A multi-dimensional data processing and modeling method for urban lifeline safety construction

Abstract

The application discloses a kind of multi-dimensional data processing and modeling method for urban lifeline safety construction, gas line maintenance technical field, including acquisition multi-dimensional data, the pre-processing of city area map and gas pipe network distribution data, then coordinate alignment is carried out, gas pipe network attribute data is associated with city gas pipe network distribution diagram, obtains maintenance accident data, the position corresponding to maintenance accident data is mapped to city gas pipe network distribution diagram, the coordinate of accident position in three-dimensional coordinate system is obtained, historical accident data is integrated into three-dimensional model according to time sequence, and three-dimensional city gas pipe network model is obtained;In the process of coordinate alignment, feature point extraction and space deduplication and other technologies are used, and the optimal feature point is selected as reference for coordinate conversion, to reduce the workload of reference object labeling in advance, while ensuring that the space coverage of coordinate alignment meets the requirements of engineering specifications, the efficiency and accuracy of coordinate alignment are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of gas line maintenance, and more particularly relates to a multi-dimensional data processing and modeling method for urban lifeline safety construction. BACKGROUND

[0002] Urban lifeline safety construction refers to ensuring the safe operation of urban key infrastructure through technical means and management strategies, preventing accidents and improving urban resilience. The core goal is to reduce the probability of accidents such as gas explosions, bridge collapses, and waterlogging through real-time monitoring, risk assessment, and intelligent early warning, ensuring the normal operation of urban functions and the safety of residents' lives and property.

[0003] By establishing a model based on real-time monitoring data and environmental data of urban gas, water supply, drainage, and bridge lifeline systems, early hidden danger identification of the city is achieved. However, for mountainous cities, due to large terrain undulations and complex geological conditions, underground pipe networks are prone to corrosion and displacement risks, and bridges and tunnels are vulnerable to landslides and settlement threats. Moreover, data sources are extensive, requiring modeling of various types of urban lifelines, including gas lines, water supply lines, drainage lines, and bridges. Among them, gas lines are important and have a high risk of accidents, making their modeling particularly important.

[0004] In actual modeling, city maps and gas pipeline maps need to be aligned. In existing technologies, to meet spatial coverage, large areas and reference objects are selected as reference bases for alignment, which increases the workload, especially in mountainous areas.

[0005] Moreover, urban gas pipe networks are distributed in different depth spaces, including surface pressure regulating stations, meters, and other facilities, shallow underground main pipelines, and deep underground pipelines. Traditional single plane coordinate systems cannot accurately represent the complex spatial relationships between these different depth pipe networks, such as three-dimensional intersections and upper and lower layer avoidance, leading to problems such as ambiguous pipe network positioning and collision conflicts. For example, shallow main pipelines and deep river-crossing pipelines may appear to overlap in the same plane coordinate system. SUMMARY

[0006] To solve the above problems, the application provides a multi-dimensional data processing and modeling method for urban lifeline safety construction.

[0007] The application provides a multi-dimensional data processing and modeling method for urban lifeline safety construction, including the following steps:

[0008] S1, collect multi-dimensional data, including city area map data, gas pipe network distribution data, gas pipe network attribute data, and maintenance accident data;

[0009] S2. Preprocess the urban area map and gas pipeline distribution data, then perform coordinate alignment, and overlay the gas pipeline distribution data onto the urban area map;

[0010] S3. Associate the gas pipeline network attribute data with the urban gas pipeline network distribution map, and bind the gas pipeline network attribute data to the corresponding gas pipeline network segment;

[0011] S4. For each independent management area, select the feature point with the highest coverage density from the reference feature points selected in S2 as a candidate node, ensuring that there is at least one candidate point in each management area, and obtain the candidate point set.

[0012] The typical depth value of each independent management area is extracted from the candidate point set. Then, the hierarchical boundary threshold is calculated based on the gas pipeline network attribute data and the candidate point set. Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer. Each layer is assigned an independent coordinate system. The three-level coordinate system with hierarchical relationship is output. A three-dimensional coordinate system is established for the urban gas pipeline network distribution map. Then, the three-dimensional position coordinates of the gas pipeline network line segment in each independent management area are obtained.

[0013] Acquire maintenance accident data, map the location corresponding to the maintenance accident data to the urban gas pipeline network distribution map, and obtain the coordinates of the accident location in the three-dimensional coordinate system;

[0014] Historical accident data is integrated into a three-dimensional model according to time series to obtain a three-dimensional urban gas pipeline network model;

[0015] S5. Based on the three-dimensional urban gas pipeline network model, a risk assessment model is constructed. The risk assessment model receives the data provided by the three-dimensional urban gas pipeline network model and outputs the risk assessment results of each independent management area in the three-dimensional urban gas pipeline network model.

[0016] Preferably, step S2 includes the following steps:

[0017] S21. Collect urban area map data and gas pipeline network distribution data, and perform integrity checks on them, supplementing any missing information;

[0018] S22. Select a unified geographic coordinate system, and convert the urban area map data and gas pipeline network distribution data to the unified coordinate system to complete the coordinate alignment.

[0019] S23. Overlay the coordinate-aligned gas pipeline distribution data with the urban area map to merge the gas pipeline distribution data into the urban area map and generate an urban gas pipeline distribution map.

[0020] Preferably, the specific working steps of S22 further include the following:

[0021] First, feature point extraction is performed. For urban area maps, road intersections, corner points of independent buildings, and bridge endpoints are extracted as the first type of feature points.

[0022] For gas pipeline network distribution data, valve nodes and pipeline inflection points are extracted as the second type of feature points;

[0023] Then set a distance threshold. Spatial deduplication is performed on the first type of feature points and the second type of feature points;

[0024] The first type of feature points and the second type of feature points are respectively formed into two feature point sets. The point closest to the boundary in the first type of feature points and the second type of feature points are selected as the base point. With the base point as the origin, the polar angle of all other points relative to the base point is calculated and sorted in the counterclockwise direction.

[0025] For both feature point sets, a stack is used to construct the convex hull. The base point and the first two sorted points are pushed onto the stack. Then, the sorted feature point set is traversed sequentially. For each new point, it is checked whether the three points at the top of the stack form a right turn. If it is a right turn, the point at the top of the stack is popped. Otherwise, the new point is pushed onto the stack. The points in the stack constitute the vertices of the convex hull. All the vertices of the convex hull are used as the selected reference feature points to obtain the first type of reference feature points and the second type of reference feature points.

[0026] The urban area map data and gas pipeline distribution data are converted to this unified coordinate system based on the first type of reference feature points and the second type of reference feature points.

[0027] Preferably, the specific steps for converting urban area map data and gas pipeline distribution data to the unified coordinate system based on the first type of reference feature points and the second type of reference feature points are as follows:

[0028] The first and second type of reference feature points obtained earlier are used as pairs of points with the same name.

[0029] Using the seven-parameter conversion function of GIS software, input these pairs of points with the same name and calculate the parameters that need to be adjusted.

[0030] The calculated seven parameters are applied to the entire gas pipeline network distribution dataset. Using the conversion tools of GIS software or programming tools, the gas pipeline network data is batch converted from the original coordinate system to the target unified coordinate system.

[0031] Preferably, step S3 includes the following steps:

[0032] S31. Obtain the boundary of the urban gas supply area and extract the boundary information of the urban gas supply area from the urban area map data.

[0033] Based on the extracted urban gas supply area boundaries, the urban gas pipeline network distribution map is divided into multiple independent management areas, each representing a specific gas supply area.

[0034] S32. In the gas pipeline network distribution data, identify the start and end points of each gas pipeline network segment, and mark a continuous gas pipeline network segment as a gas pipeline network segment from the start to the end point.

[0035] S33. Organize the attribute information related to the gas pipeline network, specifically including data on gas pipeline material, diameter, and wall thickness.

[0036] The collected gas pipeline network attribute data is associated with the corresponding pipeline segments, and a database is created to store each pipeline segment and its associated attribute data, assigning a unique ID to each gas pipeline segment.

[0037] A preliminary urban gas pipeline network distribution map is generated. The established pipeline attribute database is then combined with the urban gas pipeline network distribution map to generate a preliminary urban gas pipeline network distribution map containing detailed attribute information.

[0038] Preferably, step S4 includes the following steps:

[0039] S41. For each independent management area, select the feature point with the highest coverage density from the reference feature points selected in S2 as a candidate node, ensuring that there is at least one candidate point in each management area, and obtain the candidate point set.

[0040] S42 extracts the typical depth value of each independent management area from the candidate point set, and then calculates the hierarchical boundary threshold based on the gas pipeline network attribute data and the candidate point set. Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer, and each layer is assigned an independent coordinate system. The output is a coordinate system with hierarchical relationship of three levels.

[0041] Extract the branch structure of each independent management area within the gas pipeline network distribution data. Starting from the main pipeline, generate a local coordinate system tree according to the branch hierarchy. Merge the local coordinate system with the overall three-level coordinate system to obtain the three-dimensional position coordinates of the gas pipeline network segments within each independent management area.

[0042] S43. Extract the accident location description from the maintenance accident data, obtain the location information of the maintenance accident based on the accident location description, map the location corresponding to the maintenance accident data to a three-level coordinate system, and obtain the three-dimensional location coordinates of the accident location in the gas pipeline segment.

[0043] S44. Establish a three-dimensional urban gas pipeline network model based on the three-level coordinate system and the three-dimensional position coordinates of the gas pipeline network segments. Integrate historical accident data according to the time series to obtain a maintenance accident data dataset. Mark the maintenance accident data dataset at the coordinate position of the accident corresponding to the gas pipeline network segment. Specifically, it includes the three-dimensional coordinates of the accident point, the time of occurrence, and the maintenance accident data.

[0044] Preferably, the specific steps of S42 are as follows:

[0045] First, extract the typical depth value of each independent management area from the candidate point set;

[0046] Then, based on the gas pipeline network attributes and typical depth values, the hierarchical boundary threshold is calculated. ;

[0047] Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer;

[0048] Calculated hierarchical boundary threshold The boundary value used to distinguish between shallow and deep layers is assigned to an independent coordinate system for each layer;

[0049] Extract the branch structure of each independent management area within the gas pipeline network distribution data. Starting from the main pipeline, generate a local coordinate system tree according to the branch hierarchy, and then integrate the local coordinate system with the overall three-level coordinate system.

[0050] Preferably, the specific steps of S43 are as follows;

[0051] Based on the description of the accident location and the distribution data of the gas pipeline network, determine whether the accident occurred in the surface layer, shallow layer, or deep layer; convert the geographical coordinates of the accident location into coordinates in three-level coordinate systems; and based on the common reference point and coordinate transformation parameters, convert the latitude and longitude coordinates of the accident location into three-dimensional coordinates in the surface layer, shallow layer, or deep layer coordinate system.

[0052] The specific steps of S44 are as follows:

[0053] The three-level coordinate system and the three-dimensional position coordinate data of the gas pipeline network segments were integrated together, and a three-dimensional model of the gas pipeline network was constructed based on the three-dimensional coordinates of the pipeline network segments using three-dimensional modeling software.

[0054] Add gas pipeline attribute data to each gas pipeline segment in the gas pipeline network model;

[0055] The collected maintenance accident data is sorted according to the time of occurrence to form a time series. Based on the sorted historical accident data, a maintenance accident data dataset is created, and the maintenance accident data dataset is marked on the coordinate position of the accident corresponding to the gas pipeline segment.

[0056] In the three-dimensional urban gas pipeline network model, the maintenance accident data set is associated with the corresponding pipeline segment based on the three-dimensional coordinates of the accident point.

[0057] Preferably, step S5 includes the following steps:

[0058] S51. Install sensors on each gas pipeline segment to collect the operating status of each gas pipeline segment.

[0059] Based on a 3D urban gas pipeline network model, the operational status of each gas pipeline segment is input to construct a risk assessment model;

[0060] S52. The risk assessment model receives data from the three-dimensional urban gas pipeline network model in real time, including the pipeline topology of each independent management area, maintenance data, and equipment operating status. Using the constructed risk assessment model, it performs risk assessment calculations on the gas pipeline network of each independent management area. Based on the risk assessment calculation results of each independent management area, it identifies independent management areas with higher risks and major risk factors. Based on the assessment results, it dynamically adjusts the parameters of the risk assessment model.

[0061] Preferably, the specific working steps of S52 are as follows:

[0062] Based on the preprocessed operational status data, pipeline topology, and maintenance data, feature vectors are constructed.

[0063] The constructed feature vectors are input into the risk assessment model to perform risk assessment calculations on the gas pipeline network of each independent management area.

[0064] The risk values ​​output by the model are analyzed to determine the risk level. Based on the actual situation of the gas pipeline network and safety standards, risk thresholds are set, and the risk levels are divided into three levels: low, medium, and high. The risk level distribution of each independent management area is statistically analyzed, and the independent management area with the highest risk is identified.

[0065] Based on the assessment results, the parameters of the risk assessment model are dynamically adjusted, and the monitoring frequency is increased for the independently managed areas with the highest risk.

[0066] Beneficial effects: Through multi-dimensional data collection, relevant information on urban gas pipeline networks is comprehensively integrated, providing a rich and accurate data foundation for subsequent modeling and risk assessment;

[0067] During the coordinate alignment process, techniques such as feature point extraction and spatial deduplication are used to select the optimal feature point as a reference for coordinate transformation, reducing the workload of pre-annotating reference objects, while ensuring that the spatial coverage of coordinate alignment meets the requirements of engineering specifications, improving the efficiency and accuracy of coordinate alignment, and laying the foundation for the accuracy of subsequent modeling.

[0068] The urban gas pipeline network distribution map is rationally divided into several independent management areas, and the pipeline attribute data is linked and bound to the line segments to establish a pipeline attribute database. This enables refined management and efficient querying of pipeline information, providing strong support for subsequent analysis and decision-making.

[0069] By introducing a three-dimensional coordinate system, the urban gas pipeline network distribution map is divided into surface, shallow and deep layers, and each layer is assigned an independent coordinate system. This accurately expresses the complex spatial relationship between pipelines at different depths, avoids problems such as positioning ambiguity and collision conflicts caused by the traditional single-plane coordinate system, improves the positioning accuracy of the pipeline network, provides clear spatial guidance for the construction, renovation and maintenance of the pipeline network, and reduces the risk of construction errors.

[0070] By mapping maintenance accident data to a three-dimensional coordinate system, the three-dimensional coordinates, occurrence time, and maintenance accident data of the accident points are marked on the gas pipeline network segments. A three-dimensional urban gas pipeline network model is constructed to realize the visualization and spatiotemporal correlation analysis of accident data, which helps to quickly locate accident points and improve the efficiency and targeting of maintenance work. Attached Figure Description

[0071] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0072] like Figure 1 As shown: A multi-dimensional data processing and modeling method for urban lifeline safety construction, including the following steps:

[0073] S1. Collect multi-dimensional data, including urban area map data, gas pipeline network distribution data, gas pipeline network attribute data, and maintenance accident data. It should be noted that urban area map data can be obtained through a city map app or through the city surveying and mapping department.

[0074] Gas pipeline network distribution data, which includes the coordinates of the pipeline's starting and ending points and valve location information; this data is obtained from drawings provided by the city's gas department, and is generally in DWG format.

[0075] Gas pipeline network attribute data, specifically including gas pipeline material, diameter, and wall thickness data, is also obtained from the city gas department.

[0076] Maintenance accident data, specifically including accident type; maintenance time and maintenance results; obtained through maintenance order data from the city gas department;

[0077] S2. Preprocess the urban area map and gas pipeline network distribution data, and then perform coordinate alignment. It should be noted that, while reducing the workload of pre-marking reference objects, the spatial coverage of coordinate alignment should be ensured to meet the requirements of engineering specifications.

[0078] The gas pipeline network distribution data is overlaid onto the urban area map, and the distribution of the gas pipeline network is spatially connected with the urban area map to obtain an urban area map that displays the gas pipeline network distribution data, which is marked as the urban gas pipeline network distribution map.

[0079] S3. Divide the urban gas pipeline network distribution map into several independent management areas based on the boundaries of the urban gas supply areas in the urban area map.

[0080] The gas pipeline network attribute data is associated with gas pipeline network segments in several independent management areas. The gas pipeline network attribute data is bound to the corresponding gas pipeline network segments to establish a pipeline network attribute database. Each pipeline network segment corresponds to a unique ID, resulting in a preliminary processed urban gas pipeline network distribution map. It should be noted that the start and end points of each gas pipeline segment are marked in the gas pipeline network distribution data. A gas pipeline network segment from the start point to the end point is marked as a gas pipeline network segment.

[0081] S4. For each independent management area, select the feature point with the highest coverage density from the reference feature points selected in S2 as a candidate node, ensuring that there is at least one candidate point in each management area, and obtain the candidate point set.

[0082] The typical depth value of each independent management area is extracted from the candidate point set. Then, the hierarchical boundary threshold is calculated based on the gas pipeline network attribute data and the candidate point set. Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer. Each layer is assigned an independent coordinate system. The three-level coordinate system with hierarchical relationship is output. A three-dimensional coordinate system is established for the urban gas pipeline network distribution map. Then, the three-dimensional position coordinates of the gas pipeline network line segment in each independent management area are obtained.

[0083] Acquire maintenance accident data, map the location corresponding to the maintenance accident data to the urban gas pipeline network distribution map, and obtain the coordinates of the accident location in the three-dimensional coordinate system;

[0084] Historical accident data is integrated into a three-dimensional model according to time series. The three-dimensional coordinates of accident points, occurrence time and maintenance accident data are marked on the gas pipeline network segments to obtain a three-dimensional urban gas pipeline network model.

[0085] S5. Based on the three-dimensional urban gas pipeline network model, a risk assessment model is constructed. The three-dimensional urban gas pipeline network model updates data in real time. The risk assessment model receives the data provided by the three-dimensional urban gas pipeline network model, outputs the risk assessment results of each independent management area in the three-dimensional urban gas pipeline network model, and marks them in the three-dimensional urban gas pipeline network model.

[0086] Urban lifeline safety construction refers to ensuring the safe operation of critical urban infrastructure through technical means and management strategies, preventing accidents and enhancing urban resilience. Its core objective is to reduce the probability of accidents such as gas explosions, bridge collapses, and urban flooding through real-time monitoring, risk assessment, and intelligent early warning, thereby ensuring the normal operation of urban functions and the safety of residents' lives and property.

[0087] By establishing models based on real-time monitoring data and environmental data of lifeline systems such as urban gas, water supply, drainage, and bridges, early identification of potential hazards in cities can be achieved. However, for mountainous cities, due to the large topographic relief and complex geological conditions, underground pipe networks are prone to corrosion and displacement risks, and bridges and tunnels are susceptible to landslides and subsidence threats.

[0088] Moreover, the data sources are extensive, requiring modeling of various types of urban lifelines, including gas lines, water supply lines, drainage lines, and bridges. Among these, gas lines are particularly important as they are crucial urban lifelines and pose a significant risk of accidents.

[0089] As an optional embodiment: S2 includes the following steps:

[0090] S21. Collect urban area map data and gas pipeline network distribution data, and perform integrity checks on them, supplementing any missing information;

[0091] It should be noted that for urban area map data, it is necessary to confirm that the map data covers the entire urban area and check whether the boundaries are complete. For example, check whether the boundaries of the urban administrative divisions are closed and whether they include all relevant sub-regions (such as municipal districts, counties, etc.).

[0092] Examining road connectivity identifies road breakpoints, where gaps exist between two roads that should be connected. These potential breakpoints can be discovered using methods such as buffer zone analysis. For example, creating a narrow buffer zone for each road and checking if adjacent road buffer zones touch each other; if not, a break may exist.

[0093] Fix topology errors at road intersections to ensure that correct nodes are formed when roads intersect, and that there are no cases where nodes are missing or inaccurate at road intersections. If errors are found, the road geometry needs to be re-edited to create the correct nodes.

[0094] For gas pipeline distribution data, check whether the start and end points of the gas pipelines are complete, ensuring that each section of pipeline has a clear start and end point and that there are no unexplained pipeline interruptions. If a pipeline interruption is found, it is necessary to find the missing pipeline segment information, which can be supplemented by consulting the gas company's pipeline construction records, construction drawings, etc.

[0095] Check the connectivity of the pipelines to see if the entire gas pipeline network forms a coherent network without any isolated pipeline segments. Isolated pipeline segments can be identified through network connectivity analysis, and then corresponding measures can be taken to repair them, such as supplementing missing connecting pipelines or correcting incorrect connection relationships.

[0096] S22. Select a unified geographic coordinate system, and convert the urban area map data and gas pipeline network distribution data to the unified coordinate system to complete the coordinate alignment.

[0097] It should be noted that this can solve the problem of inconsistent coordinate systems in multidimensional data and eliminate spatial position deviations caused by differences in coordinate systems.

[0098] S23. Overlay the coordinate-aligned gas pipeline distribution data with the urban area map to integrate the gas pipeline distribution data into the urban area map, generating an urban gas pipeline distribution map. It should be noted that spatially linking the gas pipeline network with urban geographical elements generates a visualized urban gas pipeline distribution map, supporting subsequent risk analysis and decision-making.

[0099] As an optional embodiment, the specific working steps of S22 further include the following:

[0100] First, feature point extraction is performed. For urban area maps, road intersections, corner points of independent buildings, and bridge endpoints are extracted as the first type of feature points. It should be noted that these are obtained through map annotation.

[0101] For gas pipeline network distribution data, valve nodes and pipeline inflection points are extracted as the second type of feature points; it should be noted that these are obtained by labeling valve nodes and pipeline inflection points in the gas pipeline network distribution data.

[0102] Then set a distance threshold. Spatial deduplication is performed on the first type of feature points and the second type of feature points;

[0103] It should be noted that spatial deduplication is specifically used to remove duplicate points or merge multiple points within a certain range into one point, in order to reduce the amount of data and improve data processing efficiency and accuracy. The distance threshold is used to determine whether two points are close enough to need to be merged or considered as the same feature point. The specific steps are as follows:

[0104] Adjacent distances less than the distance threshold The first or second type of feature points are merged into a single point;

[0105] It should be noted that the distance threshold Adjustments will be made based on the map's accuracy, initially set at 5m, and adjusted according to actual needs.

[0106] Two feature point sets are formed by combining the first type of feature points and the second type of feature points respectively. The point closest to the boundary of the first type of feature points and the second type of feature points are selected as the base point. With the base point as the origin, the polar angle of all other points relative to the base point is calculated and sorted in a counterclockwise direction. It should be noted that when the urban feature points are widely distributed and have low density, the point set is arranged in an orderly manner by using the base point as the center and sorting by polar angle, which is convenient for constructing the convex hull and can effectively handle scattered feature points.

[0107] It should be noted that the steps for calculating the polar angle of other points relative to the base point are as follows:

[0108] According to the formula Obtain the polar angles of other points relative to the base point;

[0109] in Let i be the coordinates of the i-th point in its own coordinate system. ;

[0110] For both feature point sets, a stack is used to construct the convex hull. The base point and the first two sorted points are pushed onto the stack. Then, the sorted feature point set is traversed sequentially. For each new point, it is checked whether the top three points of the stack form a right turn. If it does, the top point of the stack is popped; otherwise, the new point is pushed onto the stack. The points in the stack constitute the vertices of the convex hull. All vertices of the convex hull are used as selected reference feature points to obtain the first type of reference feature points and the second type of reference feature points. Using the above method, the first type of feature points and the second type of feature points are combined into a feature point set. The point closest to the boundary is selected as the base point. The polar angle is sorted with the base point as the origin. Then, the stack is used to construct the convex hull. The number of vertices of the final convex hull depends on the distribution of the feature point set and is usually much smaller than the total number of feature point sets. These vertices can effectively reflect the spatial distribution range of the feature point set and provide a quantitative basis for the subsequent selection of optimal control points.

[0111] The convex hull is the smallest convex polygon containing all feature points. Its vertices are extreme points selected from the set of feature points. These vertices are highly representative in spatial distribution and can reflect the overall range and shape of the feature point set. In the selection of optimal control points, the convex hull vertices can be used as reference feature points for the following reasons:

[0112] The vertices of the convex hull are the extreme points of the feature point set, located on the boundary of the entire feature point set. They are highly representative in spatial distribution, effectively covering the area occupied by the feature point set and reflecting its shape and extent. Using these vertices as reference points ensures that control points are evenly distributed within the urban area, improving the stability and accuracy of spatial alignment.

[0113] The convex hull can contain all feature points. Based on this property, using the vertices of the convex hull as reference feature points can ensure that the final selected optimal control point set also has the ability to contain all feature points. In this way, when performing subsequent spatial alignment and coordinate transformation, the representativeness of the entire feature point set can be guaranteed to the maximum extent, thereby improving the positioning accuracy and spatial relationship preservation.

[0114] The urban area map data and gas pipeline distribution data are converted to this unified coordinate system based on the first type of reference feature points and the second type of reference feature points.

[0115] In existing technologies, to meet spatial coverage requirements, especially in mountainous areas, large areas and reference points are selected as benchmarks during coordinate alignment. This technical solution selects the optimal feature points as references through calculation, which reduces the workload of pre-marking reference points and ensures that the spatial coverage of coordinate alignment meets engineering specifications, thus improving the accuracy of subsequent modeling.

[0116] As an optional embodiment, the specific steps for converting urban area map data and gas pipeline distribution data to the unified coordinate system based on the first type of reference feature points and the second type of reference feature points are as follows:

[0117] The first and second type of reference feature points obtained earlier are used as pairs of points with the same name.

[0118] Using the seven-parameter conversion function of GIS software, input these pairs of points with the same name and calculate the parameters that need to be adjusted. It should be noted that the parameters that need to be adjusted are mainly seven parameters, including the offset of the origin of the target coordinate system relative to the origin of the source coordinate system in the X, Y, and Z axis directions, the angle by which the target coordinate system needs to be rotated around the X, Y, and Z axes to align the coordinate axes, and the scale difference between the target coordinate system and the source coordinate system.

[0119] The calculated seven parameters are applied to the entire gas pipeline network distribution dataset. Using the conversion tools of GIS software or programming tools, the gas pipeline network data is batch converted from the original coordinate system to the target unified coordinate system.

[0120] As an optional embodiment: S3 includes the following steps:

[0121] S31. Obtain the boundaries of urban gas supply areas by extracting the boundary information of urban gas supply areas from urban area map data. It should be noted that these boundaries are usually determined by urban planning departments or gas companies based on factors such as administrative divisions, geographical features, and gas supply demand.

[0122] Based on the extracted urban gas supply area boundaries, the urban gas pipeline network distribution map is divided into multiple independent management areas, each representing a specific gas supply area; it should be noted that this provides a basic unit for subsequent refined management and analysis.

[0123] S32. In the gas pipeline network distribution data, identify the start and end points of each gas pipeline network segment. From the start to the end point, mark a continuous gas pipeline network as a gas pipeline network segment. Ensure that each segment has a clear start and end point and direction, providing a clear spatial unit for subsequent attribute association and management.

[0124] S33. Organize attribute information related to the gas pipeline network, specifically including data on gas pipeline material, diameter, and wall thickness; this data comes from the gas company's operation records, construction data, etc.

[0125] The collected gas pipeline network attribute data is associated with the corresponding pipeline segments to create a database that stores each pipeline segment and its associated attribute data, assigning a unique ID to each gas pipeline segment. Attribute information related to the gas pipeline network is scanned and extracted from paper documents. The collected attribute data, such as gas pipeline material, diameter, and wall thickness, are entered into the database for quick querying, updating, and management of pipeline network information.

[0126] Assign a unique ID to each gas pipeline segment, and match and associate the entered attribute data with the corresponding gas pipeline segment ID; the ID format is area code + start point ID + end point ID + material code;

[0127] The area code is a code for an independent management area, and the codes are sorted and coded in a top-down, left-to-right order;

[0128] A preliminary urban gas pipeline network distribution map is generated. This map is then combined with the established pipeline attribute database to produce a more detailed map containing comprehensive attribute information. This provides comprehensive and accurate data support for subsequent analysis, management, and decision-making.

[0129] It should be noted that gas company records may be paper documents or unstructured electronic files, which need to be entered manually. Matching pipeline segment IDs with attribute tables relies on manual verification, which is prone to omissions or misalignments. After pipeline renovation, spatial data and attributes need to be updated synchronously, otherwise it will lead to "inconsistency between map and attribute".

[0130] This technical solution, through the above steps, can reduce the error in combining the established pipeline attribute database with the urban gas pipeline distribution map. Each pipeline segment not only has spatial location information, but also includes attribute data such as its material and pipe diameter, providing comprehensive and accurate information support for subsequent analysis, management and decision-making.

[0131] As an optional embodiment: S4 includes the following steps:

[0132] S41. For each independent management area, select the feature point with the highest coverage density from the reference feature points selected in S2 as a candidate node, ensuring that there is at least one candidate point in each management area, and obtain the candidate point set.

[0133] It should be noted that the specific steps are as follows:

[0134] Input the reference feature point set in S2 and the coordinate-aligned reference feature point set, and use the Voronoi diagram iterative algorithm to select the feature point with the highest coverage density as the candidate node in the reference feature point set, ensuring that there is at least one candidate point in each independent management area. Divide the urban gas pipeline network distribution map into multiple independent management areas. Each independent management area contains only all points that are closest to a certain specific point. For a given reference feature point set, each reference feature point corresponds to a Voronoi polygon area, and all points in this area are closer to the reference feature point than to any other reference feature point.

[0135] S42 extracts the typical depth value of each independent management area from the candidate point set, and then calculates the hierarchical boundary threshold based on the gas pipeline network attribute data and the candidate point set. Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer, and each layer is assigned an independent coordinate system. The output is a coordinate system with hierarchical relationship of three levels.

[0136] Extract the branch structure of each independent management area within the gas pipeline network distribution data. Starting from the main pipeline, generate a local coordinate system tree according to the branch hierarchy. Merge the local coordinate system with the overall three-level coordinate system to obtain the three-dimensional position coordinates of the gas pipeline network segments within each independent management area.

[0137] It should be noted that urban gas pipeline networks are distributed at different depths, including surface facilities such as pressure regulating stations and meters, shallow underground main pipelines, and deep underground pipeline sections. Traditional single-plane coordinate systems are difficult to accurately express the complex spatial relationships between these pipeline networks at different depths, such as three-dimensional intersections and vertical avoidance. This can easily lead to problems such as unclear pipeline positioning and collisions. For example, shallow main pipelines and deep pipelines crossing rivers may appear to overlap when projected onto the same plane coordinate system, but in reality, they are three-dimensionally layered and do not interfere with each other.

[0138] During the construction, renovation, and maintenance of gas pipeline networks, different construction stages involve operations at different depths. A layered coordinate system can clearly indicate the depth level of the target pipeline and its relative position to other pipeline layers for construction personnel. This avoids accidental excavation or collision with other pipeline layers due to a single coordinate system. When repairing shallow main pipelines, construction personnel can accurately avoid deep pipelines crossing subway tracks by using the layered coordinate system, reducing the risk of accidents caused by construction errors and improving the safety and accuracy of construction.

[0139] S43. Extract the accident location description from the maintenance accident data, obtain the location information of the maintenance accident based on the accident location description, and map the location corresponding to the maintenance accident data to a three-level coordinate system to obtain the three-dimensional location coordinates of the accident location in the gas pipeline network segment. It should be noted that by mapping the accident location to a three-level coordinate system and marking the maintenance accident data on the three-dimensional model, the accident point can be located more quickly, improving the efficiency and targeting of maintenance work.

[0140] S44. Establish a three-dimensional urban gas pipeline network model based on the three-level coordinate system and the three-dimensional position coordinates of the gas pipeline network segments. Integrate historical accident data according to the time series to obtain a maintenance accident data dataset. Mark the maintenance accident data dataset at the coordinate position of the accident corresponding to the gas pipeline network segment. Specifically, it includes the three-dimensional coordinates of the accident point, the time of occurrence, and the maintenance accident data.

[0141] As an optional embodiment, the specific steps of S42 are as follows:

[0142] First, extract the typical depth value of each independent management area from the candidate point set;

[0143] The specific steps are as follows:

[0144] According to the formula ;

[0145] Then, based on the gas pipeline network attributes and typical depth values, the hierarchical boundary threshold is calculated. ;

[0146] Specifically, according to the formula:

[0147] The hierarchical boundary threshold was calculated. ,in Let be the diameter of the i-th gas pipeline. Let be the material coefficient of the i-th gas pipeline, where 1.2 is for steel and 1 is for PE; Let be the actual burial depth of the i-th gas pipeline;

[0148] in The standard deviation of depth in the region is calculated using the depth values ​​of all benchmark points within the region, reflecting the geological heterogeneity.

[0149] Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer;

[0150] Calculated hierarchical boundary threshold The boundary value used to distinguish between shallow and deep layers is used to mark the range [−1m, 1m] as the surface layer and [−1m, 1m] as the deep layer. The range of m] is marked as shallow layer, and the range greater than m is marked as shallow layer. A layer greater than m is marked as deep;

[0151] Each layer is assigned an independent coordinate system. For the origin of the surface layer, the point whose horizontal projection is closest to the geometric center of the region is selected from the candidate point set of the reference points of that layer.

[0152] For the shallow origin, the vertical offset is directly below the surface origin. minus ;

[0153] For the deep origin, the vertical offset is directly below the surface origin. minus ;

[0154] Extract the branch structure of each independent management area within the gas pipeline network distribution data. Starting from the main pipeline, generate a local coordinate system tree according to the branch hierarchy, and then merge the local coordinate system with the overall three-level coordinate system. The specific steps are as follows:

[0155] Select the main pipeline within each independent management area, specifically the gas pipeline with the largest diameter:

[0156] Starting with the main pipeline, analyze its branch structure and determine the levels of each branch. Based on the connection relationship of the pipeline network, divide the branches into primary branches, secondary branches, and so on. Primary branches are pipelines that branch directly from the main pipeline, and secondary branches are pipelines that branch from the primary branches.

[0157] At the starting point of the main pipeline in each independent management area, the origin of the local coordinate system is determined, specifically the second type of reference feature point closest to the common benchmark point;

[0158] A local coordinate system is established with the direction of the main pipeline as the X-axis, the horizontal direction perpendicular to the main pipeline as the Y-axis, and the direction perpendicular to the ground as the height axis Z-axis.

[0159] For each local coordinate system, determine the transformation parameters between it and the global three-level coordinate system. These parameters include translation vector, rotation matrix, and scaling factor. Specifically, the transformation parameters are determined by the common reference point and the origin of the local coordinate system. The detailed transformation parameters are the same as those for the first type of reference feature points and the second type of reference feature points mentioned above.

[0160] Based on the determined transformation parameters, each point in the local coordinate system is transformed to the overall three-level coordinate system. The three-dimensional position coordinates of the gas pipeline network segments in each independent management area are transformed from the local coordinate system to the overall coordinate system, ensuring that the transformed coordinates are consistent with other data in the overall coordinate system.

[0161] It should be noted that traditional methods use fixed-depth division, while this solution combines the steps in S2 and uses the depth distribution of three-dimensional reference points and the dynamic calculation boundary of pipeline attributes to improve the accuracy of hierarchical division, which is beneficial to the accuracy of subsequent modeling.

[0162] The X / Y axis directions of each coordinate system strictly inherit the determined main pipeline route to ensure the spatial topology consistency of the cross-layer pipeline network.

[0163] As an optional embodiment, the specific steps of S43 are as follows;

[0164] Based on the description of the accident location and the distribution data of the gas pipeline network, determine whether the accident occurred at the surface, shallow, or deep layers. For example, if the accident location description mentions "near the pressure regulating station," it may have occurred at the surface. If it mentions "main pipeline" and the main pipeline in this area is usually laid 3-5 meters underground, it may have occurred at the shallow layer. If the accident involves pipelines crossing rivers or subway tracks, it may have occurred at the deep layer.

[0165] The geographic coordinates of the accident location are converted into coordinates in three levels of coordinate systems. Based on the common reference point and coordinate transformation parameters, the latitude and longitude coordinates of the accident location are converted into three-dimensional coordinates in the surface, shallow, or deep coordinate systems. Given the geographic coordinates of the common reference point and its coordinates in the three levels of coordinate systems, the coordinate values ​​of the accident location in the corresponding level of coordinate system are calculated through the coordinate transformation algorithm.

[0166] The specific steps of S44 are as follows:

[0167] The three-level coordinate system and the three-dimensional position coordinate data of the gas pipeline network segments were integrated together, and a three-dimensional model of the gas pipeline network was constructed based on the three-dimensional coordinates of the pipeline network segments using three-dimensional modeling software.

[0168] Add gas pipeline attribute data to each gas pipeline segment in the gas pipeline network model;

[0169] The collected maintenance accident data is sorted according to the time of occurrence to form a time series. Based on the sorted historical accident data, a maintenance accident data dataset is created, and the maintenance accident data dataset is marked on the coordinate position of the accident corresponding to the gas pipeline segment.

[0170] In a 3D urban gas pipeline network model, maintenance accident data sets are associated with corresponding pipeline segments based on the 3D coordinates of accident points. Markers or annotations can be created for each accident point in the model, indicating specific accident information. Different types of accidents are represented by icons of different colors or shapes, with the occurrence time and a brief description of the accident displayed next to the icon.

[0171] As an optional embodiment: S5 includes the following steps:

[0172] S51. Install sensors on each gas pipeline segment to collect the operating status of each gas pipeline segment; it should be noted that the operating status includes pressure, flow rate, temperature and methane concentration.

[0173] Based on a 3D urban gas pipeline network model, the operational status of each gas pipeline segment is input to construct a risk assessment model;

[0174] The specific steps for constructing a risk assessment model are as follows:

[0175] Select input parameters, specifically including real-time operating status: pressure, flow rate, temperature, methane concentration, with a data acquisition frequency of once per second;

[0176] Pipeline attributes: gas pipeline material, diameter, wall thickness data; 3D coordinates, density of adjacent pipelines, number of intersections;

[0177] Historical accident data, including leakage frequency and accident type; repair response time;

[0178] Select a suitable Long Short-Term Memory (LSTM) network, take the extracted historical data features and corresponding risk factors as input, and use historical accident data as output labels to train the model;

[0179] Construct the LSTM network structure, determine the input size, and select the number of hidden units and layers (typically 1 to 3 layers).

[0180] Output layer design: The output layer is designed according to the type of risk assessment task. For regression tasks, the output layer is a single neuron.

[0181] Model compilation: Mean squared error (MSE) is selected as the loss function, and the Adam optimizer is used for parameter updates;

[0182] Train the model using the training set, setting appropriate training epochs, batch size, and early stopping mechanism;

[0183] Model evaluation: The trained model is evaluated using a test set, and metrics such as mean squared error, root mean square error, and mean absolute error are calculated.

[0184] Plot the training and validation loss curves to observe the model's convergence and whether there is overfitting or underfitting.

[0185] Based on the risk value output by the model, and combined with the actual situation of the gas pipeline network and safety standards, the risk level is classified.

[0186] The risk values ​​predicted by the model are compared with the set thresholds, the gas pipeline network of each independent management area is divided into corresponding risk levels, and different colors or icons are used to mark and visualize the three-dimensional urban gas pipeline network model.

[0187] S52. The risk assessment model receives data from the three-dimensional urban gas pipeline network model in real time, including the pipeline topology of each independent management area, maintenance data, and equipment operating status. Using the constructed risk assessment model, it performs risk assessment calculations on the gas pipeline network of each independent management area. Based on the risk assessment calculation results of each independent management area, it identifies independent management areas with higher risks and major risk factors. Based on the assessment results, it dynamically adjusts the parameters of the risk assessment model.

[0188] As an optional embodiment, the specific working steps of S52 are as follows:

[0189] Based on the preprocessed operational status data, pipeline topology, and maintenance data, a feature vector is constructed. The feature vector should include multiple features that can reflect the risk status of the gas pipeline network, such as pressure change rate, flow fluctuation amplitude, temperature anomaly degree, methane concentration trend, pipeline density, and the intersection of adjacent pipelines.

[0190] The constructed feature vectors are input into the risk assessment model to perform risk assessment calculations on the gas pipeline network of each independent management area.

[0191] The risk values ​​output by the model are analyzed to determine the risk level. Based on the actual situation of the gas pipeline network and safety standards, risk thresholds are set, and the risk levels are divided into three levels: low, medium, and high. The risk level distribution of each independent management area is statistically analyzed, and the independent management area with the highest risk is identified.

[0192] By analyzing the internal structure of the model and the weights of the eigenvectors, the main risk factors that have a significant impact on the risk assessment results are identified.

[0193] If the methane concentration feature of a certain region has a high weight in the model, and the methane concentration in that region has recently shown an upward trend, then the methane concentration can be regarded as a major risk factor for that region.

[0194] Based on the assessment results, the parameters of the risk assessment model are dynamically adjusted, and the monitoring frequency is increased for the highest-risk, independently managed areas. It should be noted that this information is obtained by adjusting the sensor's data acquisition frequency.

[0195] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of this template.

Claims

1. A multi-dimensional data processing and modeling method for urban lifeline safety construction, characterized in that, Includes the following steps: S1. Collect multi-dimensional data, including urban area map data, gas pipeline network distribution data, gas pipeline network attribute data, and maintenance accident data; S2. Preprocess the urban area map and gas pipeline distribution data, then perform coordinate alignment, and overlay the gas pipeline distribution data onto the urban area map; S3. Associate the gas pipeline network attribute data with the urban gas pipeline network distribution map, and bind the gas pipeline network attribute data to the corresponding gas pipeline network segment; S4. For each independent management area, select the feature point with the highest coverage density from the reference feature points selected in S2 as a candidate node, ensuring that there is at least one candidate point in each management area, and obtain the candidate point set. The typical depth value of each independent management area is extracted from the candidate point set. Then, the hierarchical boundary threshold is calculated based on the gas pipeline network attribute data and the candidate point set. Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer. Each layer is assigned an independent coordinate system. The three-level coordinate system with hierarchical relationship is output. A three-dimensional coordinate system is established for the urban gas pipeline network distribution map. Then, the three-dimensional position coordinates of the gas pipeline network line segment in each independent management area are obtained. Acquire maintenance accident data, map the location corresponding to the maintenance accident data to the urban gas pipeline network distribution map, and obtain the coordinates of the accident location in the three-dimensional coordinate system; Historical accident data is integrated into a three-dimensional model according to time series to obtain a three-dimensional urban gas pipeline network model; S5. Based on the three-dimensional urban gas pipeline network model, a risk assessment model is constructed. The risk assessment model receives the data provided by the three-dimensional urban gas pipeline network model and outputs the risk assessment results of each independent management area in the three-dimensional urban gas pipeline network model.

2. The multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 1, characterized in that, S2 includes the following steps: S21. Collect urban area map data and gas pipeline network distribution data, and perform integrity checks on them, supplementing any missing information; S22. Select a unified geographic coordinate system, and convert the urban area map data and gas pipeline network distribution data to the unified coordinate system to complete the coordinate alignment. S23. Overlay the coordinate-aligned gas pipeline distribution data with the urban area map to merge the gas pipeline distribution data into the urban area map and generate an urban gas pipeline distribution map.

3. The multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 2, characterized in that, The specific working steps of S22 also include the following: First, feature point extraction is performed. For urban area maps, road intersections, corner points of independent buildings, and bridge endpoints are extracted as the first type of feature points. For gas pipeline network distribution data, valve nodes and pipeline inflection points are extracted as the second type of feature points; Then set a distance threshold. Spatial deduplication is performed on the first type of feature points and the second type of feature points; The first type of feature points and the second type of feature points are respectively formed into two feature point sets. The point closest to the boundary in the first type of feature points and the second type of feature points are selected as the base point. With the base point as the origin, the polar angle of all other points relative to the base point is calculated and sorted in the counterclockwise direction. For both feature point sets, a stack is used to construct the convex hull. The base point and the first two sorted points are pushed onto the stack. Then, the sorted feature point set is traversed sequentially. For each new point, it is checked whether the three points at the top of the stack form a right turn. If it is a right turn, the point at the top of the stack is popped. Otherwise, the new point is pushed onto the stack. The points in the stack constitute the vertices of the convex hull. All the vertices of the convex hull are used as the selected reference feature points to obtain the first type of reference feature points and the second type of reference feature points. The urban area map data and gas pipeline distribution data are converted to this unified coordinate system based on the first type of reference feature points and the second type of reference feature points.

4. The multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 3, characterized in that, The specific steps for converting urban area map data and gas pipeline network distribution data to this unified coordinate system based on the first type of reference feature points and the second type of reference feature points are as follows: The first and second type of reference feature points obtained earlier are used as pairs of points with the same name. Using the seven-parameter conversion function of GIS software, input these pairs of points with the same name and calculate the parameters that need to be adjusted. The calculated seven parameters are applied to the entire gas pipeline network distribution dataset. Using the conversion tools of GIS software or programming tools, the gas pipeline network data is batch converted from the original coordinate system to the target unified coordinate system.

5. A multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 1, characterized in that, S3 includes the following steps: S31. Obtain the boundary of the urban gas supply area and extract the boundary information of the urban gas supply area from the urban area map data. Based on the extracted urban gas supply area boundaries, the urban gas pipeline network distribution map is divided into multiple independent management areas, each representing a specific gas supply area. S32. In the gas pipeline network distribution data, identify the start and end points of each gas pipeline network segment, and mark a continuous gas pipeline network segment as a gas pipeline network segment from the start to the end point. S33. Organize the attribute information related to the gas pipeline network, specifically including data on gas pipeline material, diameter, and wall thickness. The collected gas pipeline network attribute data is associated with the corresponding pipeline segments, and a database is created to store each pipeline segment and its associated attribute data, assigning a unique ID to each gas pipeline segment. A preliminary urban gas pipeline network distribution map is generated. The established pipeline attribute database is then combined with the urban gas pipeline network distribution map to generate a preliminary urban gas pipeline network distribution map containing detailed attribute information.

6. A multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 3, characterized in that, S4 includes the following steps: S41. For each independent management area, select the feature point with the highest coverage density from the reference feature points selected in S2 as a candidate node, ensuring that there is at least one candidate point in each management area, and obtain the candidate point set. S42 extracts the typical depth value of each independent management area from the candidate point set, and then calculates the hierarchical boundary threshold based on the gas pipeline network attribute data and the candidate point set. Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer, and each layer is assigned an independent coordinate system. The output is a coordinate system with hierarchical relationship of three levels. Extract the branch structure of each independent management area within the gas pipeline network distribution data. Starting from the main pipeline, generate a local coordinate system tree according to the branch hierarchy. Merge the local coordinate system with the overall three-level coordinate system to obtain the three-dimensional position coordinates of the gas pipeline network segments within each independent management area. S43. Extract the accident location description from the maintenance accident data, obtain the location information of the maintenance accident based on the accident location description, map the location corresponding to the maintenance accident data to a three-level coordinate system, and obtain the three-dimensional location coordinates of the accident location in the gas pipeline segment. S44. Establish a three-dimensional urban gas pipeline network model based on the three-level coordinate system and the three-dimensional position coordinates of the gas pipeline network segments. Integrate historical accident data according to the time series to obtain a maintenance accident data dataset. Mark the maintenance accident data dataset at the coordinate position of the accident corresponding to the gas pipeline network segment. Specifically, it includes the three-dimensional coordinates of the accident point, the time of occurrence, and the maintenance accident data.

7. A multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 6, characterized in that, The specific steps of S42 are as follows: First, extract the typical depth value of each independent management area from the candidate point set; Then, based on the gas pipeline network attributes and typical depth values, the hierarchical boundary threshold is calculated. ; Based on the hierarchical boundary threshold, the urban gas pipeline network distribution map is divided into surface layer, shallow layer and deep layer; Calculated hierarchical boundary threshold The boundary value used to distinguish between shallow and deep layers is assigned to an independent coordinate system for each layer; Extract the branch structure of each independent management area within the gas pipeline network distribution data. Starting from the main pipeline, generate a local coordinate system tree according to the branch hierarchy, and then integrate the local coordinate system with the overall three-level coordinate system.

8. A multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 6, characterized in that, The specific steps of S43 are as follows; Based on the description of the accident location and the distribution data of the gas pipeline network, determine whether the accident occurred in the surface layer, shallow layer, or deep layer; convert the geographical coordinates of the accident location into coordinates in three-level coordinate systems; and based on the common reference point and coordinate transformation parameters, convert the latitude and longitude coordinates of the accident location into three-dimensional coordinates in the surface layer, shallow layer, or deep layer coordinate system. The specific steps of S44 are as follows: The three-level coordinate system and the three-dimensional position coordinate data of the gas pipeline network segments were integrated together, and a three-dimensional model of the gas pipeline network was constructed based on the three-dimensional coordinates of the pipeline network segments using three-dimensional modeling software. Add gas pipeline attribute data to each gas pipeline segment in the gas pipeline network model; The collected maintenance accident data is sorted according to the time of occurrence to form a time series. Based on the sorted historical accident data, a maintenance accident data dataset is created, and the maintenance accident data dataset is marked on the coordinate position of the accident corresponding to the gas pipeline segment. In the three-dimensional urban gas pipeline network model, the maintenance accident data set is associated with the corresponding pipeline segment based on the three-dimensional coordinates of the accident point.

9. A multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 6, characterized in that, S5 includes the following steps: S51. Install sensors on each gas pipeline segment to collect the operating status of each gas pipeline segment. Based on a 3D urban gas pipeline network model, the operational status of each gas pipeline segment is input to construct a risk assessment model; S52. The risk assessment model receives data from the three-dimensional urban gas pipeline network model in real time, including the pipeline topology of each independent management area, maintenance data, and equipment operating status. Using the constructed risk assessment model, it performs risk assessment calculations on the gas pipeline network of each independent management area. Based on the risk assessment calculation results of each independent management area, it identifies independent management areas with higher risks and major risk factors. Based on the assessment results, it dynamically adjusts the parameters of the risk assessment model.

10. A multi-dimensional data processing and modeling method for urban lifeline safety construction according to claim 9, characterized in that, The specific working steps of S52 are as follows: Based on the preprocessed operational status data, pipeline topology, and maintenance data, feature vectors are constructed. The constructed feature vectors are input into the risk assessment model to perform risk assessment calculations on the gas pipeline network of each independent management area. The risk values ​​output by the model are analyzed to determine the risk level. Based on the actual situation of the gas pipeline network and safety standards, risk thresholds are set, and the risk levels are divided into three levels: low, medium, and high. The risk level distribution of each independent management area is statistically analyzed, and the independent management area with the highest risk is identified. Based on the assessment results, the parameters of the risk assessment model are dynamically adjusted, and the monitoring frequency is increased for the independently managed areas with the highest risk.

Images