Urban water supply network operation performance evaluation method, device, equipment and medium

Abstract

The application relates to a kind of urban water supply network operation performance evaluation method, device, equipment and medium, method includes: water demand time series variation coefficient and second Haixian-William coefficient are input to the water supply network hydraulic model of pre-set and carry out hydraulic, water quality coupling calculation, the operation performance index of independent metering area is quantified, and the long-term operation performance change curve is generated based on the operation performance index of each independent metering area in each operating year;Analysis long-term operation performance change curve, identify the recession critical time node of water supply network in independent metering area, solve water supply network update optimization model, obtain the Pareto optimal non-inferior solution set containing the combination of different pipe replacement scheme and valve layout adjustment scheme in independent metering area, and the pipe network updating scheme suitable for long-term operation of pipe network is screened from the Pareto optimal non-inferior solution set.The application can significantly improve the long-term effectiveness and scientificity of urban water supply network partition management.

Description

Technical Field

[0001] This application relates to the field of water supply networks, and in particular to a method for evaluating the operational performance of urban water supply networks, a corresponding device, electronic equipment, and a computer-readable storage medium. Background Technology

[0002] As a vital urban infrastructure, the primary function of water supply networks is to provide residents with sufficient quantity, quality, and appropriate water pressure. To monitor network leakage in real time and optimize network operating pressure, water companies typically divide the water supply network into several independent metering zones (DMAs) using valves, and install water meters in each zone to measure flow rate, enabling more refined network management. The DMA zoning management strategy for water supply networks helps quantify the distribution of leaking water, thus allowing for targeted leakage control.

[0003] However, the scenarios faced by water supply networks during long-term operation are subject to time-varying and uncertainties. On the one hand, long-term population changes may significantly alter the water demand at various nodes of the network, rendering the network designed for the original population size unsuitable and impacting its performance. On the other hand, the basic components of the system, such as pipe sections, valves, and pumps, inevitably experience aging and corrosion during long-term service. Under these constantly changing circumstances, the water supply network may struggle to maintain normal water quality, quantity, and pressure, and the effectiveness of existing zoned management strategies may be weakened to some extent.

[0004] Previous studies on water supply network zoning management have often focused solely on short-term DMA (Districted Area Management) zoning designs, neglecting the impact of long-term dynamic factors on the network. For example, patent CN120163460A proposes a multi-objective water supply network zoning method that facilitates pressure and metering management while also considering economical retrofitting. Patent CN116542001A employs a genetic algorithm to solve the flow meter and valve placement problem in DMA, achieving the optimal placement scheme by minimizing the number of flow meters and maximizing water demand uniformity.

[0005] Patent CN118710048A provides a decision support method for long-term maintenance of water supply networks based on dynamic risk. From a life-cycle perspective, it simulates pipe wall corrosion, leakage flow, and water pressure changes over time to quantify the probability and consequences of pipeline failures. After obtaining multiple maintenance requirement sequences, a performance evaluation model is established to objectively evaluate the framework's effectiveness. Managers need to select the optimal maintenance sequence from among the many alternatives to formulate the final maintenance plan. However, it focuses more on local decisions during the maintenance phase and has not yet systematically explored the dynamic changes in system performance such as resilience, water quality, and energy consumption during long-term network operation.

[0006] In summary, existing technologies only conduct DMA zoning optimization for short-term operating conditions or formulate local maintenance plans based solely on pipeline failure risk. They do not simultaneously couple dynamic variables such as long-term population water demand evolution and pipeline aging. They cannot fully quantify the time-series changes in resilience, water quality, and energy consumption across multiple dimensions of the pipeline network throughout its entire life cycle. They also cannot generate zoned pipeline network renewal and renovation strategies that take into account hydraulics, water quality, and energy consumption based on the critical nodes of long-term performance degradation of the pipeline network. The applicant has made corresponding explorations to address this problem. Summary of the Invention

[0007] The purpose of this application is to solve the above-mentioned problems by providing a method, corresponding device, electronic equipment and computer-readable storage medium for evaluating the operational performance of urban water supply networks.

[0008] To achieve the various objectives of this application, the following technical solution is adopted:

[0009] A method for evaluating the operational performance of urban water supply networks, proposed to meet one of the purposes of this application, includes:

[0010] The water supply network of the city to be evaluated is divided into multiple independent metering zones. The current water demand and pipeline operating parameters of each independent metering zone in the baseline operating year are collected. The pipeline operating parameters include the first Hay-Williams coefficient of the pipeline and the pipeline diameter. The Hay-Williams coefficient represents the roughness of the pipe wall of the corresponding pipeline.

[0011] For each independent metering zone, the ratio between the future water demand of the independent metering zone in each operating year during the performance evaluation period and the current water demand in the baseline operating year is calculated to obtain the time-series variation coefficient of water demand in each operating year during the performance evaluation period for the independent metering zone.

[0012] For each pipe in the independent metering zone, the Hayzen-Williams coefficient time-varying decay model is used to obtain the second Hayzen-Williams coefficient for each pipe in the independent metering zone in each operating year based on the first Hayzen-Williams coefficient, the pipe diameter, and each operating year.

[0013] The water demand time series variation coefficient and the second Hayzen-Williams coefficient are input into the preset water supply network hydraulic model. Hydraulic and water quality coupling calculations are performed according to the preset time step to quantify the operating performance indicators of the independent metering area. Based on the operating performance indicators of each independent metering area in each operating year, a long-term operating performance variation curve is generated. The operating performance indicators include the network resilience index, the network weighted average water age, and the electricity consumption per thousand tons of water.

[0014] The long-term operational performance change curves are analyzed to identify the critical time nodes for the decline of the water supply network within the independent metering area. Based on the network resilience index, the weighted average water age of the network, and the water and electricity consumption per thousand tons, a water supply network renewal and optimization model corresponding to the independent metering area is constructed. A multi-objective optimization algorithm is used to solve the water supply network renewal and optimization model to obtain a Pareto optimal non-dominated solution set that includes combinations of different pipeline replacement schemes and valve layout adjustment schemes within the independent metering area. From the Pareto optimal non-dominated solution set, a network renewal and renovation scheme suitable for the long-term operation of the network is selected.

[0015] Optionally, the step of determining the future water demand of the independent metering zone for each operating year within the performance evaluation period includes:

[0016] For each independent metering area, historical population time series data, historical economic time series data, historical climate time series data, and historical water demand time series data of the independent metering area are extracted as input features to construct a feature sequence. The feature sequence is divided by a sliding window to determine multiple sets of training samples. The actual water demand of the next historical year corresponding to each sliding window is used as the sample label to train the preset water demand prediction model until convergence.

[0017] Obtain the predicted population data, predicted economic data, and predicted climate data for each operating year within the preset performance evaluation period. Input the current water demand of the independent metering area in the baseline operating year, together with the predicted population data, predicted economic data, and predicted climate data for each operating year, into the trained and converged water demand prediction model, and output the future water demand of the independent metering area for each operating year within the preset performance evaluation period.

[0018] Optionally, the expression for the time-varying decay model of the Hayzen-Williams coefficient is:

[0019] ,

[0020] in, The second Hay-Williams coefficient represents the operating year for each pipeline in an independent metering zone; Represents a fixed empirical coefficient; Indicates the pipe diameter; Indicates any operating year within the performance evaluation period; Indicates the base year of operation. This represents the first Hay-Williams coefficient corresponding to the base year of operation.

[0021] Optionally, the formula for calculating the pipeline network resilience index is as follows:

[0022]

[0023] in, It represents the pipeline resilience index corresponding to a single independent metering area, characterizing the water pressure surplus, water distribution structure, and the ability to guarantee water supply against failure in the independent metering area; Indicates the total number of water usage nodes within an independent metering zone; Indicates the number of independent measurement regions One water usage node; Indicates the number of independent measurement regions The pipe diameter uniformity coefficient of pipes connected to each node; Indicates nodes within an independent metering region The water demand at each node; Indicates nodes within an independent metering region The actual operating head; Indicates nodes within an independent metering region The minimum required head; Indicates the total number of water sources contained within an independent metering zone; Indicates the number of independent measurement regions One water source; Indicates water sources within an independent metering zone The amount of water supplied; Indicates water sources within an independent metering zone The water head at the outlet; This indicates the total number of booster pumps configured within the independent metering area; Indicates the number of independent measurement regions One booster water pump; Indicates the booster pump in the independent metering area Input the electrical power of the zoned pipeline network; It represents the specific weight of water and is used to convert the electrical energy of a water pump into equivalent head energy.

[0024] Uniformity coefficient of pipe diameter connected to nodes The calculation formula is expressed as:

[0025] ,

[0026] in, For the first in the independent measurement region The node degree of a node represents the total number of pipes directly connected to that node; Indicates nodes within an independent metering region The directly adjacent first 1 adjacent node; Within an independent metering area, connecting nodes To adjacent nodes Pipe diameter; Indicates nodes within an independent metering region The largest diameter of all connected pipes.

[0027] Optionally, the formula for calculating the weighted average water age of the pipeline network is:

[0028]

[0029] in, This represents the weighted average water age of the pipeline network in a single independent metering area; This indicates the total number of water demand nodes within an independent metering zone; This indicates the total simulation duration of the performance evaluation cycle; Indicates the number of independent measurement regions One water usage node; Indicates the first time within the performance evaluation period Each time segment corresponds to a simulation moment in a specific running year. ; Indicates the first time within the performance evaluation period The simulation time corresponding to each time segment; Indicates at simulation time The first independent measurement area Instantaneous water demand at each water-using node; Indicates at simulation time The first independent measurement area The instantaneous water age of a water-using node represents the residence time of water from the water source to that node;

[0030] The formula for calculating the electricity consumption per thousand tons of water is as follows:

[0031]

[0032] in, The term "electricity consumption per thousand tons of water" refers to the electrical energy consumed by the water pump to transport one thousand tons of water. The cumulative power consumption of the water pump over a certain time period is expressed in kWh. This represents the cumulative water supply corresponding to the pump within the same statistical period, in units of... .

[0033] Optionally, the steps for constructing a water supply network update and optimization model include:

[0034] Using the node mass conservation equation, pipe segment energy conservation equation, node water pressure upper and lower limits, pipe flow velocity upper and lower limits, and the set of optional pipe diameters as constraints, and with the goal of maximizing the network resilience index, minimizing the network weighted average water age, minimizing the water and electricity consumption per thousand tons, and minimizing the total cost of network renovation, a water supply network renewal and optimization model is constructed.

[0035] Optionally, the water demand prediction model includes a long short-term memory neural network, a limit gradient boosting tree, or an artificial neural network; the multi-objective optimization algorithm includes a non-dominated sorting genetic algorithm or a particle swarm optimization algorithm.

[0036] A device for evaluating the operational performance of an urban water supply network, provided for another purpose of this application, comprises:

[0037] The data acquisition module is configured to divide the water supply network of the city to be evaluated into multiple independent metering zones, and collect the current water demand and pipeline operating parameters of each independent metering zone in the baseline operating year. The pipeline operating parameters include the first Hay-Williams coefficient of the pipeline and the pipeline diameter. The Hay-Williams coefficient represents the roughness of the pipe wall of the corresponding pipeline.

[0038] The water demand change determination module is configured to calculate, for each independent metering zone, the ratio between the future water demand of the independent metering zone in each operating year within the performance evaluation period and the current water demand in the baseline operating year, thereby obtaining the water demand time series change coefficient of the independent metering zone in each operating year within the performance evaluation period.

[0039] The pipe wall roughness determination module is configured to use the Hayzen-Williams coefficient time-varying decay model to obtain the second Hayzen-Williams coefficient for each pipe in the independent metering area in each operating year based on the first Hayzen-Williams coefficient, pipe diameter, and each operating year.

[0040] The performance change determination module is configured to input the water demand time-series change coefficient and the second Hay-Williams coefficient into a preset water supply network hydraulic model, perform hydraulic and water quality coupling calculations according to a preset time step, quantify the operating performance indicators of the independent metering area, and generate a long-term operating performance change curve based on the operating performance indicators of each independent metering area in each operating year. The operating performance indicators include the network resilience index, the network weighted average water age, and the electricity consumption per thousand tons of water.

[0041] The pipeline network renewal and optimization module is configured to analyze the long-term operational performance change curve, identify the critical time node of the water supply network degradation in the independent metering area, construct a water supply network renewal and optimization model corresponding to the independent metering area based on the pipeline network resilience index, the weighted average water age of the pipeline network, and the water and electricity consumption per thousand tons, solve the water supply network renewal and optimization model using a multi-objective optimization algorithm, obtain a Pareto optimal non-dominated solution set including combinations of different pipeline replacement schemes and valve layout adjustment schemes in the independent metering area, and select pipeline network renewal and renovation schemes suitable for long-term operation of the pipeline network from the Pareto optimal non-dominated solution set.

[0042] An electronic device provided for another purpose of this application includes a central processing unit and a memory, the central processing unit being configured to invoke and run a computer program stored in the memory to perform the steps of the urban water supply network operation performance evaluation method of this application.

[0043] A computer-readable storage medium is provided for another purpose of this application, which stores, in the form of computer-readable instructions, a computer program implemented according to the urban water supply network operation performance evaluation method, which, when called by a computer, executes the steps included in the corresponding method.

[0044] Compared to existing technologies, this application addresses the shortcomings of existing technologies, which only conduct DMA zoning optimization for short-term operating conditions or formulate local maintenance plans based solely on pipeline failure risk. These technologies fail to simultaneously couple dynamic variables such as long-term population water demand evolution and pipeline aging, thus failing to fully quantify the time-series changes in resilience, water quality, and energy consumption across the entire pipeline network's lifecycle. Furthermore, they cannot generate zoning pipeline network upgrade and renovation strategies that consider hydraulics, water quality, and energy consumption based on critical nodes of long-term performance degradation. This application offers, but is not limited to, the following beneficial effects:

[0045] Firstly, this application divides the urban pipe network into independent metering zones and collects basic parameters such as baseline water demand and initial Hayson-Williams coefficients for the pipelines. On the one hand, it predicts the future water demand of each zone year by year through a water demand prediction model and calculates the time-series variation coefficient of water demand. On the other hand, it updates the Hayson-Williams coefficients of the pipelines year by year using a time-varying decay model of the Hayson-Williams coefficient, simultaneously coupling two long-term dynamic variables: population water consumption changes and pipeline corrosion and scaling. This application completes hydraulic and water quality coupling annual simulations for decades of performance evaluation cycle with each zone as a unit. It can fully depict the long-term evolution of the pipe network's resilience, water quality, and energy consumption in each independent metering zone, accurately generate the zone's exclusive long-term operating performance change curves, and truly restore the service status of the pipe network throughout its entire life cycle.

[0046] Secondly, this application can quantitatively identify critical nodes of performance degradation in zoned pipe networks. The timing of renovation can be determined by relying on the pipe network resilience index, weighted average water age, and time series index curves of water and electricity consumption per thousand tons obtained from annual simulations. It can intuitively identify the critical time nodes of degradation in the hydraulic reliability, water quality, and energy consumption of pipe networks in independent metering areas, changing the previous method of relying solely on the probability of pipe corrosion failure to determine the timing of maintenance. It accurately locates the time nodes when pipe networks need intervention and renewal from the comprehensive dimensions of hydraulic safety, water quality safety, and operational energy consumption, providing objective data support for phased renovation of pipe networks.

[0047] Thirdly, this application takes maximizing the pipeline resilience index, minimizing the weighted average water age and electricity consumption per thousand tons of water, and minimizing the total cost of pipeline renovation as optimization objectives. Combining engineering constraints such as hydraulic conservation, water pressure, flow velocity, and standard pipe diameter, it constructs a water supply pipeline renewal optimization model corresponding to an independent metering area. Through a multi-objective optimization algorithm, it obtains a Pareto optimal non-dominated solution set that includes combinations of pipeline replacement and valve layout adjustment. Compared with existing technologies that only focus on the optimization of local pipeline maintenance sequences, this application simultaneously considers long-term water supply reliability, water quality assurance, energy conservation and consumption reduction, and engineering renovation costs, forming a complete set of renovation alternatives with multi-dimensional trade-offs. Water management personnel can select renewal strategies that are suitable for the long-term operating conditions of the area based on the actual operation and maintenance needs of the area.

[0048] Furthermore, this application quantitatively demonstrates the long-term service performance evolution trend of the zonal pipe network under the combined effects of long-term population changes and pipeline aging, and outputs phased pipeline replacement and valve adjustment implementation plans. This can help water managers intuitively grasp the long-term operational shortcomings of the DMA zonal pipe network, scientifically formulate annual pipe network renewal and renovation plans, and significantly improve the long-term effectiveness and scientific nature of urban water supply network zonal management. Attached Figure Description

[0049] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0050] Figure 1 This is a flowchart illustrating the method for evaluating the operational performance of urban water supply networks in this application.

[0051] Figure 2 This is a long-term variation curve of the pipeline network resilience index in the independent metering area in the embodiments of this application;

[0052] Figure 3 This is a long-term variation curve of the weighted average water age of the pipeline network in the independent metering area in the embodiments of this application;

[0053] Figure 4 This is a long-term variation curve of the water and electricity consumption per thousand tons in the independent metering area in the embodiments of this application.

[0054] Figure 5 This is a schematic diagram of the annual pipeline renewal layout for the long-term operating conditions of the independent metering area in this application embodiment;

[0055] Figure 6 This is a schematic block diagram of the urban water supply network operation performance evaluation device in the embodiments of this application;

[0056] Figure 7 This is a schematic diagram of the structure of the computer device in the embodiments of this application. Detailed Implementation

[0057] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0058] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0059] Those skilled in the art will understand that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0060] Those skilled in the art will understand that the terms "client," "terminal," and "terminal device" as used herein include both devices that receive wireless signals, devices that only possess wireless signal receiver capabilities without transmission capabilities, and devices with receiving and transmitting hardware, devices that have receiving and transmitting hardware capable of bidirectional communication over a bidirectional communication link. Such devices may include: cellular or other communication devices such as personal computers or tablets, having single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service) that can combine voice, data processing, fax, and / or data communication capabilities; PDAs (Personal Digital Assistants) that may include radio frequency receivers, pagers, internet / intranet access, web browsers, notebooks, calendars, and / or GPS (Global Positioning System) receivers; and conventional laptops and / or handheld computers or other devices that have and / or include radio frequency receivers. As used herein, "client," "terminal," and "terminal device" can be portable, transportable, installed in a means of transportation (air, sea, and / or land), or suitable and / or configured to operate locally and / or in a distributed manner, operating in any other location on Earth and / or in space. "Client," "terminal," and "terminal device" as used herein can also be a communication terminal, an internet access terminal, or a music / video playback terminal, such as a PDA, a MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or a smart TV, set-top box, etc.

[0061] The hardware referred to by the names "server," "client," and "service node" in this application is essentially an electronic device with the equivalent capabilities of a personal computer. It is a hardware device with the necessary components revealed by the von Neumann architecture, such as a central processing unit (including an arithmetic logic unit and a control unit), memory, input devices, and output devices. The computer program is stored in its memory, and the central processing unit loads the program stored in the secondary storage into the main memory to run it, execute the instructions in the program, and interact with the input and output devices to complete specific functions.

[0062] It should be noted that the concept of "server" used in this application can also be extended to the case of server clusters. Based on the network deployment principles understood by those skilled in the art, the servers should be logically divided. Physically, these servers can be independent of each other but accessible through interfaces, or they can be integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method in this application.

[0063] One or more of the technical features of this application, unless explicitly specified herein, can be deployed on a server and accessed by a client remotely calling the online service interface provided by the server, or can be directly deployed and run on a client for access.

[0064] Unless otherwise specified, the neural network models referenced or potentially referenced in this application may be deployed on a remote server and invoked remotely on the client, or deployed on a client with the capability to invoke directly. In some embodiments, when running on the client, the corresponding intelligence may be acquired through transfer learning in order to reduce the requirements on the client's hardware resources and avoid excessive consumption of the client's hardware resources.

[0065] Unless otherwise specified, all data involved in this application may be stored remotely on a server or on a local terminal device, as long as it is suitable for use by the technical solution of this application.

[0066] Those skilled in the art will understand that although the various methods in this application are described based on the same concept and thus present commonality among them, they can be performed independently unless otherwise specified. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept; therefore, concepts expressed in the same way, as well as concepts that are appropriately changed for convenience but are expressed differently, should be understood equivalently.

[0067] Unless otherwise expressly stated, the various embodiments disclosed in this application can be combined in a cross-cutting manner to flexibly construct new embodiments, as long as such combination does not depart from the inventive spirit of this application and can meet the needs of the prior art or solve a certain deficiency in the prior art. Those skilled in the art should be aware of such modifications.

[0068] Please see Figure 1 In one embodiment of the urban water supply network operation performance evaluation method of this application, the method includes:

[0069] Step S10: Divide the water supply network of the city to be evaluated into multiple independent metering zones, and collect the current water demand and pipeline operating parameters of each independent metering zone in the baseline operating year. The pipeline operating parameters include the first Hay-Williams coefficient of the pipeline and the pipeline diameter. The Hay-Williams coefficient represents the roughness of the pipe wall of the corresponding pipeline.

[0070] The urban water supply network operation performance evaluation system in the terminal equipment can divide the water supply network of the city to be evaluated into multiple independent metering zones, collect the current water demand and pipeline operation parameters of each independent metering zone in the baseline operating year. The pipeline operation parameters include the first Hayson-Williams coefficient and the pipeline diameter. The Hayson-Williams coefficient represents the roughness of the corresponding pipeline wall. The larger the value, the smoother the pipe wall and the smaller the water flow friction head loss. The longer the pipeline is used and the more serious the scaling and corrosion, the lower the coefficient will be.

[0071] Step S20: For each independent metering zone, calculate and determine the ratio between the future water demand of the independent metering zone in each operating year during the performance evaluation period and the current water demand in the baseline operating year, and obtain the time series variation coefficient of water demand in each operating year of the independent metering zone during the performance evaluation period.

[0072] The water supply network of the city to be evaluated is divided into multiple independent metering zones. After collecting the current water demand and pipeline operating parameters of each independent metering zone in the baseline operating year, the ratio between the future water demand of the independent metering zone in each operating year within the performance evaluation period and the current water demand in the baseline operating year is calculated for each independent metering zone. The time-series variation coefficient of water demand in each operating year within the performance evaluation period is obtained. The time-series variation coefficient of water demand is used to characterize the water load change factor of the independent metering zone in each operating year within the performance evaluation period relative to the baseline operating year.

[0073] In some embodiments, the step of determining the future water demand of the independent metering zone for each operating year within a performance evaluation period includes:

[0074] Step S201: For each independent metering area, extract historical population time-series data, historical economic time-series data, historical climate time-series data, and historical water demand time-series data of the independent metering area as input features to construct a feature sequence. Divide the feature sequence by a sliding window to determine multiple sets of training samples, and use the actual water demand of the next historical year corresponding to each sliding window as the sample label to train the preset water demand prediction model to a convergent state. The water demand prediction model includes a long short-term memory neural network, a limit gradient boosting tree, or an artificial neural network.

[0075] Step S202: Obtain the predicted population data, predicted economic data, and predicted climate data for each operating year within the preset performance evaluation period. Input the current water demand of the independent metering area in the benchmark operating year, together with the predicted population data, predicted economic data, and predicted climate data for each operating year, into the trained and converged water demand prediction model, and output the future water demand of the independent metering area for each operating year within the preset performance evaluation period.

[0076] Specifically, for each independent metering zone, various types of historical time-series data are collected, including historical population time-series data, historical economic time-series data, historical climate time-series data, and historical water demand time-series data. At the same time, the predicted population data, predicted economic data, and predicted climate data for each operating year within the preset performance evaluation period are obtained as inputs for the model inference stage.

[0077] The historical population time series, historical economic time series, historical climate time series, and historical water demand time series of the independent metering area are used as input features to form a complete feature sequence. The feature sequence is segmented by segment using a sliding window to generate multiple sets of training samples. The actual water demand of the partition corresponding to the next historical year of each sliding window is set as the sample label to construct a supervised learning training dataset.

[0078] Multiple machine learning methods, including Extreme Gradient Boosting Tree (XGBoost), linear regression, Long Short-Term Memory (LSTM) neural network, and Artificial Neural Network (ANN), were used to perform regression fitting on the training dataset. The model performance evaluation indicators, such as R² (coefficient of determination), RMSE (root mean square error), MAE (mean absolute error), and MAPE (mean absolute percentage error), were calculated for each model. The model with the best matching degree with the historical water use time series of this independent metering area was selected by comparison. The model was continuously trained iteratively until the model converged. The optimal converged model was used as the water demand prediction model for this area.

[0079] The system retrieves the predicted population, economy, and climate data for each operating year within a preset performance evaluation period. It then inputs the current water demand of the independent metering zone in the baseline operating year, along with the predicted population, economy, and climate data for each year, into a training and converged optimal water demand prediction model. The model outputs the future water demand for each operating year within the performance evaluation period for that independent metering zone. For each operating year, the system calculates the ratio between the future water demand of the independent metering zone in each operating year within the performance evaluation period and the current water demand in the baseline operating year. This yields the time-series variation coefficient of water demand for the independent metering zone in each operating year within the performance evaluation period, which is used for subsequent hydraulic and water quality coupled simulation calculations of the pipeline network.

[0080] Step S30: For each pipe in the independent metering area, the Hayzen-Williams coefficient time-varying decay model is used to obtain the second Hayzen-Williams coefficient for each pipe in the independent metering area in each operating year based on the first Hayzen-Williams coefficient, the pipe diameter, and each operating year.

[0081] For each independent metering zone, the ratio between the future water demand of the independent metering zone in each operating year during the performance evaluation period and the current water demand in the baseline operating year is calculated and determined. After obtaining the time-series variation coefficient of water demand in each operating year of the independent metering zone during the performance evaluation period, for each pipeline in the independent metering zone, the Hayzen-Williams coefficient time-varying decay model is used to obtain the second Hayzen-Williams coefficient for each pipeline in the independent metering zone in each operating year based on the first Hayzen-Williams coefficient, the pipeline diameter, and each operating year.

[0082] In some embodiments, the expression for the Hayzen-Williams coefficient time-varying decay model is:

[0083] ,

[0084] in, The second Hay-Williams coefficient represents the operating year for each pipeline in an independent metering zone; Represents a fixed empirical coefficient; Indicates the pipe diameter; Indicates any operating year within the performance evaluation period; Indicates the base year of operation. This represents the first Hay-Williams coefficient corresponding to the base year of operation.

[0085] The aforementioned Hayzen-Williams coefficient time-varying decay model is used to quantify the time-series calculation model of the long-term operation and aging of water supply pipelines and the gradual deterioration of pipe wall roughness. It is specifically used to calculate the Hayzen-Williams coefficient of a single pipeline in an independent metering area after aging in each year of the performance evaluation cycle, providing dynamic hydraulic parameters for subsequent annual hydraulic and water quality coupled simulation, and solving the shortcomings of traditional static pipe network simulation that does not consider the annual scaling and corrosion of pipelines and has low accuracy.

[0086] Step S40: Input the water demand time series variation coefficient and the second Hayzen-Williams coefficient into the preset water supply network hydraulic model, perform hydraulic and water quality coupling calculations according to the preset time step, quantify the operating performance indicators of the independent metering area, and generate long-term operating performance change curves based on the operating performance indicators of each independent metering area in each operating year. The operating performance indicators include the network resilience index, the network weighted average water age, and the electricity consumption per thousand tons of water.

[0087] For each pipeline in the independent metering zone, a Hayzen-Williams coefficient time-varying decay model is used to obtain the second Hayzen-Williams coefficient for each pipeline in each operating year based on the first Hayzen-Williams coefficient, pipeline diameter, and operating years. Then, the water demand time-series variation coefficient and the second Hayzen-Williams coefficient are input into a preset water supply network hydraulic model. Hydraulic and water quality coupling calculations are performed according to a preset time step to quantify the operating performance indicators of the independent metering zone. Based on the operating performance indicators of each independent metering zone in each operating year, a long-term operating performance change curve is generated. The operating performance indicators include the network resilience index, the network weighted average water age, and the electricity consumption per thousand tons of water.

[0088] In some embodiments, taking an independent metering zone as a unit, the water demand time-series variation coefficient and the second Hayzen-Williams coefficient are synchronously embedded into the hydraulic model of the water supply network of the corresponding independent metering zone. Hydraulic and water quality coupling calculations are carried out according to a preset time step, and the three core operational performance indicators of the independent metering zone in each operating year within the performance evaluation period are quantified year by year. Based on the annual operational performance indicators, a long-term operational performance change curve of the independent metering zone is plotted. The operational performance indicators include the network resilience index (NRI), the network weighted average water age, and the power consumption per thousand tons of water. The network resilience index (NRI) is a hydraulic reliability index used to characterize the surplus water supply energy of the network system and the fault resistance capability of the water distribution topology. The network weighted average water age is a water quality characterization index used to quantify the overall retention time of water in the zone and reflect the risk of water aging in the network. The power consumption per thousand tons of water is an energy efficiency index used to measure the level of power utilization of water pumps in the zoned water supply system.

[0089] In some embodiments, the formula for calculating the pipeline resilience index is expressed as:

[0090]

[0091] in, It represents the pipeline resilience index corresponding to a single independent metering area, characterizing the water pressure surplus, water distribution structure, and the ability to guarantee water supply against failure in the independent metering area; Indicates the total number of water usage nodes within an independent metering zone; Indicates the number of independent measurement regions One water usage node; Indicates the number of independent measurement regions The pipe diameter uniformity coefficient of pipes connected to each node; Indicates nodes within an independent metering region The water demand at each node; Indicates nodes within an independent metering region The actual operating head; Indicates nodes within an independent metering region The minimum required head; Indicates the total number of water sources contained within an independent metering zone; Indicates the number of independent measurement regions One water source; Indicates water sources within an independent metering zone The amount of water supplied; Indicates water sources within an independent metering zone The water head at the outlet;

[0092] This indicates the total number of booster pumps configured within the independent metering area; Indicates the number of independent measurement regions One booster water pump; Indicates the booster pump in the independent metering area Input the electrical power of the zoned pipeline network; It represents the specific weight of water and is used to convert the electrical energy of a water pump into equivalent head energy.

[0093] In some embodiments, the uniformity coefficient of pipe diameter connected to nodes The calculation formula is expressed as:

[0094] ,

[0095] in, For the first in the independent measurement region The node degree of a node represents the total number of pipes directly connected to that node; Indicates nodes within an independent metering region The directly adjacent first 1 adjacent node; Within an independent metering area, connecting nodes To adjacent nodes Pipe diameter; Indicates nodes within an independent metering region The largest diameter of all connected pipes.

[0096] In some embodiments, the formula for calculating the weighted average water age of the pipeline network is:

[0097]

[0098] in, This represents the weighted average water age of the pipeline network in a single independent metering area; This indicates the total number of water demand nodes within an independent metering zone; This indicates the total simulation duration of the performance evaluation cycle; Indicates the number of independent measurement regions One water usage node; Indicates the first time within the performance evaluation period Each time segment corresponds to a simulation moment in a specific running year. ; Indicates the first time within the performance evaluation period The simulation time corresponding to each time segment; Indicates at simulation time The first independent measurement area Instantaneous water demand at each water-using node; Indicates at simulation time The first independent measurement area The instantaneous water age of a water-using node represents the residence time of water from the water source to that node;

[0099] The formula for calculating the electricity consumption per thousand tons of water is as follows:

[0100]

[0101] in, The term "electricity consumption per thousand tons of water" refers to the electrical energy consumed by the water pump to transport one thousand tons of water. The cumulative power consumption of the water pump over a certain time period is expressed in kWh. This represents the cumulative water supply corresponding to the pump within the same statistical period, in units of... .

[0102] Specifically, please refer to Figures 2 to 4 The predicted long-term population change pattern, including the time-series variation coefficient of water demand and the second Hay-Williams coefficient, was applied to a specific water supply network hydraulic model, C-Town. During the selected long-term study period (2025-2100), the network performance was evaluated every 5 years, resulting in 16 sets of data on the network's performance indicators for each 5-year period. Based on this, a long-term performance change curve for the network was plotted.

[0103] Step S50: Analyze the long-term operating performance change curve, identify the critical time node of the water supply network decline in the independent metering area, construct the water supply network renewal and optimization model corresponding to the independent metering area based on the network resilience index, the weighted average water age of the network, and the water and electricity consumption per thousand tons, and use a multi-objective optimization algorithm to solve the water supply network renewal and optimization model to obtain a Pareto optimal non-dominated solution set that includes different pipeline replacement schemes and valve layout adjustment schemes in the independent metering area. Select a network renewal and renovation scheme suitable for long-term operation of the network from the Pareto optimal non-dominated solution set.

[0104] The time-series variation coefficient of water demand and the second Hayzen-Williams coefficient are input into a preset water supply network hydraulic model. Hydraulic and water quality coupling calculations are performed at preset time steps to quantify the operational performance indicators of the independent metering area. Based on the operational performance indicators of each independent metering area in each operating year, long-term operational performance variation curves are generated. These operational performance indicators include the network resilience index, the weighted average water age of the network, and the water and electricity consumption per thousand tons. The long-term operational performance variation curves are then analyzed to identify the critical time nodes for the decline of the water supply network within the independent metering area. Based on the network resilience index, the weighted average water age of the network, and the water and electricity consumption per thousand tons, a water supply network renewal and optimization model corresponding to the independent metering area is constructed. A multi-objective optimization algorithm is used to solve the water supply network renewal and optimization model, obtaining a Pareto optimal non-dominated solution set that includes combinations of different pipeline replacement schemes and valve layout adjustment schemes within the independent metering area. From the Pareto optimal non-dominated solution set, a network renewal and renovation scheme suitable for long-term network operation is selected. The multi-objective optimization algorithm includes a non-dominated sorting genetic algorithm or a particle swarm optimization algorithm.

[0105] In some embodiments, the step of constructing a water supply network update and optimization model includes:

[0106] Using the node mass conservation equation, pipe segment energy conservation equation, node water pressure upper and lower limits, pipe flow velocity upper and lower limits, and the set of optional pipe diameters as constraints, and with the goal of maximizing the network resilience index, minimizing the network weighted average water age, minimizing the water and electricity consumption per thousand tons, and minimizing the total cost of network renovation, a water supply network renewal and optimization model is constructed.

[0107] Specifically, the objective function of the water supply network update and optimization model is expressed as:

[0108]

[0109] in, The primary optimization objective is to maximize the pipeline network resilience index. It represents the pipeline resilience index corresponding to a single independent metering area, characterizing the water pressure surplus, water distribution structure, and the ability to guarantee water supply against failure in the independent metering area; This indicates the second optimization objective: minimizing the weighted average water age of the pipeline network. It represents the weighted average water age of a single independent metering area network. The smaller the value, the shorter the water retention time in the network and the lower the risk of water quality deterioration. The third optimization objective is to minimize the electricity consumption per thousand tons of water. This indicates the energy consumption per thousand tons of water. The smaller the value, the lower the energy consumption of the zone pumps and the higher the energy utilization efficiency. The fourth optimization objective is to minimize the total cost of pipeline network renovation. This indicates the total number of pipelines to be upgraded within the independent metering zone; This represents the j-th pipeline to be modified within the independent metering zone; Indicates the selected pipe diameter At that time, the cost of modification and construction of pipelines per unit length, and the cost of pipe materials; Indicates the first The actual length of the root canal; This represents the total cost of all pipeline renovations; the lower the project cost, the better.

[0110]

[0111] in, Indicates the first in the pipeline network One water usage node; Representation and Node All directly connected pipes The associated set constituted; This indicates that all access nodes The pipeline is traversed and summed. For pipelines Water flow rate inside; For nodes The user's water demand; Indicates pipeline The starting node; Indicates pipeline The endpoint; For pipelines starting node The node head; The endpoint of pipe j The node head; For pipelines Head loss along the route; This indicates the final selected pipe diameter for the j-th pipe to be modified; This represents the set of available pipe diameters for the project; This indicates a set of national standard pipe diameters available for purchase in the market; during optimization, pipe diameters can only be selected from this set. Represents a node Actual operating water head; This indicates the minimum allowable water head at the nodes as required by the specifications, ensuring normal water supply for users on the most unfavorable floors; This indicates the maximum head allowed at a node in the pipeline network to prevent overpressure-induced pipe bursts and network damage. For pipelines The actual operating velocity of the internal water body; This indicates the minimum allowable flow velocity in the pipeline, preventing excessively low flow velocities from causing sediment deposition and deteriorating water quality. This indicates the maximum allowable flow velocity in the pipeline, to prevent excessive flow velocity from causing water hammer, pipeline erosion and wear, and excessive noise.

[0112] In a further embodiment, this embodiment uses the Non-Dominated Sorting Genetic Algorithm (NSGA-II) to solve the water supply network update and optimization model for an independent metering area, which does not constitute any limitation on this application. Specifically, for the water supply network of a single independent metering area, the Non-Dominated Sorting Genetic Algorithm (NSGA-II) is called, and algorithm hyperparameters such as population size, maximum number of iterations, crossover probability, and mutation probability are pre-configured, and an initial population is randomly generated; each individual in the population corresponds to a set of network update and renovation schemes specific to that independent metering area. For each renovation scheme, the EPANET network hydraulic model is called to carry out hydraulic and water quality coupled simulation calculations, solve the four objective function values ​​corresponding to the scheme, and at the same time verify whether the scheme violates the node mass conservation equation, pipe segment energy conservation equation, node water pressure upper and lower limits, pipe flow velocity upper and lower limits, and engineering optional pipe diameter and other engineering constraints. Selecting eligible parent individuals and performing crossover and mutation genetic operations generates a new offspring population, corresponding to new combinations of pipe diameter replacement and valve layout adjustments. The four objective function values ​​for the offspring individuals are then recalculated. The parent and offspring populations are merged and subjected to rapid non-dominated sorting to eliminate completely dominated inferior solutions. High-quality individuals are then retained and truncated according to a preset population size, entering the next iteration cycle. This iteration is repeated until the maximum number of iterations is reached or the algorithm converges. After the algorithm terminates, all non-dominated solutions from the final iteration layer are retained to form the Pareto front, outputting the Pareto optimal non-dominated solution set for the independent metering region. Each non-dominated solution in the set represents a feasible renovation plan with different trade-offs among four indicators: network resilience index, network weighted average water age, per thousand tons of water and electricity consumption, and total network renovation cost. Each plan includes complete combination information specifying the renovation year, pipe replacement location and corresponding pipe diameter, and valve layout adjustment method. Water supply management departments, based on the actual engineering operation and maintenance preferences of the area, select the optimal network renovation plan suitable for the long-term operation of the zone.

[0113] This application does not limit itself to using the non-dominated sorting genetic algorithm (NSGA-II), but may also use other multi-objective optimization algorithms such as particle swarm optimization to solve the model.

[0114] In some embodiments, please refer to Figure 5 To visually present the optimal upgrade and renovation plan for the pipeline network at different time points, i.e., to determine the pipelines that need to be replaced at different time points, this embodiment draws the pipeline sections that need to be updated in the water supply network hydraulic model C-Town in several specific years.

[0115] As can be seen from the above embodiments, compared with the prior art, the present application addresses the shortcomings of the prior art, which only conducts DMA zoning optimization for short-term operating conditions or formulates local maintenance plans based solely on the single dimension of pipeline failure risk. It fails to simultaneously couple dynamic variables such as long-term population water demand evolution and pipeline aging, and cannot fully quantify the time-series changes in resilience, water quality, and energy consumption across the entire life cycle of the pipeline network. Furthermore, it cannot generate a zoning pipeline network upgrade and renovation strategy that takes into account hydraulics, water quality, and energy consumption based on the critical nodes of long-term performance degradation. The present application includes, but is not limited to, the following beneficial effects:

[0116] Firstly, this application divides the urban pipe network into independent metering zones and collects basic parameters such as baseline water demand and initial Hayson-Williams coefficients for the pipelines. On the one hand, it predicts the future water demand of each zone year by year through a water demand prediction model and calculates the time-series variation coefficient of water demand. On the other hand, it updates the Hayson-Williams coefficients of the pipelines year by year using a time-varying decay model of the Hayson-Williams coefficient, simultaneously coupling two long-term dynamic variables: population water consumption changes and pipeline corrosion and scaling. This application completes hydraulic and water quality coupling annual simulations for decades of performance evaluation cycle with each zone as a unit. It can fully depict the long-term evolution of the pipe network's resilience, water quality, and energy consumption in each independent metering zone, accurately generate the zone's exclusive long-term operating performance change curves, and truly restore the service status of the pipe network throughout its entire life cycle.

[0117] Secondly, this application can quantitatively identify critical nodes of performance degradation in zoned pipe networks. The timing of renovation can be determined by relying on the pipe network resilience index, weighted average water age, and time series index curves of water and electricity consumption per thousand tons obtained from annual simulations. It can intuitively identify the critical time nodes of degradation in the hydraulic reliability, water quality, and energy consumption of pipe networks in independent metering areas, changing the previous method of relying solely on the probability of pipe corrosion failure to determine the timing of maintenance. It accurately locates the time nodes when pipe networks need intervention and renewal from the comprehensive dimensions of hydraulic safety, water quality safety, and operational energy consumption, providing objective data support for phased renovation of pipe networks.

[0118] Thirdly, this application takes maximizing the pipeline resilience index, minimizing the weighted average water age and electricity consumption per thousand tons of water, and minimizing the total cost of pipeline renovation as optimization objectives. Combining engineering constraints such as hydraulic conservation, water pressure, flow velocity, and standard pipe diameter, it constructs a water supply pipeline renewal optimization model corresponding to an independent metering area. Through a multi-objective optimization algorithm, it obtains a Pareto optimal non-dominated solution set that includes combinations of pipeline replacement and valve layout adjustment. Compared with existing technologies that only focus on the optimization of local pipeline maintenance sequences, this application simultaneously considers long-term water supply reliability, water quality assurance, energy conservation and consumption reduction, and engineering renovation costs, forming a complete set of renovation alternatives with multi-dimensional trade-offs. Water management personnel can select renewal strategies that are suitable for the long-term operating conditions of the area based on the actual operation and maintenance needs of the area.

[0119] Furthermore, this application quantitatively demonstrates the long-term service performance evolution trend of the zonal pipe network under the combined effects of long-term population changes and pipeline aging, and outputs phased pipeline replacement and valve adjustment implementation plans. This can help water managers intuitively grasp the long-term operational shortcomings of the DMA zonal pipe network, scientifically formulate annual pipe network renewal and renovation plans, and significantly improve the long-term effectiveness and scientific nature of urban water supply network zonal management.

[0120] Please see Figure 6 A device for evaluating the operational performance of an urban water supply network, provided for one of the purposes of this application, includes: The data acquisition module 1100 is configured to divide the water supply network of the city to be evaluated into multiple independent metering zones, and collect the current water demand and pipeline operating parameters of each independent metering zone in the baseline operating year. The pipeline operating parameters include the first Hayson-Williams coefficient and the pipe diameter, whereby the Hayson-Williams coefficient characterizes the pipe wall roughness. The water demand change determination module 1200 is configured to calculate, for each independent metering zone, the ratio between the future water demand of that independent metering zone in each operating year within the performance evaluation period and the current water demand in the baseline operating year, thus obtaining the time-series change coefficient of the water demand for each operating year within the performance evaluation period. The pipe wall roughness determination module 1300 is configured to, for each pipe in the independent metering zone, use a Hayson-Williams coefficient time-varying decay model based on the first Hayson-Williams coefficient, pipe diameter, and operating years to obtain the second Hayson-Williams coefficient for each pipe in each operating year. The performance change determination module 1400 is configured to... To input the time-series variation coefficient of water demand and the second Hay-Williams coefficient into a preset water supply network hydraulic model, hydraulic and water quality coupling calculations are performed at a preset time step to quantify the operational performance indicators of the independent metering area. Based on the operational performance indicators of each independent metering area in each operating year, a long-term operational performance variation curve is generated. The operational performance indicators include the network resilience index, the network weighted average water age, and the water and electricity consumption per thousand tons. The network renewal and optimization module 1500 is configured to analyze the long-term operational performance variation curve, identify the critical time node of the water supply network's decline within the independent metering area, and construct a water supply network renewal and optimization model corresponding to the independent metering area based on the network resilience index, the network weighted average water age, and the water and electricity consumption per thousand tons. A multi-objective optimization algorithm is used to solve the water supply network renewal and optimization model to obtain a Pareto optimal non-dominated solution set containing combinations of different pipeline replacement schemes and valve layout adjustment schemes within the independent metering area. From the Pareto optimal non-dominated solution set, a network renewal and renovation scheme suitable for long-term network operation is selected.

[0121] Based on any embodiment of this application, please refer to Figure 7Another embodiment of this application also provides an electronic device, which can be implemented by a computer device, such as... Figure 7 The diagram shows the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. The computer-readable storage medium stores an operating system, a database, and computer-readable instructions. The database may store a sequence of control information. When executed by the processor, the computer-readable instructions enable the processor to implement a method for evaluating the operational performance of an urban water supply network. The processor provides computational and control capabilities to support the operation of the entire computer device. The memory stores computer-readable instructions, which, when executed by the processor, enable the processor to execute the urban water supply network operational performance evaluation method of this application. The network interface of the computer device is used for communication with a terminal. Those skilled in the art will understand that… Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0122] In this embodiment, the processor is used to execute... Figure 6 The specific functions of each module are defined within the device, and the memory stores the program code and various data required to execute these modules. A network interface is used for data transmission between the user terminal and the server. In this embodiment, the memory stores the program code and data required to execute all modules in the urban water supply network operation performance evaluation device of this application, and the server can call the server's program code and data to execute the functions of all modules.

[0123] This application also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the urban water supply network operation performance evaluation method described in any embodiment of this application.

[0124] This application also provides a computer program product, including a computer program / instructions that, when executed by one or more processors, implement the steps of the urban water supply network operation performance evaluation method described in any embodiment of this application.

[0125] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0126] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for evaluating the operational performance of urban water supply networks, characterized in that, include: The water supply network of the city to be evaluated is divided into multiple independent metering zones. The current water demand and pipeline operating parameters of each independent metering zone in the baseline operating year are collected. The pipeline operating parameters include the first Hay-Williams coefficient of the pipeline and the pipeline diameter. The Hay-Williams coefficient represents the roughness of the pipe wall of the corresponding pipeline. For each independent metering zone, the ratio between the future water demand of the independent metering zone in each operating year during the performance evaluation period and the current water demand in the baseline operating year is calculated to obtain the time-series variation coefficient of water demand in each operating year during the performance evaluation period for the independent metering zone. For each pipe in the independent metering zone, the Hayzen-Williams coefficient time-varying decay model is used to obtain the second Hayzen-Williams coefficient for each pipe in the independent metering zone in each operating year based on the first Hayzen-Williams coefficient, the pipe diameter, and each operating year. The water demand time series variation coefficient and the second Hayzen-Williams coefficient are input into the preset water supply network hydraulic model. Hydraulic and water quality coupling calculations are performed according to the preset time step to quantify the operating performance indicators of the independent metering area. Based on the operating performance indicators of each independent metering area in each operating year, a long-term operating performance variation curve is generated. The operating performance indicators include the network resilience index, the network weighted average water age, and the electricity consumption per thousand tons of water. The long-term operational performance change curves are analyzed to identify the critical time nodes for the decline of the water supply network within the independent metering area. Based on the network resilience index, the weighted average water age of the network, and the water and electricity consumption per thousand tons, a water supply network renewal and optimization model corresponding to the independent metering area is constructed. A multi-objective optimization algorithm is used to solve the water supply network renewal and optimization model to obtain a Pareto optimal non-dominated solution set that includes combinations of different pipeline replacement schemes and valve layout adjustment schemes within the independent metering area. From the Pareto optimal non-dominated solution set, a network renewal and renovation scheme suitable for the long-term operation of the network is selected.

2. The method for evaluating the operational performance of urban water supply networks according to claim 1, characterized in that, The steps for determining the future water demand of the independent metering zone for each operating year within the performance evaluation period include: For each independent metering area, historical population time series data, historical economic time series data, historical climate time series data, and historical water demand time series data of the independent metering area are extracted as input features to construct a feature sequence. The feature sequence is divided by a sliding window to determine multiple sets of training samples. The actual water demand of the next historical year corresponding to each sliding window is used as the sample label to train the preset water demand prediction model until convergence. Obtain the predicted population data, predicted economic data, and predicted climate data for each operating year within the preset performance evaluation period. Input the current water demand of the independent metering area in the baseline operating year, together with the predicted population data, predicted economic data, and predicted climate data for each operating year, into the trained and converged water demand prediction model, and output the future water demand of the independent metering area for each operating year within the preset performance evaluation period.

3. The method for evaluating the operational performance of urban water supply networks according to claim 1, characterized in that, The expression for the time-varying decay model of the Hayzen-Williams coefficient is: ， in, The second Hay-Williams coefficient represents the operating year for each pipeline in an independent metering zone; Represents a fixed empirical coefficient; Indicates the pipe diameter; Indicates any operating year within the performance evaluation period; Indicates the base year of operation. This represents the first Hay-Williams coefficient corresponding to the base year of operation.

4. The method for evaluating the operational performance of urban water supply networks according to claim 1, characterized in that, The formula for calculating the pipeline resilience index is as follows: in, It represents the pipeline resilience index corresponding to a single independent metering area, characterizing the water pressure surplus, water distribution structure, and the ability to guarantee water supply against failure in the independent metering area; Indicates the total number of water usage nodes within an independent metering zone; Indicates the number of independent measurement regions One water usage node; Indicates the number of independent measurement regions The pipe diameter uniformity coefficient of pipes connected to each node; Indicates nodes within an independent metering region The water demand at each node; Indicates nodes within an independent metering region The actual operating head; Indicates nodes within an independent metering region The minimum required head; Indicates the total number of water sources contained within an independent metering zone; Indicates the number of independent measurement regions One water source; Indicates water sources within an independent metering zone The amount of water supplied; Indicates water sources within an independent metering zone The water head at the outlet; This indicates the total number of booster pumps configured within the independent metering area; Indicates the number of independent measurement regions One booster water pump; Indicates the pressurized water pump in the independent metering area Input the electrical power of the zoned pipeline network; It represents the specific weight of water and is used to convert the electrical energy of a water pump into equivalent head energy. Uniformity coefficient of pipe diameter connected to nodes The calculation formula is expressed as: ， in, For the first in the independent measurement region The node degree of a node represents the total number of pipes directly connected to that node; Indicates nodes within an independent metering region The directly adjacent first 1 adjacent node; Within an independent metering area, connecting nodes To adjacent nodes Pipe diameter; Indicates nodes within an independent metering region The largest diameter of all connected pipes.

5. The method for evaluating the operational performance of urban water supply networks according to claim 1, characterized in that, The formula for calculating the weighted average water age of the pipeline network is as follows: in, This represents the weighted average water age of the pipeline network in a single independent metering area; This indicates the total number of water demand nodes within an independent metering zone; This indicates the total simulation duration of the performance evaluation cycle; Indicates the number of independent measurement regions One water usage node; Indicates the first time within the performance evaluation period Each time segment corresponds to a simulation moment in a specific running year. ; Indicates the first time within the performance evaluation period The simulation time corresponding to each time segment; Indicates at simulation time The first independent measurement area Instantaneous water demand at each water-using node; Indicates at simulation time The first independent measurement area The instantaneous water age of a water-using node represents the residence time of water from the water source to that node; The formula for calculating the electricity consumption per thousand tons of water is as follows: in, The term "electricity consumption per thousand tons of water" refers to the electrical energy consumed by the water pump to transport one thousand tons of water. The cumulative power consumption of the water pump over a certain time period is expressed in kWh. This represents the cumulative water supply corresponding to the pump within the same statistical period, in units of... .

6. The method for evaluating the operational performance of urban water supply networks according to claim 1, characterized in that, The steps for constructing a water supply network update and optimization model include: Using the node mass conservation equation, pipe segment energy conservation equation, node water pressure upper and lower limits, pipe flow velocity upper and lower limits, and the set of optional pipe diameters as constraints, and with the goal of maximizing the network resilience index, minimizing the network weighted average water age, minimizing the water and electricity consumption per thousand tons, and minimizing the total cost of network renovation, a water supply network renewal and optimization model is constructed.

7. The method for evaluating the operational performance of urban water supply networks according to claim 1 or 2, characterized in that, The water demand prediction model includes a long short-term memory neural network, a limit gradient boosting tree, or an artificial neural network; the multi-objective optimization algorithm includes a non-dominated sorting genetic algorithm or a particle swarm optimization algorithm.

8. A device for evaluating the operational performance of an urban water supply network, characterized in that, include: The data acquisition module is configured to divide the water supply network of the city to be evaluated into multiple independent metering zones, and collect the current water demand and pipeline operating parameters of each independent metering zone in the baseline operating year. The pipeline operating parameters include the first Hay-Williams coefficient of the pipeline and the pipeline diameter. The Hay-Williams coefficient represents the roughness of the pipe wall of the corresponding pipeline. The water demand change determination module is configured to calculate, for each independent metering zone, the ratio between the future water demand of the independent metering zone in each operating year within the performance evaluation period and the current water demand in the baseline operating year, thereby obtaining the water demand time series change coefficient of the independent metering zone in each operating year within the performance evaluation period. The pipe wall roughness determination module is configured to use the Hayzen-Williams coefficient time-varying decay model to obtain the second Hayzen-Williams coefficient for each pipe in the independent metering area in each operating year based on the first Hayzen-Williams coefficient, pipe diameter, and each operating year. The performance change determination module is configured to input the water demand time-series change coefficient and the second Hay-Williams coefficient into a preset water supply network hydraulic model, perform hydraulic and water quality coupling calculations according to a preset time step, quantify the operating performance indicators of the independent metering area, and generate a long-term operating performance change curve based on the operating performance indicators of each independent metering area in each operating year. The operating performance indicators include the network resilience index, the network weighted average water age, and the electricity consumption per thousand tons of water. The pipeline network renewal and optimization module is configured to analyze the long-term operational performance change curve, identify the critical time node of the water supply network degradation in the independent metering area, construct a water supply network renewal and optimization model corresponding to the independent metering area based on the pipeline network resilience index, the weighted average water age of the pipeline network, and the water and electricity consumption per thousand tons, solve the water supply network renewal and optimization model using a multi-objective optimization algorithm, obtain a Pareto optimal non-dominated solution set including combinations of different pipeline replacement schemes and valve layout adjustment schemes in the independent metering area, and select pipeline network renewal and renovation schemes suitable for long-term operation of the pipeline network from the Pareto optimal non-dominated solution set.

9. An electronic device comprising a central processing unit and a memory, characterized in that, The central processing unit is used to invoke and run a computer program stored in the memory to perform the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores, in the form of computer-readable instructions, a computer program implemented according to any one of claims 1 to 7, which, when invoked by a computer, executes the steps included in the corresponding method.

Images