CN118332745B

CN118332745B - Water supply network repairing method and device, electronic equipment and computer storage medium

Info

Publication number: CN118332745B
Application number: CN202410756276.6A
Authority: CN
Inventors: 申屠华斌; 魏俊; 郑亨; 于海兰
Original assignee: PowerChina Huadong Engineering Corp Ltd
Current assignee: PowerChina Huadong Engineering Corp Ltd
Priority date: 2024-06-13
Filing date: 2024-06-13
Publication date: 2024-09-03
Anticipated expiration: 2044-06-13
Also published as: CN118332745A

Abstract

The invention provides a water supply network repairing method, a device, electronic equipment and a computer storage medium, and relates to the technical field of municipal water supply pipelines. Wherein the method comprises the following steps: constructing a topological structure model of a water supply network; checking and updating the model based on the operation data; determining an adjustment scheme of a water supply network; the first objective function and the second objective function are solved together, and an initial population is determined in an adjustment scheme; coding the initial population, and then calculating pipe network adjustment and fitness to obtain fitness; wherein the fitness calculation function is constrained based on the third objective function and the fourth objective function; continuing non-dominant sorting and crowding calculation to obtain a new parent population; iteratively updating the new parent population; until a water supply network restoration scheme is obtained; and the repair scheme is optimized and determined based on the multi-objective function, the running state and the maintenance cost of the water supply network are comprehensively considered through multi-objective function constraint, and the user experience is improved.

Description

Water supply network repairing method and device, electronic equipment and computer storage medium

Technical Field

The invention relates to the technical field of municipal water supply pipelines, in particular to a water supply network repairing method, a device, electronic equipment and a computer storage medium.

Background

Urban water supply network is an important underground infrastructure of cities, is a material foundation for survival and development of society, is called as a life line of cities, and plays an irreplaceable role in the whole fields of economy, culture, life and the like.

Aiming at the water supply network system, the complete optimization process comprises three stages of planning, designing, operating, maintaining and managing. In the operation and maintenance stage, pain points such as pipeline breakage, insufficient pipeline pressure, pipe bursting and the like exist. The most important and difficult part in the maintenance and repair work of the water supply system is the repair of the water supply network. At present, the repair of a water supply network is always a main research difficulty in the water supply field, and in view of the characteristics and operation characteristics of the water supply system, maintenance and repair are necessary and long-term tasks of the water supply system. Meanwhile, water supply network repair is a complex problem, and various aspects are required to be paid attention to in the solving process. This is a discrete variable, nonlinear, multi-objective optimization problem.

At present, in the maintenance stage of the water supply network, most of the maintenance stage is to optimize and determine a repair scheme aiming at a single target, the running state and the maintenance cost of the water supply network cannot be comprehensively considered, and the user experience is poor.

Disclosure of Invention

Accordingly, the present invention aims to provide a water supply network repairing method, a device, an electronic apparatus and a computer storage medium, which are capable of improving user experience by obtaining an adjustment scheme of a water supply network, optimizing the adjustment scheme based on multiple objective functions, and finally determining the water supply network repairing scheme, and comprehensively considering the operation state and maintenance cost of the water supply network through the constraint of the multiple objective functions.

In a first aspect, the present invention provides a water supply network repair method, including: basic parameters of a water supply network are obtained, and a topological structure model of the water supply network is constructed based on the basic parameters; checking and updating the water supply network topological structure model based on the operation data of the water supply network; determining an adjustment scheme of the water supply network based on daily maintenance information and simulated operation condition data of the water supply network; respectively carrying the adjustment scheme into a first objective function taking the corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function taking a reasonable range of the water supply network node pressure as the constraint target, and solving to obtain a plurality of first objective function values and a plurality of second objective function values; sequencing the first objective function value and the second objective function value from small to large, selecting a first objective function value with a preset proportion at the front, taking an adjustment scheme corresponding to the selected first objective function value as a first objective adjustment scheme, selecting a second objective function value with a preset proportion at the front, taking an adjustment scheme corresponding to the selected second objective function value as a second objective adjustment scheme, and combining the first objective adjustment scheme and the second objective adjustment scheme as an initial population; coding the initial population based on a preset pipe diameter code; sequentially carrying out pipe network adjustment and fitness calculation on chromosomes in the encoded initial population to obtain fitness; the function of the fitness calculation is constrained based on a third objective function taking the annual repair cost minimization in the investment period as a constraint target and a fourth objective function taking the pipe network reliability performance evaluation as a constraint target; non-dominant sorting and crowding calculation are carried out on chromosomes with fitness meeting a preset fitness threshold value, so that a new father population is obtained; iteratively updating the new parent population; and taking the new father population meeting the preset iteration times as a water supply network restoration scheme.

In some preferred embodiments of the present invention, the step of iteratively updating the new parent population comprises: carrying out genetic processing on the new parent population to obtain a child population; wherein the genetic manipulation comprises at least one of: selection, crossover and mutation; determining a new population based on the new parent population and the offspring population processed by the elite retention strategy; performing non-dominant ranking and crowding calculation on the new population; the new parent population is updated based on the results of the number of layers and congestion level calculations for the non-dominant ranking.

In some preferred embodiments of the present invention, the step of adjusting the pipe network includes: calculating the closing difference of pipe network nodes of the water supply network based on the pipe network data of the water supply network and preset calculation precision; the pipe network data comprise node water pressure; if the closing difference meets the preset precision, determining the node water pressure as the node target water pressure; and if the closing difference does not meet the preset precision, adjusting the node water pressure based on the jacobian matrix of the node water pressure until the closing difference meets the preset precision.

In some preferred embodiments of the present invention, fitness calculations are performed by the following formula: ; wherein F (k) is an fitness function, For the first weight to be given,For the second weighting, W _x is the third objective function, W _xmin is the minimum of the third objective function, W _xmax is the maximum of the third objective function, W _y is the fourth objective function, W _ymin is the minimum of the fourth objective function, and W _ymax is the maximum of the fourth objective function.

In some preferred embodiments of the present invention, the step of non-dominant ordering comprises: defining a dominant count and a dominant solution set for each solution; all solutions are performed, and a first non-inferior layer is determined; the tiers are updated based on the dominant count and the solutions of the dominant until one tier is empty.

In some preferred embodiments of the present invention, the congestion level calculation is performed based on the following formula: ; wherein i _distance is the crowding distance of the individual in the non-dominant ranking, r is the number of objective functions, As a fitness function of the (i+1) th individual on the (j) th target,Is the fitness function of the i-1 th individual on the j-th target.

In a second aspect, the present invention provides a water supply network repair device, comprising: the model construction module is used for acquiring basic parameters of the water supply network and constructing a topological structure model of the water supply network based on the basic parameters; the model updating module is used for checking and updating the topological structure model of the water supply network based on the operation data of the water supply network; the adjusting scheme processing module is used for determining an adjusting scheme of the water supply network based on daily maintenance information and simulated operation condition data of the water supply network; the initial population processing module is used for respectively bringing the adjustment schemes into a first objective function taking the corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function taking a reasonable range of the water supply network node pressure as the constraint target for solving, so as to obtain a plurality of first objective function values and a plurality of second objective function values, sequencing the first objective function values and the second objective function values from small to large, selecting a first objective function value which is in front of a preset proportion, taking the adjustment scheme which corresponds to the selected first objective function value as a first objective adjustment scheme, selecting a second objective function value which is in front of the preset proportion, taking the adjustment scheme which corresponds to the selected second objective function value as a second objective adjustment scheme, and combining the first objective adjustment scheme and the second objective adjustment scheme as an initial population; the population coding module is used for coding the initial population based on a preset pipe diameter code; the fitness calculation module is used for sequentially calculating the pipe network adjustment and the fitness of the chromosomes in the encoded initial population to obtain fitness; the function of the fitness calculation is constrained based on a third objective function taking the annual repair cost minimization in the investment period as a constraint target and a fourth objective function taking the pipe network reliability performance evaluation as a constraint target; the new father population processing module is used for carrying out non-dominant sorting and crowding calculation on chromosomes with fitness meeting a preset fitness threshold value to obtain a new father population; the new father population updating module is used for iteratively updating the new father population; the water supply network restoration scheme determining module is used for taking the new parent population meeting the preset iteration times as a water supply network restoration scheme.

In some preferred embodiments of the present invention, a new parent population update module is configured to perform genetic processing on a new parent population to obtain a child population; wherein the genetic manipulation comprises at least one of: selection, crossover and mutation; determining a new population based on the new parent population and the offspring population processed by the elite retention strategy; performing non-dominant ranking and crowding calculation on the new population; the new parent population is updated based on the results of the number of layers and congestion level calculations for the non-dominant ranking.

In a third aspect, the present invention provides an electronic device comprising a processor and a memory, the memory storing computer executable instructions executable by the processor, the processor executing the computer executable instructions to implement any one of the above methods of water supply network repair.

In a fourth aspect, the present invention provides a computer storage medium having stored thereon computer executable instructions that, when invoked and executed by a processor, cause the processor to implement a water supply network repair method according to any one of the preceding claims.

The invention has the following beneficial effects:

The invention provides a water supply network restoration method, a device, electronic equipment and a computer storage medium, wherein the method comprises the following steps: basic parameters of a water supply network are obtained, and a topological structure model of the water supply network is constructed based on the basic parameters; checking and updating the water supply network topological structure model based on the operation data of the water supply network; determining an adjustment scheme of the water supply network based on daily maintenance information and simulated operation condition data of the water supply network; respectively carrying the adjustment scheme into a first objective function taking the corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function taking a reasonable range of the water supply network node pressure as the constraint target, and solving to obtain a plurality of first objective function values and a plurality of second objective function values; sequencing the first objective function value and the second objective function value from small to large, selecting a first objective function value with a preset proportion at the front, taking an adjustment scheme corresponding to the selected first objective function value as a first objective adjustment scheme, selecting a second objective function value with a preset proportion at the front, taking an adjustment scheme corresponding to the selected second objective function value as a second objective adjustment scheme, and combining the first objective adjustment scheme and the second objective adjustment scheme as an initial population; coding the initial population based on a preset pipe diameter code; sequentially carrying out pipe network adjustment and fitness calculation on chromosomes in the encoded initial population to obtain fitness; the function of the fitness calculation is constrained based on a third objective function taking the annual repair cost minimization in the investment period as a constraint target and a fourth objective function taking the pipe network reliability performance evaluation as a constraint target; non-dominant sorting and crowding calculation are carried out on chromosomes with fitness meeting a preset fitness threshold value, so that a new father population is obtained; iteratively updating the new parent population; taking a new father population meeting the preset iteration times as a water supply network restoration scheme; the water supply network repairing scheme is finally determined by acquiring the adjusting scheme of the water supply network and optimizing the adjusting scheme based on the multiple objective functions, and the running state and the maintenance cost of the water supply network are comprehensively considered through the constraint of the multiple objective functions, so that the user experience is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a water supply network restoration method provided by an embodiment of the invention;

FIG. 2 is a flowchart of adjustment calculation according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a non-dominant ranking calculation according to an embodiment of the present invention;

Fig. 4 is a schematic diagram of congestion degree calculation according to an embodiment of the present invention;

FIG. 5 is a flowchart of a cluster iteration method according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a cross operation according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a variation operation according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a water supply network according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of pipe network adjustment analysis according to an embodiment of the present invention;

FIG. 10 is a schematic flow distribution diagram of each pipe section in the B region according to an embodiment of the present invention;

FIG. 11 is a schematic diagram of head loss distribution of each pipe segment in zone B according to an embodiment of the present invention;

FIG. 12 is a schematic diagram of flow velocity distribution of each pipe section in zone B according to an embodiment of the present invention;

FIG. 13 is a schematic view of a water supply network repairing device according to an embodiment of the present invention;

fig. 14 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Icon: 310-a model building module; 320-a model update module; 330-an adjustment scheme processing module; 340-an initial population processing module; 350-a population encoding module; 360-an fitness calculation module; 370-new parent population processing module; 380-new parent population update module; 390-water supply network repair scheme determination module; 400-memory; 401-a processor; 402-bus; 403-communication interface.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.

In the description of the present invention, it should be noted that, directions or positional relationships indicated by terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., are directions or positional relationships based on those shown in the drawings, or are directions or positional relationships conventionally put in use of the inventive product, are merely for convenience of describing the present invention and simplifying the description, and are not indicative or implying that the apparatus or element to be referred to must have a specific direction, be constructed and operated in a specific direction, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance.

Furthermore, the terms "horizontal," "vertical," "overhang," and the like do not denote a requirement that the component be absolutely horizontal or overhang, but rather may be slightly inclined. As "horizontal" merely means that its direction is more horizontal than "vertical", and does not mean that the structure must be perfectly horizontal, but may be slightly inclined.

In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.

Urban water supply network is an important underground infrastructure of cities, is a material foundation for survival and development of society, is called as a life line of cities, and plays an irreplaceable role in the whole fields of economy, culture, life and the like. Aiming at the water supply network system, the complete optimization process comprises three stages of planning, designing, operating, maintaining and managing. The water supply network optimization design is based on the water supply network topology optimization, and various optimization design schemes are developed around the water supply network optimization operation and the network optimization scheduling at present, including configuration and scheduling of water supply pumps, reconstruction and expansion of water supply pipelines and the like; the main solution is an optimization method combining pipe network topology structure optimization and pipe diameter combination scheme optimization, and adopts a genetic algorithm (GA for short) to conduct pipe diameter optimization, so that the purpose of optimizing design is achieved.

However, the operation and maintenance stage of the water supply network has not been paid attention to, and there are pain points such as pipeline breakage or insufficient pipeline pressure, pipe bursting and the like in the operation and maintenance stage. The most important and difficult part in the maintenance and repair work of the water supply system is the repair of the water supply network. At present, the repair of a water supply network is always a main research difficulty in the water supply field, and in view of the characteristics and operation characteristics of the water supply system, maintenance and repair are necessary and long-term tasks of the water supply system. Meanwhile, water supply network repair is a complex problem, and various aspects are required to be paid attention to in the solving process. This is a discrete variable, nonlinear, multi-objective optimization problem. At present, the optimized restoration of the water supply network usually uses economic cost as a single objective function, and the factors such as reliability in the network system, pressure and flow rate of the network system and the like are less comprehensively considered. When multiple targets are involved, such as lowest repair cost, highest reliability of a pipe network, etc., on the premise of meeting the service water pressure and flow of each node, how to find a balance, and a repair scheme for obtaining an optimal solution is always a problem to be solved in the art.

Further, the conventional genetic algorithm adopted at present cannot solve multiple targets, conflict exists between one fitness value of the Genetic Algorithm (GA) and multiple target functions of the repair problem, and uncertainty caused by using a weight coefficient or a penalty function is avoided; the existing solution generally sets the flow, the flow speed and the pressure of each node between a minimum value and a maximum value, and takes the flow, the flow speed and the pressure of each node as pipe network constraint conditions, but only the parameters of each node are controlled within a reasonable range, and the flow speed of each node is not controlled on the economic flow speed, and the pressure of each node is not controlled to be close to the minimum service water pressure; namely, the energy saving and consumption reduction are not really realized.

Based on the above, the invention provides a water supply network restoration method, a device, electronic equipment and a computer storage medium. Some embodiments of the present invention are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.

Example 1

The embodiment of the invention provides a water supply network repairing method, referring to a flow chart of the water supply network repairing method provided by the embodiment of the invention shown in fig. 1, the method comprises the following steps:

Step S102, obtaining basic parameters of the water supply network, and constructing a topological structure model of the water supply network based on the basic parameters.

Specifically, various basic parameters of the water supply network, such as pipeline length, pipe diameter, material, node position and the like, need to be collected. These parameters may be obtained by field measurements, design drawings, or historical data. Based on the basic parameters, a topological structure model of the water supply network can be constructed, and the model can clearly show the physical layout of the water supply network and the relation among the parts.

In some preferred embodiments of the present invention, basic parameters of a water supply network system within a target area are collected and sorted, where the number of water pumps of the water supply pump station and the parameters of a single water pump include: pump flow, head and pump energy consumption curves; historical monitoring data of flow monitoring points, flow rate monitoring points and pressure monitoring points installed in the current water supply network topological structure; the data such as the length, the pipe diameter, the node flow rate and the like of each node pipe section in the current water supply network topological structure; the nodes comprise water inlets entering residential communities, water inlets of public buildings (such as libraries, museums, gymnasiums, public toilets, airports, high-speed rail stations, subway stations, markets and the like), intersections of municipal main pipes and municipal branch pipes; the current water supply network topology system is imported into the water supply network modeling software, and the water supply network system imported into the water supply network modeling software carries vector data such as pipeline length, pipe diameter, pipe material, pipeline roughness coefficient, elevation and the like.

After the water supply network topology system is imported into the water supply network modeling software, the data information in the network topology structure in the model and the data information in the current water supply network topology structure are required to be calibrated and checked one by one, so that the accuracy of water supply network data import is ensured.

And step S104, checking and updating the water supply network topological structure model based on the operation data of the water supply network.

Specifically, the actual operation data of the water supply network, such as flow, pressure, water quality and the like, are needed to be utilized to check and update the topological structure model constructed in the previous step. This is because the water supply network in actual operation may deviate from the original design for various reasons (such as aging, damage, modification, etc.), and thus needs to be adjusted according to the actual situation.

In some preferred embodiments of the present invention, on the basis that the model has been imported into the water supply network modeling software, clicking operation in the software may obtain operation data of each node, including the water pressure of the node, the flow rate of the node, the pump lift, the pump energy consumption curve, the pump flow rate, etc.; comparing the software running result with the actually monitored historical data, calculating a relative error value, and considering that modeling is successful when the relative error value is controlled within 5%; otherwise, debugging the topological structure of the water supply network in the model, modifying the node flow of the pipeline and the pipeline roughness coefficient, and repeating the steps until the relative error between the running result and the actual result of the modeling software is not more than 5%.

And S106, determining an adjustment scheme of the water supply network based on the daily maintenance information and the simulated operation condition data of the water supply network.

Specifically, we need to combine the daily maintenance information (such as maintenance records, replacement records, etc.) of the water supply network with the simulated operation condition data (such as flow change, pressure change, etc.) to determine the adjustment scheme of the water supply network. This solution should be able to solve existing problems, increase the water supply efficiency, reduce the operating costs and extend the service life of the pipe network as much as possible.

In some preferred embodiments of the present invention, the present water supply network is analyzed to find a pipe section with a problem, and the analysis method includes the following steps:

a) According to the maintenance unit of the water supply pipe network, the pipe sections at the positions are identified by finding out pressure abnormal points, flow abnormal points, leakage points of the pipe and the like in the daily inspection of the water supply pipe network.

B) The water supply network topology structure is simulated, the hydraulic operation working conditions of the water supply network are changed, the operation working conditions comprise the working conditions of the highest day maximum time, the working conditions of the least favorable pipe section accidents and the fire-fighting working conditions, and abnormal pipe sections such as flow and pressure are obtained through software simulation.

The abnormal pipe sections obtained by analysis in the two methods (a) and (b) are marked and sorted to form all water supply pipe groups to be repaired, and the repairing scheme comprises the steps of changing the pipe (the pipe and the pipe diameter are not changed), changing the pipe diameter, communicating different pipe nodes, changing the pipe (the friction coefficients of different pipes are different, the friction coefficients are different, the head loss is different, and the pressure of the nodes is different) and the like.

N repair schemes of the abnormal pipe sections exist, and whether to replace a pipeline or to communicate among pipeline nodes can be determined in each scheme; however, the size of the replacement pipe diameter and the pipe need to be further calculated and clarified through an algorithm.

Step S108, respectively carrying the adjustment scheme into a first objective function taking the corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function taking a reasonable range of the water supply network node pressure as the constraint target, and solving to obtain a plurality of first objective function values and a plurality of second objective function values; the first objective function values and the second objective function values are sorted from small to large, the front first objective function value of the preset proportion is selected, the adjusting scheme corresponding to the selected first objective function value is used as a first objective adjusting scheme, the front second objective function value of the preset proportion is selected, the adjusting scheme corresponding to the selected second objective function value is used as a second objective adjusting scheme, and the first objective adjusting scheme and the second objective adjusting scheme are combined to be used as an initial population.

In particular, we need to establish two objective functions, one that optimizes the pipeline flow rate to achieve an economic flow rate and the other that optimizes the node pressure to achieve a minimum. The two objective functions need to be solved together on the premise of meeting certain constraint conditions so as to determine the optimal initial population. In some preferred embodiments of the invention, initializing the population is performed by listing all tube diameters that can be used for the tube segment to be repaired.

In some preferred embodiments of the present invention, a first objective function W _i, which takes the corresponding pipeline flow rate as the constraint target, is established, and represents the flow rate performance of the water supply network, and takes the pipeline meeting the economic flow rate as the objective function, such as the calculation formula (1):

（1）

wherein, As a first weight coefficient, a first set of weights,Is a second weight coefficient and is more than or equal to 0≤1，0≤≤1，+=1，For pipe flow rates below the economic flow rate (m/s),For a set of pipe groups having a velocity below the lower boundary of the economic flow rate,For pipe flow rates higher than the economic flow rate (m/s),For a set of pipe groups with a speed above the upper boundary of the economic speed,Indicating a flow rate (L/s) of the corresponding conduit below the economic flow rate,Representing the flow rate (L/s) of the corresponding conduit above the economic flow rate,The flow rate (L/s) of each section of pipeline,For the speed (m/s) of each segment of pipe,For the collection of all pipes within a region,Is an economic speed, namely, the economic flow rate of pipelines with different pipe diameters.

Establishing a second objective function W _j which takes a reasonable range of the water supply network node pressure as a constraint target, such as a calculation formula (2):

（2）

wherein, As a result of the third weight coefficient,Is a fourth weight coefficient, and is more than or equal to 0≤1，0≤≤1，+=1；Indicating that the node pressure in the water supply network is lower than the minimum service water pressure (Pa); A set of node groups representing a pressure below a minimum service water pressure; node traffic (L/s) representing a pressure below the minimum service water pressure; Indicating that the node pressure in the water supply network is higher than the maximum service water pressure (Pa); a set of node groups representing a pressure above a maximum service water pressure; node traffic (L/s) representing a pressure above the maximum service water pressure; Representing node flow (L/s) in the water supply network; representing the pressure (Pa) of any node in the water supply network; Representing the pressure corresponding to the nodes within the different blocks.

The objective functions W _i and W _j are solved, the solution cluster in W _i is set to m= { M ₁、m₂、m₃…m_n }, the solution cluster in W _j is set to k= { K ₁、k₂、k₃…k_n }, and n represents the number of solution sets. Each solution set in the solution set includes a replacement of at least one segment of tubing, typically including multiple segments of tubing.

Substituting the function values into objective functions to calculate, sorting the function values obtained in W _i、W_j from small to large, and taking 50% of solution clusters before sorting as an optimal solution cluster 1 and a most-available solution cluster 2; and carrying out fusion analysis on the optimal solution clusters 1 and the most optimal solution clusters 2, deleting the repeated parts if the repeated parts exist, and combining the two optimal solution clusters as an initial population J.

Step S110, coding the initial population based on a preset pipe diameter code.

Specifically, we need to encode the initial population according to a preset pipe diameter code to facilitate subsequent calculation and operation.

In some preferred embodiments of the present invention, the initialized population J is genetically encoded according to a certain encoding principle, each segment of the tube represents a small segment of the gene, and a series of the gene codes are combined to form a chromosome set (the segment set formed by all the segments to be repaired is the chromosome set).

In some preferred embodiments of the present invention, the coding is performed for pipe diameters, and the coding principles are shown in table 1:

TABLE 1 pipe diameter correspondence code

Illustratively, numbers 1 through 5 represent 5 schemes for a pipe segment to be repaired, each scheme comprising 5 pipe segments, and table 2 shows a coding scheme for replacing 5 pipe segments, wherein the pipe diameters of numbers 1 are DN800, DN1000, DN1400, DN800, DN100, respectively, and the gene codes are 13 17 25 130, respectively.

Table 2a repair coding scheme

Step S112, sequentially carrying out pipe network adjustment and fitness calculation on chromosomes in the encoded initial population to obtain fitness; the function of the fitness calculation is constrained based on a third objective function taking the annual repair cost in the investment period as a constraint target and a fourth objective function taking the pipe network reliability performance evaluation as the constraint target.

Specifically, we need to perform the tube network adjustment and fitness calculation on the encoded initial population to obtain fitness of each chromosome. The fitness is calculated based on two objective functions, one is to optimize annual repair costs and the other is to optimize the reliability performance of the pipe network.

Step S114, performing non-dominant sorting and crowding calculation on chromosomes with fitness meeting a preset fitness threshold value to obtain a new parent population.

Specifically, we need to perform non-dominant ranking and crowding calculation on chromosomes with fitness meeting a preset threshold to obtain a new parent population. Non-dominant ranking is to find the optimal solution, while crowding is to preserve diversity of the population.

Step S116, iteratively updating the new parent population.

In particular, we need to iteratively update the new parent population continually until a preset number of iterations or other stopping conditions are met. The preset iteration condition may be that the preset iteration number is reached, or that the constraint function satisfies the preset condition.

Step S118, taking the new parent population meeting the preset iteration times as a water supply network restoration scheme.

Specifically, a new parent population meeting the preset iteration times is used as a repairing scheme of the water supply network. This solution should be an optimal solution based on all considerations (e.g., cost, efficiency, reliability, etc.).

The invention provides a water supply network restoration method, which comprises the following steps: basic parameters of a water supply network are obtained, and a topological structure model of the water supply network is constructed based on the basic parameters; checking and updating the water supply network topological structure model based on the operation data of the water supply network; determining an adjustment scheme of the water supply network based on daily maintenance information and simulated operation condition data of the water supply network; the method comprises the steps of determining an initial population in an adjustment scheme by jointly solving a first objective function taking a corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function taking a minimum value of the pressure of a node of a water supply network as the constraint target; coding the initial population based on a preset pipe diameter code; sequentially carrying out pipe network adjustment and fitness calculation on chromosomes in the encoded initial population to obtain fitness; the function of the fitness calculation is constrained based on a third objective function taking the annual repair cost minimization in the investment period as a constraint target and a fourth objective function taking the pipe network reliability performance evaluation as a constraint target; non-dominant sorting and crowding calculation are carried out on chromosomes with fitness meeting a preset fitness threshold value, so that a new father population is obtained; iteratively updating the new parent population; taking a new father population meeting the preset iteration times as a water supply network restoration scheme; the water supply network repairing scheme is finally determined by acquiring the adjusting scheme of the water supply network and optimizing the adjusting scheme based on the multiple objective functions, and the running state and the maintenance cost of the water supply network are comprehensively considered through the constraint of the multiple objective functions, so that the user experience is improved.

In the method, compared with the traditional method, the flow rate or the flow rate in the whole pipe network system is given a specific constraint interval, the function model constructed by the method is more scientific and reasonable, each node and each section of the water supply pipe network are firstly constructed as a first objective function and a second objective function to solve, so that the free water pressure of each node meets the minimum service water pressure, the flow rate of each section meets the economic flow rate, the whole pipe network system meets the energy-saving and efficient operation, the lowest economic cost and the maximum pipe network reliability are constructed as a third objective function and a fourth objective function, the cost of the repaired pipe network system is the lowest, the reliability of the repaired pipe network system is the highest, and the pipe network repairing scheme is comprehensively optimized.

Example two

On the basis of the embodiment, the embodiment of the invention provides another water supply network repairing method, wherein in the process of analyzing and optimizing the water supply network, the pipe network adjustment is a key step, and the method involves adjusting and calculating the node water pressure so as to meet the requirements of continuity and energy conservation. The purpose of pipe network adjustment is to ensure that all node water pressures reach an equilibrium state given water flow demands and system constraints.

In some preferred embodiments of the present invention, calculating the pipe network adjustment comprises the following steps A1 to A3:

A1, calculating the closing difference of pipe network nodes of the water supply network based on pipe network data of the water supply network and preset calculation accuracy; the pipe network data comprise node water pressure.

In particular, we need to collect complete pipe network data, which typically includes the layout, size, material, roughness coefficients of the pipes, and the water pressure and flow requirements of the nodes. Such data may be obtained from field measurements, historians, or sensor monitoring systems. Next, we use this data to initialize a hydraulic model that can simulate the distribution of water flow in the pipe network and the pressure loss.

After initializing the model, we begin a preliminary hydraulic calculation to estimate the water pressure at each node. These preliminary calculations are typically based on simplifying assumptions, for example, assuming that the flow rates of all the pipes are uniform, and ignoring some factors that may affect the water pressure, such as changes in viscosity of the water, changes in temperature, etc.

Next, we calculate the closure difference of each node, i.e., the difference between the actual water pressure and the target water pressure. The closure difference is a key indicator for measuring the accuracy of the current hydraulic model. If the closing difference is small, the prediction of the description model is very close to the actual situation; if the closure difference is large, this means that an adjustment of the model is required.

And step A2, if the closing difference meets the preset precision, determining the node water pressure as the node target water pressure.

Specifically, if the calculated closing difference is within a preset accuracy range (e.g., less than a certain percentage or absolute value), we can consider the current node water pressure to be acceptable and determine it as the target water pressure for the node. This means that at these nodes the water pressure meets the design requirements without further adjustment.

And step A3, if the closing difference does not meet the preset precision, adjusting the node water pressure based on the jacobian matrix of the node water pressure until the closing difference meets the preset precision.

Specifically, if the closing difference exceeds the preset accuracy range, we need to adjust the node water pressure. This process typically involves the use of iterative methods such as the Newton-Raphson method (Newton-Raphson method). In this process we use Jacobian matrix (Jacobian matrix) to describe the relationship between node water pressure and closure difference. The jacobian matrix is a partial derivative matrix, each element of which represents the effect of a node water pressure change on the closure difference.

From the jacobian, we can calculate the amount that the water pressure needs to be adjusted for each node in order to reduce the closing difference. Then, we update the node water pressure based on these calculations and re-perform the hydraulic calculations. This process is repeated until the closing differences of all nodes meet the preset accuracy.

In practice, pipe network adjustment may require multiple iterations to achieve satisfactory results. After each iteration it is necessary to check if the closure difference is already small enough. If not, it is necessary to continue adjusting the water pressure based on the information provided by the jacobian matrix. This process can be complex because it involves a large amount of data processing and computation, but modern computers and specialized software can handle these tasks efficiently.

When the closing difference meets the preset precision, an accurate hydraulic model can be obtained. This model will provide us with the target water pressure for each node that will be used for subsequent pipe network optimization and repair decisions. In this way we ensure that the water supply network can be operated efficiently and reliably while meeting the needs of the user.

In some preferred embodiments of the present invention, a chromosome group formed by combining pipe diameters with gene codes performs pipe network adjustment and fitness function value calculation, referring to a flowchart of adjustment calculation provided in the embodiment of the present invention shown in fig. 2, the adjustment calculation includes the following steps B1 to B3:

Step B1, inputting pipe network data, including initial water head, pipeline friction coefficient and water demand, and calculating accuracy Calculating the closing difference of pipe network nodes as shown in formulas (3) to (9):

The continuity equation of pipe network nodes:

（3）

wherein, For the flow rate of the pipe section,The unit of traffic is L/s, which is the sum of all traffic connected to pipe node i.

Equation of pipe network head loss:

（4）

wherein, Is the pressure value of the node i at the two ends of the pipeline,For the pressure value of the two end nodes j of the pipeline, the unit is m, S _ij is the friction coefficient of the pipeline section ij, n is the thank coefficient, and 2 is taken in some preferred embodiments of the invention.

Pipeline head index equation:

（5）

wherein Sign is% ) As a sign function when>0，sign（) When =1=0，sign（) When=0, when<0，sign（）= -1。

Constructing a nonlinear node water pressure equation set:

（6）

In the formula (6), the pressure equation sets of the nodes 1,2,3 … N are f ₁、f₂、f₃…f_N, respectively.

The first-order calculus derivation is carried out on the nonlinear node water pressure equation set to obtain the following steps:

（7）

Constructing a node water pressure matrix J to obtain the following steps:

（8）

Let the initial value of the pressure of the pipe network node i be The initial value of the pressure of the node j isThe correction pressure of the corresponding node is、The following formula can be used:

（9）

wherein, Representing a step size factor between 0, 1.

(B) Determining calculated closure differences for all pipe sections，i=1,2,3,4,5,… ,N（Representing whether the accuracy=0.0000001 m ³/s) meets the requirement or not, if not, obtaining corrected water pressure according to calculation, updating the closing difference of the pipe network nodes, updating the node water pressure matrix J, recalculating the closing difference of the updated pipe network nodes, and repeating the operation until the accuracy meets the requirement;

(c) And finally, outputting the water pressure of the pipe network node.

At present, in the prior art, pipe network adjustment is generally rarely carried out before multi-objective function solving is calculated, and the necessity and importance of reasonable flow distribution in a water supply pipe network system are ignored; meanwhile, the running state and maintenance cost of the pipe network are not fully considered in the fitness calculation, the detailed steps of pipe network adjustment and fitness calculation are provided, the closing difference calculation of pipe network nodes is carried out based on pipe network data and preset calculation precision, and the annual repair cost and the reliability performance of the pipe network are comprehensively evaluated through a fitness function.

In some preferred embodiments of the present invention, the fitness calculation includes the following steps C1 to C5:

step C1, setting an initial chromosome I as Ri=1, decoding gene codes in a chromosome group constructed by pipe sections to be repaired to generate a corresponding pipe diameter group Z1, overlapping and combining the pipe diameter group Z1 and the pipe diameter group Z2 of the rest pipe sections which normally operate in a water supply network, and forming a pipe diameter group Z3 of the pipe diameters in the current water supply network through the operation;

step C2, pipe network adjustment is carried out on the pipe path combination Z3 so as to determine flow distribution of each pipe section and pressure of a node;

Step C3, calculating the cost and reliability function of the pipe network;

step C4, calculating the fitness function F (k) value of the chromosome Ri;

Step C5, judging whether the initial chromosome one is set to be ri=1 to be greater than or equal to R (the R value is determined according to the number of schemes to be repaired required by the actual pipe network operation condition, R represents the number of chromosomes, and the number of schemes to be repaired is generally equal to the number of chromosomes); if the value is larger than or equal to the R value, performing non-dominant sorting congestion degree calculation; if the value is smaller than the R value, the method returns to the step BC, and the pipelines are recombined until the fitness value meets the requirement, wherein the operation of the step is to confirm that the fitness of each scheme is checked and set.

In some preferred embodiments of the invention, the pipe diameters of all pipe sections are subjected to gene coding, initial groups formed by combining different pipe diameters are subjected to pipe network adjustment calculation, hydraulic characteristics such as pipe section flow distribution, head loss and water pressure of all nodes are optimized and calculated, and then the adaptability value of the pipe network is calculated.

First, a third objective function Wx is established with the annual repair cost minimized as a constraint objective during the investment period, and the formula (10) for calculating the Wx function is as follows:

（10）

Wherein a is a first coefficient in a pipeline construction cost formula, b is a second coefficient in the pipeline construction cost formula, c is a third coefficient in the pipeline construction cost formula, D _k is the diameter (mm) of the pipeline k, L _k is the length (m) of the pipeline k, and N is the total number of pipeline groups required to be repaired in the area.

And establishing a fourth objective function W _y taking the pipe network reliability performance evaluation as a constraint target. As shown in equation (11).

（11）

Wherein Q _o is the sum of the flow rates of all the pipe sections in the water supply network (m ³).

The flow entropy S _j of any node j in the water supply network is shown in the following calculation formula (12):

（12）

Wherein U _j is the set of nodes upstream of node j; q _ij is the flow of pipe ij (m ³), the flow direction is from node i to node j, n represents the pipe segment number, and Q _j is the sum of all pipe flows flowing into node j (m ³).

And solving Wx and Wy by taking the formula (13) as a constraint condition.

（13）

The fitness function is to convert the multi-objective function F into a single objective function value K by a weighted average method, and the single objective function value K is specifically represented by the following formula (14):

（14）

wherein, 、The value is between 0 and 1.

Further, in some preferred embodiments of the present invention, the fitness calculation is performed by the following formula (15):

（15）

Wherein F (k) is an fitness function, For the first weight to be given,For the second weighting, W _x is the third objective function, W _xmin is the minimum of the third objective function, W _xmax is the maximum of the third objective function, W _y is the fourth objective function, (1/W _y)_min is the minimum of the reciprocal of the fourth objective function, and (1/W _y)_max is the maximum of the reciprocal of the fourth objective function.

Further, non-dominant ordering (Non-dominated Sorting) is one method in a multi-objective optimization problem for distinguishing and classifying solutions in a solution set, which separates the solutions into different levels according to dominant relationships between the solutions. In a multi-objective optimization problem, one solution may be superior to another on one objective and inferior on another, thus requiring a special ordering method to handle the solutions. It is to solve this problem that the non-dominant ordering is designed. In some preferred embodiments of the invention, the non-dominant ordering includes the following steps D1 to D3:

Step D1, defining a dominant count and a dominant solution set for each solution.

Specifically, we first initialize two attributes for each solution: dominant counts (Dominance Count) and dominant solution sets (Dominated Set). The dominant count refers to the number of other solutions that dominant the solution, i.e., how many solutions are better or equal than it. The solution set that is dominated by the solution then refers to the set of all solutions that are subject to the solution, i.e. which solutions the solution is better or equal to. These two attributes will be used in subsequent steps to determine the hierarchy and non-inferiority of the solution.

And D2, performing all solutions, and determining a first non-inferior layer.

Specifically, we walk through all solutions, for each solution we check if its dominant count is zero. If the dominant count is zero, it is stated that no other solution dominates the solution, so the solution is non-bad, which is added to the first non-bad layer (Front). This process continues until all solutions have been checked. Solutions in the first layer non-bad layers are most advantageous because they are not freed by any other amount.

Step D3, updating the hierarchy based on the dominant count and the dominant solution set until one hierarchy is empty.

In particular, we use the determined non-bad layers to update the dominant count of the remaining solutions and the solution set of the dominant solutions. Specifically, for each solution in the first layer, non-inferior layer, we remove it from the solution set that is dominated by the solutions of the other solutions and decrement the dominance count of these solutions by one. The reason for this is that since solutions in the first non-bad layer have already been considered, they no longer affect the non-bad nature of other solutions.

Then we go through all solutions again, looking for new ones whose dominant count is zero, which will constitute the second non-bad layer. This process is repeated with each iteration determining a new non-bad layer until all solutions have been assigned to a non-bad layer. In this process, higher level solutions are always superior to lower level solutions.

Finally, the algorithm ends when all solutions are assigned to a certain non-bad layer. At this point we get a set of solutions ordered in terms of non-inferiority, where the solution of the first non-inferiority layer is optimal, followed by the solution of the second non-inferiority layer, and so on. This ordering provides us with an intuitive way to compare and select solutions, especially in multi-objective optimization problems, which often require trade-offs between different objectives.

In some preferred embodiments of the present invention, referring to a schematic diagram of non-dominant ranking calculation provided by the embodiment of the present invention shown in fig. 3, wherein the horizontal axis and the vertical axis represent two objective functions, the non-dominant ranking includes the following steps E1 to E4:

And E1, each layer shares a designated virtual fitness value, and quick non-inferior sorting operation is performed.

Step E2, first, set the dominant number n _i and the individual set S _i that is dominant by i for individual i, and store the individual in the non-inferior layer F _i when n _i =0.

Step E3, for each individual j at this time in F _i, subtracting 1 from the n _k value of all individuals k in the individual set S _j, and if n _k =0, storing the individual k in the next non-bad layer.

And E4, if the next layer F _i +1 is not empty, i=i+1, continuing iteration, and repeating the operation of the second step, otherwise, stopping iteration.

From the constructed F (k) function, we can assume that, based on the actual situation, we can firstFor the first weight to be given,The values of the second weighting and the maximum, minimum and other values of the third and fourth objective functions obtained by solving are substituted into a formula, so that virtual fitness values can be obtained, according to the illustration in fig. 3, under the condition of different virtual fitness values, different groups of non-inferior layers can be obtained, the non-inferior layers represent a plurality of groups of optimal solution sets, for example, on the non-inferior layer 1 corresponding to the virtual fitness value 1, the solution set 1 and the solution set 2 are both optimal solutions, on the non-inferior layer 2 corresponding to the virtual fitness value 2, the solution set 3 and the solution set 4 are both optimal solutions, on the non-inferior layer 3 corresponding to the virtual fitness value 3, and the solution set 5 and the solution set 6 are both optimal solutions.

Further, in some preferred embodiments of the present invention, referring to a congestion degree calculation schematic diagram provided in the embodiment of the present invention shown in fig. 4, in which the horizontal axis and the vertical axis represent two objective functions, when performing non-inferior sorting, all individuals in the population have two parameters, the first is the non-inferior layer number i _rank where the individuals are located, and the non-inferior layer number i _rank is shown in fig. 3 in detail; second, the congestion distance i _distance of the individual is calculated based on the following formula (16):

（16）

wherein i _distance is the crowding distance of the individual in the non-dominant ranking, r is the number of objective functions, As a fitness function of the (i+1) th individual on the (j) th target,Is the fitness function of the i-1 th individual on the j-th target.

Further, referring to a flowchart of a population iteration method provided by the embodiment of the present invention shown in fig. 5, for a population that has satisfied an fitness requirement, performing non-dominant ranking and crowding calculation to generate a first generation new parent population J0, performing genetic selection, crossover, mutation operations on the first generation new parent population to generate a child population, performing elite retention policy on the parent population, merging with the newly generated child population as a new population J1, performing non-dominant ranking and crowding calculation on the new population J1, replacing the original population J0 according to the number of layers and crowding, and judging whether the requirement of the iteration number set value (if the iteration number is N, it is converged); if not, repeating the operations of selection, crossover, mutation and the like.

Further, with continued reference to FIG. 5, in some preferred embodiments of the invention, iteratively updating the new parent population includes steps F1 through F4:

Step F1, carrying out genetic processing on a new parent population to obtain a child population; wherein the genetic manipulation comprises at least one of: selection, crossover and mutation.

And F2, determining a new population based on the new parent population and the offspring population processed through the elite retention strategy.

And F3, performing non-dominant ranking and congestion degree calculation on the new population.

And F4, updating the new parent population based on the result of the number of layers of the non-dominant ranking and the congestion degree calculation.

Specifically, the selecting operation includes: the elite reservation strategy is to sort the initial parent according to the fitness value, reserve 10% -30% before the fitness of the parent population scale is sorted, and merge with the next offspring to form a new population.

Further, referring to a schematic diagram of a cross operation provided in the embodiment of the present invention shown in fig. 6, the cross operation includes steps G1 to G3:

and G1, randomly selecting two parent individuals from the parent population.

And G2, randomly selecting the cross points.

And G3, exchanging gene sequences after crossing points (including crossing points) of the gene sequences of the two parent individuals to form two new individuals to become crossed child individuals, calculating corresponding fitness of the newly generated crossed child individuals, and storing the individuals into the crossed child population.

Further, referring to a schematic diagram of a mutation operation provided in the embodiment of the present invention shown in fig. 7, the mutation operation includes steps H1 to H3:

And step H1, randomly selecting individuals in the crossed offspring population, which are put back into the random acquisition population, as operation objects of mutation operators.

And H2, selecting a gene point position for each selected individual according to the adaptive gene mutation probability to mutate, and if the same gene point position is selected for multiple times, changing the value of the same gene point position for multiple times and retaining the final result.

And step H3, calculating the fitness of the newly generated individuals and storing the fitness into the variant offspring population.

The embodiment of the invention provides a water supply network repairing method, which is characterized in that a multi-objective function is established, the repairing construction cost of a water supply network system, the energy consumption of a pump station group, the manager flow rate of a pipe section to be repaired, the service water pressure of each node and the entropy reliability factor of the whole water supply network system are comprehensively considered, and a scientific basis is provided for a repairing scheme of a pipeline to be repaired; creatively establishing a pipeline flow rate to be repaired and working pressure (minimum service water pressure) of each node of a pipeline section as objective functions, and repairing the pipeline to be repaired to form a pipeline flow rate which tends to economic flow rate when the pipeline speed to be repaired is insufficient or exceeds a speed boundary; the pressure tends to the minimum working pressure when the node pressure is insufficient or exceeds the minimum working pressure, and the whole water supply network is restored into an economic and energy-saving system; solving the problem of optimizing discrete variable, nonlinearity and multiple targets by adopting an improved non-dominant genetic algorithm aiming at multiple target functions, and compared with the traditional genetic algorithm, adopting elite retention strategy, screening excellent individuals, executing genetic operations such as selection, intersection, mutation and the like to generate a child population, merging the original population and the child population, executing non-dominant sorting crowding degree calculation, replacing the original population according to the number of layers and crowding degree, and continuously iterating to form an excellent elite population, so that a group of same good (non-dominant) optimal solutions (Pareto sets) can be obtained; by selecting, crossing, mutating and the like, the method accelerates the convergence rate of the population, and not only improves the convergence rate, but also improves the rationality and feasibility of solving.

At present, the traditional genetic algorithm has fitness value conflict and uncertainty when processing a multi-objective problem, and generally needs to convert a multi-objective function into a single-objective function when solving discrete variable, nonlinear and multi-objective optimization problems, and the problems that the function can not be converged rapidly and the calculation time is long exist. The improved non-dominant genetic algorithm is adopted, the values solved by the first objective function and the second objective function are firstly used as an initial population, which is equivalent to the situation that better individuals are obtained in the initial stage, the pipe network adjustment is carried out on the initial population to ensure reasonable distribution of pressure and flow, then the non-dominant genetic algorithm operation is carried out, the excellent individuals are screened through the elite retention strategy, the genetic operations such as selection, crossover, mutation and the like are carried out, the excellent individuals are retained, the diversity of the population is enriched, the problem of multi-objective optimization is effectively solved, the rationality and the feasibility of the solution are improved, algorithm convergence is rapidly realized, the operation time is shortened, and the calculation efficiency is improved.

Example III

On the basis of the embodiment, the embodiment of the invention further describes the embodiment by taking a water supply network of a certain city in the eastern China as an example. Referring to fig. 8, a schematic diagram of a current model of a water supply network is provided according to an embodiment of the present invention, where the water supply network includes 21 effective pressure monitoring points and 4 effective flow monitoring points. And selecting 12 pressure monitoring points and 4 flow monitoring points for checking, and the remaining 9 pressure monitoring points for verification, wherein the flow error is not more than 5%.

The last three months of water volume data provided by the water supply area is shown in table 3 below.

TABLE 3 actual Water flow run data

And (3) checking the pipe network model when the water consumption of the water supply pipe network is high on a daily basis, wherein the checking results are shown in tables 4 and 5, the average checking error of the pressure is 3.88%, and the flow checking error is within 3%.

Table 4 pressure check results at maximum

Table 5 flow check results at highest

And the established water supply network model is considered to be in an error range through the analysis, and the model is considered to be rated to be successful.

Firstly, analyzing the current water supply network, and finding out that the partial area of the water supply network is in an excessively low pressure state through model analysis, wherein the specific distribution is shown in a pipe network adjustment analysis schematic diagram provided by the embodiment of the invention shown in fig. 9.

It can be seen from fig. 9 that the network water pressure is lower for the A, B, C, D, E four zones, with the water pressure being significantly lower for two of the A, B zones than for the other zones. The pressure of a part of nodes in the area A is lower than 28m, and the lowest pressure is 15.75m; the free water head in the western region of the zone B is between 10 and 20m, the free water head in the northeast corner partial region is about 5m, and the lowest free water head is only 1m.

Further, referring to a schematic flow distribution diagram of each pipe section in the B region provided by the embodiment of the present invention shown in fig. 10, a schematic head loss distribution diagram of each pipe section in the B region provided by the embodiment of the present invention shown in fig. 11, and a schematic flow distribution diagram of each pipe section in the B region provided by the embodiment of the present invention shown in fig. 12, the flow rate in the B region is only 70% of the actual demand value, and the flow rate in the B region is only 65% of the actual demand value.

In this embodiment, taking the area B as an example, the pipeline head loss and the pipeline flow rate of the area B can be obtained from the simulation operation result of the area B and the daily inspection data of the actual pipe network maintenance management unit.

The total 128 sections of the water supply network in the area B are accumulated, and the basic parameters of each section of the pipeline comprise length, diameter, flow, roughness coefficient, flow velocity, friction factor, head loss and the like. Table 6 shows the basic operating parameters of sections 1-16.

Table 6 shows basic operation parameters of partial nodes of the pipe network system

By statistical analysis of the pipes of the water supply network, it was found that the flow rate of the pipes 15, 36, 37, 38, 45, 62, 63 …, etc. as shown in Table 7 was negative, indicating that the pipes had problems.

TABLE 7 pipe section with flow problems

In this embodiment, the pressure is higher than 38 m, and is considered to be higher according to the actual situation, as shown in table 8, where the pressure at the nodes 15, 36, 37, 38, 45, 62, 63, 77 is higher, and the pressure is not lower.

Table 8 node with unreasonable pressure

Further, the pipe sections 15, 36, 37, 38, 45, 62, 63 and 77 were monitored for flow rate as shown in table 9.

TABLE 9 unreasonable flow rate range pipe section

Thus, a repair optimization scheme is provided for the water supply pipeline in the local area of the B area.

The solution is performed based on a first objective function W _i taking the corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function W _j taking a reasonable range of the water supply network node pressure as a constraint target.

For the first objective function W _i, in some preferred embodiments of the present aspect, a first weighting factor is takenSecond weight coefficientThe pipe diameter is 100-400 mm, and the pipe speed is lower than 0.6m/s; the pipe diameter is more than 400mm, the flow velocity of the pipeline is 0.9m/s, the pipeline groups are assembled to form a pipeline group cluster, and the pipeline group cluster is usedThe diameter of the pipeline is 100-400 mm, and the flow speed of the pipeline is higher than 0.9 m/s; the diameter of the pipeline is more than 400mm, the flow velocity is more than 1.4m/s, the pipeline groups are assembled to form a pipeline group cluster, the pipeline group cluster is expressed by Px, P _s is an accumulated 128-section pipeline and 256 nodes,The economic flow rates corresponding to the pipelines with different pipe diameters are shown in the table 10.

TABLE 10 economic flow Rate Range

For the second objective function W _j, in some preferred embodiments of the present aspect, a third weight coefficient is takenTaking the fourth weight coefficient，Representing a node group set with pressure higher than the maximum service water pressure, wherein the minimum service water pressure of the urban water supply pipeline is not less than 28m, and the maximum water pressure is not more than 38m; the minimum service water pressure in the rural area is not less than 18m, and the maximum water pressure is not more than 25m.

The solution cluster obtained in W _i is set to M _i={m₁、m₂、m₃,…,m_n, and the specific reference is shown in Table 11; the solution cluster set for W _j is K _j={k₁、k₂、k₃,…,k_n, as shown in Table 12.

Decolonization of Table 11M _i

Decolonization of Table 12K _i

Substituting M _i={m₁、m₂、m₃,…,m_n and K _j={k₁、k₂、k₃,…,k_n into an objective function respectively for calculation, sorting the function values obtained in Wi and Wj from small to large, and taking 50% of solution clusters before sorting as optimal solution clusters ZUi and the most-available solution clusters ZUj; the optimal solution clusters ZUi and the most optimal solution clusters ZUj are fused and analyzed for the presence of duplicates, duplicates are partially deleted, and the two optimal solution clusters are combined as an initial population CSj.

The optimal solution clusters ZUi are shown in table 13.

TABLE 13

The optimal solution clusters ZUj are shown in table 14.

TABLE 14

There are three choices for pipe ID 15 {400mm, 600mm, 500mm }, and similarly pipe ID 36 = {500mm, 700mm, 750mm }; pipe ID 37= {600mm, 650mm, 750mm }; pipe ID 38= {500mm, 300mm, 550mm }; pipe ID 45= {650mm, 550mm, 800mm }; pipe ID 62= {500mm, 300mm, 550mm }; pipe ID 63= {1000mm, 850mm, 700mm }; pipe ID 77= {900mm, 850mm, 950mm }; the pipe diameters of the pipe sections to be repaired can be selected, 8 sections of pipes are accumulated according to the arrangement and combination calculation principle, and 3 selection modes exist for each pipe, so that the accumulated pipe diameters are as follows: A scheme.

The initial population CSj requires the calculation of the piping of the entire water supply as a population.

The initial population CSj is genetically encoded, for example, in scheme 1, to repair the pipe diameter of the pipe, using pipe id15=400 mm, pipe id36=500 mm, pipe id37=600 mm, pipe id38=500 mm, pipe id45=650 mm, pipe id62=500 mm, pipe id63=1000 mm, pipe id77=900 mm.

The pipe diameters of the rest normal pipes are still coded according to the original pipe diameters, such as pipe ID 1 = 1400mm, pipe ID 2 = 1000mm, pipe ID 3 = 1000mm, pipe ID 4 = 1200mm, pipe ID 5 = 600mm, and the like, the pipe diameters of the pipes to be repaired and the pipe diameters of the normal pipes are subjected to gene coding based on the table 1, and the pipe diameters are combined to form a series of chromosome groups by gene coding combination, for example, the gene coding of the chromosome groups of the first 15 of the first group of scheme pipe IDs is as follows: {25, 17, 21, 21,9,9,9,9,9,9,5,5,9,1,0}.

The pipe network adjustment and fitness calculation are carried out on a chromosome group formed by pipe diameter gene coding combination, and the calculation comprises the following steps:

(a) Setting the initial chromosome I as Ri=1, and decoding the gene strings to generate corresponding pipe diameter combinations;

(b) Pipe network adjustment is carried out on pipe diameter combinations so as to determine flow distribution of each pipe section and pressure of nodes;

(c) Calculating the cost and reliability function of the pipe network;

(d) Calculating fitness function F (k) values of chromosome ri=1;

(e) Determining whether or not the initial chromosome one is set to ri=1 to 6561? The calculation from (a) to (d) is equivalent to the calculation of 6561 schemes, and if 6561 or more is already performed, the non-dominant ranking congestion degree calculation is performed; if the adaptability value is less than 6561, returning to the continuing step (a), and recombining the pipelines until the adaptability value meets the requirement.

Carrying out non-dominant sorting and crowding calculation on initial populations of 6561 schemes to generate a first generation new parent population J0, carrying out genetic selection, crossing and mutation operation on the first generation new parent population to generate a child population, carrying out elite retention strategy on the parent population, combining the parent population with the newly generated child population to serve as a new population J1, carrying out non-dominant sorting and crowding calculation on the new population J1, replacing the original population J0 according to the number of layers and the crowding degree, and judging whether the number of times of overlap is more than 100000 times; if not, repeating the operations of selection, crossing, variation and the like until convergence, and outputting a final result.

The final result is a solution set of 2 pipe diameter combinations of the pipe to be repaired meeting the requirements, and the following table 15 is obtained:

TABLE 15

The optimized design of the water supply network related to the prior art possibly focuses more on the planning and design stages, but the importance of the operation and maintenance stages is insufficient; the invention particularly emphasizes pipe network optimization in the operation and maintenance stage, and provides a systematic repair method which comprises the steps of pipe network current situation analysis, model checking, optimization scheme solving and the like, and is beneficial to improving the long-term operation efficiency and reliability of the water supply pipe network.

Example IV

On the basis of the above embodiments, the embodiment of the present invention provides a water supply network repairing device, referring to a schematic diagram of the water supply network repairing device provided by the embodiment of the present invention shown in fig. 13, which includes:

The model construction module 310 is configured to obtain basic parameters of the water supply network, and construct a topology model of the water supply network based on the basic parameters.

The model updating module 320 is configured to verify and update the topology model of the water supply network based on the operation data of the water supply network.

The adjustment scheme processing module 330 is configured to determine an adjustment scheme of the water supply network based on the daily maintenance information and the simulated operation condition data of the water supply network.

The initial population processing module 340 is configured to take the adjustment schemes into a first objective function taking the corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function taking a reasonable range of the water supply network node pressure as the constraint target, solve the first objective function values and the second objective function values, rank the first objective function values and the second objective function values from small to large, select a first objective function value with a preset proportion, use the adjustment scheme corresponding to the selected first objective function value as a first objective adjustment scheme, select a second objective function value with a preset proportion, use the selected second objective function value as a second objective adjustment scheme, and combine the first objective adjustment scheme and the second objective adjustment scheme as an initial population.

The population coding module 350 is configured to code the initial population based on a preset pipe diameter code.

The fitness calculation module 360 is configured to sequentially perform tube network adjustment and fitness calculation on chromosomes in the encoded initial population to obtain fitness; the function of the fitness calculation is constrained based on a third objective function taking the annual repair cost in the investment period as a constraint target and a fourth objective function taking the pipe network reliability performance evaluation as the constraint target.

And the new parent population processing module 370 is used for performing non-dominant sorting and crowding calculation on chromosomes with fitness meeting a preset fitness threshold value to obtain a new parent population.

The new parent population update module 380 is configured to iteratively update the new parent population.

The water supply network repair scheme determining module 390 is configured to take the new parent population satisfying the preset iteration number as the water supply network repair scheme.

Further, in some preferred embodiments of the present invention, a new parent population update module 380 is configured to perform genetic processing on the new parent population to obtain a child population; wherein the genetic manipulation comprises at least one of: selection, crossover and mutation; determining a new population based on the new parent population and the offspring population processed by the elite retention strategy; performing non-dominant ranking and crowding calculation on the new population; the new parent population is updated based on the results of the number of layers and congestion level calculations for the non-dominant ranking.

Further, in some preferred embodiments of the present invention, the fitness calculating module 360 is configured to calculate a closing difference of a pipe network node of the water supply network based on the pipe network data of the water supply network and a preset calculation accuracy; the pipe network data comprise node water pressure; if the closing difference meets the preset precision, determining the node water pressure as the node target water pressure; and if the closing difference does not meet the preset precision, adjusting the node water pressure based on the jacobian matrix of the node water pressure until the closing difference meets the preset precision.

Further, in some preferred embodiments of the present invention, the fitness calculating module 360 is configured to perform fitness calculation according to the following formula: ; wherein F (k) is an fitness function, For the first weight to be given,For the second weighting, W _x is the third objective function, W _xmin is the minimum of the third objective function, W _xmax is the maximum of the third objective function, W _y is the fourth objective function, W _ymin is the minimum of the fourth objective function, and W _ymax is the maximum of the fourth objective function.

Further, according to the constructed F (k) function, we can assume thatFor the first weight to be given,The values of the second weights and the maximum, minimum, etc. values of the third and fourth objective functions obtained by solving are substituted into the formula, so that virtual fitness values can be obtained, according to the illustration in fig. 3, different groups of non-inferior layers can be obtained under the condition of different virtual fitness values, the non-inferior layers represent a plurality of groups of optimal solution sets, for example, on the non-inferior layer 1, the solution set 1 and the solution set 2 are both optimal solutions.

Further, in some preferred embodiments of the present invention, a new parent population processing module 370 is used to define a dominant count and a dominant solution set for each solution; all solutions are performed, and a first non-inferior layer is determined; the tiers are updated based on the dominant count and the solutions of the dominant until one tier is empty.

Further, in some preferred embodiments of the present invention, the new parent population processing module 370 is configured to perform congestion level calculation based on the following formula: ; wherein idistance is the crowding distance of the individual in the non-dominant ranking, r is the number of objective functions, As a fitness function of the (i+1) th individual on the (j) th target,Is the fitness function of the i-1 th individual on the j-th target.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the water supply network repairing device described above may refer to the corresponding process in the foregoing embodiment of the water supply network repairing method, and will not be described herein again.

Example five

The embodiment of the invention also provides electronic equipment for operating the water supply network repairing method; referring to fig. 14, an electronic device according to an embodiment of the present invention includes a memory 400 and a processor 401, where the memory 400 is configured to store one or more computer instructions, and the one or more computer instructions are executed by the processor 401 to implement the above-mentioned water supply network repairing method.

Further, the electronic device shown in fig. 14 further includes a bus 402 and a communication interface 403, and the processor 401, the communication interface 403, and the memory 400 are connected by the bus 402.

The memory 400 may include a high-speed random access memory (RAM, random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 403 (which may be wired or wireless), which may use the internet, a wide area network, a local network, a metropolitan area network, etc. Bus 402 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 14, but not only one bus or type of bus. The processor 401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 401 or by instructions in the form of software. The processor 401 may be a general-purpose processor, including a central processing unit (Central Processing Unit, abbreviated as CPU), a network processor (Network Processor, abbreviated as NP), and the like; but may also be a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application Specific Integrated Circuit (ASIC), field-Programmable gate array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 400, and the processor 401 reads the information in the memory 400, and in combination with its hardware, performs the steps of the method of the previous embodiment.

The embodiment of the invention also provides a computer readable storage medium, which stores computer executable instructions that when being called and executed by a processor, cause the processor to implement the service recommendation method, and the specific implementation can be referred to the method embodiment and will not be described herein.

The method, the device and the computer program product of the electronic device for repairing the water supply network provided by the embodiment of the invention comprise a computer readable storage medium storing program codes, and instructions included in the program codes can be used for executing the method in the previous method embodiment, and specific implementation can be referred to the method embodiment and will not be repeated here.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and/or apparatus may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

In addition, in the description of embodiments of the present invention, unless explicitly stated and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims

1. A water supply network restoration method, comprising:

acquiring basic parameters of a water supply network, and constructing a topological structure model of the water supply network based on the basic parameters;

Checking and updating the water supply network topological structure model based on the operation data of the water supply network;

Determining an adjustment scheme of the water supply network based on daily maintenance information and simulated operation condition data of the water supply network;

Respectively carrying the adjustment scheme into a first objective function taking the corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function taking a reasonable range of water supply network node pressure as a constraint target, solving to obtain a plurality of first objective function values and a plurality of second objective function values, sequencing the first objective function values and the second objective function values from small to large, selecting a first objective function value with a preset proportion in front, taking the adjustment scheme corresponding to the selected first objective function value as a first objective adjustment scheme, selecting a second objective function value with a preset proportion in front, taking the adjustment scheme corresponding to the selected second objective function value as a second objective adjustment scheme, and combining the first objective adjustment scheme and the second objective adjustment scheme as an initial population;

coding the initial population based on a preset pipe diameter code;

sequentially carrying out pipe network adjustment and fitness calculation on the chromosomes in the initial population after encoding to obtain fitness; the function of the fitness calculation is constrained by a third objective function which is based on annual repair cost minimization and a fourth objective function which is based on pipe network reliability performance maximization;

Performing non-dominant sorting and crowding calculation on the chromosomes of which the fitness meets a preset fitness threshold value to obtain a new parent population;

iteratively updating the new parent population;

taking a new father population meeting the preset iteration times as the water supply network restoration scheme;

the first objective function is calculated by the following formula:

；

wherein, As a function of the first objective function,As a first weight coefficient, a first set of weights,Is a second weight coefficient and is more than or equal to 0≤1，0≤≤1，+=1，For the pipeline flow rate to be lower than the economic flow rate,For a set of pipe groups having a velocity below the lower boundary of the economic flow rate,For the pipeline flow rate to be higher than the economic flow rate,For a set of pipe groups with a speed above the upper boundary of the economic speed,Indicating a flow rate below the economic flow rate corresponding to the pipe,Indicating a flow rate corresponding to the pipe higher than the economic flow rate,The flow rate of each section of pipeline is equal to that of the pipeline,For the speed of each segment of tubing,For the collection of all pipes within a region,Is economic speed, namely the economic flow rate of pipelines with different pipe diameters;

Calculating the second objective function by the following formula:

；

wherein, For the second objective function, eta is a third weight coefficient, mu is a fourth weight coefficient, eta is more than or equal to 0 and less than or equal to 1, eta+mu=1; Indicating that the node pressure in the water supply network is lower than the minimum service water pressure; A set of node groups representing a pressure below a minimum service water pressure; representing node flow at a pressure below the minimum service water pressure; indicating that the node pressure in the water supply network is higher than the maximum service water pressure; a set of node groups representing a pressure above a maximum service water pressure; representing node flow at a pressure above the maximum service water pressure; representing the node flow in the water supply network; representing the pressure of any node in the water supply network; Representing the pressure corresponding to the nodes in the different blocks;

calculating the third objective function by the following formula:

；

wherein, For the third objective function, a is a first coefficient, b is a second coefficient, c is a third coefficient, D _k is the diameter of the pipeline k, L _k is the length of the pipeline k, and N is the total number of pipeline groups to be repaired in the region;

calculating the fourth objective function by the following formula:

；

wherein, Q _o is the sum of the flow rates of all the pipe sections in the water supply network for the fourth objective function,For the flow entropy of the node j in the water supply network, n represents the number of pipe sections, and Q _j is the sum of the flow of all the pipes flowing into the node j;

the flow entropy of the node j in the water supply network is calculated by the following formula:

；

Wherein U _j is the set of nodes upstream of node j; q _ij is the flow of the pipeline ij, the flow direction is from the node i to the node j, n represents the pipe section number, and Q _j is the sum of the flow of all the pipelines flowing into the node j;

the fitness calculation is performed by the following formula:

；

2. The water supply network repair method of claim 1, wherein the step of iteratively updating the new parent population comprises:

Carrying out genetic processing on the new parent population to obtain a child population; wherein the genetic manipulation comprises at least one of: selection, crossover and mutation;

Determining a new population based on the new parent population and the offspring population processed by elite retention policies;

Performing the non-dominant ranking and the crowding calculation on the new population;

Updating the new parent population based on the number of layers of the non-dominant ranking and the result of the congestion degree calculation.

3. The water supply network restoration method according to claim 1, wherein the step of pipe network adjustment includes:

Calculating the closing difference of pipe network nodes of the water supply network based on the pipe network data of the water supply network and preset calculation precision; wherein the pipe network data comprises node water pressure;

If the closing difference meets the preset precision, determining the node water pressure as a node target water pressure;

And if the closing difference does not meet the preset precision, adjusting the node water pressure based on the jacobian matrix of the node water pressure until the closing difference meets the preset precision.

4. The water supply network remediation method of claim 1 wherein the non-dominant ordering step includes:

defining a dominance count for each solution and a set of solutions for the dominance of the solution;

Determining a first non-inferior layer by using all the solutions;

The hierarchy is updated based on the dominance count and the solution set of the solution dominance until one of the hierarchy is empty.

5. The water supply network restoration method according to claim 4, wherein the congestion degree calculation is performed based on the following formula:

；

6. A water supply network repair device, comprising:

the model construction module is used for acquiring basic parameters of the water supply network and constructing a topological structure model of the water supply network based on the basic parameters;

the model updating module is used for checking and updating the topological structure model of the water supply network based on the operation data of the water supply network;

The adjusting scheme processing module is used for determining an adjusting scheme of the water supply network based on daily maintenance information and simulated operation condition data of the water supply network;

The initial population processing module is used for respectively bringing the adjustment schemes into a first objective function taking the corresponding pipeline flow rate as an economic flow rate as a constraint target and a second objective function taking a reasonable range of water supply network node pressure as a constraint target for solving, obtaining a plurality of first objective function values and a plurality of second objective function values, sequencing the first objective function values and the second objective function values from small to large, selecting a first objective function value with a preset proportion, taking the adjustment scheme corresponding to the selected first objective function value as a first objective adjustment scheme, selecting a second objective function value with a preset proportion, taking the second objective function value corresponding to the selected second objective function value as a second objective adjustment scheme, and combining the first objective adjustment scheme and the second objective adjustment scheme as an initial population;

The population coding module is used for coding the initial population based on a preset pipe diameter code;

The fitness calculation module is used for sequentially calculating the pipe network adjustment and the fitness of the chromosomes in the encoded initial population to obtain fitness; the function of the fitness calculation is constrained based on a third objective function taking the annual repair cost in the investment period as a constraint target and a fourth objective function taking the pipe network reliability performance maximization as the constraint target;

the new parent population processing module is used for carrying out non-dominant sorting and crowding calculation on the chromosomes of which the fitness meets a preset fitness threshold value to obtain a new parent population;

A new parent population updating module for iteratively updating the new parent population;

the water supply network restoration scheme determining module is used for taking a new parent population meeting preset iteration times as the water supply network restoration scheme

The first objective function is calculated by the following formula:

；

Calculating the second objective function by the following formula:

；

calculating the third objective function by the following formula:

；

calculating the fourth objective function by the following formula:

；

the fitness calculation is performed by the following formula:

；

7. The water supply network repair device according to claim 6, wherein the new parent population updating module is configured to perform genetic processing on the new parent population to obtain a child population; wherein the genetic manipulation comprises at least one of: selection, crossover and mutation; determining a new population based on the new parent population and the offspring population processed by elite retention policies; performing the non-dominant ranking and the crowding calculation on the new population; updating the new parent population based on the number of layers of the non-dominant ranking and the result of the congestion degree calculation.

8. An electronic device comprising a processor and a memory, the memory storing computer executable instructions executable by the processor, the processor executing the computer executable instructions to implement the water supply network restoration method of any one of the preceding claims 1 to 5.

9. A computer storage medium storing computer executable instructions which, when invoked and executed by a processor, cause the processor to implement the water supply network repair method of any one of claims 1 to 5.