Arrangement method and system for transmission line crossing measurement

Abstract

The present disclosure relates to the field of electric power technology, and discloses a layout method and system for transmission line crossing measurement. The specific scheme is as follows: taking the erection height of each transmission line in the target power transmission area and the crossing distance between two adjacent transmission lines as optimization variables, and taking the electrical safety performance of the target power transmission area as the dependent variable, constructing an objective function; based on the crossing distance constraint and the electrical safety performance constraint, solving the objective function for the optimal solution, and obtaining a target line layout model of the target power transmission area, wherein the target line layout model includes the erection height of each transmission line and the crossing distance between two adjacent transmission lines.

Description

Technical Field

[0001] The present disclosure relates to the field of electric power technology, and in particular to a method and system for arranging crossover measurement of transmission lines. Background Art

[0002] In the safety assessment of power transmission lines, the installation height and span distance of the transmission lines are generally involved. These parameters also involve the safety of power transmission. Therefore, how to arrange regional power transmission lines is also a problem of concern in this field. Summary of the invention

[0003] The present disclosure provides a method and system for arranging crossover measurement of transmission lines, which can solve at least one of the above problems.

[0004] The present disclosure provides a method for arranging a transmission line crossing measurement, comprising:

[0005] Taking the erection height of each transmission line in the target power transmission area and the span distance between two adjacent transmission lines as optimization variables, and taking the electrical safety performance of the target power transmission area as the dependent variable, an objective function is constructed;

[0006] Based on the spanning distance constraint and the electrical safety performance constraint, the objective function is solved for an optimal solution to obtain a target line layout model of the target power transmission area, wherein the target line layout model includes the installation height of each transmission line and the spanning distance between two adjacent transmission lines.

[0007] According to another aspect of the present disclosure, there is provided a system for arranging a cross-over transmission line, comprising:

[0008] An objective function construction module, for constructing an objective function using the installation height of each transmission line in the target power transmission area and the span distance between two adjacent transmission lines as optimization variables, and using the electrical safety performance of the target power transmission area as a dependent variable;

[0009] The objective function solving module is used to solve the objective function for the optimal solution based on the spanning distance constraint and the electrical safety performance constraint, and obtain the target line layout model of the target power transmission area, wherein the target line layout model includes the installation height of each transmission line and the spanning distance between two adjacent transmission lines.

[0010] The technical solution of the present disclosure is adopted, the installation height of each transmission line in the target power transmission area and the span distance between two adjacent transmission lines are used as optimization variables, and the electrical safety performance of the target power transmission area is used as the dependent variable to construct an objective function. Then, based on the span distance constraint and the electrical safety performance constraint, the objective function is solved for the optimal solution to obtain the target line layout model of the target power transmission area, wherein the target line layout model includes the installation height of each transmission line and the span distance between two adjacent transmission lines. In this way, a transmission line layout plan that meets the electrical safety performance can be generated. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a flow chart of a method for arranging a transmission line crossing measurement according to an embodiment of the present disclosure;

[0012] Figure 2 is a flow chart of a method for arranging transmission line crossing measurement according to another embodiment of the present disclosure;

[0013] Figure 3 It is a structural block diagram of a system for arranging transmission line crossing measurement according to an embodiment of the present disclosure;

[0014] Figure 4 This is a structural block diagram of a system for arranging transmission line crossing measurement according to another embodiment of the present disclosure.

[0015] Figure 5 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0017] Figure 1 The present invention is a flowchart of a method for arranging transmission line crossing measurement according to an embodiment of the present invention.

[0018] like Figure 1 As shown, the method can be applied to electronic devices, and the electronic devices can execute the method to obtain a transmission line layout plan. The method includes:

[0019] S110, constructing an objective function by taking the installation height of each transmission line in the target power transmission area and the span distance between two adjacent transmission lines as optimization variables, and taking the electrical safety performance of the target power transmission area as a dependent variable;

[0020] S120, based on the span distance constraint and the electrical safety performance constraint, solving the optimal solution of the objective function to obtain a target line layout model of the target power transmission area, wherein the target line layout model includes the installation height of each transmission line and the span distance between any two adjacent transmission lines.

[0021] For example, the target power transmission area may be an area within any geographical area where power transmission is performed, for example, the southern region, the Jiangsu and Zhejiang region, the southern China region, or the northern China region, etc. Alternatively, the area of ​​a certain city or a certain district.

[0022] For example, the installation height may have a preset area range. When solving the objective function, it is also necessary to limit the constraint conditions of the installation height. For example, the installation height of any transmission line needs to be between the lower limit value of the installation height and the upper limit value of the installation height.

[0023] For example, the value range of the erection height is 22-28 meters.

[0024] Exemplarily, the span distance constraint condition may be that the span distance between any two adjacent transmission lines is greater than a lower limit value of the span distance and less than an upper limit value of the span distance.

[0025] For example, the span distance between two adjacent lines ranges from 8 to 12 meters. Alternatively, the span distance is not less than 6 meters.

[0026] Exemplarily, the electrical safety performance constraint condition includes at least one of the following:

[0027] The maximum electric field strength in each transmission line is greater than the lower limit of the electric field strength and less than the upper limit of the electric field strength;

[0028] The operating voltage of each transmission line is greater than the lower voltage limit and greater than the upper voltage limit;

[0029] A difference between input power and output power of the target power transmission area is greater than a power loss lower limit value and less than a power loss upper limit value.

[0030] For example, the objective function is a function used to evaluate the electrical safety performance of a certain area. The objective function can be a linear function, an exponential function, or an objective function composed of a linear function and an exponential function. Examples are not given here one by one.

[0031] Exemplarily, the target line layout model may also include material quality, model specifications, etc. of each transmission line.

[0032] Exemplarily, the above step S120 may be performed using a particle swarm optimization algorithm.

[0033] Exemplarily, the population size is set to 100, the maximum number of iterations is 1000, the acceleration constant is 2, and the installation height and the distance between adjacent transmission lines are used as optimization variables. The crossing distance safety standard and electrical safety standard are used as constraints. The influence of conductor stress, sag and shadowing is comprehensively considered to solve the optimal conductor layout plan. During the optimization process, the inertia weight is dynamically adjusted according to the intermediate results to achieve adaptive optimization.

[0034] Exemplarily, after obtaining the target line layout model, the construction personnel arrange the poles and transmission lines in the target power transmission area according to the target line layout model.

[0035] According to the above embodiment, the installation height of each transmission line in the target power transmission area and the span distance between two adjacent transmission lines are used as optimization variables, and the electrical safety performance of the target power transmission area is used as the dependent variable to construct an objective function. Then, based on the span distance constraint and the electrical safety performance constraint, the objective function is solved for the optimal solution to obtain the target line layout model of the target power transmission area, wherein the target line layout model includes the installation height of each transmission line and the span distance between two adjacent transmission lines. In this way, a transmission line layout plan that meets the electrical safety performance can be generated.

[0036] Figure 2 The present invention is a flowchart of a method for arranging transmission line crossing measurement according to another embodiment of the present invention.

[0037] In one embodiment, Figure 2 As shown, in the above step S120, based on the spanning distance constraint and the electrical safety performance constraint, the objective function is solved for the optimal solution to obtain the target line layout model of the target power transmission area, including:

[0038] S210, determining a first circuit layout model based on the initial circuit layout model;

[0039] S220: Based on the first line arrangement model, perform the following iterative operations:

[0040] S221, in the first line layout model, simulating a dynamic distribution diagram of shadow areas formed by projections of each transmission line and each tower in the first line layout model under light;

[0041] S222, calculating the shadow shielding coefficient of the shadow area on each transmission line based on the dynamic distribution map of the shadow area;

[0042] S223, using the shadow shielding coefficient of each transmission line as the coefficient of the corresponding optimization variable in the objective function, and updating the objective function;

[0043] S224, calculating the objective function based on the installation height of each transmission line in the first line layout model and the span distance between two adjacent transmission lines to obtain the electrical safety performance of the first line layout model;

[0044] S225, when the electrical safety performance of the first line layout model does not satisfy the electrical safety performance constraint condition, and / or the spanning distance between two adjacent transmission lines in the first line layout model does not satisfy the spanning distance constraint condition, adjusting the first line layout model to obtain a second line layout model;

[0045] S226: Update the first wiring layout model based on the second wiring layout model, and return to continue to perform the iterative operation.

[0046] It is understandable that the initial line layout model can be any model. The model can include the installation height of each transmission line and the span distance between any two adjacent transmission lines.

[0047] Exemplarily, the initial wiring arrangement model is taken as the first wiring arrangement model.

[0048] Exemplarily, in the above step S210, a Monte Carlo ray tracing algorithm can be used to randomly emit 1,000 light rays in an area of ​​1 square meter according to the changes in the solar altitude angle and azimuth angle, simulating the solar illumination conditions every hour from 6:00 to 18:00, illuminating each transmission line and each tower, and obtaining a dynamic distribution map of the shadow area.

[0049] For example, according to the dynamic distribution diagram, the proportion of each transmission line blocked by the shadow area can be calculated, and then the shadow shielding coefficient of each transmission line can be calculated according to the proportion change. For example, the proportion change is integrated to obtain the shadow shielding coefficient of the transmission line.

[0050] Exemplarily, the shadow shielding coefficient of transmission line A is multiplied by the optimization variable corresponding to transmission line A and then updated in the objective function.

[0051] Exemplarily, the installation height of each transmission line in the first line layout model and the span distance between two adjacent transmission lines are input into the objective function, and then the objective function is calculated, and the calculation result obtained is the electrical safety performance of the first line layout model.

[0052] Exemplarily, the electrical safety performance may be one or more indicator data.

[0053] Exemplarily, in the above step S225, the first line layout model is adjusted, and the height and span distance involved in the first line layout model may be adjusted arbitrarily, or may be adjusted stepwise according to set height steps and span distance steps.

[0054] Exemplarily, in the above step S226, the second wiring layout model is used as the first wiring layout model.

[0055] According to the above implementation, in the process of solving the objective function, the influence of the shadow area on the installation height and span distance of the transmission line is considered, and the optimal line layout model can be solved.

[0056] In one embodiment, the above method may also include: determining the target line layout model based on the first line layout model when the number of iterations of the iterative operation meets the preset number, the electrical safety performance of the first line layout model meets the electrical safety performance constraint, and the spanning distance between two adjacent transmission lines in the first line layout model meets the spanning distance constraint.

[0057] Exemplarily, the first wiring arrangement model is used as the target wiring arrangement module.

[0058] Exemplarily, an electrical safety simulation test is performed on the first wiring arrangement model, and when the simulation test result is verified to be passed, the first wiring arrangement model is used as the target wiring arrangement module.

[0059] According to the above implementation, a line layout model that meets the electrical safety performance and spanning distance constraint conditions can be accurately obtained.

[0060] In one embodiment, the method further includes: constructing an initial line layout model based on initial position information and initial size structure information of each transmission line in the target power transmission area, and initial position information and initial size structure information of each tower; wherein the initial position information includes the erection height of the transmission line and the spanning distance between the transmission line and adjacent transmission lines.

[0061] Exemplarily, the initial size and structure information includes size, structure, and specification parameters, etc.

[0062] Exemplarily, the above-mentioned line arrangement model may be a three-dimensional model, which may be simulated in a simulation system.

[0063] For example, according to the LGJ-400 / 35 line specifications and the tower parameters of 30 meters high and 12 meters long cross arm, the initial three-dimensional line layout model is constructed. Using ANSYS finite element software, hexahedral units are set with a unit size of 0.1 meters, fixed constraints at the bottom of the tower, and 50kN tension applied to the end of the conductor, the feasible range of line adjustment is calculated: the erection height is 22-28 meters, and the distance between adjacent lines is 8-12 meters.

[0064] Exemplarily, the initial circuit layout model is randomly determined according to the above-mentioned feasible range of circuit design and circuit specification information.

[0065] According to the above implementation, a three-dimensional model of a power transmission line that meets the safety standards for the spanning distance and the electrical safety performance can be finally output.

[0066] In some examples, before executing the above embodiments, the target power transmission area has been constructed with poles and transmission lines. Therefore, the transmission lines and poles in the target power transmission area can be reconstructed in three dimensions to obtain a three-dimensional transmission line scene. The spanning distance and electrical safety performance of the transmission line are evaluated in the three-dimensional transmission line scene. If the requirements are met, there is no need to rearrange the transmission lines and poles in the target power transmission area. If the requirements are not met, the target line layout model of the target power transmission area is replanned according to the above embodiments, so as to rearrange the transmission lines and poles in the target power transmission area according to the target line layout model.

[0067] In some examples, performing three-dimensional reconstruction of the scene of the transmission lines and towers in the target power transmission area to obtain a three-dimensional scene of the transmission lines includes the following steps:

[0068] According to the dynamic simulation results of the line shadow areas corresponding to the transmission lines in the target power transmission area changing over time, the line shadow areas in the transmission lines in the panoramic image in the target power transmission area are adjusted in brightness to obtain a panoramic image with balanced illumination;

[0069] Extracting line features of each transmission line and tower features of each tower from the panoramic image after illumination equalization to obtain a feature set;

[0070] According to each line feature and each tower feature in the feature set and the terrain data of the target power transmission area, a three-dimensional point cloud scene of the transmission line in the target power transmission area is constructed to obtain a three-dimensional scene of the transmission line, which includes a shadow area.

[0071] In some examples, the above method may further include the following steps:

[0072] The density of each shadow area in the three-dimensional scene of the transmission line is adjusted and the depth information is repaired to obtain the final three-dimensional scene of the transmission line.

[0073] In some examples, the calculation process of the dynamic simulation results of the line shadow area corresponding to each transmission line in the target power transmission area changing with time can be as follows:

[0074] Constructing a three-dimensional terrain model based on digital elevation model data of the terrain in the target power transmission area;

[0075] Constructing a three-dimensional geometric model of the transmission line according to the location information and size information of each transmission line in the target power transmission area, and the location information and size information of each tower;

[0076] Superimpose the 3D terrain model and the 3D geometric model of the transmission line to obtain an integrated 3D scene containing the spatial location information of the terrain and the transmission line;

[0077] Determine various time points throughout the year at preset time intervals;

[0078] The calculation process for the projection distribution of each shadow line area on the ground at each time point is as follows: in the integrated three-dimensional scene, according to the sun position corresponding to the time point, the propagation path of light in the atmosphere is simulated to determine the intersection point of the light and the transmission line on the ground; based on each intersection point, the projection distribution of each shadow line area on the ground at the time point is determined;

[0079] Based on the projection distribution of each shadow line area on the ground at various time points throughout the year, the dynamic simulation results of the line shadow area corresponding to each transmission line in the target power transmission area changing with time are determined.

[0080] Exemplarily, when constructing a three-dimensional terrain model, digital elevation model data with a resolution of 1 meter is used to generate a continuous terrain surface through a triangular mesh interpolation method.

[0081] For example, for a transmission line, its latitude and longitude coordinates and installation height are sampled at 10-meter intervals to form a discrete point set. These discrete points are connected into a smooth curve through cubic spline interpolation, and then superimposed with the terrain model to obtain a complete three-dimensional scene.

[0082] Exemplarily, when calculating the sun's position, the NREL sun position algorithm is used, and the geographic location (such as 35.5 degrees north latitude, 114.3 degrees east longitude) and time (such as 12:00 on June 21, 2024) are input, and the sun's altitude angle of 58.7 degrees and azimuth angle of 185.2 degrees are calculated.

[0083] Exemplarily, using Snell's law and the Snel-Descartes atmospheric refraction model, the atmosphere is divided into 50 layers, each with a thickness of 200 meters, and the refractive index decreases layer by layer from 1.0003 on the ground to 1.0000, and the refraction angle of light in each layer is calculated.

[0084] Exemplarily, a Monte Carlo ray tracing algorithm is used to emit 1,000 rays at each time point to simulate their propagation paths in the atmosphere.

[0085] For example, in a three-dimensional scene, a ray-triangle intersection algorithm is used to determine the intersection of a ray with terrain and a power transmission line. For complex terrain, an octree space partition is used to accelerate the calculation.

[0086] Exemplarily, after the intersection point is obtained, the Sutherland-Hodgman polygon clipping algorithm is used to determine the shadow boundary, and the area of ​​the shadow polygon and its projection distribution on the ground are calculated.

[0087] In this way, the shadow distribution is calculated at 8760 time points throughout the year at intervals of 1 hour.

[0088] Exemplarily, the obtained shadow distribution is subjected to fast Fourier transform to extract the main cycles of shadow variation, such as the 24-hour daily variation cycle and the 365-day annual variation cycle.

[0089] Exemplarily, a Gaussian kernel density estimation algorithm may also be used, with the kernel bandwidth set to 50 meters, to generate a shadow coverage frequency distribution map of a 100x100 meter grid to quantify the proportion of time that different locations are affected by shadows throughout the year.

[0090] In some examples, the above-mentioned adjustment of the brightness of the line shadow area of ​​each transmission line in the panoramic image of the target power transmission area according to the dynamic simulation result of the line shadow area corresponding to each transmission line in the target power transmission area changing over time to obtain the panoramic image after lighting balance may include:

[0091] Determine a designated area in the panoramic image affected by the line shadow area according to a dynamic simulation result of the line shadow area corresponding to each transmission line in the target power transmission area changing over time;

[0092] Gamma correction is performed on the line shadow area and the above-mentioned designated area in the panoramic image to obtain a panoramic image with balanced illumination.

[0093] For example, for a panoramic image, the generation method can be: the five cameras carried by the multi-rotor drone are arranged in a cross shape, with the central camera facing directly downward, and the other four cameras are tilted 45 degrees forward, backward, left and right respectively. The drone collects a set of images every 50 meters along the transmission line, and the flight altitude is maintained at 100 meters. The resolution of the collected images is 4000x3000 pixels. The SIFT algorithm is used to extract 2000 feature points in each image, and then the RANSAC algorithm is used to select at least 100 pairs of matching points for image stitching to generate a panoramic image of 12000x9000 pixels.

[0094] Exemplarily, a region growing algorithm is used in combination with color and texture features to identify shadow areas on panoramic images, taking into account terrain undulations and transmission line structures, and dynamically adjusting the shadow detection threshold based on light intensity data at different time points to generate shadow area masks at different time points, marking the image areas affected by shadows.

[0095] For example, for the marked shadow area, the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm is applied, the grid size is set to 8x8 and the contrast limit parameter is set to 0.01, the pixel grayscale value is dynamically adjusted according to the local brightness distribution, and the global brightness is adjusted through gamma correction. The gamma value range is set to 0.5 to 2.0, and the adjustment step is 0.1, so as to obtain the transmission line image after illumination balance.

[0096] In some examples, the line features of each transmission line and the tower features of each tower are extracted from the panoramic image after illumination equalization to obtain a feature set, which may include:

[0097] The shadow projection direction and range are calculated according to the sun position, and the straight line structure in the panoramic image is detected using Hough transform. At the same time, the Harris corner detection algorithm is used to identify the key points of the tower in the panoramic image.

[0098] Based on the above straight line structures and key points, candidate areas of poles and wires are screened out in the panoramic image to obtain preliminary location information of poles and transmission lines;

[0099] The panoramic image is decomposed into multiple scales using the Gaussian pyramid, and the corresponding gradient direction histogram is calculated at each scale. The number and range of the gradient direction histogram are dynamically adjusted according to the distribution of line shadow areas in the panoramic image.

[0100] The local binary pattern algorithm is used to extract the texture features of the tower and conductor area, and the directional statistical features are cascaded with the texture features to construct a joint feature descriptor.

[0101] The joint feature descriptor is classified using support vector machine to divide the image area into towers, conductors and background.

[0102] The classification results are morphologically optimized by applying opening and closing operations, and the tower outline and conductor direction are extracted according to the optimized classification results;

[0103] The geometric description of the tower structure and the conductor is generated in combination with the preliminary location information, and a set of transmission line and tower feature descriptions that adapt to the distribution of the shadow area is obtained.

[0104] Specifically, the shadow projection direction and range are calculated according to the sun position, and the Hough transform is used to detect the straight line structure in the transmission line image. The angular resolution is set to 1 degree, the accumulator threshold is 100, and the Harris corner detection algorithm is used to identify the key points of the tower structure.

[0105] The candidate areas of towers and conductors are screened out through the straight line length, inclination angle and corner point distribution characteristics to obtain preliminary tower and conductor location information.

[0106] A 5-layer Gaussian pyramid is used to decompose the image at multiple scales. The gradient direction histogram is calculated at each scale. The number and range of the histogram bins are dynamically adjusted according to the distribution of the shadow area. The number of low-brightness bins is increased in the shadow area to generate directional statistical features that adapt to the shadow distribution. At the same time, the scale range of feature extraction is dynamically adjusted according to the size of the shadow area, and the main direction of the directional statistics is adjusted according to the shadow direction.

[0107] The local binary pattern algorithm is used to extract the texture features of the tower and conductor area. The neighborhood size is set between 3x3 and 7x7, and the comparison threshold range is 5 to 15. The neighborhood radius and comparison threshold are adjusted to adapt to different shadow intensities. The directional statistical features and texture features are cascaded to construct a joint feature descriptor to improve the distinguishability of the features.

[0108] The extracted features are classified by support vector machine. The radial basis kernel function is selected, the C parameter is set to 10, the gamma parameter is set to 0.1, and the parameters are optimized through 5-fold cross validation. The image area is divided into towers, conductors and background. The classification results are morphologically optimized by applying opening and closing operations. The tower outline and conductor direction are extracted according to the optimized classification results. The geometric morphology description of the tower structure and the conductor is generated by combining the preliminary position information. Finally, a set of transmission line and tower feature descriptions that adapt to the distribution of shadow areas is obtained.

[0109] For example, when processing a transmission line image, the shadow projection direction and range are first calculated based on the known sun position (such as an altitude angle of 45 degrees and an azimuth angle of 225 degrees). The Hough transform is used to detect the straight line structure in the image, and the angle resolution is set to 1 degree, the accumulator threshold is set to 100, and the Harris corner detection algorithm is used, the corner response threshold is set to 0.01, and the non-maximum suppression window size is 3x3 pixels.

[0110] By combining the features detected by these two methods, candidate areas for poles and conductors are screened out: straight lines with a length greater than 100 pixels and an inclination angle in the range of 75-105 degrees or 0-15 degrees are considered as pole candidates, while those with a length greater than 200 pixels and an inclination angle in the range of 0-30 degrees are considered as conductor candidates.

[0111] Next, a 5-layer Gaussian pyramid is used to perform multi-scale decomposition on the original image of 4000x3000 pixels with a scaling factor of 0.5. The gradient direction histogram is calculated at each scale, and the original number of bins is 36. In the detected shadow area, the number of bins in the range of 0-60 degrees is increased to 12 to improve the sensitivity to low-brightness areas.

[0112] The scale range of feature extraction is dynamically adjusted according to the size of the shadow area. For example, when the shadow area accounts for more than 30% of the image, the feature scale range is expanded by 1.5 times.

[0113] The local binary pattern algorithm is used to extract texture features. For non-shadow areas, a 3x3 neighborhood and a threshold of 5 are used, and for shadow areas, a 7x7 neighborhood and a threshold of 15 are used to adapt to different lighting conditions. The 256-dimensional LBP feature is cascaded with the 36-dimensional directional statistical feature to form a 292-dimensional joint feature descriptor.

[0114] Finally, support vector machine was used for classification, radial basis kernel function was selected, and the optimal parameters C=10 and gamma=0.1 were determined by grid search. The model performance was evaluated by 5-fold cross validation. The classification results were opened and closed by applying 3x3 structural elements to remove noise and fill small holes. According to the optimized classification results, the tower outline (connected area with an area greater than 1000 square pixels) and the conductor direction (slender area with a length greater than 500 pixels) were extracted, and the geometric description was generated by combining the preliminary position information, such as tower height, width ratio and conductor sag.

[0115] In some examples, constructing a three-dimensional point cloud scene of a transmission line in a target power transmission area according to each line feature and each tower feature in the feature set and terrain data of the target power transmission area to obtain a three-dimensional scene of the transmission line may include:

[0116] Obtain a pair of stereo images of the power transmission line collected by a binocular stereo vision camera, and set a region of interest according to a feature description set;

[0117] For the region of interest, the SIFT algorithm is used to extract feature points, and the random sampling consistency algorithm is used to perform feature matching to obtain the correspondence between the left and right images;

[0118] If the corresponding relationship is established, the two-dimensional image coordinates are converted into three-dimensional space coordinates using the triangulation principle to obtain a sparse point cloud representation of the transmission line and tower structure;

[0119] Dense reconstruction of sparse point clouds, including using cubic spline curve fitting algorithm for transmission lines and Poisson surface reconstruction algorithm for tower structures to generate a three-dimensional mesh model;

[0120] The terrain data is obtained, and the iterative closest point algorithm is used to calibrate the terrain data with the three-dimensional grid model. The shadow area is marked in the three-dimensional grid model through a shadow calculation method based on ray tracing, and a three-dimensional reconstruction result including the dynamic shadow area distribution is obtained.

[0121] Specifically, based on the extracted feature description set of the transmission line and tower structure, a stereo image pair of the transmission line is collected using a binocular stereo vision camera, and the feature description set is used to set the region of interest. Feature points are extracted in this region using the SIFT algorithm, and feature matching is performed using the random sampling consistency algorithm to establish the correspondence between the left and right images, and the initial disparity map is calculated at the same time.

[0122] The disparity map is optimized by using matched feature point pairs. A semi-global matching algorithm is adopted, the smoothness penalty coefficient is set to 0.1, the disparity range is 0-128 pixels, the left-right consistency check of the disparity map is performed, the mismatched points are eliminated, and the two-dimensional image coordinates are converted into three-dimensional space coordinates through the triangulation principle to obtain a sparse point cloud representation of the transmission line and tower structure.

[0123] The sparse point cloud is densely reconstructed. The cubic spline curve fitting algorithm is used for the transmission line. The Poisson surface reconstruction algorithm is used for the tower structure to generate a three-dimensional mesh model. The Loop subdivision algorithm is used to improve the model accuracy. The number of iterations is set to 3 to obtain an accurate three-dimensional model of the transmission line.

[0124] The terrain data is obtained, and the iterative closest point algorithm is used to align the terrain data with the reconstructed three-dimensional model of the transmission line. The maximum number of iterations is set to 50, and the convergence threshold is 0.001 meters. A unified three-dimensional point cloud scene is generated through voxelization processing. The voxel resolution is set to 0.1 meters. The shadow area is marked in the point cloud by combining the shadow calculation method based on ray tracing. The sun position and terrain occlusion are considered, and the shadow distribution at different times is simulated. Finally, a three-dimensional reconstruction result including the dynamic shadow area distribution is obtained.

[0125] Exemplarily, in the process of implementing three-dimensional reconstruction of transmission lines, firstly, based on the previously extracted feature description set, a region of interest is set on a 4000x3000 pixel stereo image pair, and a strip area with a width of 500x500 pixels around the tower position and 100 pixels in the conductor area is defined as a key analysis area.

[0126] The SIFT algorithm was applied in these areas, with the upper limit of the number of feature points set to 10,000, the contrast threshold to 0.04, and the edge response threshold to 10. The random sampling consistency algorithm was then used for feature matching, with the number of iterations set to 1,000, the inlier threshold distance to 2 pixels, and the matching confidence to 0.99. The initial disparity map was calculated based on the matching results, and the semi-global matching algorithm was used for optimization, with the smoothness penalty coefficient set to 0.1 and the disparity range to 0-128 pixels. A left-right consistency check was applied, with the threshold set to 1 pixel, and false matching points were removed. The pixel disparity was converted to depth values ​​using the camera calibration parameters (focal length 35mm, baseline distance 100mm) to generate a sparse point cloud.

[0127] For the transmission line part, cubic spline curve fitting is used, and the control point spacing is set to 5 meters; the tower structure is reconstructed using Poisson surface, the octree depth is set to 8, and then the Loop subdivision algorithm is applied for 3 iterative optimizations.

[0128] In the terrain data fusion stage, the iterative closest point algorithm was used with a maximum number of iterations of 50 and a convergence threshold of 0.001 meters to align the 1-meter resolution digital elevation model with the reconstructed model. During voxelization, the voxel size was set to 0.1 meters to generate a unified point cloud scene.

[0129] Finally, based on the ray tracing algorithm, the shadows are simulated, the sun position (such as 45 degrees in altitude and 225 degrees in azimuth) and terrain occlusion are taken into account, and the shadow distribution is calculated every hour within 24 hours to obtain the three-dimensional reconstruction results of the dynamic shadow area.

[0130] In some examples, the above-mentioned density adjustment and depth information restoration of each shadow area in the three-dimensional scene of the power transmission line to obtain the final three-dimensional scene of the power transmission line may include:

[0131] Obtain the solar altitude angle and the 3D model of the transmission line, calculate the shadow projection range according to the solar altitude angle, and use the raycasting algorithm combined with the 3D model of the transmission line to generate a shadow area mask;

[0132] Perform multi-scale wavelet decomposition on the shadow area mask to obtain shadow feature representations at different scales and calculate the point cloud density of the shadow area;

[0133] If the point cloud density is lower than the preset threshold, the adaptive point cloud filtering algorithm is used to reduce noise and smooth the point cloud in the shadow area. The search radius of the adaptive point cloud filtering algorithm is dynamically adjusted according to the point cloud density.

[0134] The depth image of the shadow area is constructed based on multi-scale feature representation, and the missing depth information of the depth image is repaired through the depth image completion algorithm based on convolutional neural network;

[0135] The repaired depth information is used to reconstruct the 3D point cloud of the shadow area, and the optimized 3D mesh model is generated by the Poisson surface reconstruction algorithm. The 3D mesh model is fused with the 3D model of the non-shadow area to obtain a complete 3D scene of the transmission line.

[0136] Specifically, the shadow projection range is calculated according to the solar altitude angle, the digital elevation model is used to analyze the terrain features, the ray casting algorithm is combined with the three-dimensional model of the transmission line to generate a shadow area mask, and the shadow area is feature extracted through multi-scale wavelet decomposition to obtain shadow feature representations at different scales. At the same time, the point cloud density of the shadow area is calculated, and the number of points per cubic meter is counted.

[0137] Using the 3D point cloud data of the non-shadow area as a reference, the point cloud data of the shadow area is subjected to density analysis. The adaptive point cloud filtering algorithm is used to reduce noise and smooth the point cloud in the shadow area. The initial search radius is set to 0.5 meters, and the minimum number of neighbors is set to 10. The filtering parameters are dynamically adjusted according to the point cloud density. When the density is lower than 5 points / cubic meter, the search radius is increased to 1 meter.

[0138] Based on multi-scale feature representation, a depth image of the shadow area is constructed. The missing depth information of the shadow area is repaired by a deep image completion algorithm based on a convolutional neural network. The repaired depth information is aligned with the original three-dimensional point cloud using an iterative closest point algorithm. The maximum number of iterations is set to 100, and the convergence threshold is 0.001 meters. The three-dimensional point cloud of the shadow area is reconstructed using the repaired depth information, and an optimized three-dimensional mesh model is generated by a Poisson surface reconstruction algorithm. Combined with the three-dimensional model of the non-shadow area, a mesh fusion algorithm based on the Poisson equation is used to generate a complete three-dimensional scene of the transmission line. Considering the shadow changes every hour within 24 hours, a continuous shadow change model is generated by cubic spline interpolation, and the three-dimensional scene is dynamically compensated to obtain a three-dimensional reconstruction result after dynamic compensation.

[0139] Exemplarily, in the process of implementing dynamic compensation for three-dimensional reconstruction of transmission lines, the solar altitude angle is first determined using a solar position calculator. For example, at noon on the summer solstice in an area at 40 degrees north latitude, the solar altitude angle is about 73.5 degrees. Combined with a 1-meter resolution digital elevation model, a ray casting algorithm is used to simulate light propagation, projecting a ray every 0.1 meters to generate a shadow area mask at the intersection with the three-dimensional model of the transmission line. A 4-level Haar wavelet decomposition is applied to the mask to obtain shadow features of different scales. At the same time, the point cloud density of the shadow area is calculated, and 1 cubic meter voxel division is used to obtain an average density of 20 points / cubic meter. For the point cloud in the shadow area, an adaptive statistical filter is applied, with an initial search radius of 0.5 meters and a minimum number of neighbors of 10. When the local density is less than 5 points / cubic meter, the search radius is increased to 1 meter, and point cloud optimization is achieved by iteration 3 times.

[0140] Subsequently, a depth image with a resolution of 500x500 pixels is constructed and input into a convolutional neural network with a U-Net structure for depth completion. The network contains 4 layers of downsampling and 4 layers of upsampling, and uses the ReLU activation function.

[0141] The iterative closest point algorithm is used to align the completed depth information with the original point cloud, with a maximum of 100 iterations and a convergence threshold of 0.001 meters. The completed depth information is used to reconstruct the point cloud of the shadow area, and Poisson surface reconstruction is applied. The octree depth is set to 8 to generate a mesh model. The mesh fusion algorithm of the Poisson equation is used with a weight coefficient of 0.7 to fuse the mesh models of the shadow area and the non-shadow area. Finally, considering the 24-hour shadow changes, sampling is performed once an hour, and 48 intermediate states are generated using cubic spline interpolation to form a continuous dynamic shadow compensation model to achieve a smooth transition of the three-dimensional scene.

[0142] Figure 3 FIG. 1 is a structural block diagram of a system for arranging transmission line crossing measurement according to an embodiment of the present disclosure. Figure 3 As shown, the system includes:

[0143] An objective function construction module 310 is used to construct an objective function using the installation height of each transmission line in the target power transmission area and the span distance between two adjacent transmission lines as optimization variables, and using the electrical safety performance of the target power transmission area as a dependent variable;

[0144] The objective function solving module 320 is used to solve the objective function for the optimal solution based on the spanning distance constraint and the electrical safety performance constraint to obtain the target line layout model of the target power transmission area, wherein the target line layout model includes the installation height of each transmission line and the spanning distance between two adjacent transmission lines.

[0145] Figure 4 FIG. 1 is a structural block diagram of a system for arranging transmission line crossing measurement according to another embodiment of the present disclosure. Figure 4 and 3 As shown, Figure 4 The objective function building module 410 and the objective function solving module 420 in Figure 3 The structures or functions of the objective function construction module 310 and the objective function solution module 320 are the same and will not be described in detail here.

[0146] like Figure 4 As shown, the objective function solving module 420 includes:

[0147] An initial model determining unit 421, configured to determine a first line layout model based on the initial line layout model;

[0148] The model iteration unit 422 is configured to perform the following iteration operations based on the first line layout model:

[0149] In the first line layout model, a dynamic distribution diagram of shadow areas formed by projections of each of the transmission lines and each of the towers in the first line layout model under light is simulated;

[0150] Based on the dynamic distribution diagram of the shadow area, calculating the shadow shielding coefficient of the shadow area on each of the transmission lines;

[0151] Using the shadow shielding coefficient of each of the transmission lines as the coefficient of the corresponding optimization variable in the objective function, updating the objective function;

[0152] Calculating the objective function based on the installation height of each of the transmission lines in the first line layout model and the span distance between two adjacent transmission lines to obtain the electrical safety performance of the first line layout model;

[0153] When the electrical safety performance of the first line layout model does not satisfy the electrical safety performance constraint condition, and / or the spanning distance between two adjacent transmission lines in the first line layout model does not satisfy the spanning distance constraint condition, adjusting the first line layout model to obtain a second line layout model;

[0154] Based on the second wiring arrangement model, the first wiring arrangement model is updated, and the iterative operation is continued.

[0155] In one implementation, the objective function solving module 420 further includes:

[0156] The target model determining unit 423 is configured to determine the target circuit layout model based on the second circuit layout model when the number of iterations of the iterative operation meets the preset number.

[0157] In one implementation, the objective function solving module 420 further includes:

[0158] An initial model determination unit 424 is used to construct the initial line layout model according to the initial position information and initial size structure information of each of the transmission lines in the target power transmission area, and the initial position information and initial size structure information of each tower;

[0159] The initial position information includes the installation height of the transmission line and the spanning distance between the transmission line and adjacent transmission lines.

[0160] According to an embodiment of the present disclosure, the above system of the present disclosure can be applied to an electronic device, a readable storage medium and a computer program product.

[0161] Figure 5 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0162] like Figure 5As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0163] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0164] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a method for arranging a transmission line crossing span measurement. For example, in some embodiments, a method for arranging a transmission line crossing span measurement may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for arranging a transmission line crossing span measurement described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute a method for arranging transmission line crossing measurement in any other appropriate manner (for example, by means of firmware).

[0165] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0166] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0167] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0168] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0169] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0170] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0171] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0172] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for arranging transmission line crossing measurement, characterized in that: include: Taking the installation height of each transmission line in the target power transmission area and the span distance between two adjacent transmission lines as optimization variables, and taking the electrical safety performance of the target power transmission area as the dependent variable, an objective function is constructed; Based on the spanning distance constraint and the electrical safety performance constraint, the objective function is solved for an optimal solution to obtain a target line layout model of the target power transmission area, which includes: Based on the initial line layout model, determining a first line layout model; Based on the first line arrangement model, the following iterative operations are performed: In the first line layout model, a dynamic distribution diagram of shadow areas formed by projections of the transmission lines and towers in the first line layout model under light is simulated; Based on the dynamic distribution diagram of the shadow area, calculating the shadow shielding coefficient of the shadow area on each of the transmission lines; Using the shadow shielding coefficient of each of the transmission lines as the coefficient of the corresponding optimization variable in the objective function, updating the objective function; Based on the installation height of each of the transmission lines in the first line layout model and the span distance between two adjacent transmission lines, the objective function is calculated to obtain the electrical safety performance of the first line layout model; When the electrical safety performance of the first line layout model does not satisfy the electrical safety performance constraint condition, and / or the spanning distance between two adjacent transmission lines in the first line layout model does not satisfy the spanning distance constraint condition, adjusting the first line layout model to obtain a second line layout model; Based on the second line layout model, updating the first line layout model, and returning to continue to perform the iterative operation; When the number of iterations of the iterative operation meets the preset number, the electrical safety performance of the first line layout model meets the electrical safety performance constraint condition, and the spanning distance between two adjacent transmission lines in the first line layout model meets the spanning distance constraint condition, determining the target line layout model based on the first line layout model; The target line layout model includes the installation height of each transmission line and the span distance between two adjacent transmission lines.

2. The method according to claim 1, characterized in that Also includes: Constructing the initial line layout model according to the initial position information and initial size structure information of each transmission line in the target power transmission area, and the initial position information and initial size structure information of each tower; The initial position information includes the installation height of the transmission line and the spanning distance between the transmission line and adjacent transmission lines.

3. The method according to claim 1, characterized in that The span distance constraint condition includes: the span distance between any two adjacent transmission lines is greater than a span distance lower limit value and less than a span distance upper limit value.

4. The method according to claim 1, characterized in that: The electrical safety performance constraint condition includes at least one of the following: The maximum electric field strength in each of the transmission lines is greater than the lower limit of the electric field strength and less than the upper limit of the electric field strength; The operating voltage of each of the transmission lines is greater than the lower voltage limit and greater than the upper voltage limit; A difference between input power and output power of the target power transmission area is greater than a power loss lower limit value and less than a power loss upper limit value.

5. A system for arranging cross-over transmission lines, characterized in that: include: An objective function construction module, for constructing an objective function using the installation height of each transmission line in the target power transmission area and the span distance between two adjacent transmission lines as optimization variables, and using the electrical safety performance of the target power transmission area as a dependent variable; An objective function solving module, used to solve the objective function for an optimal solution based on a spanning distance constraint and an electrical safety performance constraint, and obtain a target line layout model of the target power transmission area, wherein the target line layout model includes the erection height of each transmission line and the spanning distance between two adjacent transmission lines; Wherein, the objective function solving module includes: An initial model determining unit, configured to determine a first line layout model based on the initial line layout model; A model iteration unit is used to perform the following iteration operations based on the first line layout model: In the first line layout model, a dynamic distribution diagram of shadow areas formed by projections of the transmission lines and towers in the first line layout model under light is simulated; Based on the dynamic distribution diagram of the shadow area, calculating the shadow shielding coefficient of the shadow area on each of the transmission lines; Using the shadow shielding coefficient of each of the transmission lines as the coefficient of the corresponding optimization variable in the objective function, updating the objective function; Based on the installation height of each of the transmission lines in the first line layout model and the span distance between two adjacent transmission lines, the objective function is calculated to obtain the electrical safety performance of the first line layout model; When the electrical safety performance of the first line layout model does not satisfy the electrical safety performance constraint condition, and / or the spanning distance between two adjacent transmission lines in the first line layout model does not satisfy the spanning distance constraint condition, adjusting the first line layout model to obtain a second line layout model; Based on the second line layout model, updating the first line layout model, and returning to continue to perform the iterative operation; a target model determination unit, configured to determine the target line layout model based on the first line layout model when the number of iterations of the iterative operation meets a preset number, the electrical safety performance of the first line layout model meets the electrical safety performance constraint condition, and the spanning distance between two adjacent transmission lines in the first line layout model meets the spanning distance constraint condition.

6. The system according to claim 5, characterized in that The objective function solving module also includes: An initial model determination unit, configured to construct the initial line layout model according to the initial position information and initial size structure information of each of the transmission lines in the target power transmission area, and the initial position information and initial size structure information of each tower; The initial position information includes the installation height of the transmission line and the spanning distance between the transmission line and adjacent transmission lines.

Images