A water supply network intelligent simulation and dispatching method and system based on digital twinning

Abstract

This application discloses a method and system for intelligent simulation and scheduling of water supply networks based on digital twins. The method includes: collecting multi-source data of the physical network to form a basic network database; constructing a digital twin model corresponding to the physical network based on the basic network database; mapping attributes and assigning initial state values ​​to the digital twin model based on the basic network database, and mapping data to the digital twin model based on real-time monitoring data of the physical network; performing hydraulic simulation calculations of the network based on the digital twin model to obtain hydraulic simulation results; comparing the hydraulic simulation results with the actual monitoring data of the corresponding physical network, generating leakage analysis results based on the comparison results, and generating an emergency scheduling plan based on the leakage analysis results. This application can effectively overcome the problems of poor real-time performance, reliance on experience for decision-making, and data silos in existing technologies, providing reliable technical support for the intelligent management of the entire process of water supply networks.

Description

Technical Field

[0001] This application relates to the field of smart water technology, and in particular to a method and system for intelligent simulation and scheduling of water supply networks based on digital twins. Background Technology

[0002] With the acceleration of urbanization, the scale of water supply networks continues to expand, and their structure is becoming increasingly complex, posing severe challenges to their planning, operation, maintenance, and emergency dispatch. Currently, traditional water supply network management relies heavily on a combination of offline hydraulic models and human experience. This involves periodically collecting static data such as pipeline topology and equipment parameters to construct a hydraulic calculation model independent of the actual operating environment, and then conducting periodic offline simulation analyses based on historical operating conditions or typical daily data. Meanwhile, daily dispatch decisions primarily depend on the experience and judgment of dispatchers, supplemented by limited monitoring point data provided by the SCADA system.

[0003] However, this existing technology has significant drawbacks: First, the offline model is severely out of sync with the real-time status of the physical pipeline network. The model parameters are updated in a lagging manner and cannot reflect the dynamic changes in valve opening, pump operating conditions, and user water usage patterns in the pipeline network. This results in a large discrepancy between the simulation results and the actual operation, making it difficult to serve as a reliable basis for precise scheduling. Secondly, human experience-based decision-making lacks systematicity and global optimality. When faced with emergencies such as sudden pipe bursts or pump station failures, the development of dispatching plans is slow, and it is difficult to assess the comprehensive impact of multiple disposal strategies on the pressure and flow distribution of the entire pipeline network, which can easily lead to secondary risks. Furthermore, pipeline operation data, equipment ledgers, maintenance records, and user water meter data are scattered across different business systems, forming serious data silos. The lack of effective correlation and collaboration between these systems prevents the full exploitation of data value and hinders the support for refined leakage analysis, pressure optimization, and energy consumption control based on comprehensive information.

[0004] The aforementioned deficiencies make it difficult for existing technologies to achieve intuitive, efficient, and real-time control of large and complex pipe networks, and fail to meet the urgent needs for pipe network status perception, simulation, and intelligent decision-making in the context of smart water management.

[0005] Therefore, existing technologies still need improvement and development. Summary of the Invention

[0006] The technical problem to be solved by this application is to provide a method and system for intelligent simulation and scheduling of water supply networks based on digital twins, which addresses the above-mentioned deficiencies of existing technologies. The aim is to solve the problems of poor real-time performance, reliance on experience for decision-making, and data silos in existing technologies, and to provide reliable technical support for the intelligent management of the entire process of water supply networks.

[0007] The technical solution adopted in this application to solve the problem is as follows: In a first aspect, embodiments of this application provide a method for intelligent simulation and scheduling of water supply networks based on digital twins, the method comprising: Collect multi-source data of the physical pipeline network to form a basic database of the pipeline network that includes pipeline spatial attributes, equipment static parameters, real-time operation data, user water consumption data and operation and maintenance history data; A digital twin model of the physical pipeline network is constructed based on the pipeline network database. The system acquires real-time monitoring data of the physical pipeline network, performs attribute mapping and initial state assignment on the digital twin model based on the pipeline network basic database, and performs data mapping on the digital twin model based on the real-time monitoring data of the physical pipeline network. Based on the digital twin model, hydraulic simulation calculations of the pipeline network are performed to obtain hydraulic simulation results; the hydraulic simulation results are used to reflect the hydraulic state distribution of pressure at each node and flow rate in each pipe section of the entire pipeline network. The hydraulic simulation results are compared with the actual monitoring data of the corresponding physical pipe network. Based on the comparison results, leakage analysis results are generated, and an emergency dispatch plan is generated based on the leakage analysis results.

[0008] In one implementation, the step of constructing a digital twin model of the physical pipeline network based on the pipeline network infrastructure database includes: Based on the pipeline network database, the physical pipeline network is abstracted as a node-edge topology graph; where nodes represent pipeline connection points, valves, water pumps, water towers, water storage tanks, and user terminals; and edges represent pipe segments. By combining spatial data from a geographic information system with the node-edge topology map, a three-dimensional spatial network model is generated, resulting in a digital twin model corresponding to the physical pipeline network.

[0009] In one implementation, the steps of mapping attributes and assigning initial state values ​​to the digital twin model based on the pipeline network basic database, and mapping data to the digital twin model based on real-time monitoring data of the physical pipeline network, include: Based on the pipeline network database, the equipment information corresponding to each node and the pipe segment information corresponding to each edge are mapped as static attributes to the digital twin model, and initial state values ​​are assigned. The equipment information includes: equipment location and conventional supporting attributes; the pipe segment information includes: pipe diameter, material, rated power and laying year of the pipe segment. Based on the real-time monitoring data of the physical pipeline network, pressure, flow rate, and equipment operating frequency are mapped as dynamic variables to the digital twin model.

[0010] In one embodiment, the step of comparing the hydraulic simulation results with the corresponding actual monitoring data of the physical pipe network, and generating leakage analysis results based on the comparison results, includes: For each independent metering area, the actual monitoring data of the independent metering area is extracted based on the actual monitoring data of the physical pipeline network; The minimum nighttime flow rate of the zone is calculated based on the actual monitoring data of the independent metering area. The minimum nighttime flow rate of the zone is then compared with the historical baseline nighttime flow rate to obtain the flow rate difference. If the difference in flow exceeds a set threshold, it is determined that there is a risk of leakage. The measured pressure distribution data of the independent metering area is obtained based on the actual monitoring data of the independent metering area. The theoretical pressure distribution data of the independent metering area are obtained based on the hydraulic simulation results. The measured pressure distribution data of the independent metering area is compared point by point with the corresponding theoretical pressure distribution data, and leakage analysis results are generated based on the comparison results.

[0011] In one embodiment, the step of comparing the measured pressure distribution data of the independent metering area with the corresponding theoretical pressure distribution data point by point, and generating leakage analysis results based on the point-by-point comparison results includes: The measured pressure distribution data of the independent metering area is compared with the corresponding theoretical pressure distribution data point by point. Based on the point-by-point comparison results, the leakage location is identified and the leakage flow rate corresponding to the leakage location is calculated. Calculate the proportion of the leakage flow rate corresponding to the leakage location to the water supply of the independent metering area to obtain a first proportion; Calculate the ratio of the pressure drop at the location of the leak to the normal pressure to obtain the second ratio; The severity level of leakage corresponding to the leakage location is assessed based on the first ratio and the second ratio; Based on the location of the leakage and the corresponding leakage flow rate, pressure drop, and leakage severity level, leakage analysis results are generated.

[0012] In one implementation, the step of generating an emergency dispatch plan based on the leakage analysis results includes: For each leakage location in the leakage analysis results, a topological connectivity analysis is performed on the leakage location using the digital twin model to generate an optimal valve shut-off scheme; the optimal valve shut-off scheme is used to determine the control valve numbers and operation sequence that need to be closed upstream and downstream of the leakage pipe segment corresponding to the leakage location; The priority of several affected nodes around the leakage location is determined by a preset node classification strategy. For the affected node with the highest priority, if the affected node is located within the valve closure area corresponding to the optimal valve closure scheme, the local scheduling scheme for the affected node is: to start the backup pump station or emergency water source. If the affected node is located outside the valve-closing area corresponding to the optimal valve-closing scheme, the local scheduling scheme for the affected node is: to reduce the water supply pressure of non-first priority sites around the affected node, or to divide the non-first priority sites around the affected node into zones for rotational water supply, so as to ensure the water supply pressure of the affected node that is in the first priority. An emergency scheduling scheme is generated based on the optimal valve closure scheme and the local scheduling scheme of the affected node with the first priority.

[0013] In one embodiment, the method further includes: The emergency dispatch plan was simulated and verified using the digital twin model. If the simulation and pre-run verification pass, an executable emergency dispatch instruction set will be output according to the emergency dispatch plan.

[0014] Secondly, embodiments of this application also provide a digital twin-based intelligent simulation and scheduling system for water supply networks, the system comprising: The data acquisition module is used to collect multi-source data from the physical pipeline network to form a basic pipeline database that includes pipeline spatial attributes, equipment static parameters, real-time operating data, user water consumption data, and operation and maintenance history data. The model building module is used to build a digital twin model of the physical pipeline network based on the pipeline network basic database. The data mapping module is used to acquire real-time monitoring data of the physical pipeline network, perform attribute mapping and initial state assignment on the digital twin model according to the pipeline network basic database, and perform data mapping on the digital twin model according to the real-time monitoring data of the physical pipeline network. The hydraulic simulation module is used to perform hydraulic simulation calculations of the pipeline network based on the digital twin model, and obtain hydraulic simulation results; the hydraulic simulation results are used to reflect the hydraulic state distribution of pressure at each node and flow rate of each pipe segment in the entire pipeline network. The leakage analysis and emergency dispatch module is used to compare the hydraulic simulation results with the actual monitoring data of the corresponding physical pipe network, generate leakage analysis results based on the comparison results, and generate an emergency dispatch plan based on the leakage analysis results.

[0015] Thirdly, embodiments of this application also provide a terminal, the terminal including a memory and one or more processors; the memory stores one or more programs; the programs include instructions for executing the intelligent simulation and scheduling method for water supply networks based on digital twins as described above; the processor is used to execute the programs.

[0016] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions, which are adapted to be loaded and executed by a processor to implement the steps of the intelligent simulation and scheduling method for water supply networks based on digital twins as described above.

[0017] The beneficial effects of this application are as follows: This application's embodiments collect multi-source data from the physical pipeline network to form a pipeline network basic database; construct a digital twin model corresponding to the physical pipeline network based on the pipeline network basic database, and map equipment attributes and assign initial state values ​​to the digital twin model based on the physical pipeline network; perform data mapping on the digital twin model based on the pipeline network basic database and real-time monitoring data of the physical pipeline network; perform pipeline network hydraulic simulation calculations based on the digital twin model to obtain hydraulic simulation results; compare the hydraulic simulation results with the corresponding actual monitoring data of the physical pipeline network, generate leakage analysis results based on the comparison results, and generate emergency dispatch plans based on the leakage analysis results. This application, by constructing a digital twin model that is mapped to the physical pipeline network in real time, integrating multi-source heterogeneous data for dynamic data mapping and hydraulic simulation, and combining the simulation results with the comparison of actual monitoring to generate leakage analysis and emergency dispatch plans, effectively overcomes the problems of poor real-time performance, decision-making dependence on experience, and data silos in existing technologies, providing reliable technical support for the intelligent management of the entire water supply pipeline network process. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application 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 recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the intelligent simulation and scheduling method for water supply networks based on digital twins provided in this application embodiment.

[0020] Figure 2 This is a schematic diagram of the modules of the intelligent simulation and scheduling system for water supply networks based on digital twins provided in the embodiments of this application.

[0021] Figure 3 This is a schematic block diagram of the terminal provided in the embodiments of this application. Detailed Implementation

[0022] This application discloses a method and system for intelligent simulation and scheduling of water supply networks based on digital twins. To make the objectives, technical solutions, and effects of this application clearer and more explicit, the following detailed description is provided with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining this application and are not intended to limit this application.

[0023] Those skilled in the art will understand that, unless explicitly stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application’s specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein may include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0024] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have a meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0025] To address the aforementioned deficiencies in existing technologies, this application provides a method for intelligent simulation and scheduling of water supply networks based on digital twins. The method includes: collecting multi-source data from a physical network to form a basic network database containing network spatial attributes, equipment static parameters, real-time operating data, user water usage data, and historical maintenance data; constructing a digital twin model corresponding to the physical network based on the basic network database; acquiring real-time monitoring data of the physical network; mapping attributes and assigning initial state values ​​to the digital twin model based on the basic network database; and mapping data to the digital twin model based on the real-time monitoring data of the physical network; performing hydraulic simulation calculations on the network based on the digital twin model to obtain hydraulic simulation results; the hydraulic simulation results reflect the hydraulic state distribution of pressure at each node and flow rate in each pipe segment of the entire network; comparing the hydraulic simulation results with the corresponding actual monitoring data of the physical network; generating leakage analysis results based on the comparison results; and generating an emergency scheduling plan based on the leakage analysis results. This application constructs a digital twin model that is mapped to the physical pipeline network in real time, integrates multi-source heterogeneous data for dynamic data mapping and hydraulic simulation, and generates leakage analysis and emergency dispatch schemes by comparing simulation results with actual monitoring. This effectively overcomes the problems of poor real-time performance, decision-making dependence on experience, and data silos in existing technologies, and provides reliable technical support for the intelligent management of the entire process of water supply pipeline networks.

[0026] like Figure 1 As shown, the method includes: Step S100: Collect multi-source data of the physical pipeline network to form a basic pipeline network database containing pipeline network spatial attributes, equipment static parameters, real-time operation data, user water consumption data, and operation and maintenance history data.

[0027] Specifically, the multi-source data contains at least five key pieces of information about the physical pipeline network: Pipeline spatial attribute data, including the spatial orientation, burial depth, connection relationships and geographic coordinates of pipelines, can be imported through a geographic information system (GIS) or obtained through on-site surveying and mapping, and is used to define the overall topology of the pipeline network. Static parameter data of equipment, such as the model, rated power, diameter, opening and closing threshold and other inherent attributes of key equipment such as water pumps, valves, fire hydrants, flow meters and pressure sensors. This part of the data mainly comes from equipment ledgers and as-built data. Real-time operational data is collected through SCADA systems and various online monitoring instruments deployed in the physical pipeline network. Dynamic signals such as pressure, flow rate, water level, and pump operating frequency at each monitoring point are continuously collected at a fixed sampling frequency to reflect the real-time operating conditions of the pipeline network. User water consumption data is obtained through remote water meters or revenue systems, which record the water consumption of each user node in time series, including daily water consumption patterns, instantaneous flow rate and historical consumption statistics, to provide boundary conditions and load basis for hydraulic simulation. Historical maintenance data, including past maintenance work orders, pipe burst repair records, valve operation logs, and pipeline replacement history, is used to characterize the performance degradation characteristics and weak points of the pipeline network during long-term service.

[0028] The above five types of important information can be used as association indexes based on the unique codes of each device and pipe segment in the physical pipeline network. Heterogeneous data can be fused through data cleaning, time synchronization and coordinate matching to ultimately form a pipeline network basic database with a unified structure and spatiotemporal alignment.

[0029] Step S200: Construct a digital twin model of the physical pipeline network based on the pipeline network basic database.

[0030] Specifically, this embodiment establishes a corresponding digital twin model for the physical pipeline network, serving as the computational carrier for subsequent hydraulic simulation and dynamic data mapping. First, based on the spatial attribute data of the pipeline network in the basic database, topology identification and node-based processing are used to transform the actual pipe connections, node distribution, and geographical orientation in the physical pipeline network into a topological structure diagram in digital space. Simultaneously, based on the location information in the static parameters of the equipment, virtual equipment objects such as pumps, valves, flow meters, and pressure sensors are instantiated on the corresponding nodes or pipe segments of the topology structure, thereby constructing a digital twin model consistent with the geometry and component composition of the physical pipeline network.

[0031] In one implementation, the step of constructing a digital twin model of the physical pipeline network based on the pipeline network infrastructure database includes: Based on the pipeline network database, the physical pipeline network is abstracted as a node-edge topology graph; where nodes represent pipeline connection points, valves, water pumps, water towers, water storage tanks, and user terminals; and edges represent pipe segments. By combining spatial data from a geographic information system with the node-edge topology map, a three-dimensional spatial network model is generated, resulting in a digital twin model corresponding to the physical pipeline network.

[0032] Specifically, this embodiment employs graph theory modeling and spatial information fusion to construct a digital twin model corresponding to the physical pipeline network. First, based on the spatial attributes and static parameters of the equipment stored in the pipeline network database, the physical pipeline network is abstracted into a node-edge topology graph to establish the logical connectivity of the network. Nodes include not only physical connection points between pipes but also entities with independent hydraulic boundaries or control / regulation functions, such as valves, pumps, water towers, reservoirs, and user terminals. Edges represent pipe segments connecting any two nodes, including hydraulic characteristic parameters such as pipe length, diameter, and roughness. Second, the node-edge topology graph is spatially coupled with a geographic information system (GIS). Using the geographic coordinates, ground elevation, pipeline burial depth, and surrounding terrain data provided by the GIS, three-dimensional spatial coordinates are assigned and geometric shapes reconstructed for each node and edge in the topology graph. This maps the two-dimensional logical topological relationships to a real three-dimensional geographic space, generating a three-dimensional spatial network model containing elevation information and spatial configuration. This three-dimensional spatial network model serves as the digital twin model corresponding to the physical pipeline network.

[0033] Step S300: Obtain real-time monitoring data of the physical pipeline network, perform attribute mapping and initial state assignment on the digital twin model according to the pipeline network basic database, and perform data mapping on the digital twin model according to the real-time monitoring data of the physical pipeline network.

[0034] Further, the steps of mapping attributes and assigning initial state values ​​to the digital twin model based on the pipeline network basic database, and mapping data to the digital twin model based on the real-time monitoring data of the physical pipeline network, include: Based on the pipeline network database, the equipment information corresponding to each node and the pipe segment information corresponding to each edge are mapped as static attributes to the digital twin model, and initial state values ​​are assigned. The equipment information includes: equipment location and conventional supporting attributes; the pipe segment information includes: pipe diameter, material, rated power and laying year of the pipe segment. Based on the real-time monitoring data of the physical pipeline network, pressure, flow rate, and equipment operating frequency are mapped as dynamic variables to the digital twin model.

[0035] Specifically, the data mapping step is divided into two levels: static attribute mapping and dynamic variable mapping, to represent the long-term inherent characteristics and short-term transient conditions of the physical pipeline network, respectively.

[0036] For static attribute mapping and initial state assignment, a device attribute mapping operation is performed on each virtual device object in the digital twin model. This involves retrieving inherent device parameters from the pipeline network database that do not change in real time during daily operation but only during the equipment commissioning or modification cycle. These parameters include equipment information such as equipment model, rated power, diameter, and opening / closing characteristics; pipe diameter and material properties of each pipe section; rated power and corresponding head-flow characteristics of each pump; and the laying year of each pipe and equipment. These parameters / information are then assigned to the corresponding nodes or edges in the digital twin model in the form of structured fields, ensuring that the nodes or edges maintain a high degree of consistency with the actual equipment in the physical pipeline network in terms of performance response characteristics. Once the above static attributes are assigned, they remain unchanged throughout the model's operating cycle. Finally, based on the actual operating state of the physical pipeline network at the reference time, the digital twin model is assigned an initial state value. This includes using real-time operating data stored in the pipeline network database at the reference time, such as the initial pressure of each node, the initial flow rate of each pipe segment, the initial operating frequency of the pump, and the initial opening degree of the valve, as boundary conditions, and loading them onto the corresponding nodes and devices of the digital twin model to determine the initial hydraulic state of the digital twin model at the start time.

[0037] For dynamic variable mapping, the continuous time-series signals returned by online monitoring instruments such as pressure sensors and flow meters deployed in the physical pipeline network are acquired in real time through the data acquisition and monitoring system. The real-time pressure value of each monitoring point and the instantaneous flow value of each pipe section at the current sampling time are used as dynamic variables. According to the pre-established mapping relationship between equipment codes and measuring point locations, the data receiving ports of the corresponding nodes and equipment in the digital twin model are written in real time with a fixed time step or event triggering method to update the boundary conditions, initial iteration values ​​and control parameters of the digital twin model at the current time.

[0038] Step S400: Perform hydraulic simulation calculations on the pipeline network based on the digital twin model to obtain hydraulic simulation results; the hydraulic simulation results are used to reflect the hydraulic state distribution of pressure at each node and flow rate in each pipe section of the entire pipeline network.

[0039] Specifically, this embodiment utilizes a pre-constructed and fully mapped digital twin model as a computational engine to numerically simulate the hydraulic state across the entire physical pipe network. The hydraulic simulation is based on the nodal continuity equation and pipe segment energy equation of hydraulics. It uses current dynamic variables in the digital twin model (real-time pressure at each monitoring point, instantaneous flow rate of each pipe segment, and pump operating frequency, etc.) as boundary conditions and initial iteration values, and static attributes mapped in the digital twin model, such as pipe diameter, material, roughness, and rated power, as physical constraint parameters. On the three-dimensional spatial network topology defined by the digital twin model, an iterative solution algorithm (such as the Newton-Raphson method) is used to jointly solve the entire pipe network system. During the calculation, every node and every pipe segment in the digital twin model participates in the solution operation, ensuring that the solution results cover all nodes and all pipe segments of the physical pipe network. After the solution converges, the hydraulic simulation results include the pressure calculation value of each node in the digital twin model and the flow calculation value of each pipe segment. The results are output in the form of pressure distribution of each node in the entire network and flow distribution of each pipe segment, thus fully reflecting the global hydraulic state of the physical network under the current operating conditions.

[0040] Step S500: Compare the hydraulic simulation results with the actual monitoring data of the corresponding physical pipe network, generate leakage analysis results based on the comparison results, and generate an emergency dispatch plan based on the leakage analysis results.

[0041] Furthermore, the step of comparing the hydraulic simulation results with the corresponding actual monitoring data of the physical pipe network, and generating leakage analysis results based on the comparison results, includes: For each independent metering area, the actual monitoring data of the independent metering area is extracted based on the actual monitoring data of the physical pipeline network; The minimum nighttime flow rate of the zone is calculated based on the actual monitoring data of the independent metering area. The minimum nighttime flow rate of the zone is then compared with the historical baseline nighttime flow rate to obtain the flow rate difference. If the difference in flow exceeds a set threshold, it is determined that there is a risk of leakage. The measured pressure distribution data of the independent metering area is obtained based on the actual monitoring data of the independent metering area. The theoretical pressure distribution data of the independent metering area are obtained based on the hydraulic simulation results. The measured pressure distribution data of the independent metering area is compared point by point with the corresponding theoretical pressure distribution data, and leakage analysis results are generated based on the comparison results.

[0042] Specifically, using pre-defined independent metering areas (DMAs) as the basic analysis unit, leakage analysis is performed by combining flow analysis and pressure analysis. For each DMA, the first stage of flow-based initial leakage risk assessment is performed: data from each inlet flow meter and user water meter belonging to the DMA are extracted from the actual monitoring data of the physical pipe network. After data cleaning and time synchronization, a subset of actual monitoring data for the DMA is obtained. Based on this subset of actual monitoring data, continuous flow records are extracted during the period of lowest residential water consumption in the early morning (e.g., 2:00 to 4:00). The minimum nighttime flow for the DMA during this period is calculated, for example, by calculating the average flow or minimum instantaneous flow during this period. Subsequently, the minimum nighttime flow for the DMA is compared with the pre-stored historical baseline nighttime flow corresponding to the same time window to obtain the flow difference. The historical baseline nighttime flow can be obtained by statistically smoothing the flow of the same period over the past several days. If the flow difference exceeds the preset leakage judgment threshold, the DMA is determined to have leakage risk, triggering the second stage of pressure location analysis.

[0043] In the second stage, real-time pressure values ​​of each pressure monitoring point in the independent metering area are obtained from the actual monitoring data of the physical pipeline network to form measured pressure distribution data. At the same time, the calculated pressure values ​​of all nodes in the same area at the same time are extracted from the hydraulic simulation results to form theoretical pressure distribution data. The measured pressure distribution data and the theoretical pressure distribution data are compared point by point according to the spatial location of the nodes, and the pressure deviation value of each comparison node is calculated. Areas with significant and contiguous deviations are located as potential leakage sections.

[0044] By combining the analysis results from the first and second phases, a leakage analysis result is finally generated, which includes specific details such as leakage location / section, leakage flow rate, pressure drop, and leakage severity level. This provides an effective data foundation for the subsequent intelligent development of emergency dispatch plans.

[0045] In one implementation, the step of comparing the measured pressure distribution data of the independent metering area with the corresponding theoretical pressure distribution data point by point, and generating leakage analysis results based on the point-by-point comparison results, includes: The measured pressure distribution data of the independent metering area is compared with the corresponding theoretical pressure distribution data point by point. Based on the point-by-point comparison results, the leakage location is identified and the leakage flow rate corresponding to the leakage location is calculated. Calculate the proportion of the leakage flow rate corresponding to the leakage location to the water supply of the independent metering area to obtain a first proportion; Calculate the ratio of the pressure drop at the location of the leak to the normal pressure to obtain the second ratio; The severity level of leakage corresponding to the leakage location is assessed based on the first ratio and the second ratio; Based on the location of the leakage and the corresponding leakage flow rate, pressure drop, and leakage severity level, leakage analysis results are generated.

[0046] Specifically, after acquiring the measured pressure distribution data and theoretical pressure distribution data for each node within an independent metering area, the two are spatially matched according to node numbers. For each node, the pressure deviation between the theoretical and measured pressure values ​​is calculated, forming a pressure deviation field for the entire region. Then, spatial continuity analysis is performed on the entire region's pressure deviation field, extracting node clusters whose deviation values ​​exceed a preset deviation threshold and are spatially contiguous. The pipeline areas corresponding to these node clusters are identified as potential leakage locations. Subsequently, based on the deviation between the measured and theoretical pressure at the leakage location and the resistance characteristics of the upstream and downstream pipe sections at that leakage location, the leakage flow rate corresponding to the leakage location can be calculated.

[0047] Based on this, the severity of the leakage at the location needs to be assessed: First, the leakage flow rate corresponding to the leakage location is divided by the total water supply of the independent metering area within the same time window to obtain a first proportion reflecting the proportion of water loss. Second, the measured pressure drop corresponding to the leakage location is divided by the normal pressure value at that location to obtain a second proportion reflecting the degree of pressure reduction in the water supply service. The measured pressure drop is the difference between the theoretical and measured pressures, and the normal pressure value can be selected as the average pressure value or the theoretical pressure value under historical leak-free conditions during the same period. Subsequently, based on the first and second proportions, the leakage location is graded and assessed using a preset severity level determination strategy. For example, when both the first and second proportions are higher than the high threshold, it is rated as an emergency leakage level; when one is higher than the medium threshold, it is rated as a medium leakage level; and when both are lower than the low threshold, it is rated as a general leakage level, thus obtaining the leakage severity level corresponding to the leakage location.

[0048] Finally, the spatial coordinates of the leakage location, the leakage flow rate corresponding to the leakage location, the pressure drop corresponding to the leakage location, and the leakage severity level are combined in a structured manner to form the leakage analysis results.

[0049] In one implementation, the step of generating an emergency dispatch plan based on the leakage analysis results includes: For each leakage location in the leakage analysis results, a topological connectivity analysis is performed on the leakage location using the digital twin model to generate an optimal valve shut-off scheme; the optimal valve shut-off scheme is used to determine the control valve numbers and operation sequence that need to be closed upstream and downstream of the leakage pipe segment corresponding to the leakage location; The priority of several affected nodes around the leakage location is determined by a preset node classification strategy. For the affected node with the highest priority, if the affected node is located within the valve closure area corresponding to the optimal valve closure scheme, the local scheduling scheme for the affected node is: to start the backup pump station or emergency water source. If the affected node is located outside the valve-closing area corresponding to the optimal valve-closing scheme, the local scheduling scheme for the affected node is: to reduce the water supply pressure of non-first priority sites around the affected node, or to divide the non-first priority sites around the affected node into zones for rotational water supply, so as to ensure the water supply pressure of the affected node that is in the first priority. An emergency scheduling scheme is generated based on the optimal valve closure scheme and the local scheduling scheme of the affected node with the first priority.

[0050] Specifically, for each leakage location marked in the leakage analysis results, the digital twin model is first used to perform topological connectivity analysis on the pipe segment where the leakage location is located. That is, from the node-edge topology graph of the digital twin model, starting from the leakage location, the nearest controllable valve node is traced upstream and downstream along the pipe segment. The impact range of each valve closing on the hydraulic state of surrounding nodes and the degree of water supply service reduction are comprehensively considered. By listing different valve combination schemes and conducting rapid hydraulic verification and checking, the scheme that effectively isolates the leaking pipe segment, has the fewest nodes affected by valve closing, and has the least impact on key users is selected as the optimal valve closing scheme.

[0051] Subsequently, based on the optimal valve closure scheme, the upstream and downstream control valves corresponding to the leak location in the actual physical pipe network are closed to achieve physical isolation of the leak area. Simultaneously with valve closure isolation, for several affected nodes that may suffer water outages or pressure reductions due to valve closure operations, such as user nodes, hospitals, schools, fire hydrants, and other critical water-using units, priority is assigned to the affected nodes through a pre-defined node classification strategy. This node classification strategy can be pre-set based on the water importance of each user node, the type of service recipient, and the historical water supply guarantee level.

[0052] For affected nodes of the highest priority, i.e., users with the highest protection level, such as hospitals and emergency command centers, it is determined whether they are located within the valve closure area corresponding to the optimal valve closure scheme. If so, the local scheduling scheme for the affected node is to activate backup pump stations or emergency water sources to provide emergency water supply to the affected node through alternative water supply paths or temporary pressurization measures to compensate for the water supply interruption caused by valve closure isolation. If not, i.e., the affected node of the highest priority is affected by valve closure but is outside the valve closure area, the local scheduling scheme for the affected node is to reduce the water supply pressure of non-first priority sites around it, or to implement zoned rotational supply to non-first priority sites around the affected node, thereby prioritizing the allocation of limited water volume and pressure to the affected node of the highest priority to ensure its water supply pressure. Finally, the valve numbers, valve closure sequence, and operation time arrangements involved in the optimal valve closure scheme are integrated with the local scheduling schemes corresponding to each affected node of the highest priority to form an emergency scheduling scheme that includes isolation operation instructions and supply control strategies, thereby effectively controlling the expansion of leakage while minimizing the impact on the normal water use of critical users.

[0053] In one implementation, the method further includes: The emergency dispatch plan was simulated and verified using the digital twin model. If the simulation and pre-run verification pass, an executable emergency dispatch instruction set will be output according to the emergency dispatch plan.

[0054] Specifically, to reduce on-site operational risks, this embodiment will conduct a simulation and pre-verification of the emergency dispatch plan before its actual execution. First, all operational instructions involved in the emergency dispatch plan, such as the valve closing sequence, opening adjustment amount, and operation time nodes of each valve in the optimal valve closing plan, as well as the start-up sequence of backup pump stations or emergency water sources, the pressure reduction magnitude of non-priority sites, and the switching cycle of zoned rotation supply in the local dispatch plans of each first-priority affected node, are transformed into a series of discrete simulated operational events and sequentially loaded into the digital twin model as dynamic boundary conditions or control parameter inputs.

[0055] During the simulation and verification process, the digital twin model performs hydraulic simulation calculations based on the real-time operation data and static attribute parameters mapped at the current moment, according to the operation sequence specified in the emergency dispatch plan. It dynamically simulates the entire transition process from the start of the emergency dispatch plan to the entire pipeline network reaching a new steady state or the end of the preset time window, and outputs the change trajectory of pressure at each node, flow rate of each pipe section, and pump operation status at each time step during the process.

[0056] The conditions for passing the simulation and pre-verification include, but are not limited to: the pressure of all nodes must not be lower than the preset minimum water pressure value and not higher than the upper limit of the pipeline pressure; the flow velocity of all pipe sections must not exceed the safety threshold; the leaking pipe section at the leak location must be completely isolated and there must be no backflow or reverse flow; the water pressure of each affected node of the first priority must always meet its guarantee requirements; and the entire pipeline system must converge to a stable and safe hydraulic balance state after the operation is completed.

[0057] If the simulation and pre-run verification results meet the above-mentioned pass conditions, the emergency dispatch plan can be issued and executed. For example, the various operation instructions in the emergency dispatch plan are standardized and encoded according to the control protocol format, address code, and operation parameters of the corresponding equipment in the physical pipeline network to generate an executable emergency dispatch instruction set that can be issued to the field automated execution equipment.

[0058] Based on the above embodiments, this application also provides a digital twin-based intelligent simulation and scheduling system for water supply networks, such as... Figure 2 As shown, the system includes: Data acquisition module 01 is used to collect multi-source data of the physical pipeline network to form a basic database of the pipeline network, which includes pipeline spatial attributes, equipment static parameters, real-time operating data, user water consumption data and operation and maintenance history data. Model building module 02 is used to build a digital twin model of the physical pipeline network based on the pipeline network basic database; The data mapping module 03 is used to acquire real-time monitoring data of the physical pipeline network, perform attribute mapping and initial state assignment on the digital twin model according to the pipeline network basic database, and perform data mapping on the digital twin model according to the real-time monitoring data of the physical pipeline network. The hydraulic simulation module 04 is used to perform hydraulic simulation calculations of the pipeline network based on the digital twin model to obtain hydraulic simulation results; the hydraulic simulation results are used to reflect the hydraulic state distribution of pressure at each node and flow rate of each pipe segment in the entire pipeline network. The leakage analysis and emergency dispatch module 05 is used to compare the hydraulic simulation results with the actual monitoring data of the corresponding physical pipe network, generate leakage analysis results based on the comparison results, and generate an emergency dispatch plan based on the leakage analysis results.

[0059] Based on the above embodiments, this application also provides a terminal, the principle block diagram of which can be as follows: Figure 3As shown, the terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a digital twin-based intelligent simulation and scheduling method for water supply networks. The display screen can be an LCD screen or an e-ink screen.

[0060] Those skilled in the art will understand that Figure 3 The block diagram shown is only a partial structural diagram related to the solution of this application and does not constitute a limitation on the terminal on which the solution of this application is applied. The specific terminal may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0061] In one implementation, the terminal's memory stores one or more programs, and these programs are configured to be executed by one or more processors. The programs include instructions for performing a digital twin-based intelligent simulation and scheduling method for water supply networks.

[0062] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0063] In summary, this application discloses a method and system for intelligent simulation and scheduling of water supply networks based on digital twins. The method includes: collecting multi-source data of the physical network to form a basic network database containing network spatial attributes, equipment static parameters, real-time operating data, user water consumption data, and historical operation and maintenance data; constructing a digital twin model corresponding to the physical network based on the basic network database; acquiring real-time monitoring data of the physical network; performing attribute mapping and initial state assignment on the digital twin model based on the basic network database; and performing data mapping on the digital twin model based on the real-time monitoring data of the physical network; performing hydraulic simulation calculations on the network based on the digital twin model to obtain hydraulic simulation results; the hydraulic simulation results are used to reflect the hydraulic state distribution of pressure at each node and flow rate in each pipe segment of the entire network; comparing the hydraulic simulation results with the corresponding actual monitoring data of the physical network; generating leakage analysis results based on the comparison results; and generating an emergency scheduling plan based on the leakage analysis results. This application constructs a digital twin model that is mapped to the physical pipeline network in real time, integrates multi-source heterogeneous data for dynamic data mapping and hydraulic simulation, and generates leakage analysis and emergency dispatch schemes by comparing simulation results with actual monitoring. This effectively overcomes the problems of poor real-time performance, decision-making dependence on experience, and data silos in existing technologies, and provides reliable technical support for the intelligent management of the entire process of water supply pipeline networks.

[0064] It should be understood that the application of this application is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A digital-twin-based intelligent simulation and scheduling method for water supply networks, characterized in that, The method includes: Collect multi-source data of the physical pipeline network to form a basic database of the pipeline network that includes pipeline spatial attributes, equipment static parameters, real-time operation data, user water consumption data and operation and maintenance history data; A digital twin model of the physical pipeline network is constructed based on the pipeline network database. The system acquires real-time monitoring data of the physical pipeline network, performs attribute mapping and initial state assignment on the digital twin model based on the pipeline network basic database, and performs data mapping on the digital twin model based on the real-time monitoring data of the physical pipeline network. Based on the digital twin model, hydraulic simulation calculations of the pipeline network are performed to obtain hydraulic simulation results; the hydraulic simulation results are used to reflect the hydraulic state distribution of pressure at each node and flow rate in each pipe section of the entire pipeline network. The hydraulic simulation results are compared with the actual monitoring data of the corresponding physical pipe network. Based on the comparison results, leakage analysis results are generated, and an emergency dispatch plan is generated based on the leakage analysis results.

2. The intelligent simulation and scheduling method for water supply networks based on digital twins according to claim 1, characterized in that, The steps for constructing a digital twin model of the physical pipeline network based on the pipeline network database include: Based on the pipeline network database, the physical pipeline network is abstracted as a node-edge topology graph; where nodes represent pipeline connection points, valves, water pumps, water towers, water storage tanks, and user terminals; and edges represent pipe segments. By combining spatial data from a geographic information system with the node-edge topology map, a three-dimensional spatial network model is generated, resulting in a digital twin model corresponding to the physical pipeline network.

3. The digital-twin-based intelligent simulation and scheduling method for water supply networks according to claim 2, characterized in that, The steps of mapping attributes and assigning initial state values ​​to the digital twin model based on the pipeline network basic database, and mapping data to the digital twin model based on the real-time monitoring data of the physical pipeline network, include: Based on the pipeline network database, the equipment information corresponding to each node and the pipe segment information corresponding to each edge are mapped as static attributes to the digital twin model, and initial state values ​​are assigned. The equipment information includes: equipment location and conventional supporting attributes; the pipe segment information includes: pipe diameter, material, rated power and laying year of the pipe segment. Based on the real-time monitoring data of the physical pipeline network, pressure, flow rate, and equipment operating frequency are mapped as dynamic variables to the digital twin model.

4. The digital-twin-based intelligent simulation and scheduling method for water supply networks according to claim 1, characterized in that, The steps for generating leakage analysis results based on the comparison between the hydraulic simulation results and the corresponding actual monitoring data of the physical pipe network include: For each independent metering area, the actual monitoring data of the independent metering area is extracted based on the actual monitoring data of the physical pipeline network; The minimum nighttime flow rate of the zone is calculated based on the actual monitoring data of the independent metering area. The minimum nighttime flow rate of the zone is then compared with the historical baseline nighttime flow rate to obtain the flow rate difference. If the difference in flow exceeds a set threshold, it is determined that there is a risk of leakage. The measured pressure distribution data of the independent metering area is obtained based on the actual monitoring data of the independent metering area. The theoretical pressure distribution data of the independent metering area are obtained based on the hydraulic simulation results. The measured pressure distribution data of the independent metering area is compared point by point with the corresponding theoretical pressure distribution data, and leakage analysis results are generated based on the comparison results.

5. The digital-twin-based intelligent simulation and scheduling method for water supply networks according to claim 4, characterized in that, The steps of comparing the measured pressure distribution data of the independent metering area with the corresponding theoretical pressure distribution data point by point, and generating leakage analysis results based on the point-by-point comparison results, include: The measured pressure distribution data of the independent metering area is compared with the corresponding theoretical pressure distribution data point by point. Based on the point-by-point comparison results, the leakage location is identified and the leakage flow rate corresponding to the leakage location is calculated. Calculate the proportion of the leakage flow rate corresponding to the leakage location to the water supply of the independent metering area to obtain a first proportion; Calculate the ratio of the pressure drop at the location of the leak to the normal pressure to obtain the second ratio; The severity level of leakage corresponding to the leakage location is assessed based on the first ratio and the second ratio; Based on the location of the leakage and the corresponding leakage flow rate, pressure drop, and leakage severity level, leakage analysis results are generated.

6. The intelligent simulation and scheduling method for water supply networks based on digital twins according to claim 1, characterized in that, The steps for generating an emergency dispatch plan based on the leakage analysis results include: For each leakage location in the leakage analysis results, a topological connectivity analysis is performed on the leakage location using the digital twin model to generate an optimal valve shut-off scheme; the optimal valve shut-off scheme is used to determine the control valve numbers and operation sequence that need to be closed upstream and downstream of the leakage pipe segment corresponding to the leakage location; The priority of several affected nodes around the leakage location is determined by a preset node classification strategy. For the affected node with the highest priority, if the affected node is located within the valve closure area corresponding to the optimal valve closure scheme, the local scheduling scheme for the affected node is: to start the backup pump station or emergency water source. If the affected node is located outside the valve-closing area corresponding to the optimal valve-closing scheme, the local scheduling scheme for the affected node is: to reduce the water supply pressure of non-first priority sites around the affected node, or to divide the non-first priority sites around the affected node into zones for rotational water supply, so as to ensure the water supply pressure of the affected node that is in the first priority. An emergency scheduling scheme is generated based on the optimal valve closure scheme and the local scheduling scheme of the affected node with the first priority.

7. The digital-twin-based intelligent simulation and scheduling method for water supply networks according to claim 1, characterized in that, The method further includes: The emergency dispatch plan was simulated and verified using the digital twin model. If the simulation and pre-run verification pass, an executable emergency dispatch instruction set will be output according to the emergency dispatch plan.

8. A digital-twin-based intelligent simulation and scheduling system for a water supply network, characterized in that, The system includes: The data acquisition module is used to collect multi-source data from the physical pipeline network to form a basic pipeline database that includes pipeline spatial attributes, equipment static parameters, real-time operating data, user water consumption data, and operation and maintenance history data. The model building module is used to build a digital twin model of the physical pipeline network based on the pipeline network basic database. The data mapping module is used to acquire real-time monitoring data of the physical pipeline network, perform attribute mapping and initial state assignment on the digital twin model according to the pipeline network basic database, and perform data mapping on the digital twin model according to the real-time monitoring data of the physical pipeline network. The hydraulic simulation module is used to perform hydraulic simulation calculations of the pipeline network based on the digital twin model, and obtain hydraulic simulation results; the hydraulic simulation results are used to reflect the hydraulic state distribution of pressure at each node and flow rate of each pipe segment in the entire pipeline network. The leakage analysis and emergency dispatch module is used to compare the hydraulic simulation results with the actual monitoring data of the corresponding physical pipe network, generate leakage analysis results based on the comparison results, and generate an emergency dispatch plan based on the leakage analysis results.

9. A terminal, characterized by comprising: The terminal includes a memory and one or more processors; the memory stores one or more programs; the programs contain instructions for executing the intelligent simulation and scheduling method for water supply networks based on digital twins as described in any one of claims 1 to 7; the processors are used to execute the programs.

10. A computer readable storage medium having stored thereon a plurality of instructions, the plurality of instructions comprising instructions for causing a processor to: 5 The instructions are applicable to be loaded and executed by a processor to implement the steps of the intelligent simulation and scheduling method for water supply networks based on digital twins as described in any one of claims 1 to 7.

Images