Method and apparatus for determining abnormal pressure gauge node, electronic device, and storage medium

Abstract

The present invention relates to the technical field of water supply data, and provides a method and apparatus for determining an abnormal pressure gauge node, an electronic device, and a storage medium. The method comprises: on the basis of the positions of pressure gauge nodes in a water supply pipe network model diagram and pipe network water flow directions, acquiring all pressure node groups; respectively acquiring path sets of the pressure node groups, and when the path sets meet a preset condition, connecting the pressure node groups corresponding to the path sets to construct a water supply monitoring diagram; on the basis of the positional relationship between the pressure gauge nodes in the water supply monitoring diagram, determining a pressure monitoring coefficient matrix; and on the basis of pressure data of the pressure gauge nodes within an acquisition period and the pressure monitoring coefficient matrix, determining monitored and analyzed pressure data corresponding to the pressure gauge nodes, and on the basis of the monitored and analyzed pressure data, determining whether the pressure gauge nodes corresponding to the monitored and analyzed pressure data are abnormal or not. In the present invention, abnormal data in pressure data is amplified by means of a pressure monitoring coefficient matrix, thereby improving the accuracy of abnormal pressure gauge node monitoring.

Description

Abnormal pressure gauge node determination method, device, electronic device and storage medium Technical Field

[0001] The present invention relates to the field of water supply data technology, and in particular to a method, device, electronic device and storage medium for determining an abnormal pressure gauge node. Background Art

[0002] Water plays a vital role in our daily lives, and protecting water resources from pollution and waste has become a consensus. However, as one of the many abnormal events in water supply networks, leakage is a common problem in urban water supply networks.

[0003] Currently, the traditional listening method is often used to identify abnormal pressure gauge nodes in urban water supply networks. This involves manually testing the pressure of each pressure gauge node along the urban water supply pipeline. Based on the test results, each pressure gauge node is identified as an abnormal one. However, manual identification of abnormal pressure gauge nodes is inaccurate and inefficient.

[0004] Summary of the Invention

[0005] To solve the above problems, the present invention provides a method, device, electronic device and storage medium for determining abnormal pressure gauge nodes.

[0006] According to a first aspect of the present invention, a method for determining an abnormal pressure gauge node is provided, which is applied to a town water supply network. The method for determining abnormal pressure in a water supply network comprises:

[0007] Obtaining all pressure node groups based on the position of each pressure gauge node in the water supply network model diagram and the water flow direction of the network, wherein the pressure node group is composed of two pressure gauge nodes connected by water flow, and the water supply network model diagram is constructed based on the urban water supply network;

[0008] Obtaining a path set for each pressure node group respectively, and connecting two pressure gauge nodes in the pressure node group corresponding to the path set if the path set meets a preset condition to construct a water supply monitoring map;

[0009] Determine a pressure monitoring coefficient matrix based on the positional relationship between the pressure gauge nodes in the water supply monitoring map, wherein the pressure monitoring coefficient matrix is ​​used to amplify abnormal pressure values;

[0010] According to the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix, the monitoring pressure data corresponding to each pressure gauge node is determined, and according to the monitoring pressure data, it is determined whether the pressure gauge node corresponding to the monitoring pressure data is abnormal.

[0011] Optionally, respectively obtaining the path sets of the pressure node groups includes:

[0012] Obtaining node information, pipeline structure, and water flow direction of each node in the water supply network model diagram, wherein the nodes include pressure gauge nodes and non-pressure gauge nodes;

[0013] Constructing a directed adjacency matrix corresponding to the water supply network model diagram according to the node information and the pipeline structure, wherein the directed adjacency matrix is ​​used to represent the positional relationship between each of the nodes;

[0014] The path set corresponding to the pressure node group is determined according to the directed adjacency matrix.

[0015] Optionally, when determining that the path aggregation meets a preset condition, the method includes:

[0016] In a case where the nodes in at least one of the paths do not include a target pressure gauge node, determining that the path set meets a preset condition, and connecting two of the pressure gauge nodes in the pressure node group corresponding to the path set, wherein the target pressure gauge node is the pressure gauge node other than the two pressure gauge nodes in the pressure node group;

[0017] In a case where the nodes in each of the paths include the target pressure gauge node, it is determined that the path set does not meet a preset condition.

[0018] Optionally, determining the pressure monitoring coefficient matrix according to the positional relationship between the pressure gauge nodes in the water supply monitoring map includes:

[0019] Obtaining the positional relationship between the pressure gauge nodes in the water supply monitoring diagram;

[0020] Constructing an undirected adjacency matrix corresponding to the water supply monitoring map according to the positional relationship;

[0021] Determining a degree matrix corresponding to the water supply monitoring graph according to the undirected adjacency matrix;

[0022] A Laplace matrix is ​​determined according to the undirected adjacency matrix and the degree matrix, and the Laplace matrix is ​​determined as the pressure monitoring coefficient matrix.

[0023] Optionally, determining the monitoring pressure data corresponding to each pressure gauge node according to the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix includes:

[0024] Obtaining pressure data collected by the pressure gauge node during a collection period;

[0025] The monitoring pressure data is determined according to the product of the pressure data and the pressure monitoring coefficient matrix.

[0026] Optionally, determining, based on the monitoring and analysis pressure data, whether an abnormality occurs in the pressure gauge node corresponding to the monitoring and analysis pressure data includes:

[0027] When the pressure value included in the monitoring and analysis pressure data is greater than the second pressure value, or the pressure value is less than the first pressure value, determining that the pressure gauge node corresponding to the monitoring and analysis pressure data is abnormal;

[0028] When the pressure value in the monitoring and analysis pressure data is between the first pressure value and the second pressure value, it is determined that the pressure gauge node corresponding to the monitoring and analysis pressure data is normal.

[0029] Optionally, after determining the monitoring pressure data corresponding to each pressure gauge node according to the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix, the method further includes:

[0030] According to the Savitzky-Golay algorithm and the monitoring and analysis pressure data, target monitoring and analysis pressure data is generated, and according to the target monitoring and analysis pressure data, it is determined whether the pressure gauge node corresponding to the target monitoring and analysis pressure data is abnormal.

[0031] According to a second aspect of the present invention, a device for determining an abnormal pressure gauge node is provided, which is applied to a town water supply network. The device for determining an abnormal pressure gauge node comprises:

[0032] an acquisition module, configured to acquire all pressure node groups based on the position of each pressure gauge node in the water supply network model diagram and the water flow direction of the network, wherein the pressure node group is composed of two pressure gauge nodes connected by water flow, and the water supply network model diagram is constructed based on the urban water supply network;

[0033] a construction module, configured to respectively obtain a path set of each pressure node group, and connect two pressure gauge nodes in the pressure node group corresponding to the path set if the path set meets a preset condition;

[0034] A determination module, configured to determine a pressure monitoring coefficient matrix based on the positional relationship between the pressure gauge nodes in the water supply monitoring diagram, wherein the pressure monitoring coefficient matrix is ​​used to amplify abnormal pressure values;

[0035] The monitoring module is used to determine the monitoring pressure data corresponding to each pressure gauge node based on the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix, and determine whether the pressure gauge node corresponding to the monitoring pressure data is abnormal based on the monitoring pressure data.

[0036] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory is used to store computer instructions that can be executed on the processor, and the processor is used to determine the abnormal pressure gauge node based on the method described in the first aspect when executing the computer instructions.

[0037] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the program is executed by a processor, the method for determining an abnormal pressure gauge node according to the first aspect is implemented.

[0038] The technical solution provided by the present invention can have the following beneficial effects:

[0039] The present invention provides a method for determining abnormal pressure gauge nodes. First, according to the water flow direction of the pipe network and the position of each pressure gauge node in a pre-constructed water supply pipe network model diagram, all pressure node groups in the water supply model diagram are obtained. Further, a path set of each pressure node group is obtained. When the path set meets the preset conditions, two pressure gauge nodes in the pressure node group are connected to construct a water supply monitoring diagram. Further, the positional relationship between each pressure gauge node in the water supply monitoring diagram is used to determine a pressure monitoring coefficient matrix for amplifying abnormal pressure values. Further, the pressure monitoring coefficient matrix is ​​used to process the collected pressure data to determine the monitoring pressure data, and the monitoring pressure data is used to determine whether the pressure gauge node is abnormal. The present invention can construct a water supply monitoring diagram according to the structural characteristics of the water supply model diagram through the path set of the pressure node group. Further, the corresponding pressure monitoring coefficient matrix can be accurately determined according to the structural characteristics of the water supply monitoring diagram, and the pressure monitoring coefficient matrix can be used to effectively amplify the abnormal data in the pressure data, so that the monitoring pressure data can be used to accurately determine the pressure gauge node where the abnormality occurs, thereby improving the accuracy of abnormal pressure gauge node monitoring. In addition, the present invention determines the abnormal pressure gauge node through the water supply model diagram, thereby eliminating the need to determine the abnormal pressure gauge node manually, thereby improving the monitoring efficiency of the abnormal pressure gauge node. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] FIG1 is a flow chart of a method for determining an abnormal pressure gauge node provided by an embodiment of the present invention;

[0041] FIG2 is a diagram of a water supply network model provided by an embodiment of the present invention;

[0042] FIG3 is a water supply network monitoring diagram provided by an embodiment of the present invention;

[0043] FIG4 is a line graph of pressure data of the pressure gauge node 23 within a collection period provided by an embodiment of the present invention;

[0044] FIG5 is a line graph of monitoring pressure data of a pressure gauge node 23 provided in an embodiment of the present invention;

[0045] FIG6 is a flowchart of another method for determining an abnormal pressure gauge node provided by an embodiment of the present invention;

[0046] FIG7 is a block diagram of an abnormal pressure gauge node determination device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0048] The terms used in this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The singular forms "a," "the," and "the" used in this invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0049] It should be understood that although the terms "first," "second," "third," etc. may be used in the present invention to describe various information, such information should not be limited to these terms. These terms are merely used to distinguish information of the same type from one another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. Depending on the context, the term "if" as used herein may be interpreted as "when," "when," or "in response to determining."

[0050] In a first aspect, an embodiment of the present invention provides a method for determining an abnormal pressure gauge node, which is applied to a town water supply network. As shown in FIG1 , the method includes:

[0051] S101: Obtain all pressure node groups according to the position of each pressure gauge node in the water supply network model diagram and the water flow direction of the network.

[0052] In this embodiment, the node information, pipeline information, and pipeline topology of the urban water supply network to be monitored are first collected. This information is then used to construct a water supply network model diagram. Nodes include pressure gauge nodes and non-pressure gauge nodes. Node information may include elevation, water storage capacity, and location information. Pipeline information may include pipe diameter, manufacturer, and maintenance information. The pipeline topology may include the pipeline structure and the direction of water flow in the network. Furthermore, using the location of each pressure gauge node and the direction of water flow in the network, two pressure gauge nodes connected by water flow are identified. Based on these connected pressure gauge nodes, pressure node groups are then determined. The pressure gauge nodes in the water supply network model diagram are then traversed to obtain all pressure node groups.

[0053] Specifically, as shown in Figure 2, a water supply network model diagram is provided in an embodiment of the invention. The pressure gauge nodes of the water supply network model diagram are 10, 21, 23, and 32. After determining the positions of the pressure gauge nodes, the two pressure gauge nodes connected by the water flow are determined to be "10, 21", "10, 23", "10, 22", "21, 22" and "21, 23" according to the water flow direction of the network, so that the total pressure node groups are "10, 21", "10, 23", "10, 22", "21, 22" and "21, 23".

[0054] In one example, the water supply network model diagram in this embodiment can be an electronic file in inp format, or electronic files in other formats can be selected according to actual needs.

[0055] S102 , respectively obtaining a path set of each pressure node group, and if the path set meets a preset condition, connecting two pressure gauge nodes in the pressure node group corresponding to the path set to construct a water supply monitoring diagram.

[0056] In this embodiment, after all pressure node groups are obtained, the path sets corresponding to each pressure node group are obtained based on the water supply network model diagram. That is, the nodes passing between two connected pressure gauge nodes in the pressure node group are obtained to obtain the path sets corresponding to the pressure node groups. Furthermore, it is determined whether each path set meets the preset conditions. If the path set meets the preset conditions, the two pressure gauge nodes in the pressure node group corresponding to the path combination that meets the conditions are connected to construct a water supply monitoring diagram. For example, if the path set corresponding to the pressure node group "10, 21" meets the preset conditions, "10, 21" are connected, and so on, and the two pressure gauge nodes in the pressure node group corresponding to the path set that meets the preset conditions are connected respectively.

[0057] S103: Determine a pressure monitoring coefficient matrix according to the positional relationship between the pressure gauge nodes in the water supply monitoring diagram.

[0058] In this embodiment, after constructing the water supply monitoring map, the positional relationship between the pressure gauge nodes in the water supply monitoring map is obtained, and the positional relationship between the pressure gauge nodes is used to determine the pressure monitoring coefficient matrix. Specifically, the pressure monitoring coefficient matrix in this embodiment is used to amplify abnormal pressure values.

[0059] S104, determining the monitoring pressure data corresponding to each pressure gauge node based on the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix, and determining whether the pressure gauge node corresponding to the monitoring pressure data is abnormal based on the monitoring pressure data.

[0060] In this embodiment, after determining the pressure monitoring coefficient matrix, the pressure data of each pressure gauge node within the acquisition period is obtained, and the pressure monitoring coefficient matrix is ​​further used to process the obtained pressure data to obtain the pressure monitoring data corresponding to each pressure gauge node. Furthermore, the obtained pressure monitoring data is used to determine whether the corresponding pressure gauge node has an abnormality. Specifically, for example, if the water supply network model diagram includes pressure gauge node 10, pressure gauge node 21, pressure gauge node 23, and pressure gauge node 32, the pressure data corresponding to pressure gauge node 10, pressure gauge node 21, pressure gauge node 23, and pressure gauge node 32 are obtained respectively. Further, using the pressure monitoring coefficient matrix, the monitoring pressure data corresponding to pressure gauge node 10, pressure gauge node 21, pressure gauge node 23, and pressure gauge node 32 are obtained respectively. Finally, based on the monitoring pressure data, it is determined whether pressure gauge node 10, pressure gauge node 21, pressure gauge node 23, and pressure gauge node 32 are abnormal.

[0061] The present invention provides a method for determining abnormal pressure gauge nodes. First, according to the water flow direction of the pipe network and the position of each pressure gauge node in a pre-constructed water supply pipe network model diagram, all pressure node groups in the water supply model diagram are obtained. Further, a path set of each pressure node group is obtained. When the path set meets the preset conditions, two pressure gauge nodes in the pressure node group are connected to construct a water supply monitoring diagram. Further, the positional relationship between each pressure gauge node in the water supply monitoring diagram is used to determine a pressure monitoring coefficient matrix for amplifying abnormal pressure values. Further, the pressure monitoring coefficient matrix is ​​used to process the collected pressure data to determine the monitoring pressure data, and the monitoring pressure data is used to determine whether the pressure gauge node is abnormal. The present invention can construct a water supply monitoring diagram according to the structural characteristics of the water supply model diagram through the path set of the pressure node group. Further, the corresponding pressure monitoring coefficient matrix can be accurately determined according to the structural characteristics of the water supply monitoring diagram, and the pressure monitoring coefficient matrix can be used to effectively amplify the abnormal data in the pressure data, so that the monitoring pressure data can be used to accurately determine the pressure gauge node where the abnormality occurs, thereby improving the accuracy of abnormal pressure gauge node monitoring. In addition, the present invention determines the abnormal pressure gauge node through the water supply model diagram, thereby eliminating the need to determine the abnormal pressure gauge node manually, thereby improving the monitoring efficiency of the abnormal pressure gauge node.

[0062] Furthermore, the step of obtaining the path sets of each pressure node group in step S102 may include the following steps:

[0063] S1021, obtaining node information, pipeline structure and water flow direction of each node in the water supply network model diagram.

[0064] In this embodiment, after the water supply network model diagram is constructed using the water supply network, the node information of each node in the water supply network, the pipeline structure of the water supply network model diagram and the water flow direction of the water supply network model diagram are obtained.

[0065] Specifically, taking the water supply network model diagram shown in Figure 2 as an example, there are 11 nodes in the water supply network model diagram, specifically including "9, 10, 11, 21, 31, 2, 12, 22, 32, 13, 23", among which the pressure gauge nodes include "10, 21, 23, 32", and the non-pressure gauge nodes include "9, 11, 31, 2, 12, 22, 13". At the same time, the pipeline structure and the water flow direction of the network can be obtained according to the water supply network model diagram.

[0066] S1022: Construct a directed adjacency matrix corresponding to the water supply network model diagram according to the node information, the pipeline structure, and the water flow direction of the network.

[0067] In this embodiment, after obtaining the node information, pipeline structure and pipeline water flow direction, a directed adjacency matrix of the water supply network model diagram is constructed based on the node information, pipeline structure and pipeline water flow, so as to use the directed adjacency matrix to represent the positional relationship between each node.

[0068] Specifically, taking the water supply network model diagram shown in FIG2 as an example, the directed adjacency matrix corresponding to the water supply network model diagram is shown in Table 1, and the positional relationship between each node is represented by the directed adjacency matrix.

[0069] Table 1

[0070] Among them, 1 in Table 1 indicates that the two nodes are adjacent through a directed edge, and 0 in Table 1 indicates that the two nodes are not adjacent.

[0071] S1023: Determine the path set corresponding to the pressure node group according to the directed adjacency matrix.

[0072] In this embodiment, after obtaining the directed adjacency matrix corresponding to the water supply network model diagram, the depth-first search (DFS) algorithm is used to traverse the directed adjacency matrix based on the two pressure gauge nodes in each pressure node group to obtain the path set corresponding to each pressure node group.

[0073] Specifically, in this embodiment, the pressure node groups include "10, 21", "10, 23", "10, 22", "21, 22" and "21, 23". After determining the pressure node group "10, 21", according to the positions of the pressure gauge node 10 and the pressure gauge node 21 in the directed adjacency matrix, the path set corresponding to the pressure node group "10, 21" can be obtained, including "10→11→21". Similarly, the path sets corresponding to each pressure node group can be obtained. The path sets corresponding to each pressure node group in this embodiment are shown in Table 2:

[0074] Table 2

[0075] Among them, P 1021 Indicates the pressure node group "10, 21".

[0076] In an embodiment of the present invention, a directed adjacency matrix of a water supply network diagram is constructed by means of node information, pipeline structure and pipeline water flow direction, so that the direct adjacency relationship of each node can be accurately grasped, and then the path set corresponding to the pressure node group can be accurately obtained, so that a water supply monitoring diagram can be accurately constructed, and the pressure monitoring coefficient matrix can be used to effectively amplify abnormal data in the pressure data, so that the pressure gauge node where the abnormality occurs can be accurately determined by using the monitoring pressure data, thereby improving the accuracy of abnormal pressure gauge node monitoring.

[0077] Furthermore, when executing step 102, if the path set meets a preset condition, connecting the two pressure gauge nodes in the pressure node group corresponding to the path set may include the following steps:

[0078] S1024: Obtain the nodes of each path in the path set.

[0079] In this embodiment, the nodes of each path in the path set can be obtained according to Table 2, which will not be described in detail here.

[0080] S1025: When at least one node in the path does not include a target pressure gauge node, determine that the path set meets a preset condition, and connect two of the pressure gauge nodes in the pressure node group corresponding to the path set.

[0081] In this embodiment, after obtaining the nodes of each path in the path set, it is determined whether the nodes in each path include the pressure gauge node corresponding to the non-pressure node group. If at least one node in the path set does not include the pressure gauge node corresponding to the non-pressure node group, the path set is determined to meet the preset conditions, and the two pressure gauge nodes in the pressure node group corresponding to the path set are connected. In this embodiment, the target pressure gauge node is the pressure gauge node other than the two pressure gauge nodes in the pressure node group.

[0082] Specifically, take the pressure node group P in Table 2 1032 For example, P 1032 The path set corresponding to the pressure node group includes path 1 "10→11→21→31→32", path 2 "10→11→21→22→32" and path 3 "10→11→12→22→32", where P 1032 The target pressure gauge nodes corresponding to the pressure node group include pressure gauge node 21 and pressure gauge node 23. Path 1 includes pressure gauge node 21 corresponding to the non-pressure node group, and path 1 does not meet the preset conditions. Path 2 includes pressure gauge node 21 corresponding to the non-pressure node group, and path 2 does not meet the preset conditions. Path 3 does not include the target pressure gauge node, so it can be judged that P 1032 There is a path in the pressure node group that meets the preset conditions, and then it is judged that P 1032 The path set corresponding to the pressure node group meets the preset conditions and connects the pressure gauge node 10 and the pressure gauge node 32 , and so on, and it is determined whether each path set meets the preset conditions.

[0083] S1026: When the nodes in each of the paths include the target pressure gauge node, determine that the path set does not meet a preset condition.

[0084] Specifically, when each path in the path set includes the target pressure node, it is determined that the path set does not meet the preset conditions. 1032 If each path in the path set corresponding to the pressure node group includes the pressure gauge node 21 or the pressure gauge node 23, then it is determined that P 1032 The path set corresponding to the pressure node group does not meet the preset conditions.

[0085] Furthermore, when executing step 103, the embodiment of the present invention may include the following steps:

[0086] S1031: Obtain the positional relationship between the pressure gauge nodes in the water supply monitoring diagram.

[0087] In this embodiment, after the water supply monitoring map is constructed, the water supply monitoring map is read to obtain the positional relationship between the pressure gauge nodes in the water supply monitoring map.

[0088] Specifically, as shown in FIG3 , which is a water supply monitoring diagram corresponding to FIG2 of an embodiment of the present invention, the positional relationship between the various pressure gauge nodes can be accurately obtained by reading the water supply monitoring diagram.

[0089] S1032: Construct an undirected adjacency matrix corresponding to the water supply monitoring map according to the positional relationship.

[0090] In this embodiment, after obtaining the positional relationship between each pressure gauge node in the water supply monitoring map, the water supply monitoring map is used to construct an undirected adjacency matrix corresponding to the water supply monitoring map to represent the positional relationship between each pressure gauge node in the water supply monitoring map.

[0091] Specifically, taking the water supply monitoring graph shown in FIG3 as an example, the undirected adjacency matrix corresponding to the water supply monitoring graph is shown in Table 3:

[0092] Table 3

[0093] S1033: Determine a degree matrix corresponding to the water supply monitoring graph according to the undirected adjacency matrix.

[0094] In this embodiment, after obtaining the undirected adjacency matrix of the water supply monitoring map, the wireless adjacency matrix is ​​used to determine the degree matrix corresponding to the undirected adjacency matrix. Specifically, the degree matrix in this embodiment is represented by the first formula, which is as follows:

[0095] Where D represents the degree matrix, D ii Represents the value corresponding to the i-th row and i-th column in the matrix, A represents the undirected adjacency matrix, A iiRepresents the value corresponding to the i-th row and i-th column in the undirected adjacency matrix. j is the total number of columns in matrix A.

[0096] S1034: Determine a Laplace matrix according to the undirected adjacency matrix and the degree matrix, and determine the Laplace matrix as the pressure monitoring coefficient matrix.

[0097] In this embodiment, after obtaining the degree matrix, the undirected adjacency matrix and the degree matrix are used to determine the Laplace matrix, and the Laplace matrix is ​​determined as the pressure monitoring coefficient matrix. Specifically, in this embodiment, the Laplace matrix can be determined by the second formula, which is as follows: L = DA;

[0098] Where L is the Laplace matrix.

[0099] The embodiment of the present invention determines the pressure monitoring coefficient matrix by utilizing the undirected adjacency matrix and degree matrix of the water supply monitoring graph. The pressure monitoring coefficient matrix can be accurately determined according to the structural characteristics of the water supply monitoring graph, and the pressure monitoring coefficient matrix can be used to effectively amplify abnormal data in the pressure data, so that the pressure gauge nodes where abnormalities occur can be accurately determined by using the monitored pressure data, thereby improving the accuracy of monitoring abnormal pressure gauge nodes.

[0100] Furthermore, in the embodiment of the present invention, determining the monitoring pressure data corresponding to each pressure gauge node according to the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix in step 104 may include the following steps:

[0101] S1041: Obtain pressure data collected by the pressure gauge node during a collection period.

[0102] In this embodiment, after determining the pressure monitoring coefficient matrix, the pressure data of the pressure gauge nodes during the collection period is obtained. Specifically, in this embodiment, the total pressure data collected by the pressure gauge nodes during the collection period is collected through a Supervisory Control and Data Acquisition (SCADA) system. Furthermore, the pressure data corresponding to each pressure gauge node is determined from the total pressure data.

[0103] Specifically, in this embodiment, the total pressure data collected by the data acquisition and monitoring control system from the pressure gauge node during the collection period can be represented in the form of a pressure matrix, and the pressure data corresponding to each pressure gauge node can be obtained through the pressure matrix. The pressure matrix is ​​specifically as follows:

[0104] Among them, X represents the pressure matrix, x represents the pressure value of the pressure gauge node, n represents the pressure gauge node, t represents the time of acquisition, xnt Represents the pressure value of pressure gauge node n at time t.

[0105] In one example, as shown in FIG4 , a line graph of pressure data of the pressure gauge node 23 during the collection period is provided in an embodiment of the present invention. Specifically, the pressure data of the pressure gauge node 23 is extracted from the pressure matrix, wherein the X-axis in FIG4 represents the collection time and the Y-axis represents the pressure value.

[0106] S1042: Determine the monitoring pressure data according to the product of the pressure data and the pressure monitoring coefficient matrix.

[0107] In this embodiment, after the pressure data corresponding to each pressure gauge node is obtained, the monitoring pressure data corresponding to the pressure gauge node is determined by multiplying the pressure data by the pressure monitoring coefficient matrix.

[0108] Specifically, in this embodiment, the product of the pressure matrix and the pressure monitoring coefficient matrix is ​​first used to determine the total monitoring pressure data corresponding to the pressure matrix, and then the monitoring pressure data of each pressure gauge node is determined from the detected pressure data. In this embodiment, the total monitoring pressure data is represented by the monitoring pressure matrix, and the monitoring pressure matrix is ​​specifically shown as follows:

[0109] Among them, H represents the monitoring pressure matrix, h nt Represents the monitoring pressure value of pressure gauge node n at time t.

[0110] Furthermore, the monitoring pressure matrix is ​​used to determine the monitoring pressure data corresponding to each pressure gauge node. The pressure monitoring data is specifically as follows:

[0111] Among them, H n Indicates the nth row of the monitoring pressure matrix H, h nt represents the monitoring pressure value of pressure gauge node n at time t, Wn represents the number of adjacent pressure gauge nodes of pressure gauge node n, c represents an adjacent pressure gauge node of pressure gauge node n, v n represents the set of adjacent pressure gauge nodes of pressure gauge node n, x c t represents the pressure value of the adjacent pressure gauge node c of the pressure gauge node n at time t.

[0112] In one example, as shown in FIG5 , which is a line graph of the monitoring pressure data of the pressure gauge node 23 provided in the example of the present invention, it can be seen from FIG5 that the pressure value can be effectively amplified by multiplying the pressure monitoring coefficient matrix and the pressure data, and thus the abnormal pressure value can be amplified.

[0113] The embodiment of the present invention determines the pressure monitoring data through the pressure monitoring coefficient matrix and the pressure data. The pressure monitoring coefficient matrix can be used to amplify the abnormal pressure value in the pressure data, so that it can accurately determine whether there is abnormal pressure in the pressure data, and then accurately determine the pressure gauge node where the pressure abnormality occurs, thereby improving the accuracy of abnormal pressure gauge node monitoring.

[0114] Furthermore, in the embodiment of the present invention, determining whether an abnormality occurs in the pressure gauge node corresponding to the monitoring pressure data according to the monitoring pressure data in step 104 may include the following steps:

[0115] 1043. Determine a first pressure value and a second pressure value corresponding to the monitoring pressure data according to a preset statistical algorithm.

[0116] In this embodiment, after the monitored pressure is obtained, a pre-set statistical algorithm is used to calculate the first and second pressure values ​​corresponding to each monitored pressure data, i.e., to determine a normal pressure value range, where the first pressure value is less than the second pressure value. Specifically, the pre-set statistical algorithm in this embodiment may include a mean-range algorithm, an exponentially weighted moving average algorithm, and a Bollinger Bands algorithm.

[0117] S1044: When the pressure value included in the monitoring and analysis pressure data is greater than the second pressure value, or the pressure value is less than the first pressure value, determine that the pressure gauge node corresponding to the monitoring and analysis pressure data is abnormal.

[0118] In this embodiment, after determining the first pressure value and the second pressure value corresponding to the monitoring pressure data, the monitoring pressure data is compared with the first pressure value and the second pressure value respectively. If the monitoring pressure data includes a pressure value greater than the second pressure value, or a pressure value less than the first pressure value, it is determined that the pressure gauge node corresponding to the monitoring pressure data is abnormal.

[0119] S1045: When the pressure value in the monitoring and analysis pressure data is between the first pressure value and the second pressure value, determine that the pressure gauge node corresponding to the monitoring and analysis pressure data is normal.

[0120] In this embodiment, after determining the first pressure value and the second pressure value corresponding to the monitoring pressure data, the monitoring pressure data is compared with the first pressure value and the second pressure value respectively. When the monitoring pressure data are all greater than or equal to the first pressure value, and the pressure values ​​are all less than or equal to the second pressure value, that is, when the pressure value of the monitoring pressure data is between the first pressure value and the second pressure value, it is determined that the monitoring pressure data is normal, and at the same time, it is determined that the pressure gauge node corresponding to the monitoring pressure data is normal.

[0121] Furthermore, the abnormal pressure gauge node determination method provided by an embodiment of the present invention may further include the following steps after determining the monitoring pressure data corresponding to each pressure gauge node based on the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix:

[0122] S105 , generating target monitoring pressure data according to the Savitzky-Golay algorithm and the monitoring pressure data, and determining whether the pressure gauge node corresponding to the target monitoring pressure data is abnormal according to the target monitoring pressure data.

[0123] In this embodiment, after obtaining the monitoring pressure data, the Savitzky-Golay algorithm can be used to perform secondary processing on the monitoring pressure data to filter the pressure values ​​in the monitoring pressure data, thereby generating target monitoring pressure data. Furthermore, the target monitoring pressure data is used to execute S1043-S1045.

[0124] Specifically, in this embodiment, the target monitoring pressure data can be generated by the third formula, which is as follows:

[0125] Where h′ nt represents the pressure value of the target monitoring pressure data of pressure gauge node n at time t, h n(t+b) represents the monitoring pressure value of pressure gauge node n at time t+b, K represents the length of the sliding window, which can be one day, one week, or one month according to the length of the acquisition period, b represents starting from the -mth time dimension and traversing to the mth time dimension, Q b represents the smoothing coefficient.

[0126] In an example, the length of the sliding window may be based on a fourth formula, which is specifically as follows: K=2m+1.

[0127] The embodiment of the present invention can perform secondary processing on the monitoring and analysis pressure data through the Savitzky-Golay algorithm to filter the pressure values ​​in the monitoring and analysis pressure data to generate target monitoring and analysis pressure data, thereby effectively removing pressure values ​​with obvious abnormal pressures. Further use of the target monitoring and analysis pressure data can improve the accuracy of abnormal pressure value judgment and further improve the accuracy of abnormal pressure gauge node monitoring.

[0128] Furthermore, an embodiment of the present invention provides another method for determining abnormal pressure gauge nodes, as shown in Figure 6. First, the node information, pipeline information and pipeline topology of the monitored urban water supply network are obtained, and the node information, pipeline information and pipeline topology are used to construct a water supply network model diagram. Furthermore, based on the position of each pressure gauge node in the water supply network model diagram and the water flow direction of the network, two pressure gauge nodes connected by water flow are determined to obtain all pressure node groups.

[0129] After obtaining all the pressure node groups, a directed adjacency matrix corresponding to the water supply network model diagram is constructed based on the node information, pipeline structure and water flow direction of the water supply network model diagram, and the path set corresponding to each pressure node group is determined based on the directed adjacency matrix.

[0130] At the same time, it is determined whether the path set meets the preset conditions. If the path set meets the preset conditions, the two pressure gauge nodes in the pressure node group corresponding to the path set are connected to construct a water supply monitoring map. Furthermore, based on the positional relationship between the pressure gauge nodes in the water supply monitoring map, an undirected adjacency matrix corresponding to the water supply monitoring map is generated to generate a degree matrix using the undirected adjacency matrix. Furthermore, based on the undirected adjacency matrix and the degree matrix, a pressure monitoring coefficient matrix is ​​determined.

[0131] After obtaining the pressure monitoring coefficient matrix, the total pressure data collected by the data acquisition and monitoring control system from the pressure gauge nodes during the collection period is obtained, and the total monitoring pressure data is determined based on the product of the total pressure data and the pressure monitoring coefficient matrix. Furthermore, the monitoring pressure data of each pressure gauge node is obtained in the total monitoring pressure data.

[0132] After determining the monitoring pressure data of each pressure gauge, target monitoring pressure data is generated according to the Savitzky-Golay algorithm and the monitoring pressure data, and a preset statistical algorithm is further used to determine the first pressure value and the second pressure value corresponding to the target monitoring pressure data. When there is a pressure value in the target monitoring pressure data that is greater than the second pressure value, or a pressure value that is less than the first pressure value, it is determined that the pressure gauge node corresponding to the monitoring pressure data is abnormal. When the pressure value in the target monitoring pressure data is between the first pressure value and the second pressure value, it is determined that the pressure gauge node corresponding to the monitoring pressure data is normal.

[0133] In one example, the mean range algorithm in this embodiment is shown in the sixth formula to the seventh formula. The specific formulas are as follows:

[0134] Among them, UCL is the second pressure value, LCL is the first pressure value, μ is the mean of the target monitoring pressure data within the acquisition period, σ is the standard deviation, and ρ is the confidence coefficient. For example, ρ values ​​of 1, 2, and 3 approximately correspond to confidence levels of 68%, 95%, and 99.7%, respectively.

[0135] In one example, the exponentially weighted moving average algorithm is shown in the seventh formula to the ninth formula. The specific formula is as follows: t =λh′ nt +(1-λ)Z t-1 ;

[0136] Among them, h' nt represents the pressure value of the target monitoring pressure data of the pressure gauge node n at time t, λ is the smoothing coefficient, Z t To monitor and analyze pressure data, Z t-1 It is the monitoring pressure data of the last collection cycle.

[0137] In one example, the Bollinger Bands algorithm is shown in the tenth formula to the eleventh formula, and the specific formulas are as follows: UCL = MA + ρδ; LCL = MA - ρδ;

[0138] Among them, MA is the moving average and ρ is the confidence coefficient.

[0139] Specifically,

[0140] Another embodiment of the present invention provides an abnormal pressure gauge node determination device, which is applied to a town water supply network. Referring to FIG7 , the device includes:

[0141] An acquisition module 701 is configured to acquire all pressure node groups based on the position of each pressure gauge node in the water supply network model diagram and the water flow direction of the network, wherein the pressure node group is composed of two pressure gauge nodes connected by water flow, and the water supply network model diagram is constructed based on the urban water supply network;

[0142] A construction module 702 is configured to obtain a path set of each pressure node group, and if the path set meets a preset condition, connect the two pressure gauge nodes in the pressure node group corresponding to the path set to construct a water supply monitoring map;

[0143] A determination module 703 is configured to determine a pressure monitoring coefficient matrix based on the positional relationship between the pressure gauge nodes in the water supply monitoring diagram, wherein the pressure monitoring coefficient matrix is ​​used to amplify abnormal pressure values;

[0144] The monitoring module 704 is used to determine the monitoring pressure data corresponding to each pressure gauge node based on the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix, and determine whether the pressure gauge node corresponding to the monitoring pressure data is abnormal based on the monitoring pressure data.

[0145] Another embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store computer instructions that can be executed on the processor, and the processor is used to determine the abnormal pressure gauge node based on the method described in the first aspect when executing the computer instructions.

[0146] Another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the abnormal pressure gauge node determination method described in the first aspect.

[0147] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0148] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general-purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing this type of system. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0149] In addition, the memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0150] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0151] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0153] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0154] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0155] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0156] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. An abnormal pressure gauge node determination method, which is applied to the urban water supply network. The abnormal pressure determination method for the water supply network includes: Obtain all pressure node groups according to the positions of each pressure gauge node in the water supply network model diagram and the water flow direction of the water supply network. Among them, the pressure node group is composed of two pressure gauge nodes connected by water flow, and the water supply network model diagram is constructed according to the urban water supply network; Respectively obtain the path sets of each pressure node group. When the path set meets the preset conditions, connect the two pressure gauge nodes in the pressure node group corresponding to the path set to construct a water supply monitoring diagram; Determine a pressure monitoring coefficient matrix according to the positional relationship between each pressure gauge node in the water supply monitoring diagram. The pressure monitoring coefficient matrix is used to amplify the abnormal pressure value; According to the pressure data of each pressure gauge node during the acquisition period and the pressure monitoring coefficient matrix, determine the monitored and analyzed pressure data corresponding to each pressure gauge node, and determine whether the pressure gauge node corresponding to the monitored and analyzed pressure data is abnormal according to the monitored and analyzed pressure data.

2. According to the abnormal pressure gauge node determination method described in claim 1, the step of respectively obtaining the path sets of each pressure node group includes: Obtain the node information, pipeline structure and water flow direction of each node in the water supply network model diagram. The nodes include pressure gauge nodes and non-pressure gauge nodes; Construct a directed adjacency matrix corresponding to the water supply network model diagram according to the node information, pipeline structure and water flow direction. The directed adjacency matrix is used to represent the positional relationship between each node; Determine the path set corresponding to the pressure node group according to the directed adjacency matrix.

3. According to the abnormal pressure gauge node determination method described in claim 1, when the path set meets the preset conditions, connecting the two pressure gauge nodes in the pressure node group corresponding to the path set includes: Obtain the nodes of each path in the path set; When the nodes in at least one path do not include the target pressure gauge node, determine that the path set meets the preset conditions, and connect the two pressure gauge nodes in the pressure node group corresponding to the path set. Among them, the target pressure gauge node is the pressure gauge node other than the two pressure gauge nodes in the pressure node group; When the nodes in each path all include the target pressure gauge node, determine that the path set does not meet the preset conditions.

4. According to the abnormal pressure gauge node determination method described in claim 1, the step of determining the pressure monitoring coefficient matrix according to the positional relationship between each pressure gauge node in the water supply monitoring diagram includes: Obtain the positional relationship between each pressure gauge node in the water supply monitoring diagram; Construct an undirected adjacency matrix corresponding to the water supply monitoring diagram according to the positional relationship; Determine the degree matrix corresponding to the water supply monitoring diagram according to the undirected adjacency matrix; Determine the Laplacian matrix according to the undirected adjacency matrix and the degree matrix, and determine the Laplacian matrix as the pressure monitoring coefficient matrix.

5. The abnormal pressure gauge node determination method according to claim 1, wherein determining the monitored and analyzed pressure data corresponding to each pressure gauge node according to the pressure data of each pressure gauge node and the pressure monitoring coefficient matrix within the acquisition period includes: Obtain the pressure data collected by the pressure gauge node within the acquisition period; Determine the monitored and analyzed pressure data according to the product of the pressure data and the pressure monitoring coefficient matrix.

6. The abnormal pressure gauge node determination method according to claim 1, wherein determining whether the pressure gauge node corresponding to the monitored and analyzed pressure data is abnormal according to the monitored and analyzed pressure data includes: Determine a first pressure value and a second pressure value corresponding to the monitored and analyzed pressure data according to a preset statistical algorithm, wherein the first pressure value is less than the second pressure value, and the preset statistical algorithm includes at least one of the following: mean range algorithm, exponentially weighted moving algorithm, and Bollinger Bands algorithm; When the pressure value included in the monitored and analyzed pressure data is greater than the second pressure value, or less than the first pressure value, determine that the pressure gauge node corresponding to the monitored and analyzed pressure data is abnormal; When the pressure value in the monitored and analyzed pressure data is between the first pressure value and the second pressure value, determine that the pressure gauge node corresponding to the monitored and analyzed pressure data is normal.

7. The abnormal pressure gauge node determination method according to claim 1, after determining the monitored and analyzed pressure data corresponding to each pressure gauge node according to the pressure data of each pressure gauge node and the pressure monitoring coefficient matrix within the acquisition period, further includes: Generate target monitored and analyzed pressure data according to the Savitzky-Golay algorithm and the monitored and analyzed pressure data, and determine whether the pressure gauge node corresponding to the target monitored and analyzed pressure data is abnormal according to the target monitored and analyzed pressure data.

8. An abnormal pressure gauge node determination device applied to an urban water supply network, the abnormal pressure gauge node determination device includes: An acquisition module, configured to obtain all pressure node groups according to the positions of each pressure gauge node in the water supply network model diagram and the water flow direction of the water network, wherein the pressure node group is composed of two pressure gauge nodes connected by water flow, and the water supply network model diagram is constructed according to the urban water supply network; A construction module, configured to respectively obtain the path sets of each pressure node group, When the path sets respectively obtained for each pressure node group meet the preset conditions, connect the two pressure gauge nodes in the pressure node group corresponding to the path set to construct a water supply monitoring diagram; A determination module, configured to determine a pressure monitoring coefficient matrix according to the positional relationship between each pressure gauge node in the water supply monitoring diagram, and the pressure monitoring coefficient matrix is used to amplify abnormal pressure values; The monitoring module is used to determine the monitored and analyzed pressure data corresponding to each of the pressure gauge nodes according to the pressure data of each of the pressure gauge nodes within the acquisition period and the pressure monitoring coefficient matrix, and determine whether the pressure gauge nodes corresponding to the monitored and analyzed pressure data are abnormal according to the monitored and analyzed pressure data.

9. An electronic device, the electronic device includes a memory and a processor, the memory is used to store computer instructions that can be run on the processor, and the processor is used to determine the abnormal pressure gauge node determination method according to any one of claims 1 to 7 when executing the computer instructions.

10. A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the abnormal pressure gauge node determination method according to any one of claims 1 to 7.

Images