Water supply network leakage position identification method and storage medium

Abstract

The invention discloses a water supply network leakage position identification method and a storage medium. The method comprises the steps of monitoring pressure flow data of different positions of a water supply network in real time; using lattice Boltzmann to solve a right-end residual term of the pressure flow relation equation in parallel as a real-time monitoring residual term; determining the leakage position of the water supply network corresponding to the real-time monitoring residual item according to a pre-constructed mapping relation between the leakage position and the residual item; according to the method, the pressure and flow relation equation is solved in parallel through lattice Boltzmann, the equation solving efficiency is remarkably improved, meanwhile, the mapping relation between the leakage position and the residual term is established, the complex process of feature extraction is avoided, and the pipe network leakage position is rapidly and accurately recognized.

Description

Technical Field

[0001] The present invention relates to the technical field of fire water supply network fault monitoring and diagnosis, and in particular to a method for identifying a leakage position of a water supply network and a storage medium. Background Art

[0002] The water supply network plays a vital role in the fire water supply system: first, it is an important part of the fire protection system, responsible for transporting water to various fire extinguishing points to provide the necessary water source for extinguishing the fire. Secondly, the water supply network needs to maintain a high enough pressure to support the fire fighting work at the fire scene. Once the water supply network leaks, it will not be able to provide enough water to extinguish the fire in time, and the fire will spread rapidly, resulting in property losses and casualties. It is very important to quickly and accurately identify the leaking location of the water supply network.

[0003] Flow and pressure sensors are often arranged in water supply networks to monitor the operation status of the networks. There are significant differences in the distribution of pressure and flow data at different locations in the water supply network under normal working conditions (no leakage) and leakage conditions, as well as for different leakage locations. Therefore, the changes in water supply pressure and flow in the network are the main forms of leakage signal detection in the water supply network.

[0004] In the related technology, the master's thesis "Research on Leakage Detection and Location Methods of Ship Pipeline Networks, Feng Kai" describes a real-time model method: construct an accurate real-time model of the pipeline accurately calculated by a computer and execute it synchronously with the actual pipeline. By taking the pressure and flow values ​​at regular intervals and comparing them with the values ​​calculated by the theoretical model, the location of the leak can be determined. This method is too dependent on the accuracy of the initial model and software, but its mechanism for locating the leak is still based on the pressure gradient method, so it has great limitations.

[0005] Therefore, how to quickly and accurately identify the leakage location of the water supply network by monitoring the changes in pressure and flow data at different locations of the water supply network is a problem that needs to be solved urgently. Summary of the invention

[0006] The technical problem to be solved by the present invention is how to quickly and accurately identify the leakage position of a water supply network.

[0007] The present invention solves the above technical problems by the following technical means:

[0008] The present invention proposes a method for identifying a leakage position of a water supply network, the method comprising:

[0009] Real-time monitoring of pressure and flow data at different locations of the water supply network;

[0010] The residual term on the right side of the pressure-flow relationship equation is solved in parallel using the lattice Boltzmann method as the real-time monitoring residual term;

[0011] According to the pre-constructed mapping relationship between the leakage position and the residual term, the leakage position of the water supply network corresponding to the real-time monitoring residual term is determined.

[0012] Furthermore, the process of constructing the mapping relationship between the leakage position and the residual term includes:

[0013] Obtain pressure and flow data at different locations of the water supply network under normal working conditions, and use the lattice Boltzmann method to solve the right-hand side residual term of the pressure-flow relationship equation under normal working conditions in parallel as the residual term under normal working conditions;

[0014] Set a set number of leakage locations and collect pressure and flow data at different locations of the water supply network under different leakage locations;

[0015] For each leakage location, the residual term on the right side of the pressure-flow relationship equation under the leakage condition is solved in parallel using the lattice Boltzmann method as the residual term under the leakage condition;

[0016] According to all leakage locations and the residual items under the corresponding leakage conditions, a mapping relationship between different leakage locations and residual items is established to form a leakage location-residual item mapping relationship comparison table, including leakage locations, residual items and pressure and flow data at different locations of the water supply network under the working condition.

[0017] Furthermore, the leakage positions are arranged evenly or unevenly.

[0018] Furthermore, the residual term on the right side of the pressure-flow relationship equation solved in parallel using the lattice Boltzmann method is

[0019]

[0020] In the formula, δ is the residual term on the right side, φ is the pressure, and f is the fluid velocity. f=∑ i c i h i / ∑ i h i , c i is the model discrete velocity, h i is the discrete distribution function, i is the discrete velocity index, is the gradient operator.

[0021] Furthermore, the pressure-flow relationship equation is:

[0022]

[0023] The lattice Boltzmann method is used to solve the pressure-flow relationship equation in parallel, including the collision step, migration step and statistical pressure-flow data. The collision step formula is expressed as:

[0024]

[0025] The migration step formula is expressed as:

[0026]

[0027] The statistical pressure data and flow data are:

[0028]

[0029] In the formula, is the discrete distribution function after collision, h i (x, t) is the discrete distribution function at position x and time t, Ω i (h) is the collision operator, x is the position index, and t is the time index.

[0030] Furthermore, after determining the water supply network leakage position corresponding to the real-time monitoring residual term according to the pre-constructed mapping relationship between the leakage position and the residual term, the method further includes:

[0031] Calculate the non-local cosine similarity between the pressure and flow data of different locations of the real-time monitoring water supply network and the pressure and flow data under historical leakage conditions;

[0032] When the non-local cosine similarity is greater than a set similarity threshold, it is determined that the identified pipe network leakage location is correct;

[0033] When the non-local cosine similarity is less than or equal to a set similarity threshold, it is determined that the identified pipe network leakage position is wrong.

[0034] Furthermore, the calculation formula of the non-local cosine similarity is:

[0035]

[0036] Where cosα Φ is the non-local cosine similarity of pressure data, Φ is the pressure vector monitored at the current moment, Φ 0 is the pressure vector under historical leakage conditions.

[0037] Similarly, the calculation formula for the non-local cosine similarity of traffic data is:

[0038]

[0039] Where cosα F is the non-local cosine similarity of traffic data, F is the traffic data monitored at the current moment, and F 0 It is the flow data under historical leakage conditions.

[0040] Furthermore, the calculation of the non-local cosine similarity between the pressure flow data of different locations of the real-time monitoring water supply network and the pressure flow data under the historical leakage conditions includes:

[0041] According to the vector length n, the first non-local cosine similarity between the pressure and flow data of different locations of the real-time monitoring water supply network and the pressure and flow data under the historical leakage condition is calculated;

[0042] Determining whether the first non-local cosine similarity is within a set range;

[0043] If yes, then compare the non-local cosine similarity with the similarity threshold to determine whether the pipeline network leakage location identification result is accurate;

[0044] Otherwise, the vector length is reset to 2n, and the second non-local cosine similarity between the pressure and flow data of different locations of the real-time monitoring water supply network and the pressure and flow data under historical leakage conditions is calculated.

[0045] Further, after calculating the second non-local cosine similarity, the method further includes:

[0046] The difference between the second non-local cosine similarity and the first non-local cosine similarity is calculated, and the first non-local cosine similarity is output when the difference is within a set range; otherwise, the second non-local cosine similarity is output for comparison with a similarity threshold.

[0047] In addition, the present invention also proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for identifying a leakage position of a water supply network as described above is implemented.

[0048] The advantages of the present invention are:

[0049] (1) The present invention preliminarily uses the lattice Boltzmann parallel method to solve the pressure-flow relationship equation to obtain a mapping relationship between the leakage position and the residual term of the equation. When monitoring the leakage position of the water supply network, the pressure and flow data of different positions of the water supply network are monitored in real time. The residual term on the right side of the pressure-flow relationship equation is solved by the lattice Boltzmann parallel method as the real-time monitoring residual term. The pre-constructed mapping relationship is used to identify the leakage position of the network corresponding to the real-time monitoring residual term. By using the lattice Boltzmann parallel method to solve the pressure and flow relationship equation, the efficiency of solving the equation is significantly improved. At the same time, by establishing a mapping relationship between the leakage position and the residual term, the complex process of feature extraction is avoided, and the leakage position of the network is quickly and accurately identified.

[0050] (2) Based on the established mapping relationship between the leakage location and the residual term, the accuracy of the leakage location of the water supply network is further determined by comparing the pressure and flow data using the non-local cosine similarity. This reduces the number of data comparison samples and improves the accuracy of calculating the leakage location of the water supply network.

[0051] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart of a method for identifying a leakage position of a water supply network proposed in one embodiment of the present invention;

[0053] Figure 2 is a schematic diagram of the arrangement positions of pressure and flow sensors in one embodiment of the present invention;

[0054] Figure 3 is a graph showing a change trend of pressure data at different leakage locations in one embodiment of the present invention;

[0055] Figure 4 This is a graph showing the changing trend of flow data at different leakage locations in one embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying a leakage position of a water supply network, the method comprising the following steps:

[0058] S10, real-time monitoring of pressure and flow data at different locations of the water supply network;

[0059] It should be noted that, in this embodiment, pressure data and flow data at different positions of the pipeline network can be measured by means of pressure sensors and flow sensors arranged at different positions of the pipeline network.

[0060] S20, using the lattice Boltzmann parallel solution to solve the right-hand side residual term of the pressure-flow relationship equation as the real-time monitoring residual term;

[0061] S30. Determine the leakage position of the water supply network corresponding to the real-time monitoring residual item according to the pre-constructed mapping relationship between the leakage position and the residual item.

[0062] It should be noted that the pressure / flow coupling relationship equation is a nonlinear partial differential equation. If the traditional method is used to solve it, the differential equation needs to be discretized, and then the large-scale linear equations after discretization need to be solved iteratively. The amount of calculation is huge and the solution time is long. As a mesoscopic method, Lattice Boltzmann does not need to discretize macroscopic equations. It performs collision and migration through the distribution function of "fluid particles" to restore the macroscopic flow behavior of the fluid. Since it does not involve the solution of complex linear equations, LBM is easy to implement, and local operations are very suitable for large-scale parallel computing. Using Lattice Boltzmann to solve the pressure / flow relationship equation in parallel significantly improves the efficiency of equation solution. At the same time, by establishing a mapping relationship between the leakage location and the residual term, the complex process of feature extraction is avoided, and the leakage location of the pipeline network can be quickly and accurately identified.

[0063] As a further preferred technical solution, in step S30, the process of constructing the mapping relationship between the leakage position and the residual term includes the following steps:

[0064] Obtain pressure and flow data at different locations of the water supply network under normal working conditions, and use the lattice Boltzmann method to solve the right-hand side residual term of the pressure-flow relationship equation under normal working conditions in parallel as the residual term under normal working conditions;

[0065] Set a set number of leakage locations and collect pressure and flow data at different locations of the water supply network under different leakage locations;

[0066] For each leakage location, the residual term on the right side of the pressure-flow relationship equation under the leakage condition is solved in parallel using the lattice Boltzmann method as the residual term under the leakage condition;

[0067] According to all leakage locations and the residual items under the corresponding leakage conditions, a mapping relationship between different leakage locations and residual items is established to form a leakage location-residual item mapping relationship comparison table, including leakage locations, residual items and pressure and flow data at different locations of the water supply network under the working condition.

[0068] Specifically, this embodiment sets up a water supply network including 2 water tanks, 2 water pumps, 6 fire hydrants, 10 valves and 26 pipes. First, the pressure / flow data at different positions of the water supply network under normal working conditions are obtained. Then, several groups of leakage positions are set as needed. The setting of leakage positions is very flexible and can be evenly distributed or unevenly distributed. The pressure / flow data at different positions of the water supply network under different leakage positions are collected. Only one group of leakage positions is set for each test. The layout positions of pressure / flow sensors are as follows: Figure 2 As shown in the figure, the pressure data change trends and flow data change trends at different leakage locations are shown in Figure 3 and Figure 4 .

[0069] In this example, the pipeline is 400 meters long and a total of 20 sets of leakage positions are set evenly. In the first test, leakage hole 1 is opened and the other leakage holes are closed. The pressure / flow data at different positions of the water supply network under different leakage positions are collected and entered into the database for storage, as shown in Table 1.

[0070] Table 1 Storage pressure / flow data

[0071]

[0072] In the calculation process, it is inevitable to introduce truncation errors, rounding errors, etc. In order to correct the right-hand residual term under leakage conditions, the pressure and flow data at different locations of the water supply network under normal conditions are obtained, and the lattice Boltzmann method is used to solve the right-hand residual term of the pressure-flow relationship equation under normal conditions in parallel as the residual term under normal conditions. This residual term is used to correct the residual term under leakage conditions. Therefore, for each group of leakage locations, the lattice Boltzmann method is used to solve the pressure / flow relationship equation in parallel, and the residual term on the right side of the equation is calculated to establish a mapping relationship between different leakage locations and residual terms, as shown in Table 2.

[0073] Table 2 Leakage points and residual items

[0074]

[0075] The pressure / flow data at different locations of the water supply network are monitored in real time by the arranged pressure / flow sensors. The pressure / flow relationship equation is solved in parallel using the lattice Boltzmann method to calculate the residual term on the right side of the pressure / flow relationship equation at the current moment, as shown in Table 3.

[0076] Table 3 Current pressure / flow and right-hand residual term

[0077]

[0078] According to the mapping relationship between leakage position and residual term, different leakage positions lead to different pressure / flow distributions. Therefore, the residual term of the pressure / flow equation is generally different. The leakage position can be preliminarily determined by comparing the residual term value with the residual terms of different leakage positions.

[0079] Furthermore, water is an incompressible fluid, and the pressure / flow of the water supply network satisfies the following equation:

[0080]

[0081] In the formula, φ is the pressure (MPa), f is the fluid velocity (m / s), and the flow rate can be obtained by integrating the fluid velocity along the cross-sectional area. The pressure / flow relationship equation is solved in parallel using the lattice Boltzmann method. The steps are as follows:

[0082] (1) Collision step:

[0083]

[0084] (2) Migration step:

[0085]

[0086] (3) Statistical pressure / flow:

[0087]

[0088] It should be noted that using the lattice Boltzmann method to solve the pressure / flow relationship equation is a local operation and is very suitable for parallel computing.

[0089] Furthermore, due to the existence of measurement errors and calculation errors, the right-hand side term of the pressure / flow relationship equation is generally not 0, and the residual term on the right-hand side of the equation needs to be calculated. The calculation formula is as follows:

[0090]

[0091] In the formula, c i is the model discrete velocity, h i is the discrete distribution function, i is the discrete velocity index, is the gradient operator, is the discrete distribution function after collision, h i (x, t) is the discrete distribution function at position x and time t, Ω i (h) is the collision operator, x is the position index, and t is the time index.

[0092] The following is part of the calculation code for solving the pressure / flow relationship equation using the lattice Boltzmann method:

[0093] (1) Collision step:

[0094] void COLL(void){

[0095] int X;

[0096] int Y;

[0097] int I;

[0098] #pragma omp parallel for private(Y,I)num_threads(16)

[0099] for(X=0;X<=GRIX;X++){

[0100] for(Y=0;Y<=GRIY;Y++){

[0101] for (I = 0; I < 9; I++) {

[0102] FUN1[X][Y][I] = (1.0 - 1.0 / TIME) * FUN0[X][Y][I] + 1.0 / TIME * EQUI(I, DENS[X][Y], VELX[X][Y], VELY[X][Y]);

[0103] }

[0104] }

[0105] }

[0106] }

[0107] (2) Migration step:

[0108] void STRE(void) {

[0109] int X;

[0110] int Y;

[0111] int I;

[0112] #pragma omp parallel for private(Y, I) num_threads(16)

[0113] for (X = 0; X <= GRIX; X++) {

[0114] for (Y = 0; Y <= GRIY; Y++) {

[0115] for (I = 0; I < 9; I++) {

[0116] if (X - INT1[I] >= 0 && X - INT1[I] <= GRIX && Y - INT2[I] >= 0 && Y - INT2[I] <= GRIY) {

[0117] FUN0[X][Y][I] = FUN1[X - INT1[I]][Y - INT2[I]][I];

[0118] }

[0119] }

[0120] }

[0121] }

[0122] }

[0123] (3) Calculate pressure / flow rate:

[0124] void PHYS(void){

[0125] int X;

[0126] int Y;

[0127] int I;

[0128] #pragma omp parallel for private(Y,I)num_threads(16)

[0129] for(X=0;X<=GRIX;X++){

[0130] for(Y=0;Y<=GRIY;Y++){

[0131] DENS[X][Y]=0.0;

[0132] VELX[X][Y]=0.0;

[0133] VELY[X][Y]=0.0;

[0134] for(I=0;I<9;I++){

[0135] DENS[X][Y]+=FUN0[X][Y][I];

[0136] VELX[X][Y]+=INT1[I]*FUN0[X][Y][I];

[0137] VELY[X][Y]+=INT2[I]*FUN0[X][Y][I];

[0138] }

[0139] VELX[X][Y] / =DENS[X][Y];

[0140] VELY[X][Y] / =DENS[X][Y];

[0141] }

[0142] }

[0143] }

[0144] Furthermore, since different leakage locations correspond to the same or very similar residual items, in order to avoid misjudgment of the leakage location, this embodiment locates the leakage location based on the mapping relationship between the leakage location and the residual item, and at the same time combines the non-local cosine similarity to compare the pressure / flow data, thereby further improving the accuracy of calculating the leakage location of the water supply network.

[0145] Accordingly, after the step S30: determining the water supply network leakage position corresponding to the real-time monitoring residual term according to the pre-constructed mapping relationship between the leakage position and the residual term, the method further comprises the following steps:

[0146] S31, calculating the non-local cosine similarity between the pressure and flow data of different locations of the real-time monitoring water supply network and the pressure and flow data under historical leakage conditions;

[0147] S32, when the non-local cosine similarity is greater than a set similarity threshold, determining that the identified pipe network leakage location is correct;

[0148] S33: When the non-local cosine similarity is less than or equal to a set similarity threshold, determine that the identified pipe network leakage location is wrong.

[0149] Specifically, it is assumed that the real-time monitoring pressure vector at the current moment is:

[0150] Φ=(φ -n ,φ -n+1 …,φ -1 ,φ o ,φ1…,φ n-1 ,φ n )

[0151] Where φ0 is the pressure value at the node where the leakage location is initially determined.

[0152] Assuming that the leak location is the preliminary leak location, according to the leak test, the historical pressure vector under the leak condition is

[0153]

[0154] Calculate the non-local cosine similarity of the pressure vectors:

[0155]

[0156] Where cosα Φ is the non-local cosine similarity of pressure data, Φ is the pressure vector monitored at the current moment, Φ 0 is the pressure vector under historical leakage conditions.

[0157] Similarly, the calculation formula for the non-local cosine similarity of traffic data is:

[0158]

[0159] Where cosα F is the non-local cosine similarity of traffic data, F is the traffic data monitored at the current moment, and F 0 It is the flow data under historical leakage conditions.

[0160] Furthermore, if and only if cosα Φ ≥0.9 and cosα F ≥0.9, it is judged that the pipeline network leakage location is correctly identified. Otherwise, it is considered that the pressure flow data under this working condition does not match, and the pipeline network leakage location is incorrectly identified. The leakage location should be reselected for identification.

[0161] As a further preferred technical solution, the step S31: calculating the non-local cosine similarity between the pressure flow data of different locations of the real-time monitoring water supply network and the pressure flow data under historical leakage conditions, specifically includes the following steps:

[0162] S311, according to the vector length n (N / 4≤n≤N / 2), N is the number of pressure flow data, calculate the first non-local cosine similarity between the pressure flow data of different locations of the real-time monitoring water supply network and the pressure flow data under historical leakage conditions;

[0163] S312, determining whether the first non-local cosine similarity is within a set range, if so, executing step S313, otherwise executing step S314;

[0164] S313, comparing the non-local cosine similarity with the similarity threshold to determine whether the pipeline network leakage location identification result is accurate;

[0165] S314. Reset the vector length to 2n, and calculate the second non-local cosine similarity between the pressure flow data of different locations of the real-time monitoring water supply network and the pressure flow data under historical leakage conditions.

[0166] As a further preferred technical solution, after step S314, the method further includes:

[0167] The difference between the second non-local cosine similarity and the first non-local cosine similarity is calculated, and the first non-local cosine similarity is output when the difference is within a set range; otherwise, the second non-local cosine similarity is output for comparison with a similarity threshold.

[0168] It should be noted that the non-local cosine similarity calculation method proposed in this embodiment is different from the traditional method. The traditional method only calculates the cosine similarity once and then determines the similarity of the two vectors. The innovation of this method is that the determination of the vector length n is very flexible. At the beginning, a smaller n is selected to calculate the cosα of the two vectors. If cosα is too high or too low, it means that the vector length may be too short. Then the vector length 2n is reset and the cosα of the two vectors is calculated again. If the cosα calculated twice does not change much, the cosα calculated for the first time is output. It is considered that the vector length has no significant effect on the similarity and the calculation is stopped. Otherwise, the cosα calculated for the second time shall prevail.

[0169] In addition, another embodiment of the present invention further proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for identifying the leakage location of a water supply network as described in the above embodiment is implemented.

[0170] It should be noted that other embodiments of the computer-readable storage medium of the present invention or implementation methods thereof can refer to the above-mentioned method embodiments and will not be described in detail here.

[0171] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0172] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0173] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0174] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0175] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for identifying leakage locations in a water supply network. It is characterized in that The method comprises: Real-time monitoring of pressure and flow data at different locations of the water supply network; The residual term on the right side of the pressure-flow relationship equation is solved in parallel using the lattice Boltzmann method as the real-time monitoring residual term; According to the pre-constructed mapping relationship between the leakage position and the residual term, the leakage position of the water supply network corresponding to the real-time monitoring residual term is determined.

2. The method for identifying a leakage position of a water supply network according to claim 1, It is characterized in that The process of constructing the mapping relationship between the leakage position and the residual term includes: Obtain pressure and flow data at different locations of the water supply network under normal working conditions, and use the lattice Boltzmann method to solve the right-hand side residual term of the pressure-flow relationship equation under normal working conditions in parallel as the residual term under normal working conditions; Set a set number of leakage locations and collect pressure and flow data at different locations of the water supply network under different leakage locations; For each leakage location, the residual term on the right side of the pressure-flow relationship equation under the leakage condition is solved in parallel using the lattice Boltzmann method as the residual term under the leakage condition; According to all leakage locations and the residual items under corresponding leakage conditions, a mapping relationship between different leakage locations and residual items is established.

3. The method for identifying a leakage position of a water supply network according to claim 2, It is characterized in that The leakage positions are arranged evenly or unevenly.

4. The method for identifying a leakage position of a water supply network according to claim 1, It is characterized in that The residual term on the right side of the pressure-flow relationship equation solved in parallel using the lattice Boltzmann method is In the formula, δ is the residual term on the right side, φ is the pressure, and f is the fluid velocity. f=∑ i c i h i / ∑ i h i , c i is the model discrete velocity, h i is the discrete distribution function, i is the discrete velocity index, is the gradient operator.

5. The method for identifying a leakage position of a water supply network according to claim 4, It is characterized in that The pressure-flow relationship equation is: The lattice Boltzmann method is used to solve the pressure-flow relationship equation in parallel, including the collision step, migration step and statistical pressure-flow data. The collision step formula is expressed as: The migration step formula is expressed as: The statistical pressure data and flow data are: In the formula, is the discrete distribution function after collision, h i (x, t) is the discrete distribution function at position x and time t, Ω i (h) is the collision operator, x is the position index, and t is the time index.

6. The method for identifying a leakage position of a water supply network according to claim 1, It is characterized in that After determining the water supply network leakage position corresponding to the real-time monitoring residual item according to the pre-constructed mapping relationship between the leakage position and the residual item, the method further includes: Calculate the non-local cosine similarity between the pressure and flow data of different locations of the real-time monitoring water supply network and the pressure and flow data under historical leakage conditions; When the non-local cosine similarity is greater than a set similarity threshold, it is determined that the identified pipe network leakage location is correct; When the non-local cosine similarity is less than or equal to a set similarity threshold, it is determined that the identified pipe network leakage position is wrong.

7. The method for identifying a leakage position of a water supply network according to claim 6, It is characterized in that The calculation formula of the non-local cosine similarity is: Where cosα Φ is the non-local cosine similarity of pressure data, Φ is the pressure vector monitored at the current moment, Φ 0 is the pressure vector under the historical leakage condition; The calculation formula of non-local cosine similarity of traffic data is: Where cosα F is the non-local cosine similarity of traffic data, F is the traffic data monitored at the current moment, and F 0 It is the flow data under historical leakage conditions.

8. The method for identifying a leakage position of a water supply network according to claim 6, It is characterized in that The method of calculating the non-local cosine similarity between the pressure flow data of different locations of the real-time monitoring water supply network and the pressure flow data under historical leakage conditions includes: According to the vector length n, the first non-local cosine similarity between the pressure and flow data of different locations of the real-time monitoring water supply network and the pressure and flow data under the historical leakage condition is calculated; Determining whether the first non-local cosine similarity is within a set range; If yes, then compare the non-local cosine similarity with the similarity threshold to determine whether the pipeline network leakage location identification result is accurate; Otherwise, the vector length is reset to 2n, and the second non-local cosine similarity between the pressure and flow data of different locations of the real-time monitoring water supply network and the pressure and flow data under historical leakage conditions is calculated.

9. The method for identifying a leakage position of a water supply network according to claim 8, It is characterized in that After calculating the second non-local cosine similarity, the method further includes: The difference between the second non-local cosine similarity and the first non-local cosine similarity is calculated, and the first non-local cosine similarity is output when the difference is within a set range; otherwise, the second non-local cosine similarity is output for comparison with a similarity threshold.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for identifying a leakage location in a water supply network as described in any one of claims 1 to 9 is implemented.

Images