A method and system for planning and designing distribution network lines based on images captured by drones

Abstract

The present invention relates to the technical field of line planning, and specifically discloses a method and system for planning and designing a distribution network line based on an image captured by an unmanned aerial vehicle, including the following steps: Step S1: Obtain a planning area, obtain terrain information according to the image captured by the unmanned aerial vehicle, divide the planning area into several area blocks, and obtain the three-dimensional coordinates corresponding to the center points of each area block; Step S2: Select the area blocks where the starting and ending poles of the distribution network are located at the interface to obtain an initial path; on the initial path, select area blocks at a preset interval as initial area blocks; Step S3: Set a reference radius, and use the center of the initial area block as the center of the sphere to obtain a reference set, and calculate the matching value PI of each area block in the reference set; Step S4: Select the area block with the highest matching value in the reference set as the best area block, and use the center points of the best area blocks corresponding to each initial area block as the positions of the poles to obtain the final path.

Description

Technical Field

[0001] The present invention relates to the technical field of line planning, and particularly relates to a method and system for planning and designing a distribution network line based on an image captured by an unmanned aerial vehicle (UAV). Background Art

[0002] The distribution network is an important part of the power system, covering urban and rural areas and connecting thousands of households. It is the "last mile" of power supply. Its planning and construction directly affect the stability, safety and efficiency of power supply. The line planning of the distribution network involves multiple aspects, including load demand and power supply capacity, power transmission efficiency, reliability and stability, economy and cost.

[0003] When planning the distribution network line, it is very important to consider the terrain factor, because the terrain directly affects the layout of the line, the construction cost and the difficulty of future operation and maintenance. The complex terrain in mountainous areas requires that the line planning must take into account the undulation of the terrain and avoid setting lines in areas with large slopes. Generally, the terrain in rural areas is relatively open, but natural obstacles such as rivers and forests may also be encountered.

[0004] In the prior art, in order to consider the terrain factor, when planning the distribution network line, relevant professionals often need to go to the field to investigate the terrain of the distribution area. This manual field investigation method is not only inaccurate and inefficient, but also consumes labor costs. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for planning and designing a distribution network line based on an image captured by an unmanned aerial vehicle (UAV) to solve the above technical problems.

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

[0007] A method for planning and designing a distribution network line based on an image captured by an unmanned aerial vehicle (UAV) includes the following steps:

[0008] Step S1: Obtain a planning area, and obtain the terrain information of the planning area through an unmanned aerial vehicle (UAV). According to the terrain information, establish a three-dimensional model of the planning area. Divide an air area and a solid area in the three-dimensional model, and obtain an interface between the air area and the solid area;

[0009] Divide the interface grid into several regional blocks; and obtain the three-dimensional coordinates corresponding to the center points of the respective regional blocks;

[0010] Step S2: Select the regional blocks where the starting pole and the ending pole of the distribution network are located on the interface, connect the starting pole and the ending pole to obtain an initial path. On the initial path, select a regional block at every preset interval and denote it as the initial regional block of the pole;

[0011] Step S3: Set a reference radius, and take the center point of the initial region block as the center of a sphere to obtain a spherical region; and obtain the intersection of all the region blocks within the spherical region and all the region blocks on the interface, denoted as the reference set; obtain the matching value PI of each region block within the reference set:

[0012]

[0013] where n is the total number of region blocks within the reference set, P0 is the center point of the initial region block, P i is the center point of the i-th region block within the reference set, |P0P i | is the distance between P0 and P i , Pcs is the center point of the current region block, Z s is the z-axis coordinate of the center point of the s-th region block adjacent to the current region block, Z k is the z-axis coordinate of the center point of the current region block, and ε is a correction factor and ε > 0;

[0014] Step S4: Select the region block with the highest matching value within the reference set, denoted as the best region block, and replace the initial region block with the best region block; then take the center points of the best region blocks corresponding to each initial region block as the positions of the poles, and obtain the final path.

[0015] As a further solution of the present invention: The process of obtaining the three-dimensional coordinates corresponding to the center points of each region block includes:

[0016] Establish a three-dimensional coordinate system, make the plane formed by the x-axis and the y-axis parallel to the horizontal plane, and use the altitude as the z-axis, perpendicular to the horizontal plane.

[0017] As a further solution of the present invention: The process of performing mesh division on the interface includes:

[0018] Divide the interface into rectangular meshes to obtain a number of rectangular squares, denote each rectangular square as a region block; obtain the center point of the region block, and obtain the coordinates of the center point in the three-dimensional coordinate system, denoted as the coordinates of the center point of the region block.

[0019] As a further solution of the present invention: The setting range of the preset interval is [40m, 70m].

[0020] As a further solution of the present invention: The process of obtaining the matching value of each region block within the reference set includes:

[0021] Obtain each region block within the reference set, and determine whether the region block is a region block where a pole can be erected; if it is a region block where a pole can be erected, then obtain the matching value of the region block; if it is a region block where a pole cannot be erected, then exclude the region block within the reference set.

[0022] As a further solution of the present invention: when the matching values of two regional blocks in the reference set are the same, obtain the relative distances between the two regional blocks and the initial regional block Compare the relative distances of the two regional blocks, and select the regional block with the smaller relative distance as the optimal regional block.

[0023] As a further solution of the present invention: the setting process of the reference radius includes:

[0024] Denote the reference radius as R, obtain the center point of the previous optimal regional block, denoted as Pzs, then the reference radius satisfies the constraint R + |P0Pzs| ≤ 70m.

[0025] As a further solution of the present invention: a distribution network line planning and design system based on drone-captured images, including:

[0026] Acquisition and processing module: obtain the planning area, and obtain the topographic information of the planning area through a drone. According to the topographic information, establish a three-dimensional model of the planning area; divide the air area and the entity area in the three-dimensional model, and obtain the interface between the air area and the entity area;

[0027] Divide the interface grid into several regional blocks; and obtain the three-dimensional coordinates corresponding to the center points of each regional block;

[0028] Initial path determination module: select the regional blocks where the starting pole and the ending pole of the distribution network are located on the interface, connect the starting pole and the ending pole to obtain an initial path; on the initial path, select a regional block at every preset interval, denoted as the initial regional block of the pole;

[0029] Initial path correction module: set a reference radius, and take the center point of the initial regional block as the center of the sphere to obtain a spherical area; and obtain the intersection of all regional blocks in the spherical area and all regional blocks on the interface, denoted as the reference set; obtain the matching value PI of each regional block in the reference set:

[0030]

[0031] where n is the total number of regional blocks in the reference set, P0 is the center point of the initial regional block, P i is the center point of the i-th regional block in the reference set, |P0P i | is the distance between P0 and P i is the distance between P0 and P s is the z-axis coordinate of the center point of the s-th regional block adjacent to the current regional block, Z kis the z-axis coordinate of the center point of the current regional block, and ε is a correction coefficient and ε > 0;

[0032] Select the regional block with the highest matching value in the reference set, denoted as the best regional block, and replace the initial regional block with the best regional block; then, use the center points of the best regional blocks corresponding to each initial regional block as the positions of the poles, and obtain the final path.

[0033] Advantages of the present invention:

[0034] In the prior art, in order to consider terrain factors, during the distribution network line planning, relevant professionals often need to conduct on-site investigations of the terrain of the distribution area; this manual on-site investigation method is not only inaccurate enough, but also has low efficiency, and at the same time consumes labor costs; compared with the prior art, the high-definition images taken by the drone in the present invention can quickly and accurately obtain terrain and ground object information, greatly reducing the time and labor required for traditional manual surveying; the three-dimensional model can more realistically reflect the actual terrain and landforms, making the design of the distribution network more accurate and avoiding design errors caused by terrain factors; since the manual on-site survey is reduced, the labor cost and possible human errors are correspondingly reduced, which helps to reduce the overall project expenditure in the long run; it improves the quality and efficiency of the distribution network planning and design, while reducing costs and risks, and enhancing the sustainability and reliability of the project; by calculating the matching values of the regional blocks, the drone image information can be effectively used for the planning and design of the distribution network lines, improving the accuracy and scientificity of path selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention will be further described below with reference to the accompanying drawings.

[0036] Figure 1 is a schematic structural diagram of a distribution network line planning and design method and system based on drone-captured images according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0038] Please refer to Figure 1 as shown, the present invention is a distribution network line planning and design method based on drone-captured images, including the following steps:

[0039] Step S1: Obtain the planned area, and use a drone to obtain the terrain information of the planned area. Based on the terrain information, establish a three-dimensional model of the planned area; divide the air area and the solid area in the three-dimensional model, and obtain the interface between the air area and the solid area;

[0040] Divide the interface grid into several regional blocks; and obtain the three-dimensional coordinates corresponding to the center points of each regional block;

[0041] It should be noted that the terrain information is obtained from the captured images acquired by the drone, and the process includes:

[0042] Obtain the shooting range of the shooting terminal in the drone. Divide the planned area into several sub-areas according to the shooting range, number each sub-area, record the positions of each sub-area, and associate the numbers with the positions; sequentially obtain the captured images of each sub-area through the drone, and splice the captured images of each sub-area according to the number of the sub-area and its corresponding position to obtain the captured image of the planned area;

[0043] The process of obtaining the three-dimensional coordinates corresponding to the center points of each regional block includes:

[0044] Establish a three-dimensional coordinate system, make the plane formed by the x-axis and the y-axis parallel to the horizontal plane, and use the altitude as the z-axis, perpendicular to the horizontal plane;

[0045] It should be noted that on the three-dimensional model, randomly select the center point of a regional block as the origin of the three-dimensional coordinate system, and set the unit length of each coordinate axis in the three-dimensional coordinate system according to the side length of the regional block; here, set the unit length of the three-dimensional coordinate system = the side length of the regional block;

[0046] The process of grid-dividing the interface includes:

[0047] Divide the interface into a rectangular grid to obtain several rectangular squares, and denote each rectangular square as a regional block; obtain the center point of the regional block, and obtain the coordinates of the center point in the three-dimensional coordinate system, denoted as the coordinates of the center point of the regional block;

[0048] It should be noted that the distance between the line side of the pole conductor and the permanent building under the maximum wind deflection condition should not be less than the following values: 1 kV to 10 kV: 1.5 m for bare conductors and 0.75 m for insulated conductors (no doors, windows or solid walls in adjacent buildings); below 1 kV: 1 m for bare conductors and 0.2 m for insulated conductors (no doors, windows or solid walls in adjacent buildings); set the safety distance threshold L between the pole and the building as L = 1.5 m; and generally determine its floor area according to the specifications and dimensions of the cabinet; for example, if a cabinet has a width of 600 mm and a depth of 1200 mm, then its floor area is 0.72 square meters; then in the process of dividing the planned area, set the range of the side length of the rectangular grid within the rectangular grid as [1.5 m, 2 m];

[0049] Step S2: Select the area blocks where the starting pole and the ending pole of the distribution network are located on the interface, connect the starting pole and the ending pole to obtain the initial path; on the initial path, select an area block at every preset interval, denoted as the initial area block of the pole;

[0050] It can be understood that the starting pole is the power input end of the distribution network within the planned area, and the ending pole is the power output end of the distribution network within the planned area; the positions of the starting pole and the ending pole can be manually selected by relevant personnel, or can be selected by calculating the matching values of each area block at the edges of the input end and the output end of the planned area;

[0051] The range of the preset interval is [40 m, 70 m];

[0052] It can be understood that the pole spacing standard refers to the minimum distance between poles in the power transmission and distribution line to ensure the safety and reliability of power transmission; the pole spacing standard is usually formulated according to factors such as the voltage level, line length, terrain and landform of the power transmission and distribution line. In general low-voltage power lines, the pole spacing standard is usually about 50 meters; therefore, set the range of the preset interval as [40 m, 70 m];

[0053] Step S3: Set a reference radius, and take the center point of the initial area block as the center of the sphere to obtain a spherical area; and obtain the intersection of all area blocks within the spherical area and all area blocks on the interface, denoted as the reference set; obtain the matching value PI of each area block within the reference set:

[0054]

[0055] Among them, n is the total number of area blocks within the reference set, P0 is the coordinate of the center point of the initial area block, P i is the coordinate of the center point of the i-th area block within the reference set, P kP is the coordinate of the center point of the current regional block s-z is the z-axis coordinate of the center point of the s-th regional block adjacent to the initial regional block, and ε is a correction coefficient and ε > 0;

[0056] It should be noted that represents the ratio of the average distance between the center point of the initial regional block and the center points of all other regional blocks in the reference set to the distance between the center point of the initial regional block and the center point of the current regional block; represents the sum of the distances between the center point of the initial regional block and the center points of all other regional blocks in the reference set; n|P0Pcs| represents the distance between the center point of the initial regional block and the center point of the current regional block multiplied by the total number of regional blocks within the reference range, where n is used to calculate the average value; is used to measure the relative distance difference of the current regional block relative to the initial regional block and other regional blocks; if this ratio is smaller, it means that the distance between the current regional block and the initial regional block is farther;

[0057] represents the average value of the square of the height difference between the initial regional block and the current regional block on the z-axis, and is used to measure the height difference of the current regional block and the regional blocks in its vicinity. If this value is lower, it means that the height difference of the current regional block and the regional blocks in its vicinity is greater; among them, the 8 regional blocks adjacent to the current regional block are respectively the regional blocks above, below, left, right, upper left, upper right, lower left and lower right of the current regional block;

[0058] The correction coefficient ε is obtained through experiments and is used to adjust the size of the matching value to make the calculation result more in line with the actual requirements and situations;

[0059] The process of obtaining the matching values of the regional blocks in the reference set includes:

[0060] Obtain the regional blocks in the reference set, and judge whether the regional block is a regional block where a utility pole can be erected; if it is a regional block where a utility pole can be erected, obtain the matching value of the regional block; if it is a regional block where a utility pole cannot be erected, exclude the regional block from the reference set;

[0061] It can be understood that when erecting a utility pole, a certain safety distance needs to be maintained from the residents, and the utility pole cannot be erected in the regional blocks where landscapes such as rivers and trees are located; then the process of judging whether the regional block is a regional block where a utility pole can be erected includes: according to the captured image of the planned area obtained by the drone, obtaining whether there are buildings and landscapes in the regional block through image recognition technology, where the buildings include high-rise buildings and bridges, and the landscapes include rivers, trees, and farmland; record the regional blocks with buildings and landscapes as special regional blocks;

[0062] The process of obtaining the special regional blocks according to the captured image of the planned area includes:

[0063] Obtain sample images of landscapes and buildings, divide the sample images into different categories, extract features from the sample images of each category to obtain image features corresponding to each category, and establish a feature library;

[0064] Perform grid division on the captured image to obtain a number of image blocks, where the division size of the image blocks is the same as that of the area blocks; identify each image block to obtain the image features of the image block, denoted as image block features; according to the feature library, obtain the category corresponding to the image feature with the highest similarity to the image block feature, denoted as the category of the image block, that is, the category of the area block corresponding to this image block;

[0065] It can be understood that making the division size of the image blocks the same as that of the area blocks is to facilitate distinguishing the categories of each area block;

[0066] The process of setting the reference radius includes:

[0067] Denote the reference radius as R, obtain the center point of the previous best area block, denoted as Pzs, then the reference radius satisfies the constraint R + |P0Pzs| ≤ 70m;

[0068] It can be understood that according to the preset distance, the maximum distance between two utility poles cannot exceed 70m, so R + |P0Pzs| is the maximum distance between the current utility pole and the previous utility pole in the reference set, which needs to satisfy not exceeding 70m;

[0069] Step S4: Select the area block with the highest matching value in the reference set, denoted as the best area block, and replace the initial area block with the best area block; then use the center points of the best area blocks corresponding to each initial area block as the positions of the utility poles, and obtain the final path;

[0070] When there are two area blocks with the same matching value in the reference set, obtain the relative distances of the two area blocks from the initial area block Compare the relative distances of the two area blocks, and select the area block with the smaller relative distance as the best area block.

[0071] A power distribution network line planning and design system based on drone-captured images, comprising:

[0072] Acquisition and processing module: Obtain the planning area, obtain the topographic information of the planning area through a drone, and establish a three-dimensional model of the planning area according to the topographic information; divide the air area and the solid area in the three-dimensional model, and obtain the interface between the air area and the solid area;

[0073] Mesh-divide the interface into several area blocks; and obtain the three-dimensional coordinates corresponding to the center points of each area block;

[0074] Initial path determination module: Select the area blocks where the starting pole and the ending pole of the distribution network are located on the interface, connect the starting pole and the ending pole to obtain an initial path; on the initial path, select an area block at every preset interval, which is denoted as the initial area block of the pole.

[0075] Initial path correction module: Set a reference radius, and take the center point of the initial area block as the center of the sphere to obtain a spherical area; and obtain the intersection of all area blocks within the spherical area and all area blocks on the interface, which is denoted as the reference set; obtain the matching value PI of each area block within the reference set:

[0076]

[0077] where n is the total number of area blocks within the reference set, P0 is the center point of the initial area block, P i is the center point of the i-th area block within the reference set, |P0P i | is the distance between P0 and P i , Pcs is the center point of the current area block, Z s is the z-axis coordinate of the center point of the s-th area block adjacent to the current area block, Z k is the z-axis coordinate of the center point of the current area block, and ε is a correction coefficient and ε > 0;

[0078] Select the area block with the highest matching value within the reference set, which is denoted as the best area block, and replace the initial area block with the best area block; then use the center points of the best area blocks corresponding to each initial area block as the positions of the poles, and obtain the final path.

[0079] The above has described a specific embodiment of the present invention in detail, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the present invention application should still fall within the scope covered by the patent of the present invention.

Claims

1. A method for planning and designing a distribution network line based on images captured by an unmanned aerial vehicle, characterized in that Including the following steps: Step S1: Obtain the planning area, obtain the terrain information of the planning area through a drone, and establish a three-dimensional model of the planning area according to the terrain information; Divide the air area and the solid area in the three-dimensional model, and obtain the interface between the air area and the solid area; Divide the interface grid into several regional blocks, and obtain the three-dimensional coordinates corresponding to the center points of each regional block; Step S2: Select the regional blocks where the starting pole and the ending pole of the distribution network are located on the interface, connect the starting pole and the ending pole, and obtain the initial path; On the initial path, select a regional block at every preset interval, and record it as the initial regional block of the pole; Step S3: Set a reference radius, and take the center point of the initial regional block as the center of the sphere to obtain a spherical area; and obtain the intersection of all regional blocks within the spherical area and all regional blocks on the interface, and record it as the reference set; obtain the matching value PI of each regional block within the reference set: Among them, n is the total number of regional blocks in the reference set, P0 is the center point of the initial regional block, and P i is the center point of the i-th regional block in the reference set, and |P0P i | is the distance between P0 and P i , Pcs is the center point of the current regional block, and Z s is the z-axis coordinate of the center point of the s-th regional block adjacent to the current regional block, and Z k is the z-axis coordinate of the center point of the current regional block, and ε is the correction coefficient and ε > 0; Step S4: Select the regional block with the highest matching value within the reference set, and record it as the best regional block, and replace the initial regional block with the best regional block; then take the center points of the best regional blocks corresponding to each initial regional block as the positions of the poles, and obtain the final path; In step S3, the process of setting the reference radius includes: Record the reference radius as R, obtain the center point of the previous best regional block, and record it as Pzs, then the reference radius satisfies the constraint R + |P0Pzs| ≤ 70m; In step S4, when the matching values of two regional blocks in the reference set are the same, obtain the relative distances of the two regional blocks from the initial regional block Compare the relative distances of the two regional blocks, and select the regional block with the smaller relative distance as the optimal regional block.

2. The method for planning and designing a distribution network line based on an image captured by a drone according to claim 1, wherein In step S1, the process of obtaining the three-dimensional coordinates corresponding to the center points of each regional block includes: Establish a three-dimensional coordinate system, make the plane formed by the x-axis and the y-axis parallel to the horizontal plane, and use the altitude as the z-axis, perpendicular to the horizontal plane.

3. A method for planning and designing a distribution network line based on drone-captured images according to claim 2, characterized in that, In step S1, the process of grid-dividing the interface includes: Divide the interface into rectangular grids to obtain several rectangular squares, and record each rectangular square as a regional block; obtain the center point of the regional block, and obtain the coordinates of the center point in the three-dimensional coordinate system, and record it as the coordinates of the center point of the regional block.

4. A method for planning and designing a distribution network line based on images captured by an unmanned aerial vehicle according to claim 1, characterized in that, In step S2, the setting range of the preset interval is [40m, 70m].

5. A method for planning and designing a distribution network line based on images captured by a drone according to claim 1, characterized in that, In step S3, the process of obtaining the matching value of each regional block within the reference set includes: Obtain each regional block within the reference set, and judge whether the regional block is a regional block where a pole can be erected; if it is a regional block where a pole can be erected, then obtain the matching value of the regional block; if it is a regional block where a pole cannot be erected, then exclude the regional block within the reference set.

6. A distribution network line planning and design system based on images captured by drones, characterized in that, Including: Collection and processing module: Obtain the planning area, obtain the terrain information of the planning area through a drone, and establish a three-dimensional model of the planning area according to the terrain information; Divide the air area and the solid area in the three-dimensional model, and obtain the interface between the air area and the solid area; Divide the interface grid into several regional blocks; and obtain the three-dimensional coordinates corresponding to the center points of each regional block; Initial path determination module: Select the regional blocks where the starting pole and the ending pole of the distribution network are located on the interface, connect the starting pole and the ending pole, and obtain the initial path; On the initial path, a regional block is selected at every preset interval, which is denoted as the initial regional block of the utility pole. Initial path correction module: Set a reference radius, and with the center point of the initial regional block as the center of the sphere, obtain a spherical region; and obtain the intersection of all regional blocks within the spherical region and all regional blocks on the interface, which is denoted as the reference set; obtain the matching value PI of each regional block within the reference set: Among them, n is the total number of regional blocks in the reference set, P0 is the center point of the initial regional block, and P i is the center point of the i-th regional block in the reference set, and |P0P i | is the distance between P0 and P i , Pcs is the center point of the current regional block, and Z s is the z-axis coordinate of the center point of the s-th regional block adjacent to the current regional block, and Z k is the z-axis coordinate of the center point of the current regional block, and ε is a correction coefficient and ε > 0; Select the regional block with the highest matching value within the reference set, which is denoted as the optimal regional block, and replace the initial regional block with the optimal regional block; then use the center points of the optimal regional blocks corresponding to each initial regional block as the positions of the utility poles, and obtain the final path. The setting process of the reference radius includes: Denote the reference radius as R, obtain the center point of the previous optimal regional block, which is denoted as Pzs, then the reference radius satisfies the constraint R + |P0Pzs| ≤ 70m. When there are two region blocks in the reference set with the same matching value, obtain the relative distances between the two region blocks and the initial region block Compare the relative distances between the two region blocks and select the region block with the smaller relative distance as the optimal region block.

Images