Grid distribution network line path automatic planning method based on digital twinning

Abstract

The invention discloses a grid distribution network line path automatic planning method based on digital twinning, and relates to the technical field of power grid construction, and the method comprises the following steps: a calculation device collects a line drawing of a historical construction distribution network line area, carries out the fuzzy and incomplete information restoration and complementation of an image of the line drawing through a generative adversarial network, and obtains an image of the line drawing; and identifying and marking non-standard specifications and parameters in the line drawing, generating a non-standard data set, unifying information of the line drawing to a corresponding coordinate system, correcting an offset coordinate system, and exporting a digital twinborn model after correction. According to the method, the digital twin model capable of accurately reflecting the total factor state of the distribution network is constructed, path planning is deeply matched with the actual geographical environment, the equipment parameters and the environmental data by using the model, the planning scheme is highly matched with the actual scene, and a gridding path design thought is designed, so that the planning efficiency is improved. And the subsequent planning of the distribution network line path can be more intuitive and efficient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power construction, in particular to a grid-based distribution network line path automatic planning method based on digital twinning. BACKGROUND

[0002] Digital twinning is a simulation process that fully utilizes physical models, sensors, operation history and other data, integrates multi-disciplinary, multi-physical quantity, multi-scale and multi-probability, and completes mapping in a virtual space, thereby reflecting the whole life cycle process of the corresponding entity equipment. As a key component of the power system, distribution network line planning is a key link to ensure power supply reliability and economy, and the scientificity and efficiency of line design directly affect power supply reliability and power quality.

[0003] The existing distribution network line path planning method relies on two-dimensional CAD software and designer experience, lacks adaptive adjustment of dynamic weights and cross-system collaborative optimization mechanism of urban planning, and cannot accurately reflect the full-factor state of the distribution network, resulting in deviations between the path planning scheme and the actual geographical environment, operating conditions and municipal planning, high path conflict rate, frequent adjustment, poor long-term adaptability, and serious impact on the accuracy and efficiency of distribution network planning. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a grid-based distribution network line path automatic planning method based on digital twinning, which solves the problems mentioned in the background art.

[0005] To achieve the above purpose, the present application is realized by the following technical scheme: a grid-based distribution network line path automatic planning method based on digital twinning, comprising the following steps:

[0006] A1, the computing device collects the line drawing of the historical construction distribution network line area, and repairs and completes the image of the line drawing through a generative adversarial network to repair and complete the fuzzy and incomplete information of the line drawing, identifies and labels the non-standard specifications and parameters in the line drawing, and generates a non-standard data set;

[0007] The line drawing information is unified to the corresponding coordinate system, and the offset coordinate system is corrected, and the digital twinning model is derived after correction;

[0008] A2, the digital twinning model is imported into the distribution network line drawing to be constructed, the distribution network line drawing is compared with the non-standard data set to confirm the non-standard information, and a corresponding image model is generated;

[0009] The image model is used to divide the grid unit drawing according to the preset accuracy, input the starting point and the ending point of the distribution network line in the grid unit drawing, calculate the shortest path, and generate a candidate path;

[0010] A3, obtain municipal planning information, import the municipal planning information into the digital twin model to generate a conflict detection drawing, and superimpose the conflict detection drawing on the grid cell drawing to detect the conflict relationship of the candidate path;

[0011] When no conflict is detected, the preselected candidate path is marked; when there is a conflict, the path is marked for deletion and returned to step A2 for re-generation;

[0012] A4, using the digital twin model to simulate the authenticity of the preselected candidate path, and verifying the feasibility of the preselected candidate path;

[0013] If the simulation verification is feasible, the distribution network line path is confirmed; if the simulation verification is not feasible, the process returns to step A2 for re-generation until the distribution network line path is confirmed.

[0014] Preferably, the distribution network line drawing contains geographic data, distribution network equipment data, and environmental data, the grid cell drawing is pre-set to have an accuracy of 50m x 50m for urban areas with dense buildings, and an accuracy of 100m x 100m for flat areas without special construction on the ground or underground.

[0015] Preferably, the grid cell drawing is labeled with a grid number and a function label, the function label includes an industrial area, a residential area, a commercial area, and an ecological area corresponding to the grid cell drawing, and the grid number is numbered in the format of area code-row number-column number.

[0016] Preferably, the authenticity route selection scenario simulation includes:

[0017] The simulation data of the line in the distribution network line path under extreme environment, peak load of power grid, and load growth scenario in the next 5 years, the number of simulation times of the authenticity route selection scenario simulation is 3-5 times, the simulation data results are averaged to confirm the path selection feasibility of the distribution network line path.

[0018] Preferably, the coordinate system adopts the global unified coordinate system WGS-84 coordinate system standard, the satellite positioning system adopts the global satellite positioning system GPS system, the deviation of the corrected coordinate system is not more than 0.5m, and the line drawing is a dwg format file.

[0019] Preferably, the municipal planning information includes road red line, underground pipeline distribution, rail transit, protected area, and ecological protection range, and corresponding municipal planning drawing, the conflict detection drawing uses spatial overlay analysis, that is, the candidate path is superimposed on the layer of the conflict detection drawing, and the blocking and influence relationship of the path on the municipal planning information is analyzed according to the overlap analysis of the municipal planning information and the candidate path in the conflict detection drawing.

[0020] Preferably, the evaluation index of the feasibility verification includes the construction cost of the distribution network line, the construction difficulty, the safety distance compliance rate, and the compatibility with the municipal planning, and each index meets the preset threshold value, and the evaluation is "yes", otherwise, the index does not meet the preset threshold value, and the evaluation is "no".

[0021] Preferably, the shortest path is calculated by using the Dijkstra algorithm of the single-source shortest path problem, and the algorithm steps of the Dijkstra algorithm are as follows:

[0022] Before executing the algorithm, the grid cell drawing in step A2 is completed, and the starting point s and the terminal point t of the distribution network line are clearly corresponding to the marker points of the grid;

[0023] A5.1, there is a weighted graph G=(V, E), wherein V is a set of grid marker points, E is a set of grid edges, and for the grid point sV of the grid cell drawing, the shortest path Dijkstra algorithm from s to all other points in G requires three data structures, namely, an S set storing the shortest path of the explored points, a U set storing the shortest path of the unexplored points, and a D array storing the shortest distance value of each point;

[0024] A5.2, the S set only contains the starting point s of the grid cell drawing, the U set contains all the remaining points of the grid cell drawing, the shortest path of the starting point s is 0, the value in the D array is 0, and the shortest path value of the other points is infinite;

[0025] A5.3, select the grid marker point u with the minimum value in the D array from the U set, and move the grid marker point u from the U set to the S set;

[0026] A5.4, traverse all adjacent grid marker points v of the grid marker point u, calculate the temporary distance from the starting point s to the adjacent grid marker point v through the grid marker point u, and when the temporary distance is less than D[v], update D[v]=temporary distance, and record P[v]=u, wherein P is a predecessor node record array, and the predecessor node record array is used to store the shortest path predecessor node of each grid marker point for subsequent path backtracking;

[0027] A5.5, repeat step A5.3 until the terminal point t is moved to the S set, and at this time, D[t] is the shortest path distance from the starting point to the terminal point;

[0028] A5.6, starting from the terminal point t, backtracking is performed through the predecessor node array, and the sequence of the grid marker points u obtained by backtracking is arranged in order, thereby generating the candidate path of the distribution network line.

[0029] Preferably, the generative adversarial network is a GAN network, the training sample of the generative adversarial network includes 3000 or more fuzzy and incomplete distribution network line drawings, the image information integrity of the repaired and completed distribution network line drawing is not less than 95%, and the identification label of non-standard specifications and parameters in the distribution network line drawing includes coordinates, sizes, device models and electrical parameters of the image.

[0030] A computer device, characterized in that the computer device comprises a processor and a memory, the memory stores at least one program code, the at least one program code is loaded and executed by the processor to use the computer device to realize the grid-based distribution network line path automatic planning method based on digital twinning.

[0031] The application provides a grid-based distribution network line path automatic planning method based on digital twinning.

[0032] (1) By constructing a digital twinning model that can accurately reflect the full-factor state of the distribution network, the model is used to deeply match the path planning with the actual geographical environment, device parameters and environmental data, so that the planned scheme is highly consistent with the actual scene, and the grid-based path design idea is designed, so that the subsequent distribution network line path planning is more intuitive and efficient, and the grid-based path planning model is used to realize automatic path planning, effectively reducing the deviation of the path from the actual situation and improving the accuracy of the distribution network line planning.

[0033] (2) By using the grid processing and digital twinning model of the distribution network line drawing, the selection of the distribution network line path can be quickly calculated through the point-to-point of the grid, the shortest line path in the grid unit can be quickly identified, and through the simulation verification of the municipal planning information and the digital twinning model, the feasibility of the line path can be verified, and the most suitable line path can be selected, thereby improving the efficiency, safety and accuracy of the distribution network line path automatic planning.

[0034] (3) In the path generation process, municipal planning data is fused for conflict detection and adjustment under multi-field constraints, so that the candidate path can fully meet the external constraint requirements such as urban space layout and functional division, the path and municipal planning are cooperatively adapted, the spatial conflict between the path and municipal facilities is reduced, and the overall efficiency of the distribution network line planning and the safety of the selected line path are improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] Fig. 1 The application provides a planning flowchart of the grid-based distribution network line path automatic planning method based on digital twinning.

[0036] Fig. 2 A grid-based distribution network line path automatic planning method based on digital twinning. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0038] Embodiment 1

[0039] Please refer to Figs. 1-2 The present application provides a grid-based distribution network line path automatic planning method based on digital twinning. To achieve the above purpose, the present application is implemented by the following technical solutions: comprising the following steps:

[0040] A1, the computing device collects the line drawing of the historical construction distribution network line area, and repairs and completes the image of the line drawing by generating a generative adversarial network to blur and defect information, identifies and labels the non-standard specifications and parameters in the line drawing, and generates a non-standard data set;

[0041] The line drawing information is unified to the corresponding coordinate system, and the offset coordinate system is corrected, and the digital twinning model is derived after correction;

[0042] A2, the digital twinning model is used to import the distribution network line drawing to be constructed, the non-standard information is confirmed by comparing the distribution network line drawing with the non-standard data set, and the corresponding image model is generated;

[0043] The image model is used to divide the grid unit drawing according to the preset accuracy, the starting point and the end point of the distribution network line are input in the grid unit drawing, the shortest path is calculated, and the candidate path is generated;

[0044] A3, the municipal planning information is obtained, the municipal planning information is imported into the digital twinning model to generate a conflict detection drawing, and the conflict detection drawing and the grid unit drawing are superimposed to detect the conflict relationship of the candidate path;

[0045] When there is no conflict, the preselected candidate path is marked; when there is a conflict, the path is deleted and step A2 is returned to regenerate;

[0046] A4, the digital twinning model is used to simulate the reality of the preselected candidate path, and the feasibility of the preselected candidate path is verified by simulation;

[0047] When the simulation verification is feasible, the distribution network line path is confirmed; when the simulation verification is not feasible, step A2 is returned to regenerate until the distribution network line path is confirmed.

[0048] In this embodiment, the path planning of the distribution network line is realized through the digital twin model and the grid planning. When the digital twin model is created, the historical geographic data of the distribution network line path, the distribution network equipment data, and the environmental data of the line drawing are used as training data. The geographic data is the geographic image of the distribution network line region, the distribution network equipment data is the distribution network line and distribution network equipment parameters, and the environmental data is the building, pipeline, terrain, and vegetation image in the geographic data. The data amount is not less than 3000 groups. The line drawing is first repaired and completed by the Gan network for the fuzzy and incomplete parts.

[0049] When the digital twin model is generated, the computing device uses the target detection algorithm YOLOv8 model as a pre-training model, imports the repaired line drawing into the YOLOv8 model, and simplifies the YOLOv8 model call level, only the feature extraction function is retained. The simplified YOLOv8 model can reduce the computer device burden in the YOLOv8 model running process, only the required related features need to be extracted. The YOLOv8 model identifies some non-industry standard equipment lines and other specifications and parameters in the imported line drawing. Before this, the YOLOv8 model needs to import the industry standard equipment lines and other specifications and parameters in advance. In this way, non-standard specifications and parameters can be identified. Then the YOLOv8 model identifies and learns a large number of non-standard specifications and parameters in the line drawing, and generates a non-standard data set corresponding to the non-standard specification and parameter identification. Then the geographic data, distribution network equipment data, and environmental data in the learned line drawing are combined, and then mapped into the YOLOv8 model. The geographic data, distribution network equipment data, and environmental data of each group of line drawings are aligned and combined in the form of coordinate systems. Then the data of the satellite positioning system is called to correct the corresponding combined coordinate system to ensure that the image is accurate. After the training combination is completed, a group of regional models of the distribution network line path selection planning can be obtained. The extraction, training combination, and other processes of a large amount of data generate a corresponding digital twin model.

[0050] When the path planning of the distribution network line is needed, the distribution network line drawing of this distribution network construction can be imported into the digital twin model, and then the non-standard specification and parameter graphics saved by the non-standard data set are compared with the distribution network line drawing of this time, the graphics in the distribution network line drawing are recognized and the non-standard specification and parameter equipment, line and construction information in the non-standard data set are automatically matched, and a path planning model of the distribution network area can be obtained through the above steps and exported. Then the model is opened by the application software of the digital twin model (CIMPro twin master) on the computer, and the plan image of the model is meshed and divided in the two-dimensional working space. The size of each grid is consistent, and the real geographical scale is 1:50 or 1:100. The scale is adjusted according to the complexity of the terrain. After the two-dimensional image of the model is meshed, each grid is numbered and labeled with a function tag.

[0051] Then the Dijkstra algorithm is used to calculate and design the path of the distribution network line in the grid, to generate a candidate path, and then the future planning information of the corresponding area is imported into the digital twin model software to overlap with the candidate path in the form of a superimposed layer to identify whether there is future construction interference. If there is no interference, the candidate path is confirmed. If there is interference, a new shortest path is calculated by removing the above candidate path, and the interference test is performed again until there is no interference. The confirmed interference-free candidate path is simulated and verified to verify whether the use of the distribution network line in the future use process may encounter use conditions in the line environment, whether accelerated aging will occur due to environmental and surrounding power factors, and whether the use effect and service life will be affected. Therefore, after simulation verification, the candidate path is determined as the final construction path. Otherwise, the candidate path is returned to the calculation, and the optimal solution of the distribution network line path planning is repeatedly verified.

[0052] Embodiment 2

[0053] Specifically, the distribution network line drawing contains geographical data, distribution network equipment data and environmental data. The grid unit drawing is preset with an accuracy of 50m x 50m for urban building-intensive areas, and 100m x 100m for flat and ground and bottom without special construction buildings or equipment.

[0054] The grid unit drawing has a grid number and a function tag. The function tag includes the industrial area, residential area, commercial area and ecological area corresponding to the grid unit drawing. The grid number is numbered in the format of area code-row number-column number.

[0055] The authenticity route selection scene simulation includes:

[0056] The line in the distribution network line path is simulated in extreme environment, power grid load peak and future 5-year load growth scenario, the simulation times of the real line selection scenario simulation are 3-5 times, the simulation data results are averaged, and the path selection feasibility of the distribution network line path is confirmed.

[0057] The coordinate system adopts the global unified coordinate system WGS-84 coordinate system standard, the satellite positioning system adopts the global satellite positioning system GPS system, the deviation of the corrected coordinate system is not more than 0.5 m, and the line drawing is a drawing format dwg format file.

[0058] The municipal planning information includes: road red line, underground pipeline distribution, rail transit, protection area and ecological protection range and corresponding municipal planning drawing, the conflict detection drawing adopts spatial superposition analysis, that is, the candidate path is superimposed on the layer of the conflict detection drawing, and the blocking and influence relationship of the path to the municipal planning information is analyzed according to the municipal planning information in the conflict detection drawing and the candidate path superposition analysis.

[0059] The generative adversarial network is a GAN network, the training sample of the generative adversarial network includes more than 3000 blurred and incomplete distribution network line drawings, the information integrity of the repaired and completed distribution network line drawing image is not less than 95%, and the identification and labeling of non-standard specifications and parameters in the distribution network line drawing include: coordinates, size, equipment model and electrical parameters of the image

[0060] In the embodiment, the WGS-84 coordinate system has an ellipsoid parameter of a major semi-axis of 6378137 meters and a flattening of 1 / 298.257223563, which is the current standard and is suitable for global geographic positioning, providing a unified reference for the spatial coordinate system alignment of the data in the method. The satellite positioning system GPS has a positioning accuracy of centimeter level through receiving the three-dimensional coordinates of the ranging signals of at least four satellites, and the deviation is corrected by using the linear interpolation method to ensure that the overall deviation after correction is not more than 0.5 m.

[0061] The industrial area label corresponds to the factory aggregation area, and needs to match the line capacity of high-load equipment, the residential area label corresponds to the residential aggregation area, and needs to give priority to the safety distance between the line and the building and the landscape influence, the commercial area label corresponds to the shop aggregation area, and needs to focus on avoiding underground pipelines (such as gas pipes and communication optical cables), the ecological area label corresponds to natural protection areas, wetland parks and the like, and needs to strictly limit the line crossing, so it can be known which grid points in the grid area cannot perform path selection of the line, and the efficiency of path selection is improved.

[0062] The GAN network training repair uses more than 3000 pieces of distribution network line drawing paper containing blur (such as scanning noise and line blurring) and defects (such as local line segment loss and symbol breakage). The repair and completion are realized through the adversarial training of the generator and the discriminator of the GAN network. Based on the complete drawing verified by artificial checking, when the matching degree of the contour and symbol of the repaired graph element with the reference graph is greater than or equal to 95%, it is determined that the information is complete;

[0063] The feasibility is verified, the construction cost including materials (cables, towers and lines), construction (excavation, laying and labor) and future operation and maintenance expenses are verified, the preset threshold is not more than the construction budget, the construction difficulty is divided into low, medium and high levels according to the complexity of the terrain and the number of obstacles, the threshold is medium and below, the safety distance compliance rate refers to the proportion of path segments that meet the distance required by the industry, the threshold is greater than or equal to 95%, the municipal planning fit degree refers to the coordination degree of the path and the municipal planning (such as avoiding the area to be built), the threshold is greater than or equal to 90%, and each index meets the threshold, and the evaluation is "yes", otherwise it is "no";

[0064] In the grid division, 50m*50m is adopted for the urban building dense area, and 100m*100m is adopted for the flat area without special construction of buildings or equipment on the ground and the bottom, so as to reduce the model pressure of the planning grid, and the 50m*50m grid can be used for more detailed line planning in the urban building dense area.

[0065] Embodiment 3

[0066] Specifically, the shortest path is calculated by using the Dijkstra algorithm of the single-source shortest path problem, and the algorithm steps of the Dijkstra algorithm are as follows:

[0067] Before executing the algorithm, the grid unit drawing in step A2 is completed, and the starting point s and the terminal point t of the distribution network line are clearly corresponding to the marker points of the grid unit;

[0068] A5.1, there is a weighted graph G=(V, E), wherein V is a set of grid marker points, E is a set of grid edges, and for the grid point sV of the grid unit drawing, the shortest path Dijkstra algorithm requires three data structures, three data structures are S set: store the shortest path of the explored point, U set: store the shortest path of the unexplored point, and D array: store the shortest distance value of each point;

[0069] A5.2, initialize the S set to contain only the starting point s of the grid unit drawing, the U set contains all the remaining points of the grid unit drawing, the shortest path of the starting point s is 0, the value in the D array is 0, and the shortest path value of the other points is infinite;

[0070] A5.3, select a grid marker point u with the smallest D array value from the U set, and move the grid marker point u from the U set to the S set;

[0071] A5.4, traverse all adjacent grid marker points v of the grid marker point u, calculate a temporary distance from the starting point s to the adjacent grid marker point v via the grid marker point u, when the temporary distance < D[v], update D[v] = the temporary distance, and record P[v] = u, wherein P is a predecessor node record array, and the predecessor node record array is used to store the shortest path predecessor node of each grid marker point for subsequent path backtracking;

[0072] A5.5, repeat step A5.3 until the terminal point t is moved to the S set, at this time D[t] is the shortest path distance from the starting point to the terminal point;

[0073] A5.6, start from the terminal point t, backtrace through the predecessor node array, arrange the grid marker point u sequence obtained by backtracking in order, that is, generate a candidate path of the distribution network line;

[0074] In this embodiment, the implementation of the Dijkstra algorithm needs to be based on a grid unit drawing, and the specific process is as follows: taking the center point of each grid unit drawing as a node, the node number corresponds to the grid number, a directed edge between nodes is established, the initial weight of the edge is set as the straight-line distance between the two nodes, the structure of the graph is stored by using an adjacency list to reduce the storage space, a priority queue is used to store the nodes to be processed to improve the node extraction efficiency, the time complexity of the algorithm is optimized to O, the shortest distance of the node of the starting point is set to 0, and the shortest distances of other nodes are set to infinity, the priority queue is initialized to only contain the node of the starting point, and the priority of the node is 0, the node with the minimum distance is extracted from the priority queue, all adjacent nodes of the node are traversed, the distance from the starting point to the adjacent node via the minimum node is calculated, if the distance is smaller than the current shortest distance of the adjacent node, the shortest distance of the adjacent node is updated, and the adjacent node is inserted into the priority queue, the process is repeated until the priority queue is empty, when the path selection is completed, the node sequence of the shortest path is obtained by backtracking from the terminal node to the starting point through the recorded predecessor nodes, that is, the grid path of the distribution network line;

[0075] By optimizing the implementation details of the Dijkstra algorithm, the efficiency and accuracy of path calculation are improved, and it is ensured that the shortest path can be quickly found in a large-scale grid. The quantitative calculation of the path synthesis cost considers multiple dimensions, the dynamic adjustment of the proportion coefficient makes the path planning adapt to different planning targets, and the flexibility and applicability of the path scheme are improved.

[0076] Embodiment 4

[0077] Specifically: a computer device, the computer device comprising a processor and a memory, the memory storing at least one program code, the at least one program code being loaded and executed by the processor to use the computer device to implement a kind of grid-based distribution network line path automatic planning method based on digital twinning

[0078] The present application can be implemented by software, hardware, firmware or any combination thereof, in whole or in part. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the flow or function according to the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in or transmitted by a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (e.g., coaxial cable, optical fiber, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that the computer can access or a data processing device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (e.g., floppy disk, hard disk, magnetic tape), optical media (e.g., DVD) or semiconductor media (e.g., solid state disk (SSD)) and the like.

[0079] Although the embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the present application.

Claims

1. A meshed distribution network line path automatic planning method based on digital twinning, characterized in that, The method comprises the following steps: A1, the computing device collects historical construction of the line layout of the line layout area, and the image of the line layout is blurred and the missing information is repaired and completed by generating a generative adversarial network, and the non-standard specification and parameter identification label in the line layout is generated, and a non-standard data set is generated; The line layout information is unified to the corresponding coordinate system, and the offset coordinate system is corrected, and the digital twin model is derived after correction; A2, using the digital twin model to import the line layout of the line layout of the line layout, the line layout is compared with the non-standard data set to confirm the non-standard information, and the corresponding image model is generated; The image model is used to divide the grid unit layout according to the preset accuracy, the starting point and the ending point of the line layout are input in the grid unit layout, the shortest path is calculated, and the candidate path is generated; A3, get the municipal planning information, import the digital twin model to generate conflict detection layout, and the conflict detection layout is superimposed with the grid unit layout to detect the conflict relationship of the candidate path; When there is no conflict, the preselected candidate path is marked, and when there is conflict, the path is deleted and step A2 is returned to regenerate; A4, using the digital twin model to simulate the authenticity of the preselected candidate path, and verifying the feasibility of the preselected candidate path; When the simulation verification is feasible, the line layout path is confirmed, and when the simulation verification is not feasible, step A2 is returned to regenerate until the line layout path is confirmed.

2. The grid-based distribution network line path automatic planning method based on digital twinning according to claim 1, characterized in that, The line layout of the line layout contains geographic data, line layout device data and environmental data, the grid unit layout preset accuracy is 50m*50m in the city building dense area, and 100m*100m in the case of flat ground and no special construction of buildings or equipment.

3. The grid-based distribution network line path automatic planning method based on digital twinning of claim 1, wherein, The grid unit layout is labeled with grid number and function label, the function label includes industrial area, residential area, commercial area and ecological area corresponding to the grid unit layout, and the grid number is numbered in the format of area code-row number-column number.

4. The grid-based distribution network line path automatic planning method based on digital twinning of claim 1, wherein, The authenticity of the line selection scene simulation includes: The line in the line layout path is simulated in the extreme environment, peak load of power grid and future 5 years load growth scene, the simulation times of the authenticity of the line selection scene simulation is 3-5 times, the simulation data result is taken as the average value, and the path selection feasibility of the line layout path is confirmed.

5. The grid-based distribution network line path automatic planning method based on digital twinning of claim 1, wherein, The coordinate system adopts the global unified coordinate system WGS-84 coordinate system standard, the satellite positioning system adopts the global satellite positioning system GPS system, the deviation of the corrected coordinate system is not more than 0.5m, and the line layout is a drawing format dwg format file.

6. The grid-based distribution network line path automatic planning method based on digital twinning of claim 1, wherein, The municipal planning information includes road red line, underground pipeline distribution, rail transit, protected area and ecological protection range and corresponding municipal planning drawings, the conflict detection drawing adopts spatial overlay analysis, that is, the candidate path is superimposed on the layer of the conflict detection drawing, and the blocking and influence relationship of the path on the municipal planning information is analyzed according to the overlap analysis of the municipal planning information in the conflict detection drawing and the candidate path.

7. The grid-based distribution network line path automatic planning method based on digital twinning of claim 1, wherein, The evaluation indexes of the feasibility verification include construction cost, construction difficulty, safety distance compliance rate and municipal planning fitting degree of the distribution network line, and the evaluation is "yes" when each index meets the preset threshold, and the evaluation is "no" when the index does not meet the preset threshold.

8. The grid-based distribution network line path automatic planning method based on digital twinning of claim 1, wherein, The shortest path is calculated by using the Dijkstra algorithm of the single-source shortest path problem, and the algorithm steps of the Dijkstra algorithm are as follows: Before executing the algorithm, the generation of the grid cell drawing in step A2 is completed, and the starting point s and the terminal point t of the distribution network line are clearly corresponding to the mark points of the grid cells; A5.1, there is a weighted graph G=(V, E), wherein V is a set of grid mark points, E is a set of grid edges, and for the grid point sV of the grid cell drawing, the shortest path Dijkstra algorithm requires three data structures, the S set: storing the shortest path of the explored point, the U set: storing the shortest path of the unexplored point, and the D array: storing the shortest distance value of each point; A5.2, the S set only contains the starting point s of the grid cell drawing, the U set contains all the remaining points of the grid cell drawing, the shortest path of the starting point s is 0, the value in the D array is 0, and the shortest path value of the other points is infinite; A5.3, select the grid mark point u with the minimum D array value from the U set, and move the grid mark point u from the U set to the S set; A5.4, traverse all adjacent grid mark points v of the grid mark point u, calculate the temporary distance from the starting point s to the adjacent grid mark point v through the grid mark point u, and when the temporary distance is less than D[v], update D[v]=temporary distance, and record P[v]=u, wherein P is a predecessor node record array, and the predecessor node record array is used for subsequent path backtracking and stores the shortest path predecessor node of each grid mark point; A5.5, repeat step A5.3 until the terminal point t is moved to the S set, at this time, D[t] is the shortest path distance from the starting point to the terminal point; A5.6, start from the terminal point t, backtrace through the predecessor node array, arrange the grid mark point u sequence obtained by backtracking in order, and generate the candidate path of the distribution network line.

9. The grid-based distribution network line path automatic planning method based on digital twinning of claim 1, wherein, The generated adversarial network is a GAN network, training samples of the generated adversarial network include more than 3000 blurred and incomplete distribution network line drawings, the image information integrity of the repaired and completed distribution network line drawings is not less than 95%, and the identification and labeling of non-standard specifications and parameters in the distribution network line drawings include coordinates, sizes, device models and electrical parameters.

10. A computer device, comprising: The computer device includes a processor and a memory, and the memory stores at least one program code, the at least one program code is loaded and executed by the processor to use the computer device to realize the grid-based distribution network line path automatic planning method based on digital twinning as any one of claims 1-9.

Images