Drainage pipe network waterlogging key node identification method, system and device and medium

Abstract

The invention discloses a drainage pipe network waterlogging key node identification method, system and device and a medium. The method comprises the steps that pipe network basic information is acquired; according to the basic information of the pipe network, topological attributes, vulnerability, water catchment amount and pipe network characteristics corresponding to each initial node are determined, the topological attributes represent the degree of communication between a target node and other initial nodes and the possibility that water flow passes through the target node, and the vulnerability is used for representing the degree of influence of damage of the target node on the drainage pipe network system; the pipe network characteristics are used for representing upstream and downstream pipeline characteristics of a target node, and the target node is any one of a plurality of initial nodes; calculating an index score corresponding to the topological attribute, the vulnerability, the water collection amount and the pipe network characteristics of each initial node based on an entropy weight method; and according to each index score and a preset node number, selecting a plurality of initial nodes as key waterlogging nodes from each initial node. According to the embodiment of the invention, the efficiency, accuracy, normalization and systematicness of drainage pipe network waterlogging key node identification can be improved.

Description

Technical Field

[0001] The present application relates to the technical field related to urban drainage pipe network systems, and in particular to methods, systems, devices and media for identifying key nodes of waterlogging in drainage pipe networks. Background Art

[0002] In the past, the selection of key nodes for waterlogging in urban drainage networks was mostly based on on-site investigations and historical data collection, which were then manually processed and analyzed to determine the key nodes for waterlogging in urban drainage networks. Although the selected key nodes for waterlogging can reflect the status of the drainage network, due to the large number of networks and the complex actual situation, the selection of key nodes for waterlogging often requires huge manpower and lacks certain standardization and systematicness. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a method for identifying key nodes of waterlogging in a drainage network, which can improve the efficiency, accuracy, standardization and systematicness of identifying key nodes of waterlogging in a drainage network.

[0004] The present application also provides a drainage network waterlogging key node identification system, a control device and a computer-readable storage medium.

[0005] According to a method for identifying key nodes of waterlogging in a drainage network according to a first aspect of the present application, the method includes: Obtain basic information of the drainage pipe network system; Determine the topological attributes, fragility, water collection and pipe network characteristics corresponding to each initial node in the drainage pipe network system according to the pipe network basic information, wherein the topological attributes are used to characterize the degree of connectivity between the target node and other initial nodes and the possibility of water flowing through the target node, the fragility is used to characterize the degree of influence of damage to the target node on the drainage pipe network system, and the pipe network characteristics are used to characterize the characteristics of the upstream and downstream pipes of the target node, and the target node is any one of the multiple initial nodes; Calculate the index scores corresponding to the topological attributes, the vulnerability, the water catchment volume and the pipe network characteristics of each of the initial nodes based on the entropy weight method; A plurality of key nodes for waterlogging are selected from the initial nodes according to the index scores and the preset number of nodes.

[0006] The method for identifying key nodes of waterlogging in a drainage network according to the embodiment of the present application has at least the following beneficial effects: The present application evaluates the criticality of each initial node by considering four waterlogging indicators with a high correlation with waterlogging, namely topological attributes, vulnerability, water catchment volume and pipe network characteristics. The identified key waterlogging nodes are more accurate, and objectively assigned values ​​through the entropy weight method. The weights of each waterlogging indicator are determined based on the variability of the data itself, which can effectively avoid the deviation of subjective assignment. After calculating the indicator scores corresponding to the topological attributes, vulnerability, water catchment volume and pipe network characteristics of each initial node, multiple nodes are selected from each initial node as key waterlogging nodes according to a preset number of nodes, which can improve the efficiency, accuracy, standardization and systematicness of identifying key nodes for waterlogging in drainage pipe networks.

[0007] According to some embodiments of the present application, the topological attribute and the vulnerability are obtained by the following steps: Constructing a drainage network topology structure according to the basic information of the network; The topological attribute and the vulnerability corresponding to each of the initial nodes in the drainage network topological structure are determined.

[0008] According to some embodiments of the present application, the topological attributes include degree and betweenness, and the fragility includes the relative size of network efficiency and the relative size of the largest connected subgraph.

[0009] According to some embodiments of the present application, the water volume includes the water catchment area and the average runoff coefficient.

[0010] According to some embodiments of the present application, the pipe network characteristics include a downstream pipe diameter, an upstream and downstream pipe diameter difference, and a downstream pipe slope.

[0011] According to some embodiments of the present application, the entropy weight method is used to calculate the index scores corresponding to the topological attributes, the vulnerability, the water volume, and the pipe network characteristics of each of the initial nodes, including: An evaluation index matrix is ​​constructed according to the topological attributes, the vulnerability, the water catchment volume, the pipe network characteristics, and the corresponding plurality of initial nodes, wherein the evaluation index matrix is ​​used to represent the index value of each waterlogging index corresponding to each initial node; Calculate the index proportion of each waterlogging index corresponding to each initial node based on the evaluation index matrix; Calculate the information entropy value of each waterlogging indicator according to the indicator proportion of each waterlogging indicator corresponding to each of the initial nodes; The weight of each waterlogging indicator is calculated according to the information entropy value of each waterlogging indicator; Normalizing the index values ​​of each waterlogging index corresponding to each of the initial nodes to obtain the standard values ​​of each waterlogging index corresponding to each of the initial nodes; The index scores corresponding to the topological attributes, the vulnerability, the water catchment volume and the pipe network characteristics of each node are determined according to the weights of each waterlogging index and the standard values ​​of each waterlogging index corresponding to each initial node.

[0012] According to some embodiments of the present application, the step of selecting a plurality of key nodes from the initial nodes according to the index scores and the preset number of nodes as waterlogging key nodes includes: Arrange the scores of each indicator in order from high to low; A plurality of the initial nodes with the highest index scores are selected as the key waterlogging nodes, and the number of the key waterlogging nodes is equal to the preset number of nodes.

[0013] According to a drainage network waterlogging key node identification system according to a second aspect of the present application, the system includes: The pipe network information acquisition module is used to obtain the basic pipe network information of the drainage pipe network system; A waterlogging index determination module, used to determine the topological attributes, vulnerability, water collection and pipe network characteristics corresponding to each initial node in the drainage pipe network system according to the basic pipe network information, wherein the topological attributes are used to characterize the degree of connectivity between the target node and other initial nodes and the possibility of water flowing through the target node, the vulnerability is used to characterize the degree of influence of damage to the target node on the drainage pipe network system, and the pipe network characteristics are used to characterize the characteristics of the upstream and downstream pipes of the target node, and the target node is any one of the multiple initial nodes; An index score determination module, used to calculate the index scores corresponding to the topological attributes, the vulnerability, the water volume and the pipe network characteristics of each of the initial nodes based on the entropy weight method; The waterlogging key node determination module is used to select a plurality of waterlogging key nodes from each of the initial nodes according to each of the indicator scores and a preset number of nodes.

[0014] The drainage network waterlogging key node identification system according to the embodiment of the present application has at least the following beneficial effects: The present application evaluates the criticality of each initial node by considering four waterlogging indicators with a high correlation with waterlogging, namely topological attributes, vulnerability, water catchment volume and pipe network characteristics. The identified key waterlogging nodes are more accurate, and objectively assigned values ​​through the entropy weight method. The weights of each waterlogging indicator are determined based on the variability of the data itself, which can effectively avoid the deviation of subjective assignment. After calculating the indicator scores corresponding to the topological attributes, vulnerability, water catchment volume and pipe network characteristics of each initial node, multiple nodes are selected from each initial node as key waterlogging nodes according to a preset number of nodes, which can improve the efficiency, accuracy, standardization and systematicness of identifying key nodes for waterlogging in drainage pipe networks.

[0015] According to the third aspect of the present application, the control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for identifying key nodes of waterlogging in the drainage network as described in the first aspect of the embodiment. Since the control device adopts all the technical solutions of the method for identifying key nodes of waterlogging in the drainage network in the above embodiment, it has at least all the beneficial effects brought by the technical solutions of the above embodiment.

[0016] According to the computer-readable storage medium of the fourth aspect embodiment of the present application, computer executable instructions are stored, and the computer executable instructions are used to execute the method for identifying key nodes of waterlogging in the drainage network as described in the first aspect embodiment. Since the computer-readable storage medium adopts all the technical solutions of the method for identifying key nodes of waterlogging in the drainage network of the above embodiment, it has at least all the beneficial effects brought by the technical solutions of the above embodiment.

[0017] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent from the description, or may be understood by practicing the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 This is a flow chart of a method for identifying key nodes of waterlogging in a drainage network according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0020] In the description of this application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0021] In the description of the present application, it should be understood that the descriptions involving orientation, such as the orientation or positional relationship indicated as up, down, etc., are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0022] In the description of this application, it should be noted that, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0023] The following will be combined Figure 1 A clear and complete description is given of the method for identifying key nodes of waterlogging in a drainage network according to an embodiment of the present invention. Obviously, the embodiment described below is only a part of the embodiments of the present invention, but not all of the embodiments.

[0024] According to a method for identifying key nodes of waterlogging in a drainage network according to a first aspect of the present invention, the method comprises: Obtain basic information of the drainage pipe network system; The topological attributes, vulnerability, water collection and network characteristics corresponding to each initial node in the drainage network system are determined according to the basic network information. The topological attributes are used to characterize the degree of connectivity between the target node and other initial nodes and the possibility of water flowing through the target node. The vulnerability is used to characterize the degree of impact of damage to the target node on the drainage network system. The network characteristics are used to characterize the characteristics of the upstream and downstream pipelines of the target node. The target node is any one of the multiple initial nodes. The index scores corresponding to the topological attributes, vulnerability, catchment volume and network characteristics of each initial node are calculated based on the entropy weight method; According to the scores of each indicator and the preset number of nodes, multiple nodes are selected from each initial node as the key nodes for waterlogging.

[0025] It can be understood that the basic information of the pipe network is the two-dimensional data of the drainage pipe network, and the basic information of the pipe network is obtained through the following steps: Obtain basic information of the study area, nodes and drainage network; Perform data cleaning and outlier processing on the basic information of the research area, the basic information of the nodes, and the basic information of the drainage network, normalize the processed basic information of the research area, the basic information of the nodes, and the basic information of the drainage network, and extract features from the normalized basic information of the research area, the basic information of the nodes, and the basic information of the drainage network to form feature vectors; Input the feature vector into the trained drainage network simulation model to obtain the two-dimensional data of the drainage network; Among them, data cleaning and outlier processing specifically include: removing or completing missing data, removing or modifying data with format and content errors, and removing or modifying data with logical errors.

[0026] In some embodiments of the present application, topological attributes and fragility are obtained by the following steps: Construct the drainage network topology structure based on the basic information of the network; Determine the topological attributes and vulnerabilities corresponding to each initial node in the drainage network topology.

[0027] It is understandable that the topological structure of the drainage network is built based on complex networks. Topological structure is an important concept in complex networks. Complex networks can abstract various components and relationships in actual systems into the form of graphs, and graphs are considered to be the best tools for describing topological structures. Graphs are composed of nodes, connections, and mapping functions that define node connections, which constitute a data structure that represents the network structure. Nodes are used to represent different components, while connections are called edges, which are used to represent the relationship between different components or nodes, thereby effectively expressing the complex network structure and topological relationship.

[0028] The topological attributes in the drainage network topology mainly refer to the association between the components in the drainage network system. The topological relationship only represents the connection between nodes and pipe segments, and does not reflect the spatial distribution and attributes of the components themselves. The nodes in the topological attributes can represent ancillary facilities such as rainwater inlets and inspection wells connected to the pipe segment, while the edges represent the pipe segment itself.

[0029] It should be noted that the above-mentioned nodes are equivalent to the initial nodes in the embodiments of the present application.

[0030] In order to successfully construct the topological structure of the drainage network and calculate the index of the topological attributes, it is necessary to first construct the adjacency matrix of the drainage network system based on the complex network. There are two ways to store the network structure. In the expression of the set form, the number of nodes in the network i Used to represent the number of components in a complex network ( N ), namely the inspection wells and other ancillary facilities in the drainage network system, j The set of edges E Therefore, the network structure of a drainage pipe network system can be directly represented by a set of nodes and edges, that is, G= ( N, E ). In addition, the adjacency matrix is ​​also one of the commonly used expressions, generally using A =( ) to indicate whether there is an edge between nodes. =1, it means the node i and j There is an edge connecting the two nodes; if =0 means node i and j There is no connection between them.

[0031] In some embodiments of the present application, the topological attributes include degree and betweenness, and the fragility includes the relative size of network efficiency and the relative size of the largest connected subgraph.

[0032] In a network structure, the degree of a node refers to the number of directed or undirected edges connected to the node. Degree is a basic and key indicator for describing the topological properties of a single node. N ) represents the number of components in the system and is usually used to indicate the size of the network. N A network of nodes G , if there is an adjacency matrix A =( ) N * N , then the degree of a node can be defined as follows: ;Formula (1) in, Indicates degree, N Indicates the total number of nodes, i and j All represent nodes. Representation Node i and nodes j The connectivity status between them.

[0033] Theoretically, in the entire network, the greater the degree of a node, the more important it is. In the drainage network system, the degree reflects the degree of connectivity between a single node and other nodes. The greater the degree, the more likely it is that this node will receive more water from other nodes, and the more likely it is to become a flood-prone point when fully loaded.

[0034] In addition, betweenness is also one of the key indicators in topological properties. A To Node B In the process of j The ratio of the number of to the total number of shortest paths is defined as follows: ;Formula (2) in, represents the betweenness, Representation Node A To Node B In the process of j The number of Representation Node A To Node B The total number of shortest paths in the process.

[0035] The larger the betweenness of a node, the more important it is to the entire network. In a drainage network system, the larger the betweenness of a single node, the greater the possibility that water will flow through the node.

[0036] In a complex network, network performance will gradually decline as nodes or edges are damaged, and may even cause the network to collapse. This performance degradation is mainly manifested in characteristics such as the vulnerability (resistance) of the network. These characteristics are interrelated and together constitute the key indicators for evaluating the performance of the entire network. Specific indicators that describe network performance after node damage usually include network efficiency, network connectivity, and the largest connected subgraph, among which network efficiency and connectivity reflect the utility and connectivity of the network, and the largest connected subgraph reflects the network's resistance to destruction. In a drainage network system, the failure of a node or the overload of a pipe section will also have an impact on the entire system. Generally speaking, the greater the impact of node damage on the entire system, the more critical this node is, and the more it needs to be the focus of subsequent governance strategies.

[0037] In the entire network, when the node A and nodes B If there is a path between them, they are considered connected; otherwise, if there is no such path, the nodes A and nodes B is considered disconnected. If all pairs of nodes in the network are connected, the network is called a fully connected network. In addition, if there is at least one path between any two nodes in a subgraph in the network, then this subgraph is called a connected subgraph of the original graph. Among all the connected subgraphs, the one with the most nodes is called the maximal connected subgraph of the network, also called the largest connected subgraph. Assume N is the number of components when fully connected. When a component malfunctions or is damaged, the entire network system begins to decompose into several networks or sub-connected graphs, and the largest connected sub-graph gradually becomes smaller. N’ is the number of components in the largest connected subgraph after damage. The relative size of the largest connected subgraph is defined as N' / N ,but j The relative size of the largest connected subgraph indicates the removal of j The ratio of the number of components in the largest connected subgraph after the node to the number of components in the largest connected subgraph of the entire network is as follows: ;Formula (3) in, J represents the relative size of the largest connected subgraph, N’ is the number of components in the maximum connected subgraph after damage, N is the number of components when it is fully connected.

[0038] Similarly, the relative size of the network efficiency of a single node indicates the change in network efficiency after the node is damaged. The smaller the value of the relative size of the network efficiency, the greater the impact of this node on the entire drainage network system after being damaged. The calculation formula for network efficiency is as follows: ;Formula (4) in, Indicates the relative size of network efficiency, N is the number of components when fully connected, i and j All represent nodes. G Represents the network, node i and nodes j The distance between.

[0039] From the four indicators of degree, betweenness, relative size of network efficiency, and relative size of the largest connected subgraph, it can be seen that there are large differences between the indicators of individual nodes based on complex networks. From an overall analysis, the larger the degree of the node, the larger the betweenness, and the smaller the relative size of the network efficiency, the smaller the relative size of the largest connected subgraph.

[0040] In some embodiments of the present application, the water catchment volume includes the catchment area and the average runoff coefficient.

[0041] It is understandable that the water volume of a single node is mainly related to the catchment area of ​​the node and the average runoff coefficient of the node. Generally speaking, the larger the catchment area of ​​the node, the larger the average runoff coefficient, the greater the amount of water entering the pipe section, and the more likely it is to form waterlogging and waterlogging points at this node and its downstream pipe section.

[0042] In some embodiments of the present application, the pipe network characteristics include the downstream pipe diameter, the difference between upstream and downstream pipe diameters, and the downstream pipe slope.

[0043] The smaller the downstream pipe diameter of a single node, the greater the difference between the upstream and downstream pipe diameters, and the smaller the downstream pipeline slope, the easier it is for the pipeline to be overloaded, and the more likely it is that the node will be a critical point where waterlogging may occur.

[0044] Since there are large differences among several waterlogging indicators such as degree, betweenness, relative size of network efficiency, relative size of the largest connected subgraph, catchment area, average runoff coefficient, downstream pipe diameter, upstream and downstream pipe diameter difference and downstream pipe slope, it is necessary to reasonably allocate the weight coefficients of various waterlogging indicators.

[0045] In some embodiments of the present application, the index scores corresponding to the topological attributes, vulnerability, water catchment and pipe network characteristics of each initial node are calculated based on the entropy weight method, including: An evaluation index matrix is ​​constructed based on topological attributes, vulnerability, water catchment, pipe network characteristics, and corresponding multiple initial nodes. The evaluation index matrix is ​​used to represent the index value of each waterlogging index corresponding to each initial node; Based on the evaluation index matrix, calculate the index proportion of each waterlogging index corresponding to each initial node; The information entropy value of each waterlogging indicator is calculated according to the indicator proportion of each waterlogging indicator corresponding to each initial node; The weight of each waterlogging indicator is calculated according to the information entropy value of each waterlogging indicator; Normalize the index values ​​of each waterlogging index corresponding to each initial node to obtain the standard value of each waterlogging index corresponding to each initial node; According to the weight of each waterlogging indicator and the standard value of each waterlogging indicator corresponding to each initial node, the indicator score corresponding to the topological attribute, vulnerability, water catchment and pipe network characteristics of each node is determined.

[0046] It is understandable that according to M Waterlogging indicators and their corresponding N Initial nodes, construct the evaluation index matrix: R = ;Formula (5) in, R represents the evaluation index matrix, x Indicates the indicator value.

[0047] The calculation formula of the index proportion is: ;Formula (6) in, Indicates j The first i The index proportion of each node, Indicates j The first i The index value of each node, m is the total number of nodes.

[0048] The calculation formula of information entropy value is: ;Formula (7) in, Indicates j The first i The information entropy value of each node is Indicates j The first i The index proportion of each node, m is the total number of nodes, k=1 / lnm .

[0049] The weight calculation formula is: ;Formula (8) in, Indicates j The first i The information entropy value of each node is Indicates j The weight of the waterlogging index, and 0≤ ≤1, n It is the total number of waterlogging indicators.

[0050] Since the selected waterlogging indicators include positive indicators and negative indicators, and the dimensions of each waterlogging indicator are different, in order to facilitate comprehensive calculation, the indicator values ​​of each waterlogging indicator are normalized. The calculation formula of the standard value is: ;Formula (9) in, Indicates j The first i The standard value of nodes, and 0≤ ≤1, Indicates j The first i The index value of each node, and Respectively represent j The maximum and minimum values ​​of all indicators of the waterlogging index.

[0051] The indicator score is equal to the product of the indicator value and the standard value.

[0052] In some embodiments of the present application, multiple nodes are selected from each initial node as waterlogging key nodes according to each indicator score and a preset number of nodes, including: Arrange the scores of each indicator from high to low; A number of initial nodes with high index scores are selected as key nodes for waterlogging, and the number of key nodes for waterlogging is equal to the preset number of nodes.

[0053] It is understandable that the higher the index score, the greater the criticality of the initial node, and the greater the probability that it is a key node for waterlogging. Selecting multiple initial nodes with the highest index scores as key nodes for waterlogging can effectively identify accurate key nodes for waterlogging. It should be noted that the number of key nodes for waterlogging can be determined as needed and cannot be regarded as a limitation on this application.

[0054] According to the method for identifying key nodes of waterlogging in the drainage network in the embodiment of the present application, the present application evaluates the criticality of each initial node by considering four waterlogging indicators with a high correlation with waterlogging, namely topological attributes, vulnerability, water collection volume and network characteristics. The identified key nodes of waterlogging are more accurate, and objectively assigned values ​​through the entropy weight method. The weights of each waterlogging indicator are determined based on the variability of the data itself, which can effectively avoid the deviation of subjective assignment. After calculating the indicator scores corresponding to the topological attributes, vulnerability, water collection volume and network characteristics of each initial node, multiple nodes are selected from each initial node as key nodes of waterlogging according to a preset number of nodes, which can improve the efficiency, accuracy, standardization and systematicness of identifying key nodes of waterlogging in the drainage network.

[0055] According to the drainage network waterlogging key node identification system of the second aspect of the present application, the system includes a network information acquisition module, a waterlogging index determination module, an index score determination module and a waterlogging key node determination module.

[0056] The pipe network information acquisition module is used to obtain the basic pipe network information of the drainage pipe network system; The waterlogging index determination module is used to determine the topological attributes, vulnerability, water collection and network characteristics corresponding to each initial node in the drainage network system according to the basic information of the network. The topological attributes are used to characterize the degree of connectivity between the target node and other initial nodes and the possibility of water flow through the target node. The vulnerability is used to characterize the degree of impact of the damage of the target node on the drainage network system. The network characteristics are used to characterize the characteristics of the upstream and downstream pipelines of the target node. The target node is any one of the multiple initial nodes. The indicator score determination module is used to calculate the indicator scores corresponding to the topological attributes, vulnerability, water catchment and pipe network characteristics of each initial node based on the entropy weight method; The waterlogging key node determination module is used to select multiple waterlogging key nodes from each initial node according to each indicator score and a preset number of nodes.

[0057] It can be understood that the basic information of the pipe network is the two-dimensional data of the drainage pipe network, and the basic information of the pipe network is obtained through the following steps: Obtain basic information of the study area, nodes and drainage network; Perform data cleaning and outlier processing on the basic information of the research area, the basic information of the nodes, and the basic information of the drainage network, normalize the processed basic information of the research area, the basic information of the nodes, and the basic information of the drainage network, and extract features from the normalized basic information of the research area, the basic information of the nodes, and the basic information of the drainage network to form feature vectors; Input the feature vector into the trained drainage network simulation model to obtain the two-dimensional data of the drainage network; Among them, data cleaning and outlier processing specifically include: removing or completing missing data, removing or modifying data with format and content errors, and removing or modifying data with logical errors.

[0058] In some embodiments of the present application, topological attributes and fragility are obtained by the following steps: Construct the drainage network topology structure based on the basic information of the network; Determine the topological attributes and vulnerabilities corresponding to each initial node in the drainage network topology.

[0059] It is understandable that the topological structure of the drainage network is built based on complex networks. Topological structure is an important concept in complex networks. Complex networks can abstract various components and relationships in actual systems into the form of graphs, and graphs are considered to be the best tools for describing topological structures. Graphs are composed of nodes, connections, and mapping functions that define node connections, which constitute a data structure that represents the network structure. Nodes are used to represent different components, while connections are called edges, which are used to represent the relationship between different components or nodes, thereby effectively expressing the complex network structure and topological relationship.

[0060] The topological attributes in the drainage network topology mainly refer to the association between the components in the drainage network system. The topological relationship only represents the connection between nodes and pipe segments, and does not reflect the spatial distribution and attributes of the components themselves. The nodes in the topological attributes can represent ancillary facilities such as rainwater inlets and inspection wells connected to the pipe segment, while the edges represent the pipe segment itself.

[0061] Topological attributes include degree and betweenness, and vulnerability includes the relative size of network efficiency and the relative size of the largest connected subgraph. The larger the degree of a node, the more important the node is. In the drainage network system, the degree reflects the degree of connectivity between a single node and other nodes. The larger the degree, the more likely this node is to receive more water from other nodes, and the more likely it is to become a flood-prone point when fully loaded. The larger the betweenness of a node, the more important this node is to the entire network. In the drainage network system, the larger the betweenness of a single node, the greater the possibility that water will flow through the node. The smaller the relative size of the network efficiency and the relative size of the largest connected subgraph, the greater the impact of this node on the entire drainage network system after being damaged.

[0062] The water volume includes the catchment area and the average runoff coefficient, and the pipe network characteristics include the downstream pipe diameter, the difference between the upstream and downstream pipe diameters, and the downstream pipe slope. The water volume of a single node is mainly related to the catchment area of ​​this node and the average runoff coefficient of the node. Generally speaking, the larger the catchment area of ​​the node, the larger the average runoff coefficient, the greater the amount of water entering the pipe section, and the more likely it is to form waterlogging and waterlogging points at this node and its downstream pipe section. The smaller the downstream pipe diameter of a single node, the greater the difference between the upstream and downstream pipe diameters, and the smaller the downstream pipe slope, the easier it is to cause pipeline overload, and the more likely it is to be a critical node where waterlogging may occur.

[0063] It should be noted that the above-mentioned nodes are equivalent to the initial nodes in the embodiments of the present application.

[0064] Since there are large differences among several waterlogging indicators such as degree, betweenness, relative size of network efficiency, relative size of the largest connected subgraph, catchment area, average runoff coefficient, downstream pipe diameter, upstream and downstream pipe diameter difference and downstream pipe slope, it is necessary to reasonably allocate the weight coefficients of various waterlogging indicators.

[0065] In some embodiments of the present application, the index scores corresponding to the topological attributes, vulnerability, water catchment and pipe network characteristics of each initial node are calculated based on the entropy weight method, including: An evaluation index matrix is ​​constructed based on topological attributes, vulnerability, water catchment, pipe network characteristics, and corresponding multiple initial nodes. The evaluation index matrix is ​​used to represent the index value of each waterlogging index corresponding to each initial node; Based on the evaluation index matrix, calculate the index proportion of each waterlogging index corresponding to each initial node; The information entropy value of each waterlogging indicator is calculated according to the indicator proportion of each waterlogging indicator corresponding to each initial node; The weight of each waterlogging indicator is calculated according to the information entropy value of each waterlogging indicator; Normalize the index values ​​of each waterlogging index corresponding to each initial node to obtain the standard value of each waterlogging index corresponding to each initial node; According to the weight of each waterlogging indicator and the standard value of each waterlogging indicator corresponding to each initial node, the indicator score corresponding to the topological attribute, vulnerability, water catchment and pipe network characteristics of each node is determined.

[0066] The entropy weight method can perform objective assignment and determine the weights of various waterlogging indicators based on the variability of the data itself, which can effectively avoid the deviation of subjective assignment. After calculating the indicator scores corresponding to the topological attributes, vulnerability, water volume and network characteristics of each initial node, multiple nodes are selected from each initial node as key waterlogging nodes according to the preset number of nodes, which can improve the efficiency, accuracy, standardization and systematicness of identifying key nodes for waterlogging in the drainage network.

[0067] According to the drainage network waterlogging key node identification system of the embodiment of the present application, the present application evaluates the criticality of each initial node by considering four waterlogging indicators with a high correlation with waterlogging, namely topological attributes, vulnerability, water collection volume and network characteristics. The identified key waterlogging nodes are more accurate, and objectively assigned values ​​through the entropy weight method. The weights of each waterlogging indicator are determined based on the variability of the data itself, which can effectively avoid the deviation of subjective assignment. After calculating the indicator scores corresponding to the topological attributes, vulnerability, water collection volume and network characteristics of each initial node, multiple nodes are selected from each initial node as waterlogging key nodes according to a preset number of nodes, which can improve the efficiency, accuracy, standardization and systematicness of identifying key nodes for waterlogging in the drainage network.

[0068] In addition, an embodiment of the present application further provides a control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor and the memory may be connected via a bus or other means.

[0069] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0070] The non-transient software program and instructions required to implement the drainage network waterlogging key node identification method of the above embodiment are stored in the memory, and when executed by the processor, the drainage network waterlogging key node identification method of the above embodiment is executed.

[0071] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] In addition, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor or controller, for example, by the above-mentioned processor, so that the above-mentioned processor can execute the method for identifying key nodes of waterlogging in the drainage network in the above-mentioned embodiment.

[0073] It will be appreciated by those skilled in the art that all or some of the steps and systems in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0074] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. A method for identifying key nodes of waterlogging in a drainage network, characterized in that: The method comprises: Obtain basic information of the drainage pipe network system; Determine the topological attributes, fragility, water collection and pipe network characteristics corresponding to each initial node in the drainage pipe network system according to the pipe network basic information, wherein the topological attributes are used to characterize the degree of connectivity between the target node and other initial nodes and the possibility of water flowing through the target node, the fragility is used to characterize the degree of influence of damage to the target node on the drainage pipe network system, and the pipe network characteristics are used to characterize the characteristics of the upstream and downstream pipes of the target node, and the target node is any one of the multiple initial nodes; Calculate the index scores corresponding to the topological attributes, the vulnerability, the water catchment volume and the pipe network characteristics of each of the initial nodes based on the entropy weight method; A plurality of key nodes for waterlogging are selected from the initial nodes according to the index scores and the preset number of nodes.

2. The method for identifying key nodes of waterlogging in drainage network according to claim 1, characterized in that: The topological attributes and the vulnerability are obtained by the following steps: Constructing a drainage network topology structure according to the basic information of the network; The topological attribute and the vulnerability corresponding to each of the initial nodes in the drainage network topological structure are determined.

3. The method for identifying key nodes of waterlogging in a drainage network according to claim 1 or 2, characterized in that: The topological properties include degree and betweenness, and the fragility includes the relative size of network efficiency and the relative size of the largest connected subgraph.

4. The method for identifying key nodes of waterlogging in drainage network according to claim 1, characterized in that: The water volume includes the water catchment area and the average runoff coefficient.

5. The method for identifying key nodes of waterlogging in drainage network according to claim 1, characterized in that: The pipe network characteristics include downstream pipe diameter, upstream and downstream pipe diameter difference and downstream pipe slope.

6. The method for identifying key nodes of waterlogging in drainage network according to claim 1, characterized in that: The calculating of the index scores corresponding to the topological attributes, the vulnerability, the water catchment volume and the pipe network characteristics of each of the initial nodes based on the entropy weight method includes: An evaluation index matrix is ​​constructed according to the topological attributes, the vulnerability, the water catchment volume, the pipe network characteristics, and the corresponding plurality of initial nodes, wherein the evaluation index matrix is ​​used to represent the index value of each waterlogging index corresponding to each initial node; Calculate the index proportion of each waterlogging index corresponding to each initial node based on the evaluation index matrix; Calculate the information entropy value of each waterlogging indicator according to the indicator proportion of each waterlogging indicator corresponding to each of the initial nodes; The weight of each waterlogging indicator is calculated according to the information entropy value of each waterlogging indicator; Normalizing the index values ​​of each waterlogging index corresponding to each of the initial nodes to obtain the standard values ​​of each waterlogging index corresponding to each of the initial nodes; The index scores corresponding to the topological attributes, the vulnerability, the water catchment volume and the pipe network characteristics of each node are determined according to the weights of each waterlogging index and the standard values ​​of each waterlogging index corresponding to each initial node.

7. The method for identifying key nodes of waterlogging in drainage network according to claim 1, characterized in that: The selecting a plurality of key nodes from each of the initial nodes according to each of the indicator scores and the preset number of nodes as waterlogging key nodes includes: Arrange the scores of each indicator in order from high to low; A plurality of the initial nodes with the highest index scores are selected as the key waterlogging nodes, and the number of the key waterlogging nodes is equal to the preset number of nodes.

8. A drainage network waterlogging key node identification system, characterized in that: The system comprises: The pipe network information acquisition module is used to obtain the basic pipe network information of the drainage pipe network system; A waterlogging index determination module, used to determine the topological attributes, vulnerability, water collection and pipe network characteristics corresponding to each initial node in the drainage pipe network system according to the basic pipe network information, wherein the topological attributes are used to characterize the degree of connectivity between the target node and other initial nodes and the possibility of water flowing through the target node, the vulnerability is used to characterize the degree of influence of damage to the target node on the drainage pipe network system, and the pipe network characteristics are used to characterize the characteristics of the upstream and downstream pipes of the target node, and the target node is any one of the multiple initial nodes; An index score determination module, used to calculate the index scores corresponding to the topological attributes, the vulnerability, the water volume and the pipe network characteristics of each of the initial nodes based on the entropy weight method; The waterlogging key node determination module is used to select a plurality of waterlogging key nodes from each of the initial nodes according to each of the indicator scores and a preset number of nodes.

9. A control device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for identifying key nodes of waterlogging in a drainage network as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that: The computer executable instructions are used to execute the method for identifying key nodes of waterlogging in a drainage network as described in any one of claims 1 to 7.

Images