A water supply scheduling planning method for a residential area, a medium and equipment

Abstract

The application discloses a kind of resident aggregation area's water supply scheduling planning method, medium and equipment, method includes: the basic water supply data of adjacent water source is collected, and basic water supply data is generated by preprocessing;Using constraint shortest path algorithm generates alternative scheduling route meeting pipe material pressure limit and construction period constraint, and calculates its comprehensive cost weight;Extract water supply mutation characteristics by time domain analysis, establish response strategy library containing typical water supply abnormal scene;Build multi-source collaborative scheduling and emergency switching optimization decision model;Establish the characteristic mapping relationship of benchmark water supply working condition and emergency water supply mode;Finally, build multi-dimensional water supply scheduling knowledge base containing water source characteristics, pipe network topology, scheduling strategy and emergency response.The application improves the response speed of water supply system to emergency, realizes the dynamic optimization scheduling of water supply system, enhances the stability of multi-source collaborative scheduling, improves the emergency response efficiency and system reliability.

Description

Technical Field

[0001] This invention relates to the field of water supply system optimization and scheduling technology, and in particular to a water supply scheduling planning method, medium and equipment for residential areas. Background Technology

[0002] Residential water supply scheduling is a crucial aspect of urban infrastructure management, its core being the dynamic balance between water supply and user demand. Currently, water supply systems primarily rely on fixed pipeline topologies and pre-defined scheduling rules, facing numerous challenges in practical applications. Fluctuations in water quality, seasonal water consumption variations, and aging pipelines make traditional static model-based scheduling methods ill-suited to complex and ever-changing operating environments. Especially in responding to emergencies such as water pollution or pipeline bursts, manual intervention is often required to develop emergency plans, significantly limiting response efficiency. Regarding path optimization, conventional methods often focus on finding the optimal solution for a single objective, lacking comprehensive consideration of multiple factors such as construction feasibility, operational energy consumption, and system reliability. Furthermore, the coordinated scheduling between different water sources lacks an effective dynamic decision-making mechanism, potentially leading to pressure fluctuations or water quality mixing issues when switching water supply routes. With the expansion of urban scale and the diversification of water demand, establishing a more intelligent and flexible water supply scheduling system has become a pressing technical challenge for the water supply industry. Summary of the Invention

[0003] In view of this, the purpose of this invention is to propose a water supply scheduling planning method, medium and equipment for residential areas, which realizes intelligent collaborative scheduling of the water supply system through multi-source data fusion and dynamic optimization decision-making, and solves the problems of delayed response and insufficient risk resistance of water supply scheduling.

[0004] To achieve the aforementioned technical objectives, in a first aspect, this application provides a water supply scheduling and planning method for residential areas, comprising:

[0005] Collect basic water supply data from nearby water sources, including water quality parameters, available water volume, water transmission network topology information, and construction access conditions.

[0006] The basic water supply data is preprocessed to obtain the optimized scheduling input data, which includes the water quality compliance assessment results, dynamic water supply capacity curves, and a set of feasible construction paths.

[0007] Based on the set of feasible construction paths, the constrained shortest path algorithm is used to generate alternative scheduling routes. The alternative scheduling routes must meet the pressure limit of pipe materials and the construction period constraint. The comprehensive cost weight of each alternative scheduling route is calculated. The comprehensive cost weight includes water transmission energy consumption, construction and modification costs and emergency redundancy.

[0008] Time-domain analysis of dynamic water supply capacity curves is performed to extract water supply mutation characteristics and establish a response strategy library containing typical water supply anomaly scenarios. Typical water supply anomaly scenarios include at least one of sudden pollution, equipment failure, and demand peak.

[0009] Based on the water quality compliance assessment results, alternative scheduling routes, water supply change characteristics, and response strategy database, an optimized decision-making model for multi-source coordinated scheduling and emergency switching is constructed.

[0010] Based on the optimized decision-making model, a characteristic mapping relationship between the benchmark water supply condition and the emergency water supply mode is established. The characteristic mapping relationship includes the pressure fluctuation transfer function, the water quality mixing prediction matrix, and the construction interference compensation coefficient.

[0011] The alternative scheduling routes, water supply mutation characteristics, response strategy library, optimization decision model and feature mapping relationship are stored in a structured manner to build a multi-dimensional water supply scheduling knowledge base that includes water source characteristics, pipeline topology, scheduling strategies and emergency response.

[0012] In some embodiments, basic water supply data is preprocessed to obtain optimized scheduling input data. The optimized scheduling input data includes water quality compliance assessment results, dynamic water supply capacity curves, and a set of feasible construction paths, including:

[0013] A multi-indicator weighted evaluation of water source water quality parameters is conducted to generate water quality compliance evaluation results. The multi-indicator weighted evaluation includes at least one of heavy metal content, turbidity, and residual chlorine concentration, and a compliance matrix of multiple indicators with preset water use standards is established.

[0014] Based on available water volume and water transmission network topology information, a hydraulic transient model is used to calculate dynamic water supply capacity curves under different operating conditions. The dynamic water supply capacity curve includes at least one of the following: maximum water supply, pressure fluctuation range, and critical switching time.

[0015] Based on the construction access conditions, a three-dimensional geographic constraint model is constructed. The three-dimensional geographic constraint model integrates road excavation restrictions, existing pipeline distribution and geological survey data. An improved Dijkstra algorithm is used to search for K feasible construction paths in the constraint space to form a set of feasible construction paths.

[0016] The results of water quality compliance assessment, dynamic water supply capacity curves, and sets of feasible construction paths are spatiotemporally aligned to generate standardized and optimized scheduling input data.

[0017] In some embodiments, based on a set of feasible construction paths, a constrained shortest path algorithm is used to generate alternative scheduling routes. These alternative routes must meet pipe pressure limits and construction period constraints, including:

[0018] Establish a multi-dimensional path evaluation model, which includes at least one of hydraulic performance indicators, construction feasibility indicators, and economic indicators, and construct a correlation matrix between hydraulic performance indicators, construction feasibility indicators, economic indicators, and engineering constraints.

[0019] Based on the set of feasible construction paths, the hydraulic characteristic parameters of each path are calculated using a pressure-flow coupling algorithm. The hydraulic characteristic parameters include at least one of the following: steady-state water supply, transient pressure fluctuation value, and water hammer risk level.

[0020] Based on the pressure-bearing limits of pipe materials, a pressure safety assessment model is established. The pressure safety assessment model integrates the pipe strength coefficient, the peak operating pressure, and the safety margin threshold to generate a set of pressure compliance paths.

[0021] In conjunction with construction period constraints, a spatiotemporal conflict detection model is constructed. The spatiotemporal conflict detection model integrates construction machinery scheduling plan, traffic control period and resident impact assessment, and outputs a set of feasible paths for the construction period.

[0022] A multi-objective optimization algorithm is used to jointly solve the set of pressure-compliant paths and the set of feasible paths for the project period, generating the Pareto optimal alternative scheduling route set, which includes multiple alternative scheduling routes.

[0023] In some embodiments, a comprehensive cost weight is calculated for each alternative scheduling route. The comprehensive cost weight includes water conveyance energy consumption, construction and modification costs, and emergency redundancy, including:

[0024] Perform the following operations for each alternative scheduling route:

[0025] The energy consumption value of the drainage route of the alternative scheduling route is calculated and expressed by formula (1), which is as follows:

[0026] ;

[0027] In formula (1), For the first The water conveyance energy consumption value of each alternative dispatch route. For the first The coefficient of friction of the pipe section For the first The length of the pipe section For the first Design flow rate of the pipe section For the density of water, Standard gravitational acceleration, For the first The elevation difference of the alternative dispatch routes;

[0028] The construction and modification costs of the alternative scheduling routes are calculated using formula (2), which is as follows:

[0029] ;

[0030] In formula (2), For the first The construction and modification costs of one alternative dispatch route, For the first Pipe material costs for one alternative dispatch route, For the first Construction costs for one alternative dispatch route, For the first Road repair costs for one alternative dispatch route;

[0031] The emergency redundancy of the alternative scheduling routes is calculated using formula (3), which is as follows:

[0032] ;

[0033] In formula (3), For the first Emergency redundancy of alternative dispatch routes, As the first weighting coefficient, This refers to the number of standby pumping stations. This is the second weighting coefficient. To quickly switch the number of valves, The third weighting coefficient, For emergency water reserves;

[0034] The overall cost weight of the alternative scheduling routes is calculated using formula (4), which is as follows:

[0035] ;

[0036] In formula (4), This is the weighting coefficient for hydrophobic energy consumption value. This is the weighting coefficient for construction and renovation costs. This is the inverse weighting coefficient for emergency redundancy. ,and ;

[0037] Repeat the above steps until the comprehensive cost weight of all candidate scheduling routes has been calculated, and then map and store the comprehensive cost weight with the candidate scheduling paths.

[0038] Furthermore, the alternative scheduling paths are sorted from highest to lowest according to their overall cost weight.

[0039] In some embodiments, time-domain analysis is performed on the dynamic water supply capacity curve to extract water supply abrupt change characteristics and establish a response strategy library containing typical water supply anomaly scenarios, including:

[0040] Perform spectral analysis and waveform decomposition on the dynamic water supply capacity curve to identify at least one of the following characteristics: sudden change point in water supply pressure, sudden drop point in flow rate, and abnormal point in water quality parameters.

[0041] Based on the identification results, water supply anomalies are classified into three levels: Level 1, Level 2, and Level 3. Level 1 anomalies are configured as main water supply pipeline failures, Level 2 anomalies as local pipeline leaks, and Level 3 anomalies as sudden increases in water demand.

[0042] Establish a database of typical water supply anomaly scenarios, including main pump station shutdown, pipeline rupture, and peak water usage scenarios;

[0043] Develop response strategies for each typical water supply anomaly scenario, including:

[0044] In the event of a main pumping station shutdown, start the backup pumping station and adjust the opening of the pipeline valves;

[0045] In the event of a pipe burst, shut off the nearest valve and activate the emergency water supply truck;

[0046] For peak water usage scenarios, adjust the reservoir's water release and start the booster pump set;

[0047] The abnormal water supply characteristics, abnormality level classification, typical abnormal water supply scenarios, and response strategies are linked and stored to form a response strategy library.

[0048] In some embodiments, an optimized decision-making model for multi-source coordinated scheduling and emergency switching is constructed based on water quality compliance assessment results, alternative scheduling routes, water supply mutation characteristics, and a response strategy library, including:

[0049] A hydraulic-water quality coupled calculation model is established, which is expressed by formula (5), as follows:

[0050] ;

[0051] In formula (5), For the pressure measurement section water head, The component of gravitational acceleration, The inlet flow rate of the pipe section. This refers to the outlet flow rate of the pipe section. For source terms, For water quality concentration, Where is the diffusion coefficient. The spatial second derivative of water concentration. For the flow rate of the pipe section, The cross-sectional area of ​​the pipe. For water quality concentration gradient, The water quality reaction rate constant;

[0052] The hydraulic-water quality coupled calculation model is solved to obtain multiple solution results, and each solution result corresponds to a scheduling decision under a certain working condition.

[0053] The scheduling decisions are screened using the finite state machine principle combined with the characteristics of sudden changes in water supply. The selected scheduling decisions are denoted as the screening decisions. The screening conditions are defined, including:

[0054] when In such cases, switch to the emergency dispatch plan;

[0055] when When necessary, switch to the hybrid control scheme;

[0056] when When necessary, switch to the boost scheduling scheme;

[0057] Multiple screening decisions are used to generate a multi-level buffer control strategy, which is expressed by formula (6):

[0058] ;

[0059] In formula (6), This refers to the valve opening adjustment amount. This is the proportional control coefficient. For head deviation, The integral control coefficient, For the historical head deviation integral variable, These are the differential control coefficients;

[0060] That is, to generate an optimal decision model.

[0061] In some embodiments, based on an optimized decision-making model, a characteristic mapping relationship between the baseline water supply condition and the emergency water supply mode is established. This characteristic mapping relationship includes a pressure fluctuation transfer function, a water quality mixing prediction matrix, and a construction disturbance compensation coefficient, including:

[0062] Hydraulic modeling is performed on the baseline water supply conditions, and pressure fluctuation characteristic parameters are extracted. The pressure fluctuation characteristic parameters include at least one of the dominant frequency amplitude, attenuation rate, and propagation speed.

[0063] The pressure fluctuation transfer function is established and expressed by formula (7), which is as follows:

[0064] ;

[0065] In formula (7), Let be the transfer function for pressure fluctuations. Let Laplace be a complex variable. The base of the natural logarithm, Due to the time delay of pressure wave propagation, For systematic time constants, For the Laplace transform of the input pressure disturbance, The Laplace transform of the output pressure response;

[0066] A water quality mixing prediction matrix is ​​constructed, which is expressed by formula (8), as follows:

[0067] ;

[0068] In formula (8), For the first The first section of the pipe Mixed transfer function of water quality parameters;

[0069] The construction interference compensation coefficient is constructed and expressed by formula (9), which is as follows:

[0070] ;

[0071] In formula (9), This is the construction interference compensation coefficient. It is the fourth weighting coefficient. for Construction interference index;

[0072] The pressure fluctuation transfer function, water quality mixing prediction matrix, and construction disturbance compensation coefficient are integrated to obtain the mapping characteristic relationship, which is expressed by formula (10), as follows:

[0073] ;

[0074] In formula (10), For pressure domain, For water quality zone, For the traffic domain, To adjust the flow rate, This is the baseline flow rate.

[0075] In some embodiments, alternative scheduling routes, water supply mutation characteristics, response strategy library, optimization decision model, and feature mapping relationships are structured and stored to construct a multi-dimensional water supply scheduling knowledge base containing water source characteristics, pipeline topology, scheduling strategies, and emergency responses, including:

[0076] Perform topology coding on the alternative scheduling routes to generate a route feature description set that includes path node sequence, pipeline characteristic parameters and switching constraints;

[0077] Water supply mutation characteristics are classified and stored according to anomaly type. A mutation characteristic database containing pressure mutation mode, flow mutation mode and water quality mutation mode is established. Each mutation mode is associated with the corresponding time-frequency characteristic parameters and trigger threshold.

[0078] The response strategy library is organized hierarchically to form a hierarchical response strategy tree;

[0079] The optimization decision-making model is decomposed into three sub-libraries: model parameter set, constraint set, and solution algorithm set. The model parameter set includes hydraulic calculation parameters, water quality simulation parameters, and economic evaluation parameters.

[0080] A multi-dimensional index is constructed on the feature mapping relationship to form a pressure-water quality-flow collaborative mapping relationship network, which supports multi-dimensional retrieval by working condition type, anomaly level and construction stage;

[0081] An update mechanism for a multi-dimensional water supply scheduling knowledge base based on spatiotemporal characteristics is established, including timed updates, event-triggered updates, and incremental updates. Timed updates are configured to refresh basic data according to a preset cycle. Event-triggered updates are configured to initiate a comprehensive update when a major pipeline renovation or water source change occurs. Incremental updates are configured to record the execution effect of scheduling decisions in real time and perform local optimizations.

[0082] In a second aspect, the present invention also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the method described in the first aspect.

[0083] In a third aspect, the present invention also provides an electronic device including a memory and a processor, the memory being used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0084] By adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art:

[0085] This invention provides a method, medium, and equipment for water supply scheduling planning in densely populated residential areas. The method includes: collecting water quality parameters, available water volume, water transmission network topology information, and construction access conditions from nearby water sources; preprocessing to generate water quality compliance assessment results, dynamic water supply capacity curves, and a set of feasible construction paths; using a constrained shortest path algorithm to generate alternative scheduling routes that meet pipe pressure limits and construction period constraints, and calculating a comprehensive cost weight including water transmission energy consumption, construction and renovation costs, and emergency redundancy; extracting water supply mutation characteristics through time-domain analysis, and establishing a response strategy library for typical water supply anomaly scenarios such as sudden pollution, equipment failure, and peak demand; constructing an optimized decision-making model for multi-source collaborative scheduling and emergency switching; establishing a feature mapping relationship between baseline water supply conditions and emergency water supply modes; and finally constructing a multi-dimensional water supply scheduling knowledge base including water source characteristics, network topology, scheduling strategies, and emergency responses. This invention significantly improves the response speed of the water supply system to emergencies, effectively reduces the risk of network pressure fluctuations, realizes dynamic optimization scheduling of the water supply system, enhances the stability of multi-source collaborative scheduling, and improves emergency response efficiency and system reliability. Attached Figure Description

[0086] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0087] Figure 1 This is a flowchart illustrating steps S101 to S107 of the planning method described in the specific implementation.

[0088] Figure 2 This is a flowchart illustrating steps S201 to S204 of the planning method described in the specific implementation.

[0089] Figure 3 This is a schematic diagram of the structure of the electronic device described in a specific embodiment.

[0090] The reference numerals used in the above figures are explained as follows:

[0091] 1. Electronic equipment;

[0092] 11. Memory;

[0093] 12. Processor. Detailed Implementation

[0094] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the invention. Similarly, the following embodiments are only some, not all, embodiments of the present invention, and all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0095] Please see Figure 1 In a first aspect, this embodiment provides a water supply scheduling and planning method for residential areas, including:

[0096] S101. Collect basic water supply data from nearby water sources. The basic water supply data includes water quality parameters of the water source, available water volume, water transmission network topology information, and construction access conditions.

[0097] S102. Preprocess the basic water supply data to obtain optimized scheduling input data, which includes water quality compliance assessment results, dynamic water supply capacity curves, and a set of feasible construction paths.

[0098] S103. Based on the set of feasible construction paths, the constrained shortest path algorithm is used to generate alternative scheduling routes. The alternative scheduling routes must meet the pressure limit of pipe materials and the construction period constraint. The comprehensive cost weight of each alternative scheduling route is calculated. The comprehensive cost weight includes water transmission energy consumption, construction and modification costs and emergency redundancy.

[0099] S104. Perform time-domain analysis on the dynamic water supply capacity curve, extract the characteristics of sudden water supply changes, and establish a response strategy library containing typical water supply anomaly scenarios. Typical water supply anomaly scenarios include at least one of sudden pollution, equipment failure, and demand peak.

[0100] S105. Based on the water quality compliance assessment results, alternative scheduling routes, water supply change characteristics, and response strategy library, construct an optimized decision-making model for multi-source coordinated scheduling and emergency switching.

[0101] S106. Based on the optimization decision-making model, establish the characteristic mapping relationship between the benchmark water supply condition and the emergency water supply mode. The characteristic mapping relationship includes the pressure fluctuation transfer function, the water quality mixing prediction matrix and the construction interference compensation coefficient.

[0102] S107. Structure and store alternative scheduling routes, water supply mutation characteristics, response strategy library, optimization decision model and feature mapping relationship to build a multi-dimensional water supply scheduling knowledge base that includes water source characteristics, pipeline topology, scheduling strategy and emergency response.

[0103] In step S101, basic water supply data from nearby water sources constitutes the original input for water supply scheduling planning. Among them, water quality parameters of the water source are obtained through online monitoring equipment, including key indicators such as turbidity, residual chlorine, and pH value. The monitoring frequency of these indicators can be dynamically adjusted according to seasonal changes, such as increasing the sampling rate during the flood season to cope with the risk of water quality fluctuations. Available water volume is collected in real time through the flow meter at the water source, representing the total amount of currently dispatchable water resources. Furthermore, meteorological forecast data can be introduced to assist in predicting the water volume change trend in the next 72 hours. The topology information of the water transmission pipeline network comes from the GIS system database, recording the pipeline connection relationship and spatial distribution, and specially marking old pipe sections and key nodes to prioritize key areas. Construction access conditions are determined through engineering surveys, including factors such as pipeline interface specifications and construction space constraints. Among them, interface compatibility assessment uses three-dimensional scanning technology to achieve millimeter-level precision matching.

[0104] In the preprocessing process of step S102, the water quality compliance assessment results are obtained by comparing water quality parameters with national standard limits. Preferably, fuzzy logic is introduced to handle boundary value cases, and a verification and testing process is initiated when a certain indicator reaches a critical value. The dynamic water supply capacity curve is generated by fitting historical water consumption data. Preferably, time series decomposition technology is used to separate trend terms, periodic terms, and random terms, thereby more accurately reflecting the changing patterns of water supply demand in different time periods. The set of feasible construction paths is screened based on pipeline topology and construction conditions. Preferably, augmented reality technology is introduced to conduct virtual pipe laying simulation and visualize the feasibility of the paths. Furthermore, the preprocessing process adopts adaptive data cleaning and feature extraction technology to implement intelligent repair based on clustering for abnormal data, ensuring the integrity and usability of the input data.

[0105] In step S103, the constrained shortest path algorithm operates based on the set of feasible construction paths. Pipe pressure limits are determined according to pipe material and service life, and the remaining strength coefficient of the pipe wall can be dynamically updated using acoustic wave detection data. Construction period constraints are derived from project schedule requirements, and critical path analysis is introduced to identify bottleneck processes. In the calculation of comprehensive cost weights, optionally, water transmission energy consumption is estimated using a pipeline hydraulic model, with model parameters maintained in sync with actual operating conditions using an online calibration mechanism. Construction and renovation costs are calculated based on project budget quotas and dynamically adjusted using material price indices. Emergency redundancy is assessed based on backup path coverage. This step achieves a multi-dimensional balance between project feasibility and economic efficiency.

[0106] In the time-domain analysis of step S104, water supply mutation characteristics can be identified using an improved sliding window algorithm. The window size is adaptively adjusted according to the signal frequency band characteristics, effectively capturing abnormal patterns at different time scales. Optionally, the response strategy library is constructed using a hybrid intelligent method. Sudden pollution scenarios correspond to water source switching strategies, and an integrated water quality diffusion model predicts the arrival time of the pollution front. Equipment failure scenarios enable a fault tree-based intelligent diagnostic scheme, automatically generating disposal suggestions including spare parts inventory information. Peak demand scenarios trigger tiered pressurization scheduling measures, with pressure adjustment ranges set according to user sensitivity zones. Furthermore, the judgment threshold for typical water supply anomaly scenarios employs transfer learning technology, extracting empirical values ​​from historical data of similar areas for localized calibration.

[0107] In step S105, preferably, the optimization decision model is constructed using an improved multi-objective programming method, wherein the water quality compliance assessment results are transformed into constraint weights through the analytic hierarchy process; a reliability assessment module is introduced into the alternative scheduling routes to calculate the Monte Carlo simulation of the path failure probability; the water supply mutation characteristics are triggered by the event-driven engine to switch strategies; the response strategy library adopts a hybrid mechanism of case reasoning and rule reasoning, and the new strategies are automatically archived after being verified through online trial operation.

[0108] In the feature mapping relationship established in step S106, preferably, the pressure fluctuation transfer function is constructed using a system identification method, and the dynamic characteristics of the pipeline network are obtained through impulse response tests; the water quality mixing prediction matrix is ​​introduced into computational fluid dynamics simulation to simulate the material diffusion process under different mixing ratios; the construction interference compensation coefficient establishes a dynamic evaluation model based on a Bayesian network, and the prediction accuracy is updated in real time by absorbing construction monitoring data.

[0109] In step S107, the multidimensional water supply scheduling knowledge base is stored using a spatiotemporal graph database. This database includes water source characteristics such as water quality fingerprint maps and ecological flow thresholds; pipeline health scores and remaining life predictions for pipeline network topology maintenance; performance degradation curves and applicable condition metadata for scheduling strategies; and a failure mode library and exercise records for emergency response management plans. Furthermore, the multidimensional water supply scheduling knowledge base achieves autonomous strategy evolution through a reinforcement learning mechanism. When a strategy execution deviation exceeds the tolerance limit, a knowledge reconstruction process is automatically triggered.

[0110] This embodiment establishes a multi-dimensional data foundation encompassing water quality, water quantity, pipeline network, and construction conditions. After intelligent preprocessing, it generates optimized scheduling input data. Subsequently, through constraint optimization and feature analysis, it forms alternative solutions that balance engineering feasibility and economy. Finally, it constructs a self-learning knowledge base to enable continuous strategy evolution. By using intelligent sensing and digital twin technology to construct a dynamic mirror of the water supply system, it injects adaptive learning capabilities into traditional optimization methods, forming a smart decision-making system with metabolic update characteristics. For example, when a rainstorm warning is triggered, the system automatically activates the flood control plan, assesses the impact range of emergency projects through the construction interference compensation coefficient, adjusts the water storage strategy in advance based on the dynamic water supply capacity curve, and ultimately generates a composite scheduling instruction that includes a temporary pressurization plan and the timing of backup water source switching. This solution enables the water supply system to leap from passive response to active defense, significantly improving the system's response speed to abnormal scenarios such as sudden pollution and equipment failure. It effectively controls the risk of pipeline pressure fluctuations through feature mapping relationships such as pressure fluctuation transfer function and water quality mixing prediction matrix. Relying on the reinforcement learning mechanism of multi-dimensional water supply scheduling knowledge base, it realizes the dynamic optimization of scheduling strategy, enhances the stability of multi-source collaborative supply and the reliability of emergency switching, and provides intelligent protection for water supply safety in densely populated residential areas.

[0111] Please see Figure 2 In some embodiments, basic water supply data is preprocessed to obtain optimized scheduling input data. This optimized scheduling input data includes water quality compliance assessment results, dynamic water supply capacity curves, and a set of feasible construction paths, including:

[0112] S201. Conduct a multi-indicator weighted evaluation of water source water quality parameters to generate water quality compliance evaluation results. The multi-indicator weighted evaluation includes at least one of heavy metal content, turbidity, and residual chlorine concentration, and establish a compliance matrix of multiple indicators with preset water use standards.

[0113] S202. Based on available water volume and water transmission network topology information, use a hydraulic transient model to calculate dynamic water supply capacity curves under different operating conditions. The dynamic water supply capacity curve includes at least one of the following: maximum water supply volume, pressure fluctuation range, and critical switching time.

[0114] S203. Based on the construction access conditions, a three-dimensional geographic constraint model is constructed. The three-dimensional geographic constraint model integrates road excavation restrictions, existing pipeline distribution and geological survey data. An improved Dijkstra algorithm is used to search for K feasible construction paths in the constraint space to form a set of feasible construction paths.

[0115] S204. Spatiotemporal alignment processing is performed on the water quality compliance assessment results, dynamic water supply capacity curves, and set of feasible construction paths to generate standardized optimized scheduling input data.

[0116] In step S201, the water quality compliance assessment results are the basis for decision-making through a systematic evaluation of source water quality parameters. Key indicators such as heavy metal content, turbidity, and residual chlorine concentration are acquired in real time through online monitoring equipment. The compliance matrix is ​​constructed by comparing the measured values ​​of each indicator with the national drinking water hygiene standard limits in multiple dimensions. Preferably, the multi-indicator weighted assessment uses the analytic hierarchy process (AHP) to determine the weight of each parameter. When an indicator reaches a critical threshold, a verification mechanism is automatically triggered to ensure the reliability of the assessment results. Furthermore, a dynamic adjustment mechanism is introduced to set the critical threshold, automatically tightening the allowable fluctuation range of heavy metal content during flood season or peak industrial discharge periods. A seasonal correction coefficient is established to make the assessment standards more closely reflect actual environmental changes. This adaptive assessment system can effectively identify potential water quality risk inflection points and provide more accurate early warning signals for subsequent scheduling decisions.

[0117] In step S202, the dynamic water supply capacity curve is monitoring data reflecting the changes in pipeline water supply parameters over time, characterizing the water conveyance performance of the pipeline system. It can be acquired in real time through pressure sensors, flow meters, and water quality probes. The maximum water supply is calculated and determined based on pipe diameter and pump station capacity. The pressure fluctuation range is captured by transient analysis to mitigate the impact of water hammer, and the critical switching time is estimated based on the propagation speed of pipeline pressure waves. Preferably, the model parameters are calibrated using historical operating data to ensure that the curve reflects the dynamic characteristics of the actual system. Furthermore, the boundary conditions of the hydraulic model incorporate a machine learning prediction module. By analyzing external factors such as meteorological data and user water usage patterns, it predicts the future 24-hour pipeline load change trend, enabling the dynamic water supply capacity curve to have short-term predictive capabilities. This forward-looking modeling method can significantly improve the system's response to peak water usage periods, providing data support for preventative scheduling.

[0118] In step S203, the three-dimensional geographic constraint model is a digital engineering environment that integrates spatial constraints. Road excavation restrictions can be set based on municipal planning data, existing pipeline distribution comes from an underground pipeline database, and geological survey data includes soil bearing capacity and groundwater level information. The improved Dijkstra algorithm operates in the constrained space, introducing obstacle penalty factors and construction cost weights to select K feasible paths from the topological network that meet the engineering requirements. Preferably, path feasibility is verified through virtual construction simulation to ensure the practical operability of the solution. Furthermore, a construction risk quantification assessment module can be introduced during the algorithm optimization process to automatically increase the safety redundancy coefficient in areas with dense underground pipeline intersections. At the same time, the path selection strategy is dynamically adjusted in conjunction with the operating radius of construction machinery to minimize the risk of construction accidents while ensuring the economy of the path.

[0119] In step S204, spatiotemporal alignment is a key step in achieving multi-source information fusion through a unified data benchmark. It involves collaboratively calibrating the spatial distribution of water quality assessment, the temporal variation characteristics of water supply capacity, and the spatial constraints of construction paths. Preferably, the standardized optimization scheduling input data is stored in a spatiotemporal coding format to ensure that the subsequent optimization decision model can accurately resolve the spatiotemporal correlation of each parameter. Furthermore, the alignment process can employ multi-resolution matching technology to establish a hierarchical mapping relationship based on the spatiotemporal accuracy differences of different data sources. For example, high-frequency collected water quality data and daily updated construction progress data can be dynamically coupled through a sliding time window. This step effectively solves the scale inconsistency problem during heterogeneous data fusion, providing a more complete data view for global optimization.

[0120] This embodiment, by introducing methods such as adaptive assessment, predictive modeling, risk quantification search, and multi-resolution alignment, enables the water supply scheduling system to possess environmental awareness and proactive decision-making capabilities. For example, when the system detects that a certain area is about to enter a peak water consumption period, preventative scheduling can be initiated 12 hours in advance: adjusting the dynamic water supply capacity curve based on predictive models, selecting high-quality water sources based on real-time water quality assessment results, and quickly completing the pipeline configuration switch through risk-optimized construction paths, ultimately forming a comprehensive solution that balances water quality safety, water supply stability, and construction efficiency. This embodiment, through a technical approach that integrates environmental intelligence and engineering decision-making, achieves a paradigm shift from passive response to proactive optimization.

[0121] In some embodiments, based on a set of feasible construction paths, a constrained shortest path algorithm is used to generate alternative scheduling routes. These alternative routes must meet pipe pressure limits and construction period constraints, including:

[0122] Establish a multi-dimensional path evaluation model, which includes at least one of hydraulic performance indicators, construction feasibility indicators, and economic indicators, and construct a correlation matrix between hydraulic performance indicators, construction feasibility indicators, economic indicators, and engineering constraints.

[0123] Based on the set of feasible construction paths, the hydraulic characteristic parameters of each path are calculated using a pressure-flow coupling algorithm. The hydraulic characteristic parameters include at least one of the following: steady-state water supply, transient pressure fluctuation value, and water hammer risk level.

[0124] Based on the pressure-bearing limits of pipe materials, a pressure safety assessment model is established. The pressure safety assessment model integrates the pipe strength coefficient, the peak operating pressure, and the safety margin threshold to generate a set of pressure compliance paths.

[0125] In conjunction with construction period constraints, a spatiotemporal conflict detection model is constructed. The spatiotemporal conflict detection model integrates construction machinery scheduling plan, traffic control period and resident impact assessment, and outputs a set of feasible paths for the construction period.

[0126] A multi-objective optimization algorithm is used to jointly solve the set of pressure-compliant paths and the set of feasible paths for the project period, generating the Pareto optimal alternative scheduling route set, which includes multiple alternative scheduling routes.

[0127] In this embodiment, hydraulic performance indicators characterize the water conveyance efficiency of the pipeline network and can be calculated using parameters such as pressure loss rate and flow uniformity; construction feasibility indicators reflect the difficulty of project implementation and include elements such as geological condition scoring and construction interference degree; economic indicators are used to measure construction costs, covering pipe material costs and construction period conversion costs. Preferably, the geological condition scoring incorporates ground-penetrating radar detection data to update soil stability parameters in real time, and the construction interference degree is dynamically adjusted by monitoring the population density around the construction site using IoT devices.

[0128] The pressure-flow coupling algorithm is a numerical method for simulating water flow by solving the hydraulic balance equations of a pipe network. The steady-state water supply reflects the pipeline's water delivery capacity under constant flow conditions and can be calculated using the nodal flow balance equations. Transient pressure fluctuations capture the magnitude of water pressure changes caused by valve opening and closing operations and can be solved using the method of characteristics. The water hammer risk level can be graded and assessed based on parameters such as pressure wave propagation velocity and valve closing time. Furthermore, the algorithm incorporates a pipe aging coefficient, dynamically adjusting the friction coefficient based on the pipe's service life and corrosion detection data, making the hydraulic simulation more closely resemble the actual attenuation state.

[0129] The pressure safety assessment model serves as an analytical framework for verifying the pressure-bearing capacity of pipelines. The pipe material strength coefficient is determined based on the pipe material and service life. The peak operating pressure is taken from the maximum value of the hydraulic simulation results. Preferably, the safety margin threshold is set to 1.5 times the design pressure according to engineering specifications. Furthermore, the model establishes a pipe section health record, integrating historical pressure test records and leakage repair data, and automatically increases the safety factor requirements for pipe sections with latent damage. Optionally, an online monitoring system based on acoustic emission technology can be introduced to capture micro-crack propagation signals in real time, dynamically adjusting the pressure limit value to ensure the pipeline network operates within the material's elastic deformation range while maximizing pipe material utilization.

[0130] The spatiotemporal conflict detection model is a scheduling tool that coordinates construction plans with external constraints. Construction machinery scheduling considers equipment transfer time and parallel operation limitations, traffic control periods integrate municipal traffic management data, and resident impact assessment quantifies the impact of construction noise and road closures on the community. Optionally, the model can access real-time urban traffic data streams to automatically reschedule construction periods during sudden traffic control measures. It also incorporates a community complaint prediction module to analyze historical complaint data and resident demographics to predict construction plans that may provoke strong opposition. Furthermore, by creating a construction impact heatmap, it visually displays the differences in social acceptance of different alternative routes, providing visual support for decision-making.

[0131] The multi-objective optimization algorithm adopts an evolutionary algorithm framework such as NSGA-II, taking pressure-bearing safety and project schedule feasibility as mutually constraining optimization objectives. It generates a Pareto front solution set through non-dominated sorting and congestion calculation. Preferably, an expert experience database is introduced during the algorithm's population initialization phase to prioritize gene combinations that conform to engineering practices; an emergency plan completeness score is added to the fitness function to improve the robustness of the solution; each alternative scheduling route not only includes traditional technical parameters but also an implementation risk radar chart and an emergency response flowchart, providing decision-makers with a comprehensive selection basis.

[0132] This embodiment establishes a multi-dimensional evaluation system integrating real-time monitoring data to comprehensively quantify path attributes. It verifies technical feasibility by introducing a dynamic model of pipeline health status, then coordinates internal and external constraints during construction to ultimately generate an optimal solution set that balances engineering standards and social benefits. For example, in pipeline renovation projects traversing commercial areas, the system might recommend a nighttime construction plan. While this increases labor costs, it significantly reduces the impact on businesses. Simultaneously, it uses reinforced pipe materials to compensate for the pressure risks posed by the complex underground environment, forming a technically feasible, economically reasonable, and socially acceptable optimized solution. This intelligent decision-making method, integrating IoT monitoring and social perception, enables path selection to dynamically adapt to complex environments.

[0133] In some embodiments, a comprehensive cost weight is calculated for each alternative scheduling route. The comprehensive cost weight includes water conveyance energy consumption, construction and modification costs, and emergency redundancy, including:

[0134] Perform the following operations for each alternative scheduling route:

[0135] The energy consumption value of the drainage route of the alternative scheduling route is calculated and expressed by formula (1), which is as follows:

[0136] ;

[0137] In formula (1), For the first The water conveyance energy consumption value of each alternative dispatch route. For the first The coefficient of friction of the pipe section For the first The length of the pipe section For the first Design flow rate of the pipe section For the density of water, Standard gravitational acceleration, For the first The elevation difference of the alternative dispatch routes;

[0138] The construction and modification costs of the alternative scheduling routes are calculated using formula (2), which is as follows:

[0139] ;

[0140] In formula (2), For the first The construction and modification costs of one alternative dispatch route, For the first Pipe material costs for one alternative dispatch route, For the first Construction costs for one alternative dispatch route, For the first Road repair costs for one alternative dispatch route;

[0141] The emergency redundancy of the alternative scheduling routes is calculated using formula (3), which is as follows:

[0142] ;

[0143] In formula (3), For the first Emergency redundancy of alternative dispatch routes, As the first weighting coefficient, This refers to the number of standby pumping stations. This is the second weighting coefficient. To quickly switch the number of valves, The third weighting coefficient, For emergency water reserves;

[0144] The overall cost weight of the alternative scheduling routes is calculated using formula (4), which is as follows:

[0145] ;

[0146] In formula (4), This is the weighting coefficient for hydrophobic energy consumption value. This is the weighting coefficient for construction and renovation costs. This is the inverse weighting coefficient for emergency redundancy. ,and ;

[0147] Repeat the above steps until the comprehensive cost weight of all candidate scheduling routes has been calculated, and then map and store the comprehensive cost weight with the candidate scheduling paths.

[0148] Furthermore, the alternative scheduling paths are sorted from highest to lowest according to their overall cost weight.

[0149] In this embodiment, the water conveyance energy consumption value characterizes the energy loss during pipeline operation and is calculated using formula (1), where the first... Friction coefficient of pipe section The determination can be made by referring to a table based on the pipe type and pipe wall roughness. Design flow rate of the pipe section Based on the water demand forecasting model, the height difference is calculated. It can be extracted through a digital elevation model. Preferably, a seasonal correction factor can be introduced into the formula to dynamically adjust the flow parameters based on historical water consumption data, making the energy consumption calculation more in line with actual operating conditions.

[0150] Construction and renovation costs are used to quantify the economic input of project implementation. Pipe material costs for alternative dispatch routes Based on current market prices and usage, the first Construction costs of alternative dispatch routes Considering labor costs and machine operating costs, the first Road repair costs for the alternative dispatch routes The cost is determined based on the road surface type and the area of ​​damage. Furthermore, regional economic coefficients can be introduced into the calculation of construction and renovation costs to weight additional construction costs in special areas (such as commercial areas and cultural relic protection areas), thereby improving the accuracy of construction and renovation cost estimation.

[0151] Emergency redundancy reflects a system's reserve capacity to respond to emergencies, including the number of backup pump stations. The number of valves to be quickly switched is determined based on the pipeline topology. Based on the standard configuration per kilometer of pipeline, the emergency water reserve capacity is calculated as follows: Reference area peak water demand configuration. First weighting coefficient. Second weighting coefficient Third weighting coefficient The analytic hierarchy process (AHP) is used to determine that redundancy in critical facilities should be prioritized. Optionally, the system can establish an emergency equipment health scoring mechanism to automatically reduce the redundancy contribution value of backup equipment that has exceeded its service life.

[0152] The overall cost weighting achieves multi-objective normalization through weighted summation, where the hydrophobic energy consumption value has a weighting coefficient. Construction and renovation cost weighting coefficient Emergency redundancy inverse weighting coefficient It can be determined through expert scoring, and settings can be made. The rigid constraints ensure a minimum level of emergency response capability. Preferably, the system establishes a dynamic weight adjustment mechanism, automatically increasing the emergency redundancy weight during the flood season and appropriately increasing the economic weight during the off-season, making the optimal solution more environmentally adaptable.

[0153] This embodiment establishes a quantitative cost assessment system, transforming multiple objectives such as energy consumption, economy, and safety into comparable comprehensive indicators. For example, in the renovation of pipeline networks in old urban areas, the system may recommend using a higher-cost corrosion-resistant pipe material scheme. Although the initial investment is larger, its excellent emergency redundancy performance and lower long-term operating energy consumption ultimately yield the optimal comprehensive weight. This multi-dimensional cost-benefit analysis method effectively avoids the problem of unilaterally pursuing the extreme value of a single indicator in the comparison and selection process.

[0154] In some embodiments, time-domain analysis is performed on the dynamic water supply capacity curve to extract water supply abrupt change characteristics and establish a response strategy library containing typical water supply anomaly scenarios, including:

[0155] Perform spectral analysis and waveform decomposition on the dynamic water supply capacity curve to identify at least one of the following characteristics: sudden change point in water supply pressure, sudden drop point in flow rate, and abnormal point in water quality parameters.

[0156] Based on the identification results, water supply anomalies are classified into three levels: Level 1, Level 2, and Level 3. Level 1 anomalies are configured as main water supply pipeline failures, Level 2 anomalies as local pipeline leaks, and Level 3 anomalies as sudden increases in water demand.

[0157] Establish a database of typical water supply anomaly scenarios, including main pump station shutdown, pipeline rupture, and peak water usage scenarios;

[0158] Develop response strategies for each typical water supply anomaly scenario, including:

[0159] In the event of a main pumping station shutdown, start the backup pumping station and adjust the opening of the pipeline valves;

[0160] In the event of a pipe burst, shut off the nearest valve and activate the emergency water supply truck;

[0161] For peak water usage scenarios, adjust the reservoir's water release and start the booster pump set;

[0162] The abnormal water supply characteristics, abnormality level classification, typical abnormal water supply scenarios, and response strategies are linked and stored to form a response strategy library.

[0163] In this embodiment, sudden changes in water supply pressure can be identified using a derivative rate of change detection algorithm, sudden drops in flow rate are captured using a sliding window variance analysis method, and abnormal water quality parameters trigger alarms based on set thresholds. Preferably, the system incorporates wavelet transform technology to separate noise signals, improving the accuracy of feature recognition.

[0164] The classification of water supply anomalies is determined based on the scope of the fault's impact and the difficulty of repair. Level 1 anomalies correspond to systemic faults such as main pipeline ruptures, and are determined by both the magnitude of the pressure drop and the number of affected users. Level 2 anomalies involve localized pipeline leaks, confirmed by changes in pressure gradients and acoustic detection signals. Level 3 anomalies reflect a surge in regional water demand, identified through analysis of flow rate mutation rates and user water usage patterns. Furthermore, the system establishes a dynamic adjustment mechanism for anomaly levels; when a Level 2 anomaly continues to worsen, it can automatically escalate to a Level 1 anomaly response.

[0165] The typical water supply anomaly scenario library is a pre-established set of failure modes. Preferably, main pump station shutdown scenarios are confirmed through power status monitoring and pump vibration data; pipeline rupture scenarios are determined by combining pressure wave propagation characteristics and acoustic emission signals; and peak water consumption scenarios are predicted based on historical water consumption curves and weather data. Optionally, the scenario library incorporates case-based reasoning technology, automatically generating temporary scenario categories when new anomaly patterns are detected, and forming standard scenarios after accumulating sufficient cases.

[0166] The response strategy considers the matching relationship between fault type and disposal resources. The backup pump station activation strategy prioritizes the pump station with the closest topological distance and matching capacity. Valve opening adjustment is based on the optimal configuration calculated by the hydraulic model. Emergency water supply truck dispatch can incorporate GIS route planning, comprehensively considering road conditions and water usage priorities. The booster pump group control can adopt a fuzzy PID algorithm to achieve a smooth transition of flow and pressure. Preferably, the strategy library establishes an effect feedback mechanism to dynamically optimize strategy priorities based on historical disposal success rates.

[0167] This embodiment establishes an intelligent water supply anomaly identification and response mechanism, enabling rapid diagnosis and precise handling of water supply system faults. Time-domain analysis of dynamic water supply capacity curves accurately captures various anomaly characteristics. Combined with multi-level anomaly classification and typical scenario matching, it ensures the comprehensiveness and accuracy of fault determination. The establishment of a response strategy library allows the system to automatically trigger optimal handling solutions for different scenarios such as main pump station shutdowns and pipeline ruptures, including intelligent scheduling of backup pump stations and precise control of valve openings. This embodiment significantly improves the response efficiency and handling accuracy of the water supply system in dealing with emergencies, minimizing the impact of faults while ensuring water supply safety. In particular, the introduction of dynamic anomaly level adjustment and strategy effect feedback mechanisms enables the system to continuously optimize, effectively solving the problems of delayed response and insufficient decision-making basis in traditional manual handling.

[0168] In some embodiments, an optimized decision-making model for multi-source coordinated scheduling and emergency switching is constructed based on water quality compliance assessment results, alternative scheduling routes, water supply mutation characteristics, and a response strategy library, including:

[0169] A hydraulic-water quality coupled calculation model is established, which is expressed by formula (5), as follows:

[0170] ;

[0171] In formula (5), For the pressure measurement section water head, The component of gravitational acceleration, The inlet flow rate of the pipe section. This refers to the outlet flow rate of the pipe section. For source terms, For water quality concentration, Where is the diffusion coefficient. The spatial second derivative of water concentration. For the flow rate of the pipe section, The cross-sectional area of ​​the pipe. For water quality concentration gradient, The water quality reaction rate constant;

[0172] The hydraulic-water quality coupled calculation model is solved to obtain multiple solution results, and each solution result corresponds to a scheduling decision under a certain working condition.

[0173] The scheduling decisions are screened using the finite state machine principle combined with the characteristics of sudden changes in water supply. The selected scheduling decisions are denoted as the screening decisions. The screening conditions are defined, including:

[0174] when At that time, switch to the emergency dispatch plan. The rate of change of head pressure, The pressure change rate threshold is determined based on statistical analysis of pressure fluctuation data from historical pipe rupture / leakage events. This indicates that the system may be experiencing a sudden pipe burst or a large-scale leak, requiring an immediate switch to an emergency dispatch plan (such as shutting off valves or isolating the fault area).

[0175] when At that time, switch to the hybrid control scheme. For water quality concentration safety standards, The water quality deviation threshold is set according to the proportion of the safety limit of the water quality standard. When a pollution event is detected (such as chemical pollution or abnormal turbidity), a mixing and adjustment plan (such as dilution or addition of chemicals) needs to be initiated.

[0176] when At that time, switch to the boost scheduling scheme. The rate of change of flow rate in the pipe section. The flow rate change rate threshold is determined through peak-valley fluctuation analysis of normal water use. This indicates a surge in demand or localized congestion, requiring the implementation of booster scheduling measures (such as starting pumps or regulating valves) to stabilize the flow rate.

[0177] Multiple screening decisions are used to generate a multi-level buffer control strategy, which is expressed by formula (6):

[0178] ;

[0179] In formula (6), This refers to the valve opening adjustment amount. This is the proportional control coefficient. For head deviation, The integral control coefficient, For the historical head deviation integral variable, These are the differential control coefficients;

[0180] That is, to generate an optimal decision model.

[0181] In this embodiment, the hydraulic-water quality coupled calculation model is used to simultaneously simulate the hydraulic characteristics of the pipe network and the water quality transmission process, wherein the piezometric head of the pipe section is... Water quality concentration is monitored in real time by a pressure sensor. The diffusion coefficient was collected by an online water quality monitoring instrument. The water quality reaction rate constant is determined by referring to a table based on the pipe material characteristics. The results were obtained through laboratory measurements. Preferably, the model incorporates adaptive mesh technology, automatically refining the computational nodes in water-sensitive areas to improve simulation accuracy.

[0182] The finite state machine principle is used to construct the transition logic for scheduling decisions, preferably with a pressure change rate threshold. The water quality deviation threshold was determined by analyzing the 95th percentile of pressure fluctuations in historical pipe burst events. Take 20% of the water quality standard limit, and the flow rate change threshold. The threshold is set based on the flow fluctuation characteristics during peak water usage periods. Furthermore, the system establishes a dynamic threshold adjustment mechanism to automatically increase sensitivity during special periods (such as the period for ensuring the smooth operation of major events).

[0183] The multi-level buffer control strategy uses a PID algorithm to achieve gradual adjustment of pipeline parameters, with a proportional control coefficient. The integral control coefficient is set based on the pipe section impedance characteristics. Differential control coefficients used to eliminate steady-state errors Suppress system overshoot. Preferably, the control parameters are dynamically adjusted using fuzzy logic, and automatically readjusted when a change in the pipeline topology is detected.

[0184] This embodiment achieves intelligent scheduling through a three-stage process of coupled modeling, state determination, and strategy generation. For example, when the system simultaneously detects a sudden drop in pressure and water quality exceeding standards, the coupled model can accurately predict the extent of pollution spread, the finite state machine immediately triggers an emergency isolation plan, and the buffer control strategy smoothly adjusts the valve opening, thus quickly isolating the pollution while avoiding water hammer. This embodiment combines physical modeling with intelligent control, effectively solving the response lag problem caused by the separation of water quality and hydraulic processes in traditional scheduling, and achieving a balance between safety and stability.

[0185] In some embodiments, based on an optimized decision-making model, a characteristic mapping relationship between the baseline water supply condition and the emergency water supply mode is established. This characteristic mapping relationship includes a pressure fluctuation transfer function, a water quality mixing prediction matrix, and a construction disturbance compensation coefficient, including:

[0186] Hydraulic modeling is performed on the baseline water supply conditions, and pressure fluctuation characteristic parameters are extracted. The pressure fluctuation characteristic parameters include at least one of the dominant frequency amplitude, attenuation rate, and propagation speed.

[0187] The pressure fluctuation transfer function is established and expressed by formula (7), which is as follows:

[0188] ;

[0189] In formula (7), Let be the pressure fluctuation transfer function. Let Laplace be a complex variable. The base of the natural logarithm, Due to the time delay of pressure wave propagation, For systematic time constants, For the Laplace transform of the input pressure disturbance, The Laplace transform of the output pressure response;

[0190] A water quality mixing prediction matrix is ​​constructed, which is expressed by formula (8), as follows:

[0191] ;

[0192] In formula (8), For the first The first section of the pipe Mixed transfer function of water quality parameters;

[0193] The construction interference compensation coefficient is constructed and expressed by formula (9), which is as follows:

[0194] ;

[0195] In formula (9), This is the construction interference compensation coefficient. It is the fourth weighting coefficient. for Construction interference index The corresponding mechanical construction interference index, The corresponding traffic-related construction interference index, The corresponding environmental interference category construction interference index;

[0196] The pressure fluctuation transfer function, water quality mixing prediction matrix, and construction disturbance compensation coefficient are integrated to obtain the mapping characteristic relationship, which is expressed by formula (10), as follows:

[0197] ;

[0198] In formula (10), For pressure domain, For water quality zone, For the traffic domain, To adjust the flow rate, The baseline flow rate is Typical range under normal operating conditions;

[0199] The feature mapping relation library supports the following functions:

[0200] Real-time output pressure compensation , For real-time input of pressure disturbances;

[0201] Predicted water quality mixed concentration , Input pollutant concentration;

[0202] Generate flow regulation instructions , This is the planned baseline flow rate.

[0203] In this embodiment, the baseline water supply condition is the hydraulic and water quality characteristics of the pipeline network under normal operating conditions, established through statistical analysis of long-term monitoring data. The dominant frequency amplitude reflects the energy distribution characteristics of pressure fluctuations, the attenuation rate characterizes the damping properties of the pipeline network, and the propagation speed depends on the elastic modulus of the pipe material and the fluid density. Preferably, the system employs wavelet packet decomposition technology to extract pressure fluctuation characteristic parameters in different frequency bands, improving the resolution of feature recognition.

[0204] The pressure fluctuation transfer function is used to describe the propagation law of pressure disturbances in a pipeline network, and the systematic time constant is used to describe the propagation law of pressure disturbances in a pipeline network. The overall inertia of the pipeline network can be characterized by step response tests; the pressure wave propagation time delay can also be measured. The pressure fluctuation transfer function is determined based on pipe segment length and wave velocity. Furthermore, a pipe aging correction factor can be incorporated into the pressure fluctuation transfer function to dynamically adjust the function parameters according to pipe age and corrosion level, thereby improving the model's adaptability.

[0205] Mixing transfer function in water quality mixing prediction matrix The mixing effect can be calibrated through tracer experiments, taking into account the influence of factors such as flow rate, pipe diameter, and number of bends. Preferably, the system establishes a mixing effect prediction model based on deep learning, which automatically generates a temporary transfer function when a new pollutant is detected and gradually refines it into the matrix.

[0206] The construction interference compensation coefficient comprehensively assesses the impact of various construction activities on the water supply system. The preferred coefficients are: mechanical construction interference indexes monitored by vibration sensors; traffic interference indexes calculated based on vehicle load data; and environmental interference indexes considering factors such as sudden temperature changes. (Fourth weighting coefficient) The analytic hierarchy process (AHP) can be used to determine the relative importance of different types of disturbances. Furthermore, the system establishes a construction record database, pre-entering planned construction information to optimize the prediction of compensation coefficients.

[0207] This embodiment significantly improves the water supply system's ability to respond to sudden disturbances by constructing a multi-dimensional feature mapping relationship between baseline water supply conditions and emergency water supply modes. The pressure fluctuation transfer function accurately characterizes the propagation law of pipeline pressure disturbances, the water quality mixing prediction matrix enables accurate prediction of pollutant diffusion, and the construction disturbance compensation coefficient effectively quantifies the impact of external construction on the system. This embodiment combines steady-state characteristics with dynamic disturbances to achieve coordinated optimization and control of pressure, water quality, and flow, effectively solving the problem of insufficient adaptability of traditional scheduling models under emergency conditions and ensuring the stable operation of the water supply system in complex environments.

[0208] In some embodiments, alternative scheduling routes, water supply mutation characteristics, response strategy library, optimization decision model, and feature mapping relationships are structured and stored to construct a multi-dimensional water supply scheduling knowledge base containing water source characteristics, pipeline topology, scheduling strategies, and emergency responses, including:

[0209] Perform topology coding on the alternative scheduling routes to generate a route feature description set that includes path node sequence, pipeline characteristic parameters and switching constraints;

[0210] Water supply mutation characteristics are classified and stored according to anomaly type. A mutation characteristic database containing pressure mutation mode, flow mutation mode and water quality mutation mode is established. Each mutation mode is associated with the corresponding time-frequency characteristic parameters and trigger threshold.

[0211] The response strategy library is organized hierarchically to form a hierarchical response strategy tree;

[0212] The optimization decision-making model is decomposed into three sub-libraries: model parameter set, constraint set, and solution algorithm set. The model parameter set includes hydraulic calculation parameters, water quality simulation parameters, and economic evaluation parameters.

[0213] A multi-dimensional index is constructed on the feature mapping relationship to form a pressure-water quality-flow collaborative mapping relationship network, which supports multi-dimensional retrieval by working condition type, anomaly level and construction stage;

[0214] An update mechanism for a multi-dimensional water supply scheduling knowledge base based on spatiotemporal characteristics is established, including timed updates, event-triggered updates, and incremental updates. Timed updates are configured to refresh basic data according to a preset cycle. Event-triggered updates are configured to initiate a comprehensive update when a major pipeline renovation or water source change occurs. Incremental updates are configured to record the execution effect of scheduling decisions in real time and perform local optimizations.

[0215] In this embodiment, the topology coding of the candidate scheduling routes is implemented using an adjacency list structure in graph theory. The path node sequence records the complete delivery path from the water source to the user. Pipe segment characteristic parameters include key attributes such as pipe diameter, material, and age. Switching constraints define operational restrictions such as the minimum switching interval. Preferably, the system uses spatial indexing technology to accelerate route retrieval and supports rapid filtering of feasible scheduling schemes by geographical region.

[0216] The classification and storage of water supply anomaly characteristics are based on historical event statistical analysis. Pressure anomaly patterns include characteristic waveforms from scenarios such as pipe bursts and pump station failures; flow anomaly patterns distinguish between user-side demand anomalies and network-side leaks; and water quality anomaly patterns cover types such as contaminant intrusion and abnormal residual chlorine. Time-frequency characteristic parameters are extracted using short-time Fourier transform, and trigger thresholds are set according to the severity of the event. Furthermore, the system establishes an evolutionary map of anomaly patterns, recording the transformation rules between different types of anomalies.

[0217] The hierarchical response strategy tree is organized using a decision tree structure. The top layer branches according to event type, the middle layer classifies response timeliness, and the bottom layer refines specific operational instructions. Hydraulic calculation parameters include fluid dynamics parameters such as pipe friction coefficients, water quality simulation parameters involve reaction kinetics parameters such as pollutant decay rates, and economic evaluation parameters include operational indicators such as energy consumption costs. Preferably, the model parameter set incorporates a parameter sensitivity analysis module to automatically identify key parameters and improve their update frequency.

[0218] The pressure-water quality-flow collaborative mapping network is stored in a graph database, where nodes represent operational features and edge weights reflect the strength of feature associations. The system supports semantic-based hybrid retrieval, such as querying the control strategies corresponding to "abnormal water quality during construction." The timed update cycle is dynamically adjusted according to the data change rate. Major pipeline renovations trigger full database verification, while incremental updates utilize online learning algorithms to optimize strategies. For example, when a scheduling decision deviates from expectations after multiple executions, the system automatically adjusts relevant parameters and updates the knowledge base.

[0219] This embodiment achieves systematic management and intelligent application of scheduling elements by constructing a structured, multi-dimensional water supply scheduling knowledge base. The multi-dimensional water supply scheduling knowledge base transforms discrete scheduling experience into computable and optimizable digital assets, preserving the logical integrity of expert decision-making while possessing the structured features required for machine learning. In particular, the spatiotemporal feature-driven update mechanism ensures the continuous evolution of the knowledge base, providing core support for the transformation of water supply systems from experience-based scheduling to intelligent scheduling.

[0220] In a second aspect, this embodiment also provides a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the method described in the first aspect.

[0221] The computer program involved in this embodiment can be stored in a computer device readable storage medium, which includes, but is not limited to, disks, magnetic tapes, magnetic cards, floppy disks, flash memory, optical disks, optical cards, read-only memory (ROM), random access memory (RAM), erasable programmable ROM (EPROM), and electrically erasable programmable ROM (EEPROM), etc. It also includes other biological, physical, or chemical structures capable of performing similar or equivalent functions to the storage media listed above, such as DNA, RNA, proteins, and other units with information storage capabilities. In specific embodiments, the storage medium involved can be one of the above-mentioned media types or a combination of the above media types. In different embodiments, the computer program involved in the embodiment can be centrally stored in a single medium or distributed across multiple media. The memory containing the computer device readable storage medium can be non-volatile memory or random access memory. These computer device readable storage media can be built into the device or connected to the device involved in the embodiment as an external device or part of an external device. In some embodiments, the memory having a computer device readable storage medium is deployed locally; in other embodiments, the memory may be deployed remotely from the processor, for example, as a network-attached memory accessed via RF circuitry or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), or a suitable combination thereof, as long as computer device access to the memory is enabled. Furthermore, the computer program involved in the embodiments may be stored in plaintext / ciphertext form, or it may be designed as training data, integrated and recombined through model training and implicitly stored in the parameter states of a deep neural network or other machine learning model.

[0222] Please see Figure 3 In a third aspect, this embodiment also provides an electronic device 1, including a memory 11 and a processor 12, wherein the memory 11 is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor 12 to implement the method described in the first aspect.

[0223] The processor described in this embodiment can be implemented by hardware, firmware, software, or a combination thereof. It can be a circuit, one or more of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field-programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, or a microprocessor. It also includes other physical, biological, or chemical structures that can implement the same or equivalent functions as the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of this application, or any combination of the steps mentioned therein.

[0224] Unlike existing technologies, the above-mentioned technical solutions offer the following advantages: By constructing a multi-dimensional water supply scheduling knowledge base and intelligent decision-making system, the technical challenges of delayed response and insufficient control precision in traditional water supply systems when dealing with sudden anomalies are effectively solved. A multi-dimensional data foundation is established based on water source characteristics, pipeline topology, and construction conditions. Constrained optimization algorithms generate alternative scheduling routes that balance engineering feasibility and economy. Time-frequency analysis methods are used to extract water supply mutation characteristics, establishing a hierarchical response mechanism to achieve accurate identification and rapid handling of typical water supply anomaly scenarios, from pipe bursts and leaks to water pollution. Through feature mapping relationships such as pressure fluctuation transfer functions and water quality mixing prediction matrices, coordinated optimization and control of pressure, water quality, and flow are achieved. These technical solutions deeply integrate physical models with intelligent algorithms. A hydraulic-water quality coupled calculation model enables accurate prediction of system states. Construction interference compensation coefficients quantify the impact of the external environment. A self-learning knowledge base is constructed to continuously optimize strategies, enabling the water supply system to transition from passive response to active defense. This significantly improves the stability of multi-source coordinated supply and the reliability of emergency switching, providing intelligent protection for water supply safety in densely populated residential areas.

[0225] The above description is only a part of the embodiments of the present invention and does not limit the scope of protection of the present invention. Any equivalent device or equivalent process transformation made based on the content of the present invention specification and drawings, or direct or indirect application in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A water supply scheduling planning method for a residential cluster, characterized by, The method comprises the following steps: Collecting basic water supply data of water sources, including water quality parameters, available water quantity, water pipe network topology information and construction access conditions; Preprocessing the basic water supply data to obtain optimized scheduling input data, including water quality evaluation results, dynamic water supply capacity curves and a set of feasible construction paths; Based on the set of feasible construction paths, a constraint shortest path algorithm is used to generate alternative scheduling routes, which need to meet the pipe pressure limit and construction period constraint, and the comprehensive cost weight of each alternative scheduling route is calculated, including water transmission energy consumption, construction cost and emergency redundancy; Performing time domain analysis on the dynamic water supply capacity curve to extract water supply mutation characteristics, and establishing a response strategy library containing typical water supply abnormal scenes, including at least one of sudden pollution, equipment failure and demand peak; According to the water quality evaluation results, the alternative scheduling route, the water supply mutation characteristics and the response strategy library, an optimization decision model of multi-source collaborative scheduling and emergency switching is constructed; Based on the optimization decision model, a characteristic mapping relationship between the baseline water supply working condition and the emergency water supply mode is established, including the pressure fluctuation transfer function, the water quality mixing prediction matrix and the construction interference compensation coefficient; The alternative scheduling route, the water supply mutation characteristics, the response strategy library, the optimization decision model and the characteristic mapping relationship are stored in a structured manner to construct a multi-dimensional water supply scheduling knowledge base containing water source characteristics, pipe network topology, scheduling strategy and emergency response.

2. The method for water supply dispatching planning of residential area according to claim 1, characterized in that, The method comprises the following steps: Performing multi-index weighted evaluation on the water quality parameters to generate water quality evaluation results, including at least one of heavy metal content, turbidity and residual chlorine concentration, and establishing a compliance matrix of multiple indexes and preset water standards; Based on the available water quantity and water pipe network topology information, a hydraulic transient model is used to calculate the dynamic water supply capacity curve under different working conditions, which contains at least one of the maximum water supply quantity, the pressure fluctuation range and the critical switching time; According to the construction access conditions, a three-dimensional geographic constraint model is constructed, which integrates road excavation restrictions, existing pipeline distribution and geological survey data, and uses an improved Dijkstra algorithm to search for K feasible construction paths in the constraint space to form a set of feasible construction paths; The water quality evaluation results, dynamic water supply capacity curves and set of feasible construction paths are processed in space-time alignment to generate standardized optimized scheduling input data.

3. The method for water supply scheduling planning of residential area according to claim 1, characterized in that, Based on the set of feasible construction paths, a constraint shortest path algorithm is used to generate alternative scheduling routes, which need to meet the pipe pressure limit and construction period constraint, including: A multi-dimensional path evaluation model is established, which includes at least one of hydraulic performance indicators, construction feasibility indicators and economic indicators, and a correlation matrix of hydraulic performance indicators, construction feasibility indicators and economic indicators and engineering constraint conditions is constructed; Based on the set of feasible construction paths, a pressure-flow coupling algorithm is used to calculate the hydraulic characteristic parameters of each path, including at least one of steady-state water supply, transient pressure fluctuation value and water hammer risk level; According to the pressure limit of the pipe material, a pressure safety evaluation model is established, which integrates the pipe material strength coefficient, the working condition pressure peak value and the safety margin threshold to generate a set of pressure compliance paths; Combined with the construction period constraint, a time-space conflict detection model is constructed, which integrates the construction machinery scheduling plan, the traffic control period and the resident influence evaluation to output a set of feasible construction period paths; A multi-objective optimization algorithm is used to collaboratively solve the set of pressure compliance paths and the set of feasible construction period paths to generate a set of Pareto optimal candidate scheduling routes.

4. The method for water supply dispatching planning of residential area according to claim 3, characterized in that, The comprehensive cost weight of each candidate scheduling route is calculated, including water delivery energy consumption, construction cost and emergency redundancy, including: For each candidate scheduling route, the following operations are performed: Calculate the water delivery energy consumption value of the candidate scheduling route, which is represented by formula (1) as follows: ； In formula (1), is the water conveyance energy consumption value of the first alternative scheduling route, is the water conveyance energy consumption value of the first alternative scheduling route, is the friction coefficient of the first pipe section, is the friction coefficient of the first pipe section, is the pipe section length of the first pipe section, is the pipe section length of the first pipe section, is the design flow of the first pipe section, is the design flow of the first pipe section, is the water density, is the standard gravity acceleration, is the height difference of the first alternative scheduling route, is the height difference of the first alternative scheduling route. Calculate the construction cost of the candidate scheduling route, which is represented by formula (2) as follows: ； In formula (2), is the construction cost of the first alternative dispatch route, is the pipe cost of the first alternative dispatch route, is the construction cost of the first alternative dispatch route, is the road repair cost of the first alternative dispatch route; Calculate the emergency redundancy of the candidate scheduling route, which is represented by formula (3) as follows: ； In formula (3), is the emergency redundancy of the nth alternative dispatching route, is the first weight coefficient, is the number of standby pump stations, is the second weight coefficient, is the number of fast switching valves, is the third weight coefficient, is the emergency water source reserve​ Calculate the comprehensive cost weight of the candidate scheduling route, which is represented by formula (4) as follows: ； In formula (4), is a weight coefficient of hydrophobic energy consumption value, is a weight coefficient of construction modification cost, is an inverse weight coefficient of emergency redundancy, , and ; Repeat the above steps until the comprehensive cost weights of all candidate scheduling routes are calculated, and store the mapping of the comprehensive cost weights and candidate scheduling paths; And sort the candidate scheduling paths according to the comprehensive cost weights from high to low.

5. The method for water supply scheduling planning of residential area according to claim 1, characterized in that, Perform time domain analysis on the dynamic water supply capacity curve, extract water supply mutation characteristics, and establish a response strategy library containing typical water supply abnormal scenes, including: Perform frequency spectrum analysis and waveform decomposition on the dynamic water supply capacity curve to identify at least one of the features of water supply pressure mutation points, flow sudden drop points and water quality parameter abnormal points; According to the identification result, the water supply abnormality level is divided, including first-level abnormality, second-level abnormality and third-level abnormality, the first-level abnormality is configured as main water supply pipeline failure, the second-level abnormality is configured as local pipe network leakage, and the third-level abnormality is configured as sudden increase of water demand; A typical water supply abnormal scene library is established, including main pump station shutdown scene, pipe burst scene and peak water consumption scene; For each typical water supply abnormal scene, a response strategy is developed, including: For the main pump station shutdown scene, start the standby pump station and adjust the pipe network valve opening; For the pipe burst scene, close the nearest valve and enable the emergency water supply vehicle; For the peak water consumption scene, adjust the reservoir water release amount and start the booster pump set; The water supply anomaly feature, anomaly level division, typical water supply anomaly scene library and response strategy are stored in association to form a response strategy library.

6. The method for water supply scheduling planning of residential clusters according to claim 1, characterized in that, According to the water quality standard evaluation result, the alternative dispatching route, the water supply mutation feature and the response strategy library, an optimization decision model for multi-water source collaborative dispatching and emergency switching is constructed, including: A hydraulic-water quality coupling calculation model is established, which is expressed by formula (5) as follows: ； in equation (5), is the piezometric tube segment water head, is the gravity acceleration component, is the pipe segment inlet flow rate, is the pipe segment outlet flow rate, is the source term, is the water quality concentration, is the diffusion coefficient, is the spatial second derivative of the water quality concentration, is the pipe segment flow rate, is the pipe cross-sectional area, is the water quality concentration gradient, is the water quality reaction rate constant; The hydraulic-water quality coupling calculation model is solved to obtain a plurality of solution results, each of which corresponds to a dispatching decision under a working condition; The dispatching decisions are screened using the finite state machine principle combined with the water supply mutation feature to obtain screened dispatching decisions, denoted as screening decisions, and the screening conditions are defined, including: When the emergency dispatching scheme is switched to; When the mixed regulation scheme is switched to; When a boost schedule is switched to; The plurality of screening decisions are generated into a multi-level buffer control strategy, which is expressed by formula (6) as follows: ； In equation (6), is the valve opening adjustment amount, is the proportional control coefficient, is the water head deviation, is the integral control coefficient, is the historical water head deviation integral variable, is the differential control coefficient; That is, the optimization decision model is generated.

7. The method for water supply dispatching planning of residential area according to claim 6, characterized in that, Based on the optimization decision model, a feature mapping relationship between the benchmark water supply working condition and the emergency water supply mode is established, including a pressure fluctuation transfer function, a water quality mixing prediction matrix and a construction interference compensation coefficient, including: The pressure fluctuation feature parameters are extracted by modeling the water pressure of the benchmark water supply working condition, including at least one of the main frequency amplitude, the attenuation rate and the propagation speed; The pressure fluctuation transfer function is established and expressed by formula (7) as follows: ； in equation (7), is the transfer function for pressure fluctuations, is the Laplace complex variable, is the natural logarithm base, is the pressure wave propagation time delay, is the systematic time constant, is the Laplace transform of the input pressure disturbance, is the Laplace transform of the output pressure response; The water quality mixing prediction matrix is constructed and expressed by formula (8) as follows: ； In equation (8), for the first for the first mixing transfer function of the water quality parameter; The construction interference compensation coefficient is constructed and expressed by formula (9) as follows: ； In formula (9), is a construction interference compensation coefficient, is a fourth weight coefficient, is a construction interference degree index. The pressure fluctuation transfer function, the water quality mixing prediction matrix and the construction interference compensation coefficient are integrated to obtain a mapping feature relationship, which is expressed by formula (10) as follows: ； In Equation (10), is a pressure domain, is a water quality domain, is a flow rate domain, is an adjusted flow rate, is a reference flow rate.

8. The method for water supply scheduling planning of residential clusters according to claim 1, characterized in that, The alternative dispatching route, the water supply mutation feature, the response strategy library, the optimization decision model and the feature mapping relationship are stored in a structured manner to construct a multi-dimensional water supply dispatching knowledge base containing water source characteristics, pipe network topology, dispatching strategies and emergency responses, including: The alternative dispatching route is topologically coded to generate a route feature description set containing path node sequences, pipe segment characteristic parameters and switching constraint conditions; The water supply mutation feature is stored in a classified manner according to anomaly types to establish a mutation feature database containing pressure mutation modes, flow mutation modes and water quality mutation modes, each mutation mode being associated with corresponding time-frequency feature parameters and trigger thresholds; The response strategy library is hierarchically organized to form a hierarchical response strategy tree; The optimization decision model is decomposed into a model parameter set, a constraint condition set and a solution algorithm set, wherein the model parameter set includes hydraulic calculation parameters, water quality simulation parameters and economic evaluation parameters; The feature mapping relationship is constructed with multi-dimensional indexing to form a pressure-water quality-flow collaborative mapping relationship network, supporting multi-dimensional retrieval according to working condition types, anomaly levels and construction stages; An updating mechanism of the multi-dimensional water supply scheduling knowledge base based on space-time characteristics is established, including timing updating, event-triggered updating and incremental updating, the timing updating is configured to refresh the basic data at a preset period, the event-triggered updating is configured to start comprehensive updating when significant pipe network reconstruction or water source change occurs, and the incremental updating is configured to record the scheduling decision execution effect in real time and perform local optimization.

9. A computer readable storage medium having stored thereon computer program instructions, wherein, The computer program instructions, when executed by a processor, implement the method of any one of claims 1-8.

10. An electronic device comprising a memory and a processor, characterized in that, The memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any one of claims 1-8.

Images