Method, device and equipment for determining hidden danger marking information of distribution network line, storage medium and program product

Abstract

This application relates to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining hazard labeling information of distribution network lines. The method includes: acquiring inspection information of the distribution network line; and based on the inspection information, using an image acquisition device to acquire hazard images of high-risk areas of the distribution network line, the hazard images including hazard-prone equipment; determining feature data of the hazard-prone equipment based on the hazard images; and determining initial hazard labeling information of the distribution network line based on the feature data and preset hazard feature data; determining the validity information of the initial hazard labeling information; and determining target hazard labeling information of the distribution network line based on the initial hazard labeling information and the validity information, the target hazard labeling information including hazard labeling information corresponding to each segment of the distribution network line. This method can accurately determine the hazard labeling information of distribution network lines.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining hidden danger labeling information of distribution network lines. Background Technology

[0002] Distribution network lines are a core component of the power system, referring to the power lines that transmit electrical energy from substations to distribution transformers and then distribute it to end users such as industrial, commercial, and residential users. The safety of their operation directly determines the stability and reliability of the power supply. Obtaining accurate information on potential hazards in power grid lines is a crucial prerequisite for ensuring the safe operation of the distribution network and reducing the risk of power outages due to faults.

[0003] Therefore, there is an urgent need for a method that can accurately identify the hidden dangers of power distribution network lines. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for accurately determining the hidden danger labeling information of distribution network lines, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for determining hidden danger labeling information for distribution network lines, including:

[0006] Obtain inspection information of distribution network lines, and based on the inspection information, use image acquisition equipment to obtain images of potential hazards in high-risk areas of distribution network lines. The images of potential hazards include the equipment in question.

[0007] Based on the images of potential hazards, the characteristic data of the equipment with potential hazards are determined, and the initial hazard labeling information of the distribution network line is determined based on the characteristic data and the preset hazard characteristic data.

[0008] Determine the validity information of the initial hazard labeling information, and based on the initial hazard labeling information and the validity information, determine the target hazard labeling information of the distribution network line. The target hazard labeling information includes the hazard labeling information corresponding to each line segment of the distribution network line.

[0009] In one embodiment, based on inspection information, image acquisition equipment is used to acquire images of potential hazards in high-risk areas of the distribution network line, including: determining the location of potential hazards in the distribution network line based on inspection information, and determining high-risk areas of potential hazards in the distribution network line based on the location of potential hazards; acquiring meteorological data of high-risk areas, and determining image acquisition time periods that meet preset image acquisition conditions based on the meteorological data; and acquiring images of potential hazards in high-risk areas of the distribution network line using image acquisition equipment during the image acquisition time period.

[0010] In one embodiment, determining the feature data of the equipment with potential hazards based on the hazard image includes: acquiring the pixel resolution of the hazard image, and determining a mapping function based on the pixel resolution and the actual size parameters of the equipment with potential hazards; wherein the mapping function is used to indicate the mapping relationship between the image pixels of the hazard image and the actual size parameters of the equipment with potential hazards; and determining the feature data of the equipment with potential hazards based on the mapping function and the hazard image.

[0011] In one embodiment, determining the feature data of the equipment with potential hazards based on a mapping function and a hazard image includes: using an edge detection algorithm to determine the image feature data of the equipment with potential hazards based on the hazard image; and using a mapping function to determine the feature data of the equipment with potential hazards.

[0012] In one embodiment, determining the validity information of the initial hazard labeling information includes: acquiring the acquisition timestamp of the hazard image and the generation timestamp of the initial hazard labeling information; determining the time difference based on the acquisition timestamp and the generation timestamp; determining the timeliness threshold based on the initial hazard labeling information; and determining the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold.

[0013] In one embodiment, determining the target hidden danger labeling information of the distribution network line based on the initial hidden danger labeling information and the validity information includes: using the validity information to filter out the valid hidden danger labeling information from the initial hidden danger labeling information; and matching the valid hidden danger labeling information with each segment of the distribution network line to obtain the target hidden danger labeling information.

[0014] Secondly, this application also provides a device for determining hidden danger marking information of distribution network lines, including:

[0015] The acquisition module is used to acquire inspection information of distribution network lines, and based on the inspection information, to acquire images of potential hazards in high-risk areas of the distribution network lines using image acquisition equipment. The images of potential hazards include the equipment in question.

[0016] The first determining module is used to determine the feature data of the equipment with potential hazards based on the hazard image, and to determine the initial hazard labeling information of the distribution network line based on the feature data and the preset hazard feature data.

[0017] The second determining module is used to determine the validity information of the initial hidden danger labeling information, and to determine the target hidden danger labeling information of the distribution network line based on the initial hidden danger labeling information and the validity information. The target hidden danger labeling information includes the hidden danger labeling information corresponding to each line segment of the distribution network line.

[0018] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the embodiments of the first aspect above.

[0019] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the embodiments of the first aspect above.

[0020] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the embodiments of the first aspect above.

[0021] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining hazard labeling information for distribution network lines acquire inspection information of distribution network lines, and based on this inspection information, use image acquisition equipment to acquire hazard images of high-risk areas of the distribution network lines, the hazard images including hazard-prone equipment; determine feature data of the hazard-prone equipment based on the hazard images, and determine initial hazard labeling information for the distribution network lines based on the feature data and preset hazard feature data; determine the validity information of the initial hazard labeling information, and determine target hazard labeling information for the distribution network lines based on the initial hazard labeling information and the validity information, the target hazard labeling information including hazard labeling information corresponding to each segment of the distribution network lines. The method for determining hazard labeling information for distribution network lines provided in this application can accurately locate high-risk areas through inspection information, reduce the collection of invalid data, improve labeling efficiency, and, through precise matching and validity verification of hazard equipment feature data and preset hazard features, can achieve higher accuracy in obtaining target hazard labeling information. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a method for determining the hidden danger labeling information of a distribution network line in one embodiment;

[0024] Figure 2 This is a flowchart illustrating a method for obtaining hazard images of high-risk areas in a distribution network line, as shown in one embodiment.

[0025] Figure 3 This is a flowchart illustrating a method for determining characteristic data of potentially hazardous equipment in one embodiment;

[0026] Figure 4This is a flowchart illustrating a method for determining feature data of potentially hazardous equipment based on a mapping function and a potential hazard image, as shown in one embodiment.

[0027] Figure 5 This is a flowchart illustrating a method for determining the validity information of initial hazard labeling information in one embodiment;

[0028] Figure 6 This is a flowchart illustrating a method for determining target hazard labeling information for distribution network lines in one embodiment.

[0029] Figure 7 This is a flowchart illustrating a method for determining the hidden danger labeling information of distribution network lines in another embodiment;

[0030] Figure 8 This is a structural block diagram of a device for determining hidden danger marking information of a distribution network line in one embodiment;

[0031] Figure 9 This is an internal structural diagram of a computer device in one embodiment;

[0032] Figure 10 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0034] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0035] Distribution network lines are a core component of the power system, referring to the power lines that transmit electrical energy from substations to distribution transformers and then distribute it to end users such as industrial, commercial, and residential users. The safety of their operation directly determines the stability and reliability of the power supply. Obtaining accurate information on potential hazards in power grid lines is a crucial prerequisite for ensuring the safe operation of the distribution network and reducing the risk of power outages due to faults.

[0036] Therefore, there is an urgent need for a method that can accurately identify the hidden dangers of power distribution network lines.

[0037] In view of this, this application provides a method for determining hazard labeling information for distribution network lines. The method involves acquiring inspection information of the distribution network lines, and based on this information, using image acquisition equipment to obtain hazard images of high-risk areas, where the hazard images include hazardous equipment. The method then determines feature data of the hazardous equipment based on the hazard images, and determines initial hazard labeling information for the distribution network lines based on this feature data and preset hazard feature data. Finally, the method determines the validity information of the initial hazard labeling information, and determines target hazard labeling information for the distribution network lines based on the initial hazard labeling information and the validity information. The target hazard labeling information includes hazard labeling information corresponding to each segment of the distribution network lines. The method for determining hazard labeling information for distribution network lines provided by this application accurately locates high-risk areas through inspection information, reducing the collection of invalid data and improving labeling efficiency. Furthermore, through precise matching and validity verification of hazardous equipment feature data with preset hazard features, the accuracy of the obtained target hazard labeling information is significantly improved.

[0038] The method for determining the hidden danger labeling information of the distribution network line provided in this application can be executed by a computer device, which can be a terminal or a server.

[0039] In one exemplary embodiment, such as Figure 1 As shown, a method for determining hidden danger labeling information of distribution network lines is provided. The method includes the following steps:

[0040] Step 101: Obtain inspection information of the distribution network lines, and based on the inspection information, use image acquisition equipment to obtain images of potential hazards in high-risk areas of the distribution network lines.

[0041] Optionally, the distribution network line can be a 10kV distribution network line, which is a medium-voltage distribution line that connects the regional substation and the distribution transformer and undertakes the function of voltage reduction and distribution of power.

[0042] Optionally, the inspection information of distribution network lines refers to the basic data and historical records collected during the operation and maintenance of distribution networks that are related to the operating status of lines and equipment. For example, the inspection information of distribution network lines may include pole / tower number, hazard type, and GPS latitude and longitude coordinates.

[0043] Optionally, the image acquisition equipment can be drones, handheld high-definition inspection instruments, infrared thermal imagers, gimbal cameras, imaging devices mounted on line inspection robots, etc.

[0044] Optionally, a high-risk area refers to a region where the probability of a hazard occurring is higher than a preset probability threshold. The hazard image may include the equipment involved in the hazard.

[0045] For example, the hazard images of high-risk areas may include the coordinate range of the high-risk area, equipment morphology images, and environmental parameters during the acquisition period. The coordinate range of the high-risk area refers to the precise geographic location data corresponding to the high-risk area, which may include the GPS latitude and longitude of the area boundary, the associated tower numbers, and the line section numbers; the equipment morphology images refer to high-definition visual images of the distribution network equipment within the high-risk area, which may include visible light photographs of the equipment exterior, close-up images of defective parts, infrared thermal images, etc.; the environmental parameters during the acquisition period refer to the on-site environmental data at the time of image acquisition, which may include temperature, humidity, wind speed, visibility, etc.

[0046] In some exemplary embodiments, the computer device can obtain inspection information of the distribution network lines.

[0047] Specifically, computer equipment can establish communication connections with the distribution network operation and maintenance management system, historical inspection database, and on-site inspection terminals through preset data interfaces to obtain inspection information of distribution network lines.

[0048] Furthermore, after acquiring inspection information of the distribution network lines, the computer equipment can use image acquisition equipment to obtain images of potential hazards in high-risk areas of the distribution network lines based on the inspection information.

[0049] Specifically, computer equipment can first identify high-risk areas from the regions corresponding to the distribution network lines based on inspection information, and then use image acquisition equipment to obtain images of the high-risk areas of the distribution network lines.

[0050] Step 102: Determine the feature data of the equipment with potential hazards based on the hazard image, and determine the initial hazard labeling information of the distribution network line based on the feature data and the preset hazard feature data.

[0051] Optionally, the feature data of the potentially hazardous equipment may include image features such as edge pixel coordinates, surface texture distribution, and contour pixel perimeter, as well as parameters such as grayscale difference, pixel area, and texture complexity of the defective area.

[0052] The preset hazard characteristic data can be used to indicate the characteristic thresholds of typical hazards, such as the characteristic thresholds of typical hazards such as insulator damage and broken strands of conductors and ground wires.

[0053] In some exemplary embodiments, after acquiring images of potential hazards in high-risk areas of the power distribution network based on inspection information using image acquisition equipment, the computer device can determine the characteristic data of the hazard-prone equipment based on the hazard images.

[0054] Specifically, computer equipment can input images of potential hazards into a feature analysis model to obtain feature data of the hazard-prone equipment output by the feature analysis model.

[0055] Computer equipment can also utilize Canny edge detection and LBP texture extraction algorithms to obtain feature data of potentially hazardous equipment from images of potential hazards.

[0056] Furthermore, after determining the characteristic data of the equipment with potential hazards based on the hazard image, the computer equipment can determine the initial hazard labeling information of the distribution network line based on the characteristic data and the preset hazard characteristic data.

[0057] Specifically, computer equipment can compare the characteristic data of potentially hazardous equipment with preset potential hazard characteristic data to generate initial hazard labeling information based on the comparison results.

[0058] The computer equipment can also input feature data and preset hidden danger feature data into the feature analysis model to obtain the initial hidden danger labeling information of the distribution network line output by the feature analysis model.

[0059] Step 103: Determine the validity information of the initial hazard labeling information, and determine the target hazard labeling information of the distribution network line based on the initial hazard labeling information and the validity information.

[0060] The target hazard labeling information includes hazard labeling information corresponding to each segment of the distribution network line. The hazard labeling information for each segment can include the segment number, standardized equipment number, hazard type, precise labeling coordinates, effectiveness judgment result, and rectification status indicator.

[0061] In some exemplary embodiments, after determining the initial hazard labeling information of the distribution network line based on feature data and preset hazard feature data, the computer device can determine the validity information of the initial hazard labeling information.

[0062] Specifically, the computer device can acquire the acquisition timestamp of the hazard image and the generation timestamp of the initial hazard labeling information; determine the time difference based on the acquisition timestamp and the generation timestamp; determine the timeliness threshold based on the initial hazard labeling information; and determine the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold.

[0063] Furthermore, after determining the validity information of the initial hazard labeling information, the computer equipment can determine the target hazard labeling information of the distribution network line based on the initial hazard labeling information and the validity information.

[0064] Specifically, the computer equipment can use the validity information to filter out valid hazard labeling information from the initial hazard labeling information; and match the valid hazard labeling information with each segment of the distribution network line to obtain the target hazard labeling information.

[0065] The aforementioned method for determining hazard labeling information for distribution network lines involves acquiring inspection information of the distribution network lines, and based on this information, using image acquisition equipment to obtain hazard images of high-risk areas, including hazard-prone equipment. The method then determines the feature data of the hazard-prone equipment based on these images, and determines initial hazard labeling information for the distribution network lines based on this feature data and pre-set hazard feature data. Finally, it determines the validity information of the initial hazard labeling information, and based on this initial and validity information, determines target hazard labeling information for the distribution network lines, including hazard labeling information corresponding to each segment of the distribution network lines. The method for determining hazard labeling information for distribution network lines provided in this application accurately locates high-risk areas using inspection information, reducing the collection of invalid data and improving labeling efficiency. Furthermore, through precise matching and validity verification of hazard equipment feature data with pre-set hazard features, the accuracy of the obtained target hazard labeling information is significantly improved.

[0066] In one exemplary embodiment, such as Figure 2 As shown, based on inspection information, images of potential hazards in high-risk areas of the distribution network lines are obtained using image acquisition equipment, including the following steps:

[0067] Step 201: Determine the location of potential hazards in the distribution network lines based on the inspection information, and determine the high-risk areas of potential hazards in the distribution network lines based on the location of the potential hazards.

[0068] In some exemplary embodiments, the computer device can determine the location of potential hazards in the distribution network line based on inspection information, and determine the high-incidence area of ​​potential hazards in the distribution network line based on the location of the potential hazards.

[0069] Specifically, computer equipment can first extract the coordinate data of all potential hazard locations from the inspection information, then map these coordinates to the distribution network line direction coordinate system, and calculate the distribution density of each potential hazard location by counting the number of potential hazards occurring per unit area, thereby determining the high-incidence areas of potential hazards.

[0070] Specifically, the computer equipment can extract the latitude and longitude coordinates of all potential hazard locations from the inspection records, convert the latitude and longitude coordinates into coordinate values ​​in a Cartesian coordinate system, set up a square grid with a side length of 50 meters to cover the line area, count the number of potential hazard points in each grid, calculate the ratio of the number of potential hazard points in the grid to the grid area (total equipment) to obtain the distribution density of each grid. When the distribution density of a certain grid exceeds 0.02 points / square meter, the grid is marked as a high-density grid. Adjacent high-density grids are merged to form a continuous area, and this continuous area is identified as a high-risk area for potential hazards.

[0071] Furthermore, the computer equipment can also calculate the coordinates of the diagonal vertices of the circumscribed rectangle of a high-risk area. For example, a high-risk area may contain grid A (coordinate range X1=356200 to 356250, Y1=332150 to 332200) and grid B (coordinate range X2=356250 to 356300, Y2=332200 to 332250). Taking Xmin=356200, Xmax=356300, Ymin=332150, Ymax=332250, the coordinate range (356200, 332150) to (356300, 332250) is obtained, thus generating the coordinate range of the high-risk area.

[0072] Step 202: Obtain meteorological data for areas with high incidence of potential hazards, and determine the image acquisition period that meets the preset image acquisition conditions based on the meteorological data.

[0073] In some exemplary embodiments, after determining the high-risk area of ​​the distribution network line based on the location of the potential hazard, the computer device can obtain meteorological data of the high-risk area.

[0074] Specifically, computer equipment can call the meteorological department's API interface to obtain meteorological data for areas with high risk of hazards. This meteorological data can include temperature, humidity, wind speed, visibility, and other data.

[0075] Furthermore, after acquiring meteorological data from areas with high incidence of potential hazards, the computer equipment can determine the image acquisition period that meets the preset image acquisition conditions based on the meteorological data.

[0076] Specifically, computer equipment can determine the required image acquisition time period by comparing it with preset image acquisition standards.

[0077] The preset image acquisition conditions can be: temperature 15°C to 35°C, humidity 40% to 70%, wind speed 0.5 m / s to 8.0 m / s, and visibility greater than 5000 meters. The computer equipment can compare the acquired meteorological data with the preset image acquisition conditions. When all parameters in the meteorological data simultaneously meet the preset image acquisition conditions, that time period is determined to be a qualified time period. The start time and duration of consecutive qualified time periods are counted, and the period with the longest duration is selected as the optimal time period, which is also the image acquisition period. For example, on a certain day, from 9:00 to 11:00, the temperature is 25°C, humidity is 55%, wind speed is 3.2 m / s, and visibility is 7800 meters, meeting the standard and lasting for 120 minutes. However, from 13:00 to 14:00, the temperature is 38°C, exceeding the standard range. Therefore, 9:00 to 11:00 is determined to be the image acquisition period.

[0078] Step 203: During the image acquisition period, use image acquisition equipment to collect images of potential hazards in high-risk areas of the power distribution network.

[0079] In some exemplary embodiments, after determining the image acquisition period that meets the preset image acquisition conditions based on meteorological data, the computer device can use the image acquisition device to acquire images of potential hazards in high-risk areas of the power distribution network during the image acquisition period.

[0080] Specifically, computer equipment can activate image acquisition devices, adjust the focus and shooting angle, and take pictures of high-risk areas based on the regional coordinates and image acquisition time period of the high-risk areas, generating hazard images of the high-risk areas.

[0081] For example, the area with high incidence of potential hazards has coordinates ranging from (356200, 332150) to (356300, 332250). The image acquisition period is from 9:00 to 11:00. At the start of the image acquisition period, the drone acquisition equipment is started, and the center point (356250, 332200) is calculated based on the coordinate range. The drone's flight altitude is adjusted to 80 meters, the camera focal length is set to 35mm, and the shooting angle is adjusted to 90 degrees vertically downward. The image coverage area is calculated based on the area's diagonal length of 156 meters. The shooting interval is set to 15 seconds. During the image acquisition period, the drone continuously shoots at the center point coordinates. After the shooting is completed, an image of potential hazards covering the entire high incidence area is generated through an image stitching algorithm.

[0082] In one exemplary embodiment, such as Figure 3 As shown, determining the characteristic data of potentially hazardous equipment based on hazardous images includes the following steps:

[0083] Step 301: Obtain the pixel resolution of the hazard image and determine the mapping function based on the pixel resolution and the actual size parameters of the hazard equipment.

[0084] The mapping function is used to indicate the mapping relationship between the image pixels of the potential hazard image and the actual size parameters of the potential hazard equipment.

[0085] In some exemplary embodiments, the computer device can acquire the pixel resolution of the hazard image and determine a mapping function based on the pixel resolution and the actual size parameters of the hazard device.

[0086] Specifically, the computer equipment can access the distribution network line design drawing database and retrieve the drawing file for insulator model FXBW4-10 / 70 to obtain the design values ​​for insulator skirt diameter (120 mm), tower height (18500 mm), and conductor / ground wire diameter (26.8 mm). Further, the computer equipment uses image processing tools to measure the insulator pixel height in the hazard image as 240 pixels. Given that the actual insulator height is 400 mm, the formula for calculating pixel resolution is... Where R represents resolution (mm / pixel). Indicates the actual height (in millimeters). The pixel height (in pixels) is calculated by dividing the actual height of 400 mm by the pixel height of 240 pixels, resulting in a resolution value of 1.667 mm / pixel. When verifying the resolution data, the width of the tower foundation in the hazard image was measured in pixels as 180. Multiplying 180 pixels by the resolution of 1.667 mm / pixel yields an actual width of 300 mm, consistent with the 300 mm foundation width in the design drawings.

[0087] Furthermore, the actual diameter of the insulator is obtained as 120 mm, and the resolution data is 1.667 mm / pixel. Dividing the actual diameter by the resolution gives the pixel diameter: 120 mm ÷ 1.667 mm / pixel = 72 pixels. The actual height of the tower is obtained as 18500 mm, and dividing the actual height by the resolution gives the pixel height: 18500 mm ÷ 1.667 mm / pixel = 11098 pixels. The actual diameter of the conductor is obtained as 26.8 mm, and dividing the actual diameter by the resolution gives the pixel diameter: 26 mm / pixel = 72 pixels. 0.8 mm ÷ 1.667 mm / pixel = 16 pixels; After rounding the converted pixel values, the insulator diameter is rounded to 72 pixels, the tower height to 11098 pixels, and the conductor diameter to 16 pixels. A device parameter reference table is established, recording the actual insulator diameter of 120 mm corresponding to a pixel diameter of 72 pixels, the actual tower height of 18500 mm corresponding to a pixel height of 11098 pixels, and the actual conductor diameter of 26.8 mm corresponding to a pixel diameter of 16 pixels. This completes the acquisition of the device pixel corresponding parameters, which is also the determination of the mapping function.

[0088] Step 302: Determine the characteristic data of the equipment with potential hazards based on the mapping function and the hazard image.

[0089] In some exemplary embodiments, after determining the mapping function based on the pixel resolution and the actual size parameters of the potentially hazardous device, the computer device can determine the feature data of the potentially hazardous device based on the mapping function and the image of the potentially hazardous device.

[0090] In one exemplary embodiment, such as Figure 4 As shown, the characteristic data of the equipment with potential hazards are determined based on the mapping function and the hazard image, including the following steps:

[0091] Step 401: Using an edge detection algorithm, determine the image feature data of the equipment with potential hazards based on the hazard image.

[0092] In some exemplary embodiments, a computer device may use an edge detection algorithm to determine the image feature data of a potential hazard based on a hazard image.

[0093] Specifically, the computer equipment can use the Canny edge detection operator to extract the insulator contour pixels in the hazard image, record the set of contour pixel coordinates, such as [(x1, y1), (x2, y2), ..., (xk, yk)], calculate the perimeter of the contour pixels as the sum of the Euclidean distances of all adjacent pixels, use the LBP operator to extract the pixel distribution of the insulator surface texture, and statistically analyze a 256-dimensional LBP feature histogram; for the tower area, the Sobel operator is used to extract the edge gradient, and the coordinates of pixels with a gradient greater than 50 are recorded; for the conductor and ground wire area, the Hough transform is used to detect straight line segments, and the pixel coordinates of the endpoints of the line segments are recorded.

[0094] For example, a total of 852 contour pixels were extracted from the insulator image, and the formula for calculating the distance between adjacent pixels is as follows: Where d represents the distance between adjacent pixels. and The x and y coordinates of the i-th pixel are represented by the sum of the distances between all adjacent points to obtain the perimeter value of 1240 pixels. At the same time, the surface texture LBP feature is extracted to obtain the histogram distribution [0.02, 0.15, ..., 0.08], thus completing the acquisition of image feature data.

[0095] Step 402: Use mapping functions and image feature data to determine the feature data of the equipment with potential hazards.

[0096] In some exemplary embodiments, after a computer device uses an edge detection algorithm to determine the image feature data of a potentially hazardous device based on a potential hazard image, it can use a mapping function and the image feature data to determine the feature data of the potentially hazardous device.

[0097] Specifically, the computer device can access the insulator standard perimeter of 1180 pixels from the device pixel-to-parameter table, read the actual measured insulator outline perimeter of 1240 pixels, and calculate the absolute deviation value. The formula for calculating the relative deviation of pixels is: ,in, Indicates relative deviation. Represents the actual pixel value. The standard pixel value is 60 / 1180 = 0.051. The allowable deviation range is set to a relative deviation of no more than 0.08. Since 0.051 is less than 0.08, the deviation is determined to be within the allowable range. The coordinates of the outer rectangle of the insulator area are extracted, and the coordinates of the upper left corner (156, 238) and the lower right corner (284, 422) are recorded. The same operation is performed on the tower area. The pixel deviation value of the tower height is calculated as |11098-10850| = 248 pixels. The relative deviation is 248 / 10850 = 0.023, which is less than the allowable range of 0.05. The coordinates of the tower area (88, 156) to (192, 11234) are recorded to complete the determination of the target equipment area coordinates.

[0098] Furthermore, within the coordinate range of the target equipment area, the pixel grayscale difference of the insulator area is calculated. The average grayscale value of the intact area is 125, and the average grayscale value of the damaged area is 86, resulting in a grayscale difference of 39. The pixel area of ​​the damaged area is calculated, and the area of ​​consecutive pixel regions with grayscale values ​​less than 100 is statistically determined to be 285 pixels. The texture complexity is calculated using the Local Binary Mode Variance (LBP), and the LBP feature variance in the damaged area is calculated to be 0.18. For the soil-filled area of ​​the tower foundation, the pixel area of ​​the soil-filled area is calculated, and the difference in grayscale value between the soil-filled area and the surrounding ground is statistically analyzed. The area of ​​a pixel region greater than 25 is 650 pixels. The texture roughness of the soil-filled area is calculated to be 0.24. For the broken strand area of ​​the conductor, the gray-level change value of the pixel at the broken strand is calculated. The number of pixels with a gray-level difference greater than 30 between adjacent pixels is counted as 42. The area ratio of the broken strand area is calculated to be 0.15. For example, the gray-level difference of the damaged insulator area is 39, which is greater than the threshold of 25. The area is 285 pixels, which is greater than the threshold of 200. The texture complexity is 0.18, which is greater than the threshold of 0.12. If all three conditions are met, the feature data of the hidden danger equipment is obtained.

[0099] Furthermore, in one embodiment, determining the initial hazard labeling information of the distribution network line based on feature data and preset hazard feature data includes: comparing the feature data with the preset hazard feature data, determining whether the degree of consistency meets the set standard, and if the standard is met, labeling the hazard type and equipment number to form the initial hazard labeling information.

[0100] Specifically, the insulator damage feature parameters are set as follows: grayscale difference threshold 25, area threshold 200 pixels, and texture complexity threshold 0.12. The grayscale difference is 39, the area is 285 pixels, and the texture complexity is 0.18 in the device area feature data. 39 is greater than 25, 285 is greater than 200, and 0.18 is greater than 0.12. The consistency index is calculated. When all parameters exceed the threshold, the consistency is determined to be 100%.

[0101] The characteristic parameters for the soil pile of the tower foundation are set as follows: area threshold of 500 pixels and texture roughness threshold of 0.20. The area of ​​the soil pile region is read as 650 pixels and the texture roughness is 0.24. The comparison shows that 650 is greater than 500 and 0.24 is greater than 0.20, and the match is determined to be 100%.

[0102] The conductor strand breakage feature parameters were set as follows: grayscale abrupt change threshold 30, area ratio threshold 0.10. 42 abrupt change points were read in the strand breakage area, with an area ratio of 0.15. The comparison showed that 42 was greater than 30 and 0.15 was greater than 0.10, thus the match rate was determined to be 100%.

[0103] For areas with 100% agreement, mark the hazard type as "insulator damage" and the equipment number as "B-15", mark the hazard type as "soil piling on tower foundation" and the equipment number as "T-27", and mark the hazard type as "conductor / ground wire broken strand" and the equipment number as "W-09", thus forming the initial hazard marking information.

[0104] In one exemplary embodiment, such as Figure 5 As shown, determining the validity of initial hazard labeling information includes the following steps:

[0105] Step 501: Obtain the timestamp of the hazard image acquisition and the timestamp of the initial hazard labeling information generation.

[0106] In some exemplary embodiments, the computer device can acquire the timestamp of the acquisition of the hazard image and the timestamp of the generation of the initial hazard labeling information.

[0107] Specifically, obtain the collection timestamp of record number B-15, 2024-06-15 09:30:00, and the corresponding initial hazard labeling information generation timestamp, 2024-06-15 14:25:00. Convert both timestamps to Unix timestamp format: the collection timestamp is converted to 1718422200, and the generation timestamp is converted to 1718439900; obtain the collection timestamp of record number T-27, 20... The timestamp 24-06-15 10:15:00 is converted to 1718424900, and the timestamp generated 2024-06-15 11:30:00 is converted to 1718436600; the timestamp of the acquisition of record number W-09 2024-06-15 08:45:00 is converted to 1718419500, and the timestamp generated 2024-06-15 16:20:00 is converted to 1718446800.

[0108] Step 502: Determine the time difference based on the collection timestamp and the generation timestamp.

[0109] In some exemplary embodiments, after acquiring the acquisition timestamp of the hazard image and the generation timestamp of the initial hazard labeling information, the computer device can determine the time difference based on the acquisition timestamp and the generation timestamp.

[0110] Specifically, the time difference is calculated as 1718439900 minus 1718422200, which equals 17700 seconds. Converting the seconds to hours, 17700 seconds divided by 3600 equals 4.92 hours. The time difference is calculated as 1718436600 minus 1718424900, which equals 11700 seconds, converted to 3.25 hours. The time difference is calculated as 1718446800 minus 1718419500, which equals 27300 seconds, converted to 7.58 hours.

[0111] Step 503: Determine the timeliness threshold based on the initial hazard labeling information, and determine the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold.

[0112] In some exemplary embodiments, after determining the time difference based on the acquisition timestamp and the generation timestamp, the computer device can determine the timeliness threshold based on the initial hazard labeling information, and determine the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold.

[0113] Specifically, the change cycle standard for potential hazards such as insulator damage is 6 hours, the change cycle standard for potential hazards such as soil accumulation in tower foundations is 8 hours, and the change cycle standard for potential hazards such as broken conductor strands is 4 hours.

[0114] The B-15 hazard type is insulator damage, with a time interval of 4.92 hours. Since 4.92 is less than 6, the data is considered valid. The T-27 hazard type is soil accumulation on the tower foundation, with a time interval of 3.25 hours. Since 3.25 is less than 8, the data is considered valid. The W-09 hazard type is conductor / ground wire breakage, with a time interval of 7.58 hours. Since 7.58 is greater than 4, the data is considered invalid.

[0115] The data validity judgment rule is set as follows: the time interval value is considered valid when it is less than or equal to the change cycle standard, and invalid when it is greater than the change cycle standard. A data validity judgment result table is generated, recording B-15 as valid, T-27 as valid, and W-09 as invalid. For example, a new record B-16, with an insulator damage time interval value of 6.5 hours, is added. Comparing 6.5 with 6, it is determined that the data is invalid.

[0116] Furthermore, the computer equipment can also call up the hazard rectification time in the inspection record, combine it with the validity information of the initial hazard labeling information, mark the rectification status, and output intermediate hazard labeling information.

[0117] Specifically, the computer equipment can access the inspection record database, query the rectification time data, read the rectification completion time of B-15 (2024-06-18 15:00:00), read the rectification completion time of T-27 (2024-06-17 09:30:00), and read the empty rectification completion time of W-09. Based on the data validity judgment results, B-15 is valid and the rectification completion time already exists, so the rectification status is marked as "rectified"; T-27 is valid and the rectification completion time already exists, so the rectification status is marked as "rectified"; W-09 is invalid and the rectification completion time is empty, so the rectification status is marked as "pending review". Rectification status marking rules are then set. Then, when the data is valid and a rectification completion time exists, it is marked as rectified; when the data is valid but the rectification completion time is empty, it is marked as pending rectification; when the data is invalid and the rectification completion time is empty, it is marked as pending review; when the data is invalid but the rectification completion time exists, it is marked as reviewed. For example, if the newly added record B-16 is invalid but the rectification completion time 2024-06-19 10:00:00 exists, the rectification status is marked as reviewed, and the timeliness verification labeling data table is output, including equipment number B-15 marked as rectified, T-27 marked as rectified, W-09 marked as pending review, and B-16 marked as reviewed, completing the output of intermediate hidden danger labeling information.

[0118] In one exemplary embodiment, such as Figure 6 As shown, determining the target hazard labeling information for distribution network lines based on initial hazard labeling information and validity information includes the following steps:

[0119] Step 601: Using validity information, select valid hazard labeling information from the initial hazard labeling information.

[0120] Step 602: Match the effective hazard labeling information with each segment of the distribution network line to obtain the target hazard labeling information.

[0121] In some exemplary embodiments, the computer device may use validity information to filter out valid hazard labeling information from the initial hazard labeling information.

[0122] Furthermore, the effective hazard labeling information is matched with the various segments of the distribution network lines to obtain the target hazard labeling information.

[0123] Specifically, for the initial hazard labeling information, the equipment number fields B-15, T-27, and W-09 are obtained; the hazard type fields "insulator damage," "tower foundation soil accumulation," and "conductor / ground wire broken strands" are extracted; the labeling coordinate fields (156, 238)-(284, 422), (88, 156)-(192, 11234), and (345, 567)-(389, 612) are extracted; the rectification status fields "rectified," "rectified," and "pending review" are extracted; and the timeliness judgment result fields "valid," "valid," and "invalid" are extracted. The distribution network line segmentation rule library is called, and the rule is set to divide the line segments by the first letter of the tower number: B series belongs to line segment 1, T series belongs to line segment 2, and W series belongs to line segment 3. Equipment number B-15 is assigned to line segment 1, equipment number T-27 to line segment 2, and equipment number W-09 to line segment 3. For each line segment, establish a line segment data set. Line segment 1 contains data record {Equipment No. B-15, Hazard Type: Insulator Damage, Coordinates: (156, 238) - (284, 422), Rectification Status: Rectified, Timeliness Judgment: Valid}. Line segment 2 contains data record {Equipment No. T-27, Hazard Type: Poles on Tower Foundation, Coordinates: (88, 156) - (192, 11234), Rectification Status: Rectified, Timeliness Judgment: Valid}. Line segment 3 contains data record {Equipment No. W-09, Hazard Type: Conductor / Ground Wire Strand Breakage, Coordinates: (345, 567) - (389, 612), Rectification Status: Pending Review, Timeliness Judgment: Invalid}. For example, add equipment No. B-16 to line segment 1 and equipment No. T-28 to line segment 2 to complete the construction of the line segment data set.

[0124] Furthermore, based on the segmented data set of the line, the data in line segment 1 is sorted alphabetically by equipment number, with the order being B-15 and B-16; the data in line segment 2 is sorted alphabetically by equipment number, with the order being T-27 and T-28; and the data in line segment 3 is sorted alphabetically by equipment number, with the order being W-09. A unified data format standard is applied, with the equipment number field being a uniform 6-character length, padded with zeros if necessary. B-15 is formatted as B-015, T-27 as T-027, and W-09 as W-009. The hazard type field is uniformly 8 characters long, with insulator damage formatted as "insulation damage," tower foundation soil piling formatted as "foundation soil piling," and conductor / ground wire broken strand formatted as "conductor / ground wire broken strand." The coordinate label field is uniformly formatted as "starting X-starting Y-ending X-ending Y," and the coordinates (156, 238)-(284, 422) are formatted as "156-238-284-4". 22”, the rectification status field is uniformly 4 characters long, formatted as “rectified” for “rectified” and “pending review” for “pending review”. The timeliness judgment result field is uniformly 2 characters long, formatted as “valid” for “valid” and “invalid” for “invalid”. Generate a 10kV distribution network fine annotation dataset, including data table {B-015, insulation damage, 156-238-284-422, rectified, valid} and {B-016, insulation damage, 167-2} for line segment 1. 45-295-431, pending review, invalid}, data table for line segment 2 {T-027, foundation soil piling, 88-156-192-11234, rectified, valid} and {T-028, foundation soil piling, 95-162-201-11240, rectified, valid}, data table for line segment 3 {W-009, conductor and ground strand break, 345-567-389-612, pending review, invalid}, completed the generation of the 10kV distribution network fine annotation dataset.

[0125] In one exemplary embodiment, such as Figure 7 As shown, another method for determining the hidden danger labeling information of distribution network lines is provided. This method includes the following steps:

[0126] Step 701: Obtain inspection information of distribution network lines, determine the location of hidden dangers in distribution network lines based on the inspection information, and determine the high-incidence area of ​​hidden dangers in distribution network lines based on the location of hidden dangers; obtain meteorological data of high-incidence areas of hidden dangers, and determine the image acquisition period that meets the preset image acquisition conditions based on the meteorological data; during the image acquisition period, use image acquisition equipment to acquire hidden danger images of high-incidence areas of hidden dangers in distribution network lines, and the hidden danger images include the hidden danger equipment.

[0127] Step 702: Obtain the pixel resolution of the hazard image and determine the mapping function based on the pixel resolution and the actual size parameters of the hazard equipment; wherein, the mapping function is used to indicate the mapping relationship between the image pixels of the hazard image and the actual size parameters of the hazard equipment; use an edge detection algorithm to determine the image feature data of the hazard equipment based on the hazard image; use the mapping function and the image feature data to determine the feature data of the hazard equipment, and determine the initial hazard labeling information of the distribution network line based on the feature data and the preset hazard feature data;

[0128] Step 703: Obtain the acquisition timestamp of the hazard image and the generation timestamp of the initial hazard labeling information; determine the time difference based on the acquisition timestamp and the generation timestamp; determine the timeliness threshold based on the initial hazard labeling information, and determine the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold, and use the validity information to filter out the valid hazard labeling information from the initial hazard labeling information; match the valid hazard labeling information with each line segment of the distribution network to obtain the target hazard labeling information, which includes the hazard labeling information corresponding to each line segment of the distribution network.

[0129] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0130] Based on the same inventive concept, this application also provides a device for determining the hidden danger labeling information of distribution network lines to implement the above-mentioned method for determining the hidden danger labeling information of distribution network lines. The solution provided by this device is similar to the solution described in the above-described method. Therefore, the specific limitations of one or more embodiments of the device for determining the hidden danger labeling information of distribution network lines provided below can be found in the limitations of the method for determining the hidden danger labeling information of distribution network lines above, and will not be repeated here.

[0131] In one exemplary embodiment, such as Figure 8As shown, a device 800 for determining hidden danger marking information of distribution network lines is provided, including: an acquisition module 801, a first determination module 802, and a second determination module 803, wherein:

[0132] The acquisition module 801 is used to acquire inspection information of the distribution network lines, and based on the inspection information, to acquire images of potential hazards in high-risk areas of the distribution network lines using image acquisition equipment. The images of potential hazards include the equipment in question.

[0133] The first determining module 802 is used to determine the feature data of the hidden danger equipment based on the hidden danger image, and to determine the initial hidden danger labeling information of the distribution network line based on the feature data and the preset hidden danger feature data.

[0134] The second determining module 803 is used to determine the validity information of the initial hidden danger labeling information, and to determine the target hidden danger labeling information of the distribution network line based on the initial hidden danger labeling information and the validity information. The target hidden danger labeling information includes the hidden danger labeling information corresponding to each line segment of the distribution network line.

[0135] In one embodiment, the acquisition module 801 is specifically used to determine the location of potential hazards in the distribution network line based on inspection information, and to determine the high-incidence area of ​​potential hazards in the distribution network line based on the location of potential hazards; to acquire meteorological data of the high-incidence area of ​​potential hazards, and to determine the image acquisition period that meets the preset image acquisition conditions based on the meteorological data; and to acquire potential hazard images of the high-incidence area of ​​potential hazards in the distribution network line using image acquisition equipment during the image acquisition period.

[0136] In one embodiment, the first determining module 802 is specifically used to obtain the pixel resolution of the hazard image and determine a mapping function based on the pixel resolution and the actual size parameters of the hazard equipment; wherein, the mapping function is used to indicate the mapping relationship between the image pixels of the hazard image and the actual size parameters of the hazard equipment; and to determine the feature data of the hazard equipment based on the mapping function and the hazard image.

[0137] In one embodiment, the first determining module 802 is specifically used to determine the image feature data of the hidden danger equipment based on the hidden danger image using an edge detection algorithm; and to determine the feature data of the hidden danger equipment using a mapping function and the image feature data.

[0138] In one embodiment, the second determining module 803 is specifically used to obtain the acquisition timestamp of the hazard image and the generation timestamp of the initial hazard labeling information; determine the time difference based on the acquisition timestamp and the generation timestamp; determine the timeliness threshold based on the initial hazard labeling information; and determine the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold.

[0139] In one embodiment, the second determining module 803 is specifically used to use validity information to filter out valid hazard labeling information from the initial hazard labeling information; and to match the valid hazard labeling information with each segment of the distribution network line to obtain the target hazard labeling information.

[0140] The various modules in the aforementioned device for identifying potential hazards in power distribution lines can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0141] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for determining hidden danger labeling information for power distribution lines.

[0142] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for determining hidden danger labeling information of power distribution lines.

[0143] Those skilled in the art will understand that Figure 9 and Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0144] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0145] Obtain inspection information of distribution network lines, and based on the inspection information, use image acquisition equipment to obtain images of potential hazards in high-risk areas of distribution network lines. The images of potential hazards include the equipment in question.

[0146] Based on the images of potential hazards, the characteristic data of the equipment with potential hazards are determined, and the initial hazard labeling information of the distribution network line is determined based on the characteristic data and the preset hazard characteristic data.

[0147] Determine the validity information of the initial hazard labeling information, and based on the initial hazard labeling information and the validity information, determine the target hazard labeling information of the distribution network line. The target hazard labeling information includes the hazard labeling information corresponding to each line segment of the distribution network line.

[0148] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the location of potential hazards in the distribution network line based on inspection information, and determining the high-incidence area of ​​potential hazards in the distribution network line based on the location of potential hazards; acquiring meteorological data of the high-incidence area of ​​potential hazards, and determining the image acquisition period that meets the preset image acquisition conditions based on the meteorological data; and during the image acquisition period, acquiring potential hazard images of the high-incidence area of ​​potential hazards in the distribution network line using image acquisition equipment.

[0149] In one embodiment, when the processor executes the computer program, it further performs the following steps: acquiring the pixel resolution of the hazard image, and determining a mapping function based on the pixel resolution and the actual size parameters of the hazard equipment; wherein the mapping function is used to indicate the mapping relationship between the image pixels of the hazard image and the actual size parameters of the hazard equipment; and determining the feature data of the hazard equipment based on the mapping function and the hazard image.

[0150] In one embodiment, when the processor executes the computer program, it further performs the following steps: using an edge detection algorithm to determine the image feature data of the equipment with potential hazards based on the image of the potential hazard; and using a mapping function and the image feature data to determine the feature data of the equipment with potential hazards.

[0151] In one embodiment, when the processor executes the computer program, it further performs the following steps: acquiring the acquisition timestamp of the hazard image and the generation timestamp of the initial hazard labeling information; determining the time difference based on the acquisition timestamp and the generation timestamp; determining the timeliness threshold based on the initial hazard labeling information; and determining the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold.

[0152] In one embodiment, when the processor executes the computer program, it further performs the following steps: using validity information to filter out valid hazard labeling information from the initial hazard labeling information; matching the valid hazard labeling information with each segment of the distribution network line to obtain the target hazard labeling information.

[0153] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0154] Obtain inspection information of distribution network lines, and based on the inspection information, use image acquisition equipment to obtain images of potential hazards in high-risk areas of distribution network lines. The images of potential hazards include the equipment in question.

[0155] Based on the images of potential hazards, the characteristic data of the equipment with potential hazards are determined, and the initial hazard labeling information of the distribution network line is determined based on the characteristic data and the preset hazard characteristic data.

[0156] Determine the validity information of the initial hazard labeling information, and based on the initial hazard labeling information and the validity information, determine the target hazard labeling information of the distribution network line. The target hazard labeling information includes the hazard labeling information corresponding to each line segment of the distribution network line.

[0157] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the location of potential hazards in the distribution network line based on inspection information, and determining the high-incidence area of ​​potential hazards in the distribution network line based on the location of potential hazards; acquiring meteorological data of the high-incidence area of ​​potential hazards, and determining the image acquisition period that meets the preset image acquisition conditions based on the meteorological data; and during the image acquisition period, acquiring potential hazard images of the high-incidence area of ​​potential hazards in the distribution network line using image acquisition equipment.

[0158] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring the pixel resolution of the hazard image, and determining a mapping function based on the pixel resolution and the actual size parameters of the hazard equipment; wherein the mapping function is used to indicate the mapping relationship between the image pixels of the hazard image and the actual size parameters of the hazard equipment; and determining the feature data of the hazard equipment based on the mapping function and the hazard image.

[0159] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: using an edge detection algorithm to determine the image feature data of the equipment with potential hazards based on the image of the potential hazard; and using a mapping function and the image feature data to determine the feature data of the equipment with potential hazards.

[0160] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring the acquisition timestamp of the hazard image and the generation timestamp of the initial hazard labeling information; determining the time difference based on the acquisition timestamp and the generation timestamp; determining the timeliness threshold based on the initial hazard labeling information; and determining the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold.

[0161] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: using validity information to filter out valid hazard labeling information from the initial hazard labeling information; matching the valid hazard labeling information with each segment of the distribution network line to obtain the target hazard labeling information.

[0162] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0163] Obtain inspection information of distribution network lines, and based on the inspection information, use image acquisition equipment to obtain images of potential hazards in high-risk areas of distribution network lines. The images of potential hazards include the equipment in question.

[0164] Based on the images of potential hazards, the characteristic data of the equipment with potential hazards are determined, and the initial hazard labeling information of the distribution network line is determined based on the characteristic data and the preset hazard characteristic data.

[0165] Determine the validity information of the initial hazard labeling information, and based on the initial hazard labeling information and the validity information, determine the target hazard labeling information of the distribution network line. The target hazard labeling information includes the hazard labeling information corresponding to each line segment of the distribution network line.

[0166] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the location of potential hazards in the distribution network line based on inspection information, and determining the high-incidence area of ​​potential hazards in the distribution network line based on the location of potential hazards; acquiring meteorological data of the high-incidence area of ​​potential hazards, and determining the image acquisition period that meets the preset image acquisition conditions based on the meteorological data; and during the image acquisition period, acquiring potential hazard images of the high-incidence area of ​​potential hazards in the distribution network line using image acquisition equipment.

[0167] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring the pixel resolution of the hazard image, and determining a mapping function based on the pixel resolution and the actual size parameters of the hazard equipment; wherein the mapping function is used to indicate the mapping relationship between the image pixels of the hazard image and the actual size parameters of the hazard equipment; and determining the feature data of the hazard equipment based on the mapping function and the hazard image.

[0168] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: using an edge detection algorithm to determine the image feature data of the equipment with potential hazards based on the image of the potential hazard; and using a mapping function and the image feature data to determine the feature data of the equipment with potential hazards.

[0169] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring the acquisition timestamp of the hazard image and the generation timestamp of the initial hazard labeling information; determining the time difference based on the acquisition timestamp and the generation timestamp; determining the timeliness threshold based on the initial hazard labeling information; and determining the validity information of the initial hazard labeling information based on the time difference and the timeliness threshold.

[0170] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: using validity information to filter out valid hazard labeling information from the initial hazard labeling information; matching the valid hazard labeling information with each segment of the distribution network line to obtain the target hazard labeling information.

[0171] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0172] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0173] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining hidden danger marking information of a network wiring line, characterized in that, The method includes: Obtain inspection information of the distribution network line, and based on the inspection information, use image acquisition equipment to obtain hazard images of high-risk areas of the distribution network line, the hazard images including hazard-prone equipment; Based on the hazard image, the feature data of the hazard device is determined, and based on the feature data and preset hazard feature data, the initial hazard labeling information of the distribution network line is determined; The validity information of the initial hazard labeling information is determined, and the target hazard labeling information of the distribution network line is determined based on the initial hazard labeling information and the validity information. The target hazard labeling information includes the hazard labeling information corresponding to each line segment of the distribution network line.

2. The method of claim 1, wherein, The step of acquiring hazard images of high-risk areas of the distribution network lines based on the inspection information using image acquisition equipment includes: Based on the inspection information, the location of potential hazards in the distribution network line is determined, and based on the location of potential hazards, the high-incidence area of ​​potential hazards in the distribution network line is determined. Acquire meteorological data of the high-risk areas and determine the image acquisition period that meets the preset image acquisition conditions based on the meteorological data; During the image acquisition period, the image acquisition device is used to acquire images of potential hazards in high-risk areas of the power distribution network line.

3. The method according to claim 1, characterized in that, The step of determining the feature data of the equipment with potential hazards based on the hazard image includes: Obtain the pixel resolution of the hazard image, and determine a mapping function based on the pixel resolution and the actual size parameters of the hazard device; The mapping function is used to indicate the mapping relationship between the image pixels of the potential hazard image and the actual size parameters of the potential hazard equipment; The characteristic data of the equipment with potential hazards are determined based on the mapping function and the hazard image.

4. The method according to claim 3, characterized in that, The step of determining the feature data of the equipment with potential hazards based on the mapping function and the hazard image includes: Using an edge detection algorithm, the image feature data of the equipment posing a hazard is determined based on the hazard image; The feature data of the potentially hazardous equipment are determined using the mapping function and the image feature data.

5. The method according to any one of claims 1 to 4, characterized in that, The information used to determine the validity of the initial hazard labeling information includes: Obtain the timestamp of the acquisition of the hazard image and the timestamp of the generation of the initial hazard labeling information; The time difference is determined based on the acquisition timestamp and the generation timestamp; A timeliness threshold is determined based on the initial hazard labeling information, and the validity information of the initial hazard labeling information is determined based on the time difference and the timeliness threshold.

6. The method according to any one of claims 1 to 4, characterized in that, The step of determining the target hazard labeling information of the distribution network line based on the initial hazard labeling information and the validity information includes: Using the validity information, valid hazard labeling information is filtered out from the initial hazard labeling information; The effective hazard labeling information is matched with each segment of the distribution network line to obtain the target hazard labeling information.

7. A device for determining hidden danger marking information of a distribution network line, characterized in that, The device includes: The acquisition module is used to acquire inspection information of the distribution network line, and based on the inspection information, to acquire hazard images of high-risk areas of the distribution network line using an image acquisition device, wherein the hazard images include hazard-prone equipment; The first determining module is used to determine the feature data of the hidden danger equipment based on the hidden danger image, and to determine the initial hidden danger labeling information of the distribution network line based on the feature data and preset hidden danger feature data; The second determining module is used to determine the validity information of the initial hidden danger labeling information, and to determine the target hidden danger labeling information of the distribution network line based on the initial hidden danger labeling information and the validity information. The target hidden danger labeling information includes the hidden danger labeling information corresponding to each line segment of the distribution network line.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images