Method, device and equipment for constructing global digital base map of power grid and medium

Abstract

The invention relates to the technical field of power grid monitoring, and discloses a power grid global digital base map construction method and device, equipment and a medium, and the method comprises the steps: obtaining high-resolution satellite image data based on a first time interval, and taking the high-resolution satellite image data as first satellite image data; preprocessing the first satellite image data to obtain second satellite image data; and generating a power grid global digital base map as a target digital base map according to the second satellite image data. Therefore, the power grid global digital base map can accurately display the power transmission line path of the power grid and the surrounding geographical environment of the power transmission line, and accurate support is provided for safety management of the power transmission line.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid monitoring and image processing, and in particular to a method, device, equipment and medium for constructing a global digital base map of a power grid. Background Art

[0002] Transmission lines are widely distributed and the geographical environment they cross is becoming increasingly complex. Traditional power inspection work is increasingly difficult to adapt to the new development trend of transmission lines. In order to solve this problem, drones are currently used to capture images to build a digital base map of the entire power grid. Due to the wide geographical area of ​​transmission lines, drone photography takes a long time. In addition, the geographical environment may change due to factors such as manpower and weather, so that the digital base map of the entire power grid cannot accurately display the transmission line path of the power grid and the surrounding geographical environment of the transmission line, and thus cannot provide accurate support for the safety management of the transmission line. Summary of the invention

[0003] Based on this, it is necessary to address the technical problem that the existing technology of using drone images to construct a global digital base map of the power grid cannot accurately display the transmission line paths of the power grid and the surrounding geographical environment of the transmission lines. A method, device, equipment and medium for constructing a global digital base map of the power grid are proposed.

[0004] In a first aspect, a method for constructing a global digital base map of a power grid is provided, the method comprising:

[0005] Acquire high-resolution satellite image data based on a first time interval as first satellite image data;

[0006] Preprocessing the first satellite image data to obtain second satellite image data;

[0007] A digital base map of the entire power grid is generated based on the second satellite image data as a target digital base map.

[0008] In a second aspect, a device for constructing a global digital base map of a power grid is provided, the device comprising:

[0009] A data acquisition module, used to acquire high-resolution satellite image data based on a first time interval as first satellite image data;

[0010] A preprocessing module, used for preprocessing the first satellite image data to obtain second satellite image data;

[0011] The digital base map generation module is used to generate a digital base map of the entire power grid based on the second satellite image data as a target digital base map.

[0012] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for constructing the above-mentioned global digital base map of the power grid when executing the computer program.

[0013] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for constructing the above-mentioned global digital base map of the power grid are implemented.

[0014] The construction method, device, equipment and medium of the global digital base map of the power grid of the present application obtains high-resolution satellite image data based on a first time interval as the first satellite image data, pre-processes the first satellite image data to obtain second satellite image data, and generates a global digital base map of the power grid based on the second satellite image data as the target digital base map. The generation of the global digital base map of the power grid based on high-resolution satellite image data is achieved. Since the time required to obtain high-resolution satellite image data is short, the cycle of updating the global digital base map of the power grid is shortened, so that the global digital base map of the power grid can more accurately display the transmission line path of the power grid and the surrounding geographical environment of the transmission line, thereby providing accurate support for the safety management of the transmission line. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] in:

[0017] Figure 1 A diagram of an application environment of a method for constructing a global digital base map of a power grid in one embodiment;

[0018] Figure 2 It is a flowchart of a method for constructing a global digital base map of a power grid in one embodiment;

[0019] Figure 3 It is a structural block diagram of a device for constructing a global digital base map of a power grid in one embodiment;

[0020] Figure 4 FIG. 4 is a structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The method for constructing a global digital base map of a power grid provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the client 110 communicates with the server 120 through the network.

[0023] Optionally, the server 120 can obtain high-resolution satellite image data through the client 110 based on a first time interval, and use the obtained high-resolution satellite image data as the first satellite image data. The server 120 is used to: pre-process the first satellite image data to obtain second satellite image data, and generate a global digital base map of the power grid based on the second satellite image data as the target digital base map. The generation of the global digital base map of the power grid based on high-resolution satellite image data is achieved. Since the time required to obtain high-resolution satellite image data is short, the cycle of updating the global digital base map of the power grid is shortened, so that the global digital base map of the power grid can more accurately display the transmission line path of the power grid and the surrounding geographical environment of the transmission line, thereby providing accurate support for the safety management of the transmission line.

[0024] Optionally, the server 120 obtains high-resolution satellite image data from a third-party application (e.g., a satellite data receiving platform for receiving impact data taken by a satellite) based on a first time interval, and uses the obtained high-resolution satellite image data as the first satellite image data. The server 120 is used to: pre-process the first satellite image data to obtain second satellite image data, and generate a global digital base map of the power grid based on the second satellite image data as the target digital base map.

[0025] The client 110 may be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server 120 may be implemented by an independent server or a server cluster consisting of multiple servers.

[0026] The present invention is described in detail below through specific embodiments.

[0027] See also Figure 2 As shown, Figure 2 A schematic flow chart of a method for constructing a global digital base map of a power grid provided by an embodiment of the present invention includes the following steps:

[0028] S1: acquiring high-resolution satellite image data based on a first time interval as first satellite image data;

[0029] The first time interval is a duration value. The first time interval is a constant.

[0030] High-resolution satellite image data is image data taken by high-resolution satellites. In the present application, high-resolution satellite image data is data obtained by photographing the transmission line path and the surrounding geographical environment of the transmission line using high-resolution satellites. High-resolution satellite image data has high resolution, clear details and accurate geographical information, so it can well describe the information of the transmission line path and the information of the surrounding geographical environment of the transmission line, wherein the information of the transmission line path includes the coordinates of the transmission line tower and the direction of the transmission line.

[0031] Specifically, the high-resolution satellite captures the designated capture range at a first time interval, and all high-resolution satellite image data obtained in each capture is used as the first satellite image data. The first satellite image data can be obtained from a preset storage space based on the first time interval, or from a third-party application (e.g., a satellite data receiving platform for receiving satellite image data) based on the first time interval.

[0032] S2: preprocessing the first satellite image data to obtain second satellite image data;

[0033] Specifically, the first satellite image data is preprocessed to ensure the accuracy and consistency of the image data.

[0034] The preprocessing operations include: one or more of geometric correction and radiation correction.

[0035] Radiation correction: Eliminate radiation errors caused by sensor response and atmospheric factors, so that the brightness value of the image can truly reflect the radiation characteristics of the object.

[0036] Geometric correction: Use information such as ground control points to correct the geometric deformation of satellite images so that they accurately match the actual geographic location.

[0037] S3: Generate a digital base map of the entire power grid based on the second satellite image data as a target digital base map.

[0038] Specifically, a contrast adjustment algorithm and a color enhancement algorithm are used to perform image enhancement on the second satellite image data to improve the visual effect of the image and highlight the features of important land objects. An image classification algorithm is used to classify the land objects in the image enhanced data (for example, different types of land objects such as poles, towers, buildings, roads, water bodies, vegetation, etc.), and corresponding annotation information is added to convert the outlines of important land objects and other information into vector data. The converted vector data is the global digital base map of the power grid (that is, the satellite image base map). The global digital base map of the power grid generated this time is named the target digital base map.

[0039] The core algorithm of contrast adjustment is to achieve the difference between light and dark areas by adjusting the pixel values ​​of the image. Contrast refers to the measurement of different brightness levels between the brightest white and the darkest black in the light and dark areas of an image. The larger the difference range, the greater the contrast, and the smaller the difference range, the smaller the contrast. The contrast adjustment algorithm of this application can be selected from the existing technology and will not be described here.

[0040] The contrast adjustment algorithm of the present application adopts a piecewise linear contrast adjustment algorithm or a CLAHE (Contrast-Limited Adaptive Histogram Equalization) algorithm. The piecewise linear contrast adjustment algorithm divides the grayscale range into segments and performs linear stretching to different degrees. The CLAHE algorithm performs adaptive contrast adjustment in local areas.

[0041] The color enhancement algorithm used in this application adopts the HSV (Hue, Saturation, Value) color space algorithm or the algorithm based on wavelet transform. The HSV color space algorithm achieves color enhancement by adjusting the hue (H), saturation (S) and brightness (V). The algorithm based on wavelet transform uses wavelet transform to process color information.

[0042] The global digital base map of the power grid can more accurately display the path of the transmission line (including the coordinates of the towers and the direction of the line) and the changes in the surrounding geographical environment of the transmission line.

[0043] This embodiment realizes the generation of a global digital base map of the power grid based on high-resolution satellite image data. Since the time required to obtain high-resolution satellite image data is short, the cycle of updating the global digital base map of the power grid is shortened, so that the global digital base map of the power grid can more accurately display the transmission line paths of the power grid and the surrounding geographical environment of the transmission lines, thereby providing accurate support for the safe management of the transmission lines.

[0044] In one embodiment, the step of generating a global digital base map of the power grid as a target digital base map according to the second satellite image data includes:

[0045] S31: Find a data block with a clear image from the second satellite image data as a first clear block, and find a data block with an unclear image from the second satellite image data as a first problem block;

[0046] Specifically, the second satellite image data can be divided into blocks based on a preset area division configuration, and the data corresponding to each block is taken as a data block; each data block obtained by the division is input into an image unclear prediction model to predict image unclearness, and the classification category corresponding to the vector element with the largest value obtained from the prediction is taken as the classification result of the data block. If the classification result of the data block is yes, the image is unclear, and the data block with the classification result of yes is taken as the first problem block; if the classification result of the data block is no, the image is clear, and the data block with the classification result of no is taken as the first clear block.

[0047] The preset area division configuration includes an area identifier and a coordinate range of the area. The area identifier can be data that uniquely identifies an area, such as an area name and an area ID.

[0048] The image unclear prediction model is a binary classification model. The model structure and model training method of the image unclear prediction model can be selected from the existing technology and will not be described in detail here.

[0049] S32: updating a clear image library according to the first clear block, and finding a data block from the clear image library according to the first problem block as a first substitute block;

[0050] Specifically, the first clear block is replaced and updated in a database in an image clear library having the same shooting range as the first clear block; a data block having the same shooting range as the first problem block is found from the image clear library, and the found data block is used as a first substitute block.

[0051] S33: using the first substitute block to replace the first problem block corresponding to the first substitute block in the second satellite image data, to obtain third satellite image data;

[0052] Specifically, the first substitute block is used to replace the data block corresponding to the first substitute block in the second satellite image data (that is, the first problem block). After all the first problem blocks are replaced, the second satellite image data is used as the third satellite image data.

[0053] S34: Generate a digital base map of the entire power grid according to the third satellite image data as a target digital base map.

[0054] Specifically, a contrast adjustment algorithm and a color enhancement algorithm are used to perform image enhancement on the third satellite image data to improve the visual effect of the image and highlight the features of important land objects. An image classification algorithm is used to classify land objects in the image (for example, different types of land objects such as poles, towers, buildings, roads, water bodies, vegetation, etc.), and corresponding annotation information is added. The outlines of important land objects and other information are converted into vector data. The converted vector data is the global digital base map of the power grid (that is, the satellite image base map). The global digital base map of the power grid generated this time is named the target digital base map.

[0055] It is understandable that due to weather reasons, some areas in the high-resolution satellite image data may be unclear, resulting in unclear areas in the global digital base map of the power grid. In order to solve this problem, this embodiment finds a data block from the image clarity library according to the first problem block as the first substitute block, and uses the first substitute block to replace the data block corresponding to the first substitute block in the second satellite image data (that is, the first problem block), so that the images of the third satellite image data used to generate the global digital base map of the power grid are clear, and then the target digital base map is clear, thereby providing accurate support for the safe management of transmission lines.

[0056] In one embodiment, after the step of generating a global digital base map of the power grid according to the third satellite image data as a target digital base map, the method further includes:

[0057] S361: Obtain current weather forecast data;

[0058] Specifically, current weather forecast data can be obtained from third-party applications.

[0059] The current weather forecast data is the weather forecast data for a preset period of time in the future starting from the current time.

[0060] S362: Determine a supplementary shooting time range of the first problem block according to the current weather forecast data and the position data of the first problem block;

[0061] Specifically, according to the location data of the first problem block, a time range suitable for shooting is found from the current weather forecast data, and the found time range is used as the supplementary shooting time range of the first problem block. The time range suitable for shooting refers to the time range of clear weather.

[0062] S363: Acquire high-resolution satellite image data according to the first problem block and the supplementary shooting time range as fourth satellite image data;

[0063] Optionally, a high-resolution satellite may be used to supplement the shooting range corresponding to the first problem block for any one of the starting value, middle value, and ending value of each supplementary shooting time range to obtain high-resolution satellite image data, and the high-resolution satellite image data obtained may be used as the fourth satellite image data.

[0064] Optionally, calculate the union of all the supplementary shooting time ranges corresponding to each first problem block, and use a high-resolution satellite to supplement the shooting ranges corresponding to all the first problem blocks according to any one of the starting value, middle value, and ending value in the union (that is, the time range) to obtain high-resolution satellite image data, and use the captured high-resolution satellite image data as the fourth satellite image data.

[0065] S364: determining a second substitute block corresponding to the first problem block according to the fourth satellite image data, and updating the clear image library according to the second substitute block, wherein the second substitute block is a data block with clear images;

[0066] Specifically, the fourth satellite image data is preprocessed, and a data block with the same shooting range as the first problem block is found from the preprocessed data, and the found data block is input into a binary classification model to predict unclear images, and the classification category corresponding to the vector element with the largest predicted value is used as the classification result of the data block; if the image of the data block with a classification result of "no" is clear, the data block with the classification result of "no" is used as the second substitute block corresponding to the first problem block; if the image of the data block with a classification result of "yes" is unclear, the data block with the classification result of "yes" is not used as the second substitute block. The second substitute block is used to replace and update the data block with the same shooting range as the second substitute block in the image clarity library.

[0067] S365: Use the second substitute block to update the target digital base map.

[0068] Specifically, a digital base map is generated according to the second substitute block, and based on the generated digital base map, a base map area corresponding to the second substitute block in the target digital base map is replaced and updated.

[0069] The method for generating a digital base map based on the second substitute block specifically includes: using a contrast adjustment algorithm and a color enhancement algorithm to perform image enhancement on the second substitute block to improve the visual effect of the image and highlight the characteristics of important land objects; using an image classification algorithm to classify land objects (for example, different types of land objects such as poles, buildings, roads, water bodies, vegetation, etc.) in the image enhanced data, and adding corresponding annotation information, converting information such as the outline of important land objects into vector data, and the converted vector data is the digital base map.

[0070] This embodiment first determines the supplementary shooting time range of the first problem block based on the current weather forecast data and the position data of the first problem block, and then obtains high-resolution satellite image data based on the first problem block and the supplementary shooting time range, extracts data blocks with clear images through the supplementary high-resolution satellite image data, and updates the target digital base map, thereby improving the clarity and real-time performance of the target digital base map; and obtaining high-resolution satellite image data based on the first problem block reduces the shooting range, shortens the shooting time, reduces the data processing time, and improves the accuracy of updating the target digital base map.

[0071] In one embodiment, the method further comprises:

[0072] S41: Acquire the three-dimensional laser radar data of the machine patrol based on the second time interval as the first laser radar data, wherein the first laser radar data represents the data of the transmission line itself, the tower body data and the transmission line environment data;

[0073] The second time interval is a duration value. The second time interval is a constant.

[0074] Optionally, the second time interval is smaller than the first time interval.

[0075] Specifically, a drone equipped with a laser three-dimensional radar scanning device is used to scan the transmission line to obtain the data of the transmission line itself, scan the tower body of the transmission line to obtain the tower body data, and scan the surrounding environment of the transmission line to obtain the transmission line environment data.

[0076] S42: preprocessing the first laser radar data to obtain second laser radar data;

[0077] Specifically, the first laser radar data is preprocessed, and the preprocessed data is used as the second laser radar data.

[0078] The method for preprocessing the first laser radar data includes: a combination of one or more of data filtering, coordinate transformation, data alignment, data segmentation, denoising, and data compression. Data filtering is to remove invalid data, noise data, etc. Coordinate transformation is to convert data into a desired coordinate system. Data alignment is to align data collected at different times or by different devices in space. Data segmentation is to divide a scene into different areas or objects. Denoising is to reduce noise interference in the data. Data compression is used to reduce the amount of data for easy storage and processing.

[0079] S43: Perform three-dimensional modeling based on the second laser radar data and the target digital base map to obtain a three-dimensional model of the entire power grid, wherein the target digital base map represents the transmission line path data and the transmission line geographical environment data.

[0080] First, the second laser radar data and the target digital base map are fused. The specific method of data fusion includes: accurately determining the relative position of the second laser radar data and the target digital base map through a geographic coordinate system or a specific reference mark, and obtaining the target laser radar data by modifying the second laser radar data for coordinate alignment; using a feature matching algorithm to find common feature points between the target laser radar data and the target digital base map, such as building corners, road intersections, etc., to improve the accuracy of fusion; converting and adjusting the data format of the target laser radar data and the target digital base map so that the target laser radar data and the target digital base map can be seamlessly connected and interacted.

[0081] Secondly, the second laser radar data (that is, the target laser radar data) after data fusion processing is processed by point cloud processing. The point cloud processing method includes: using a filtering algorithm to remove obvious noise points in the target laser radar data, such as a filtering method based on statistical characteristics or distance thresholds; for the target laser radar data after removing noise points, the point cloud data is classified according to different elements such as the ground, the tower body, the transmission line (that is, the line of the transmission line), buildings and vegetation for subsequent processing and modeling. The classification technology can be based on information such as the geometric characteristics and reflection intensity of the point cloud.

[0082] Then, mesh construction is performed based on the results of point cloud processing and the target digital base map. The specific method of mesh construction includes: constructing a triangular mesh or other suitable geometric mesh structure based on the results of point cloud processing. Mesh construction is one of the key steps in 3D modeling, which converts discrete point cloud data into a continuous geometric surface. Commonly used mesh construction methods include De l aunay triangulation, regular triangulation, etc.

[0083] Finally, texture mapping is performed, which specifically includes: using the image information of the target digital base map to accurately map the texture onto the surface of the grid. Texture mapping can give the 3D model a realistic appearance and texture. Texture mapping technology can be achieved through methods such as image registration and projection mapping. In the mapping process, factors such as texture continuity, directionality and resolution need to be considered to ensure the realism and consistency of the mapping effect.

[0084] The three-dimensional model obtained by texture mapping is used as the full-domain real-scene three-dimensional model of the power grid.

[0085] This embodiment obtains a three-dimensional model of the entire power grid by performing three-dimensional modeling based on the second lidar data and the target digital base map, and the target digital base map can more accurately display the transmission line paths of the power grid and the surrounding geographical environment of the transmission lines, so that the three-dimensional model of the entire power grid can more accurately display the three-dimensional model of the transmission line paths of the power grid and the surrounding geographical environment of the transmission lines, thereby providing accurate support for the safety management of the transmission lines.

[0086] In one embodiment, the step of preprocessing the first laser radar data to obtain the second laser radar data includes:

[0087] S421: preprocessing the first laser radar data to obtain laser radar data to be analyzed;

[0088] Specifically, the first laser radar data is preprocessed, and the preprocessed data is used as the laser radar data to be analyzed.

[0089] S422: Finding a data block with an abnormality from the laser radar data to be analyzed as a second problem block;

[0090] Specifically, firstly, based on the preset area division configuration, the laser radar data to be analyzed is divided into blocks, and the data blocks obtained by the division are input into the anomaly prediction model for anomaly classification prediction, and the classification category corresponding to the vector element with the largest predicted value is used as the classification result of the data block. If the classification result is yes, the data block has an anomaly, so the data block with the classification result is yes as the second problem block, and if the classification result is no, the data block has no anomaly, so the data block with the classification result is not used as the second problem block.

[0091] The anomaly prediction model is a binary classification model. The model structure and model training method of the anomaly prediction model can be selected from the existing technology and will not be described here.

[0092] S423: Acquire the aircraft patrol 3D laser radar data according to the second question block as the third laser radar data;

[0093] Specifically, a drone equipped with a three-dimensional laser radar scanning device is used to rescan the scanning range corresponding to the second problem block, and the scanned data (also called drone three-dimensional laser radar data) is used as the third laser radar data.

[0094] S424: Finding a data block corresponding to the second problematic block from the third laser radar data as an initial substitute block, wherein the initial substitute block is a data block without any abnormality;

[0095] Specifically, find out the data block corresponding to the second problem block from the third lidar data, input the data block into the anomaly prediction model for anomaly classification prediction, and use the classification category corresponding to the vector element with the largest predicted value as the classification result of the data block. If the classification result is no, use the data block as the initial substitute block. If the classification result is yes, discard the current third lidar data. If the classification result is yes, jump to step S423 and execute again, or end the processing of the current second problem block and obtain the next second problem block to execute step S423.

[0096] That is, steps S423 and S424 are executed for each second question block.

[0097] S425: preprocessing the initial substitute block to obtain a second substitute block;

[0098] Specifically, the initial substitute block is preprocessed, and the preprocessed data is used as the second substitute block.

[0099] The method for preprocessing the initial substitute block includes: one or more combinations of data filtering, coordinate conversion, data registration, data segmentation, denoising, and data compression.

[0100] S426: Use each of the second substitute blocks to replace and update the second problem block corresponding to the second substitute block in the laser radar data to be analyzed, so as to obtain the second laser radar data.

[0101] Specifically, each of the second substitute blocks is used to replace and update the data block corresponding to the second substitute block in the lidar data to be analyzed (that is, the second problem block). When all the second substitute blocks are updated to the lidar data to be analyzed, the lidar data to be analyzed is used as the second lidar data.

[0102] This embodiment rescans the scanning range corresponding to the abnormal data blocks in the laser radar data to be analyzed to obtain data blocks without abnormalities, and updates the data blocks with abnormalities in the laser radar data to be analyzed with the data blocks without abnormalities, thereby improving the accuracy of the second laser radar data and further improving the accuracy of the full-domain real-life three-dimensional model of the power grid.

[0103] In one embodiment, after the step of performing three-dimensional modeling according to the second laser radar data and the target digital base map to obtain a three-dimensional model of the entire power grid, the method further includes:

[0104] S51: Acquire the global real-scene three-dimensional model of the power grid, the target digital base map and the second laser radar data according to a preset first time window to obtain a first data packet;

[0105] Specifically, the global real-life three-dimensional model of the power grid, the target digital base map and the second lidar data are acquired according to a preset first time window, so as to acquire the global real-life three-dimensional model of the power grid, the target digital base map and the second lidar data within a time period, and all acquired global real-life three-dimensional model of the power grid, the target digital base map and the second lidar data are taken as the first data packet.

[0106] S52: using a preset area division configuration to divide the first data packet into regions to obtain first data sub-packets corresponding to each region;

[0107] Specifically, a preset area division configuration is used to divide the first data packet into regions, and the data corresponding to an area in the global real-life three-dimensional model of the power grid is used as a first data sub-packet, the data corresponding to an area in the target digital base map is used as a first data sub-packet, and the data corresponding to an area in the second lidar data is used as a first data sub-packet.

[0108] S53: Inputting each of the first data sub-packets corresponding to the designated area into a first classification model corresponding to the designated area to perform classification prediction of regional faults, and obtaining a first prediction result corresponding to the designated area, wherein the designated area is any one of the areas;

[0109] Specifically, the first data subpackets corresponding to the designated area are spliced ​​and input into the first classification model corresponding to the designated area to perform classification prediction of regional faults, and the classification category corresponding to the vector element with the largest value obtained from the prediction is used as the first prediction result corresponding to the designated area.

[0110] The first classification model is a two-classification model. The model structure and model training method of the first classification model can be selected from the existing technology and will not be described in detail here.

[0111] The value of the first prediction result is fault or normal.

[0112] It can be understood that by executing step S53 for each region, the first prediction result corresponding to each region can be obtained.

[0113] S54: extracting, from each of the first data sub-packets corresponding to the area where the first prediction result is a fault, the first data sub-packet corresponding to the global real-life three-dimensional model of the power grid and having the latest data collection time, the first data sub-packet corresponding to the target digital base map and having the latest data collection time, and the first data sub-packet corresponding to the second laser radar data and having the latest data collection time as a sub-packet set to be analyzed;

[0114] S55: inputting the sub-packet set to be analyzed into a pre-trained second classification model to perform fault classification prediction of pixel points to obtain a second prediction result;

[0115] Specifically, the sub-package set to be analyzed is input into the pre-trained second classification model to perform fault classification prediction for each pixel point. For the prediction value corresponding to each pixel point, if the prediction value is greater than a preset threshold, the pixel point corresponding to the prediction value is marked as a fault mark; if the prediction value is less than or equal to the preset threshold, the pixel point corresponding to the prediction value is marked as a normal mark.

[0116] The preset threshold is a preset constant. The setting of the preset threshold can be determined based on limited experiments and will not be described in detail here.

[0117] Optionally, the fault flag is 0 and the normal flag is 1, or the fault flag is 1 and the normal flag is 0.

[0118] The second classification model is a multi-classification model. Each predicted value of the second classification model corresponds to a pixel point.

[0119] S56: According to the second prediction result, extract the data block corresponding to the fault point from the first data sub-packet of the sub-packet set to be analyzed corresponding to the global real-life three-dimensional model of the power grid as the fault block corresponding to the sub-packet set to be analyzed.

[0120] Specifically, from the first data sub-packet of the sub-packet set to be analyzed corresponding to the global real-life three-dimensional model of the power grid, the data corresponding to the pixel points marked as faults in the second prediction result are extracted, and all the extracted data are used as the fault blocks corresponding to the sub-packet set to be analyzed.

[0121] This embodiment determines the fault block based on the global real-life three-dimensional model of the power grid within the first time window, the target digital base map and the second lidar data, thereby automatically determining the specific data block where the fault occurs, providing a basis for rapid troubleshooting.

[0122] In one embodiment, after the step of performing three-dimensional modeling according to the second laser radar data and the target digital base map to obtain a three-dimensional model of the entire power grid, the method further includes:

[0123] S61: Acquire the global real-scene three-dimensional model of the power grid, the target digital base map and the second laser radar data according to a preset second time window to obtain a second data packet;

[0124] Specifically, the global real-life three-dimensional model of the power grid, the target digital base map and the second lidar data are obtained according to a preset second time window, so as to obtain the global real-life three-dimensional model of the power grid, the target digital base map and the second lidar data within a time period, and all the obtained global real-life three-dimensional model of the power grid, the target digital base map and the second lidar data are used as a second data packet.

[0125] S62: using a preset area division configuration to divide the second data packet into regions to obtain second data sub-packets corresponding to each region;

[0126] Specifically, the preset area division configuration is used to divide the second data packet into regions, and the data corresponding to an area in the global real-life three-dimensional model of the power grid is used as a second data sub-packet, the data corresponding to an area in the target digital base map is used as a second data sub-packet, and the data corresponding to an area in the second lidar data is used as a second data sub-packet.

[0127] S63: inputting each of the second data sub-packets corresponding to the same region into a pre-trained third classification model to perform classification prediction of external force damage to the region, and obtaining a third prediction result;

[0128] Specifically, each of the second data sub-packets corresponding to the same area is spliced ​​and input into a pre-trained third classification model to perform classification prediction of external force damage to the area, and the classification category corresponding to the vector element with the largest value obtained from the prediction is used as the third prediction result.

[0129] The third classification model is a two-classification model. The model structure and model training method of the third classification model can be selected from the existing technology and will not be described in detail here.

[0130] The value of the third prediction result is the presence of external force damage or the absence of external force damage.

[0131] S64: taking the region where the third prediction result indicates that there is external force damage as a region to be processed;

[0132] S65: Generate an alarm prompt according to the area to be processed.

[0133] Specifically, based on the preset alarm generation rules, an alarm prompt is generated according to the area to be processed.

[0134] The warning prompt can be a signal or a combination of prompt information and prompt mode configuration.

[0135] This embodiment determines the area where external force damage exists based on the full-domain real-life three-dimensional model of the power grid within the second time window, the target digital base map and the second lidar data, and generates an alarm prompt for the area where external force damage exists, thereby realizing automatic determination of the specific area where external force damage occurs.

[0136] See also Figure 3 As shown, in one embodiment, a device for constructing a global digital base map of a power grid is provided, the device comprising:

[0137] The data acquisition module 801 is used to acquire high-resolution satellite image data based on a first time interval as first satellite image data;

[0138] A preprocessing module 802 is used to preprocess the first satellite image data to obtain second satellite image data;

[0139] The digital base map generation module 803 is used to generate a digital base map of the entire power grid according to the second satellite image data as a target digital base map.

[0140] This embodiment realizes the generation of a global digital base map of the power grid based on high-resolution satellite image data. Since the time required to obtain high-resolution satellite image data is short, the cycle of updating the global digital base map of the power grid is shortened, so that the global digital base map of the power grid can more accurately display the transmission line paths of the power grid and the surrounding geographical environment of the transmission lines, thereby providing accurate support for the safe management of the transmission lines.

[0141] In one embodiment, the step of generating a global digital base map of the power grid according to the second satellite image data as a target digital base map in the digital base map generating module 803 includes:

[0142] Find a data block with a clear image from the second satellite image data as a first clear block, and find a data block with an unclear image from the second satellite image data as a first problem block;

[0143] updating a clear image library according to the first clear block, and finding a data block from the clear image library according to the first problem block as a first substitute block;

[0144] Using the first substitute block, replacing the first problem block corresponding to the first substitute block in the second satellite image data, to obtain third satellite image data;

[0145] A digital base map of the entire power grid is generated according to the third satellite image data as a target digital base map.

[0146] In one embodiment, after the step of generating a global digital base map of the power grid according to the third satellite image data as a target digital base map, the digital base map generating module 803 further includes:

[0147] Get current weather forecast data;

[0148] Determining a supplementary shooting time range of the first problem block according to the current weather forecast data and the position data of the first problem block;

[0149] Acquire high-resolution satellite image data according to the first problem block and the supplementary shooting time range as fourth satellite image data;

[0150] Determine a second substitute block corresponding to the first problem block according to the fourth satellite image data, and update the clear image library according to the second substitute block, wherein the second substitute block is a data block with clear images;

[0151] The target digital base map is updated using the second substitute block.

[0152] In one embodiment, the device further comprises: a three-dimensional modeling module, wherein the three-dimensional modeling module is used to:

[0153] Acquire the three-dimensional laser radar data based on the second time interval as the first laser radar data, wherein the first laser radar data represents the data of the transmission line itself, the tower body data and the transmission line environment data;

[0154] Preprocessing the first laser radar data to obtain second laser radar data;

[0155] Three-dimensional modeling is performed based on the second laser radar data and the target digital base map to obtain a three-dimensional model of the entire power grid in real life, wherein the target digital base map represents the transmission line path data and the transmission line geographical environment data.

[0156] In one embodiment, the step of preprocessing the first laser radar data to obtain the second laser radar data in the three-dimensional modeling module includes:

[0157] Preprocessing the first laser radar data as laser radar data to be analyzed;

[0158] Finding a data block with an abnormality from the laser radar data to be analyzed as a second problem block;

[0159] According to the second question block, obtain the three-dimensional laser radar data of the aircraft patrol as the third laser radar data;

[0160] Finding a data block corresponding to the second problem block from the third laser radar data as an initial substitute block, wherein the initial substitute block is a data block without any abnormality;

[0161] Preprocessing the initial substitute block to obtain a second substitute block;

[0162] Each of the second substitute blocks is used to replace and update the second problem block corresponding to the second substitute block in the laser radar data to be analyzed, so as to obtain the second laser radar data.

[0163] In one embodiment, the device further comprises: a fault analysis module, wherein the fault analysis module is configured to:

[0164] Acquire the global real-scene three-dimensional model of the power grid, the target digital base map and the second laser radar data according to a preset first time window to obtain a first data packet;

[0165] Using a preset area division configuration, the first data packet is divided into regions to obtain first data sub-packets corresponding to each region;

[0166] Input each of the first data sub-packets corresponding to a designated area into a first classification model corresponding to the designated area to perform classification prediction of regional faults, and obtain a first prediction result corresponding to the designated area, wherein the designated area is any one of the areas;

[0167] From each of the first data sub-packets corresponding to the area where the first prediction result is a fault, extract the first data sub-packet corresponding to the global real-life three-dimensional model of the power grid and having the latest data collection time, the first data sub-packet corresponding to the target digital base map and having the latest data collection time, and the first data sub-packet corresponding to the second laser radar data and having the latest data collection time as a sub-packet set to be analyzed;

[0168] Inputting the sub-packet set to be analyzed into a pre-trained second classification model to perform fault classification prediction of pixel points to obtain a second prediction result;

[0169] According to the second prediction result, a data block corresponding to a fault point is extracted from the first data sub-packet of the sub-packet set to be analyzed corresponding to the global real-life three-dimensional model of the power grid as a fault block corresponding to the sub-packet set to be analyzed.

[0170] In one embodiment, the device further comprises: an external force damage analysis module, wherein the external force damage analysis module is used to:

[0171] Acquire the global real-scene three-dimensional model of the power grid, the target digital base map and the second laser radar data according to a preset second time window to obtain a second data packet;

[0172] Using a preset area division configuration, the second data packet is divided into areas to obtain each second data sub-packet corresponding to each area;

[0173] Inputting each of the second data sub-packets corresponding to the same area into a pre-trained third classification model to perform classification prediction of external force damage to the area, and obtaining a third prediction result;

[0174] The area where the third prediction result indicates that there is external force damage is used as the area to be processed;

[0175] Generate an alarm prompt based on the area to be processed.

[0176] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the functions or steps on the service side of a method for constructing a global digital base map of a power grid are realized.

[0177] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0178] Acquire high-resolution satellite image data based on a first time interval as first satellite image data;

[0179] Preprocessing the first satellite image data to obtain second satellite image data;

[0180] A digital base map of the entire power grid is generated based on the second satellite image data as a target digital base map.

[0181] This embodiment realizes the generation of a global digital base map of the power grid based on high-resolution satellite image data. Since the time required to obtain high-resolution satellite image data is short, the cycle of updating the global digital base map of the power grid is shortened, so that the global digital base map of the power grid can more accurately display the transmission line paths of the power grid and the surrounding geographical environment of the transmission lines, thereby providing accurate support for the safe management of the transmission lines.

[0182] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0183] Acquire high-resolution satellite image data based on a first time interval as first satellite image data;

[0184] Preprocessing the first satellite image data to obtain second satellite image data;

[0185] A digital base map of the entire power grid is generated based on the second satellite image data as a target digital base map.

[0186] This embodiment realizes the generation of a global digital base map of the power grid based on high-resolution satellite image data. Since the time required to obtain high-resolution satellite image data is short, the cycle of updating the global digital base map of the power grid is shortened, so that the global digital base map of the power grid can more accurately display the transmission line paths of the power grid and the surrounding geographical environment of the transmission lines, thereby providing accurate support for the safe management of the transmission lines.

[0187] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0188] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0189] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0190] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for constructing a global digital base map of a power grid, the method comprising: Acquire high-resolution satellite image data based on a first time interval as first satellite image data; Preprocessing the first satellite image data to obtain second satellite image data; A digital base map of the entire power grid is generated based on the second satellite image data as a target digital base map.

2. The method for constructing a global digital base map of a power grid according to claim 1, characterized in that: The step of generating a global digital base map of the power grid as a target digital base map according to the second satellite image data includes: Find a data block with a clear image from the second satellite image data as a first clear block, and find a data block with an unclear image from the second satellite image data as a first problem block; updating a clear image library according to the first clear block, and finding a data block from the clear image library according to the first problem block as a first substitute block; Using the first substitute block, replacing the first problem block corresponding to the first substitute block in the second satellite image data, to obtain third satellite image data; A global digital base map of the power grid is generated according to the third satellite image data as a target digital base map.

3. The method for constructing a global digital base map of a power grid according to claim 2, characterized in that: After the step of generating a global digital base map of the power grid according to the third satellite image data as a target digital base map, the method further includes: Get current weather forecast data; Determining a supplementary shooting time range of the first problem block according to the current weather forecast data and the position data of the first problem block; Acquire high-resolution satellite image data according to the first problem block and the supplementary shooting time range as fourth satellite image data; Determine a second substitute block corresponding to the first problem block according to the fourth satellite image data, and update the clear image library according to the second substitute block, wherein the second substitute block is a data block with clear images; The target digital base map is updated using the second substitute block.

4. The method for constructing a global digital base map of a power grid according to claim 1, characterized in that: The method further comprises: Acquire the three-dimensional laser radar data based on the second time interval as the first laser radar data, wherein the first laser radar data represents the data of the transmission line itself, the tower body data and the transmission line environment data; Preprocessing the first laser radar data to obtain second laser radar data; Three-dimensional modeling is performed based on the second laser radar data and the target digital base map to obtain a three-dimensional model of the entire power grid in real life, wherein the target digital base map represents the transmission line path data and the transmission line geographical environment data.

5. The method for constructing a global digital base map of a power grid according to claim 4, characterized in that: The step of preprocessing the first laser radar data to obtain the second laser radar data includes: Preprocessing the first laser radar data as laser radar data to be analyzed; Finding a data block with an abnormality from the laser radar data to be analyzed as a second problem block; According to the second question block, obtain the three-dimensional laser radar data of the aircraft patrol as the third laser radar data; Finding a data block corresponding to the second problem block from the third laser radar data as an initial substitute block, wherein the initial substitute block is a data block without any abnormality; Preprocessing the initial substitute block to obtain a second substitute block; Each of the second substitute blocks is used to replace and update the second problem block corresponding to the second substitute block in the laser radar data to be analyzed, so as to obtain the second laser radar data.

6. The method for constructing a global digital base map of a power grid according to claim 4, characterized in that: After the step of performing three-dimensional modeling according to the second laser radar data and the target digital base map to obtain a three-dimensional model of the entire power grid real scene, the method further includes: Acquire the global real-scene three-dimensional model of the power grid, the target digital base map and the second laser radar data according to a preset first time window to obtain a first data packet; Using a preset area division configuration, the first data packet is divided into regions to obtain first data sub-packets corresponding to each region; Input each of the first data sub-packets corresponding to a designated area into a first classification model corresponding to the designated area to perform classification prediction of regional faults, and obtain a first prediction result corresponding to the designated area, wherein the designated area is any one of the areas; From each of the first data sub-packets corresponding to the area where the first prediction result is a fault, extract the first data sub-packet corresponding to the global real-life three-dimensional model of the power grid and having the latest data collection time, the first data sub-packet corresponding to the target digital base map and having the latest data collection time, and the first data sub-packet corresponding to the second laser radar data and having the latest data collection time as a sub-packet set to be analyzed; Inputting the sub-packet set to be analyzed into a pre-trained second classification model to perform fault classification prediction of pixel points to obtain a second prediction result; According to the second prediction result, a data block corresponding to a fault point is extracted from the first data sub-packet of the sub-packet set to be analyzed corresponding to the global real-life three-dimensional model of the power grid as a fault block corresponding to the sub-packet set to be analyzed.

7. The method for constructing a global digital base map of a power grid according to claim 4, characterized in that: After the step of performing three-dimensional modeling according to the second laser radar data and the target digital base map to obtain a three-dimensional model of the entire power grid, the method further includes: Acquire the global real-life three-dimensional model of the power grid, the target digital base map, and the second laser radar data according to a preset second time window to obtain a second data packet; Using a preset area division configuration, the second data packet is divided into areas to obtain each second data sub-packet corresponding to each area; Inputting each of the second data sub-packets corresponding to the same area into a pre-trained third classification model to perform classification prediction of external force damage to the area, and obtaining a third prediction result; The area where the third prediction result indicates that there is external force damage is used as the area to be processed; Generate an alarm prompt according to the area to be processed.

8. A device for constructing a global digital base map of a power grid, characterized in that: The device comprises: A data acquisition module, used to acquire high-resolution satellite image data based on a first time interval as first satellite image data; A preprocessing module, used for preprocessing the first satellite image data to obtain second satellite image data; The digital base map generation module is used to generate a digital base map of the entire power grid based on the second satellite image data as a target digital base map.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for constructing a global digital base map of a power grid as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for constructing a global digital base map of a power grid as claimed in any one of claims 1 to 7 are implemented.

Images