Overhead distribution line construction management and control method based on space-time sequence characteristics

Abstract

The invention provides an overhead distribution line construction management and control method based on space-time sequence characteristics, and the method achieves the construction process and quality management of a distribution line. The method comprises the following steps: acquiring an image of an overhead distribution line construction area at a certain moment, and recording related information during image shooting; identifying a target device in the image by using an identification algorithm model, selecting and marking the target device through an identification frame, and recording a pixel coordinate of the target device; determining space coordinates of the target equipment based on the pixel coordinates of the target equipment and the related information during image shooting; based on a preset maximum allowable link distance of a tower and the space coordinates of the target equipment, generating a tower topology by adopting a nearest neighbor algorithm, and carrying out adjacent tower association on the target equipment except the tower to generate an overall topology; obtaining the overall topology of other moments; and determining the construction process and the construction quality of the distribution line by comparing and analyzing the overall topology at different moments and the target equipment on the overall topology at the same moment.

Description

Technical Field

[0001] The present application relates to the field of overhead distribution line construction process control, and specifically to a method, system, device and storage medium for overhead distribution line construction control based on spatiotemporal sequence characteristics. Background Art

[0002] With the rapid growth of the economy, the scale of power grid construction has continued to expand, and the construction of overhead distribution lines has become an important part of power system construction.

[0003] However, current progress control at construction sites relies primarily on manual reporting, resulting in insufficient understanding of the overall line status. This lack of process control can lead to construction quality issues, such as missed inspections or improper installation of key components. Failure to strictly verify that the number of installed insulators matches the design drawings during construction can result in missing insulators on some towers. When tower assembly and conductor installation are handled by different teams, the boundaries of responsibility for insulator installation become blurred, creating "no man's land" areas. Furthermore, deviations between actual line construction and planned routes are common. Furthermore, this lack of process control can lead to construction delays and missed completion schedules, particularly in regions like Northeast China, where the annual construction period is impacted by inclement weather such as rain, snow, and ice, further complicating distribution network construction. At the end of each year, the overall completion rate is often below average, necessitating an urgent need to accelerate construction within the appropriate construction period to ensure on-time completion.

[0004] In view of this, how to improve construction quality and construction period control efficiency and reduce labor costs is a problem that needs to be solved at present. Summary of the Invention

[0005] The embodiments of the present application provide a method for controlling the construction of overhead distribution lines based on spatiotemporal sequence characteristics, which enables accurate evaluation and efficient management of the construction quality and progress of overhead distribution lines.

[0006] To achieve the above objectives, this application adopts the following technical solutions: In a first aspect, the present application provides a method for controlling the construction of overhead distribution lines based on spatiotemporal sequence characteristics, the method comprising: S101. A drone collects an image of an overhead distribution line construction area at a certain moment, and records the drone's flight altitude, the drone's shooting position, and the pixel coordinates of the image center point corresponding to the image being captured. The number of images is at least one. S102. Identify target devices in the image using a recognition algorithm model, select and mark the target devices with an identification frame, and record the pixel coordinates of the target devices. The target devices include poles, insulators, and conductors. The pixel coordinates of the target devices are the pixel coordinates of the center point of the identification frame. S103, determining the spatial coordinates of the target device based on the pixel coordinates of the target device, the flight altitude of the drone, the shooting position of the drone, and the pixel coordinates of the center point of the image; S104. Based on the preset maximum allowable link distance of the tower and the spatial coordinates of the target device, a nearest neighbor algorithm is used to generate a tower topology, and for target devices other than the tower, adjacent towers are associated to generate an overall topology. S105. Repeat steps S101-S104 until the overall topology of the overhead distribution line construction area at other times is obtained; S106. Determine the construction progress and construction quality of the overhead distribution line by comparing and analyzing the overall topology at different times and the target devices on the overall topology at the same time.

[0007] A possible design scheme, the first aspect of the method also includes adopting the YOLO V5 framework in the recognition algorithm model, and combining the CBAM attention mechanism and the Mosaic-9 data enhancement strategy.

[0008] In one possible design solution, the method of the first aspect further includes determining the spatial coordinates of the target device based on the pixel coordinates of the target device, the flight altitude of the drone, the shooting position of the drone, and the pixel coordinates of the center point of the image, including: The pixel resolution is obtained based on the pixel size of the camera fixed on the drone, the camera imaging focal length of the camera, and the flight altitude of the drone, wherein the pixel size of the camera and the camera imaging focal length of the camera are obtained from the hardware specifications of the camera; Based on the pixel coordinates of the target device and the pixel coordinates of the center point of the image, the pixel offset of the target device is obtained; Based on the pixel offset and pixel resolution of the target device, the spatial distance between the target device and the center point of the image is obtained; The spatial coordinates of the target device are obtained based on the spatial distance and the spatial coordinates of the image center point, where the spatial coordinates of the image center point are the shooting position of the drone.

[0009] In one possible design solution, the method of the first aspect further includes, after step S103 and before step S104, the following steps: Based on the spatial coordinates of the target devices, spatial coordinate sets of different types of target devices are constructed respectively, wherein the spatial coordinate sets of different types of target devices include the spatial coordinate set of the tower, the spatial coordinate set of the insulator, and the spatial coordinate set of the conductor; For different types of target devices, the parameters of the DBSCAN clustering algorithm are preset respectively, wherein the parameters of the DBSCAN clustering algorithm include the neighborhood radius and the minimum number of points; Based on the preset parameters of the DBSCAN clustering algorithm, the DBSCAN clustering algorithm is performed on the spatial coordinate sets of different types of target devices to obtain the spatial coordinates of the target devices after deduplication.

[0010] A possible design solution, the method of the first aspect further includes generating a tower topology using a nearest neighbor algorithm based on a preset maximum allowable tower link distance and the spatial coordinates of the target device, and associating neighboring towers with other target devices other than the tower to generate an overall topology, including: Based on the spatial coordinates of the target equipment, a spatial coordinate set of the tower is constructed; Select any tower as the initial tower, use the nearest neighbor algorithm to calculate the Euclidean distance between the initial tower and the spatial coordinates of other towers, and select the tower with the smallest Euclidean distance as the second tower, where the Euclidean distance between the second tower and the initial tower meets the preset maximum allowable tower connection distance; For other towers, continue to use the nearest neighbor algorithm until all towers are connected to generate a tower topology; For other target devices except towers, the adjacent towers are associated to generate the overall topology.

[0011] In one possible design solution, the method of the first aspect further includes, after step S104 and before step S105, further including: The overall topology is manually reviewed. If the error between the pole tower distance in the overall topology and the pole tower distance in the overhead distribution line construction design plan is greater than the preset value, an early warning is triggered.

[0012] A possible design solution, the method of the first aspect further includes determining the construction progress and quality of the overhead distribution line by comparing and analyzing the overall topology at different times and the target devices in the overall topology at the same time, including: Analyze the overall topology at different times. If the spatial coordinate distance between towers at different times is less than 5m, they are considered to be the same tower. When there is an isolated point on a tower, if the isolated point appears in the overall topology at a later time, it is considered to be a newly added tower. If the isolated point appears in the overall topology at an earlier time, manual intervention is required to determine whether it is a demolished tower.

[0013] In a second aspect, the present application provides an overhead distribution line construction management and control system based on spatiotemporal sequence characteristics, the system comprising: a drone, a ground remote control terminal and a computer terminal, wherein: The drone collects an image of the overhead distribution line construction area at a certain moment, and records the drone's flight altitude, the drone's shooting position, and the pixel coordinates of the image center point corresponding to the image capture, wherein the number of images is at least one; The ground remote control terminal is used to transmit the drone's flight altitude, the drone's shooting position, and the pixel coordinates of the image center point when the drone captured the image and recorded the image to the computer terminal; The computer terminal includes an identification module, a processing module and an analysis module, wherein: The recognition module is used to identify the target device in the image using the recognition algorithm model, select and mark the target device with an identification box, and record the pixel coordinates of the target device. The target device includes a tower, insulator, and conductor. The pixel coordinates of the target device are the pixel coordinates of the center point of the identification box. The processing module is used to determine the spatial coordinates of the target device based on the pixel coordinates of the target device, the flight altitude of the drone, the shooting position of the drone, and the pixel coordinates of the center point of the image. It is also used to generate the tower topology using the nearest neighbor algorithm based on the preset maximum allowable tower connection distance and the spatial coordinates of the target device, and to associate neighboring towers with other target devices other than the tower to generate the overall topology. It is also used to obtain the overall topology of the overhead distribution line construction area at other times. The analysis module is used to determine the construction progress and construction quality of the overhead distribution line by analyzing the overall topology at different times and the target devices on the overall topology at the same time.

[0014] In a third aspect, a device for controlling the construction of an overhead distribution line based on spatiotemporal sequence characteristics is provided. The device for controlling the construction of an overhead distribution line based on spatiotemporal sequence characteristics includes a module for executing the method of the first aspect.

[0015] In one possible design, the apparatus for controlling overhead distribution line construction based on spatiotemporal sequence characteristics of the third aspect may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used to enable the apparatus for controlling overhead distribution line construction based on spatiotemporal sequence characteristics of the third aspect to communicate with other devices.

[0016] In one possible design, the apparatus for controlling overhead distribution line construction based on spatiotemporal sequence characteristics of the third aspect may further include a memory. The memory may be integrated with the processor or provided separately. The memory may be used to store instructions related to the method of the first aspect.

[0017] In a fourth aspect, a device for controlling the construction of an overhead distribution line based on spatiotemporal sequence characteristics is provided. The device comprises a processor coupled to a memory, configured to execute instructions stored in the memory to cause the device to perform the method of the first aspect.

[0018] In one possible design, the apparatus for controlling construction of an overhead distribution line based on spatiotemporal sequence characteristics in the fourth aspect may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used to enable the apparatus for controlling construction of an overhead distribution line based on spatiotemporal sequence characteristics in the fourth aspect to communicate with other devices.

[0019] In the fifth aspect, an overhead distribution line construction control device based on time-space sequence characteristics is provided, comprising: a processor and a memory; the memory is used to store instructions, and when the processor executes the instructions, the overhead distribution line construction control device based on time-space sequence characteristics executes the method of the first aspect.

[0020] In one possible design, the fifth aspect of the apparatus for controlling overhead distribution line construction based on spatiotemporal sequence characteristics may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the fifth aspect of the apparatus for controlling overhead distribution line construction based on spatiotemporal sequence characteristics to communicate with other devices.

[0021] In a sixth aspect, a computer-readable storage medium is provided, which includes a computer program or instruction stored therein. When the computer program or instruction is executed, the overhead distribution line construction control method based on spatiotemporal sequence characteristics of the first aspect is executed.

[0022] In the embodiment of the present application, by integrating high-precision drone positioning data with drone imaging principles and combining target detection algorithms, key components such as poles, crossarms, and insulators at the construction site are accurately identified. Through the spatial solution technology of the target detection identification frame, the recognition results in the image coordinate system are mapped to the real three-dimensional space, and a precise association between pole tower components and pole towers and geographic information is established. At the same time, based on the pole tower coordinate calculation capability of image solution, the line topology offset is monitored in real time, providing an automated method for overhead distribution line data verification, reducing manual survey errors and time costs. Finally, the construction node status is matched based on the spatiotemporal feature sequence to achieve construction progress and quality control.

[0023] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1A flowchart of a method for controlling the construction of overhead distribution lines based on spatiotemporal sequence characteristics provided in an embodiment of the present application; Figure 2 Schematic diagram of the identification results of the tower and its ancillary facilities provided in the embodiment of the present application; Figure 3 A reference diagram illustrating the coordinate analysis principle of drone imaging provided in the embodiments of this application; Figure 4 Reference images for drone and gimbal imaging correction provided in the embodiments of the present application; Figure 5 This is an example diagram of different stages of tower and line construction provided in the embodiment of this application; Figure 6 A multi-phase topology diagram of the line during the specific construction period provided in the embodiment of this application; Figure 7 Images are collected at typical moments with obvious time characteristics during the specific construction period provided in the embodiments of this application; Figure 8 A schematic diagram of the system structure of an overhead distribution line construction management and control system based on spatiotemporal sequence characteristics provided in an embodiment of the present application; Figure 9 Schematic diagram of the structure of the overhead distribution line construction control device based on spatiotemporal sequence characteristics provided in the embodiment of the present application Figure 1 ; Figure 10 Schematic diagram of the structure of the overhead distribution line construction control device based on spatiotemporal sequence characteristics provided in the embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application. At the same time, in the description of the embodiments of the present application, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0027] Figure 1 A flowchart of a method for controlling the construction of overhead distribution lines based on spatiotemporal sequence characteristics provided in an embodiment of the present application.

[0028] The process of the overhead distribution line construction control method based on spatiotemporal sequence characteristics is as follows: In step S101, a drone collects an image of an overhead distribution line construction area at a certain moment, and records the drone's flight altitude, the drone's shooting position, and the pixel coordinates of the image center point corresponding to the image shooting, wherein the number of images is at least one.

[0029] The drone is equipped with a three-axis stabilized gimbal with an angular jitter tolerance of less than ±0.01°. It is also equipped with a high-precision positioning module (horizontal positioning accuracy of ±10mm), enabling precise control of the hovering altitude error to less than 0.5m. The drone's longitude and latitude are based on the WGS84 coordinate system, and its altitude is based on the EGM96 elevation datum. The camera on the drone is stabilized by the gimbal and should have a resolution greater than 20 megapixels, a 1 / 1.7" CMOS sensor, an optical zoom range of 31.7-556.2mm (35mm equivalent focal length), and support for 10x digital zoom. The aperture range is f / 2.8-f / 11, and the shutter speed is adjustable from 1 / 8000s to 30s.

[0030] This application uses a drone to take a bird's-eye view of the construction site in a hovering position. During the shooting process, the drone remains in a horizontal position. To ensure clear imaging, the imaging height does not exceed 50m.

[0031] In addition, for each image taken, the corresponding drone flight altitude, drone shooting position and pixel coordinates of the image center point are recorded. The pixel coordinates of the image center point can be understood as follows: assuming the width of the image is W and the height is H, the pixel coordinates of the image center point are .

[0032] It should also be noted that the drone's attitude information and gimbal angle can also be recorded. At the same time, EXIF records the imaging optical zoom ratio, digital zoom ratio, imaging height and other related parameters, and performs other data processing, which is not restricted here.

[0033] Step S102: Use the recognition algorithm model to identify the target device in the image, select and mark the target device with an identification box, and record the pixel coordinates of the target device. The target device includes a pole tower, insulator, and conductor, and the pixel coordinates of the target device are the pixel coordinates of the center point of the identification box.

[0034] It should be noted that the center point of the identification box is the middle position of the box. The center point pixel coordinates can be obtained by calculating the average of the pixel coordinates of the upper left corner and the lower right corner of the identification box, and then the pixel coordinates of the target device can be obtained.

[0035] Since the construction progress survey focuses on the installation status of each pole tower and its ancillary facilities, and the drone's high flight altitude makes it impossible to identify more detailed information, there is no need to carefully confirm the project quality acceptance for project progress monitoring, and there is no need to pay attention to equipment defects and construction processes. Therefore, the recognition algorithm only needs to identify key components, such as pole towers, conductors, insulators, transformers, crossarms and other equipment and materials. At the same time, the ground status, such as excavated but not backfilled pit foundation, is also identified. The details are as follows: The recognition algorithm model uses the YOLO V5 framework and combines the CBAM attention mechanism and Mosaic-9 data enhancement strategy to identify the target device in the image. It selects and marks the target device with an identification box and records the pixel coordinates of the target device.

[0036] Optionally, for pole towers, the features of the pole tower connections can be extracted based on the fusion edge detection operator and the gradient direction histogram to effectively distinguish the spatial positions of adjacent pole towers.

[0037] Optionally, for insulators, a circle detection algorithm (Hough Circles) can be cross-validated with deep learning results, and cluster analysis of circle center coordinates can be performed to eliminate false detections caused by pan / tilt shake.

[0038] Optionally, for the conductor, the sag characteristics of the conductor can be established based on Hough transform straight line detection and the flight altitude of the drone.

[0039] The target equipment may also be a transformer, a cross arm, an excavation pit foundation, etc., depending on the actual situation and is not limited here.

[0040] For example, Figure 2 As shown in the figure, different types of feature enhancement strategies are used to achieve the recognition results of towers and their ancillary facilities (such as crossarms, insulators, conductors, and excavation without backfill).

[0041] Step S103 , determining the spatial coordinates of the target device based on the pixel coordinates of the target device, the flight altitude of the drone, the shooting position of the drone, and the pixel coordinates of the center point of the image.

[0042] Step S103 specifically includes the following contents, which can be combined with Figure 3 Figure (a) and Figure 3 Understand Figure (b) in .

[0043] Step 1: Based on the pixel size of the fixed camera on the drone , the camera's imaging focal length and drone flight altitude , through the formula , get the pixel resolution (also known as the spatial size corresponding to each pixel) .

[0044] The camera's pixel size and focal length are determined by the camera's hardware specifications. If the camera is equipped with interchangeable lenses, the focal length will vary depending on the type of lens used. The pixel size of a camera refers to the physical width and height of a unit pixel on the sensor, and is generally measured in microns ( ), the smaller the pixel size, the higher the image resolution, the wider the field of view, and the smaller the target can be detected.

[0045] Step 2: Based on the pixel coordinates of the target device and the pixel coordinates of the image center point , get the pixel offset of the target device .

[0046] in, is the horizontal pixel offset, is the vertical pixel offset.

[0047] Step 3: Pixel offset based on target device and pixel resolution , get the spatial distance between the target device and the center point of the image ; Step 4: Based on spatial distance and the spatial coordinates of the image center point , get the spatial coordinates of the target device , where the spatial coordinates of the center point of the image are the shooting position of the drone.

[0048] It's important to note that the above assumes the drone is filming from a vertical (90-degree) angle, with the camera lens pointing directly downward. This is commonly referred to as looking down or vertically. If the drone isn't filming from a vertical (90-degree) angle, image correction is required based on the recorded drone attitude information and gimbal angle. This is briefly explained below.

[0049] The drone coordinate system moves with the movement of the drone, e.g. Figure 4 As shown, the center of mass of the drone is the origin , ahead of Axis, rightward Axis, vertically downward axis, satisfying the right-hand rule, if the target is in front of the drone, then , on the east side of the drone , below the drone ; like Figure 4 As shown, in the gimbal coordinate system, the center of mass of the gimbal is the origin , the camera optical axis faces forward Axis, camera right is axis, below the camera is axis According to the attitude angle φ of the UAV, , ψ, we can get the transfer matrix from the UAV coordinate system to the earth coordinate system

[0050]

[0051] Similarly, according to the attitude angle of the gimbal, the transfer matrix from the gimbal coordinate system to the drone coordinate system can be obtained: , then the transfer matrix from the camera coordinate system to the ground coordinate system is: .

[0052] Optionally, after step S103 and before step S104, the method further includes: Based on the spatial coordinates of the target devices, spatial coordinate sets of different types of target devices are constructed respectively, wherein the spatial coordinate sets of different types of target devices include the spatial coordinate set of the tower, the spatial coordinate set of the insulator, and the spatial coordinate set of the conductor; For different types of target devices, the parameters of the DBSCAN clustering algorithm are preset respectively, wherein the parameters of the DBSCAN clustering algorithm include the neighborhood radius and the minimum number of points; Based on the preset parameters of the DBSCAN clustering algorithm, the DBSCAN clustering algorithm is performed on the spatial coordinate sets of different types of target devices to obtain the spatial coordinates of the target devices after deduplication.

[0053] Understandably, the same tower may appear in multiple images, resulting in duplicated spatial coordinates of the tower and its associated equipment (such as crossarms, insulators, conductors, and excavation pits). Therefore, a clustering algorithm, specifically the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, is needed to deduplicate these coordinates.

[0054] For example, for towers, the parameters of the DBSCAN clustering algorithm are set, where the neighborhood radius (ε) is 5 meters and the minimum number of points (MinPts) is set. That is, when the distance between the spatial coordinates of two towers is less than 5 meters, they are considered to be the same tower. Because some towers may only appear in a single image and have no overlapping areas with towers in other images, they cannot be directly clustered, so MinPts is set to 1. In other words, each spatial coordinate point will at least be clustered as a separate cluster.

[0055] The specific clustering steps are: (1) Start from any unvisited tower spatial coordinate point.

[0056] (2) With the current spatial coordinate point as the center, search for all other spatial coordinate points within its neighborhood. The neighborhood range is determined by the set 5-meter radius.

[0057] (3) If other tower spatial coordinate points are found within the neighborhood radius, these points are added to the same cluster and the search for their neighborhoods continues starting from these newly added points.

[0058] (4) The search process continues to expand until no more points that meet the neighborhood conditions can be found.

[0059] (5) When the search for a cluster is completed, the average coordinates of all points in the cluster are calculated, and they are considered to represent the same tower.

[0060] (6) Then, continue to look for the next unvisited point and repeat the above process until all points have been visited.

[0061] (7) Finally, the points within a cluster represent the same tower.

[0062] For example, suppose there are two images, each with several tower coordinates and auxiliary facility coordinates parsed. The tower coordinates in Image 1 are (10, 15) and (50, 60), while the tower coordinates in Image 2 are (10.1, 15.1) and (51, 61). Given a neighborhood radius of 5 meters, the distance between (10, 15) and (10.1, 15.1) is less than 5 meters, so they are considered the same tower. Similarly, (50, 60) and (51, 61) are also considered the same tower. Ultimately, the clustering results for the two towers are: the first tower has coordinates (10.05, 15.05) (average coordinates), and the second tower has coordinates (50.5, 60.5) (average coordinates).

[0063] Similar to poles and towers, equipment such as crossarms, insulators, conductors, and excavated foundations also appear repeatedly in the image. We use the same deduplication method as for poles and towers to cluster and remove duplicates from the identification boxes of these equipment. This will not be detailed here.

[0064] Step S104: Based on the preset maximum allowable link distance of the tower and the spatial coordinates of the target device, a nearest neighbor algorithm is used to generate a tower topology, and for target devices other than the tower, adjacent towers are associated to generate an overall topology.

[0065] The specific steps are: (1) Based on the spatial coordinates of the target equipment, construct the spatial coordinate set of the tower.

[0066] (2) Select any tower as the initial tower, use the nearest neighbor algorithm to calculate the Euclidean distance between the initial tower and the spatial coordinates of other towers, and select the tower with the smallest Euclidean distance as the second tower, where the Euclidean distance between the second tower and the initial tower meets the preset maximum allowable connection distance of the towers.

[0067] Among them, during the connection process, when the Euclidean distances between two towers are close, the point with a smaller angular deviation (<30°) from the current line segment is preferred to avoid sudden changes in the path.

[0068] (3) For the second tower, the nearest neighbor algorithm is repeatedly used to calculate the Euclidean distances between the spatial coordinates of the second tower and other towers, and the tower with the smallest Euclidean distance is selected as the third tower, where the Euclidean distance between the third tower and the second tower meets the preset maximum allowable link distance of the towers.

[0069] (4) For other towers, continue to use the nearest neighbor algorithm until all towers are connected and the tower topology is generated.

[0070] (5) For other target devices except the towers, the adjacent towers are associated to generate the overall topology.

[0071] After the tower topology is generated, if the identification frame contains accessories such as crossarms, insulators, and conductors, the adjacent towers are associated. Specifically, for the association between the conductor identification frame and the tower, when the midpoint of the conductor identification frame is at the midpoint of the line connecting the two towers, the conductor is associated with the two towers.

[0072] It's also important to note that setting a maximum link distance can effectively prevent the generation of overly long, discontinuous, or unreasonable line connections in actual applications. It also helps improve the accuracy and reliability of the topology and avoids incorrect connections caused by calculation errors or data anomalies. For example, if two towers are incorrectly calculated to be several hundred meters apart due to certain factors (such as sensor errors or inconsistent data), the maximum allowable link distance will prevent this misconnection and ensure that the generated topology is more realistic.

[0073] Optionally, after step S104 and before step S105, the method further includes: The overall topology is manually reviewed. If the error between the pole tower distance in the overall topology and the pole tower distance in the overhead distribution line construction design plan is greater than the preset value, an early warning is triggered.

[0074] Specifically, during a manual review of the entire tower topology, the actual generated tower distances (i.e., the actual distances between adjacent towers in the entire topology) are compared with the distances planned in the original design. If the difference between these distances exceeds a pre-set threshold (error limit), the system triggers an alert to prevent deviations from the construction route or other problems.

[0075] Step S105 , repeating steps S101 - S104 until the overall topology of the overhead distribution line construction area at other times is obtained.

[0076] Data collection and analysis are carried out according to different construction period points.

[0077] Step S106 , determining the construction progress and construction quality of the overhead distribution line by analyzing the overall topology at different times and the target devices on the overall topology at the same time.

[0078] The overall topology at different times is analyzed. If the spatial coordinate distance between towers at different times is less than 5m, they are determined to be the same tower. If there are isolated points on the towers, if the isolated points appear in the overall topology at a later time, they are considered to be newly added towers. If the isolated points appear in the overall topology at an earlier time, manual intervention is required to determine whether the towers have been demolished.

[0079] It can be understood that after carrying out multi-phase project progress surveys, the obtained multi-phase topological data (topological data at multiple different times) are spatially matched and analyzed to judge the construction progress; at the same time, the target equipment on the overall topology at the same time, such as, the characteristics of all towers in the area at the same time, are compared to determine whether all towers in the area have completed the current stage characteristics and whether there is any equipment missing, and then judge the construction quality.

[0080] For example, taking the construction of a tower line as an example, the current state of the tower construction can be determined based on the identification frame features recognized in the collected image, such as Figure 5 shown.

[0081] Features of the pre-construction stage: The captured images do not contain identification frames for towers, crossarms, insulators, conductors, and pit foundations; Characteristics of the pole erection stage: The captured image contains identification frames for the pole tower and pit foundation, but no identification frames for crossarms, insulators, or conductors. Features of the auxiliary equipment installation stage: Based on the features of the pole erection stage, the captured image has additional identification frames for crossarms, insulators, etc., but no identification frames for conductors. Features of the wiring stage: Based on the features of the ancillary facilities installation stage, a conductor identification frame is added; for substation construction, the construction process of pole-mounted equipment such as transformers, lightning arresters, and primary and secondary fusion switches can also be expanded.

[0082] When construction is complete, the tower is constructed, the pit foundation is backfilled, and ancillary facilities and conductors are installed. Using these phase characteristics, a construction progress chronological comparison is performed. If there is an estimated construction period, it can be compared with the construction schedule to determine progress deviations. The schedule can then be adjusted while the construction period is estimated.

[0083] Optionally, the construction process model built based on spatiotemporal sequence characteristics can also automatically generate structured construction logs, realize full-cycle digital archiving, and provide traceable historical data support for subsequent operations and maintenance by dynamically adjusting the progress baseline.

[0084] In summary, in the embodiments of the present application, by integrating high-precision drone positioning data with drone imaging principles and combining target detection algorithms, key components such as poles, crossarms, and insulators at the construction site are accurately identified. Through the spatial solution technology of the target detection identification frame, the recognition results in the image coordinate system are mapped to the real three-dimensional space, and an accurate association between the pole tower components and the pole tower and geographic information is established. At the same time, based on the pole tower coordinate calculation capability of image solution, the line topology offset is monitored in real time, providing an automated method for overhead distribution line data verification, reducing manual survey errors and time costs. Finally, the construction node status is matched based on the spatiotemporal feature sequence to achieve construction progress and quality control.

[0085] Combination of the above Figure 1-Figure 5 The construction control method of overhead distribution lines based on spatiotemporal sequence characteristics provided by the embodiments of the present application is described in detail, and specific application examples are given below.

[0086] At the State Grid UHV AC test base, field verification and testing of the algorithm will be carried out during the construction process of the overhead distribution line. The construction period is from October 23, 2024 to November 26, 2024. During the construction period, field testing and verification of the technology of the present invention will be carried out from time to time. Construction site survey data collection, tower and ancillary equipment identification, identification frame coordinate analysis, tower topology generation, spatial time series comparison and construction process time series analysis will be carried out. The multi-phase topology diagram of the line is as follows: Figure 6 As shown, the images collected at typical moments with obvious time characteristics are as follows Figure 7 shown.

[0087] in, Figure 7 Figure ① shows the line before construction, in which the pit foundation, towers, and their ancillary facilities and other accessories are not identified.

[0088] Figure 7Figure ② was collected on October 28, 2024. The image was used to identify pole tower equipment and structural components. The image shows features such as foundation excavation, pole towers, and crossarms. Therefore, it is judged that at the time of collection, the target line tower was in the stage of erecting the pole and installing the crossarm. The next step should be to install insulators and erect conductors.

[0089] Figure 7 Figure ③ was collected on November 5, 2024. The image was used to identify pole tower equipment and structural parts. The image shows features such as foundation excavation, pole towers and crossarms. At the same time, new types of insulators have appeared. Therefore, it is judged that the time of collection was the installation stage of pole-mounted auxiliary facilities such as insulators. The next step should be to carry out line assumptions and foundation backfilling.

[0090] Figure 7 Figure ④ was collected on November 13, 2024. The image was used to identify pole tower equipment and structural parts. The image shows features such as foundation excavation, pole towers, crossarms, insulators, and a new feature type, conductors, has also appeared. Therefore, it is judged that the collection time was the line stringing stage. The next step should be to complete the line stringing and other tasks, as well as the backfilling of the pit foundation.

[0091] Figure 7 The target equipment characteristics of each tower at different construction stages are shown in Table 1.

[0092]

[0093] Table 1 Target equipment characteristics at different construction stages Through the above analysis, we can clearly understand the construction progress of overhead distribution lines and realize the control of the construction process of overhead distribution lines.

[0094] Combination of the above Figure 1-Figure 7 The construction control method and application of overhead distribution line based on spatiotemporal sequence characteristics provided by the embodiment of the present application are described in detail. Figure 8 A detailed description is given of the overhead distribution line construction management and control system based on spatiotemporal sequence characteristics provided in the embodiments of the present application.

[0095] The system specifically includes: UAV, ground remote control terminal and computer terminal, among which, The drone collects images of the overhead distribution line construction area at a certain moment and records the drone's flight altitude, the drone's shooting position, and the pixel coordinates of the image center point corresponding to the image shooting, wherein the number of images is at least one.

[0096] The ground remote control terminal is used to transmit the images collected by the drone and the corresponding drone flight altitude when the recorded images were taken, the drone's shooting position and the pixel coordinates of the image center point to the computer terminal.

[0097] The ground remote control terminal may be transmitted to the computer terminal via wireless transmission or via an SD card, or other possible methods, which are not limited here.

[0098] The computer terminal includes an identification module, a processing module and an analysis module, wherein: The recognition module is used to identify the target device in the image using the recognition algorithm model, select and mark the target device by an identification box, and record the pixel coordinates of the target device. The target device includes a pole tower, insulator, and conductor. The pixel coordinates of the target device are the pixel coordinates of the center point of the identification box.

[0099] The processing module is used to determine the spatial coordinates of the target device based on the pixel coordinates of the target device, the flight altitude of the drone, the shooting position of the drone, and the pixel coordinates of the center point of the image; it is also used to generate the tower topology based on the preset maximum allowable link distance of the tower and the spatial coordinates of the target device using the nearest neighbor algorithm, and to associate the neighboring towers of other target devices other than the tower to generate the overall topology; it is also used to obtain the overall topology of the overhead distribution line construction area at other times.

[0100] The analysis module is used to determine the construction progress and construction quality of the overhead distribution line by analyzing the overall topology at different times and the target devices on the overall topology at the same time.

[0101] In addition, for the above-mentioned specific implementation of the system, since it is basically similar to the method implementation, the description is relatively simple, and the relevant parts can be referred to the partial description of the method implementation. Moreover, it should be noted that in each module of the system of the present application, the components therein are logically divided according to the functions to be implemented, but the present application is not limited thereto, and the components can be re-divided or combined as needed.

[0102] The above describes the overhead distribution line construction control method and system based on spatiotemporal sequence characteristics provided by the embodiment of the present application. Figure 9-10 A detailed description is given of an overhead distribution line construction control device based on spatiotemporal sequence characteristics for executing the embodiments of the present application.

[0103] Figure 9 This is a schematic diagram of the structure of the overhead distribution line construction control device based on time-space sequence characteristics provided by the embodiment of the present application. Figure 1 For example, Figure 9 As shown, the overhead distribution line construction control device 900 based on spatiotemporal sequence characteristics includes: a transceiver module 901 and a processing module 902. For ease of explanation, Figure 9 Only the main components of the overhead distribution line construction control device based on spatiotemporal sequence characteristics are shown.

[0104] Among them, the transceiver module 901 is used to perform the transceiver function of the above-mentioned overhead distribution line construction control method based on time-space sequence characteristics, and the processing module 902 is used to perform other functions of the above-mentioned overhead distribution line construction control method based on time-space sequence characteristics except the transceiver function.

[0105] Optionally, the transceiver module 901 may include a sending module ( Figure 9 Not shown) and the receiving module ( Figure 9 (not shown). The sending module is used to implement the sending function of the overhead distribution line construction control device 900 based on spatiotemporal sequence characteristics, and the receiving module is used to implement the receiving function of the overhead distribution line construction control device 900 based on spatiotemporal sequence characteristics.

[0106] Optionally, the overhead distribution line construction control device 900 based on spatiotemporal sequence characteristics may further include a storage module ( Figure 9 (not shown in the figure), the storage module stores a program or instruction. When the processing module 902 executes the program or instruction, the overhead distribution line construction control device 900 based on spatiotemporal sequence characteristics can execute the overhead distribution line construction control method based on spatiotemporal sequence characteristics in the embodiment of the present application.

[0107] The following combination Figure 10 Each component of the overhead distribution line construction control device 1000 based on spatiotemporal sequence characteristics is specifically introduced: The processor 1001 is the control center of the overhead distribution line construction control device 1000 based on spatiotemporal sequence characteristics, and can be a single processor or a collective term for multiple processing elements. For example, the processor 1001 can be one or more central processing units (CPUs), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, such as one or more microprocessors (digital signal processors, DSPs) or one or more field programmable gate arrays (FPGAs).

[0108] Optionally, the processor 1001 can execute various functions of the overhead distribution line construction control device 1000 based on time-space sequence characteristics by running or executing a software program stored in the memory 1002, and calling data stored in the memory 1002, such as executing the overhead distribution line construction control method based on time-space sequence characteristics in the embodiment of the present application.

[0109] In a specific implementation, as an embodiment, the processor 1001 may include one or more CPUs, such as Figure 10 CPU0 and CPU1 are shown in FIG.

[0110] In a specific implementation, as an embodiment, the overhead distribution line construction control device 1000 based on spatiotemporal sequence characteristics may also include multiple processors, such as Figure 10 The processor 1001 and processor 1004 shown in FIG. Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions). The memory 1002 is used to store the software program that executes the solution of the present application, and the execution is controlled by the processor 1001. The specific implementation method can refer to the above-mentioned method embodiment and will not be repeated here.

[0111] Optionally, the memory 1002 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 1002 may be integrated with the processor 1001 or exist independently and access the processor 1001 through the interface circuit ( Figure 10 (not shown) is coupled to the processor 1001, which is not specifically limited in this embodiment of the present application.

[0112] The transceiver 1003 is used for communicating with other communication devices. For example, the overhead distribution line construction control device 1000 based on spatiotemporal sequence characteristics is a first device, and the transceiver 1003 can be used for communicating with a second device or a third device.

[0113] Optionally, the transceiver 1003 may include a receiver and a transmitter ( Figure 10 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0114] Optionally, the transceiver 1003 may be integrated with the processor 1001 or may exist independently and communicate with the overhead distribution line construction control device 1000 based on spatiotemporal sequence characteristics through an interface circuit ( Figure 10 (not shown) is coupled to the processor 1001, which is not specifically limited in this embodiment of the present application.

[0115] It is understandable that Figure 10 The structure of the overhead distribution line construction control device 1000 based on time-space sequence characteristics shown in the figure does not constitute a limitation of the overhead distribution line construction control device based on time-space sequence characteristics. The overhead distribution line construction control device based on time-space sequence characteristics may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0116] In addition, the technical effects of the overhead distribution line construction control device 1000 based on spatiotemporal sequence characteristics can refer to the technical effects of the method described in the above method embodiment, and will not be repeated here.

[0117] It should be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), but may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0118] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0119] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

Claims

1. A method for controlling the construction of overhead distribution lines based on spatiotemporal sequence characteristics, characterized in that: The method comprises: S101. A drone collects an image of an overhead distribution line construction area at a certain moment, and records the drone's flight altitude, the drone's shooting position, and the pixel coordinates of the image's center point corresponding to the image being captured, wherein the number of the images is at least one; S102. Identify target devices in the image using a recognition algorithm model, select and mark the target devices with an identification frame, and record pixel coordinates of the target devices, wherein the target devices include poles, insulators, and conductors, and the pixel coordinates of the target devices are the pixel coordinates of the center point of the identification frame; S103, determining the spatial coordinates of the target device based on the pixel coordinates of the target device, the flight altitude of the drone, the shooting position of the drone, and the pixel coordinates of the center point of the image; S104, based on the preset maximum allowable link distance of the tower and the spatial coordinates of the target device, using the nearest neighbor algorithm to generate a tower topology, and for other target devices other than the tower, performing association with adjacent towers to generate an overall topology; S105. Repeat steps S101-S104 until the overall topology of the overhead distribution line construction area at other times is obtained; S106 , determining the construction progress and construction quality of the overhead distribution line by comparing and analyzing the overall topology at different times and the target devices on the overall topology at the same time.

2. The method for controlling the construction of overhead power distribution lines based on spatiotemporal sequence characteristics according to claim 1, characterized in that: The recognition algorithm model adopts the YOLO V5 framework and combines the CBAM attention mechanism and Mosaic-9 data enhancement strategy.

3. The method for controlling the construction of overhead power distribution lines based on spatiotemporal sequence characteristics according to claim 1, characterized in that: The determining of the spatial coordinates of the target device based on the pixel coordinates of the target device, the flight altitude of the drone, the shooting position of the drone, and the pixel coordinates of the center point of the image includes: Obtaining a pixel resolution based on a pixel size of a fixed camera on the drone, a camera imaging focal length of the camera, and a flight altitude of the drone, wherein the pixel size of the camera and the camera imaging focal length of the camera are obtained by hardware specifications of the camera; Obtaining a pixel offset of the target device based on the pixel coordinates of the target device and the pixel coordinates of the center point of the image; Obtaining a spatial distance between the target device and a center point of the image based on a pixel offset of the target device and the pixel resolution; The spatial coordinates of the target device are obtained based on the spatial distance and the spatial coordinates of the image center point, wherein the spatial coordinates of the image center point are the shooting position of the drone.

4. The method for controlling the construction of overhead power distribution lines based on spatiotemporal sequence characteristics according to claim 1, characterized in that: After step S103 and before step S104, the following steps are further included: Based on the spatial coordinates of the target devices, constructing spatial coordinate sets of different types of target devices respectively, wherein the spatial coordinate sets of the different types of target devices include a spatial coordinate set of a tower, a spatial coordinate set of an insulator, and a spatial coordinate set of a conductor; For different types of target devices, the parameters of the DBSCAN clustering algorithm are preset respectively, wherein the parameters of the DBSCAN clustering algorithm include neighborhood radius and minimum number of points; Based on the preset parameters of the DBSCAN clustering algorithm, the spatial coordinate sets of the different types of target devices are processed by the DBSCAN clustering algorithm to obtain the spatial coordinates of the target devices after deduplication.

5. The method for controlling the construction of overhead power distribution lines based on spatiotemporal sequence characteristics according to claim 1, characterized in that: The method uses a nearest neighbor algorithm based on the preset maximum allowable link distance of the tower and the spatial coordinates of the target device to generate a tower topology, and associates neighboring towers with other target devices other than the tower to generate an overall topology, including: Constructing a spatial coordinate set of a tower based on the spatial coordinates of the target device; Select any tower as an initial tower, use the nearest neighbor algorithm to calculate the Euclidean distances between the spatial coordinates of the initial tower and the other towers, and select the tower with the smallest Euclidean distance as the second tower, wherein the Euclidean distance between the second tower and the initial tower meets the preset maximum allowable tower connection distance; For other towers, continue to use the nearest neighbor algorithm until all towers are connected to generate a tower topology; For other target devices except towers, the adjacent towers are associated to generate the overall topology.

6. The method for controlling the construction of overhead power distribution lines based on spatiotemporal sequence characteristics according to claim 1, characterized in that: After step S104 and before step S105, the method further includes: The overall topology is manually reviewed, and if the error between the pole tower distance in the overall topology and the pole tower distance in the overhead distribution line construction design plan is greater than a preset value, an early warning is triggered.

7. The method for controlling the construction of overhead power distribution lines based on spatiotemporal sequence characteristics according to claim 1 is characterized in that The determining of the construction progress and construction quality of the overhead distribution line by comparing and analyzing the overall topology at different times and the target devices on the overall topology at the same time includes: Analyze the overall topology at different times. If the spatial coordinate distance between towers at different times is less than 5m, they are considered to be the same tower. When there is an isolated point on a tower, if the isolated point appears in the overall topology at a later time, it is considered to be a newly added tower. If the isolated point appears in the overall topology at an earlier time, manual intervention is required to determine whether it is a demolished tower.

8. An overhead distribution line construction management and control system based on spatiotemporal sequence characteristics, characterized in that: The system includes: a drone, a ground remote control terminal and a computer terminal, wherein: The drone collects an image of the overhead distribution line construction area at a certain moment, and records the drone's flight altitude, the drone's shooting position, and the pixel coordinates of the image center point corresponding to when the image was captured, wherein the number of the images is at least one; The ground remote control terminal is used to transmit the image captured by the drone and the flight altitude of the drone corresponding to the recording of the image, the shooting position of the drone, and the pixel coordinates of the center point of the image to the computer terminal; The computer terminal includes an identification module, a processing module and an analysis module, wherein: The recognition module is configured to identify a target device in the image using a recognition algorithm model, select and mark the target device with an identification frame, and record the pixel coordinates of the target device, wherein the target device includes a pole tower, an insulator, and a conductor, and the pixel coordinates of the target device are the pixel coordinates of the center point of the identification frame; The processing module is configured to determine the spatial coordinates of the target device based on the pixel coordinates of the target device, the flight altitude of the drone, the shooting position of the drone, and the pixel coordinates of the center point of the image; further configured to generate a tower topology using a nearest neighbor algorithm based on a preset maximum allowable tower link distance and the spatial coordinates of the target device, and to associate neighboring towers with other target devices other than the tower to generate an overall topology; and further configured to obtain the overall topology of the overhead distribution line construction area at other times; The analysis module is used to determine the construction progress and construction quality of the overhead distribution line by analyzing the overall topology at different times and the target devices on the overall topology at the same time.

9. An overhead power distribution line construction control device based on spatiotemporal sequence characteristics, characterized in that: The apparatus comprises: a module for executing the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program or instructions, which, when executed, causes the method according to any one of claims 1 to 7 to be performed.

Images