Construction method of water supply and drainage pipe network system model

Abstract

The invention belongs to the technical field of water supply and drainage system data analysis, and provides a water supply and drainage pipe network system model construction method, which comprises the following steps of: firstly, judging the deviation degree of main pipes of different pipelines according to the property value performance of the different pipelines in a water supply and drainage pipe network system and the access condition of other pipelines; carrying out clustering operation on the pipelines; then, the pipelines are combined according to the unification degree of the main pipe deviation performance and the using effect of all the pipelines in the edge cluster obtained after clustering of the water supply and drainage pipeline network; combining the pipelines according to the distribution expression of the main pipes and the branch pipes in the regional convergence cluster after the clustering of the water supply and drainage pipeline network; and finally, judging the reasonable degree of the simplified model according to the simplification degree of the simplified model obtained after each time of pipeline combination and a verification effect feedback condition, and obtaining a final simple model. The simplified model obtained by the invention not only can reduce the calculation amount, but also can effectively retain the characteristics of the urban pipe network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water supply and drainage system data analysis, and particularly relates to a water supply and drainage pipe network system model construction method. BACKGROUND

[0002] Simplifying the distribution of the urban water supply and drainage pipe network system according to the location characteristics can significantly reduce the complexity and calculation cost of the water supply and drainage pipe network system model, improve the simulation efficiency, and ensure the reliability of the model in macro planning, risk identification and operation scheduling by preferentially retaining the "skeleton" structure such as the main pipe network and key nodes when simplifying the distribution of the urban water supply and drainage pipe network system, thereby providing clear and efficient decision-making basis for scientific management.

[0003] The traditional method for simplifying the distribution of the urban water supply and drainage pipe network system only combines the pipe sections at the edge of the pipe network according to the distribution of the pipe diameters, lengths and positions of different pipe sections, without considering the complex connection relationship between different pipes and being unable to reasonably combine the pipes according to the importance of the pipes in the pipe network, so that the obtained simplified model is not accurate enough. SUMMARY

[0004] In order to solve the above technical problems, the present application provides a water supply and drainage pipe network system model construction method.

[0005] According to the water supply and drainage pipe network system model construction method provided by the present application, the method comprises the following steps: obtaining the pipe network layout and the attribute values of each pipe in the water supply and drainage pipe network system; obtaining the main pipe bias degree of each pipe according to the attribute value size of different pipes and the access conditions of other pipes in the pipe network layout; performing clustering operation on all pipes in the water supply and drainage pipe network based on the main pipe bias degree to obtain a plurality of clustering clusters, wherein the clustering clusters comprise edge clusters and regional convergence clusters; for the edge clusters, analyzing the merging bias degree of each pipe based on the main pipe bias degree, and merging the pipes in the edge clusters; for the regional convergence clusters, analyzing the distribution of the main pipes and branch pipes in the pipes based on the main pipe bias degree, and then combining the merging bias degree to obtain the merging pipe section proportion of the regional convergence clusters, and merging the pipes in the regional convergence clusters; obtaining the simplified model each time the pipes are merged, analyzing the simplification degree and verification effect of the simplified model, obtaining the simplification rationality of the simplified model, and determining the final simplified model.

[0006] In some embodiments of the present application, the trunk pipe bias degree of each pipe section is obtained according to the attribute value size of different pipes and the access of other pipes in the pipe network layout, comprising: segmenting the pipes in the water supply and drainage pipe network to obtain a plurality of pipe sections; obtaining the length and pipe diameter of each pipe section from the attribute values of the pipes to obtain the water supply and drainage capacity of each pipe section; counting the number of other pipes accessed on each pipe section according to the pipe network layout; obtaining the trunk pipe bias degree of each pipe section according to the water supply and drainage capacity and the number of accesses.

[0007] In some embodiments of the present application, the trunk pipe bias degree of each pipe section is obtained according to the water supply and drainage capacity and the number of accesses, comprising: obtaining the maximum water supply and drainage capacity of all pipe sections in the water supply and drainage pipe network, and comparing the size relationship between the water supply and drainage capacity of each pipe section and the maximum water supply and drainage capacity; obtaining the maximum number of accesses of other pipes accessed on all pipe sections in the water supply and drainage pipe network, and comparing the ratio relationship between the number of accesses corresponding to each pipe section and the maximum number of accesses; obtaining the trunk pipe bias degree of each pipe according to the size relationship and the ratio relationship.

[0008] In some embodiments of the present application, based on the trunk pipe bias degree, the clustering operation is performed on all pipes in the water supply and drainage pipe network to obtain a plurality of clustering clusters, comprising: obtaining a water supply and drainage pipe network graph by taking the pipe sections as edges and the connection points between the pipe sections as nodes, and the direction of the edges follows the water flow direction; obtaining a plurality of clustering clusters by performing clustering operation on the water supply and drainage pipe network graph through spectral clustering method, taking the trunk pipe bias degree corresponding to each pipe section as the weight of each edge.

[0009] In some embodiments of the present application, for the edge cluster, the merging bias degree of each pipe is analyzed based on the trunk pipe bias degree, comprising: nodes with only incoming edges and no outgoing edges within the edge cluster are recorded as terminal nodes, and a plurality of terminal nodes in the edge cluster are obtained; calculating the average of the trunk pipe bias degrees of all pipe sections connected to the terminal nodes to obtain the average trunk pipe bias degree; analyze a difference between the trunk pipe bias degree of each pipe segment connected to the terminal node and the average trunk pipe bias degree, and obtain a combined bias degree of each pipe segment connected to the terminal node in combination with the average trunk pipe bias degree.

[0010] In some embodiments of the present application, the merging of the pipes in the edge cluster comprises: a preset merging threshold; determining whether the combined bias degree is greater than the merging threshold; if yes, merging all pipe segments connected to the terminal node to obtain a merged pipe segment.

[0011] In some embodiments of the present application, for the regional convergence cluster, based on the trunk pipe bias degree, the distribution of the trunk pipe and the branch pipe in the pipe is analyzed, comprising: a preset bias degree threshold; counting a first number of pipe segments in the regional convergence cluster whose trunk pipe bias degree is less than the bias degree threshold, and calculating a first ratio of the first number to a first total number of pipe segments in the regional convergence cluster to obtain a number distribution of the trunk pipe and the branch pipe in the pipe; obtaining a convex hull area of all pipe segments in the regional convergence cluster, and combining the first total number to obtain a distribution density of the pipe; obtaining a mergable degree of the pipe in the regional convergence cluster according to the number distribution and the distribution density in combination with the trunk pipe bias degree.

[0012] In some embodiments of the present application, in combination with the combined bias degree, a merged pipe segment proportion of the regional convergence cluster is obtained, comprising: regarding a node with only an incoming edge but no outgoing edge in the range of the regional convergence cluster as a terminal node, and obtaining a plurality of terminal nodes in the regional convergence cluster; counting a second number of pipe segments connected to the terminal node in the range of the regional convergence cluster, and counting a second total number of pipe segments connected to the terminal node, and calculating a second ratio of the second number to the second total number; obtaining the merged pipe segment proportion of the regional convergence cluster in combination with the combined bias degree, the mergable degree and the second ratio.

[0013] In some embodiments of the present application, the merging of the pipes in the regional convergence cluster comprises: obtaining a mergable pipe number in the regional convergence cluster in combination with the second total number according to the merged pipe segment proportion; Sort all the pipe segments connected with the terminal in the region convergence cluster according to the trunk pipe bias degree from small to large, and merge the first number of the mergeable pipe segments in the sequence.

[0014] In some embodiments of the present application, a simplified model is obtained each time the pipe is merged, the verification effect and the simplification degree of the simplified model are analyzed, the simplification rationality of the simplified model is obtained, and the final simplified model is determined, comprising: A simplified model is obtained each time the pipe is merged; The output difference of the key performance indicators is obtained by inputting the same conditions to the simplified model and the original model, and the verification effect of the simplified model is obtained; The ratio of the simplified length of all pipes in the simplified model to the original length of the pipes in the original model is calculated, and the third total number of the pipe segments in the simplified model is combined to obtain the simplification degree of the simplified model; The verification effect and the simplification degree are combined to obtain the simplification rationality of the simplified model; A reasonable degree threshold is preset, and when the simplification rationality is greater than the reasonable degree threshold for the first time, the simplified model corresponding to the simplification rationality is determined as the final simplified model.

[0015] As can be seen from the above embodiments, the water supply and drainage pipe network system model construction method provided by the embodiments has the following beneficial effects: Firstly, according to the attribute value size performance of different pipes in the water supply and drainage pipe network system and the access situation of other pipes, the trunk pipe bias degree of different pipes is judged, and all the pipes in the water supply and drainage pipe network are clustered. Then, according to the trunk pipe bias performance of each pipe in the edge cluster after clustering of the water supply and drainage pipe network and the unified degree of use, the pipes in the edge cluster are merged. And according to the distribution performance of the trunk pipe and branch pipe in the region convergence cluster after clustering of the water supply and drainage pipe network, the proportion of the mergeable pipes in a single range is obtained, and then the pipes in the region convergence cluster are merged. Finally, according to the simplification degree and verification effect feedback of the simplified model obtained after each pipe merging, the rationality of the simplified model is judged, and then the appropriate simplified model is selected. The present application not only considers the distribution of pipe diameter, length and position of different pipe segments, but also considers the connection complex relationship between different pipes and the drainage effect in the pipe, and the pipe segments at the edge of the pipe network are merged, so that the obtained simplified model not only reduces the calculation amount, but also effectively retains the characteristics of the urban pipe network.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0018] Figure 1 A schematic diagram of the basic flow of a sewer network system model construction method provided by the embodiments of the present application is shown. Figure 2 An example diagram of edge cluster in sewer network graph provided by the embodiments of the present application is shown. Figure 3 An example diagram of regional convergence cluster in sewer network graph provided by the embodiments of the present application is shown. Figure 4 An example diagram of the comparison visualization display of the original model and the simplified model provided by the embodiments of the present application is shown. DETAILED DESCRIPTION

[0019] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the specific implementation, structure, features and effects of the sewer network system model construction method according to the present application are described in detail as follows by combining the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms such as "comprise", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the circuit structure, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such article or device. Without more limitation, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the article or device comprising the element. The terms "first" and "second" and the like relational terms are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations.

[0021] The sewer network system model construction method provided by the embodiments of the present application will be described in detail below in combination with the drawings.

[0022] Please refer toFigure 1 Fig. 1 shows a basic flow of a method for constructing a sewer network system model according to an embodiment of the present application.

[0023] As shown in Fig. 1, the method for constructing a sewer network system model according to an embodiment of the present application includes the following steps. Figure 1 S100: obtaining the layout of the sewer network system and the attribute values of each pipe. S100: obtaining the layout of the sewer network system and the attribute values of each pipe.

[0024] The layout of the sewer network system and the attribute values of each pipe are obtained, wherein the layout of the sewer network system includes the connection relationship between pipes (the number of other pipes connected to each pipe, etc.), and the attribute values include the pipe type (water supply / wastewater), pipe diameter, length. Specifically, first, the layout and direction of the sewer network system are preliminarily obtained through the sewer engineering planning drawing in the overall city planning drawing. Then, the scanned sewer engineering planning drawing is aligned with the correct geographic coordinates in the GIS (Geographic Information System) software, and each pipe on the sewer engineering planning drawing is manually tracked and converted into vector data. In key road sections where the sewer engineering planning drawing is severely missing, use devices such as ground penetrating radar (GPR) to quickly scan and outline the general direction and depth of each pipe. Convert data from different sources into a unified coordinate system and file format. And overlay and match the digitized pipeline with the road network to correct obvious spatial deviations. The topological relationship (connectivity) of the pipe network is established in the GIS software to ensure that the pipes are logically connected. Finally, add core attributes such as pipe type (water supply / wastewater), pipe diameter, length, etc. to each pipe.

[0025] S200: obtaining the main pipe bias degree of each pipe according to the attribute value size of different pipes and the access situation of other pipes in the pipe network layout.

[0026] Effective model simplification of the urban sewer network system can greatly reduce the complexity and computational cost of the model. To simplify the model reasonably, the main pipe and branch pipe should be distinguished first. Since the main pipe in the sewer network system is a large intercepting trunk or a conveying trunk that collects the flow of multiple areas, it has the characteristics of large buried depth, large pipe diameter, and total flow bearing; while the branch pipe is a pipe that connects from the street internal gully and the sewage inspection well, it has the characteristics of shallow buried depth, small pipe diameter, and source collection. Therefore, the main pipe and branch pipe can be distinguished by the pipe diameter, length, and the number of connected other pipes.

[0027] Based on the above analysis, in the embodiments of the present invention, the degree of deviation of the main pipe of each pipe segment is obtained according to the magnitude of the attribute values ​​of different pipes and the connection status of other pipes in the pipe network layout. Further, it includes: First, the pipes in the water supply and drainage network are segmented to obtain several pipe segments. Specifically, the pipes in the water supply and drainage network are segmented using nodes such as inspection wells, outlets, pumping stations, and treatment plants to obtain several pipe segments.

[0028] Then, from the pipe's attribute values, obtain the length and diameter of each pipe segment to get the water supply and drainage capacity of each pipe segment, and obtain the maximum water supply and drainage capacity of all pipe segments in the water supply and drainage network.

[0029] In addition, based on the pipeline network layout, the number of other pipelines connected to each pipeline segment is counted, and the maximum number of other pipelines connected to all pipeline segments in the water supply and drainage network is obtained.

[0030] Finally, based on the water supply and drainage capacity and the number of connections, the degree of deviation of the main pipe for each pipeline segment is obtained. Specifically, by comparing the water supply and drainage capacity of each pipeline segment with the maximum water supply and drainage capacity, and comparing the ratio of the number of connections for each pipeline segment to the maximum number of connections, the degree of deviation of the main pipe for each pipeline segment is obtained based on these relationships. The formula for calculating the degree of deviation of the main pipe in a segmented pipeline is as follows:

[0031] In the formula: Indicates the first The degree of deviation of the main pipeline in each section of the pipeline; This indicates the maximum water supply and drainage capacity of all sections of the pipeline in the water supply and drainage network. Indicates the first The length of each segment of the pipeline; Indicates the first The diameter of each section of the pipeline; Indicates the first The number of other pipelines connected to a section of the pipeline; This indicates the maximum number of other pipes that can be connected to any section of the water supply and drainage network. This represents the minimum value greater than 0. This is to prevent the denominator from being 0, so that it is set ; This represents the minimum value greater than 0. In order to avoid When it is 0 =0 (in) When it is 0, the first Pipeline sections may also be main pipelines, and are set up as follows: ; This represents the maximum and minimum normalization function, with a range of [0,1].

[0032] Indicates the first The water supply and drainage capacity of the segmented pipeline. Indicates the first The relationship between the water supply and drainage capacity of each section of the pipeline and its maximum water supply and drainage capacity. Indicates the first The ratio of the number of connections corresponding to each pipeline segment to the maximum number of connections; when the first segment... Drainage capacity of segmented pipelines The drainage capacity corresponding to the pipe section with the largest drainage capacity The gap The smaller, and the first Number of connecting pipes in a segmented pipeline With maximum number of accesses ratio When it is larger, the first The more a segment of a pipeline matches the characteristics of a main pipeline—larger diameter, higher flow rate, and convergence of flow from multiple areas—the more suitable it is to be classified as a main pipeline. The greater the deviation of the main pipe in the segmented pipeline.

[0033] S300: Based on the degree of deviation of the main pipeline, clustering operation is performed on all pipelines in the water supply and drainage network to obtain several clusters, including edge clusters and regional convergence clusters.

[0034] Based on the degree of deviation of the main pipeline, clustering is performed on all pipelines in the water supply and drainage network to obtain several clusters, including edge clusters and regional convergence clusters. Specifically, firstly, pipeline segments are used as edges, with the direction of the edges following the direction of water flow. Connection points between pipeline segments are used as nodes, i.e., manholes, outlets, pumping stations, treatment plants, etc., to obtain the water supply and drainage network map. Then, using the degree of deviation of the main pipeline corresponding to each pipeline segment as the weight of each edge (each pipeline segment) in the water supply and drainage network map, Spectral Clustering (SC) is used to cluster the drainage network map to obtain several clusters. These clusters include edge clusters and regional convergence clusters. In the drainage network map, clusters containing source nodes (nodes with no incoming edges, only outgoing edges) are designated as edge clusters, such as... Figure 2 As shown; clusters containing the average deviation of each edge (each pipe segment) from the main pipe with a deviation less than 0.7, and which are not edge clusters, are designated as regional convergence clusters, such as... Figure 3 As shown.

[0035] S400: For edge clusters, based on the degree of deviation of the main pipe, analyze the degree of merging deviation of each pipe and merge the pipes in the edge cluster.

[0036] In the edge clusters after water supply and drainage pipe network clustering, when multiple pipe segments converge to the same pipe segment, and the pipe diameters of each pipe segment are small and the deviation of the main pipe is small and similar, the more likely each pipe segment is to undertake similar and very limited local water supply and drainage tasks, the more it can be simplified and merged with the connecting pipe (the pipe segment to which multiple pipe segments converge) with a larger deviation of the main pipe.

[0037] Based on the above analysis, in the embodiments of the present invention, for the edge cluster, based on the degree of deviation of the main pipe, the degree of merging deviation of each pipe is analyzed, and the pipes in the edge cluster are merged. Wherein: For edge clusters, based on the degree of main pipe bias, the merging bias degree of each pipe is analyzed. This further includes: First, nodes within the edge cluster that have only incoming edges and no outgoing edges are designated as endpoints, obtaining multiple endpoints in the edge cluster; then, the average main pipe bias degree of all pipe segments connected to the endpoints is calculated to obtain the average main pipe bias degree; finally, the difference between the main pipe bias degree of each pipe segment connected to the endpoint and the average main pipe bias degree is analyzed, and combined with the average main pipe bias degree, the merging bias degree of each pipe segment connected to the endpoint is obtained. Specifically, for edge clusters... A single endpoint For example, calculation and endpoint The average deviation of the main pipe from all connected edges (all pipe segments) is denoted as: Then calculate the endpoint. The difference in the degree of deviation of the main pipe on each connected side (each pipe segment) is as follows: ( For edge clusters Midpoint and Endpoint The number of connected pipe segments.

[0038] When the edge cluster It does not exist in When the edge is, the edge cluster endpoint in Differences in the orientation of the main pipes across all connected sides (pipe segments) The smaller the value, and the greater the average degree of main pipe bias. The smaller the size, the smaller the pipe diameter and the smaller the flow rate of each pipe segment in this edge cluster, with the endpoint... The more the connected pipe segments are consistent with the characteristics of the edge branch pipe, and the more consistent the main pipe deviation degree is, the more likely the pipe segments are to undertake similar very limited local water supply and drainage tasks, and the more possible it is to combine the pipe segments corresponding to the outgoing edges of the terminal nodes. The connected pipe segments and the terminal nodes are combined and simplified. Thus, the edge cluster is constructed. The connected pipe segments and the terminal nodes are combined and simplified. Thus, the edge cluster is constructed.

[0039] In the formula, the deviation degree of the main pipe of the pipe segment connected to the terminal node in the edge cluster is represented by ; the deviation degree of the main pipe of the pipe segment connected to the terminal node in the edge cluster is represented by ; the deviation degree of the main pipe of the pipe segment connected to the terminal node in the edge cluster is represented by ; the average deviation degree of the main pipe of all the pipe segments connected to the terminal node in the edge cluster is represented by ; the average deviation degree of the main pipe of all the pipe segments connected to the terminal node in the edge cluster is represented by ; the average deviation degree of the main pipe of all the pipe segments connected to the terminal node in the edge cluster is represented by ; the number of the pipe segments connected to the terminal node in the edge cluster is represented by ; the absolute value is represented by; and the maximum-minimum normalization function whose value range is [0, 1] is represented by

[0040] The merging of the pipes in the edge cluster further includes the following steps. First, a merging threshold is preset, which can be 0.6. It is determined whether the merging deviation degree is greater than the merging threshold. If yes, i.e. , all the pipe segments connected to the terminal node are combined to obtain a combined pipe segment. If no, i.e. , the pipe segments connected to the terminal node are not combined. Specifically, taking the terminal node in the edge cluster as an example, , the pipe segments connected to the terminal node in the edge cluster and the pipe segments corresponding to the outgoing edges of the terminal node are combined, and the merging of the pipe segments connected to the terminal node in the edge cluster is completed.

[0041] Similarly, the merging of the pipe segments connected to each terminal node in the edge cluster is completed.

[0042] ​​​​​​​​​​S500: For the regional convergence cluster, based on the backbone pipe bias degree, the distribution of the backbone pipe and the branch pipe in the pipeline is analyzed, and then combined with the merging bias degree, the merging pipeline segment proportion of the regional convergence cluster is obtained, and the pipelines in the regional convergence cluster are merged.

[0043] To simplify the water supply and drainage pipe network as much as possible, the pipelines in the regional convergence cluster can also be merged to a certain extent. Since there may be some important backbone pipelines in the regional convergence cluster, the mergable pipelines should be screened through the containing proportion of different types of pipelines in the regional convergence cluster.

[0044] Based on the above analysis, in the embodiments of the present application, for the regional convergence cluster, based on the backbone pipe bias degree, the distribution of the backbone pipe and the branch pipe in the pipeline is analyzed, and then combined with the merging bias degree, the merging pipeline segment proportion of the regional convergence cluster is obtained, and the pipelines in the regional convergence cluster are merged. Wherein: For the regional convergence cluster, based on the backbone pipe bias degree, the distribution of the backbone pipe and the branch pipe in the pipeline is analyzed, and further includes: First, a bias degree threshold is preset, which can be 0.5; the first number of pipeline segments with a backbone pipe bias degree less than the bias degree threshold in the regional convergence cluster is counted, and the first ratio of the first number to the first total number of pipeline segments in the regional convergence cluster is calculated, to obtain the number distribution of the backbone pipe and the branch pipe in the pipeline. Specifically, taking the regional convergence cluster as an example, the first number of pipeline segments with a backbone pipe bias degree less than the bias degree threshold in the regional convergence cluster is counted, denoted as , and the first total number of all pipeline segments in the regional convergence cluster is counted, denoted as , and the first ratio of the first number to the first total number is calculated as . In addition, the convex hull area of all pipeline segments in the regional convergence cluster is obtained, and combined with the first total number, the distribution density of the pipeline is obtained. Specifically, taking the regional convergence cluster as an example, the convex hull area of all pipeline segments in the regional convergence cluster is obtained (the area of the minimum convex polygon containing all pipeline segments in the regional convergence cluster , that is, the area of the convex polygon formed by connecting the outermost nodes in the regional convergence cluster

[0045] ), denoted as , and the distribution density of the pipeline is . ​​​.

[0046] Then, based on the quantity distribution and distribution density, combined with the degree of main pipeline bias, the degree of merging potential of pipelines in the regional convergence cluster is obtained. Specifically, taking the regional convergence cluster as an example... For example, when regional clusters converge... Dense distribution of pipeline segments within the area Larger, regional clusters The average degree of deviation of the main pipe corresponding to all included edges (pipe segments). The smaller the ratio When the size is larger, the regional clusters converge. Within the defined pipeline segmentation area, the main pipeline exhibits a relatively small overall deviation and a high distribution density, making it more suitable for extensive pipeline merging. This leads to the formation of regional convergence clusters. The degree to which sections of the central pipeline can be merged is as follows:

[0047] In the formula, Indicates regional clusters The degree to which sections of the pipeline can be merged; Indicates regional clusters The first total number of all pipeline segments in the pipeline; Indicates regional clusters The area of ​​the convex hull of all pipe segments in the middle; Indicates regional clusters The mean of the main pipe deviation corresponding to all edges (pipe segments) contained therein; Indicates regional clusters middle The first number of the corresponding pipeline segments; This represents the maximum and minimum normalization function, with a range of [0,1].

[0048] Based on the degree of merging bias, the proportion of merged pipeline segments in the regional convergence cluster is obtained, further including: First, nodes within the region aggregation cluster that have only incoming edges and no outgoing edges are denoted as endpoints, and multiple endpoints in the region aggregation cluster are obtained.

[0049] Then, the second number of pipe segments connected to the endpoint within the regional convergence cluster is counted, and the second total number of pipe segments connected to the endpoint is counted. A second ratio is then calculated between the second number and the second total number. Specifically, this ratio is based on the regional convergence cluster. endpoint in For example, statistical regional clusters Within range and endpoint The second number of connected pipe segments is denoted as... and the endpoint The second total number of connected pipe segments (including those not belonging to regional clusters) Pipeline segments within the scope), denoted as ; Calculate the second quantity With the second total quantity The second ratio is .

[0050] Combining the degree of merging bias, the degree of merging potential, and the second ratio, the proportion of merged pipeline segments in regional convergence clusters is obtained. Specifically, based on regional convergence clusters... endpoint in For example, compute region clustering Midpoint and Endpoint The degree of merging bias of the connected pipe sections is denoted as... When regional clusters converge Mergeability of pipeline segments The larger it is, and the closer it is to the endpoint. The degree of merging bias of connected pipeline segments The larger, the second quantity With the second total quantity The second ratio When the size is larger, the regional clusters converge. The more branch pipes in a pipeline segment, and the more they are connected to the endpoint... The more branch pipes exist within a connected pipeline segment, the more suitable it is for pipeline merging, and the larger the proportion of pipeline segments to be merged should be. This leads to the concept of regional convergence clusters. The proportion of the merged pipeline segments is as follows:

[0051] In the formula, Indicates regional clusters The proportion of merged pipeline segments; Indicates regional clusters The degree to which sections of the pipeline can be merged; Indicates regional clusters Midpoint and Endpoint The degree of merging bias of each connected pipe segment (determined in the same way as the method described above for obtaining the degree of merging bias of each pipe segment connected to the endpoint in the edge cluster). Indicates regional clusters Within range and endpoint The second number of connected pipe segments; Indicates connection to the endpoint The second total number of pipeline segments; This represents the maximum and minimum normalization function, with a range of [0,1].

[0052] The merging of the pipes in the regional convergence cluster further includes: First, according to the merging pipe segment proportion, combined with the second total number, the number of mergable pipes in the regional convergence cluster is obtained. Specifically, the number of mergable pipe segments connected to the terminal node in the regional convergence cluster is calculated according to the following formula:

[0053] In the formula, represents the number of mergable pipe segments connected to the terminal node in the regional convergence cluster; represents the second number of pipe segments connected to the terminal node in the regional convergence cluster; represents the merging pipe segment proportion of the regional convergence cluster. represents the floor function. Then, all pipe segments connected to the terminal node in the regional convergence cluster are sorted in descending order according to the trunk pipe bias degree, and the first number of mergable pipe segments in the sequence is merged to complete the merging of the pipe segments connected to the terminal node in the regional convergence cluster. Similarly, the merging of the pipe segments connected to each terminal node in the regional convergence cluster is completed.

[0054] S600: Obtain a simplified model each time the pipe is merged, analyze the simplification degree and verification effect of the simplified model, obtain the simplification rationality of the simplified model, and determine the final simplified model. Under the condition of excessive simplification of the model, a large amount of flow in the model may be injected into the trunk pipe at a point in time, which overestimates the drainage capacity of the system trunk pipe and cannot accurately evaluate the real load of each section of the trunk pipe. Therefore, each time the pipe is merged, the drainage pipe network is simplified once, and the drainage effect is verified with the simplified model. When the verification effect is good and the pipe model is simple enough, it is more in line with the requirements of model simplification, and finally a suitable simplified model is obtained.

[0055]

[0056] S600: Obtain a simplified model each time the pipe is merged, analyze the simplification degree and verification effect of the simplified model, obtain the simplification rationality of the simplified model, and determine the final simplified model.

[0057] Under the condition of excessive simplification of the model, a large amount of flow in the model may be injected into the trunk pipe at a point in time, which overestimates the drainage capacity of the system trunk pipe and cannot accurately evaluate the real load of each section of the trunk pipe. Therefore, each time the pipe is merged, the drainage pipe network is simplified once, and the drainage effect is verified with the simplified model. When the verification effect is good and the pipe model is simple enough, it is more in line with the requirements of model simplification, and finally a suitable simplified model is obtained.

[0058] ​​​​​​​​​​​​Based on the above analysis, in the embodiments of the present application, a simplified model is obtained by each pipeline merging, and the simplification degree and verification effect of the simplified model are analyzed to obtain the simplification rationality of the simplified model, and the final simplified model is determined. Further comprising: First, a simplified model is obtained by each pipeline merging. Specifically, the "simplification" tool of modern water modeling software (such as InfoWate, etc.) is used to perform intelligent merging operation on the pipe network according to the pipe segments to be merged obtained in the above steps, and the corresponding simplified model is obtained. It is required to obtain a simplified model once for each merging analysis.

[0059] Then, the same conditions are input into the simplified model and the original model to obtain the output difference of the key performance indicators, and the verification effect of the simplified model is obtained. Specifically, the same conditions such as precipitation event, infiltration / inflow model, simulation time length are input into the simplified model and the original model, and the corresponding total water volume deviation, peak flow error, Nash efficiency coefficient NSE, percentage bias PBIAS and other key performance indicators are output by the two models, and the difference degree between the corresponding key performance indicators output by the two models is obtained. The difference degree calculation formula can be:

[0060] In the formula, represents the difference degree between the key performance indicators output by the simplified model and the original model; represents the value of the key performance indicator output by the original model; represents the value of the key performance indicator output by the simplified model; represents the absolute value.

[0061] According to the influence degree of the key performance indicators on the construction of the water supply and drainage pipe network system model, for example, the total water volume deviation has a greater influence on the construction of the water supply and drainage pipe network system model, and the corresponding weight can be set to 0.5, and the percentage bias has a smaller influence on the construction of the water supply and drainage pipe network system model, and the corresponding weight can be set to 0.1 (the specific weight value is set according to experience), and the difference degree between the key performance indicators output by the simplified model and the original model is weighted to obtain the comprehensive score of the simplified model meeting the requirements, and the simplified model The comprehensive score meeting the requirements is quantified as follows:

[0062] In the formula, represents the comprehensive score of the simplified model meeting the requirements; ​Indicates key performance indicators The weights of all key performance indicators The sum of the corresponding weights is 1; Key performance indicators (KPIs) of the simplified model and the original model output. The degree of difference between them; This indicates the number of key performance indicators.

[0063] In addition, the ratio of the simplified length of all pipes in the simplified model to the original length of the pipes in the original model is calculated. Combined with the third total number of pipe segments in the simplified model, the degree of simplification of the simplified model is obtained. Specifically, using the simplified model... For example, calculate the pipeline network model. The length of all pipes in the middle The length of the pipe in the original model without simplification ratio and statistical simplification models The number of pipe sections in the pipeline is denoted as When the ratio The smaller the number of pipe segments The smaller the size, the better the pipeline model. The greater the degree of simplification, the better. Therefore, constructing a simplified model... The formula for calculating the degree of simplification is:

[0064] In the formula, Representing a simplified model The degree of simplification; This represents the original length of the pipe in the original model; Represents the original model Simplified length of the central pipe; Representing a simplified model The third total number of pipeline segments.

[0065] Furthermore, by combining the verification results and the degree of simplification, the simplification rationality of the simplified model is obtained. Specifically, the simplified model... For example, after the previous simplification, the simplified model... simplification The larger the score, the better. The larger the value, the better the current simplified model meets the requirements; therefore, constructing a simplified model... The simplified formula for calculating rationality is:

[0066] In the formula, Representing a simplified model The degree of simplification and rationality; simplified model simplification degree; simplified model comprehensive score meeting the requirement; max-min normalization function, whose value range is [0, 1].

[0067] Finally, a reasonable degree threshold (the value can be 0.9) is preset. When the simplification reasonable degree is greater than the reasonable degree threshold, that is, , it is indicated that the current simplified model has reached the requirement. Therefore, the simplified model corresponding to the first time when the simplification reasonable degree is greater than the reasonable degree threshold ( ) is taken as the final simplified model.

[0068] Through the above method, the pipes at different positions in the water supply and drainage pipe network system are simplified in the processor, and the final simplified model of the water supply and drainage pipe network is obtained through evaluation. The positions of different pipes in the simplified model and the pipe diameter size are transmitted to the database for storage. Through obtaining the data of the simplified model and the original model in the database, the visualization display of the distribution diagram of the water supply and drainage pipe network model before and after simplification is performed on the display screen of the staff, as shown in Figure 4 .

[0069] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0070] Each embodiment in the specification is described in a progressive manner, and the same and similar parts between each embodiment can be referred to each other. Each embodiment mainly describes the differences from other embodiments.

Claims

1. A method for constructing a model of a water supply and drainage pipe network system, characterized in that, The method comprises: obtaining the pipe network layout and attribute values of each pipe in the water supply and drainage pipe network system; obtaining the trunk pipe bias degree of each pipe according to the attribute value size of different pipes and the access situation of other pipes in the pipe network layout; based on the trunk pipe bias degree, performing clustering operation on all pipes in the water supply and drainage pipe network to obtain a plurality of clustering clusters, the clustering cluster including an edge cluster and a regional convergence cluster; for the edge cluster, based on the trunk pipe bias degree, analyzing the merging bias degree of each pipe, and merging the pipes in the edge cluster; for the regional convergence cluster, based on the trunk pipe bias degree, analyzing the distribution of trunk pipes and branch pipes in the pipes, and then combining the merging bias degree to obtain the merging pipe segmentation proportion of the regional convergence cluster, and merging the pipes in the regional convergence cluster; obtaining a simplified model each time the pipes are merged, analyzing the simplification degree and verification effect of the simplified model, obtaining the simplification rationality of the simplified model, and determining the final simplified model.

2. The sewer network system model construction method according to claim 1, characterized by, According to the attribute value size of different pipes and the access situation of other pipes in the pipe network layout, the trunk pipe bias degree of each pipe is obtained, comprising: segmenting the pipes in the water supply and drainage pipe network to obtain a plurality of pipe segments; from the attribute values of the pipes, the length and pipe diameter of each pipe segment are obtained to obtain the water supply and drainage capacity of each pipe segment; according to the pipe network layout, the number of other pipes accessed on each pipe segment is counted; according to the water supply and drainage capacity and the access number, the trunk pipe bias degree of each pipe segment is obtained.

3. The sewer network system model construction method according to claim 2, characterized by, According to the water supply and drainage capacity and the access number, the trunk pipe bias degree of each pipe is obtained, comprising: obtaining the maximum water supply and drainage capacity of all pipe segments in the water supply and drainage pipe network, and comparing the size relationship between the water supply and drainage capacity of each pipe segment and the maximum water supply and drainage capacity; obtaining the maximum access number of other pipes accessed on all pipe segments in the water supply and drainage pipe network, and comparing the ratio relationship between the access number corresponding to each pipe segment and the maximum access number; according to the size relationship and the ratio relationship, the trunk pipe bias degree of each pipe is obtained.

4. The sewer network system model construction method according to claim 2, characterized by, Based on the trunk pipe bias degree, clustering operation is performed on all pipes in the water supply and drainage pipe network to obtain a plurality of clustering clusters, comprising: taking the pipe segments as edges and the direction of the edges following the water flow direction, and taking the connection points between the pipe segments as nodes to obtain a water supply and drainage pipe network graph; taking the trunk pipe bias degree corresponding to each pipe segment as the weight of each edge, and performing clustering operation on the water supply and drainage pipe network graph by spectral clustering method to obtain a plurality of clustering clusters.

5. The sewer network system model construction method according to claim 4, characterized by, For the edge cluster, based on the trunk pipe bias degree, the merging bias degree of each pipe is analyzed, comprising: nodes in the edge cluster range with only incoming edges and no outgoing edges are recorded as terminal nodes, and a plurality of terminal nodes in the edge cluster are obtained; the average of the trunk pipe bias degrees of all pipe segments connected with the terminal nodes is calculated to obtain the average trunk pipe bias degree; The difference between the trunk pipe bias degree of each pipe segment connected to the terminal node and the average trunk pipe bias degree is analyzed, and the average trunk pipe bias degree is combined to obtain a combined bias degree of each pipe segment connected to the terminal node.

6. The sewer network system model construction method according to claim 5, characterized by, The pipes in the edge cluster are combined, including: a preset combination threshold is set; it is determined whether the combined bias degree is greater than the combination threshold; if yes, all pipe segments connected to the terminal node are combined to obtain a combined pipe segment.

7. The sewer network system model construction method according to claim 1, characterized by, For the regional convergence cluster, the distribution of trunk pipes and branch pipes in the pipes is analyzed based on the trunk pipe bias degree, including: a preset bias degree threshold is set; a first number of pipe segments in the regional convergence cluster with a trunk pipe bias degree less than the bias degree threshold is counted, and a first ratio of the first number to a first total number of pipe segments in the regional convergence cluster is calculated to obtain the number distribution of trunk pipes and branch pipes in the pipes; the convex hull area of all pipe segments in the regional convergence cluster is obtained, and the first total number is combined to obtain the distribution density of the pipes; the combinable degree of the pipes in the regional convergence cluster is obtained according to the number distribution and the distribution density, combined with the trunk pipe bias degree.

8. The sewer network system model construction method according to claim 7, characterized by, The combined pipe segment proportion of the regional convergence cluster is obtained in combination with the combined bias degree, including: nodes with only incoming edges and no outgoing edges in the range of the regional convergence cluster are recorded as terminal nodes, and a plurality of terminal nodes in the regional convergence cluster are obtained; a second number of pipe segments connected to the terminal nodes in the regional convergence cluster is counted, and a second total number of pipe segments connected to the terminal nodes is counted, and a second ratio of the second number to the second total number is calculated; the combined pipe segment proportion of the regional convergence cluster is obtained in combination with the combined bias degree, the combinable degree, and the second ratio.

9. The sewer network system model construction method according to claim 8, characterized by, The pipes in the regional convergence cluster are combined, including: the number of combinable pipes in the regional convergence cluster is obtained according to the combined pipe segment proportion and the second total number; all pipe segments connected to the terminal nodes in the regional convergence cluster are sorted in ascending order of the trunk pipe bias degree, and the first number of pipe segments are combined in the sequence.

10. The sewer network system modeling method according to claim 1, characterized by, A simplified model is obtained once for each pipe combination, the verification effect and the simplification degree of the simplified model are analyzed, the simplification rationality of the simplified model is obtained, and the final simplified model is determined, including: a simplified model is obtained once for each pipe combination; the same conditions are input into the simplified model and the original model, the output difference of the key performance indicators is obtained, and the verification effect of the simplified model is obtained; the ratio of the simplified length of all pipes in the simplified model to the original length of the pipes in the original model is calculated, and the third total number of pipe segments in the simplified model is combined to obtain the simplification degree of the simplified model; the simplification rationality of the simplified model is obtained in combination with the verification effect and the simplification degree; a preset rationality threshold is set, and the simplified model corresponding to the first time when the simplification rationality is greater than the rationality threshold is determined as the final simplified model.

Images