Cable repairing method based on layered path planning and related equipment

Abstract

The invention relates to the technical field of cable safety, in particular to a cable repairing method based on hierarchical path planning and related equipment, and the method comprises the steps: obtaining an original point cloud of a target cable, carrying out the preprocessing of the original point cloud, and obtaining a damaged region point cloud; according to the method, the damaged area point cloud is subjected to voxelization processing, the damaged area point cloud subjected to voxelization processing is subjected to internal voxel filling, the zigzag path of the target cable is generated according to the voxelization damaged point cloud, the target cable is repaired based on the zigzag path, the method can adapt to the complex form of the damaged area, and the repairing integrity and the repairing quality are improved.

Description

Technical Field

[0001] The present application relates to the field of cable safety technology, and in particular to a cable repair method based on hierarchical path planning and related equipment. Background Art

[0002] In the modern industrial field, cables are important load-bearing structures, and their safety and reliability are of vital importance. During long-term use, cables may be damaged to varying degrees due to external environmental factors, mechanical damage, or material aging, which will not only reduce the load-bearing capacity of the cables, but may also cause serious safety hazards. Therefore, it is necessary to repair the damaged areas of the cables in a timely and effective manner.

[0003] Traditional repair methods mainly rely on manual inspection and repair operations, which are not only inefficient and costly, but also difficult to ensure the quality of repair. However, with the development of technology, automatic repair methods based on robotics technology have gradually been widely used, significantly improving the automation level and efficiency of repair. However, the shape of the damaged area of ​​the cable is complex, and the repair path generated by the existing cable repair method cannot completely cover all the damaged areas, resulting in incomplete repair or reduced repair quality. Summary of the invention

[0004] In order to overcome the deficiencies of the prior art, the present invention provides a cable repair method and related equipment based on hierarchical path planning, which can adapt to the complex morphology of the damaged area and improve the repair integrity and quality.

[0005] A first aspect of the present application provides a cable repair method based on hierarchical path planning, the method comprising: Obtain the original point cloud of the target cable; Preprocessing the original point cloud to obtain a damaged area point cloud; Performing voxel processing on the damaged area point cloud, and performing internal voxel filling on the damaged area point cloud after the voxel processing, to obtain a voxelized damaged point cloud; generating a zigzag path of the target cable according to the voxelized damage point cloud; The target cable is repaired based on the zigzag path.

[0006] In an optional embodiment, the method further comprises: Inserting sampling points between adjacent path points of the zigzag path to obtain a new path point set; Re-voxelizing the damaged area point cloud using the new voxel size to obtain a new voxelized damaged point cloud; Determine k nearest neighbor voxels corresponding to each path point in the zigzag path according to the new path point set and the new voxelized damaged point cloud, where k is an integer greater than or equal to 1; The zigzag path is modified based on the k nearest neighbor voxels.

[0007] In an optional embodiment, generating the zigzag path of the target cable according to the voxelized damage point cloud comprises: Layering the voxelized damaged point cloud along the height direction to obtain a plurality of slices; Determine the center position of each voxel in a target slice, wherein the target slice is any one of the multiple slices; Each slice is traversed and the zigzag path is generated according to the center position.

[0008] In an optional embodiment, the repairing the target cable based on the zigzag path includes: Determining a starting filling position of the zigzag path; Calculate the damaged volume of the damaged area corresponding to the damaged area point cloud; Determining the repair time and amount of repair materials for the target cable according to the damaged volume; When traversing the zigzag path layer by layer according to the starting filling position, the damaged area is repaired according to the repair time and the amount of the repair material.

[0009] In an optional embodiment, the method further comprises: Comparing the amount of repair material used with actual material consumption data to obtain a comparison result; Whether the actual material consumption data meets expectations is determined based on the comparison result.

[0010] In an optional implementation, the step of performing internal voxel filling on the damaged area point cloud after the voxelization process to obtain a voxelized damaged point cloud comprises: Dividing the damaged area point cloud into a plurality of voxel grids according to a preset voxel side length; Binarizing a target voxel grid to determine occupied voxels and unoccupied voxels in the target voxel grid, wherein the target voxel grid is any voxel grid among the multiple voxel grids; Determine the inner space of the damaged area point cloud according to the occupied voxels and the unoccupied voxels; The internal space is filled with internal voxels to obtain the voxelized damaged point cloud.

[0011] In an optional implementation, the preprocessing of the original point cloud to obtain the damaged area point cloud includes: Calculating an average distance between a target original point and each original point in a local neighborhood, wherein the original point cloud includes a plurality of original points, and the target original point is any one of the plurality of original points; Eliminate outlier original points in the original point cloud according to the average distance and a preset threshold to obtain a target point cloud; The target point cloud is fitted with a cylindrical surface to obtain the damaged area point cloud.

[0012] A second aspect of the present application provides a cable repair device based on hierarchical path planning, the device comprising: An acquisition module, used to acquire the original point cloud of the target cable; A first processing module, used for preprocessing the original point cloud to obtain a damaged area point cloud; A second processing module is used to voxelize the damaged area point cloud and fill the damaged area point cloud with internal voxels after the voxelization process to obtain a voxelized damaged point cloud; A third processing module, configured to generate a zigzag path of the target cable according to the voxelized damage point cloud; A repair module is used to repair the target cable based on the zigzag path.

[0013] A third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the cable repair method based on hierarchical path planning when executing the computer program.

[0014] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned cable repair method based on hierarchical path planning.

[0015] In summary, the cable repair method and related equipment based on hierarchical path planning provided by the present application obtain the original point cloud of the target cable, extract the point cloud of the damaged area after preprocessing the original point cloud, and accurately identify the damaged area to avoid misoperation on the non-damaged area, thereby improving the repair quality. Secondly, the point cloud of the damaged area is voxelized and the internal voxel is filled, which can convert the complex point cloud data into a regular voxel grid, which not only simplifies the data structure, but also retains the spatial information of the damaged area, and fills the void inside the damaged area, reducing the uncertainty in the repair process. Furthermore, the zigzag path generated based on the voxelized damaged point cloud can flexibly adapt to the complex morphology of the damaged area, ensuring the feasibility and effectiveness of the repair path. By performing the repair operation along the zigzag path, it can be ensured that the damaged area is completely covered and effectively repaired, thereby improving the integrity and quality of the repair. In addition, the original path nodes are replaced with the smaller voxel centers of the k nearest neighbors to achieve path optimization. In addition, by calculating the volume of the damaged area, the amount of material required for repair can be accurately estimated, thus avoiding material waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a cable repair method based on hierarchical path planning shown in an embodiment of the present application; Figure 2 is another flow chart of a cable repair method based on hierarchical path planning shown in an embodiment of the present application; Figure 3 is a schematic diagram of an original point cloud preprocessing process shown in an embodiment of the present application; Figure 4 is an initial path generation diagram in a target cable repair process shown in an embodiment of the present application; Figure 5 is a diagram showing the initial path correction result during the target cable repair process shown in an embodiment of the present application; Figure 6 It is a functional module diagram of a cable repair device based on hierarchical path planning shown in an embodiment of the present application; Figure 7 It is a structural schematic diagram of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0018] The following will clearly and completely describe the concept, specific structure and technical effects of the present invention in combination with the embodiments and drawings, so as to fully understand the purpose, characteristics and effects of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, other embodiments obtained by technicians in this field without creative work are all within the scope of protection of the present invention. In addition, all the connection / connection relationships involved in the patent do not refer to the direct connection of components, but refer to the formation of a better connection structure by adding or reducing connection accessories according to the specific implementation situation. The various technical features in the invention can be combined interchangeably without conflicting with each other.

[0019] Reference Figure 1 As shown, it is a flow chart of a cable repair method based on hierarchical path planning shown in an embodiment of the present application. The cable repair method based on hierarchical path planning includes the following steps.

[0020] S11, obtaining the original point cloud of the target cable.

[0021] The target cable refers to any cable that has a PE layer (i.e., a polyethylene material layer wrapped around the outer layer of the cable) to be repaired. The original point cloud includes three-dimensional scanning point data of the damaged area of ​​the target cable and its surrounding environment. In some embodiments, the electronic device can obtain three-dimensional point cloud data of the target cable including the damaged area of ​​the cable, i.e., the original point cloud, through laser scanning, structured light scanning, and other technologies.

[0022] S12, preprocessing the original point cloud to obtain a damaged area point cloud.

[0023] Among them, the original point cloud contains a large number of invalid points and noise points, so the original point cloud needs to be preprocessed. For example, the electronic device can first use the point cloud filtering algorithm to remove the noise points in the original point cloud and reduce the point cloud density, and extract the damaged point cloud through cylindrical fitting.

[0024] In an optional implementation, the preprocessing of the original point cloud to obtain the damaged area point cloud includes: Calculating an average distance between a target original point and each original point in a local neighborhood, wherein the original point cloud includes a plurality of original points, and the target original point is any one of the plurality of original points; Eliminate outlier original points in the original point cloud according to the average distance and a preset threshold to obtain a target point cloud; The target point cloud is fitted with a cylindrical surface to obtain the damaged area point cloud.

[0025] Refer to Figure 3, where (A) is the original point cloud, (B) is the target point cloud obtained by statistical filtering and voxel downsampling, (C) is the RANSAC cylindrical fitting, and (D) is the damaged area point cloud. In some implementations, the electronic device can process the original point cloud (A) using a statistical filtering method, which can specifically include calculating the average distance of the local neighborhood of each point in the original point cloud, where the local neighborhood refers to the set of points within a certain range around the current point (target original point). For each point in the original point cloud, taking the target original point as an example, the electronic device can calculate the distance from all points in the local neighborhood to the target original point, and calculate the average value of the distance, that is, the average distance. Among them, the average distance reflects the closeness or consistency between the target original point and its surrounding points. According to a preset threshold, the average distance corresponding to the target original point is compared with the preset threshold. If the average distance is greater than the preset threshold, it is considered that there is a significant inconsistency between the target original point and the surrounding points, and the target original point is identified as an outlier original point. According to the same embodiment, by traversing each point in the original point cloud, calculating the average distance between it and each point in the local neighborhood, and comparing it with the preset threshold, the outlier original points in the original point cloud can be eliminated to obtain the target point cloud. Since the target point cloud after statistical filtering still contains a large amount of redundant data, the electronic device can use voxel downsampling to reduce the density to obtain the preprocessed target point cloud (B). After completing the preprocessing, the electronic device can further use the Random Sample Consensus (RANSAC) algorithm to fit the target point cloud (B) with a cylindrical surface. Among them, the RANSAC algorithm randomly samples in the point cloud, iteratively searches for the best model parameters, and divides the point cloud into two parts: one part is the points fitted to the cylindrical surface, and the other part is the points not on the cylindrical surface. The points not on the cylindrical surface are the internal surface point clouds of the scanned damaged area. In order to generate a complete point cloud of the damaged area, these internal point clouds are reprojected onto the fitted cylindrical surface, and the projected points are merged with the points on the initially fitted cylindrical surface to complete the extraction of the damaged area point cloud (D), where the complete damaged point cloud contains the internal and external surface information of the damaged area.

[0026] Through the above optional implementation, through a series of preprocessing steps (including statistical filtering, voxel downsampling and RANSAC cylindrical fitting), the noise and redundant data in the original point cloud are effectively removed, and the point cloud of the damaged area is accurately extracted, which not only improves the quality of the point cloud data, but also ensures the accuracy of subsequent path planning and repair operations.

[0027] S13, voxelizing the damaged area point cloud, and filling the damaged area point cloud with internal voxels after the voxelization process, to obtain a voxelized damaged point cloud.

[0028] After extracting the damaged area point cloud from the original point cloud, the electronic device can voxelize the damaged area point cloud, where voxelization is the process of dividing the three-dimensional space into a number of cubic (voxel) grids.

[0029] Since the damaged area point cloud extracted from the original point cloud only contains surface information, the internal space is empty, that is, there is no actual point cloud data in the internal space. When the damaged area point cloud is voxelized, only the surface point cloud can be voxelized, and the generated voxels only cover the outer surface of the object. In order to generate the corresponding filling path in the internal space, the electronic device needs to perform internal voxel filling on the internal space of the damaged area point cloud after voxelization.

[0030] In an optional implementation, the step of performing internal voxel filling on the damaged area point cloud after the voxelization process to obtain a voxelized damaged point cloud comprises: Dividing the damaged area point cloud into a plurality of voxel grids according to a preset voxel side length; Binarizing a target voxel grid to determine occupied voxels and unoccupied voxels in the target voxel grid, wherein the target voxel grid is any voxel grid among the multiple voxel grids; Determine the inner space of the damaged area point cloud according to the occupied voxels and the unoccupied voxels; The internal space is filled with internal voxels to obtain the voxelized damaged point cloud.

[0031] In some embodiments, the electronic device can construct an axially parallel bounding box (AABB) according to the damaged area point cloud, wherein the bounding box tightly encloses all the point cloud data in the damaged area point cloud. In the AABB bounding box, the electronic device can divide the space of the damaged area point cloud into regular voxel grids along the coordinate axis according to the preset voxel side length to obtain multiple voxel grids. Among them, each voxel grid has a fixed size and coordinates. Taking the target voxel grid as an example, the electronic device can perform binary processing on the target voxel grid to distinguish between occupied voxels (which can be marked as 1) and unoccupied voxels (which can be marked as 0). The occupied voxels are the outer surface voxels, and part of the unoccupied voxels are the internal areas that need to be filled, and the other part is the external space. According to the same implementation method as above, until each voxel grid in the damaged area point cloud is traversed. Then, the electronic device can start from the boundary of the voxel grid and traverse the entire voxel grid using algorithms such as depth first search (DFS) or breadth first search (BFS). During the traversal process, unoccupied voxels that are directly connected to the external environment (i.e., unoccupied voxels that can be directly accessed through the boundary) are marked as part of the external space. After the external space is marked, by comparing all unoccupied voxels, excluding the unoccupied voxels that have been marked as connected to the external space, the hollow areas in the internal space are identified. Specifically, the areas in the remaining unoccupied voxels that are completely surrounded by the surrounding occupied voxels (i.e., the outer surface voxels) are the internal hollow areas.

[0032] Therefore, the identified internal void area can be marked as the area that needs to be filled, that is, the internal space of the damaged area point cloud. Since the internal space is surrounded by the surrounding surface voxels and cannot be directly connected to the external space, it can be filled by generating a filling path. Specifically, the electronic device can use a filling strategy (for example, scan line filling, seed filling, parallel line filling, etc.) to perform internal voxel filling on the internal space. After the internal voxel filling, the internal space in the damaged area point cloud is filled with a series of voxels, thereby obtaining a voxelized damaged point cloud. Among them, the voxelized damaged point cloud not only contains the information of the model surface, but also contains the structural information inside the model, which provides a basis for subsequent hierarchical path planning and repair operations.

[0033] In an embodiment of the present application, the electronic device can layer the damaged area point cloud after voxelization (hereinafter referred to as the voxelized model) along the height direction (Z axis) to obtain multiple slices. Each slice contains a layer of voxels, which is continuous in the XY plane, but separated from the voxels in other slices in the Z axis direction. For each slice, all voxels occupied by the voxelized model in the layer are traversed, and the center position of each voxel (that is, the midpoint coordinates of the voxel in the X, Y, and Z directions) is calculated, and the center position will be used as the starting point for generating the filling path. Then, the electronic device can use a path planning algorithm (such as Zigzag, Concentric, Hilbert Curve, etc.) to traverse the voxel center and generate a filling path. After completing the generation of the filling path of one layer of slices, it will move to the next layer of slices and repeat the above process to obtain the filling path of each slice layer, so the electronic device can fill the internal voxels of the internal space according to the filling path of each slice layer.

[0034] Through the above optional implementation, the problem of missing internal space of the damaged area point cloud is effectively solved through voxel processing and internal voxel filling. By constructing AABB bounding boxes and dividing voxel grids, the point cloud of the damaged area is accurately discretized, and the internal voxel filling ensures that the internal space is completely filled, which improves the guarantee for subsequent hierarchical path planning and repair operations.

[0035] S14: Generate a zigzag path of the target cable according to the voxelized damage point cloud.

[0036] Based on the filled voxelized damage point cloud, the electronic device can generate one or more zigzag paths, wherein the zigzag paths cover the entire damage area and ensure that the repair material can be evenly and effectively covered.

[0037] In an optional embodiment, generating the zigzag path of the target cable according to the voxelized damage point cloud comprises: Layering the voxelized damaged point cloud along the height direction to obtain a plurality of slices; Determine the center position of each voxel in a target slice, wherein the target slice is any one of the multiple slices; Each slice is traversed and the zigzag path is generated according to the center position.

[0038] In some embodiments, the electronic device can layer the voxelized damage point cloud along the height direction (Z-axis direction), and for each layer of voxel slices in the height direction, the voxel center is used as a path node, and a zigzag path is generated using a DFS algorithm, A*, BFS, Dijkstra, etc. Figure 4 . Among them, the DFS algorithm recursively traverses the voxels in the slice, starting from a starting voxel and visiting the unvisited voxels in turn along four adjacent directions. Each time a new voxel node is visited, the node is marked as visited, and its adjacent unvisited nodes are explored. The recursive process continues until all accessible voxels of the current path have been traversed. Then, the DFS algorithm backtracks to the previous node and continues to explore other unvisited paths. In addition, when a layer of slices is traversed, the next layer is traversed from the same end of the path end of that layer to ensure that subsequent repair devices are filled coherently between layers. In addition, electronic devices can also use Fermat spirals, Piano curves, contours, Hilbert curves, etc. as filling paths.

[0039] Through the above optional implementation, a zigzag path is generated through hierarchical voxelization and DFS algorithm to ensure uniform coverage of the damaged area of ​​the cable, improve the repair efficiency and effect, achieve coherent filling of the repair material in the height direction, and optimize the repair path planning.

[0040] S15, repairing the target cable based on the zigzag path.

[0041] In some embodiments, a suitable repair material such as carbon fiber cloth, epoxy resin, etc. may be selected according to the material and damage of the target cable. Then, the electronic device may generate a repair instruction based on the zigzag path obtained in step S14, and send the repair instruction to the repair device, so that the repair device can cover the damaged area of ​​the target cable with the repair material layer by layer along the planned zigzag path.

[0042] In an optional embodiment, the repairing the target cable based on the zigzag path includes: Determining a starting filling position of the zigzag path; Calculate the damaged volume of the damaged area corresponding to the damaged area point cloud; Determining the repair time and amount of repair materials for the target cable according to the damaged volume; When traversing the zigzag path layer by layer according to the starting filling position, the damaged area is repaired according to the repair time and the amount of the repair material.

[0043] In some embodiments, during the repair process, the electronic device can first determine the starting filling position of the zigzag path, control the repair device (such as a glue gun) to start from the inspiration filling position, fill layer by layer, and use a serpentine movement method between layers. Since the coordinate system of the damaged point cloud is random relative to the slicing direction, it is necessary to rotate the point cloud so that the slicing plane is parallel to the coordinate plane. First, the center coordinates of the damaged point cloud are calculated, and then the vertical direction from the center to the cylindrical axis is determined as the height direction of the model, and the plane perpendicular to the height direction is the slicing plane. Secondly, based on the calculated volume of the damaged area, the time required for the entire filling process and the amount of repair materials can be estimated in advance, ensuring that the repair materials and equipment are ready, starting from the starting filling position, and repairing layer by layer according to the zigzag path. In addition, during the repair process, the repair device can also start from the bottom of the damaged area and traverse the path layer by layer to fill.

[0044] Specifically, the electronic device can use the α-shape algorithm to triangulate the point cloud of the damaged area to obtain a three-dimensional model of the damaged area. Among them, the α-shape algorithm can effectively process the point cloud data, generate accurate boundaries, and construct a triangulated mesh model of the damaged area. In addition, the electronic device can also triangulate the point cloud of the damaged area using triangulated models such as Poisson reconstruction and spherical rotation to generate a triangulated point cloud. On this basis, the volume calculation formula of the polyhedron is used to accurately calculate the volume of the damaged area. Calculating the volume of the damaged area helps to accurately estimate the amount of material extrusion (amount of repair material) required during the repair process, thereby ensuring the effective use of materials and avoiding waste. Secondly, during the repair process, the amount of repair material is kept matching the actual volume of the damaged area, thereby improving the repair efficiency and reducing material waste.

[0045] In an optional embodiment, the method further comprises: Comparing the amount of repair material used with actual material consumption data to obtain a comparison result; Whether the actual material consumption data meets expectations is determined based on the comparison result.

[0046] In some embodiments, after the repair is completed, the electronic device can obtain the actual consumption data of the repair material during the filling process, and compare the amount of repair material calculated based on the damaged volume with the actual material consumption data to determine whether the material consumption during the filling process meets expectations. If the difference between the actual material consumption data and the amount of repair material is within a preset range, it is considered that the material consumption during the repair process is in line with expectations, otherwise it is not in line with expectations. When the actual material consumption data is greater than the amount of repair material, and the difference between the two exceeds the preset range, it is necessary to take corresponding corrective measures, such as adjusting the parameters of the repair equipment, improving the operating process, replacing high-quality materials, etc., to reduce future material waste.

[0047] Through the above optional implementation methods, the material consumption in the repair process can be effectively monitored and managed to ensure the rationality and economy of material use.

[0048] In some embodiments, when a larger-sized voxelized model is used for voxelization processing, some voxel centers may exceed the model boundary, resulting in a path outside the model, that is, the zigzag path is outside the boundary of the target cable. Therefore, after determining the zigzag path of the target cable, the electronic device can further correct the zigzag path.

[0049] In an optional embodiment, the method further comprises: Inserting sampling points between adjacent path points of the zigzag path to obtain a new path point set; Re-voxelizing the damaged area point cloud using the new voxel size to obtain a new voxelized damaged point cloud; Determine k nearest neighbor voxels corresponding to each path point in the zigzag path according to the new path point set and the new voxelized damaged point cloud, where k is an integer greater than or equal to 1; The zigzag path is modified based on the k nearest neighbor voxels.

[0050] In some embodiments, since the original path point set of the zigzag path is generated based on a large voxel size in step S13, the path points in the original path point set are relatively sparse, so the electronic device can first insert additional sampling points between adjacent path points in the original path point set of the zigzag path to obtain a new path point set to increase the density and accuracy of the path. Next, the electronic device re-voxelizes the damaged area point cloud using a smaller voxel size (new voxel size) than the voxel size used in the voxelization process in step S13 according to the same embodiment as step S13, obtains a new voxelized damaged point cloud, and further locates and searches for the nearest neighbor small voxels based on the original path point set and the new voxelized damaged point cloud.

[0051] Specifically, the electronic device can determine the small voxel layer closest to the currently processed large voxel layer by comparing the height coordinates of the voxel layer in the height direction, and for each path point in the original path point set, in the point cloud after voxelization, the small voxel closest to the path point is determined by calculating the distance from the path point to the center of each small voxel, and the small voxel is used as the center to search for the k nearest neighbor small voxels within the specified radius. The electronic device can then use the k nearest neighbor small voxels to replace the zigzag path and the original path point set to achieve the correction of the zigzag path. It should be noted that the value of k is set according to actual needs and is not limited in this application.

[0052] In some embodiments, the electronic device may also use a B-spline interpolation method to smooth the modified zigzag path to generate a final smooth and continuous path, so that the zigzag path is more natural visually. Figure 5 Among them, B-spline interpolation can define the curve through control points (i.e., corrected path points) and node vectors, thereby generating a path that meets the geometric shape requirements and has good smoothness.

[0053] Through the above optional implementation, by inserting sampling points, re-voxelizing, searching for the nearest small voxel and correcting the zigzag path, the problem of the path exceeding the model boundary caused by large-size voxelization is effectively solved. In addition, the corrected path is smoothed by B-spline interpolation, which improves the visual naturalness and continuity of the path and ensures the accuracy and aesthetics of the cable path.

[0054] Reference Figure 2 As shown, the cable repair method based on hierarchical path planning proposed in the present application first obtains the original point cloud of the target cable including its damaged area, and pre-processes the original point cloud, such as filtering and cylindrical fitting, to extract the corresponding damaged area. In order to more effectively process the damaged area, the electronic device can calculate the direction of each slice in the point cloud of the damaged area, and fill the voxels according to the direction of each slice. At the same time, the surface of the damaged area is converted into a triangulated point cloud by triangulation technology, and the volume of all polyhedrons in the triangulated point cloud is calculated to obtain the total volume of the damaged area. Then, based on the results obtained by the above processing, a preliminary repair path is generated to guide the repair device to perform the repair operation along the running trajectory corresponding to the repair path. Furthermore, the electronic device can also correct and optimize the generated initial path to ensure that the repair path can accurately cover the damaged area and minimize material waste and repair time. Finally, the repair device can accurately transport the repair material to the damaged area along the corrected repair path and complete the final repair work.

[0055] Reference Figure 6, which is a functional module diagram of a cable repair device based on hierarchical path planning according to an embodiment of the present application.

[0056] In some embodiments, the cable repair device 60 based on hierarchical path planning may include a plurality of functional modules composed of computer program segments. The computer program of each program segment of the cable repair device 60 based on hierarchical path planning may be stored in a memory of an electronic device and executed by at least one processor to perform the cable repair based on hierarchical path planning (see Figure 1 Description).

[0057] In this embodiment, the cable repair device based on hierarchical path planning can be divided into multiple functional modules according to the functions it performs. The functional modules may include: an acquisition module 601, a first processing module 602, a second processing module 603, a third processing module 604, a repair module 605, a correction module 606 and a comparison module 607. The module referred to in this application refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0058] The acquisition module 601 is used to acquire the original point cloud of the target cable.

[0059] The first processing module 602 is used to pre-process the original point cloud to obtain a damaged area point cloud.

[0060] The second processing module 603 is used to perform voxelization processing on the damaged area point cloud, and perform internal voxel filling on the damaged area point cloud after the voxelization processing, so as to obtain a voxelized damaged point cloud.

[0061] The third processing module 604 is used to generate a zigzag path of the target cable according to the voxelized damage point cloud.

[0062] The repair module 605 is used to repair the target cable based on the zigzag path.

[0063] The correction module 606 is used to: insert sampling points between adjacent path points of the zigzag path to obtain a new path point set; re-voxelize the damaged area point cloud using the new voxel size to obtain a new voxelized damaged point cloud; determine the k nearest neighbor voxels corresponding to each path point in the zigzag path according to the new path point set and the new voxelized damaged point cloud, where k is an integer greater than or equal to 1; and correct the zigzag path based on the k nearest neighbor voxels.

[0064] The third processing module 604 is further specifically used to: layer the voxelized damaged point cloud along the height direction to obtain multiple slices; determine the center position of each voxel in the target slice, wherein the target slice is any one of the multiple slices; traverse each slice and generate the zigzag path according to the center position.

[0065] The repair module 605 is also specifically used to: determine the starting filling position of the zigzag path; calculate the damaged volume of the damaged area corresponding to the damaged area point cloud; determine the repair time and the amount of repair material for the target cable according to the damaged volume; and repair the damaged area according to the repair time and the amount of repair material when traversing the zigzag path layer by layer according to the starting filling position.

[0066] The comparison module 607 is used to compare the amount of repair material used with the actual material consumption data to obtain a comparison result; and determine whether the actual material consumption data meets expectations based on the comparison result.

[0067] The second processing module 603 is further specifically used to: divide the damaged area point cloud into multiple voxel grids according to a preset voxel side length; perform binarization processing on the target voxel grid to determine the occupied voxels and unoccupied voxels in the target voxel grid, wherein the target voxel grid is any one of the multiple voxel grids; determine the internal space of the damaged area point cloud according to the occupied voxels and the unoccupied voxels; and fill the internal space with the internal voxels to obtain the voxelized damaged point cloud.

[0068] The first processing module 602 is also specifically used to: calculate the average distance between the target original point and each original point in the local neighborhood, wherein the original point cloud includes multiple original points, and the target original point is any original point among the multiple original points; eliminate outlier original points in the original point cloud according to the average distance and a preset threshold to obtain a target point cloud; perform cylindrical surface fitting on the target point cloud to obtain the damaged area point cloud.

[0069] It should be understood that the various variations and specific embodiments of the cable repair method based on hierarchical path planning provided in the above-mentioned embodiments are also applicable to the cable repair device based on hierarchical path planning in the present embodiment. Through the above-mentioned detailed description of the cable repair method based on hierarchical path planning, those skilled in the art can clearly know the implementation method of the cable repair device based on hierarchical path planning in the present embodiment. For the sake of brevity of the specification, it will not be described in detail here.

[0070] See also Figure 7As shown, a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. In a preferred embodiment of the present application, the electronic device 7 includes a memory 71, at least one processor 72 and at least one communication bus 73. Among them, the electronic device can be integrated on a repair device for repairing a target cable. In some embodiments, the electronic device 7 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, a dedicated integrated circuit, a programmable gate array, a digital processor, and an embedded device.

[0071] Those skilled in the art should understand that Figure 3 The structure of the electronic device shown does not constitute a limitation of the embodiments of the present application, and can be either a bus structure or a star structure. The electronic device 7 can also include more or less other hardware or software than shown in the figure, or a different component arrangement.

[0072] In some embodiments, the electronic device 7 may also be independent of the repair device. The electronic device 7 may also include a user device, which includes but is not limited to any electronic product that can interact with a user through a keyboard, mouse, remote control, touch pad or voice control device, such as a personal computer, tablet computer, smart phone, digital camera, etc.

[0073] In the above embodiments provided in the present application, it should be understood that the disclosed methods, devices, computer-readable storage media, and electronic devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple components or modules can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or components or modules, which can be electrical, mechanical or other forms.

[0074] The components described as separate components may or may not be physically separated, and the components shown as components may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the components may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each component may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0076] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0077] It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should be aware that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0078] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] The above is a specific description of the preferred implementation of the present invention, but the invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A cable repair method based on hierarchical path planning, characterized in that: The method comprises: Obtain the original point cloud of the target cable; Preprocessing the original point cloud to obtain a damaged area point cloud; Performing voxel processing on the damaged area point cloud, and performing internal voxel filling on the damaged area point cloud after the voxel processing, to obtain a voxelized damaged point cloud; generating a zigzag path of the target cable according to the voxelized damage point cloud; The target cable is repaired based on the zigzag path.

2. The cable repair method based on hierarchical path planning according to claim 1, characterized in that: The method further comprises: Inserting sampling points between adjacent path points of the zigzag path to obtain a new path point set; Re-voxelizing the damaged area point cloud using the new voxel size to obtain a new voxelized damaged point cloud; Determine k nearest neighbor voxels corresponding to each path point in the zigzag path according to the new path point set and the new voxelized damaged point cloud, where k is an integer greater than or equal to 1; The zigzag path is modified based on the k nearest neighbor voxels.

3. The cable repair method based on hierarchical path planning according to claim 1, characterized in that: Generating the zigzag path of the target cable according to the voxelized damaged point cloud comprises: Layering the voxelized damaged point cloud along the height direction to obtain a plurality of slices; Determine the center position of each voxel in a target slice, wherein the target slice is any one of the multiple slices; Each slice is traversed and the zigzag path is generated according to the center position.

4. The cable repair method based on hierarchical path planning according to claim 1, characterized in that: The repairing of the target cable based on the zigzag path comprises: Determining a starting filling position of the zigzag path; Calculate the damaged volume of the damaged area corresponding to the damaged area point cloud; Determining the repair time and amount of repair materials for the target cable according to the damaged volume; When traversing the zigzag path layer by layer according to the starting filling position, the damaged area is repaired according to the repair time and the amount of the repair material.

5. The cable repair method based on hierarchical path planning according to claim 4, characterized in that: The method further comprises: Comparing the amount of repair material used with actual material consumption data to obtain a comparison result; Whether the actual material consumption data meets expectations is determined based on the comparison result.

6. The cable repair method based on hierarchical path planning according to claim 1, characterized in that: The step of performing internal voxel filling on the damaged area point cloud after the voxelization process to obtain a voxelized damaged point cloud comprises: Dividing the damaged area point cloud into a plurality of voxel grids according to a preset voxel side length; Binarizing a target voxel grid to determine occupied voxels and unoccupied voxels in the target voxel grid, wherein the target voxel grid is any voxel grid among the multiple voxel grids; Determine the inner space of the damaged area point cloud according to the occupied voxels and the unoccupied voxels; The internal space is filled with internal voxels to obtain the voxelized damaged point cloud.

7. The cable repair method based on hierarchical path planning according to claim 1, characterized in that: The preprocessing of the original point cloud to obtain the damaged area point cloud comprises: Calculating an average distance between a target original point and each original point in a local neighborhood, wherein the original point cloud includes a plurality of original points, and the target original point is any one of the plurality of original points; Eliminate outlier original points in the original point cloud according to the average distance and a preset threshold to obtain a target point cloud; The target point cloud is fitted with a cylindrical surface to obtain the damaged area point cloud.

8. A cable repair device based on hierarchical path planning, characterized in that: The device comprises: An acquisition module, used to acquire the original point cloud of the target cable; A first processing module, used for preprocessing the original point cloud to obtain a damaged area point cloud; A second processing module is used to voxelize the damaged area point cloud and fill the damaged area point cloud with internal voxels after the voxelization process to obtain a voxelized damaged point cloud; A third processing module, configured to generate a zigzag path of the target cable according to the voxelized damage point cloud; A repair module is used to repair the target cable based on the zigzag path.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the cable repair method based on hierarchical path planning described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cable repair method based on hierarchical path planning according to any one of claims 1 to 7 are implemented.

Images