Flat area power transmission line sag measurement method based on airborne laser radar

Through RandLA-Net model and filtering, clustering, and projection fitting technology, the problems of conductor defects and low measurement accuracy in the sag measurement of transmission lines are solved, and more efficient and accurate sag measurement is achieved, which is suitable for power transmission in flat areas. line.

CN119090939AActive Publication Date: 2024-12-06SHANGHAI UNIVERSITY OF ELECTRIC POWER

Patent Information

Application Number
CN202411212461.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-12-06
Estimated Expiration
2044-08-30

AI Technical Summary

Technical Problem

The prior art has problems such as low measurement accuracy, manual operation risk, high cost and limited applicability in the measurement of transmission line sag. Especially in airborne lidar applications in flat areas, the defect of the conductor affects the measurement accuracy of the sag.

Method used

The point cloud semantic segmentation model based on RandLA-Net is used to determine the conductor suspension point. Through filtering denoising, clustering, projection fitting and rotation reconstruction technologies, the integrity of the conductor point cloud and the accuracy of the sag measurement are improved.

Benefits of technology

It improves the accuracy and efficiency of sag measurement, reduces the difficulty of selecting wire suspension points, avoids manual measurement of personnel risks, and is suitable for fast and accurate measurement of transmission lines in flat areas.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090939A_ABST
    Figure CN119090939A_ABST
Patent Text Reader

Abstract

The invention relates to a flat area power transmission line sag measurement method based on an airborne laser radar, and the method comprises the steps: obtaining the point cloud data of a power transmission line, and carrying out the preprocessing; performing point cloud segmentation by adopting a pre-constructed RandLA-Net-based point cloud semantic segmentation model to obtain an electric tower point cloud and a conductor point cloud; conducting wire point clouds closest to the electric tower point clouds are clustered, and conducting wire suspension points and unit span power transmission line point clouds are determined; projection and straight line fitting are carried out based on the unit span power transmission line point clouds, and a plurality of three-dimensional conductor point clouds are identified; fitting the curve point cloud, performing quality evaluation on the three-dimensional traverse point cloud, and determining the point cloud of the traverse missing at the lowest point; reconstructing the incomplete point cloud; and based on the reconstructed point cloud, according to the condition that the heights of the two conductor suspension points are the same and the heights of the two conductor suspension points are different, calculating a unit span power transmission line sag value. Compared with the prior art, the method has the advantages of improving the measurement efficiency and precision and the like.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of power transmission technology, and in particular to a method for measuring the sag of power transmission lines in flat areas based on an airborne laser radar. Background Art

[0002] In the power transmission system, the safety and stability of the transmission line are crucial to power operation. Among them, sag is one of the important indicators for evaluating the status of the transmission line. Sag refers to the bending or sagging state of the transmission line due to its own weight and external forces. In the transmission line, due to the weight of the line itself and the influence of external factors such as wind and temperature, the line will present a certain degree of curve, which is the sag. Excessive or too small sag may cause serious harm to the transmission line and the power system. When the sag is too large, the risk of contact between the transmission line and the ground or surrounding objects increases, which may cause safety hazards such as electric shock accidents or fires, and large sag will increase the vibration of the line, affecting the stability and reliability of the power system. When the sag is too small, it may cause excessive force on the transmission line, causing problems such as line breakage or tower tilting. Therefore, in the operation of the transmission line, it is necessary to measure the sag regularly to ensure that the sag is within a safe range.

[0003] The main methods for measuring the sag of transmission lines are: (1) Traditional manual measurement method, which uses measuring tools such as measuring ropes or distance meters for measurement. However, this method is limited by factors such as terrain and weather, and has high labor costs; (2) Stress measurement method, which uses devices such as tension sensors or strain gauges to directly measure the tension or stress in the transmission line, and then derives the sag of the line. However, this method requires the installation of sensors on the transmission line, resulting in high engineering costs and may affect the normal operation of the transmission line; (3) Image measurement method, which uses a camera to obtain line images and uses image processing and computer vision technology for measurement, avoiding the safety risks of touching the line. However, it is affected by environmental conditions, the image quality is unstable, and complex image processing algorithms are required. Its applicability is limited by line obstruction and complex terrain. (4) LiDAR measurement method uses LiDAR to obtain three-dimensional point cloud data of transmission lines and their sag points, and realizes sag measurement by analyzing the point cloud data. Based on different scanning methods, LiDAR measurement method is divided into ground-based LiDAR measurement method and airborne LiDAR measurement method. Ground-based LiDAR measurement method is limited by limited coverage range and high time cost, while airborne LiDAR measurement method has the advantages of quickly covering a large area and obtaining elevation information.

[0004] When using LiDAR to measure the sag of transmission lines, the methods of manually selecting the suspension points of transmission lines and using machine learning methods to segment transmission lines and towers and then selecting suspension points are often very complicated. These methods require a lot of effort and require constant adjustment of threshold parameters to adapt to different point cloud data. In contrast, the transmission line point cloud semantic segmentation network based on RandLA-Net can complete the tasks of transmission line segmentation and suspension point determination more efficiently and intelligently. In addition, when the airborne LiDAR scans the transmission line, due to the difference in reflection intensity and the resolution and accuracy limitations of the LiDAR, the scanned wires are discontinuous. If the lowest point of the wire is incomplete, it will greatly affect the accuracy of the sag measurement. Summary of the invention

[0005] The purpose of the present invention is to provide a method for measuring the sag of a power transmission line in a flat area based on an airborne laser radar, which improves the accuracy of the sag measurement.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method for measuring sag of a transmission line in a flat area based on an airborne laser radar comprises the following steps:

[0008] Acquire and pre-process transmission line point cloud data, wherein the transmission line point cloud data is obtained by scanning an airborne laser radar in a flat area;

[0009] Based on the pre-processed transmission line point cloud data, the pre-built RandLA-Net-based point cloud semantic segmentation model is used to perform point cloud segmentation, and the semantic segmentation results are obtained, including the tower point cloud and the conductor point cloud.

[0010] Clustering the wire point cloud closest to the tower point cloud, determining the wire suspension point, and determining the unit span transmission line point cloud based on the wire suspension point;

[0011] Based on the unit span transmission line point cloud, projection and straight line fitting are performed to identify multiple three-dimensional conductor point clouds in the unit span transmission line point cloud;

[0012] According to the straight line fitting direction and the identified three-dimensional wire point cloud, the curve point cloud is fitted, and the quality of the three-dimensional wire point cloud is evaluated and the lowest point missing wire point cloud is determined based on the curve point cloud;

[0013] Reconstructing the residual point cloud according to the quality assessment result and the missing wire point cloud at the lowest point;

[0014] Based on the reconstructed point cloud, the sag value of the transmission line per unit span is calculated according to the situations where the heights of the two conductor suspension points are the same and the heights of the two conductor suspension points are different.

[0015] Furthermore, the preprocessing operation includes filtering and denoising processing, and the steps of filtering and denoising processing include:

[0016] Taking any point in the point cloud data of the transmission line as a sampling point, and taking k neighboring points of the sampling point;

[0017] Calculate the Euclidean distance d from the sampling point to the k nearest neighbor points i , the mean m and standard deviation σ of the Euclidean distance are calculated as follows:

[0018]

[0019] Where, d i is the sampling point P j (x j ,y j z j ) is the Euclidean distance to the k nearest neighbors, m is the mean, and σ is the standard deviation;

[0020] The Euclidean distance d i Points larger than m±σ are considered as abnormal points and removed from the transmission line point cloud data.

[0021] Furthermore, the step of determining the wire suspension point includes:

[0022] Calculate the centroid of the highest a points in each cluster as the wire suspension point. For a cluster, the calculation formula of the centroid coordinates is:

[0023]

[0024] Where P b is the centroid coordinate, i.e. the position of the wire suspension point, (x i ,y i , z i ) is the coordinate information of the point cloud in each cluster.

[0025] Furthermore, the step of determining the point cloud of the unit span transmission line includes:

[0026] Using two adjacent electric towers, the Euclidean distance between the wire suspension points is calculated. The calculation formula of the Euclidean distance is:

[0027]

[0028] Where d1 is the wire suspension point P b0 (x0,y0,z0) and the wire suspension point P b1 The Euclidean distance between (x1,y1,z1);

[0029] The Euclidean distances smaller than the set value are classified as the same group of hanging points;

[0030] The point clouds of multiple conductors between two nearest suspension point groups are determined as the point clouds of unit-span transmission lines.

[0031] Furthermore, the step of identifying a plurality of three-dimensional conductor point clouds in the unit span transmission line point cloud comprises:

[0032] Projecting the unit span transmission line point cloud from the XOY direction to obtain a two-dimensional projection point cloud;

[0033] Using the RANSAC algorithm to perform straight line fitting on each wire in the two-dimensional projection point cloud to obtain multiple fitting straight lines;

[0034] The Euclidean distance between the two-dimensional projection point cloud and the plurality of fitting straight lines is calculated to realize the recognition of the plurality of three-dimensional conductor point clouds in the unit span transmission line point cloud.

[0035] Furthermore, the step of realizing the identification of multiple three-dimensional conductor point clouds in the unit span transmission line point cloud includes:

[0036] In the two-dimensional projected point cloud, the Euclidean distance from each point to each fitted straight line is calculated, and the calculation expression is:

[0037]

[0038] Where d2 is the Euclidean distance from each point in the two-dimensional projection point cloud to each fitted line, (x, y) represents the point in the two-dimensional projection point cloud, Ax+By+C=0 represents the fitted line, and A, B, and C are the line coefficients;

[0039] According to the calculated Euclidean distance, the point closest to each fitting line is regarded as the two-dimensional point cloud corresponding to each fitting line, so as to realize the recognition of multiple two-dimensional wire point clouds;

[0040] According to the X-coordinate and Y-coordinate information and the Z-coordinate index of the two-dimensional wire point cloud, the Z-coordinate index information is restored to realize the recognition of multiple three-dimensional wire point clouds.

[0041] Furthermore, the step of fitting the curve point cloud includes:

[0042] The three-dimensional wire point cloud is rotated from the Z axis to the X axis and parallel to the straight line fitting direction, where the rotation angle θ and the rotation matrix R of the three-dimensional wire point cloud are respectively:

[0043]

[0044] In the formula, A and B are linear coefficients;

[0045] According to the rotation result, the rotated wire point cloud is obtained, and the expression is:

[0046] A2=R*A1

[0047] Where A2 is the wire point cloud after rotation, and A1 is the original wire point cloud, that is, the three-dimensional wire point cloud before rotation;

[0048] The rotated wire point cloud is projected in the XOZ plane direction to obtain a two-dimensional point cloud B1, and a quadratic curve is fitted on the two-dimensional point cloud B1 using the least squares method;

[0049] The curve point cloud B2 is generated at equal intervals according to the fitted quadratic curve.

[0050] Furthermore, the steps of performing quality assessment of the three-dimensional wire point cloud and determining the lowest point missing wire point cloud include:

[0051] Calculate the distance from each point in the curve point cloud to the nearest multiple points on the rotated wire point cloud A2, and calculate the average distance;

[0052] Determine the relationship between the average distance and the set threshold value, and obtain the quality assessment results of the three-dimensional wire point cloud, including a complete point cloud, a slightly residual point cloud, a moderately residual point cloud, and a heavily residual point cloud;

[0053] The partial points with the lowest height of the two-dimensional point cloud are taken, and the partial points are subjected to incomplete detection, and the incomplete three-dimensional wire point cloud detected is used as the lowest point missing wire point cloud.

[0054] Furthermore, the step of reconstructing the residual defect cloud includes:

[0055] For the lowest point missing wire point cloud, the moderate residual defect cloud and the severe residual defect cloud, the curve point cloud B2 is fused with the two-dimensional point cloud B1 generated by the projection of A2 in the XOZ plane direction to obtain a fused point cloud A3;

[0056] In order to restore the Y coordinate information of the fused point cloud A3, the average value of the Y coordinates in the A2 point cloud is used as the Y coordinate of the curve point cloud A3, and the fused point cloud A4 after the Y coordinate information is restored is obtained;

[0057] A4 is rotated to the coordinate system of the original wire point cloud A1 to obtain point cloud A5, which is the incompletely reconstructed point cloud, where A5 is:

[0058] A5=R1*A4

[0059]

[0060] Where R1 is the rotation matrix and θ is the rotation angle.

[0061] Furthermore, the step of calculating the sag value of the transmission line per unit span includes:

[0062] When the heights of the two wire suspension points are the same, in the incompletely reconstructed point cloud A5, the straight line equation l1 is determined according to the wire suspension points A and B, and the distance f from the lowest point C to the straight line equation l1 is calculated, and the distance f is the sag;

[0063] When the heights of the two wire suspension points are different, in the incompletely reconstructed point cloud A5, the straight line equation l1 is determined according to the wire suspension point A and the wire suspension point B, and the vertical distance f1 from the lowest point C1 to the straight line equation l1 is calculated. The vertical distance f1 is the sag of the lowest point. The vertical distance from each point in A5 to l1 is calculated and the maximum value f2 is taken. The maximum value f2 is the maximum sag.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] (1) The present invention reduces the difficulty of selecting the wire suspension points by extracting the wire suspension points on the basis of point cloud segmentation. It evaluates the quality of the wire point clouds and determines the lowest point missing wire point clouds by identifying multiple three-dimensional wire point clouds and fitting curve point clouds. It restores the incomplete wire point clouds by using a reconstruction method, effectively solving the problem of wire incompleteness in the point cloud data of the transmission line, thereby improving the accuracy of sag measurement.

[0066] (2) The present invention utilizes a rotational projection method to reconstruct the incomplete conductor point cloud, thereby further improving the integrity of the conductor point cloud and the accuracy of sag measurement.

[0067] (3) The present invention uses a non-contact airborne 3D laser radar for measurement, which avoids dangerous manual measurement by personnel and provides more accurate and rapid measurement results, providing strong support and technical foundation for the intelligent development of power transmission systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0069] Figure 2 It is a schematic diagram of the projected point cloud straight line fitting and rotation angle calculation of the present invention;

[0070] Figure 3 It is a schematic diagram of the wire point cloud after rotation of the present invention;

[0071] Figure 4 It is a schematic diagram of the projection of the wire point cloud after rotation and the curve fitting of the projection point cloud of the present invention;

[0072] Figure 5This is a schematic diagram of the Y coordinate recovery of the fused point cloud of the present invention;

[0073] Figure 6 A schematic diagram of a wire point cloud after reconstruction according to the present invention;

[0074] Figure 7 It is a schematic diagram of calculating the sag of the same hanging point height according to the present invention;

[0075] Figure 8 Schematic diagram of calculating different sags of suspension point heights according to the present invention;

[0076] Fig. 9 It is a schematic diagram of the transmission line reconstruction and sag measurement process of the present invention;

[0077] Fig.10 This is a visualization comparison diagram of the semantic segmentation of the power transmission line point cloud of the present invention;

[0078] Fig.11 It is a flow chart of wire reconstruction of the present invention. DETAILED DESCRIPTION

[0079] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0080] This embodiment provides a method for measuring the sag of a transmission line in a flat area based on an airborne laser radar. Figure 1 As shown, the method comprises the following steps:

[0081] S1. Use airborne laser radar to scan the transmission line to complete the point cloud data collection of the transmission corridor, and filter the collected transmission line point cloud data.

[0082] Specifically, the filtering process described in step S1 includes:

[0083] Take any point in the point cloud data as a sampling point and take k neighboring points of the sampling point;

[0084] Calculate the sampling point P j (x j ,y j z j ) to the k nearest neighbors. i The mean m and standard deviation σ are calculated as follows:

[0085]

[0086] The sampling point P j (x j ,yj z j ) The points whose Euclidean distance to k nearest neighbor points is greater than m±σ are considered as outliers and are removed.

[0087] S2. After filtering the transmission line point cloud, use Cloud Compare software to label the towers, wires, ground, vegetation, and buildings in the transmission line point cloud, and make a transmission line point cloud semantic segmentation dataset for RandLA-Net point cloud semantic segmentation network model training;

[0088] Among them, the transmission line point cloud semantic segmentation dataset is divided into training set, validation set and test set according to 6:2:2.

[0089] S3, based on the tower point cloud and wire point cloud obtained by semantic segmentation, cluster the wire point cloud closest to the tower point cloud, and calculate the centroid of the highest 50 points in each cluster as the wire hanging point;

[0090] Among them, for a cluster, the calculation formula of the centroid coordinates is:

[0091]

[0092] S4. Determine the point cloud of the transmission line with unit span by using two adjacent towers and their suspension points;

[0093] Specifically, the step of determining the unit span transmission line point cloud in step S4 includes:

[0094] Calculate the distance between the wire suspension points, and classify the two suspension points with a Euclidean distance d1 less than 200 as the same group of suspension points;

[0095] Two suspension points P b0 (x0,y0,z0) and P b1 The Euclidean distance between (x1,y1,z1) is:

[0096]

[0097] The point clouds of multiple conductors between two nearest suspension point groups are determined as the point clouds of unit-span transmission lines.

[0098] S5. In the point cloud coordinate system, XY represents the horizontal and vertical coordinates on the plane, and Z represents the height coordinate perpendicular to the plane. By projecting the unit span transmission line point cloud from the XOY direction, multiple straight line fitting is performed on the two-dimensional transmission line point cloud;

[0099] Specifically, the wire point cloud projection and straight line fitting steps in step S5 include:

[0100] Based on the world coordinates, the point cloud of the unit span transmission line is projected from the XOY direction, and the RANSAC algorithm is used to perform a straight line fitting on each conductor in the two-dimensional point cloud generated by the projection.

[0101] S6. Calculate the Euclidean distance between the projected point cloud and the fitted multiple straight lines to identify multiple conductors in the point cloud of the unit span transmission line;

[0102] Specifically, the step of identifying multiple wires in the unit span transmission line point cloud described in step S6 includes:

[0103] In the projected point cloud, calculate the distance d2 from each point to each line;

[0104] The Euclidean distance formula from a point to a line in a two-dimensional point cloud is:

[0105]

[0106] Then, the point closest to each straight line is regarded as the two-dimensional point cloud corresponding to each straight line to realize the identification of multiple wires in the two-dimensional point cloud. Finally, according to the X-coordinate and Y-coordinate information of the two-dimensional point cloud and its Z-coordinate index, its Z information is restored to realize the identification of multiple wires in the three-dimensional point cloud.

[0107] S7. According to the direction of the fitted straight line, the wire point cloud is rotated along the Z axis until the X axis is parallel to the straight line direction, the rotated point cloud is projected in the XOZ plane direction, and then the curve point cloud is fitted using the least squares method. The quality of the single wire point cloud is evaluated according to the curve point cloud, and it is classified into complete point cloud, slight defect, moderate defect, and severe defect;

[0108] For details, please refer to Figure 2 , Figure 3 and Figure 4 The curve point cloud fitting step after the wire rotation and projection in step S7 includes:

[0109] According to the slope of the fitted straight line L1, the angle at which the point cloud needs to rotate around the Z axis and its rotation matrix R are calculated;

[0110] The formula for calculating the rotation angle around the Z axis is:

[0111]

[0112] The rotation matrix for rotating θ degrees around the Z axis is:

[0113]

[0114] The original point cloud is A1, and the rotated point cloud A2 is:

[0115] A2=R*A

[0116] The rotated point cloud A2 is projected in the XOZ plane direction to obtain a two-dimensional point cloud B1, and a quadratic curve is fitted on the two-dimensional point cloud B1 using the least squares method;

[0117] Generate a curve point cloud B2 at equal intervals according to the fitted quadratic polynomial, and calculate the average distance between each point on the curve point cloud B2 and the nearest 16 points on the point cloud A2;

[0118] The distance threshold is set, and the average distance less than 20 is classified as a complete point cloud, the average distance greater than 20 and less than 100 is classified as a slightly residual point cloud, the average distance greater than 100 and less than 200 is classified as a moderately residual point cloud, and the average distance greater than 200 is classified as a severely residual point cloud.

[0119] S8, based on the part of points with the lowest height in the two-dimensional point cloud B1, detecting whether these parts of points are detected to be incomplete, and if detected to be incomplete, defining the wire point cloud as the wire point cloud with the lowest point missing;

[0120] Take the 150 points with the lowest height of the two-dimensional point cloud B1. If any of these points are detected to be incomplete, the wire point cloud is determined to be the wire point cloud with the lowest point missing.

[0121] S9, for the lowest point missing point cloud, the moderate residual point cloud and the severe residual point cloud, the projection point cloud B1 is fused with the curve point cloud B2, and the average value of the Y coordinate of the point cloud A2 is used as the Y coordinate of the fused point cloud, and finally the fused point cloud is rotated back to the original coordinate system to complete the reconstruction of the residual point cloud;

[0122] For details, please refer to Figure 5 and Figure 6 , the residual cloud reconstruction steps described in step 9 include:

[0123] For the lowest point missing, medium defect and severe residual point cloud, the fitted curve point cloud B2 is fused with the point cloud B1 projected by A2 on the XOZ plane, and the fused point cloud is A3;

[0124] In order to restore the Y coordinate information of the fused point cloud A3, the average value of the Y coordinates in the A2 point cloud is used as the Y coordinate of the point cloud A3. The fused point cloud after restoring the Y coordinate information is A4.

[0125] The point cloud after point cloud A4 is rotated to the point cloud A1 coordinate system is called point cloud A5. Point cloud A5 is the incompletely reconstructed point cloud, and its rotation matrix is ​​R1.

[0126]

[0127] The process of converting point cloud A4 to point cloud A1 coordinate system is as follows:

[0128] A5=R1*A4

[0129] S10, calculating the sag value of the transmission line per unit span according to two situations where the heights of the two suspension points are the same and the heights of the two suspension points are different;

[0130] For details, please refer to Figure 7 and Figure 8 The sag measurement steps for the two cases of the same suspension point height and the different suspension point heights described in step 9 include:

[0131] When the heights of the two suspension points are the same, in the incompletely reconstructed point cloud A5, the straight line equation l1 is determined according to the suspension points A and B, and the distance f from the lowest point C to the straight line equation l1 is calculated, where f is the sag;

[0132] When the heights of the two suspension points are different, in the incompletely reconstructed point cloud A5, the straight line equation l1 is determined according to the suspension points A and B, and the vertical distance f1 from C1 to l1 is calculated, where f1 is the sag of the lowest point. The vertical distance from each point in the point cloud A5 to l1 is calculated and the maximum value is taken, that is, the vertical distance f2 from C2 to l1, where f2 is the maximum sag.

[0133] The embodiment of the present invention provides a verification result for the above-mentioned transmission line sag measurement method in a flat area based on airborne laser radar, wherein a 26.32-kilometer transmission line point cloud in a certain map is intercepted as a transmission line point cloud semantic segmentation dataset, wherein the transmission line reconstruction and sag measurement process is as follows: Fig. 9 As shown in Table 1, the accuracy comparison of the semantic segmentation results of the transmission line point cloud is 97.39%. Fig.10 As shown in Figure 2, the wire reconstruction process is as follows: Fig.11 The sag measurement experimental results are shown in Table 2.

[0134] Table 1: Transmission line point cloud semantic segmentation accuracy

[0135]

[0136] Table 2: Sag measurement test results

[0137] Transmission Lines Measurement value (m) True value (m) Error(m) Accuracy Single line 1 9.444 9.316 0.128 98.64% Single Line 2 9.305 9.538 -0.233 97.55% Single line 3 9.313 9.152 0.161 98.24% Single line 4 9.291 9.189 0.102 98.89% Single line 5 9.269 9.385 -0.116 98.76% Single line 6 9.266 9.393 -0.127 98.65%

[0138] During the experiment, after using this method to complete the semantic segmentation of the transmission line, reconstruction of the incomplete conductor point cloud and sag measurement, the measured sag value was compared with the true value, and the overall sag measurement accuracy reached 98.455%, and the absolute error was less than 0.233m, which greatly improved the accuracy of the transmission line sag measurement.

[0139] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0140] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0141] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 produce 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.

[0142] 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.

[0143] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0144] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0145] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for measuring sag of power transmission lines in flat areas based on airborne laser radar, characterized in that: The following steps are involved: Acquire and pre-process transmission line point cloud data, wherein the transmission line point cloud data is obtained by scanning an airborne laser radar in a flat area; Based on the pre-processed transmission line point cloud data, the pre-built RandLA-Net-based point cloud semantic segmentation model is used to perform point cloud segmentation, and the semantic segmentation results are obtained, including the tower point cloud and the conductor point cloud. Clustering the wire point cloud closest to the tower point cloud, determining the wire suspension point, and determining the unit span transmission line point cloud based on the wire suspension point; Based on the unit span transmission line point cloud, projection and straight line fitting are performed to identify multiple three-dimensional conductor point clouds in the unit span transmission line point cloud; According to the straight line fitting direction and the identified three-dimensional wire point cloud, the curve point cloud is fitted, and the quality of the three-dimensional wire point cloud is evaluated and the lowest point missing wire point cloud is determined based on the curve point cloud; Reconstructing the residual point cloud according to the quality assessment result and the missing wire point cloud at the lowest point; Based on the reconstructed point cloud, the sag value of the transmission line per unit span is calculated according to the situations where the heights of the two conductor suspension points are the same and the heights of the two conductor suspension points are different.

2. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 1, characterized in that: The preprocessing operation includes filtering and denoising processing, and the steps of filtering and denoising processing include: Taking any point in the point cloud data of the transmission line as a sampling point, and taking k neighboring points of the sampling point; Calculate the Euclidean distance d from the sampling point to the k nearest neighbor points i , the mean m and standard deviation σ of the Euclidean distance are calculated as follows: Where, d i is the sampling point P j (x j ,y j z j ) is the Euclidean distance to the k nearest neighbors, m is the mean, and σ is the standard deviation; The Euclidean distance d i Points larger than m±σ are considered as abnormal points and removed from the transmission line point cloud data.

3. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 1, characterized in that: The step of determining the wire suspension point comprises: Calculate the centroid of the highest a points in each cluster as the wire suspension point. For a cluster, the calculation formula of the centroid coordinates is: Where P b is the centroid coordinate, i.e. the position of the wire suspension point, (x i ,y i , z i ) is the coordinate information of the point cloud in each cluster.

4. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 1, characterized in that: The step of determining the unit span transmission line point cloud comprises: Using two adjacent electric towers, the Euclidean distance between the wire suspension points is calculated. The calculation formula of the Euclidean distance is: Where d1 is the wire suspension point P b0 (x0,y0,z0) and the wire suspension point P b1 The Euclidean distance between (x1,y1,z1); The Euclidean distances smaller than the set value are classified as the same group of hanging points; The point clouds of multiple conductors between two nearest suspension point groups are determined as the point clouds of unit-span transmission lines.

5. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 1, characterized in that: The step of identifying a plurality of three-dimensional conductor point clouds in the unit span transmission line point cloud comprises: Projecting the unit span transmission line point cloud from the XOY direction to obtain a two-dimensional projection point cloud; Using the RANSAC algorithm to perform straight line fitting on each wire in the two-dimensional projection point cloud to obtain multiple fitting straight lines; The Euclidean distance between the two-dimensional projection point cloud and the plurality of fitting straight lines is calculated to realize the recognition of the plurality of three-dimensional conductor point clouds in the unit span transmission line point cloud.

6. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 5, characterized in that: The step of realizing the identification of multiple three-dimensional wire point clouds in the unit span transmission line point cloud comprises: In the two-dimensional projected point cloud, the Euclidean distance from each point to each fitted straight line is calculated, and the calculation expression is: Where d2 is the Euclidean distance from each point in the two-dimensional projection point cloud to each fitted line, (x, y) represents the point in the two-dimensional projection point cloud, Ax+By+C=0 represents the fitted line, and A, B, and C are the line coefficients; According to the calculated Euclidean distance, the point closest to each fitting line is regarded as the two-dimensional point cloud corresponding to each fitting line, so as to realize the recognition of multiple two-dimensional wire point clouds; According to the X-coordinate and Y-coordinate information and the Z-coordinate index of the two-dimensional wire point cloud, the Z-coordinate index information is restored to realize the recognition of multiple three-dimensional wire point clouds.

7. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 1, characterized in that: The step of fitting the curve point cloud comprises: The three-dimensional wire point cloud is rotated from the Z axis to the X axis and parallel to the straight line fitting direction, where the rotation angle θ and the rotation matrix R of the three-dimensional wire point cloud are respectively: In the formula, A and B are linear coefficients; According to the rotation result, the rotated wire point cloud is obtained, and the expression is: A2=R*A1 Where A2 is the wire point cloud after rotation, and A1 is the original wire point cloud, that is, the three-dimensional wire point cloud before rotation; The rotated wire point cloud is projected in the XOZ plane direction to obtain a two-dimensional point cloud B1, and a quadratic curve is fitted on the two-dimensional point cloud B1 using the least squares method; The curve point cloud B2 is generated at equal intervals according to the fitted quadratic curve.

8. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 7, characterized in that: The steps of evaluating the quality of the three-dimensional wire point cloud and determining the lowest point missing wire point cloud include: Calculate the distance from each point in the curve point cloud to the nearest multiple points on the rotated wire point cloud A2, and calculate the average distance; Determine the relationship between the average distance and the set threshold value, and obtain the quality assessment results of the three-dimensional wire point cloud, including a complete point cloud, a slightly residual point cloud, a moderately residual point cloud, and a heavily residual point cloud; The points with the lowest height of the curve point cloud are taken, and the incompleteness detection is performed on the points, and the incomplete three-dimensional wire point cloud detected is used as the lowest point missing wire point cloud.

9. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 8, characterized in that: The step of reconstructing the residual defect cloud comprises: For the lowest point missing wire point cloud, the moderate residual defect cloud and the severe residual defect cloud, the curve point cloud B2 is fused with the two-dimensional point cloud B1 generated by the projection of A2 in the XOZ plane direction to obtain a fused point cloud A3; In order to restore the Y coordinate information of the fused point cloud A3, the average value of the Y coordinates in the A2 point cloud is used as the Y coordinate of the point cloud A3, and the fused point cloud A4 after the Y coordinate information is restored is obtained; A4 is rotated to the coordinate system of the original wire point cloud A1 to obtain point cloud A5, which is the incompletely reconstructed point cloud, where A5 is: A5=R1*A4 Where R1 is the rotation matrix and θ is the rotation angle.

10. The method for measuring sag of power transmission lines in flat areas based on airborne laser radar according to claim 9, characterized in that: The step of calculating the sag value of the transmission line per unit span comprises: When the heights of the two wire suspension points are the same, in the incompletely reconstructed point cloud A5, the straight line equation l1 is determined according to the wire suspension points A and B, and the distance f from the lowest point C to the straight line equation l1 is calculated, and the distance f is the sag; When the heights of the two wire suspension points are different, in the incompletely reconstructed point cloud A5, the straight line equation l1 is determined according to the wire suspension point A and the wire suspension point B, and the vertical distance f1 from the lowest point C1 to the straight line equation l1 is calculated. The vertical distance f1 is the sag of the lowest point. The vertical distance from each point in A5 to l1 is calculated and the maximum value f2 is taken. The maximum value f2 is the maximum sag.

Citation Information

Patent Citations

  • Transmission line sag precise measuring method based on laser point cloud data

    CN109458936A

  • The invention discloses a binocular image-based ground object safety distance detection method and equipment under a power line

    CN109829908A

  • Power transmission line sag measurement method based on unmanned aerial vehicle laser point cloud model

    CN114396878A

  • Online reconstruction method and system for laser point cloud model of power transmission line

    CN114972631A

  • Transmission conductor sag measurement method, device and equipment based on point cloud analysis

    CN116128835A

Cited By

  • Road marking identification method based on vehicle-mounted LiDAR point cloud

    CN119888671A

  • Visual sag detection method, system and device

    CN120740456A

  • A visual sag detection method, system and apparatus

    CN120740456B

  • A method and device for measuring conductor sag based on three-dimensional data, and a computer readable storage medium

    CN122737002A