may contain multiple point cloud sets, the point cloud data can be aligned to a common coordinate system, which can facilitate subsequent point checking and modeling. After preprocessing the point cloud data, the initial point cloud corresponding to the preprocessed point cloud data can be obtained in the same coordinate system, and the Euclidean distance between the points in the initial point cloud and the corresponding points in the point cloud data can be minimized. Then, the transformation matrix of the type can be calculated through the correspondence between the points in the point cloud data and the points in the initial point cloud. After obtaining the transformation matrix, the initial point cloud can be rigidly transformed according to the transformation matrix, so that a new point cloud set can be obtained. The average distance between the new point cloud set and the corresponding points in the corresponding point cloud data is used to determine whether the initial point cloud meets the requirements. When the average distance meets the requirements, the initial point cloud can be a point cloud that meets the requirements, and then the initial point cloud corresponding to the point cloud data can be obtained.

[0108] In one embodiment of the present invention, Figure 5 As shown, when the average distance does not meet the requirements, the process can return to step S29. The process of returning to step S29 can re-iterate the initial point cloud until the initial point cloud meets the requirements, thereby aligning the data point cloud to the same coordinate system.

[0109] In one embodiment of the present invention, Figure 6 As shown, the process of building a three-dimensional model may include:

[0110] In step S34, initial data corresponding to the point cloud data in the unified coordinate system is acquired.

[0111] In step S35, the coordinate data of each point in the initial data is obtained.

[0112] In step S36 , a triangular mesh is generated according to the Delaunay triangulation algorithm and the coordinate data of the points in the initial data.

[0113] In step S37, the triangular mesh is fitted to obtain a three-dimensional model.

[0114] In the present invention, after obtaining the initial data in the unified coordinate system, the coordinate data of each point in the initial data can be obtained. After obtaining the coordinate data, a triangular mesh can be generated according to the Delaunay triangulation algorithm and the coordinate data of the points in the initial data. The triangular mesh can represent the specific contours of the power line and the power tower, so after obtaining the triangular mesh, the triangular mesh can be fitted to obtain a three-dimensional model.

[0115] In one embodiment of the present invention, the three-dimensional model may include a three-dimensional model of the power tower and the power line.

[0116] On the other hand, the present invention can also provide a modeling system for power facilities, and the modeling system can include: a data acquisition module and a data processing module. The data acquisition module can acquire laser point clouds about power towers and power lines. The data processing module can acquire the laser point clouds and can execute the method for performing device modeling based on device parameters in a distribution network line as described above.

[0117] On the other hand, the present invention may also provide a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute a method for performing device modeling based on device parameters in a distribution network line as described above.

[0118] Through the above technical solution, the present invention provides a method for equipment modeling based on equipment parameters in a distribution network line. By acquiring point cloud data about power towers and power lines, the point cloud data can be preprocessed to remove useless points such as noise, discrete points and invalid data in the point cloud data. After preprocessing the point cloud data, the preprocessed point cloud data can be point cloud registered to align the point cloud data to a common coordinate system for subsequent modeling. After aligning the point cloud data, the aligned point cloud data can be three-dimensionally reconstructed and modeled, so that a three-dimensional model of the power tower and power line can be constructed. This method can accurately construct a three-dimensional model of power lines and power towers based on laser point clouds.

[0119] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0123] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0124] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0125] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0126] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0127] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for device modeling based on device parameters in a distribution network line, characterized in that: The method comprises: Obtain point cloud data about power facilities during circuit inspection in distribution network lines; Preprocessing the point cloud data to remove noise, discrete points and invalid data in the point cloud data; Performing point cloud registration on the preprocessed point cloud data to align the point cloud data into a common coordinate system; The aligned point cloud data are three-dimensionally reconstructed and modeled to construct a three-dimensional model of the power tower and power lines.

2. The method according to claim 1, characterized in that The point cloud data of power facilities obtained during the circuit inspection of the distribution network includes: The drone performs a laser radar scan on the power facilities to obtain data samples, wherein the power facilities include power lines and power towers; Marking data of ground points in the data sample; According to the feature that the power tower and the power line must be placed above the ground, data above the ground point are selected; The data above the ground point is marked as point cloud data including the power tower and the power line.

3. The method according to claim 1, characterized in that: Preprocessing the point cloud data to remove noise, discrete points and invalid data in the point cloud data includes: Acquiring point cloud data about the power tower and power lines; Marking the point cloud data to obtain a set of marked points in the point cloud data about the approximate directions of the power tower and the power line as a training point set; Obtaining points in the point cloud data excluding the training point set as points to be divided; Obtaining the distance between each of the points to be divided and each of the points in the training point set; Arranging the distances between each of the points to be divided and the points in the training point set in ascending order; Selecting a point in the training point set whose distance is within the preset distance; Obtaining the category of the point with the highest frequency of occurrence in the training point set within the preset distance; Classifying the points to be classified into the category of the points with the highest frequency of occurrence in the training point set; The points that cannot be classified are removed from the points to be classified.

4. The method according to claim 3, characterized in that Preprocessing the point cloud data to remove noise, discrete points and invalid data in the point cloud data includes: Acquire the classified point cloud data; Dividing each category of the point cloud data into data sets corresponding to points in the training point set; Determining the orientation of the point cloud in the data set; Determining a span of the point cloud in the data set according to the direction of the point cloud in the data set, wherein the span includes a length of the span and a direction of the span; Dividing the data set into intervals according to the orientation of the first point cloud in the data set and the span to obtain an interval point set; Obtain all point cloud data in the interval point set and mark them; Select any one point cloud data in the interval point set, and determine whether the number of the point cloud data in the interval point set whose distance to the selected point cloud data is less than a set distance is greater than a set number; When the number of point cloud data whose distance from the selected point cloud data is less than a set distance among the remaining point cloud data in the interval point set is greater than a set number, determining the selected point cloud data as subsequent point cloud data; When the number of the point cloud data whose distance from the selected point cloud data is less than a set distance among the remaining point cloud data in the interval point set is not greater than a set number, removing the point cloud data; All the post-point cloud data are collected to obtain pre-processed point cloud data.

5. The method according to claim 4, characterized in that Performing point cloud registration on the preprocessed point cloud data to align the point cloud data into a common coordinate system includes: Acquire the preprocessed point cloud data; Acquire an initial point cloud corresponding to the point cloud data in a unified coordinate system, wherein the Euclidean distance between points in the initial point cloud and corresponding points in the point cloud data is the minimum; Calculate a new transformation matrix based on the correspondence between the points in the point cloud data and the corresponding points in the initial point cloud; Performing a rigid transformation on the initial point cloud according to the transformation matrix to obtain a new point cloud set; Determining whether the initial point cloud meets the requirements according to the average distance between the new point cloud set and the corresponding points in the corresponding point cloud data; When the average distance meets the requirement, an initial point cloud corresponding to the point cloud data is obtained.

6. The method according to claim 5, characterized in that Performing point cloud registration on the preprocessed point cloud data to align the point cloud data into a common coordinate system includes: When the average distance does not meet the requirement, return to the step of obtaining an initial point cloud corresponding to the point cloud data in a unified coordinate system, wherein the Euclidean distance between points in the initial point cloud and corresponding points in the point cloud data is the smallest.

7. The method according to claim 5, characterized in that The aligned point cloud data is subjected to three-dimensional reconstruction and modeling to construct a three-dimensional model of the power tower and the power line, including: Acquire initial data corresponding to the point cloud data in a unified coordinate system; Get the coordinate data of each point in the initial data; Generate a triangular mesh according to the Delaunay triangulation algorithm and the coordinate data of the points in the initial data; The triangular mesh is fitted to obtain a three-dimensional model.

8. The method according to claim 7, characterized in that The three-dimensional model includes a three-dimensional model of the power tower and the power line.

9. A modeling system for electric power facilities, characterized in that: The modeling system comprises: Data acquisition module, which acquires laser point clouds about power towers and power lines; A data processing module is used to obtain the laser point cloud and execute a method for device modeling based on device parameters in a distribution network line as described in any one of claims 1 to 8.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for causing a machine to execute a method for performing device modeling based on device parameters in a distribution network line as described in any one of claims 1 to 8.