An intelligent detection method for a power grid framework and a satellite image processing system

Abstract

The present invention relates to the technical field of intelligent operation and maintenance of transmission lines, and particularly to an intelligent detection method for a power grid framework and a satellite image processing system. The method includes: detecting the power grid framework according to the collected multi-source monitoring information, obtaining a number of power grid structure information, establishing a power grid topology model, and performing connection analysis on the power grid topology model to obtain a power grid topology analysis result. By collecting the coordinate information of the power grid framework and the power grid topology analysis result, spatial distribution analysis is performed on the power grid framework to obtain power grid coverage data. The several power grid structure information, power grid topology analysis result, and power grid coverage data are subjected to data visualization to generate a power grid framework detection result. Through the present invention, the problem of easy omission of detection in weak edge regions in the identification of power grid frameworks in large-scale and high-complexity scenarios is effectively solved, the efficiency and accuracy of power grid framework identification are significantly improved, and the cost and time of manual inspection are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent operation and inspection of power transmission lines, and in particular to an intelligent detection method for a power grid and a satellite image processing system. Background Art

[0002] With the continuous expansion of the scale of power systems and the continuous improvement of their intelligence levels, the monitoring and efficient management of power grids have become core needs for the development of the power industry. Satellite remote sensing technology has gradually become an important tool for power grid monitoring and analysis due to its advantages such as wide coverage, multi-source data acquisition cycle, and high spatial resolution. Especially in complex terrain and remote areas, satellite remote sensing technology can provide large-scale, high-precision power grid infrastructure information, providing strong data support for power grid planning, operation and maintenance, and disaster warning.

[0003] However, existing intelligent detection methods for power grids still have significant shortcomings in multi-source data fusion, transmission line continuity optimization, dynamic assessment of substation layout, and tower feature extraction. Traditional solutions mostly rely on a single remote sensing data source, making it difficult to fully capture the multi-dimensional characteristics of the power grid, resulting in limited recognition accuracy. In addition, existing methods fail to effectively integrate multi-source remote sensing data with historical grid operation data in power grid topology modeling and spatial distribution analysis, resulting in a low match between the model and the actual power grid structure. In particular, there are obvious defects in key links such as transmission line continuity optimization, substation layout assessment, and tower feature extraction.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0005] The present invention provides a cardiac stress response regulation method based on data analysis, which can effectively solve the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is:

[0007] An intelligent detection method for a power grid, the method comprising:

[0008] Collecting multi-source monitoring information, detecting the power grid frame based on the multi-source monitoring information, and obtaining some power grid structure information;

[0009] Establishing a power grid topology model based on the power grid structure information, and performing connection analysis on the power grid topology model to obtain a power grid topology analysis result;

[0010] Collect the grid network frame coordinate information, and perform spatial distribution analysis on the grid network frame according to the grid network frame coordinate information and the grid topology analysis result to obtain grid coverage data;

[0011] Visualize a number of the grid structure information, grid topology analysis results, and grid coverage data to generate grid network frame detection results.

[0012] Further, performing spatial distribution analysis on the grid network frame according to the grid network frame coordinate information and the grid topology analysis result includes:

[0013] Respectively obtain the geographical coordinates of transmission lines, the geographical coordinates of poles and towers, and the geographical coordinates of substations according to the grid network frame coordinate information;

[0014] Fit the spatial path of the transmission line according to the geographical coordinates of the transmission line, and calculate the distribution density of poles and towers according to the geographical coordinates of the poles and towers;

[0015] Obtain regional load center data according to the geographical information system, perform spatial overlay analysis on the geographical coordinates of the substations and the regional load center data, and obtain the substation layout evaluation result;

[0016] Based on the spatial path of the transmission line, the distribution density of poles and towers, and the substation layout evaluation result, draw the spatial coverage range of the grid network frame.

[0017] Further, performing spatial overlay analysis on the geographical coordinates of the substations and the regional load center data to obtain the substation layout evaluation result includes:

[0018] Obtain the coordinates of a number of regional load centers and load demand data according to the geographical information system;

[0019] Match each of the load center coordinates with a number of the geographical coordinates of the substations respectively to obtain a load-substation mapping relationship, calculate the spatial straight-line distance according to the load-substation mapping relationship, and the load-substation mapping relationship represents the geographical coordinates of the substation with the shortest distance to each of the load center coordinates;

[0020] Collect the capacity of each substation respectively, determine the load demand data of the corresponding load center according to the load-substation mapping relationship and the substation capacity, and calculate the substation capacity matching degree;

[0021] Set a spatial threshold and a capacity threshold according to the historical power system operation data, and evaluate the substation layout according to the spatial straight-line distance and the substation capacity matching degree to obtain the substation layout evaluation result.

[0022] Further, detecting the grid network frame according to the multi-source monitoring information includes:

[0023] Convert the remote sensing image in the multi-source monitoring information into grayscale to obtain a grayscale image, and perform noise reduction processing on the grayscale image;

[0024] Calculate the gradient magnitude and gradient direction of the image based on the denoised grayscale image, and identify potential edge regions according to the gradient magnitude and gradient direction;

[0025] Based on the potential edge region, perform pixel point screening along the gradient direction to obtain a refined edge region;

[0026] Set a gradient magnitude threshold based on historical power system operation data, and perform threshold segmentation according to the gradient magnitude threshold to obtain strong edge regions and weak edge regions;

[0027] Detect whether the pixel points in the weak edge region are connected to the strong edge region. If so, retain the weak edge region; otherwise, remove the weak edge region, and connect the weak edge region to the strong edge region to obtain a continuous transmission line.

[0028] Furthermore, obtain a continuous transmission line and optimize the generated continuous transmission line, including:

[0029] Perform binary segmentation on the continuous transmission line based on a deep learning algorithm to obtain a binary segmentation image;

[0030] Extract historical transmission line features according to the historical power system operation data, and construct a linear kernel according to the historical transmission line features;

[0031] Perform edge filling and noise reduction processing on the binary segmentation image according to the linear kernel, and perform linear fitting on the binary segmentation image after the edge filling and noise reduction processing to optimize the continuous transmission line.

[0032] Furthermore, detect the power grid network according to the multi-source monitoring information, including:

[0033] Extract the pole tower edge contour according to the multi-source monitoring information, and calculate the pole tower geometric features;

[0034] Determine the contour local feature points according to the pole tower edge contour, and perform smoothing and correction on the pole tower edge contour based on the contour local feature points to obtain the pole tower area contour;

[0035] Obtain the spatial distribution of pixel gray values according to the pole tower area contour, and extract several local pole tower texture features respectively;

[0036] Perform feature enhancement on several local pole tower texture features to generate a texture response map;

[0037] Obtain pole tower information based on the geometric features of the pole tower, local pole tower texture features, and texture response map.

[0038] Furthermore, detect the power grid network based on the multi-source monitoring information, including:

[0039] Extract the substation area image according to the multi-source monitoring information, locate the substation equipment in the substation based on the substation area image, and obtain a number of substation bounding boxes;

[0040] Extract and classify the overall features of the substation in the substation area image to generate a probability distribution map of the functional areas of the substation;

[0041] Perform pixel-level classification on the substation area image to obtain a number of substation equipment mask images;

[0042] Determine the boundary range of the substation based on the substation bounding box, probability distribution map of the functional areas, and substation equipment mask image.

[0043] Furthermore, establish a power grid topology model based on a number of the power grid structure information, including:

[0044] Extract transmission line information and power grid facility information according to a number of the power grid structure information;

[0045] Determine power grid nodes and power grid paths respectively according to the power grid facility information and transmission line information, create an adjacency matrix according to the number of the power grid nodes, and each row and column of the adjacency matrix corresponds to one of the power grid nodes;

[0046] Traverse the power grid paths corresponding to the transmission line information, determine the power grid nodes connected by the power grid paths, represent the connected power grid nodes as 1, and the rest as 0, and fill them into the adjacency matrix;

[0047] Determine the connection relationship of the power grid facilities according to the adjacency matrix, and add power grid configuration attributes respectively to construct a power grid topology model.

[0048] A satellite image processing system, the system includes:

[0049] A power grid structure extraction module, which collects multi-source monitoring information, detects the power grid network according to the multi-source monitoring information, and obtains a number of power grid structure information;

[0050] A power grid topology analysis module, which establishes a power grid topology model according to a number of the power grid structure information, and performs connection analysis on the power grid topology model to obtain a power grid topology analysis result;

[0051] The power grid spatial analysis module collects the coordinate information of the power grid network framework, and conducts spatial distribution analysis on the power grid network framework according to the coordinate information of the power grid network framework and the power grid topology analysis result, so as to obtain power grid coverage data;

[0052] The power grid visualization display module visualizes the data of a number of the power grid structure information, the power grid topology analysis result and the power grid coverage data, and generates a power grid network framework detection result.

[0053] Further, the power grid spatial analysis module includes:

[0054] The power grid coordinate extraction unit respectively obtains the geographical coordinates of transmission lines, the geographical coordinates of poles and towers, and the geographical coordinates of substations according to the coordinate information of the power grid network framework;

[0055] The transmission line path modeling unit fits and generates the spatial path of the transmission line according to the geographical coordinates of the transmission line, and calculates the pole and tower distribution density according to the geographical coordinates of the poles and towers;

[0056] The substation layout analysis unit obtains the regional load center data according to the geographical information system, and conducts spatial overlay analysis on the geographical coordinates of the substations and the regional load center data to obtain the substation layout evaluation result;

[0057] The power grid coverage analysis unit draws the spatial coverage range of the power grid network framework based on the spatial path of the transmission line, the pole and tower distribution density and the substation layout evaluation result.

[0058] Through the technical solution of the present invention, the following technical effects can be achieved:

[0059] It effectively solves the problem that weak edge areas are prone to be missed in the monitoring of the power grid network framework in large-scale and high-complexity scenarios. Through satellite remote sensing technology, it can quickly and widely obtain the spatial distribution information of the power grid network framework. Combined with the automatic recognition algorithm, it significantly improves the efficiency and accuracy of power grid network framework recognition, and reduces the cost and time of manual inspection; By verifying the identified power grid network framework structure with the account books such as the power line distribution map, through the accurate recognition and spatial information management of the power grid network framework, it provides a data basis for the planning, construction and operation and maintenance of the smart grid, and helps the digital transformation and intelligent upgrading of the power system.

[0060] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically given below. Description of the Drawings

[0061] To more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0062] Figure 1 It is a schematic flowchart of an intelligent detection method for a power grid network framework;

[0063] Figure 2 It is a schematic flowchart of spatial distribution analysis for a power grid network framework;

[0064] Figure 3 It is a schematic flowchart of obtaining the evaluation result of substation layout;

[0065] Figure 4 It is an architecture diagram of spatial distribution analysis for a power grid network framework;

[0066] Figure 5 It is an architecture diagram of a satellite image processing system. Specific embodiments

[0067] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments.

[0068] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0069] Embodiment 1;

[0070] As Figure 1 shown, the present application provides an intelligent detection method for a power grid network framework. The method includes:

[0071] S100: Collect multi-source monitoring information, detect the power grid network framework according to the multi-source monitoring information, and obtain a number of power grid structure information;

[0072] S200: Establish a power grid topology model according to the number of power grid structure information, and perform connection analysis on the power grid topology model to obtain a power grid topology analysis result;

[0073] S300: Collect the grid network coordinate information, conduct a spatial distribution analysis of the grid network based on the grid network coordinate information and the grid topology analysis results, and obtain the grid coverage data;

[0074] S400: Visualize a number of grid structure information, grid topology analysis results, and grid coverage data to generate the grid network detection results.

[0075] Specifically, first, by collecting multi-source monitoring information, such as grid operation status information, equipment monitoring data, relevant data on the environment and meteorology, etc., to ensure comprehensive coverage of the grid network. Subsequently, preprocess the collected multi-source monitoring information, and the preprocessing includes radiometric correction, geometric correction, and image enhancement. After preprocessing, detect the grid network for the multi-source monitoring information. The grid network includes transmission lines, pole and tower substations, power plants, and substations, etc. For example, the following methods can be used to extract and identify power plants: Use YOLOv5 to detect landmark structures such as chimneys, cooling towers, photovoltaic panels, wind turbines, and dams to obtain the key target information of the power generation site. Further use ResNet to extract target features and combine with a classifier to determine the type of the site. Among them, the simultaneous appearance of a chimney and a cooling tower indicates a thermal power plant, a large area of photovoltaic panels indicates a photovoltaic power station, tall wind turbines indicate a wind power plant, and a dam corresponds to a hydropower plant. For areas with multiple power generation devices, comprehensively analyze the target distribution and feature matching to identify hybrid energy sites. Subsequently, based on the identified grid structure information, extract the geographical coordinates of transmission lines, poles, and substations, and construct a grid topology model. Use topology analysis methods (such as the shortest path algorithm, network centrality analysis) to evaluate the connection characteristics of the grid, identify possible isolated nodes or redundant grid areas, so as to optimize the grid network layout. During the grid spatial distribution analysis process, by collecting the grid network coordinate information and combining with the grid topology analysis results, evaluate and analyze the spatial coverage of the grid to obtain the grid coverage data. Visualize the identified grid structure information, topology analysis results, and spatial coverage data to generate the grid network detection results. Then, the grid network data can be visually displayed using Geographic Information System (GIS) software, including key structures such as transmission lines, poles, substations, and power plants, and use topology visualization methods (such as force-directed graph layout) to display the connectivity of the grid. In addition, classify different grid network structures, including radial structure, loop structure, mesh structure, chain structure, hybrid structure, double-circuit structure, multi-terminal DC transmission structure, hierarchical and zonal structure, and microgrid structure, to intuitively present different types of grid topology forms. At the same time, combine the Geographic Information System to draw the spatial coverage range of the transmission lines, and through grid load matching analysis, evaluate the power supply capacity and load coverage of the substations, providing scientific decision-making support for grid planning and management.

[0076] Through the technical solution of the present invention, the problem of easy omission of detection in weak edge areas during the monitoring of the power grid network in large-scale and high-complexity scenarios by traditional methods is effectively solved. Through satellite remote sensing technology, the spatial distribution information of the power grid network can be obtained quickly and on a large scale. Combining with an automatic recognition algorithm, the efficiency and accuracy of power grid network recognition are significantly improved, and the cost and time of manual inspection are reduced. Through the identified power grid network structure, it is verified with account books such as the power line distribution map. Through the accurate recognition and spatial information management of the power grid network, a data foundation is provided for the planning, construction and operation and maintenance of the smart grid, helping the digital transformation and intelligent upgrade of the power system.

[0077] Furthermore, as Figure 2 and Figure 4 shown, the spatial distribution analysis of the power grid network is carried out according to the power grid network coordinate information and the power grid topology analysis result, including:

[0078] S310: Obtain the geographical coordinates of the transmission line, the geographical coordinates of the pole tower and the geographical coordinates of the substation respectively according to the power grid network coordinate information;

[0079] S320: Fit the spatial path of the transmission line according to the geographical coordinates of the transmission line, and calculate the pole tower distribution density according to the geographical coordinates of the pole tower;

[0080] S330: Obtain the regional load center data according to the geographical information system, and perform a spatial overlay analysis on the geographical coordinates of the substation and the regional load center data to obtain the substation layout evaluation result;

[0081] S340: Draw the spatial coverage range of the power grid network based on the spatial path of the transmission line, the pole tower distribution density and the substation layout evaluation result.

[0082] Preferably, as in the above embodiments, the grid network coordinate information is first obtained by remote sensing image extraction and corrected in combination with historical grid data to ensure the accuracy of the path. The grid network coordinate information includes the geographical coordinates of transmission lines, the geographical coordinates of poles and towers, and the geographical coordinates of substations. After obtaining the basic geographical data, the transmission line coordinates are analyzed: The affine transformation matrix can be used to convert the transmission line pixels extracted from the remote sensing image into geographical coordinates, and then the spline interpolation or Bezier curve method can be used to smoothly fit the path of the transmission line to eliminate the influence of remote sensing image noise and errors and ensure the coherence and accuracy of the transmission line. In addition, by calculating the spatial distribution density of the geographical coordinates of poles and towers: Preferably, the number of poles and towers within a unit area is calculated by fixed area division, and the pole and tower distribution pattern is detected by spatial clustering algorithms (such as DBSCAN, K-Means) to identify the dense areas, sparse areas, and possible missing points of poles and towers. Further, in order to optimize the grid spatial layout, the regional load center data is obtained based on the geographical information system, and the spatial superposition analysis is performed on the geographical coordinates of substations and the load center data to evaluate the rationality and power supply capacity of the substations. After completing the path fitting of the transmission line, the calculation of the pole and tower distribution density, and the evaluation of the substation layout, the spatial coverage range of the grid network is drawn. This process comprehensively considers the spatial path of the transmission line, the pole and tower distribution density, and the substation layout evaluation results, and the Thiessen polygon or triangulation can be used to generate the coverage map of the grid.

[0083] Furthermore, as Figure 3 shown, the spatial superposition analysis is performed on the geographical coordinates of substations and the regional load center data to obtain the substation layout evaluation results, including:

[0084] S331: Obtain the coordinates and load demand data of several regional load centers according to the geographical information system;

[0085] S332: Match the coordinates of each load center with the geographical coordinates of several substations respectively to obtain the load-substation mapping relationship, and calculate the spatial straight-line distance according to the load-substation mapping relationship. The load-substation mapping relationship represents the geographical coordinates of the substation with the shortest distance to the coordinates of each load center;

[0086] S333: Collect the capacity of each substation respectively, and determine the load demand data of the corresponding load center according to the load-substation mapping relationship and the substation capacity, and calculate the substation capacity matching degree;

[0087] S334: Set the spatial threshold and capacity threshold according to the historical power system operation data, and evaluate the substation layout according to the spatial straight-line distance and the substation capacity matching degree to obtain the substation layout evaluation results.

[0088] In this embodiment, first, based on the geographic information system, the geographic coordinates of multiple regional load centers and the corresponding load demand data are extracted. A load center refers to an area with intensive power demand, such as the core urban area, industrial park, large commercial area, etc. The data can be obtained from channels such as the power grid management system, smart meter data, and urban power demand forecasting system. In addition, by combining night light remote sensing data, high-energy-consuming areas can be further identified to enhance the accuracy of the data. Then, using the geospatial matching method, each load center is matched with a substation to form a load-substation mapping relationship. Specifically, the Euclidean distance between the load center and the substation is calculated, and the nearest substation is selected as its main power supply station based on the nearest neighbor algorithm to form a mapping relationship. After obtaining the load-substation mapping relationship, the power supply capacity of the substation is further calculated to ensure reasonable load distribution: First, the rated capacity of each substation is extracted from the power system database. Combining the load-substation mapping relationship, the actual load situation of the substation is calculated. According to the actual load situation of the substation, the substation capacity matching degree is calculated. The formula for calculating the substation capacity matching degree is: , is the capacity matching degree of substation j, , is the total power supply load of the substation, is the rated capacity of the substation, where the total power supply load is obtained by adding all load demand data; when the substation capacity matching degree is greater than 1, it means that the substation is operating overloaded and may need to adjust the power supply range or add new substations. When the substation capacity matching degree is less than 0.5, it indicates that there is power supply redundancy in the substation and the load distribution may need to be readjusted. Finally, based on the above calculation results, the rationality of the current substation layout is evaluated to obtain the substation layout evaluation result.

[0089] Furthermore, the power grid framework is detected according to multi-source monitoring information, including:

[0090] The remote sensing image in the multi-source monitoring information is converted to grayscale to obtain a grayscale image, and the grayscale image is denoised;

[0091] According to the denoised grayscale image, the gradient amplitude and gradient direction of the image are calculated, and potential edge regions are identified based on the gradient amplitude and gradient direction;

[0092] Based on the potential edge regions, pixel points are screened along the gradient direction to obtain a refined edge region;

[0093] Based on the historical power system operation data, a gradient amplitude threshold is set, and threshold segmentation is performed according to the gradient amplitude threshold to obtain strong edge regions and weak edge regions;

[0094] Detect whether the pixel points in the weak edge area are connected to the strong edge area. If so, retain the weak edge area; otherwise, remove the weak edge area. Connect the weak edge area to the strong edge area to obtain the continuous transmission line.

[0095] Specifically, first convert the remote sensing image in the multi-source monitoring information collected into grayscale, that is, convert the multi-band optical image into a single-channel grayscale image to reduce the computational complexity, enhance the edge information of the image at the same time, and can use Gaussian filtering or bilateral filtering for denoising processing. After denoising is completed, extract the edge information of the image based on the gradient calculation method, and the method is as follows: First, the Sobel or Prewitt operator can be used to perform convolution calculation on the denoised grayscale image, calculate the gradients in the x-axis and y-axis directions respectively, and calculate the gradient magnitude and gradient direction according to the gradients in the x and y directions. The gradient magnitude calculation formula is as follows: , represents the gradient intensity at the pixel point , represents the gradient in the x direction, represents the gradient in the y direction; the gradient direction calculation formula is as follows: , is the gradient direction, represents the gradient in the x direction, represents the gradient in the y direction; according to the gradient direction, extract the potential edge area and initially identify the possible transmission line area. On this basis, non-maximum suppression can be used to screen pixel points along the gradient direction, eliminate the noise edges, and obtain the refined edge area; then extract the historical power system operation data and set the gradient magnitude threshold. According to the set gradient magnitude threshold, perform threshold segmentation on the edge detection result to obtain the strong edge area and the weak edge area respectively. Among them, the strong edge area corresponds to the obvious transmission line, while the weak edge area may contain some break points or low-contrast areas of the transmission line. Then, perform connectivity analysis on the pixel points in the weak edge area to detect whether they are connected to the strong edge area. If there is a pixel-level connection between the weak edge area and the strong edge area, retain the weak edge area; otherwise, remove it to reduce false detection. In the final optimization stage, connect the weak edge area to the strong edge area, and use morphological operations (such as closing operation) to fill in the missing parts to ensure the integrity and coherence of the transmission line, so as to obtain the final continuous transmission line.

[0096] Furthermore, obtain the continuous transmission line and optimize the generation of the continuous transmission line, including:

[0097] Perform binary segmentation on the continuous transmission line based on the deep learning algorithm to obtain the binary segmentation image;

[0098] Extract historical transmission line features based on historical power system operation data, and construct a linear kernel according to the historical transmission line features;

[0099] Perform edge filling and noise reduction processing on the binary segmentation image according to the linear kernel, and perform linear fitting on the binary segmentation image after edge filling and noise reduction processing to optimize the continuous transmission line.

[0100] As a preference of the above embodiment, use the obtained image of the continuous transmission line as the input, and adopt the U-Net model for pixel-level segmentation. The method is as follows: according to the obtained multi-source monitoring information; and establish a training data set through manual annotation or automated edge detection methods, and optimize it using cross-entropy loss. Subsequently, the trained U-Net model can automatically detect the transmission lines in the image and generate a binary segmentation map, where white pixels 1 represent transmission lines and black pixels 0 represent the background; after U-Net segmentation, extract the historical features of the transmission lines based on the historical power system operation data, including line direction features, spatial distribution features, and topological consistency features, and construct a linear kernel according to these features; after the binary segmentation and linear kernel construction are completed, further perform edge filling and noise reduction processing. The method is as follows: First, use morphological closing operation to connect the broken transmission line areas to avoid line loss caused by noise interference. At the same time, use morphological opening operation to remove isolated noise points, reduce false detections, and improve the stability of recognition. In addition, in order to ensure the direction consistency of the transmission lines, combined with direction gradient analysis, optimize the filled transmission lines to make them consistent with the direction of the original lines and avoid misconnection phenomena; then, in this embodiment, use the Hough transform to fit the optimized transmission lines. The fitting process is as follows: extract preliminary edge information according to the continuous transmission line and input it into the Hough transform for line detection. By constructing a Hough accumulator matrix, traverse all edge pixel points, calculate the polar coordinate parameters at different angles, and vote in the accumulator. Subsequently, select the line with the highest number of votes as the main direction of the transmission line. On this basis, use the least squares method to calculate the fitting equation of the transmission line to obtain the optimized continuous transmission line.

[0101] Furthermore, detect the power grid framework according to the multi-source monitoring information, including:

[0102] Extract the pole tower edge contour according to the multi-source monitoring information, and calculate the geometric features of the pole tower;

[0103] Determine the local feature points of the contour according to the pole tower edge contour, and smooth and correct the pole tower edge contour based on the local feature points of the contour to obtain the pole tower area contour;

[0104] Obtain the spatial distribution of pixel gray values according to the pole tower area contour, and extract several local pole tower texture features respectively;

[0105] Feature enhancement is performed on several local tower texture features to generate a texture response map;

[0106] Tower information is obtained based on the tower geometric features, local tower texture features, and texture response map.

[0107] In this embodiment, first, the tower edge contour is extracted according to multi-source monitoring information, and the Canny edge detection algorithm is used to calculate the gradient to identify the area with a large gradient change and highlight the contour structure of the tower. Subsequently, the geometric features of the tower are calculated, including area, perimeter, aspect ratio, rectangularity, etc., to characterize the spatial form of the tower; among them, the aspect ratio is used to measure the structural features of the tower by calculating the width-to-height ratio of the minimum circumscribed rectangle of the tower, and the rectangularity is used to evaluate the regularity of the tower structure; in this embodiment, the Arris corner detection algorithm is used to extract the key points of the tower, and the extraction method is as follows: the Sobel operator is used to calculate the gradients in the x and y directions, and a second-order gradient matrix is constructed to calculate the corner response value, and the possible key points of the tower are screened out; after obtaining the tower edge contour and geometric features, the local texture features of the tower are further extracted, and the spatial gray distribution of the pixels in the tower area is analyzed by calculating the gray-level co-occurrence matrix, and texture features such as contrast, correlation, energy, and homogeneity are extracted. At the same time, the local binary pattern is used to calculate the detailed texture information of the tower to distinguish different types of towers; after extracting the local texture features of the tower, the Gabor filter is used to extract the multi-scale and multi-directional texture features of the tower to enhance the edge information and structural information of the tower area. Finally, the complete tower recognition information is generated by integrating the geometric features of the tower, local tower texture features, and texture response map.

[0108] Furthermore, the power grid network is detected according to multi-source monitoring information, including:

[0109] The substation area image is extracted according to multi-source monitoring information, and the power station equipment is located in the substation according to the substation area image to obtain several substation bounding boxes;

[0110] The overall feature extraction and classification of the substation area image are performed to generate a probability distribution map of the functional areas of the substation;

[0111] Pixel-level classification is performed on the substation area image to obtain several power station equipment mask images;

[0112] The power station boundary range is determined according to the substation bounding box, the probability distribution map of the functional areas, and the power station equipment mask image.

[0113] Specifically, to extract the substation area image from multi-source monitoring information, the YOLO object detection model can be used to detect the iconic devices (such as transformers, switchgear, busbars, etc.) inside the substation, obtain the location information and bounding boxes of the devices. The YOLO model can extract the key features of the substation area based on the convolutional neural network and predict the locations of various substation devices through bounding box regression. After the object detection results are output, combined with the geographical information system data, the location of the substation is spatially calibrated to ensure that the substation device recognition results are consistent with the real power grid layout. After completing the object detection of substation devices, the overall classification of the substation area can be carried out. The ResNet deep learning model can be used to segment the remote sensing image of the substation: First, preprocess the remote sensing image, including pixel normalization, size adjustment, and data augmentation, to ensure the consistency of the input data. Then, the ResNet model extracts the spatial features of the substation through convolutional layers and residual blocks, uses global average pooling for feature dimensionality reduction, and calculates the classification probability of the substation area through the fully connected layer to generate the probability heatmaps of the core area (such as transformers, switchgear) and the peripheral area of the substation. Different areas correspond to different functions of the substation, such as the main transformer area, high-voltage switch area, busbar area, control room area, etc. This distribution map can provide prior information for subsequent pixel-level classification. After obtaining the overall classification information of the substation, the U-Net deep learning model can be further used for pixel-level classification to obtain several substation device mask maps. Finally, based on the substation bounding box, the functional area probability distribution map, and the substation device mask maps, the spatial boundary range of the substation is optimized.

[0114] Furthermore, a power grid topology model is established according to several power grid structure information, including:

[0115] Extract transmission line information and power grid facility information according to several power grid structure information;

[0116] Determine the power grid nodes and power grid paths according to the power grid facility information and transmission line information respectively, create an adjacency matrix according to the number of power grid nodes, and each row and column of the adjacency matrix corresponds to a power grid node;

[0117] Traverse the power grid paths corresponding to the transmission line information, determine the power grid nodes connected by the power grid paths, represent the connected power grid nodes as 1, and the rest as 0, and fill them into the adjacency matrix;

[0118] Determine the power grid facility connection relationship according to the adjacency matrix, and add power grid configuration attributes respectively to construct a power grid topology model.

[0119] As a preference of the above embodiments, first, a target detection algorithm can be combined with an edge detection algorithm to extract transmission line information and power grid facility information based on a number of power grid structure information. Among them, the transmission line information includes the spatial path of the transmission line, the geographical coordinates of the poles and towers, and the voltage level of the line. The power grid facility information includes the location, capacity, power supply range, etc. of the substation; after the extraction of the power grid structure information is completed, the power grid nodes and power grid paths are further determined, and an adjacency matrix is created based on the number of nodes to represent the connection relationship between power grid facilities. The power grid nodes include key facilities such as substations, poles and towers, and load centers. The power grid path refers to the transmission line connecting these nodes; if there is a direct transmission line between two power grid nodes, it is represented as 1, and if there is no transmission line, it is represented as 0; traverse the transmission line information, determine the power grid nodes connected by each transmission line, and fill the adjacency matrix. The traversal can be carried out in the following way: based on the geographical coordinate data of the poles and towers and the transmission lines, calculate the start and end points of the transmission line and determine the power grid facilities it connects. Use the shortest path algorithm or breadth-first search to calculate the connectivity between power grid nodes, and assign weights to transmission lines of different voltage levels in the adjacency matrix. The weight value corresponds to the voltage level of the transmission line and can be used for power grid load flow calculation; after the adjacency matrix is constructed, further determine the connection relationship of power grid facilities, and add power grid configuration attributes to each power grid node, including node type, voltage level, power supply capacity, etc. Based on the adjacency matrix and power grid configuration data, finally construct a power grid topology model.

[0120] Embodiment 2;

[0121] Based on the same inventive concept as an intelligent detection method for a power grid framework in the foregoing embodiments, the present invention also provides a satellite image processing system, as Figure 5 shown, the system includes:

[0122] A power grid structure extraction module, which collects multi-source monitoring information, detects the power grid framework according to the multi-source monitoring information, and obtains a number of power grid structure information;

[0123] A power grid topology analysis module, which establishes a power grid topology model according to a number of power grid structure information, and conducts connection analysis on the power grid topology model to obtain a power grid topology analysis result;

[0124] A power grid spatial analysis module, which collects power grid framework coordinate information, and conducts spatial distribution analysis on the power grid framework according to the power grid framework coordinate information and the power grid topology analysis result to obtain power grid coverage data;

[0125] A power grid visualization display module, which visualizes the data of a number of power grid structure information, the power grid topology analysis result and the power grid coverage data to generate a power grid framework detection result.

[0126] The above adjustment system in the present invention can effectively implement an intelligent detection method for a power grid network framework, and the technical effects that can be achieved are as described in the above embodiments, which will not be elaborated here.

[0127] Furthermore, the power grid spatial analysis module includes:

[0128] A power grid coordinate extraction unit, which respectively obtains the geographical coordinates of transmission lines, the geographical coordinates of poles and towers, and the geographical coordinates of substations according to the power grid network framework coordinate information;

[0129] A transmission line path modeling unit, which fits and generates the spatial path of the transmission line according to the geographical coordinates of the transmission line, and calculates the pole and tower distribution density according to the geographical coordinates of the poles and towers;

[0130] A substation layout analysis unit, which obtains the regional load center data according to the geographical information system, performs a spatial overlay analysis on the geographical coordinates of the substation and the regional load center data, and obtains the substation layout evaluation result;

[0131] A power grid coverage analysis unit, which draws the spatial coverage range of the power grid network framework based on the spatial path of the transmission line, the pole and tower distribution density, and the substation layout evaluation result.

[0132] Similarly, for the above optimization solutions of the system, the corresponding optimization effects of the method in Embodiment 1 can also be respectively achieved, which will not be elaborated here either.

[0133] Although the present application has been described in combination with specific features and their embodiments, obviously, various modifications and combinations can be made without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary descriptions of the present application defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An intelligent detection method for a power grid network framework, characterized in that, The method includes: Collect multi-source monitoring information, detect the power grid network framework according to the multi-source monitoring information, and obtain a number of power grid structure information; Establish a power grid topology model according to a number of the power grid structure information, and conduct connection analysis on the power grid topology model to obtain a power grid topology analysis result; Collect power grid network framework coordinate information, and conduct spatial distribution analysis on the power grid network framework according to the power grid network framework coordinate information and the power grid topology analysis result to obtain power grid coverage data; Visualize a number of the power grid structure information, the power grid topology analysis result and the power grid coverage data to generate a power grid network framework detection result; Conduct spatial distribution analysis on the power grid network framework according to the power grid network framework coordinate information and the power grid topology analysis result, including: Respectively obtain the geographical coordinates of transmission lines, the geographical coordinates of poles and towers, and the geographical coordinates of substations according to the power grid network framework coordinate information; Fit the spatial path of the transmission line according to the geographical coordinates of the transmission line, and calculate the pole and tower distribution density according to the geographical coordinates of the poles and towers; Obtain regional load center data according to the geographical information system, conduct spatial overlay analysis on the geographical coordinates of the substations and the regional load center data, and obtain a substation layout evaluation result; Draw the spatial coverage range of the power grid network framework based on the spatial path of the transmission line, the pole and tower distribution density, and the substation layout evaluation result; Conduct spatial overlay analysis on the geographical coordinates of the substations and the regional load center data to obtain a substation layout evaluation result, including: Obtain a number of regional load center coordinates and load demand data according to the geographical information system; Respectively match each of the load center coordinates with a number of the geographical coordinates of the substations to obtain a load-substation mapping relationship, calculate the spatial straight-line distance according to the load-substation mapping relationship, and the load-substation mapping relationship represents the geographical coordinates of the substation with the shortest distance to each of the load center coordinates; Respectively collect the capacity of each substation, determine the load demand data of the corresponding load center according to the load-substation mapping relationship and the substation capacity, and calculate the power station capacity matching degree; Set a spatial threshold and a capacity threshold according to the historical power system operation data, and evaluate the substation layout according to the spatial straight-line distance and the power station capacity matching degree to obtain a substation layout evaluation result.

2. The intelligent detection method of the power grid network framework according to claim 1, characterized in that, Detect the power grid network framework according to the multi-source monitoring information, including: Convert the remote sensing image in the multi-source monitoring information into grayscale to obtain a grayscale image, and perform noise reduction processing on the grayscale image; Calculate the gradient amplitude and gradient direction of the image according to the denoised grayscale image, and identify potential edge regions according to the gradient amplitude and gradient direction; Perform pixel point screening along the gradient direction based on the potential edge regions to obtain a refined edge region; Set a gradient amplitude threshold based on the historical power system operation data, and perform threshold segmentation according to the gradient amplitude threshold to obtain a strong edge region and a weak edge region; Detect whether the pixel points in the weak edge area are connected to the strong edge area. If so, retain the weak edge area; otherwise, remove the weak edge area, connect the weak edge area to the strong edge area, and obtain the continuous transmission line.

3. The intelligent detection method for the power grid network framework according to claim 2, characterized in that, Obtain the continuous transmission line and optimize the generation of the continuous transmission line, including: Perform binary segmentation on the continuous transmission line based on a deep learning algorithm to obtain a binary segmentation image; Extract historical transmission line features according to the historical power system operation data, and construct a linear kernel according to the historical transmission line features; Perform edge filling and noise reduction processing on the binary segmentation image according to the linear kernel, and perform linear fitting on the binary segmentation image after the edge filling and noise reduction processing to optimize the continuous transmission line.

4. The intelligent detection method of the power grid network framework according to claim 1, characterized in that, Detect the power grid framework according to the multi-source monitoring information, including: Extract the pole tower edge contour according to the multi-source monitoring information and calculate the geometric features of the pole tower; Determine the contour local feature points according to the pole tower edge contour, smooth and correct the pole tower edge contour based on the contour local feature points, and obtain the pole tower area contour; Obtain the spatial distribution of pixel gray values according to the pole tower area contour, and extract several local pole tower texture features respectively; Enhance the features of several local pole tower texture features to generate a texture response map; Obtain the pole tower information according to the pole tower geometric features, local pole tower texture features and texture response map.

5. The intelligent detection method for the power grid network framework according to claim 1, characterized in that Detect the power grid framework according to the multi-source monitoring information, including: Extract the substation area image according to the multi-source monitoring information, perform power station equipment positioning on the substation according to the substation area image, and obtain several substation bounding boxes; Extract and classify the overall features of the power station for the substation area image to generate a probability distribution map of the functional areas of the substation; Perform pixel-level classification on the substation area image to obtain several power station equipment mask images; Determine the power station boundary range according to the substation bounding boxes, probability distribution map of functional areas and power station equipment mask images.

6. The intelligent detection method of the power grid network framework according to claim 1, characterized in that, Establish a power grid topology model according to several pieces of the power grid structure information, including: Extract transmission line information and power grid facility information according to several pieces of the power grid structure information; Determine the power grid nodes and power grid paths according to the power grid facility information and transmission line information respectively, create an adjacency matrix according to the number of the power grid nodes, and each row and column of the adjacency matrix corresponds to one of the power grid nodes; Traverse the power grid paths corresponding to the transmission line information, determine the power grid nodes connected by the power grid paths, represent the connected power grid nodes as 1, and the rest as 0, and fill them into the adjacency matrix; Determine the connection relationship of the power grid facilities according to the adjacency matrix, and add power grid configuration attributes respectively to construct a power grid topology model.

7. A satellite image processing system, characterized in that, Adopt the intelligent detection method for the power grid framework as described in claim 1, and the system includes: A power grid structure extraction module, which collects multi-source monitoring information, detects the power grid framework according to the multi-source monitoring information, and obtains several pieces of power grid structure information; The power grid topology analysis module establishes a power grid topology model based on a number of the power grid structure information, and performs connection analysis on the power grid topology model to obtain the power grid topology analysis result; The power grid spatial analysis module collects the power grid network frame coordinate information, and performs spatial distribution analysis on the power grid network frame according to the power grid network frame coordinate information and the power grid topology analysis result to obtain the power grid coverage data; The power grid visualization display module visualizes the data of a number of the power grid structure information, the power grid topology analysis result and the power grid coverage data to generate the power grid network frame detection result; The power grid spatial analysis module includes: The power grid coordinate extraction unit respectively obtains the geographical coordinates of the transmission line, the geographical coordinates of the pole tower and the geographical coordinates of the substation according to the power grid network frame coordinate information; The transmission line path modeling unit fits and generates the spatial path of the transmission line according to the geographical coordinates of the transmission line, and calculates the pole tower distribution density according to the geographical coordinates of the pole tower; The substation layout analysis unit obtains the regional load center data according to the geographic information system, and performs spatial overlay analysis on the geographical coordinates of the substation and the regional load center data to obtain the substation layout evaluation result; The power grid coverage analysis unit draws the spatial coverage range of the power grid network frame based on the spatial path of the transmission line, the pole tower distribution density and the substation layout evaluation result.

Images