Power grid distribution monitoring method, system, equipment, medium and product
By acquiring and superimposing grid edge layout and GIS map data, a deep neural network model is constructed, which solves the problem of inefficiency of traditional grid edge layout monitoring methods, and achieves efficient and accurate fault identification and early warning.
Patent Information
- Application Number
- CN202510708679.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-29
- Publication Date
- 2025-08-26
AI Technical Summary
Traditional power grid edge monitoring methods rely on manual inspection, which is inefficient and difficult to detect faults in a timely manner, and cannot conduct fault warnings efficiently and accurately.
By obtaining low-voltage edge layout data and GIS map data, layer overlay, extracting feature data, building a training data set, using deep neural network to train the grid edge layout fault identification model, and identifying the current fault category.
It improves the efficiency and accuracy of fault identification along the cloth, and can promptly detect faults along the grid, ensuring the safe and stable operation of the power grid.
Smart Images
Figure CN120546282A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power systems, and in particular to a method, system, equipment, medium and product for monitoring the distribution of power grids. Background Art
[0002] In the low-voltage distribution network sector of the power system, ensuring the reliability, stability, and efficiency of power supply is one of the key goals. At the same time, with the massive increase in the access of distributed power sources and electric vehicle charging facilities, the structure and operating characteristics of the low-voltage distribution network have become increasingly complex.
[0003] Grid layout is a key factor in monitoring the structure and operating status of low-voltage distribution networks. Traditional grid layout monitoring methods often rely on manual inspections, which are not only inefficient but also difficult to detect faults along the grid layout in a timely manner, making it impossible to provide efficient and accurate fault warnings along the grid layout. Summary of the Invention
[0004] In view of this, the present invention provides a method, system, equipment, medium and product for monitoring the distribution of power grids, which solves the technical problem that traditional methods for monitoring the distribution of power grids often rely on manual inspections, which is not only inefficient but also difficult to detect faults along the distribution of power grids in a timely manner, and cannot provide fault warnings along the distribution of power grids efficiently and accurately.
[0005] A first aspect of the present invention provides a method for monitoring the distribution of power grids, comprising:
[0006] Obtain low-voltage grid layout data and GIS map data of the target power grid area;
[0007] Overlaying the low-voltage edge layout data and the target components in the GIS map data to obtain an edge layout overlay layer;
[0008] Extracting a plurality of feature data of the overlay layer along the fabric and a fabric fault category corresponding to each feature data;
[0009] Constructing a training data set according to the plurality of feature data and the plurality of distribution fault categories;
[0010] The deep neural network is trained using the training data set to obtain a power grid fault identification model;
[0011] The acquired current characteristic data in the target power grid area is input into the power grid distribution fault identification model, and the distribution fault category corresponding to the current characteristic data is output.
[0012] Preferably, the step of overlaying the low-voltage layout data and the target components in the GIS map data to obtain a layout overlay layer further includes:
[0013] The coordinate systems of the low-voltage edge layout data and the GIS map data are uniformly operated.
[0014] Preferably, the method further comprises:
[0015] Performing denoising processing on the low-voltage edge layout data and the GIS map data respectively;
[0016] The histogram equalization method is used to perform equalization operations on the denoised low-voltage layout data and the denoised GIS map data.
[0017] Edge enhancement operations are performed on the low-voltage edge layout data after equalization operation and the GIS map data after equalization operation.
[0018] Preferably, the feature data includes shape features, texture features and color features; and the step of extracting the plurality of feature data of the overlaid layers along the cloth includes:
[0019] Extracting shape features of the layers superimposed along the cloth by Hough transform;
[0020] Extracting texture features of the layer superimposed along the cloth by using a gray level co-occurrence matrix;
[0021] The overlay layer along the fabric is divided into a plurality of sub-images, and the color histogram in each of the sub-images is extracted as the category of the fault along the fabric.
[0022] Preferably, the method further comprises:
[0023] According to the preset layout trend anomaly rule, identifying the type of fault along the fabric in the overlay layer along the fabric;
[0024] The identified fabric fault category is matched with each of the feature data, and the fabric fault category corresponding to the matched feature data is marked.
[0025] Preferably, the method further comprises:
[0026] Constructing a test set according to the plurality of feature data and the plurality of distribution fault categories;
[0027] The power grid fault identification model is tested using the test set, and network parameters of the power grid fault identification model are optimized according to the test results to obtain an optimized power grid fault identification model.
[0028] In a second aspect, the present invention provides a power grid distribution monitoring system, comprising:
[0029] Data acquisition module, used to obtain low-voltage layout data and GIS map data of the target power grid area;
[0030] A layer overlay module is used to overlay the low-voltage layout data and the target components in the GIS map data to obtain a layout overlay layer;
[0031] A feature extraction module is used to extract multiple feature data of the overlay layer along the fabric and the category of the fabric fault corresponding to each feature data;
[0032] A training set construction module, configured to construct a training data set based on the plurality of feature data and the plurality of distribution fault categories;
[0033] A model training module is used to train a deep neural network using the training data set to obtain a power grid fault identification model;
[0034] The fault identification module is used to input the acquired current characteristic data in the target power grid area into the power grid distribution fault identification model, and output the distribution fault category corresponding to the current characteristic data.
[0035] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the power grid distribution monitoring method as described in the first aspect.
[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the steps of the power grid layout monitoring method as described in the first aspect.
[0037] In a fifth aspect, the present invention provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions, wherein when the program instructions are executed by a computer, the computer is caused to execute the steps of the power grid distribution monitoring method as described in the first aspect.
[0038] It can be seen from the above technical solutions that the present invention obtains the low-voltage layout data and GIS map data of the target power grid area, and superimposes layers on the target components in the low-voltage layout data and GIS map data, thereby coupling the line direction and geographic information, and constructs a training data set by extracting multiple feature data of the superimposed layout overlay layer and the layout fault category corresponding to each feature data. The deep neural network is trained by the training data set to obtain a power grid layout fault identification model, and the current layout fault category is identified by the power grid layout fault identification model, thereby improving the efficiency of layout fault identification, being able to timely discover power grid layout faults, and improving the accuracy of layout fault identification. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.
[0040] Figure 1 A diagram illustrating an application environment of a power grid distribution monitoring method provided by an embodiment of the present invention;
[0041] Figure 2 A flow chart of a method for monitoring the distribution of power grids provided by an embodiment of the present invention;
[0042] Figure 3 A schematic structural diagram of a power grid distribution monitoring system provided by an embodiment of the present invention;
[0043] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0044] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only 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 making creative efforts shall fall within the scope of protection of the present invention.
[0045] The grid distribution monitoring method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 101 communicates with the server 102 through the network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or it can be placed on the cloud or other network servers. The terminal 101 or the server 102 obtains the low-voltage layout data and GIS map data of the target power grid area; overlays the target components in the low-voltage layout data and the GIS map data to obtain a layout overlay layer; extracts multiple feature data of the layout overlay layer and the layout fault category corresponding to each feature data; constructs a training data set based on the multiple feature data and the multiple layout fault categories; trains the deep neural network through the training data set to obtain a power grid layout fault identification model; inputs the current feature data in the target power grid area into the power grid layout fault identification model, and outputs the layout fault category corresponding to the current feature data.
[0046] The terminal 101 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and the like.
[0047] The server 102 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.
[0048] like Figure 2 As shown, the embodiment of the present application provides a method for monitoring the distribution of power grids, which is applied to Figure 1 The terminal 101 or the server 102 in the example is used to illustrate the method, which includes the following steps S1 to S4.
[0049] Step S1: Obtain low-voltage grid layout data and GIS map data of the target grid area.
[0050] Low-voltage line layout data is acquired through power data collection equipment or systems. This data details the layout and direction of low-voltage lines within the target power grid area, as well as related power equipment information. GIS map data is acquired through a geographic information system and contains detailed information such as the geographic coordinates, topography, and building distribution of the target power grid area.
[0051] Step S2: Overlay the low-voltage layout data and the target components in the GIS map data to obtain a layout overlay layer.
[0052] The coordinate systems of the low-voltage grid layout data and the GIS map data were unified, allowing them to be accurately overlaid within the same coordinate system. The resulting overlaid layer contains both low-voltage grid layout and GIS (Geographic Information System) map information, providing a comprehensive and accurate data foundation for subsequent feature extraction and fault identification. This overlaid layer allows for intuitive visualization of the relationship between the grid layout and the geographic environment.
[0053] Step S3: extracting a plurality of feature data of the overlay layer along the fabric and the fabric fault category corresponding to each feature data.
[0054] Feature data includes, but is not limited to, shape, texture, and color features. These features comprehensively and accurately reflect the various information of the overlay layers along the power grid. Shape features primarily describe the shape and layout of the power grid along the power grid, such as the curvature and branching of the lines. Texture features reflect the differences in texture between the power grid along the power grid and its surroundings, such as the thickness of the lines and the texture of the materials. Color features primarily describe the color information along the power grid along the power grid, such as the color of the lines and the color of the markings. By extracting and analyzing these feature data, the fault type along the power grid can be further determined, such as abnormal line detours and line crossings.
[0055] Step S4: construct a training data set based on the multiple feature data and the multiple distribution fault categories.
[0056] Step S5: Train the deep neural network using the training data set to obtain a grid fault recognition model.
[0057] Deep neural networks are intelligent models that automatically learn and identify faults along power grids. Using extensive training data, these models can accurately identify various types of faults along power grids. During training, the deep neural network processes the input feature data layer by layer, extracting deeper feature information to accurately identify faults along power grids. Once trained, the model can be applied to actual power grid monitoring systems, enabling real-time monitoring and fault warning along power grids, significantly improving monitoring efficiency and accuracy.
[0058] Step S6: input the acquired current characteristic data in the target power grid area into the power grid distribution fault identification model, and output the distribution fault category corresponding to the current characteristic data.
[0059] Specifically, the current characteristic data within the target power grid area is fed into a trained grid fault identification model. The model rapidly analyzes and processes this characteristic data, accurately outputting the corresponding fault category based on the learned mapping between characteristic information and fault categories. This allows grid operations and maintenance personnel to quickly locate potential problems along the grid's distribution network based on the fault category output by the model and implement appropriate repair or adjustment measures, thereby ensuring safe and stable grid operation.
[0060] In actual operation, the trained power grid fault identification model is deployed in the actual application system, and a software interface is developed for users to view and analyze abnormal results. When the power grid fault identification model detects an abnormality, the system triggers an alarm and notifies the operation and maintenance personnel through the software to inspect and maintain the alarm area.
[0061] It should be noted that the embodiment of the present application obtains low-voltage layout data and GIS map data of the target power grid area, and superimposes layers on the target components in the low-voltage layout data and GIS map data, thereby coupling the line direction and geographic information, and constructs a training data set by extracting multiple feature data of the superimposed layout overlay layer and the layout fault category corresponding to each feature data. The deep neural network is trained with the training data set to obtain a power grid layout fault identification model, and the current layout fault category is identified by the power grid layout fault identification model, thereby improving the efficiency of layout fault identification, being able to timely discover power grid layout faults, and improving the accuracy of layout fault identification.
[0062] In some embodiments, the method further comprises:
[0063] Step S21: De-noising the low-voltage edge layout data and the GIS map data respectively.
[0064] Among them, low-voltage edge layout data and GIS map data will be interfered by noise during the collection or transmission process. These noise interferences include Gaussian noise and salt and pepper noise. Median filtering is used to suppress noise, that is, the median value of the pixel value in the neighborhood is used to replace the current pixel value, and Gaussian filtering is used to perform weighted averaging on the pixels in the neighborhood, thereby removing noise while retaining the edge information of the image.
[0065] Step S22: Using a histogram equalization method, perform equalization operations on the denoised low-voltage edge layout data and the denoised GIS map data.
[0066] Among them, the histogram equalization method is used to adjust the grayscale histogram of the image to make the grayscale distribution of the image more uniform, thereby enhancing the contrast of the image.
[0067] Step S23: performing edge enhancement operations on the low-voltage edge layout data after the equalization operation and the GIS map data after the equalization operation.
[0068] Among them, the Laplace operator and Sobel operator are used for edge enhancement to highlight the edge information in the image, so as to facilitate the subsequent recognition of lines and component contours in the circuit.
[0069] In some embodiments, the feature data includes shape features, texture features, and color features; extracting multiple feature data along the overlay layer of the cloth includes:
[0070] Step S301: extracting shape features of the layers superimposed along the cloth through Hough transform.
[0071] The Hough transform is a feature extraction method used to detect geometric shapes in images, particularly suitable for detecting regular shapes such as lines and circles. In power grid monitoring, the Hough transform can effectively extract shape features such as the direction and curvature of power lines, providing key information for subsequent fault identification.
[0072] Step S302: extracting texture features of the overlaid layers along the cloth using a gray-level co-occurrence matrix.
[0073] The gray-level co-occurrence matrix is a statistical method used to describe image texture. By analyzing the grayscale relationships between pairs of pixels in an image, it can extract texture features such as roughness and contrast. In power grid monitoring, the gray-level co-occurrence matrix can be used to identify texture differences between power lines and their surroundings, further determining whether there are any anomalies along the grid.
[0074] Step S303: Segment the overlay layer along the fabric into multiple sub-images, and extract the color histogram in each sub-image as the category of the fabric fault.
[0075] A color histogram is a statistical method used to describe the color distribution of an image. By segmenting the grid overlay into multiple sub-images and extracting the color histogram from each sub-image, we can further analyze the color characteristics of the grid. For example, if the color of a power line differs significantly from the surrounding color, this likely indicates an anomaly along the grid.
[0076] In some embodiments, the method further comprises:
[0077] Step S31: Identify the type of fault along the fabric in the overlay layer along the fabric according to the preset layout trend anomaly rule.
[0078] Among them, the types of faults along the layout include abnormal line detours, abnormal line crossings, and abnormal line crossings of prohibited areas. A line detour refers to unnecessary bends or detours in the layout of power grid lines, which may lead to reduced power transmission efficiency and increased line losses; a line crossing refers to the crossing or overlapping of lines of different voltage levels in the layout, which may pose a safety hazard; and a line crossing of prohibited areas refers to power grid lines crossing areas where construction is prohibited or restricted, such as nature reserves and military restricted areas, which may cause legal or environmental issues. These types of faults along the layout can be automatically identified through preset layout direction anomaly rules, providing strong support for subsequent maintenance or adjustment measures.
[0079] Layout anomaly rules are pre-defined based on the grid's layout characteristics, common fault types, and expert experience. These rules cover a variety of possible fault scenarios, including abnormal line detours, abnormal line crossings, and line crossing restricted areas. By carefully analyzing the overlay layer and comparing it with the pre-defined layout anomaly rules, the overlay layer can automatically identify fault types, such as abnormal line detours, line crossings, and abnormal line crossings.
[0080] For example, if the actual length of the line exceeds 30% of the theoretical straight-line distance between two points, it can be determined that the line is abnormally circuitous and the transformer is too far away from the load center. That is, the distance from the transformer to the load center in urban residential areas and industrial plants exceeds 500 meters, and the distance from the transformer to the load center in rural areas exceeds 1000 meters. When these situations occur, it can be determined that the layout problem is improper equipment layout.
[0081] Combined with GIS information, the abnormal layout rules are determined, including situations where the line layout conflicts with the terrain and landforms, such as the line crossing terrain that is not suitable for construction or the distance from buildings and trees is lower than the standards of my country's power industry. The line direction is inconsistent with the road and building layout of the urban planning, such as the line layout violates the urban planning.
[0082] Step S32: Match the identified fault category along the fabric with each feature data, and mark the fault category along the fabric corresponding to the matched feature data.
[0083] The identified fault categories, such as abnormal line detours and line crossings, are precisely matched with extracted feature data, such as shape, texture, and color. This step compares the correlation between the fault category and the feature data to identify data items that accurately reflect the fault characteristics. Once the match is complete, the fault category corresponding to the matched feature data is annotated, marking the feature data with the corresponding fault type. This allows power grid operations and maintenance personnel to intuitively understand potential fault issues when viewing the feature data, allowing them to quickly locate and take appropriate measures.
[0084] In some embodiments, the method further comprises:
[0085] Step S701: construct a test set based on multiple feature data and multiple distribution fault categories;
[0086] Step S702: testing the power grid fault identification model using a test set, and optimizing the network parameters of the power grid fault identification model according to the test results to obtain an optimized power grid fault identification model.
[0087] Among them, the test set is constructed to verify the accuracy and reliability of the power grid fault identification model. The test set contains feature data and fault categories that are similar to but not exactly the same as the training set to ensure that the model can still maintain high performance when faced with new data. By testing the power grid fault identification model on the test set, the model's predictive ability for unknown data can be evaluated and possible problems or deficiencies can be discovered. According to the test results, the network parameters of the power grid fault identification model can be optimized, such as adjusting the network structure, modifying the learning rate, adding regularization terms, etc., to improve the model's recognition accuracy and generalization ability. The optimized power grid fault identification model will have stronger robustness and adaptability, and can more accurately identify various types of faults in the power grid, providing more reliable protection for the safe and stable operation of the power grid.
[0088] Based on the same inventive concept, an embodiment of the present application further provides a power grid edge monitoring system for implementing the above-mentioned power grid edge monitoring method.
[0089] The implementation solution provided by the system to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more power grid distribution monitoring system embodiments provided below can be found in the above limitations on the power grid distribution monitoring method and will not be repeated here.
[0090] like Figure 3 As shown, an embodiment of the present application provides a power grid distribution monitoring system, comprising:
[0091] The data acquisition module 100 is used to obtain low-voltage layout data and GIS map data of the target power grid area;
[0092] The layer overlay module 200 is used to overlay the target components in the low-voltage layout data and the GIS map data to obtain a layout overlay layer;
[0093] A feature extraction module 300 is used to extract multiple feature data of the overlay layer along the fabric and the category of the fabric fault corresponding to each feature data;
[0094] A training set construction module 400 is used to construct a training data set based on a plurality of feature data and a plurality of distributed fault categories;
[0095] The model training module 500 is used to train the deep neural network using the training data set to obtain a grid fault identification model;
[0096] The fault identification module 600 is configured to input the acquired current characteristic data in the target power grid area into a power grid distribution fault identification model, and output a distribution fault category corresponding to the current characteristic data.
[0097] In some embodiments, the system further comprises:
[0098] The coordinate operation module is used to uniformly operate the coordinate systems of low-voltage layout data and GIS map data.
[0099] In some embodiments, the system further comprises:
[0100] Denoising module, used to perform denoising on low-voltage layout data and GIS map data respectively;
[0101] The equalization module is used to perform equalization operations on the low-voltage layout data after denoising and the GIS map data after denoising by using a histogram equalization method;
[0102] The edge enhancement module is used to perform edge enhancement operations on the low-voltage edge layout data after the equalization operation and the GIS map data after the equalization operation.
[0103] In some embodiments, the feature data includes shape features, texture features, and color features; the feature extraction module 300 is used to:
[0104] The shape features of the layers superimposed along the cloth are extracted through Hough transform;
[0105] The texture features of the overlay layers along the cloth are extracted through the gray-level co-occurrence matrix;
[0106] The overlay layer along the fabric is divided into multiple sub-images, and the color histogram in each sub-image is extracted as the category of the fabric fault.
[0107] In some embodiments, the system further comprises:
[0108] A fault category determination module is used to identify the fault category along the fabric in the overlay layer according to the preset layout trend anomaly rules;
[0109] The category labeling module is used to match the identified fault category along the fabric with each feature data, and label the fault category along the fabric corresponding to the matched feature data.
[0110] In some embodiments, the system further comprises:
[0111] A test set construction module is used to construct a test set based on multiple feature data and multiple distributed fault categories;
[0112] The model optimization module is used to test the power grid fault identification model through a test set, and optimize the network parameters of the power grid fault identification model according to the test results to obtain an optimized power grid fault identification model.
[0113] like Figure 4As shown, an embodiment of the present application provides an electronic device, the electronic device 10 includes a memory 20 and a processor 30, the memory 20 stores a computer program, and when the computer program is executed by the processor 30, the processor 30 executes the steps of the power grid distribution monitoring method in the above embodiment.
[0114] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the steps of the power grid distribution monitoring method in the above-mentioned embodiment are implemented.
[0115] An embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the steps of the power grid distribution monitoring method described in the above embodiments.
[0116] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, electronic devices, computer program products, and computer storage media can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0117] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or apparatuses.
[0118] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.
[0119] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, electronic devices, computer storage media, computer program products and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0120] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0121] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0122] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the method described in each embodiment of the present invention via a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0123] The above embodiments 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 they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.
Claims
1. A method for monitoring the distribution of power grids, characterized in that: include: Obtain low-voltage grid layout data and GIS map data of the target power grid area; Overlaying the low-voltage edge layout data and the target components in the GIS map data to obtain an edge layout overlay layer; Extracting a plurality of feature data of the overlay layer along the fabric and a fabric fault category corresponding to each feature data; Constructing a training data set according to the plurality of feature data and the plurality of distribution fault categories; The deep neural network is trained using the training data set to obtain a power grid fault identification model; The acquired current characteristic data in the target power grid area is input into the power grid distribution fault identification model, and the distribution fault category corresponding to the current characteristic data is output.
2. The method for monitoring the distribution of power grids according to claim 1, wherein: The low-voltage layout data and the target components in the GIS map data are layered to obtain a layout overlay layer, which also includes: The coordinate systems of the low-voltage edge layout data and the GIS map data are uniformly operated.
3. The method for monitoring the distribution of power grids according to claim 1, wherein: Also includes: Performing denoising processing on the low-voltage edge layout data and the GIS map data respectively; The histogram equalization method is used to perform equalization operations on the denoised low-voltage layout data and the denoised GIS map data. Edge enhancement operations are performed on the low-voltage edge layout data after equalization operation and the GIS map data after equalization operation.
4. The method for monitoring the distribution of power grids according to any one of claims 1 to 3, characterized in that: The feature data includes shape features, texture features and color features; The step of extracting a plurality of feature data of the overlaid layers along the fabric includes: Extracting shape features of the layers superimposed along the cloth by Hough transform; Extracting texture features of the layer superimposed along the cloth by using a gray level co-occurrence matrix; The overlay layer along the fabric is divided into a plurality of sub-images, and the color histogram in each of the sub-images is extracted as the category of the fault along the fabric.
5. The method for monitoring the distribution of power grids according to claim 4, characterized in that: Also includes: According to the preset layout trend anomaly rule, identifying the type of fault along the fabric in the overlay layer along the fabric; The identified fabric fault category is matched with each of the feature data, and the fabric fault category corresponding to the matched feature data is marked.
6. The method for monitoring the distribution of power grids according to claim 4, characterized in that: Also includes: Constructing a test set according to the plurality of feature data and the plurality of distribution fault categories; The power grid fault identification model is tested using the test set, and network parameters of the power grid fault identification model are optimized according to the test results to obtain an optimized power grid fault identification model.
7. A power grid monitoring system, characterized in that: include: Data acquisition module, used to obtain low-voltage layout data and GIS map data of the target power grid area; A layer overlay module is used to overlay the low-voltage layout data and the target components in the GIS map data to obtain a layout overlay layer; A feature extraction module is used to extract multiple feature data of the overlay layer along the fabric and the category of the fabric fault corresponding to each feature data; A training set construction module, configured to construct a training data set based on the plurality of feature data and the plurality of distribution fault categories; A model training module is used to train a deep neural network using the training data set to obtain a power grid fault identification model; The fault identification module is used to input the acquired current characteristic data in the target power grid area into the power grid distribution fault identification model, and output the distribution fault category corresponding to the current characteristic data.
8. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the power grid distribution monitoring method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the steps of the power grid layout monitoring method according to any one of claims 1 to 6 are implemented.
10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer is caused to perform the steps of the power grid distribution monitoring method according to any one of claims 1 to 6.