A water supply pipe network pipe burst positioning method, device, equipment and storage medium

Abstract

The present application relates to the technical field of municipal engineering, and in particular to a water supply pipe network pipe burst positioning method, device, equipment and storage medium. The water supply pipe network pipe burst positioning method provided by the present application determines the time when the pipe burst pressure wave reaches each monitoring point through high-frequency pressure monitoring data, and based on the time and the propagation time of the transient flow pressure wave, the possible pipe burst position is first circled, and then based on the transient flow model, the transient flow pressure data at each monitoring point is simulated and calculated, and then by considering the continuous change information of the pressure wave, the simulated transient pressure data and the high-frequency monitoring data are matched, so that the pipe burst position is accurately positioned from the possible pipe burst position. Therefore, the problem that the positioning result is easily affected by the wave velocity estimation error caused by the pipe burst position positioning based only on the time difference of the transient pressure wave reaching each monitoring point in the related art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of municipal engineering, and in particular to a water supply pipe network pipe burst positioning method, device, equipment and storage medium. BACKGROUND

[0002] In a water supply system, a water supply pipe network bears the important responsibility of delivering treated water to thousands of households, and is an important link to realize water supply safety guarantee. The pipe burst event will affect the water supply capacity and water quality safety of the water supply pipe network. Therefore, it is particularly important to discover and locate the pipe burst event in the water supply pipe network as soon as possible.

[0003] With the development of high-frequency pressure monitoring equipment, it is possible to perform high-frequency pressure monitoring in the water supply pipe network at a lower cost. Compared with the traditional monitoring equipment, the high-frequency pressure monitoring equipment can capture the instantaneous pressure change in the pipe network, which is beneficial to more timely and accurate positioning of the pipe burst event in the pipe network. However, the current water supply pipe network pipe burst positioning method based on high-frequency pressure monitoring data is simply based on the time difference of the transient pressure wave caused by the pipe burst reaching each monitoring point, which makes the positioning result easily affected by the wave velocity estimation error. SUMMARY

[0004] Therefore, the present application provides a water supply pipe network pipe burst positioning method, device, equipment and storage medium to solve the problem that the existing pipe burst positioning method is easily affected by the wave velocity estimation error.

[0005] In a first aspect, the present application provides a water supply pipe network pipe burst positioning method, which comprises: acquiring high-frequency pressure monitoring data of each monitoring point in the water supply pipe network, the high-frequency pressure monitoring data comprising pressure values and monitoring times corresponding to each pressure value; determining, based on the high-frequency pressure monitoring data, the time of arrival of the pipe burst pressure wave at each monitoring point using the cumulative sum algorithm; determining the possible pipe burst location based on the relationship between the transient flow pressure wave propagation time between any two nodes in the water supply pipe network and each time; matching the new steady-state pressure monitoring data obtained after the pipe burst with the pressure estimation data corresponding to different pipe burst coefficients determined based on the steady-state model, to determine the pipe burst coefficient of the possible pipe burst location; based on the transient flow model, simulating and calculating the transient flow pressure data of the pipe burst at each possible pipe burst location using the pipe burst coefficient, and matching the transient flow pressure data with the high-frequency pressure monitoring data to determine the pipe burst location.

[0006] The water supply pipe network pipe burst positioning method provided by the embodiment of the application determines the time when the pipe burst pressure wave reaches each monitoring point through high-frequency pressure monitoring data, first circumscribes the possible pipe burst position based on the time and the propagation time of the transient flow pressure wave, then simulates and calculates the transient flow pressure data at each monitoring point based on the transient flow model, and finally matches the simulated transient pressure data and the high-frequency monitoring data by considering the continuous change of the pressure wave, so as to realize accurate positioning of the pipe burst position from the possible pipe burst position. Thus, the problem that the positioning result is easily affected by the wave velocity estimation error caused by the positioning of the pipe burst position only based on the time difference of the arrival of the transient pressure wave at each monitoring point in the related art is solved.

[0007] In an optional embodiment, based on the high-frequency pressure monitoring data, the cumulative sum algorithm is used to determine the time when the pipe burst pressure wave reaches each monitoring point, including: based on the high-frequency pressure monitoring data, the cumulative sum algorithm is used to calculate the time when the pressure change accumulation is greater than a threshold value, and the pressure change accumulation greater than the threshold value is determined as the occurrence of the pipe burst pressure wave; and based on the time when the pressure change accumulation starts recorded in the cumulative sum algorithm, the time when the pipe burst pressure wave reaches each monitoring point is determined.

[0008] In the embodiment, the cumulative sum algorithm is used to determine the time when the pipe burst pressure wave occurs, which provides a data basis for determining the possible pipe burst position.

[0009] In an optional embodiment, before determining the possible pipe burst position based on the relationship between the transient flow pressure wave propagation time and the time of any two nodes in the water supply pipe network, the method further includes: based on the topological structure of the water supply pipe network, determining the nodes of the water supply pipe network and the pipes between the nodes; and based on the length of the pipe between the two nodes and the transient flow wave velocity of the pipe, calculating the transient flow pressure wave propagation time in any pipe.

[0010] In an optional embodiment, the possible pipe burst position is determined based on the relationship between the transient flow pressure wave propagation time and the time of any two nodes in the water supply pipe network, including: based on the transient flow pressure wave propagation time in any pipe of the water supply pipe network, the shortest path algorithm is used to determine the shortest time of the pressure wave propagation between any two nodes; and based on the minimum value of the difference between the time difference of the arrival of the pipe burst pressure wave at any two monitoring points and the difference between the shortest time of the pressure wave propagation of any node to the corresponding two monitoring points, a target function is determined, and the possible pipe burst position is determined by solving the target function.

[0011] In an optional embodiment, the target function is expressed by the following formula:

[0012]

[0013] In the formula, k represents any node of the water supply pipe network, M represents a set of monitoring points, t i represents the time when the pipe burst pressure wave reaches the monitoring point i, and tj represents the time when the burst pipe pressure wave reaches the monitoring point j, T ik represents the shortest time for the transient flow pressure wave to propagate between the monitoring point i and the node k, T jk represents the shortest time for the transient flow pressure wave to propagate between the monitoring point j and the node k.

[0014] In this embodiment, based on the transient flow pressure wave generated when the burst pipe occurs, the possible burst pipe position is determined according to the propagation time of the transient flow pressure wave and the time when the burst pipe pressure wave reaches each monitoring point, and the burst pipe position is preliminarily screened.

[0015] In an alternative embodiment, the new steady-state pressure monitoring data obtained after the burst pipe and the pressure estimation data corresponding to different burst pipe coefficients determined based on the steady-state model are matched to determine the burst pipe coefficient of the possible burst pipe position, including: obtaining new steady-state pressure monitoring data of each monitoring point after the burst pipe occurs; calculating pressure estimation data of the possible burst pipe position under different burst pipe coefficients based on the pre-constructed steady-state model of the water supply network; determining a target function based on the difference between the new steady-state pressure monitoring data and the pressure estimation data, solving the target function using a genetic algorithm, and determining the burst pipe coefficient of each possible burst pipe position.

[0016] In this embodiment, the steady-state model is used to calculate the pressure estimation data of the possible burst pipe position under different burst pipe coefficients, and the burst pipe coefficient of each possible burst pipe position is determined based on the relationship between the pressure estimation data and the pressure monitoring data, thereby providing a data basis for subsequent analysis of the transient flow model.

[0017] In an alternative embodiment, based on the transient flow model, the transient flow pressure data of the burst pipe at each possible burst pipe position is simulated and calculated using the burst pipe coefficient, and the transient flow pressure data and the high-frequency pressure monitoring data are matched to determine the burst pipe position, including: based on the transient flow model, the transient flow pressure data of the burst pipe at each possible burst pipe position is simulated and calculated using the burst pipe coefficient; the transient flow pressure data and the high-frequency pressure monitoring data of each monitoring point are matched using a dynamic time warping algorithm, and the burst pipe position is determined according to the matching result.

[0018] In this embodiment, the transient flow model is used to calculate the pressure data of each monitoring point corresponding to the burst pipe coefficient of the possible burst pipe position, and the continuous transformation information of the pressure wave is utilized; when the dynamic time warping algorithm is used for matching, the points in one sequence can be matched with other time points in another sequence, and the influence of shape stretching or compression can be excluded.

[0019] In a second aspect, the present application provides a water supply network pipe burst positioning device, which comprises: a data acquisition module, configured to acquire high-frequency pressure monitoring data of each monitoring point in the water supply network, the high-frequency pressure monitoring data comprising pressure values and monitoring times corresponding to the pressure values; a pipe burst monitoring module, configured to determine, based on the pressure monitoring data, times at which a pipe burst pressure wave reaches each monitoring point by using a cumulative sum algorithm; a preliminary positioning module, configured to determine a possible pipe burst position based on a relationship between a transient flow pressure wave propagation time between any two nodes in the water supply network and the times; a pipe burst coefficient determination module, configured to match new steady-state pressure monitoring data acquired after a pipe burst with pressure estimation data corresponding to different pipe burst coefficients determined based on a steady-state model, and determine a pipe burst coefficient of the possible pipe burst position; and a positioning module, configured to simulate and calculate transient flow pressure data of pipe bursts at each possible pipe burst position based on a transient flow model and the pipe burst coefficient, match the transient flow pressure data with the high-frequency pressure monitoring data, and determine the pipe burst position.

[0020] In a third aspect, the present application provides a computer device, which comprises a memory and a processor, the memory and the processor are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the water supply network pipe burst positioning method of the first aspect or any of the corresponding embodiments thereof.

[0021] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the water supply network pipe burst positioning method of the first aspect or any of the corresponding embodiments thereof.

[0022] In a fifth aspect, the present application provides a computer program product, which comprises computer instructions, and the computer instructions are used to make a computer execute the water supply network pipe burst positioning method of the first aspect or any of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed in the specific embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0024] Figure 1 is a flowchart of the water supply network pipe burst positioning method according to an embodiment of the present application;

[0025] Figure 2 is a schematic diagram of a water supply network pipe burst position according to an embodiment of the present application;

[0026] Figure 3is a water supply network pipe explosion positioning diagram according to an embodiment of the present application;

[0027] Figure 4 is a structural diagram of a water supply network pipe explosion positioning device according to an embodiment of the present application;

[0028] Figure 5 is a hardware structure diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0030] According to an embodiment of the present application, a water supply network pipe explosion positioning method embodiment is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0031] In the present embodiment, a water supply network pipe explosion positioning method is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 1 is a flowchart of a water supply network pipe explosion positioning method according to an embodiment of the present application, as shown in Figure 1 The flowchart includes the following steps:

[0032] In step S101, pressure monitoring data of each monitoring point in the water supply network is obtained, and the pressure monitoring data includes pressure values and monitoring times corresponding to the pressure values. Specifically, the number and position of the monitoring points can be determined according to the topological structure of the water supply network, and the actual situation such as cost can also be considered when setting the monitoring points, so as to determine the final monitoring points. After the monitoring points are determined, high-frequency pressure sensors can be set at the monitoring points for pressure monitoring, and high-frequency pressure monitoring data can be obtained. When pressure monitoring is performed, high-frequency pressure monitoring data can be collected based on a pre-set sampling frequency, so that the high-frequency pressure monitoring data includes the pressure values collected by the high-frequency pressure sensors and the collection times corresponding to the pressure values.

[0033] Step S102, based on the high-frequency pressure monitoring data, the cumulative sum algorithm is used to determine the time when the burst pipe pressure wave reaches each monitoring point. Specifically, when the water supply pipeline bursts, a pressure wave will be generated and propagate in the pipe network, so it can be determined whether a burst pipe occurs and the burst pipe time by processing and calculating the high-frequency pressure monitoring data. In this embodiment, the cumulative sum algorithm is used to process the pressure monitoring data, which quickly identifies when the system deviates from the normal operating state, i.e. a burst pipe occurs, by calculating the cumulative deviation of the pressure monitoring data stream, and determines the time when the burst pipe pressure wave reaches each monitoring point according to the time when the deviation starts to accumulate.

[0034] Step S103, based on the relationship between the transient flow pressure wave propagation time between any two nodes in the water supply network and the time, the possible burst pipe location is determined. Among them, the nodes in the water supply network can be determined based on the topological structure of the water supply network and the graph theory algorithm. For example, the graph theory algorithm can be used to abstract the water supply network as a weighted graph. The vertex in the weighted graph represents the node in the pipe network. The edge in the weighted graph represents the pipeline in the pipe network, connecting two nodes, which is an undirected edge, and its weight is the propagation time of the transient flow pressure wave in the pipeline corresponding to the edge.

[0035] Specifically, when a burst pipe event occurs, a transient flow pressure wave appears in the pipeline, and the propagation time of the transient flow pressure wave between any two nodes can be determined in advance according to the wave speed of the transient flow pressure wave. Thus, the possible burst pipe location can be circled according to the propagation time and the time when the burst pipe pressure wave reaches each monitoring point. In addition, it should be noted that when determining the monitoring point, it should be determined from the nodes of the water supply network, i.e. first determine the nodes of the water supply network, and then select part of the nodes as the monitoring points.

[0036] Step S104, match the new steady-state pressure monitoring data obtained after the burst pipe with the pressure estimation data corresponding to different burst pipe coefficients determined based on the steady-state model, to determine the burst pipe coefficient of the possible burst pipe location. Specifically, after the burst pipe occurs, the pressure fluctuation will dissipate within tens of seconds and reach a new steady state. Therefore, after the burst pipe is monitored, the new steady-state pressure monitoring data of each monitoring point can be obtained. At the same time, for each possible burst pipe location, the steady-state model and the burst pipe coefficient can also be used to calculate the pressure estimation data of each monitoring point; then the relationship between the new steady-state pressure monitoring data and the pressure estimation data is used to determine the burst pipe coefficient corresponding to the possible burst pipe location.

[0037] Step S105, based on the transient flow model, simulating the transient flow pressure data of each possible pipe burst position, matching the transient flow pressure data and the high-frequency pressure monitoring data to determine the pipe burst position. Specifically, after determining the pipe burst coefficient of the possible pipe burst position, the pipe burst coefficient can be substituted into the transient flow model to calculate the transient flow pressure data of the corresponding monitoring point when the pipe burst occurs at the possible pipe burst position. The calculated transient flow pressure data and the high-frequency pressure monitoring data are matched, and the pipe burst position is accurately positioned from the possible pipe burst position according to the matching result.

[0038] The pipe burst positioning method for water supply network provided by the embodiment of the present application determines the time when the pipe burst pressure wave reaches each monitoring point through high-frequency pressure monitoring data, and first circumscribes the possible pipe burst position based on the time and the propagation time of the transient flow pressure wave. Then, based on the transient flow model, the transient flow pressure data at each monitoring point is simulated, and the simulated transient pressure data and the high-frequency monitoring data are matched by considering the continuous change of the pressure wave, so as to accurately position the pipe burst position from the possible pipe burst position. Thus, the problem that the positioning result is easily affected by the wave velocity estimation error in the related art is solved.

[0039] In the embodiment, a pipe burst positioning method for water supply network is provided, and the flow includes the following steps:

[0040] Step S201, acquiring high-frequency pressure monitoring data of each monitoring point in the water supply network, and the high-frequency pressure monitoring data includes pressure values and monitoring times corresponding to the pressure values. For details, please refer to Figure 1 The step S101 of the embodiment shown in the figure will not be described here.

[0041] Step S202, based on the pressure monitoring data, using the cumulative sum algorithm to determine the time when the pipe burst pressure wave reaches each monitoring point.

[0042] Specifically, the above step S202 includes:

[0043] Step S2021, using the cumulative sum algorithm to calculate the time when the pressure change accumulation is greater than a threshold based on the high-frequency pressure monitoring data. If the pressure change accumulation is greater than the threshold, it is determined that the pipe burst pressure wave occurs. Specifically, for any monitoring point, the monitored pressure change is H(t), and in this embodiment, the high-frequency pressure monitoring data is collected through a certain sampling frequency. Therefore, the collected high-frequency pressure monitoring data is a discrete data sequence, which can be expressed as:

[0044] H n =H(nΔt)

[0045] In the formula, Δt represents the time step, that is, the reciprocal of the sampling frequency, and n represents the nth time step.

[0046] The pressure change amount of the nth time step is:

[0047] ΔH n = H n - H n-1

[0048] The cumulative sum (CUSUM) algorithm is used to iteratively calculate A n , B n and S n in the following manner:

[0049] A0= B0= 0

[0050] A n = max(A n-1 - ΔH n - v, 0)

[0051]

[0052] where v is the drift parameter of the CUSUM algorithm. B n is the cumulative sum of the CUSUM algorithm; S n is the time step at which the cumulative sum starts to accumulate. The cumulative sum starts to accumulate and reflects the start of the change in pressure of the system. If B n is greater than the threshold value K, a pressure drop warning is issued, indicating that the cumulative pressure change amount is greater than the threshold value at this time, and it is considered that a pipe burst pressure wave may have occurred, and S n is recorded, i.e. the time step at which the cumulative pressure change amount starts to accumulate is recorded.

[0053] Step S2022, according to the time at which the cumulative pressure change amount starts to accumulate recorded in the cumulative sum algorithm, determine the times at which the pipe burst pressure wave reaches the monitoring points. Specifically, the time at which the pipe burst pressure wave reaches the monitoring points is S n Δt. Wherein, for each monitoring point, S n determined by the above step S2021 can be used respectively, and further according to S n Δt, the time at which the pipe burst pressure wave reaches the monitoring point is obtained.

[0054] Step S203, based on the topology of the water supply network, determine the nodes and the pipes between the nodes of the water supply network; based on the length of the pipe between two nodes and the transient flow wave speed of the pipe, calculate the propagation time of the transient flow pressure wave in any pipe. Specifically, through the graph algorithm, the set of all nodes of the water supply network can be denoted as V, and the set of all pipes can be denoted as E, then the pipe network can be denoted as G(V, E). The adjacency matrix of the graph G can be denoted as A, and the elements of the adjacency matrix are:

[0055]

[0056] where τ ij represents the pipe weight, which can be calculated as follows:

[0057]

[0058] where L ij is the length of the pipe between node i and node j, and a ij is the transient flow wave speed between node i and node j. The physical meaning of the pipe weight τ ij is the time for the transient flow pressure wave to pass through the pipe between node i and node j.

[0059] Step S204, determining the possible pipe burst location based on the relationship between the transient flow pressure wave propagation time between any two nodes in the water supply network and each time.

[0060] Specifically, the above step S204 includes:

[0061] Step S2041, using the shortest path algorithm to determine the shortest time for the pressure wave to propagate between any two nodes in the water supply network based on the transient flow pressure wave propagation time in any pipe in the water supply network; specifically, using the shortest path algorithm such as the Dijkstra algorithm on the above matrix A to determine the shortest time T ij needed for the transient flow pressure wave to propagate between any point i and another point j in the water supply network. Wherein the way of determining the shortest time and the shortest path using the Dijkstra algorithm is similar, when the weight between nodes is time rather than distance, one node can be taken as the starting point and the other node as the end point, thereby obtaining the shortest time needed for the starting point to the end point.

[0062] Step S2042, determining the objective function based on the minimum value of the difference between the time difference of the pressure wave caused by the pipe burst reaching any two monitoring points and the difference between the shortest time of the pressure wave propagating from any node to the corresponding two monitoring points, and solving the objective function to determine the possible pipe burst location. In this embodiment, the set of monitoring points is denoted as M, and if the pipe burst occurs at the kth node in the network, theoretically, there are:

[0063]

[0064] where t i and t j are the times when the pressure wave caused by the pipe burst propagates to the monitoring points i and j. The formula indicates that the difference between the propagation time of the pipe burst pressure wave between the burst location and any two monitoring points and the propagation time of the transient flow pressure wave is theoretically 0. However, in actual situations, due to monitoring errors and other factors, even if the pipe burst occurs at k, S kis not equal to 0. Therefore, the minimization can be taken as the objective function, and the possible pipe burst location can be determined by solving the objective function.

[0065] Specifically, the objective function is expressed by the following formula:

[0066]

[0067] In the formula, k represents any node of the water supply network, M represents a set of monitoring points, t i represents the time when the pipe burst pressure wave reaches the monitoring point i, t j represents the time when the pipe burst pressure wave reaches the monitoring point j, T ik represents the shortest time for the transient flow pressure wave to propagate between the monitoring point i and the node k, T jk represents the shortest time for the transient flow pressure wave to propagate between the monitoring point j and the node k.

[0068] Wherein, when solving the objective function, the exhaustive method can be used to obtain the optimal solution and several suboptimal solutions as possible pipe burst locations. The set of these possible pipe burst locations is denoted as Y.

[0069] Step S205, matching the new steady-state pressure monitoring data obtained after the pipe burst with the pressure estimation data corresponding to different pipe burst coefficients determined based on the steady-state model, to determine the pipe burst coefficient of the possible pipe burst location.

[0070] Specifically, the above step S205 includes:

[0071] Step S2051, obtaining new steady-state pressure monitoring data of each monitoring point after the pipe burst; Specifically, when the pipe burst occurs, the pressure fluctuation will dissipate within tens of seconds and reach a new steady state. Therefore, after the pipe burst is monitored, the new steady-state pressure monitoring data of each monitoring point can be reacquired by using a high-frequency pressure sensor. The steady-state water head monitoring value obtained in the embodiment is H i,obs as the new steady-state pressure monitoring data.

[0072] Step S2052, calculating pressure estimation data of the possible pipe burst location under different pipe burst coefficients based on the pre-constructed steady-state model of the water supply network; Specifically, the steady-state model of the water supply network can be constructed by using the EPANET software, such as constructing the model of the water supply network first, and then setting the boundary conditions to configure the model, thereby obtaining the steady-state model. After obtaining the steady-state model, the steady-state analysis can be performed by using the steady-state model, such as calculating the new steady-state water head estimation value H k of each monitoring point i after the pipe burst occurs at the possible pipe burst location k with the pipe burst coefficient such as the orifice outflow coefficient c k >0). i,cal (k,c k) as pressure estimation data, wherein the burst pipe coefficient c k The size of the burst pipe coefficient c

[0073] At step S2053, a target function is determined based on the difference between the new steady-state pressure monitoring data and the pressure estimation data, and a genetic algorithm is used to solve the target function to determine the burst pipe coefficient for each possible burst pipe location. Specifically, for each possible burst pipe location, the pressure estimation data corresponding to different burst pipe coefficients and the new steady-state pressure monitoring data can be respectively calculated by difference, and when the difference is the smallest, the corresponding burst pipe coefficient is the burst pipe coefficient corresponding to the possible burst pipe location. Thus, for each possible burst pipe location, the corresponding burst pipe coefficient can be determined by using the following target function:

[0074]

[0075] For this target function, a genetic algorithm can be used for solving, and the specific solving manner can be implemented by referring to related technologies, which will not be described here.

[0076] At step S206, based on the transient flow model, the transient flow pressure data of the burst pipe occurring at each possible burst pipe location is simulated and calculated by using the burst pipe coefficient, and the transient flow pressure data and the high-frequency pressure monitoring data are matched to determine the burst pipe location.

[0077] Specifically, the above step S206 includes:

[0078] At step S2061, based on the transient flow model, the transient flow pressure data of the burst pipe occurring at each possible burst pipe location is simulated and calculated by using the burst pipe coefficient. The transient flow model can be used to simulate the transient change of water flow pressure in the water supply pipe network. For example, the TSNet software can be used to construct the transient flow model of the water supply pipe network. When constructing, the topological model of the water supply pipe network can be constructed first, and then the transient conditions and solver parameters are set, and thus the transient flow model is obtained. For the constructed transient flow model, transient flow simulation can be performed, such as calculating and displaying the dynamic parameters of the water supply pipe network changing with time, such as pressure and flow rate. In this embodiment, the burst pipe coefficient c k The size of the burst pipe is used as the transient condition of the transient flow model simulation, so that the transient flow model is used to calculate the pressure change time series h k (k) of each monitoring point, i.e., the transient flow pressure data, when the burst pipe with the size c i,cal occurs at the possible burst pipe location k.

[0079] In step S2063, the transient flow pressure data and the high-frequency pressure monitoring data of each monitoring point are matched by using a dynamic time warping algorithm, and the burst pipe position is determined according to the matching result. The dynamic time warping (DTW) algorithm is an algorithm for measuring the similarity between two sequences, and can process time sequence data of different lengths. When the DTW algorithm is used, unlike the Euclidean distance, the points in one sequence are allowed to correspond to the points at other time points in another sequence to exclude the influence of shape stretching or compression. Therefore, the pressure data of each monitoring point and the new pressure monitoring data are matched by using the dynamic time warping algorithm, which can be expressed by the following formula:

[0080]

[0081] Therefore, by using the DTW algorithm, the pressure change time sequence and the steady-state water head monitoring value of each possible burst pipe position are calculated by the above formula, and the distance between the two is calculated. i,obs The distance is the minimum distance, and the possible burst pipe position corresponding to the minimum distance is taken as the final positioning of the burst pipe position.

[0082] Compared with the burst pipe positioning method using conventional monitoring data, the burst pipe positioning method provided by the embodiment of the application uses high-frequency pressure monitoring data, has better timeliness and positioning effect. The application not only uses the pressure wave arrival time for burst pipe positioning, but also couples the transient flow model of the pipe network to utilize the continuous change information of the pressure wave, thereby improving the accuracy of the burst pipe positioning.

[0083] As a specific application embodiment of the embodiment of the application, the burst pipe positioning and monitoring of the water supply pipe network shown in FIGS. Figure 2 and Figure 3 are taken as examples for description. For the water supply pipe network, the nodes are first determined, and high-frequency pressure monitoring data is collected at the positions of the nodes J57, J100, J151, J193 and J365, and the sampling frequency is 250 Hz. If a related technology such as only using the pressure wave arrival time for positioning is used, the result is that the burst pipe occurs at the node J147. Other possible burst pipe positions are sorted in descending order of possibility as follows: J158, J429, J124, J144, …… If the method provided by the embodiment of the application is used, the information of the continuous change of the pressure wave is analyzed, and the burst pipe can be accurately positioned at the node J124.

[0084] A water supply network pipe burst positioning device is also provided in the present embodiment, which is used to implement the above embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated.

[0085] The present embodiment provides a water supply network pipe burst positioning device, as shown in Figure 4 comprises:

[0086] A data acquisition module 41 is configured to acquire high-frequency pressure monitoring data of each monitoring point in the water supply network, the high-frequency pressure monitoring data including pressure values and monitoring times corresponding to the pressure values.

[0087] A pipe burst monitoring module 42 is configured to determine, based on the high-frequency pressure monitoring data, times at which a pipe burst pressure wave reaches each monitoring point using a cumulative sum algorithm.

[0088] A preliminary positioning module 43 is configured to determine a possible pipe burst location based on a relationship between transient flow pressure wave propagation times between any two nodes in the water supply network and the times.

[0089] A pipe burst coefficient determination module 44 is configured to determine a pipe burst coefficient of the possible pipe burst location by matching new steady-state pressure monitoring data acquired after the pipe burst and pressure estimation data corresponding to different pipe burst coefficients determined based on a steady-state model.

[0090] A positioning module 45 is configured to simulate and calculate transient flow pressure data of pipe bursts at each possible pipe burst location using the pipe burst coefficient based on a transient flow model, and determine a pipe burst location by matching the transient flow pressure data and the high-frequency pressure monitoring data.

[0091] In an alternative embodiment, the pipe burst monitoring module is specifically configured to calculate, based on the high-frequency pressure monitoring data, times at which a pressure change amount accumulation is greater than a threshold value using a cumulative sum algorithm, and determine that a pipe burst pressure wave occurs when the pressure change amount accumulation is greater than the threshold value; and determine the times at which the pipe burst pressure wave reaches each monitoring point according to times at which a pressure change amount starts to accumulate recorded in the cumulative sum algorithm.

[0092] In an alternative embodiment, the device further comprises a time calculation module configured to determine nodes of the water supply network and pipes between the nodes based on a topology of the water supply network; and calculate transient flow pressure wave propagation times in any pipe based on lengths of the pipes between the nodes and transient flow wave velocities of the pipes.

[0093] In an alternative embodiment, the preliminary determination module is specifically configured to: determine the shortest time for pressure wave propagation between any two nodes based on the propagation time of transient flow pressure wave in any pipe of the water supply network by using a shortest path algorithm; determine the objective function based on the minimum value of the difference between the time difference of the arrival of the pressure wave at any two monitoring points and the difference between the shortest time of pressure wave propagation from any node to the corresponding two monitoring points; and solve the objective function to determine the possible pipe burst location.

[0094] In an alternative embodiment, the objective function is expressed by the following formula:

[0095]

[0096] In the formula, k represents any node of the water supply network, M represents a set of monitoring points, t i represents the time of arrival of the pressure wave at monitoring point i, t j represents the time of arrival of the pressure wave at monitoring point j, T ik represents the shortest time of transient flow pressure wave propagation between monitoring point i and node k, T jk represents the shortest time of transient flow pressure wave propagation between monitoring point j and node k.

[0097] In an alternative embodiment, the pipe burst coefficient determination module is specifically configured to: obtain new steady-state pressure monitoring data of each monitoring point after the pipe burst; calculate pressure estimation data of the possible pipe burst location under different pipe burst coefficients based on the pre-constructed steady-state model of the water supply network; determine the objective function based on the difference between the new steady-state pressure monitoring data and the pressure estimation data, solve the objective function by using a genetic algorithm, and determine the pipe burst coefficient of each possible pipe burst location.

[0098] In an alternative embodiment, the positioning module is specifically configured to: simulate and calculate the transient flow pressure data of the pipe burst at each possible pipe burst location by using the pipe burst coefficient based on the transient flow model; match the transient flow pressure data and the high-frequency pressure monitoring data of each monitoring point by using a dynamic time warping algorithm, and determine the pipe burst location according to the matching result.

[0099] Further function descriptions of the above modules are the same as those of the corresponding embodiments, and will not be described here again.

[0100] The embodiments of the present application also provide a computer device having the above-mentioned Figure 4 water supply network pipe burst positioning device.

[0101] Please refer to Figure 5 , Figure 5 is a structural schematic diagram of a computer device provided by an alternative embodiment of the present application, as Figure 5As shown, the computer device includes one or more processors 10, memory 20, and interfaces 30 for the various components to communicate with one another. The various components communicate through the use of an interconnection network 100. Although not shown, various components could be connected to the interconnection network 100 through a peripheral component interconnect (PCI) bridge, PCI express (PCIe) bridge 101, or uses any of several available technologies. Figure 5 The processor 10 is, for example, a central processing unit (CPU), a network processing unit, or a combination thereof.

[0102] The processor 10 can be a central processing unit, a network processing unit, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a general array logic, or any combination thereof.

[0103] The memory 20 stores instructions that can be executed by the at least one processor 10, so that the at least one processor 10 performs the method shown in the above embodiments.

[0104] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system, application programs required by at least one function, and the like. The data storage area can store data created according to the use of the computer device, and the like. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some alternative embodiments, the memory 20 can optionally include a memory that is remotely arranged with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0105] The memory 20 can include a volatile memory, such as a random access memory, and can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid state disk. The memory 20 can further include a combination of the above-mentioned kinds of memories.

[0106] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0107] The embodiments of the present application further provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded to a local storage medium through network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0108] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, the method and / or technical solutions according to the present application can be invoked or provided. Those skilled in the art should understand that the form of computer program instructions in a computer readable medium includes but is not limited to source files, executable files, installation package files, etc. Correspondingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0109] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A method for locating a burst pipe in a water supply network, characterized in that: The method comprises: Obtaining high-frequency pressure monitoring data of each monitoring point in the water supply network, wherein the high-frequency pressure monitoring data includes pressure values ​​and monitoring times corresponding to each pressure value; Based on the high-frequency pressure monitoring data, a cumulative sum algorithm is used to determine the time when the burst pressure wave reaches each monitoring point; Determine the possible burst location based on the relationship between the transient flow pressure wave propagation time and the above-mentioned time between any two nodes in the water supply network; Match the new steady-state pressure monitoring data obtained after the pipe burst with the pressure estimation data corresponding to different pipe burst coefficients determined based on the steady-state model to determine the pipe burst coefficient at the possible pipe burst location; Based on the transient flow model, using the pipe burst coefficient, simulate and calculate the transient flow pressure data of each possible pipe burst location, match the transient flow pressure data with the high-frequency pressure monitoring data, and determine the pipe burst location; Based on the high-frequency pressure monitoring data, a cumulative sum algorithm is used to determine the time when the burst pressure wave reaches each monitoring point, including: A cumulative sum algorithm is used to calculate the time when the cumulative pressure change is greater than a threshold value based on the high-frequency pressure monitoring data. If the cumulative pressure change is greater than the threshold value, it is determined that a pipe burst pressure wave has occurred; Determine the time when the burst pressure wave reaches each monitoring point based on the time when the pressure change recorded in the cumulative sum algorithm begins to accumulate; Determining the possible burst location based on the relationship between the transient flow pressure wave propagation time and each time between any two nodes in the water supply network includes: The shortest path algorithm is used to determine the shortest time for pressure wave propagation between any two nodes based on the propagation time of transient flow pressure waves in any pipe of the water supply network. The objective function is determined based on the minimum value of the difference between the time when the burst pressure wave reaches any two monitoring points and the difference between the shortest pressure wave propagation time from any node to the corresponding two monitoring points, and the possible burst position is determined by solving the objective function.

2. The method according to claim 1, characterized in that Before determining the possible pipe burst location based on the relationship between the transient flow pressure wave propagation time between any two nodes in the water supply network and the respective moments, the method further includes: Based on the topological structure of the water supply network, determine the nodes of the water supply network and the pipes between the nodes; The propagation time of transient flow pressure waves in any pipe is calculated based on the length of the pipe between two nodes and the transient flow wave velocity of the pipe.

3. The method according to claim 1, characterized in that The objective function is expressed by the following formula: Where k represents any node in the water supply network, M represents the set of monitoring points, and t i represents the time when the burst pressure wave reaches the monitoring point i, t j represents the time when the burst pressure wave reaches the monitoring point j, T ik represents the shortest time for transient flow pressure wave propagation between monitoring point i and node k, T jk It represents the shortest time for transient flow pressure wave to propagate between monitoring point j and node k.

4. The method according to claim 1, wherein Match the new steady-state pressure monitoring data obtained after the pipe burst with the pressure estimation data corresponding to different pipe burst coefficients determined based on the steady-state model to determine the pipe burst coefficient at the possible pipe burst location, including: Obtain new steady-state pressure monitoring data for each monitoring point after a pipe burst occurs; Calculate pressure estimates at possible burst locations based on a pre-built steady-state model of the water supply network under different burst coefficients; An objective function is determined based on the difference between the new steady-state pressure monitoring data and the pressure estimation data, and a genetic algorithm is used to solve the objective function to determine a pipe burst coefficient for each possible pipe burst position.

5. The method according to claim 1, wherein Based on the transient flow model and using the pipe burst coefficient, transient flow pressure data of pipe bursts at each possible pipe burst location are simulated and calculated, and the transient flow pressure data are matched with the high-frequency pressure monitoring data to determine the pipe burst location, including: Based on the transient flow model and using the pipe burst coefficient, the transient flow pressure data of pipe burst at each possible pipe burst position is simulated and calculated; A dynamic time warping algorithm is used to match the transient flow pressure data of each monitoring point with the high-frequency pressure monitoring data, and the burst position is determined based on the matching result.

6. A burst pipe locating device for a water supply network, characterized in that: The device comprises: A data acquisition module is used to obtain high-frequency pressure monitoring data of each monitoring point in the water supply network, wherein the high-frequency pressure monitoring data includes pressure values ​​and monitoring times corresponding to each pressure value; a pipe burst monitoring module, configured to determine the time when the pipe burst pressure wave reaches each monitoring point using a cumulative sum algorithm based on the high-frequency pressure monitoring data; A preliminary positioning module is used to determine the possible burst location based on the relationship between the transient flow pressure wave propagation time and the said moments between any two nodes in the water supply network; The burst coefficient determination module is used to match the new steady-state pressure monitoring data obtained after the burst with the pressure estimation data corresponding to different burst coefficients determined based on the steady-state model to determine the burst coefficient of the possible burst location; a positioning module for simulating and calculating transient flow pressure data of pipe bursts at each possible pipe burst location based on a transient flow model and using the pipe burst coefficient, matching the transient flow pressure data with the high-frequency pressure monitoring data to determine the pipe burst location; Based on the high-frequency pressure monitoring data, a cumulative sum algorithm is used to determine the time when the burst pressure wave reaches each monitoring point, including: A cumulative sum algorithm is used to calculate the time when the cumulative pressure change is greater than a threshold value based on the high-frequency pressure monitoring data. If the cumulative pressure change is greater than the threshold value, it is determined that a pipe burst pressure wave has occurred; Determine the time when the burst pressure wave reaches each monitoring point based on the time when the pressure change recorded in the cumulative sum algorithm begins to accumulate; Determining the possible burst location based on the relationship between the transient flow pressure wave propagation time and each time between any two nodes in the water supply network includes: The shortest path algorithm is used to determine the shortest time for pressure wave propagation between any two nodes based on the propagation time of transient flow pressure waves in any pipe of the water supply network. The objective function is determined based on the minimum value of the difference between the time when the burst pressure wave reaches any two monitoring points and the difference between the shortest pressure wave propagation time from any node to the corresponding two monitoring points, and the possible burst position is determined by solving the objective function.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the water supply network burst pipe locating method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the water supply network pipe burst locating method according to any one of claims 1 to 5.

Images