An intelligent scheduling method for waterlogging of important urban infrastructure

Abstract

The present invention relates to the technical field of urban waterlogging prevention and control, and in particular to an intelligent scheduling method for waterlogging in important urban infrastructure. The method comprises the following steps: collecting and processing basic data including urban topography, pipe network, hydrology, rainfall, waterlogging, etc.; establishing an urban waterlogging model that couples a one-dimensional pipe network with a two-dimensional surface, and verifying and calibrating the model; combining important infrastructure and waterlogging buffer zones, setting protection targets and permissible ranges for waterlogging, performing initialization simulations, and obtaining initial waterlogging conditions; dynamically adjusting scheduling parameters such as pump station flow and valve switches through optimization algorithms, generating an optimal scheduling parameter group, and executing scheduling strategies; dynamically adjusting the model initial field through comparative analysis of real-time monitoring data and simulation results, and iteratively optimizing until the waterlogging control target is achieved. The present invention can effectively reduce the risk of waterlogging in important urban infrastructure and improve the scheduling efficiency and emergency response capabilities of drainage systems.

Description

Technical Field

[0001] The present invention relates to the technical field of urban waterlogging prevention and control, and in particular to an intelligent scheduling method for waterlogging of important urban infrastructure. Background Art

[0002] Urban flooding has become a major challenge facing urban flood control and drainage systems. Especially under extreme weather conditions, the sudden onset and rapid spread of floodwater pose a serious threat to the normal operation of critical urban infrastructure, such as transportation hubs and power facilities. Existing flood control and prevention methods primarily rely on passive flood model simulations. While these methods can identify the location and extent of flooding, the lack of an effective dynamic scheduling mechanism results in passive and lagging drainage strategies, effectively limiting them to passive defense.

[0003] In addition, traditional smart drainage methods for urban pipelines mainly focus on monitoring the internal status of the pipeline network and achieving optimization by adjusting the pipeline network drainage strategy. However, this method is mostly limited to the pipeline system itself, ignoring the dynamic interaction between the one-dimensional pipeline network and surface water, and unable to simulate the formation and evolution process of surface water. The ability to prevent and control the risk of water accumulation in important infrastructure is insufficient. Summary of the Invention

[0004] Based on this, it is necessary for the present invention to provide an intelligent scheduling method for urban waterlogging of important infrastructure to solve at least one of the above technical problems.

[0005] To achieve the above objectives, a method for intelligently dispatching urban waterlogging for important urban infrastructure includes the following steps:

[0006] Step S1: Obtaining basic geographic data of an urban area, urban area pipe network data, urban area hydrological data, urban area rainfall data, and urban area waterlogging data; performing an urban area pipe network topology inspection based on the urban area pipe network data, thereby obtaining urban area pipe network inspection data; integrating urban area surface features based on the basic geographic data of the urban area, thereby obtaining urban area surface feature data; performing data preprocessing based on the urban area rainfall data and the urban area waterlogging data, thereby obtaining the urban area rainfall data to be analyzed and the urban area waterlogging data to be analyzed;

[0007] Step S2: constructing a one-dimensional pipe network model based on the urban area pipe network inspection data; constructing a two-dimensional surface model based on the urban area surface feature data; coupling the one-dimensional pipe network model and the two-dimensional surface model to obtain a coupled waterlogging model, and automatically calibrating and optimizing the coupled waterlogging model using an ant colony algorithm to obtain an urban waterlogging model;

[0008] Step S3: Obtaining important infrastructure data in the urban area, and calculating the waterlogging range of the important infrastructure in the urban area based on the surface characteristic data of the urban area, thereby obtaining waterlogging range data of the important infrastructure in the urban area; selecting an urban waterlogging buffer zone based on the surface characteristic data of the urban area, thereby obtaining urban waterlogging buffer zone data; and setting an allowable waterlogging range for the urban waterlogging buffer zone data, thereby obtaining allowable waterlogging range data for the waterlogging buffer zone;

[0009] Step S4: Performing urban waterlogging simulation on the urban area rainfall data using the urban waterlogging model to obtain first urban waterlogging simulation data; performing regional waterlogging division on the urban area important infrastructure data and the urban waterlogging buffer zone data based on the first urban waterlogging simulation data to obtain important infrastructure area waterlogging data and urban waterlogging buffer zone waterlogging data; determining waterlogging scheduling parameters for the important infrastructure area waterlogging data and the urban waterlogging buffer zone waterlogging data based on the important urban infrastructure area waterlogging range data and the waterlogging buffer zone waterlogging allowable range data to obtain an urban area waterlogging scheduling parameter group, and uploading the group to the urban drainage management platform to execute the waterlogging scheduling task;

[0010] Step S5: Using the urban area waterlogging scheduling parameter group to update the model parameters of the urban waterlogging model, thereby obtaining an urban waterlogging scheduling model; and using the urban waterlogging scheduling model to simulate urban area rainfall data, thereby obtaining second urban waterlogging simulation data; obtaining real-time urban area waterlogging data, and performing a difference analysis on the second urban waterlogging simulation data and the real-time urban area waterlogging data, thereby obtaining a scheduling difference report;

[0011] Step S6: Update the model input of the urban waterlogging scheduling model according to the scheduling difference report to obtain an updated urban waterlogging model. Based on the updated urban waterlogging model, re-execute steps S4 and S5, and continuously iterate and optimize the scheduling parameters through difference analysis between the new simulation results and the real-time urban area waterlogging data until the difference meets the preset conditions.

[0012] Optionally, step S1 specifically includes:

[0013] Step S11: Acquire urban area geographic basic data, urban area pipe network data, urban area hydrological data, urban area rainfall data, and urban area waterlogging data, wherein the urban area geographic basic data includes urban area topography data and urban area land use type data;

[0014] Step S12: performing a pipe network connection node consistency check on the urban area pipe network data, thereby obtaining pipe network connection consistency node data, and performing a pipe section continuity check based on the pipe network connection consistency node data, thereby obtaining urban area pipe network inspection data;

[0015] Step S13: Based on the urban area land use type data, regional division is performed according to a preset land use classification standard, thereby obtaining land use type regional data;

[0016] Step S14: integrating the land use type regional data and the urban area terrain data into regional surface characteristics, thereby obtaining urban area surface characteristic data;

[0017] Step S15: performing data preprocessing on the urban area rainfall data and the urban area waterlogging data, respectively, to obtain the urban area rainfall data to be analyzed and the urban area waterlogging data to be analyzed.

[0018] Optionally, step S2 is specifically:

[0019] Step S21: constructing a one-dimensional pipe network model based on the urban area pipe network inspection data;

[0020] Step S22: constructing a two-dimensional surface model based on the urban area surface feature data;

[0021] Step S23: performing coupling model time step matching on the one-dimensional pipe network model and the two-dimensional surface model to obtain a time step coordinated model set; performing water exchange calculation on the time step coordinated model set to obtain a water exchange model set;

[0022] Step S24: performing boundary condition coupling on the water exchange model set to obtain a boundary condition coupling model; dynamically updating the boundary condition coupling model according to rainfall data and waterlogging data in the urban area to be analyzed to obtain a coupled waterlogging model;

[0023] Step S25: using an ant colony algorithm to automatically calibrate and optimize the coupled waterlogging model, thereby obtaining an urban waterlogging model.

[0024] Optionally, step S21 is specifically as follows:

[0025] Step S211: extracting pipe network pump station parameter features, pipe network parameter features, and pipe network liquid level features from the urban area pipe network inspection data, thereby obtaining pipe network pump station data, pipe network pipeline data, and pipe network liquid level data;

[0026] Step S212: Formatting and integrating the pipeline network pump station data, pipeline network pipeline data, and pipeline network liquid level data to obtain a pipeline parameter set;

[0027] Step S213: constructing a pipe network topology model based on the pipe parameter set;

[0028] Step S214: setting water flow exchange boundary conditions based on the pipe network liquid level data and the pipe network pump station data, thereby obtaining water flow exchange boundary conditions;

[0029] Step S215: constructing a one-dimensional pipe network model according to the pipe network topology model and the water flow exchange boundary conditions.

[0030] Optionally, step S22 is specifically as follows:

[0031] Step S221: extracting regional elevation features from urban area surface feature data to obtain urban area elevation data;

[0032] Step S222: Based on the land use type regional data and in combination with the preset correspondence between land use and surface attributes, the infiltration conditions and Manning coefficients of different regions are derived, thereby obtaining regional infiltration condition data and regional Manning coefficient data;

[0033] Step S223: setting hydrological boundary conditions based on the urban area hydrological data, thereby obtaining hydrological boundary conditions;

[0034] Step S224: constructing a two-dimensional surface model based on water exchange boundary conditions, urban area elevation data, regional infiltration condition data, and regional Manning coefficient data.

[0035] Optionally, step S3 specifically includes:

[0036] Step S31: Acquire important infrastructure data in the urban area, and extract the geographical location of the important infrastructure and the waterlogging prevention needs of the important infrastructure in the urban area, thereby obtaining the geographical location data of the important infrastructure and the waterlogging prevention needs data of the important infrastructure;

[0037] Step S32: extracting surface features of important infrastructure locations from the urban area surface feature data based on the important infrastructure geographic location data, thereby obtaining surface feature data of important infrastructure locations;

[0038] Step S33: Calculating the upper limit of the waterlogging area and the upper limit of the waterlogging depth of the important infrastructure based on the surface characteristic data of the location of the important infrastructure and the waterlogging prevention demand data of the important infrastructure, thereby obtaining the waterlogging range data of the important urban infrastructure;

[0039] Step S34: selecting an urban waterlogging buffer zone based on the urban area surface characteristic data to obtain urban waterlogging buffer zone data, and integrating the surface characteristics of the buffer zones on the urban waterlogging buffer zone data to obtain surface characteristic data of the waterlogging buffer zones;

[0040] Step S35: setting a water accumulation area threshold and a water accumulation depth threshold for the surface characteristic data of the water accumulation buffer zone, thereby obtaining data on the allowable range of water accumulation in the water accumulation buffer zone.

[0041] Optionally, step S34 is specifically as follows:

[0042] Extracting terrain elevation features, permeability features, and vegetation coverage features from urban area surface feature data, thereby obtaining urban area vegetation coverage data, urban area permeability data, and urban area terrain elevation data;

[0043] Extract the pipe network distribution characteristics from the urban area pipe network inspection data to obtain the drainage pipe network distribution data;

[0044] Identify low-lying areas based on urban area terrain elevation data to obtain low-lying area data;

[0045] Select high vegetation coverage areas from urban area vegetation coverage data to obtain high vegetation coverage area data;

[0046] Screening the urban area permeability data for high permeability areas to obtain high permeability area data;

[0047] Select the pipe network coverage area based on the drainage pipe network distribution data to obtain the pipe network coverage area data;

[0048] Allocating land use type priorities based on urban area land use type data to obtain land use type priority data, and dividing sub-priority areas based on the land use type priority data to obtain land use sub-priority area data;

[0049] Perform spatial overlay analysis on low-lying area data, high vegetation coverage area data, high permeability area data, pipe network coverage area data, and land use secondary priority area data to generate urban waterlogging buffer zone data;

[0050] Based on the urban waterlogging buffer zone data, the surface characteristic data of the urban area are integrated to obtain the surface characteristic data of the waterlogging buffer zone.

[0051] Optionally, step S4 is specifically:

[0052] Step S41: performing urban waterlogging simulation on the urban area rainfall data using an urban waterlogging model, thereby obtaining first urban waterlogging simulation data;

[0053] Step S42: Based on the first urban waterlogging simulation data, the urban area important infrastructure data and the urban waterlogging buffer zone data are divided into regional waterlogging data, thereby obtaining important infrastructure area waterlogging data and urban waterlogging buffer zone waterlogging data; and waterlogging benchmarks are set based on the important infrastructure area waterlogging data and the urban waterlogging buffer zone waterlogging data, thereby obtaining initial simulated waterlogging benchmark data.

[0054] Step S43: extracting the pipe network pump station and valve control parameters from the urban area pipe network inspection data, thereby obtaining pump station control parameter data and valve control parameter data;

[0055] Step S44: setting an objective function and constraints based on the water accumulation range data of important urban infrastructure and the water accumulation allowable range data of the water accumulation buffer zone, thereby obtaining a fitness function and a constraint condition function;

[0056] Step S45: generating an initialized particle swarm based on the initial simulated waterlogging benchmark data, the fitness function, and the constraint condition function, and based on the pump station control parameter data and the valve control parameter data; calculating the initial fitness values ​​of the particles in the initialized particle swarm; selecting the global optimal particle from the initial fitness values ​​of the particles; and recording the individual optimal solution of each particle, thereby obtaining the global optimal particle and the individual optimal solution of the particle;

[0057] Step S46: Iteratively optimize based on the constraint function and the global optimal particle and the individual optimal solution of the particle until the preset early stopping condition is met, thereby obtaining the global optimal solution;

[0058] Step S47: convert the global optimal solution into waterlogging scheduling parameters to obtain a waterlogging scheduling parameter group for the urban area, and upload it to the urban drainage management platform to execute the waterlogging scheduling task.

[0059] Optionally, step S44 is specifically as follows:

[0060] Step S441: constructing a penalty function based on the water accumulation allowable range data of the water accumulation buffer zone;

[0061] Step S442: Constructing a fitness function based on the penalty function and the waterlogging range data of important urban infrastructure, wherein the fitness function is specifically:

[0062]

[0063] Where f is the fitness function value, n is the total number of important infrastructures, i is the index of important infrastructure, α is the global weight of the buffer penalty, and w i is the weight used to control the water depth of the i-th important infrastructure in the fitness function, k i is the weight of the waterlogged area of ​​the i-th important infrastructure in the fitness function, D i is the water depth of the i-th important infrastructure, d i is the water depth target of the i-th important infrastructure, A i is the waterlogged area of ​​the i-th important infrastructure, a i is the waterlogging area target of the i-th important infrastructure, At is the total waterlogging area excluding the waterlogging buffer zone, and A tr is the total waterlogged area target excluding the waterlogged buffer zone, and K is the weight of the total waterlogged area;

[0064] The present invention constructs a fitness function by consulting relevant materials and deducing. This function fully considers the global weight α of the buffer penalty that affects the fitness function value f, and is used to control the weight w of the water depth of the i-th important infrastructure in the fitness function. i , used to control the weight k of the waterlogged area of ​​the i-th important infrastructure in the fitness function i , the water depth D of the i-th important infrastructure i , the water depth target d of the i-th important infrastructure i , the waterlogged area A of the i-th important infrastructure i , the water accumulation area target a of the i-th important infrastructure i , excluding the total waterlogged area A of the waterlogged buffer zone t , excluding the total waterlogged area target A of the waterlogged buffer zone tr , the weight K of the total waterlogged area forms a functional relationship:

[0065]

[0066] in, First, the deviation of the water depth and area is calculated (that is, the difference between the actual value and the target value). The max(0,X) function is used to ensure that the deviation will not have a negative impact on the fitness function when it is negative, that is, when the water depth or area does not exceed the target value, this item will not penalize the fitness function. When the water depth or area exceeds the target value, a positive penalty will be generated on the fitness function. This item ensures that the drainage system focuses on the safety of infrastructure when optimizing by controlling the difference between the water depth and area and the target value, and reduces the impact of excessive water on the city. Through w i and k iThe weight coefficient can adjust the priority of water depth and area according to the specific needs of different infrastructures, thus achieving more precise control. t ―A tr ) part reflects the total control of the water accumulation area in the whole system. t Exceed the preset target A tr When , a penalty value is generated, which is proportional to the weight K. This means that if the total flooded area exceeds the target, the fitness value will increase, thereby guiding the optimization algorithm to avoid large-scale flooding as much as possible. This ensures that the drainage system not only controls the flooding of individual infrastructure, but also pays attention to the flooding of the entire city or region to avoid large-scale flooding disasters. By introducing the weight K of the total flooded area, the drainage capacity of each area of ​​the city and the consistency of the flooding control target can be guaranteed during the optimization of the overall drainage system. α·f buffer The introduction of is intended to ensure the effectiveness of the use of the buffer zone, to avoid excessive water accumulation in the buffer zone, or to allow the water accumulation in the buffer zone to exceed the predetermined safety range, thereby avoiding system collapse in extreme weather conditions. The buffer zone is used to temporarily accommodate accumulated water that cannot be immediately removed, ensuring that in extreme rainfall conditions, accumulated water does not directly threaten the safety of important infrastructure. The effectiveness of the buffer zone can be ensured by penalizing situations where the buffer zone capacity is exceeded. The weight coefficient α can flexibly adjust the importance of the buffer zone in the entire drainage optimization, thereby giving priority to ensuring sufficient buffer zone capacity in extreme cases. The fitness function ensures that both local and global drainage goals are taken into account during the optimization process by comprehensively evaluating the water accumulation depth and area of ​​each infrastructure, the total water accumulation area, and the buffer zone capacity. Through appropriate weight coefficients w i 、k i The settings of ,K, and α can adjust the optimization strategy according to the specific needs of different infrastructures, thereby reducing the impact of water disasters on infrastructure and ensuring the safety of urban operations.

[0067] Step S443: constructing a control parameter constraint condition function according to the pump station control parameter data and the valve control parameter data, thereby obtaining a constraint condition function.

[0068] Optionally, step S45 is specifically as follows:

[0069] Step S451: performing random combinations of scheduling parameters based on the constraint condition function, the pump station control parameter data, and the valve control parameter data, thereby obtaining control scheduling parameter combination data;

[0070] Step S452: Initialize particles according to the control scheduling parameter combination data to obtain an initialized particle swarm;

[0071] Step S453: performing urban waterlogging simulation on the urban area rainfall data and the initialized particle swarm using the urban waterlogging model, thereby obtaining initialized particle simulation data;

[0072] Step S454: performing particle initialization fitness calculation on the initialized particle simulation data using a fitness function, thereby obtaining the particle initial fitness value;

[0073] Step S455: performing individual optimal solution selection on the initial fitness value of the particle to obtain the individual optimal solution of the particle, and performing global optimal solution screening based on the individual optimal solution of the particle to obtain the global optimal particle.

[0074] The present invention effectively compensates for the lack of linkage between traditional urban waterlogging prediction and scheduling technologies through multi-dimensional data integration and intelligent scheduling methods, and has significant beneficial effects. By acquiring and preprocessing urban area geographical basic data, pipe network data, hydrological data, rainfall data, and waterlogging data, an accurate data input basis is provided for subsequent analysis. These data cover basic data such as urban topography, pipe network, hydrology, rainfall, and waterlogging, making decisions on waterlogging scheduling more scientific and accurate. In the process of pipe network model construction and coupled optimization, by combining a one-dimensional pipe network model with a two-dimensional surface model and using an ant colony algorithm for automatic calibration and optimization, it is possible to quickly search for the optimal solution under multi-variable and complex conditions, greatly improving the calibration efficiency and accuracy of the model. In response to the limitations of the existing system, the introduction of a waterlogging buffer zone provides an effective auxiliary measure for urban waterlogging prevention and control. The waterlogging buffer zone can serve as a buffer space between surface waterlogging and the drainage system, effectively reducing the instantaneous pressure on the drainage system by absorbing the short-term waterlogging load. By coupling simulations of a one-dimensional pipe network model with a two-dimensional surface model, combined with an optimization algorithm to dynamically control scheduling parameters such as pumping stations and valves in the pipe network, accumulated water can be scientifically directed to appropriate waterlogging buffer zones, fully utilizing the buffer zones' storage capacity to avoid waterlogging risks in critical infrastructure areas and achieve refined and efficient management of urban flood control. By analyzing data on critical infrastructure in urban areas and calculating the extent of waterlogging, critical infrastructure at risk from waterlogging can be clearly identified and appropriate preventative measures formulated. Combined with the selection and optimization of waterlogging buffer zones, more flexible and efficient scheduling strategies can be implemented for urban flood control and drainage systems, ensuring timely protection of critical facilities during waterlogging events and minimizing or preventing losses. Waterlogging simulations and iterative optimization of scheduling parameters fully consider actual rainfall conditions, waterlogging data, and drainage network capacity, ensuring real-time adjustments to scheduling strategies in a dynamically changing waterlogging environment. For example, analysis of waterlogging discrepancy reports enables real-time optimization of scheduling parameters and updates of model initial conditions, avoiding the inefficiencies and delayed responses often associated with traditional models. Overall, the advantages of this approach lie in its integration of a coupled model of a one-dimensional pipe network and a two-dimensional surface, pipe network drainage optimization, and the introduction of a waterlogging buffer zone as a key auxiliary measure for waterlogging prevention and control. By optimizing the scheduling algorithm, it provides an intelligent and precise solution to waterlogging issues in critical urban infrastructure. It not only predicts waterlogging but also dynamically adjusts the drainage system to scientifically direct accumulated water into the buffer zone, alleviating pressure on the drainage system. This approach achieves proactive defense and intelligent optimization in drainage scheduling and waterlogging prevention and control management, effectively reducing the impact of waterlogging on critical urban infrastructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0076] Figure 1 This is a schematic flow chart of the steps of an intelligent scheduling method for urban waterlogging and important infrastructure according to the present invention;

[0077] Figure 2 The urban area pipe network distribution map in the urban area pipe network inspection data in step S1;

[0078] Figure 3 This is a schematic diagram of water accumulation in the urban area before water accumulation regulation;

[0079] Figure 4 Schematic diagram of water accumulation in an urban area after water accumulation regulation according to the present invention;

[0080] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0081] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0082] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0083] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0084] To achieve this, please refer to Figures 1 to 4 The present invention provides an intelligent scheduling method for waterlogging of important urban infrastructure, which can be an intelligent scheduling method for waterlogging of urban infrastructure. The method includes the following steps:

[0085] Step S1: Obtaining basic geographic data of an urban area, urban area pipe network data, urban area hydrological data, urban area rainfall data, and urban area waterlogging data; performing an urban area pipe network topology inspection based on the urban area pipe network data, thereby obtaining urban area pipe network inspection data; integrating urban area surface features based on the basic geographic data of the urban area, thereby obtaining urban area surface feature data; performing data preprocessing based on the urban area rainfall data and the urban area waterlogging data, thereby obtaining the urban area rainfall data to be analyzed and the urban area waterlogging data to be analyzed;

[0086] In this embodiment, the geographic information of the urban area, including topography, landform, hydrology, land use type, etc., is obtained through the GIS system. The data format is GeoTIFF or Shapefile for subsequent analysis. Data is extracted from the SCADA system of the urban drainage system or the municipal pipe network management platform, including pipe location, diameter, material, pipe network nodes, etc. The data is stored in the form of a database (such as PostGIS) and imported into a modeling tool for topological analysis. The past 24 hours or long-term historical rainfall data is obtained through a meteorological station or ground monitoring station. The data is in the form of time series data (such as CSV format), including time, rainfall and rainfall intensity. Data such as waterlogging time, waterlogging depth, and duration are obtained from the urban area's waterlogging monitoring station, and the format is usually CSV or Excel. Use geographic information system (GIS) software or dedicated pipe network management software (such as EPANET, SWMM) to perform pipe network topology inspection. The inspection content includes pipe connection consistency check, pipe continuity check and network topology structure integrity verification. Combined with the city's geographic basic data, the city's surface features, such as urban green space, buildings, roads and water body distribution, are analyzed. Remote sensing image processing technology is used to extract the boundary information of buildings, roads, and water bodies, and GIS tools are used to analyze and determine land cover types. Time series data filling, missing value interpolation, and outlier detection are performed on rainfall and waterlogging data to obtain rainfall and waterlogging data for the urban areas to be analyzed.

[0087] Step S2: constructing a one-dimensional pipe network model based on the urban area pipe network inspection data; constructing a two-dimensional surface model based on the urban area surface feature data; coupling the one-dimensional pipe network model and the two-dimensional surface model to obtain a coupled waterlogging model, and automatically calibrating and optimizing the coupled waterlogging model using an ant colony algorithm to obtain an urban waterlogging model;

[0088] In this embodiment, a one-dimensional pipe network modeling tool (such as SWMM) is used to construct a one-dimensional pipe network model of the urban area based on the pipe network topology inspection data. The model includes modules such as pipelines, pump stations, and outlets, and parameters include the geometric properties of the pipes (such as length and diameter), friction coefficient, sub-catchment area, rainfall data, and pump station operation characteristics. In combination with GIS tools and urban geographic basic data, a two-dimensional surface model of the city is constructed using professional two-dimensional surface modeling tools (such as MIKE). The two-dimensional surface model includes characteristic parameters such as urban topography, surface permeability, and surface friction coefficient, which are used to simulate the surface runoff behavior after rainfall. The dynamic coupling of the one-dimensional pipe network model and the two-dimensional surface model is achieved through programming. An interface program is written in Python or other programming languages, and the SWMM API (such as pyswmm) and the data interface of the two-dimensional model are called to complete the data interaction and linkage simulation between the models. During the programming process, the flow rate of the one-dimensional pipe network and the water volume of the two-dimensional surface are exchanged as key input and output parameters, and the model boundary conditions are dynamically updated. During the optimization and calibration stage, the parameters of the SWMM pipe network model and the two-dimensional surface model are adjusted respectively for the key parameters in the coupled waterlogging model. The ant colony algorithm is used to quickly realize the automatic calibration of the model parameters, and finally the optimized coupled waterlogging model is generated.

[0089] Step S3: Obtaining important infrastructure data in the urban area, and calculating the waterlogging range of the important infrastructure in the urban area based on the surface characteristic data of the urban area, thereby obtaining waterlogging range data of the important infrastructure in the urban area; selecting an urban waterlogging buffer zone based on the surface characteristic data of the urban area, thereby obtaining urban waterlogging buffer zone data; and setting an allowable waterlogging range for the urban waterlogging buffer zone data, thereby obtaining allowable waterlogging range data for the waterlogging buffer zone;

[0090] In this embodiment, based on the surface characteristic data of the urban area and the waterlogging prevention needs of important infrastructure, the waterlogging range of important infrastructure (such as hospitals, power plants, transportation hubs, etc.) in the urban area is calculated, including the waterlogging depth and area. The calculation of the waterlogging range comprehensively considers the terrain characteristics and functional protection needs of the facility's location to ensure that the assessment results are scientific and targeted. Based on the surface characteristic data of the urban area, including factors such as terrain, elevation, vegetation coverage, permeability, drainage network distribution and land use priority, a spatial overlay analysis method is used to select areas around important infrastructure that are suitable as waterlogging buffer zones to generate urban waterlogging buffer zone data. According to the functional requirements of important infrastructure, the maximum depth and duration of waterlogging allowed are set. For example, for key areas such as transportation hubs or power facilities, the allowable waterlogging depth and duration must be strictly limited to ensure the normal operation of the facilities; for areas such as parks and green spaces, if selected as waterlogging buffer zones, the upper limits of the allowable waterlogging depth and duration can be appropriately increased to give full play to the storage capacity of the buffer zone and reduce the pressure on the overall drainage system.

[0091] Step S4: Performing urban waterlogging simulation on the urban area rainfall data using the urban waterlogging model to obtain first urban waterlogging simulation data; performing regional waterlogging division on the urban area important infrastructure data and the urban waterlogging buffer zone data based on the first urban waterlogging simulation data to obtain important infrastructure area waterlogging data and urban waterlogging buffer zone waterlogging data; determining waterlogging scheduling parameters for the important infrastructure area waterlogging data and the urban waterlogging buffer zone waterlogging data based on the important urban infrastructure area waterlogging range data and the waterlogging buffer zone waterlogging allowable range data to obtain an urban area waterlogging scheduling parameter group, and uploading the group to the urban drainage management platform to execute the waterlogging scheduling task;

[0092] In this embodiment, the optimized urban waterlogging model is used to simulate waterlogging conditions by inputting future forecast rainfall data. The simulation results include waterlogging depth and range. Based on the results of the first round of waterlogging simulation, the urban area is divided into waterlogging areas. A geographic information system is used for spatial analysis to determine which areas are most severely waterlogged and which infrastructure is most affected, which serves as the initial input for algorithms such as particle swarm optimization. An urban waterlogging scheduling model is constructed based on the particle swarm optimization algorithm, with the goal of minimizing the depth and area of ​​waterlogging in important infrastructure areas. A fitness function is constructed and a penalty function for the range and depth of waterlogging in the buffer zone is set. According to the objective function, scheduling parameters such as the start and stop time of the pump station, operating power, and the opening and closing status of the drainage valve are optimized. Particle initialization, iterative optimization, and fitness calculation are performed in combination with the model constraints. Finally, the global optimal solution is output to generate an optimized scheduling parameter configuration plan for the pump station and valve, that is, a waterlogging scheduling parameter group for the urban area. The parameter group is uploaded to the urban drainage management platform to perform the waterlogging scheduling task.

[0093] Step S5: Using the urban area waterlogging scheduling parameter group to update the model parameters of the urban waterlogging model, thereby obtaining an urban waterlogging scheduling model; and using the urban waterlogging scheduling model to simulate urban area rainfall data, thereby obtaining second urban waterlogging simulation data; obtaining real-time urban area waterlogging data, and performing a difference analysis on the second urban waterlogging simulation data and the real-time urban area waterlogging data, thereby obtaining a scheduling difference report;

[0094] In this embodiment, the output urban waterlogging scheduling parameter set is executed, and parameters such as pump station flow rate and valve opening and closing status are applied to the waterlogging model constructed in step S2. These parameters are converted into model input parameters, and the urban waterlogging model is rerun. Based on the model's running results, after a period of operation, during the execution of the scheduling plan, the real-time monitoring waterlogging data obtained from the monitoring station is compared with the waterlogging situation under the optimized scheduling plan, particularly the waterlogging situation in critical infrastructure and waterlogging buffer zones. The real-time monitoring waterlogging data and model simulation results are compared and analyzed. Deviations that occur during the scheduling process are analyzed, along with their causes, including model parameters (such as whether pump station flow rate and valve opening settings are reasonable), equipment operating conditions (such as whether pump stations are operating as planned and valves are operating normally), and external environmental influences (such as actual rainfall not matching the forecast or sudden rainfall changes). The effectiveness of the existing drainage plan is evaluated. Finally, feedback conclusions are generated, identifying areas of discrepancy and their causes, and recommendations for optimizing scheduling parameters or revising the model are proposed, providing a basis for subsequent optimization.

[0095] Step S6: Update the model input of the urban waterlogging scheduling model according to the scheduling difference report to obtain an updated urban waterlogging model. Based on the updated urban waterlogging model, re-execute steps S4 and S5, and continuously iterate and optimize the scheduling parameters through difference analysis between the new simulation results and the real-time urban area waterlogging data until the difference meets the preset conditions.

[0096] In this embodiment, when there is a deviation between the feedback scheduling result of the scheduling difference report and the measured result, the model input is updated according to the scheduling difference report, including the latest rainfall forecast, surface water status and external river water level and other initial conditions, and step S4 is re-executed to generate a new scheduling parameter group. Through dynamic iteration, it is ensured that the scheduling strategy adapts to the latest conditions, and then the difference analysis of step S5 is performed until the measured and simulation results are consistent during operation.

[0097] Optionally, step S1 specifically includes:

[0098] Step S11: Acquire urban area geographic basic data, urban area pipe network data, urban area hydrological data, urban area rainfall data, and urban area waterlogging data, wherein the urban area geographic basic data includes urban area topography data and urban area land use type data;

[0099] In this embodiment, geographic information about urban areas, including topography, landforms, hydrology, and land use types, is obtained through remote sensing technology and geographic information systems (GIS). Topographic data can be obtained through digital elevation models (DEMs), while land use type data can be obtained through interpretation of satellite imagery and current land use maps. Land use type data and river data can also be generated based on land use surveys or classification data. Hydrological data, including precipitation, river flow, and river water levels, can be obtained from local hydrological or water bureaus. Urban area pipeline network data, including pipeline layout, pipeline parameters, and pump station operating characteristics, can be obtained by consulting water conservancy and drainage network drawings provided by urban planning departments and conducting actual pipeline network surveys using smart sensors and underground detection technology (such as ground laser scanning). Rainfall data and waterlogging data are collected through meteorological monitoring stations and watershed hydrological monitoring stations, using a combination of rain gauges and ground surface water sensors. Urban area rainfall data includes historical rainfall data and real-time monitored rainfall data; urban area waterlogging data includes historical waterlogging data and real-time monitored waterlogging data.

[0100] Step S12: performing a pipe network connection node consistency check on the urban area pipe network data, thereby obtaining pipe network connection consistency node data, and performing a pipe section continuity check based on the pipe network connection consistency node data, thereby obtaining urban area pipe network inspection data;

[0101] In this embodiment, a one-dimensional pipe network model is constructed using the SWMM modeling method based on the urban area pipe network inspection data. By extracting the pipe network nodes (such as rainwater wells, outlets, pump stations) and pipe segment information (such as pipe length, diameter, slope, roughness coefficient), a complete pipe network structure is set. According to the division of sub-catchment areas, the area, slope, impermeable ratio and other parameters of each area are defined and associated with the corresponding nodes. The rainfall station data is used to define rainfall conditions, allocated to sub-catchment areas, and simulate the dynamic changes of rainfall intensity and distribution. A complete one-dimensional pipe network model containing information such as nodes, pipe segments, sub-catchment areas and rainfall stations is generated.

[0102] Step S13: Based on the urban area land use type data, regional division is performed according to a preset land use classification standard, thereby obtaining land use type regional data;

[0103] In this embodiment, the land use type data is classified according to the local land use classification standard from the Natural Resources Planning Bureau where the target city is located.

[0104] Step S14: integrating the land use type regional data and the urban area terrain data into regional surface characteristics, thereby obtaining urban area surface characteristic data;

[0105] In this example, a GIS platform is used to perform spatial overlay analysis of land use type regional data and urban area terrain data. In this process, the land use type data serves as the "background layer" and the terrain data serves as the "surface elevation layer." The combination of the two provides a more intuitive display of land use patterns under different terrain conditions. Algorithms (such as weighted averaging and spatial interpolation) are used to fuse the two spatial data to generate new urban area surface feature data.

[0106] Step S15: performing data preprocessing on the urban area rainfall data and the urban area waterlogging data, respectively, to obtain the urban area rainfall data to be analyzed and the urban area waterlogging data to be analyzed.

[0107] In this embodiment, rainfall and waterlogging data are preprocessed. Rainfall data is obtained from meteorological monitoring stations or rain gauges, while waterlogging data is collected through manually reported waterlogging records and waterlogging monitoring equipment. Preprocessing includes data cleaning and missing value filling, such as using interpolation to supplement missing rainfall data. For waterlogging data, data smoothing (such as moving average) is used to remove noise, and time series analysis is used to determine the frequency and duration of waterlogging events.

[0108] Optionally, step S2 is specifically:

[0109] Step S21: constructing a one-dimensional pipe network model based on the urban area pipe network inspection data;

[0110] In this example, a one-dimensional pipe network model was constructed using the SWMM modeling method based on urban regional pipe network inspection data. By extracting network nodes (such as stormwater wells and pumping stations), pipe segment information (such as pipe length, diameter, and slope), pumping stations, outlets, sub-catchments, and rainfall stations, and setting the pipe network structure and related parameters (such as friction coefficient and initial water level), a complete one-dimensional pipe network model was generated, providing basic data for subsequent hydraulic simulations.

[0111] Step S22: constructing a two-dimensional surface model based on the urban area surface feature data;

[0112] In this embodiment, a two-dimensional surface grid model is generated using a digital elevation model (DEM) based on urban area surface characteristic data. Surface characteristic parameters (such as roughness coefficient, impermeability, and permeability) are extracted and assigned. Combined with rainfall input and boundary conditions, a surface hydrodynamic model is established.

[0113] Step S23: performing coupling model time step matching on the one-dimensional pipe network model and the two-dimensional surface model to obtain a time step coordinated model set; performing water exchange calculation on the time step coordinated model set to obtain a water exchange model set;

[0114] In this embodiment, the one-dimensional and two-dimensional models use different time steps. The one-dimensional model uses a larger specified step size for calculation (larger means Δt1D>Δt2D), while the two-dimensional pipe network model uses a smaller adaptive time step size for multiple calculations. This can reduce the amount of calculation for the two-dimensional model while ensuring that the two models exchange water volume data at the same time point. That is: Δt1D = N * Δt2D; where Δt1D is the time step of the one-dimensional pipe network model; Δt2D is the time step of the two-dimensional pipe network model; N is an integer, indicating that N two-dimensional model time steps are simulated within one one-dimensional model time step. The water volume exchange calculation is to calculate the overflow volume based on the water level difference and overflow cross-sectional area of ​​the pipe network model when the pipe network water level exceeds the surface elevation of the well point; when the surface water head height is greater than the well point water head height, the orifice outflow or weir flow formula is used to calculate the accumulated water return volume. Assume that the time step of the one-dimensional pipe network model is 5 seconds. The two-dimensional surface model will dynamically adjust the step size (such as 1 second, 0.5 second, etc.) according to the simulation requirements within these 5 seconds to complete multiple calculations. The two-dimensional model adaptively adjusts the time step. At the end of each one-dimensional model time step, its calculation time is accurately synchronized to the end point of the current one-dimensional step. At the end of each one-dimensional time step, the total simulation time of the two-dimensional model is synchronized with the one-dimensional model time, ensuring the timeliness and consistency of data exchange and realizing the overall coordinated operation of the model.

[0115] Step S24: performing boundary condition coupling on the water exchange model set to obtain a boundary condition coupling model; dynamically updating the boundary condition coupling model according to rainfall data and waterlogging data in the urban area to be analyzed to obtain a coupled waterlogging model;

[0116] In this embodiment, water exchange between the pipe network and the surface is achieved through the location of wellpoints in the pipelines. The wellpoints in the one-dimensional pipe network serve as point source boundary conditions for the two-dimensional surface model. When the pipe network's drainage capacity reaches its upper limit, water overflows through the wellpoints to the surface, simulating the diffusion of accumulated water. When the surface water level exceeds the wellpoint elevation, the accumulated water flows back into the pipe network through the wellpoints, achieving drainage.

[0117] This step requires determining the boundary conditions for water flow based on the city's geographic information and pipe network locations. Then, actual rainfall data, waterlogging data, surface water accumulation, and river level monitoring data are used as dynamic inputs to adjust the model's input boundary conditions. By dynamically updating the model, precipitation conditions, surface flow conditions, and pipe network loads can be reflected in real time, ultimately resulting in a coupled waterlogging model.

[0118] Step S25: using an ant colony algorithm to automatically calibrate and optimize the coupled waterlogging model, thereby obtaining an urban waterlogging model.

[0119] In this embodiment, the root mean square error (RMSE) and mean absolute error (MAE) are used for verification by comparing the water depths of the measured waterlogging points in the city and the waterlogging points simulated by the model. RMSE measures the square error between the simulated and measured waterlogging depths to evaluate the overall accuracy of the model; MAE calculates the average absolute error of the two to reflect the prediction deviation. If the error is within the allowable range, the model continues to run; if the error is large, the model parameters are adjusted. When the model verification error is large, the ant colony algorithm is used to automatically calibrate and optimize the model parameters, which includes the following steps: initializing the key parameters of the model, including pipe network roughness, surface permeability, runoff coefficient, surface roughness, etc. The ant colony algorithm generates multiple parameter combinations, each combination represents a set of model parameters, and the model simulates urban waterlogging based on these parameters, compares them with the measured waterlogging data, and outputs the error value. The "pheromone" weight is increased for the parameter combinations with smaller errors, and these combinations are retained as optimization directions first, gradually guiding the subsequent parameter search process. Through multiple iterations, the model parameters converged to the optimal combination, minimizing the error between the surface waterlogging simulation results of the waterlogging model and the measured water depth data, completing the parameter calibration and optimization.

[0120] Optionally, step S21 is specifically as follows:

[0121] Step S211: extracting pipe network pump station parameter features, pipe network parameter features, and pipe network liquid level features from the urban area pipe network inspection data, thereby obtaining pipe network pump station data, pipe network pipeline data, and pipe network liquid level data;

[0122] In this embodiment, when extracting data from pipeline network pump stations, attention is paid to the operating status of the pump stations (such as start-up and shutdown times, operating efficiency, pump flow rate, etc.). When extracting pipeline parameters, attention is paid to physical properties such as the diameter, material, length, number of pipes, starting point elevation, and inner wall roughness. For pipeline network liquid level data, real-time liquid level data is collected from liquid level gauges installed in the pipeline network. Through data cleaning and preprocessing, noise and outliers are removed to ensure that valid pipeline network pump station data, pipeline data, and pipeline network liquid level data are obtained.

[0123] Step S212: Formatting and integrating the pipeline network pump station data, pipeline network pipeline data, and pipeline network liquid level data to obtain a pipeline parameter set;

[0124] In this embodiment, a data processing tool is used to integrate the pipe network pump station data, pipeline data and pipeline flow data in a unified format. Specifically, the pipe network pump station data can be integrated in time series to form a table of pump station operation status, including operation rule data under different working conditions of each pump station. The physical parameters of the pipeline (such as pipeline length, diameter, material, friction coefficient, starting point elevation, etc.) are extracted from multiple data sources and integrated into a unified database structure. In this process, Python's Pandas library can be used to clean and integrate data in different formats. The liquid level data of the key nodes of the pipe network collected by the liquid level sensor are synchronized in time and formatted into a unified time series data set to ensure time consistency between the data. A complete pipeline parameter set is generated through data fusion technology, including pump station parameters, pipeline parameters and liquid level data, to form a set of standardized data sets that can be used for further analysis. And a unified data storage format (such as CSV, JSON or database table) is adopted. Finally, a standardized pipeline parameter set is output through a data processing program (such as pandas in Python) for subsequent analysis and modeling.

[0125] Step S213: constructing a pipe network topology model based on the pipe parameter set;

[0126] In this example, a pipe network topology model was constructed using the SWMM modeling method based on the integrated pipe parameter set. The model uses nodes and pipes as basic units. Nodes represent facilities such as manholes, pumping stations, and access points, while pipes represent the drainage pipes connecting the nodes. During the modeling process, the spatial location and properties of the nodes are determined based on the pipe parameter set. Pipeline geometric characteristics (such as length, slope, and diameter) and hydraulic properties (such as roughness coefficient) are used to describe the pipeline properties.

[0127] Step S214: setting water flow exchange boundary conditions based on the pipe network liquid level data and the pipe network pump station data, thereby obtaining water flow exchange boundary conditions;

[0128] In this embodiment, boundary conditions for water flow exchange are set based on the extracted pipe network liquid level data and pump station operation data to ensure the rationality and consistency of the boundary conditions. For pump station boundary conditions, they are defined based on the pump station's start and stop status, operating flow rate, and time data to ensure accurate simulation of water flow exchange between the pump station and the pipe network. For pipeline liquid level boundary conditions, the inlet and outlet liquid level ranges of the pipeline nodes are determined by combining real-time monitored liquid level data (or historical liquid level data) with the pipe network's operating characteristics, and used as the boundary liquid level condition input into the model.

[0129] Step S215: constructing a one-dimensional pipe network model according to the pipe network topology model and the water flow exchange boundary conditions.

[0130] In this embodiment, a one-dimensional hydraulic model of the pipe network is constructed based on the constructed pipe network topology and the set water exchange boundary conditions. This model generally assumes that the water flow along the flow direction of the pipe is approximately one-dimensional, and takes into account factors such as the flow resistance, friction loss, and local resistance of the pipe. In specific implementation, the pipe network is first divided into multiple small sections in the model, and the pipes of each small section are regarded as a one-dimensional flow model, taking into account parameters such as the length, diameter, and slope of the pipe. Then, the inlet and outlet boundary values ​​of each pipe section are determined by water flow boundary conditions such as the flow rate of the pump station. For the construction of a one-dimensional model, hydraulic equations (such as the Hagen-Poset flow formula, the energy equation, etc.) are generally used to describe the water flow state of each pipe section. The pipe network is solved by numerical methods (such as the finite difference method or the finite element method) to obtain the flow rate and liquid level distribution at each point in the pipe network. Professional hydraulic simulation software (such as SWMM, etc.) can be used for simulation calculations and output the water flow state of the well points and pipe sections of the pipe network.

[0131] Optionally, step S22 is specifically as follows:

[0132] Step S221: extracting regional elevation features from urban area surface feature data to obtain urban area elevation data;

[0133] In this embodiment, a high-resolution digital elevation model (DEM) of the target area can be obtained from the city's Natural Resources and Planning Bureau. The resolution is adjusted according to the area to balance simulation accuracy and computational efficiency: a 2-meter resolution grid is used for areas over 1,000 square kilometers, a 5-meter resolution grid is used for areas between 200 and 1,000 square kilometers, and a 10-meter resolution grid is used for areas under 200 square kilometers. Buildings and other artificial structures are identified and labeled using GIS tools. Building outlines are manually vectorized and combined with field measurements or building height data, which are then superimposed on the original DEM to obtain surface elevation data that takes artificial buildings into account.

[0134] Step S222: Based on the land use type regional data and in combination with the preset correspondence between land use and surface attributes, the infiltration conditions and Manning coefficients of different regions are derived, thereby obtaining regional infiltration condition data and regional Manning coefficient data;

[0135] In this embodiment, the permeability conditions and Manning coefficients of different areas are derived by combining the land use data (such as buildings, roads, bare soil, grassland, water bodies, etc.) in the urban area. First, different land use types are classified through the current land use data of the city (which can be obtained through remote sensing images, land use classification maps or urban planning data). Then, according to the characteristics of different land types, the permeability conditions and Manning coefficients of each area are determined according to the preset correspondence table between land use and surface attributes. For example, urban hardened pavement (such as asphalt or concrete) usually has lower permeability, while green space or wetland has higher permeability. For the Manning coefficient, hardened ground generally takes a lower value (such as 0.015), while natural ground such as grassland or farmland takes a higher value (such as 0.030). Through GIS tools, for areas with different land use types, combined with the corresponding permeability conditions and Manning coefficients, permeability condition data and Manning coefficient data of each area are generated to provide parameters for the two-dimensional surface model.

[0136] Step S223: setting hydrological boundary conditions based on the urban area hydrological data, thereby obtaining hydrological boundary conditions;

[0137] In this embodiment, hydrological boundary conditions are set based on data such as precipitation, evaporation, and flow included in the hydrological data of the urban area. For example, for rivers or drainage systems in urban areas, boundary flows or water levels can be set based on the hydrological data to simulate rainwater discharge and runoff. At the same time, surface runoff in the area is calculated using rainfall, soil type, and land use data. In actual operation, the use of hydrological simulation software (such as HEC-HMS or SWMM) can help accurately set hydrological boundary conditions to ensure that they reflect the actual hydrological changes.

[0138] Step S224: constructing a two-dimensional surface model based on water exchange boundary conditions, urban area elevation data, regional infiltration condition data, and regional Manning coefficient data.

[0139] In this embodiment, a two-dimensional surface hydrological model is constructed by a numerical simulation method using the aforementioned water exchange boundary conditions, urban area elevation data, regional infiltration condition data and Manning coefficient data. First, a suitable two-dimensional surface model (such as MIKE) is selected and the aforementioned data is input into the model. In the initial stage of the model, a digital elevation model (DEM) of the urban area is generated based on the elevation data as the basic terrain information of the model. Then, the infiltration condition data and Manning coefficient data are used as key parameters of the model to calculate the speed and direction of water flow in the area. According to the set water boundary conditions, how the precipitation flow is distributed in different terrain areas, how it flows along the drainage path, and how it infiltrates through the permeability of different surfaces is simulated. Ultimately, the distribution of water flow, including the range and depth of water accumulation, is output through simulation.

[0140] Optionally, step S3 specifically includes:

[0141] Step S31: Acquire important infrastructure data in the urban area, and extract the geographical location of the important infrastructure and the waterlogging prevention needs of the important infrastructure in the urban area, thereby obtaining the geographical location data of the important infrastructure and the waterlogging prevention needs data of the important infrastructure;

[0142] In this embodiment, the urban geographic information system (GIS) is used to obtain data on important infrastructure (lifeline facilities engineering) in the urban area, including hospitals, power stations, transportation hubs, etc. These data can be obtained through urban planning bureaus, engineering companies or third-party data providers (such as OpenStreetMap). The data format may include map data (Shapefile, GeoJSON, etc.) and databases (PostGIS, Oracle Spatial, etc.). Spatial analysis tools (such as ArcGIS, QGIS) are used to extract the geographical location of these infrastructures and mark the specific latitude and longitude positions of each infrastructure. Based on the elevation data of the area where the facilities are located, the historical waterlogging situation and the functional characteristics of the facilities, a comprehensive analysis of their waterlogging prevention needs is performed. The prevention requirements for facilities in higher terrain are relatively low, while facilities in low-lying areas need to set higher protection standards. Different important infrastructures have different waterlogging prevention and control requirements. For example, hospitals need to consider strict waterlogging area prevention requirements, while power plants need to focus on waterlogging depth prevention requirements.

[0143] Step S32: extracting surface features of important infrastructure locations from the urban area surface feature data based on the important infrastructure geographic location data, thereby obtaining surface feature data of important infrastructure locations;

[0144] In this example, spatial analysis is used to extract surface features near infrastructure locations, combined with geographic location data. For example, terrain elevation and slope characteristics around infrastructure are extracted to determine whether it is prone to water accumulation. The density of surrounding drainage facilities, land use types, and surface material properties are analyzed and combined with historical waterlogging data to assess the direction of water flow and the potential extent of waterlogging around the facilities. This extracted surface feature data is then correlated and integrated with facility location data to generate surface feature data for key infrastructure locations.

[0145] Step S33: Calculating the upper limit of the waterlogging area and the upper limit of the waterlogging depth of the important infrastructure based on the surface characteristic data of the location of the important infrastructure and the waterlogging prevention demand data of the important infrastructure, thereby obtaining the waterlogging range data of the important urban infrastructure;

[0146] In this embodiment, based on historical waterlogging data, its own flood prevention threshold and terrain height information, combined with the surface feature data of important infrastructure, the upper limit of the waterlogging area and the upper limit of the waterlogging depth of each facility are evaluated and calculated. The waterlogging range data that the facility can withstand is directly calculated, including the waterlogging area and the waterlogging depth. For example, a hospital needs to ensure that the waterlogging depth does not exceed 0.3 meters and the waterlogging area is controlled within 3,000 square meters. The waterlogging range data of each important infrastructure is obtained, including the upper limit of the waterlogging area and the upper limit of the waterlogging depth. These data will be used for subsequent buffer zone selection and waterlogging risk assessment.

[0147] Step S34: selecting an urban waterlogging buffer zone based on the urban area surface characteristic data to obtain urban waterlogging buffer zone data, and integrating the surface characteristics of the buffer zones on the urban waterlogging buffer zone data to obtain surface characteristic data of the waterlogging buffer zones;

[0148] In this embodiment, based on the surface characteristics of the urban area, areas that meet the surrounding requirements are selected as buffer zones. For example, low-lying areas, unpaved surfaces, green spaces, or areas covered by vegetation are prioritized as water accumulation buffer zones, while also considering their connectivity with the drainage system and their water storage capacity. The water accumulation buffer zone acts as a buffer between surface water and the drainage system, absorbing short-term water loads, dispersing surface water, and reducing water pressure on critical infrastructure.

[0149] Step S35: setting a water accumulation area threshold and a water accumulation depth threshold for the surface characteristic data of the water accumulation buffer zone, thereby obtaining data on the allowable range of water accumulation in the water accumulation buffer zone.

[0150] In this embodiment, a threshold value for the area of ​​waterlogging is set based on the surface characteristic data of the waterlogging buffer zone and the historical waterlogging event data. For example, if the waterlogging area in a certain area exceeds 5,000 square meters, it will affect the normal operation of the infrastructure. Therefore, a reasonable area threshold is set, and only when the waterlogging area is less than the threshold will the area be considered to be within an acceptable risk range. At the same time, the waterlogging depth threshold is set according to the inherent characteristics of the buffer zone and the terrain characteristics of the surrounding area. For example, in a buffer zone, if the depth of waterlogging exceeds 0.5 meters, it may cause overflow to spread to the main traffic artery, so the depth threshold is set to 0.5 meters to ensure that the waterlogging is controllable within the buffer zone. By setting dual thresholds of area and depth, the allowable range of waterlogging in the waterlogging buffer zone is defined.

[0151] Optionally, step S34 is specifically as follows:

[0152] Extracting terrain elevation features, permeability features, and vegetation coverage features from urban area surface feature data, thereby obtaining urban area vegetation coverage data, urban area permeability data, and urban area terrain elevation data;

[0153] In this embodiment, the terrain elevation feature extraction is based on the digital elevation model (DEM). The DEM data is raster analyzed by GIS tools to extract the elevation values ​​within the area. The vegetation coverage and permeability feature extraction are based on the land use classification data. Using the urban area land use data, the vegetation coverage and permeability characteristics are calculated according to different types (such as green space, hardened road surface, bare land, water body, etc.). For example, green space and grassland have a higher vegetation coverage and better permeability, while hardened road surface has lower permeability. The land use classification results are spatially analyzed by GIS tools to generate a vegetation coverage map and a permeability distribution map of the urban area. The DEM elevation data is integrated with the vegetation coverage and permeability data derived from the land use classification.

[0154] Extract the pipe network distribution characteristics from the urban area pipe network inspection data to obtain the drainage pipe network distribution data;

[0155] In this embodiment, the spatial distribution characteristics of the drainage network are extracted by analyzing the inspection data of the urban area pipeline network. The drainage network is the core facility for realizing the scheduling of accumulated water, and the coverage area determines whether the accumulated water can be directed to the buffer zone. The specific method includes: using GIS tools to read the pipeline network data, extracting the geographical distribution of pipeline network nodes (such as rainwater wells, water outlets) and connecting pipes; combining information such as pipe diameter, material, slope, etc., to calibrate the drainage range and generate a drainage network distribution map. This distribution map is used to clarify the coverage area of ​​the pipeline network and ensure that the location of the buffer zone is within the controllable range of the drainage network.

[0156] Identify low-lying areas based on urban area terrain elevation data to obtain low-lying area data;

[0157] Extracted urban area terrain elevation data is classified into highlands, medium areas, and lowlands based on elevation ranges. For example, by calculating local elevation differences (e.g., relative to the average elevation of a 500-meter radius), low-lying areas that are lower than the surrounding area can be identified. Elevation data can be reclassified using the "Reclassify" function in GIS tools (such as ArcGIS), combined with spatial analysis tools (such as "Focal Statistics") to identify local low-lying areas.

[0158] Select high vegetation coverage areas from urban area vegetation coverage data to obtain high vegetation coverage area data;

[0159] In this example, based on urban vegetation coverage data derived from land use types, areas with high vegetation coverage are screened, with areas with coverage exceeding 60% marked as high vegetation coverage areas. High vegetation coverage areas have good water absorption and buffering capabilities, providing support for the selection of waterlogging buffer zones.

[0160] Screening the urban area permeability data for high permeability areas to obtain high permeability area data;

[0161] In this example, based on urban area permeability data derived from land use types, we screened for areas with high permeability (such as green spaces, grasslands, and bare land) and labeled them as high permeability areas. High permeability areas can effectively reduce surface runoff and mitigate the risk of waterlogging, providing support for the site selection and design of waterlogging buffer zones. GIS spatial analysis was used to identify areas that met the criteria.

[0162] Select the pipe network coverage area based on the drainage pipe network distribution data to obtain the pipe network coverage area data;

[0163] In this embodiment, drainage network distribution data is analyzed to identify areas covered by the drainage network. Using GIS tools, the effective coverage area of ​​the network is determined based on network nodes (such as stormwater wells and outfalls) and the service area of ​​the pipelines. The coverage area refers to the area where water accumulation can be managed through the network, with its boundaries determined by factors such as pipeline service capacity and topographical conditions. The generated network coverage area data is used to ensure that the water accumulation buffer zone is located within the controllable range of the drainage network.

[0164] Allocating land use type priorities based on urban area land use type data to obtain land use type priority data, and dividing sub-priority areas based on the land use type priority data to obtain land use sub-priority area data;

[0165] In this embodiment, land use types are assigned a priority based on factors such as resource scarcity and environmental impact. Ecologically sensitive areas are given priority for protection, and certain types of land (such as wetlands and forests) are given a higher priority for protection or restoration. Infrastructure construction priority, in urban development, development priorities are set based on factors such as the location of the land, infrastructure needs, and transportation networks. In certain specific application scenarios, land use types are assigned different levels or priorities. Certain areas are divided into "priority development areas" or "secondary development areas", and within these areas, different land use types have different priority development orders. Combined with urban land use type data, important ecological protection areas, urban planning development land and other sensitive areas with higher priorities are excluded to generate land use secondary priority area data.

[0166] Perform spatial overlay analysis on low-lying area data, high vegetation coverage area data, high permeability area data, pipe network coverage area data, and land use secondary priority area data to generate urban waterlogging buffer zone data;

[0167] In this example, the generation of a waterlogging buffer zone relies on the overlay of various spatial data sets, including low-lying terrain, high vegetation cover, high permeability areas, pipe network coverage, and areas of low land use priority. Using GIS tools like ArcGIS and the "Overlay" or "Spatial Analyst" tool in spatial analysis, these different datasets are overlaid and analyzed to generate the waterlogging buffer zone data.

[0168] Based on the urban waterlogging buffer zone data, the surface characteristic data of the urban area are integrated to obtain the surface characteristic data of the waterlogging buffer zone.

[0169] In this example, integrated surface feature analysis based on the waterlogging buffer zone typically requires combining multiple surface feature data (such as terrain elevation, vegetation coverage, and permeability) for comprehensive analysis. Using the "Intersect" or "Union" tools in GIS, different feature layers are combined to extract surface feature information within the waterlogging buffer zone, generating the final surface feature data for the buffer zone. This data can be further used for waterlogging risk assessment and urban disaster prevention planning.

[0170] Optionally, step S4 is specifically:

[0171] Step S41: performing urban waterlogging simulation on the urban area rainfall data using an urban waterlogging model, thereby obtaining first urban waterlogging simulation data;

[0172] In this embodiment, a coupled urban waterlogging model is used to simulate and analyze a target area using future rainfall forecasts to generate first urban waterlogging simulation data. This data includes the distribution of urban waterlogging, such as the depth, extent, and duration of waterlogging in each area.

[0173] Step S42: Based on the first urban waterlogging simulation data, the urban area important infrastructure data and the urban waterlogging buffer zone data are divided into regional waterlogging data, thereby obtaining important infrastructure area waterlogging data and urban waterlogging buffer zone waterlogging data; and waterlogging benchmarks are set based on the important infrastructure area waterlogging data and the urban waterlogging buffer zone waterlogging data, thereby obtaining initial simulated waterlogging benchmark data.

[0174] In this example, by combining the first urban flooding simulation data with the location data of key urban infrastructure, the initial flooding conditions for each key infrastructure were calculated, including the flooding depth, area, and duration. Combining the simulation results with spatial analysis, the flooded area of ​​the entire urban area was divided into the flooded area of ​​key infrastructure areas and the flooded area of ​​buffer zones. This yielded the initial flooding baseline data before scheduling intervention, including the total flooded area (excluding the amount of water in the flooding buffer zone) and detailed flooding conditions for each key infrastructure area.

[0175] Step S43: extracting the pipe network pump station and valve control parameters from the urban area pipe network inspection data, thereby obtaining pump station control parameter data and valve control parameter data;

[0176] In this embodiment, the data of the urban drainage network system, especially the control parameters of the pumping stations and valves, are extracted from the network inspection data. The network inspection data includes information such as the diameter, flow rate, slope, processing capacity of the pumping station, and the opening and closing control rules of the valves of each drainage pipe. For example, the flow control parameter of a pumping station in the urban drainage network is 5000m 3 / h, the valve control parameter is to open automatically when the water depth exceeds 30cm.

[0177] Step S44: setting an objective function and constraints based on the water accumulation range data of important urban infrastructure and the water accumulation allowable range data of the water accumulation buffer zone, thereby obtaining a fitness function and a constraint condition function;

[0178] In this embodiment, objective functions and constraints need to be defined. These objective functions are generally related to minimizing waterlogging. For example, the corresponding water depth of important infrastructure is reduced, the water area is reduced, and the total water area is reduced (excluding the water buffer zone). Constraints include water depth limits (for example, the water depth of infrastructure must not exceed 50cm), drainage capacity limits, and water buffer capacity limits for specific areas. By setting these functions and conditions, reasonable objectives and constraints can be provided for subsequent optimization calculations.

[0179] Step S45: generating an initialized particle swarm based on the initial simulated waterlogging benchmark data, the fitness function, and the constraint condition function, and based on the pump station control parameter data and the valve control parameter data; calculating the initial fitness values ​​of the particles in the initialized particle swarm; selecting the global optimal particle from the initial fitness values ​​of the particles; and recording the individual optimal solution of each particle, thereby obtaining the global optimal particle and the individual optimal solution of the particle;

[0180] In this embodiment, based on the aforementioned initial simulated waterlogging benchmark data, fitness function and constraint function, optimization is performed using a particle swarm algorithm (PSO). The initialization of the particle swarm includes randomly generating a certain number of particles, each particle representing a possible waterlogging scheduling scheme. The particles calculate their fitness values ​​based on control parameters (such as pump station opening time, valve control switch status, etc.). Then, the global optimal particle is selected from them, and the individual optimal solution of each particle is recorded. Assume that there are 100 particles, each particle represents a combination of a pump station and valve control parameters (for example, the opening time of pump station 1 is 15 minutes, and the opening degree of valve A is 50%). The particle swarm selects the best solution by calculating the fitness value of each particle (for example, the cumulative waterlogging depth or drainage efficiency).

[0181] Step S46: Iteratively optimize based on the constraint function and the global optimal particle and the individual optimal solution of the particle until the preset early stopping condition is met, thereby obtaining the global optimal solution;

[0182] In this embodiment, the iterative mechanism of the particle swarm algorithm is used. Based on the current global optimal solution and the individual optimal solution, multiple calculations and adjustments are performed to gradually optimize the control parameters of each particle. Through continuous iterative optimization of the fitness function, the particle swarm will continue to approach the optimal solution until the preset stop condition is met (for example, after a fixed number of iterations or a certain accuracy standard is reached). Assume that the optimal solution at the beginning is that the pump station opening time is 15 minutes and the valve opening is 50%. After several rounds of iterations, the particle swarm finds that when the pump station opening time is extended to 20 minutes and the valve opening is increased to 60%, the water depth is the smallest and the fitness value is the highest, so this is the optimal solution.

[0183] Step S47: convert the global optimal solution into waterlogging scheduling parameters to obtain a waterlogging scheduling parameter group for the urban area, and upload it to the urban drainage management platform to execute the waterlogging scheduling task.

[0184] In this embodiment, the final global optimal solution (including the opening time of the pump station, the control parameters of the valve, etc.) needs to be converted into actual control parameters for use by the urban drainage management platform. These scheduling parameters will be uploaded to the drainage management platform, and the drainage system will be scheduled in real time based on these parameters to cope with future rainfall events. The control parameters in the global optimal solution (for example, the opening time of pump station 1 is 20 minutes, and the opening of valve A is 60%) are uploaded to the urban drainage management platform. The platform can dynamically adjust the operation of the drainage system according to the real-time rainfall conditions and water level changes in the basin to ensure that the accumulated water is effectively drained.

[0185] Optionally, step S44 is specifically as follows:

[0186] Step S441: constructing a penalty function based on the water accumulation allowable range data of the water accumulation buffer zone;

[0187] In this embodiment, the water accumulation area of ​​the water accumulation buffer zone is controlled to be no more than The depth of water in the water buffer zone does not exceed Set the penalty function f buffer The penalty function is:

[0188]

[0189] where h j The depth of water in the buffer zone, is the maximum water depth allowed in the buffer zone, A j is the water accumulation area of ​​the buffer zone, is the maximum water accumulation area allowed in the buffer zone; w j is the depth of the buffer, k j is the area weight of the buffer zone, and j is the index of the buffer zone.

[0190] Step S442: Constructing a fitness function based on the penalty function and the waterlogging range data of important urban infrastructure, wherein the fitness function is specifically:

[0191]

[0192] Where f is the fitness function value, n is the total number of important infrastructures, i is the index of important infrastructure, α is the global weight of the buffer penalty, and w i is the weight used to control the water depth of the i-th important infrastructure in the fitness function, k iis the weight of the waterlogged area of ​​the i-th important infrastructure in the fitness function, D i is the water depth of the i-th important infrastructure, d i is the water depth target of the i-th important infrastructure, A i is the waterlogged area of ​​the i-th important infrastructure, a i is the target waterlogging area of ​​the i-th important infrastructure, A t is the total waterlogged area excluding the waterlogged buffer zone, A tr is the total waterlogged area target excluding the waterlogged buffer zone, and K is the weight of the total waterlogged area;

[0193] In this example, the scheduling objectives are first determined, minimizing the depth of waterlogging in each critical infrastructure area to below their respective target depths (e.g., target 1: critical infrastructure to have a water depth of less than 20 cm, target 2: critical infrastructure to have a water depth of less than 30 cm, and so on). The waterlogged area is controlled to not exceed the target value (e.g., target 1: critical infrastructure to have an area of ​​less than 100 square meters, target 2: critical infrastructure to have an area of ​​less than 100 square meters, and so on). The total waterlogged area of ​​the entire simulation area, including the critical infrastructure area (excluding the waterlogging buffer zone), is reduced to 50% of the original value. A fitness function is constructed based on these scheduling objectives, the penalty function, and the waterlogging range data for the city's critical infrastructure.

[0194] Step S443: constructing a control parameter constraint condition function according to the pump station control parameter data and the valve control parameter data, thereby obtaining a constraint condition function.

[0195] In this embodiment, control parameters are obtained based on the pump station's design flow rate, operating capacity, and valve opening and closing control data. For example, the maximum flow rate of a pump station is 2000 cubic meters per hour, and the opening control range of a valve is 0-100%. Based on this data, a constraint function is constructed to ensure that the parameters of the pump station and valve do not exceed their physical or technical limitations. For example:

[0196]

[0197] Where: i is the pump station index; j is the valve index; Q i Control flow for pumping station; Q max is the maximum allowable flow rate of the pump station; θ j is the valve opening; θ max is the maximum valve opening.

[0198] Optionally, step S45 is specifically as follows:

[0199] Step S451: performing random combinations of scheduling parameters based on the constraint condition function, the pump station control parameter data, and the valve control parameter data, thereby obtaining control scheduling parameter combination data;

[0200] In this embodiment, multiple particles are generated based on the pump station control parameter data and the valve control parameter data. Each particle represents a combination of the dispatching parameters of the pump station and the valve (such as flow rate and switch status). Each particle is randomly distributed within the parameter space and conforms to the constraint function. For example, the start and stop sequence of the pump station and the valve opening setting are randomly selected. The generation of the control parameter combination must ensure that the operational constraints and system balance requirements are met. For example, the on / off state of the pump station must match the valve opening to avoid conflicting combinations.

[0201] Step S452: Initialize particles according to the control scheduling parameter combination data to obtain an initialized particle swarm;

[0202] In this embodiment, the particle swarm is initialized based on the obtained control scheduling parameter combination data. Each particle represents a possible scheduling scheme, its position is determined by the scheduling parameter combination, and the speed represents the change in the adjustment of these parameters. For example, if the position of a particle is a vector of a pump station start-stop sequence and a set of valve opening settings, then the speed of the particle can be a fine-tuning of these parameters. During initialization, the positions and speeds of all particles are randomly initialized, and the particle swarm size is set, for example, 50-100 particles, and the dimension of each particle is the number of pump stations plus the number of valves. Continue to iterate, set to 300 times, to ensure that there are enough searches to find a solution that meets the needs of multiple regions. The individual learning factor and the social learning factor are both set to 2.0, and the inertia weight is gradually reduced from 0.9 to 0.4.

[0203] Step S453: performing urban waterlogging simulation on the urban area rainfall data and the initialized particle swarm using the urban waterlogging model, thereby obtaining initialized particle simulation data;

[0204] In this embodiment, an urban waterlogging model is used to simulate waterlogging for each scheduling scheme of the initialized particles. The urban waterlogging model inputs rainfall data (such as rainfall intensity, duration, etc.) and the control scheduling parameters in the particle swarm (such as pump station start and stop time, valve opening) for simulation calculation. During the simulation process, the model predicts the waterlogging situation under different scheduling schemes through water flow equations and hydraulic calculations of the drainage network. For example, the scheme represented by a certain particle increases the pump station opening in the case of heavy rain, thereby improving drainage capacity and reducing water accumulation. The simulation results will output data such as water accumulation depth and water accumulation area in different areas corresponding to different particles.

[0205] Step S454: performing particle initialization fitness calculation on the initialized particle simulation data using a fitness function, thereby obtaining the particle initial fitness value;

[0206] In this embodiment, the water accumulation range and depth of important infrastructure, the water accumulation range and depth of the buffer zone, and the total water accumulation area (excluding the total area of ​​the buffer zone) are counted after each simulation. These data are substituted into the aforementioned fitness function for calculation to obtain the fitness value of each particle.

[0207] Step S455: performing individual optimal solution selection on the initial fitness value of the particle to obtain the individual optimal solution of the particle, and performing global optimal solution screening based on the individual optimal solution of the particle to obtain the global optimal particle.

[0208] In this embodiment, based on the fitness value of each particle, the particle with the best fitness is selected as the "individual optimal solution." By recording the historical optimal fitness of each particle and comparing it with the current fitness value, if the current fitness value is better, the individual optimal solution is updated. Then, the individual optimal solutions of all particles are compared, and the particle with the best fitness is selected as the "global optimal solution." For example, if the pump station start-stop sequence and valve opening setting corresponding to a particle performs best in the simulation and meets the system operation constraints, then this particle is the global optimal solution. Through an iterative process, the particle's speed and position are continuously updated, and ultimately the global optimal solution is reached.

[0209] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0210] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent scheduling method for urban waterlogging and accumulation of important infrastructure, characterized by: The following steps are involved: Step S1: Obtaining urban area geographic basic data, urban area pipe network data, urban area hydrological data, urban area rainfall data, and urban area waterlogging data; performing urban area pipe network topology inspection based on the urban area pipe network data, thereby obtaining urban area pipe network inspection data; integrating urban area surface features based on the urban area geographic basic data, thereby obtaining urban area surface feature data; Data preprocessing is performed respectively according to the urban area rainfall data and the urban area waterlogging data, thereby obtaining the urban area rainfall data and the urban area waterlogging data to be analyzed; Step S2: constructing a one-dimensional pipe network model based on the urban area pipe network inspection data; constructing a two-dimensional surface model based on the urban area surface feature data; The one-dimensional pipe network model and the two-dimensional surface model are coupled to obtain a coupled waterlogging model. The coupled waterlogging model is automatically calibrated and optimized using an ant colony algorithm to obtain an urban waterlogging model. Step S3: Obtaining important infrastructure data in the urban area, and calculating the waterlogging range of the important infrastructure in the urban area based on the surface characteristic data of the urban area, thereby obtaining waterlogging range data of the important infrastructure in the urban area; selecting an urban waterlogging buffer zone based on the surface characteristic data of the urban area, thereby obtaining urban waterlogging buffer zone data; and setting an allowable waterlogging range for the urban waterlogging buffer zone data, thereby obtaining allowable waterlogging range data for the waterlogging buffer zone; Step S4: Performing urban waterlogging simulation on the urban area rainfall data using the urban waterlogging model to obtain first urban waterlogging simulation data; performing regional waterlogging division on the urban area important infrastructure data and the urban waterlogging buffer zone data based on the first urban waterlogging simulation data to obtain important infrastructure area waterlogging data and urban waterlogging buffer zone waterlogging data; determining waterlogging scheduling parameters for the important infrastructure area waterlogging data and the urban waterlogging buffer zone waterlogging data based on the important urban infrastructure area waterlogging range data and the waterlogging buffer zone waterlogging allowable range data to obtain an urban area waterlogging scheduling parameter group, and uploading the group to the urban drainage management platform to execute the waterlogging scheduling task; Step S5: Using the urban area waterlogging scheduling parameter group to update the model parameters of the urban waterlogging model, thereby obtaining an urban waterlogging scheduling model; and using the urban waterlogging scheduling model to simulate urban area rainfall data, thereby obtaining second urban waterlogging simulation data; obtaining real-time urban area waterlogging data, and performing a difference analysis on the second urban waterlogging simulation data and the real-time urban area waterlogging data, thereby obtaining a scheduling difference report; Step S6: Update the model input of the urban waterlogging scheduling model according to the scheduling difference report to obtain an updated urban waterlogging model. Based on the updated urban waterlogging model, re-execute steps S4 and S5, and continuously iterate and optimize the scheduling parameters through difference analysis between the new simulation results and the real-time urban area waterlogging data until the difference meets the preset conditions.

2. The intelligent dispatching method for urban waterlogging and important infrastructure according to claim 1 is characterized in that: Step S1 is specifically as follows: Step S11: Acquire urban area geographic basic data, urban area pipe network data, urban area hydrological data, urban area rainfall data, and urban area waterlogging data, wherein the urban area geographic basic data includes urban area topography data and urban area land use type data; Step S12: performing a pipe network connection node consistency check on the urban area pipe network data, thereby obtaining pipe network connection consistency node data, and performing a pipe section continuity check based on the pipe network connection consistency node data, thereby obtaining urban area pipe network inspection data; Step S13: Based on the urban area land use type data, regional division is performed according to a preset land use classification standard, thereby obtaining land use type regional data; Step S14: integrating the land use type regional data and the urban area terrain data into regional surface characteristics, thereby obtaining urban area surface characteristic data; Step S15: performing data preprocessing on the urban area rainfall data and the urban area waterlogging data, respectively, to obtain the urban area rainfall data to be analyzed and the urban area waterlogging data to be analyzed.

3. The intelligent dispatching method for urban waterlogging and important infrastructure according to claim 1 is characterized in that: Step S2 is specifically as follows: Step S21: constructing a one-dimensional pipe network model based on the urban area pipe network inspection data; Step S22: constructing a two-dimensional surface model based on the urban area surface feature data; Step S23: performing coupling model time step matching on the one-dimensional pipe network model and the two-dimensional surface model to obtain a time step coordinated model set; performing water exchange calculation on the time step coordinated model set to obtain a coupled waterlogging model; Step S24: using an ant colony algorithm to automatically calibrate and optimize the coupled waterlogging model, thereby obtaining an urban waterlogging model.

4. The intelligent scheduling method for urban waterlogging and important infrastructure according to claim 3 is characterized in that: Step S21 is specifically as follows: Step S211: extracting pipe network pump station parameter features, pipe network parameter features, and pipe network liquid level features from the urban area pipe network inspection data, thereby obtaining pipe network pump station data, pipe network pipeline data, and pipe network liquid level data; Step S212: Formatting and integrating the pipeline network pump station data, pipeline network pipeline data, and pipeline network liquid level data to obtain a pipeline parameter set; Step S213: constructing a pipe network topology model based on the pipe parameter set; Step S214: setting water flow exchange boundary conditions based on the pipe network liquid level data and the pipe network pump station data, thereby obtaining water flow exchange boundary conditions; Step S215: constructing a one-dimensional pipe network model according to the pipe network topology model and the water flow exchange boundary conditions.

5. The intelligent dispatching method for urban waterlogging and important infrastructure according to claim 2 is characterized in that: Step S22 is specifically as follows: Step S221: extracting regional elevation features from urban area surface feature data to obtain urban area elevation data; Step S222: Based on the land use type regional data and in combination with the preset correspondence between land use and surface attributes, the infiltration conditions and Manning coefficients of different regions are derived, thereby obtaining regional infiltration condition data and regional Manning coefficient data; Step S223: setting hydrological boundary conditions based on the urban area hydrological data, thereby obtaining hydrological boundary conditions; Step S224: constructing a two-dimensional surface model based on the hydrological boundary conditions, urban area elevation data, regional infiltration condition data, and regional Manning coefficient data.

6. The intelligent dispatching method for urban waterlogging and important infrastructure according to claim 1 is characterized in that: Step S3 is specifically as follows: Step S31: Acquire important infrastructure data in the urban area, and extract the geographical location of the important infrastructure and the waterlogging prevention needs of the important infrastructure in the urban area, thereby obtaining the geographical location data of the important infrastructure and the waterlogging prevention needs data of the important infrastructure; Step S32: extracting surface features of important infrastructure locations from the urban area surface feature data based on the important infrastructure geographic location data, thereby obtaining surface feature data of important infrastructure locations; Step S33: Calculating the upper limit of the waterlogging area and the upper limit of the waterlogging depth of the important infrastructure based on the surface characteristic data of the location of the important infrastructure and the waterlogging prevention demand data of the important infrastructure, thereby obtaining the waterlogging range data of the important urban infrastructure; Step S34: selecting an urban waterlogging buffer zone based on the urban area surface characteristic data to obtain urban waterlogging buffer zone data, and integrating the surface characteristics of the buffer zones on the urban waterlogging buffer zone data to obtain surface characteristic data of the waterlogging buffer zones; Step S35: setting a water accumulation area threshold and a water accumulation depth threshold for the surface characteristic data of the water accumulation buffer zone, thereby obtaining data on the allowable range of water accumulation in the water accumulation buffer zone.

7. The intelligent dispatching method for urban waterlogging and important infrastructure according to claim 6 is characterized in that: Step S34 is specifically as follows: Extracting terrain elevation features, permeability features, and vegetation coverage features from urban area surface feature data, thereby obtaining urban area vegetation coverage data, urban area permeability data, and urban area terrain elevation data; Extract the pipe network distribution characteristics from the urban area pipe network inspection data to obtain the drainage pipe network distribution data; Identify low-lying areas based on urban area terrain elevation data to obtain low-lying area data; Select high vegetation coverage areas from urban area vegetation coverage data to obtain high vegetation coverage area data; Screening the urban area permeability data for high permeability areas to obtain high permeability area data; Select the pipe network coverage area based on the drainage pipe network distribution data to obtain the pipe network coverage area data; Allocating land use type priorities based on urban area land use type data to obtain land use type priority data, and dividing sub-priority areas based on the land use type priority data to obtain land use sub-priority area data; Perform spatial overlay analysis on low-lying area data, high vegetation coverage area data, high permeability area data, pipe network coverage area data, and land use secondary priority area data to generate urban waterlogging buffer zone data; Based on the urban waterlogging buffer zone data, the surface characteristic data of the urban area are integrated to obtain the surface characteristic data of the waterlogging buffer zone.

8. The intelligent dispatching method for urban waterlogging and important infrastructure according to claim 1 is characterized in that: Step S4 is specifically as follows: Step S41: performing urban waterlogging simulation on the urban area rainfall data using an urban waterlogging model, thereby obtaining first urban waterlogging simulation data; Step S42: Based on the first urban waterlogging simulation data, the urban area important infrastructure data and the urban waterlogging buffer zone data are divided into regional waterlogging data, thereby obtaining important infrastructure area waterlogging data and urban waterlogging buffer zone waterlogging data; and waterlogging benchmarks are set based on the important infrastructure area waterlogging data and the urban waterlogging buffer zone waterlogging data, thereby obtaining initial simulated waterlogging benchmark data. Step S43: extracting the pipe network pump station and valve control parameters from the urban area pipe network inspection data, thereby obtaining pump station control parameter data and valve control parameter data; Step S44: setting an objective function and constraints based on the water accumulation range data of important urban infrastructure and the water accumulation allowable range data of the water accumulation buffer zone, thereby obtaining a fitness function and a constraint condition function; Step S45: generating an initialized particle swarm based on the initial simulated waterlogging benchmark data, the fitness function, and the constraint condition function, and based on the pump station control parameter data and the valve control parameter data; calculating the initial fitness values ​​of the particles in the initialized particle swarm; selecting the global optimal particle from the initial fitness values ​​of the particles; and recording the individual optimal solution of each particle, thereby obtaining the global optimal particle and the individual optimal solution of the particle; Step S46: Iteratively optimize based on the constraint function and the global optimal particle and the individual optimal solution of the particle until the preset early stopping condition is met, thereby obtaining the global optimal solution; Step S47: convert the global optimal solution into waterlogging scheduling parameters to obtain a waterlogging scheduling parameter group for the urban area, and upload it to the urban drainage management platform to execute the waterlogging scheduling task.

9. The intelligent dispatching method for urban waterlogging and important infrastructure according to claim 8 is characterized in that: Step S44 is specifically as follows: Step S441: constructing a penalty function based on the water accumulation allowable range data of the water accumulation buffer zone; Step S442: Constructing a fitness function based on the penalty function and the waterlogging range data of important urban infrastructure, wherein the fitness function is specifically: Where f is the fitness function value, n is the total number of important infrastructures, i is the index of important infrastructure, α is the global weight of the buffer penalty, and w i is the weight used to control the water depth of the i-th important infrastructure in the fitness function, k i is the weight of the waterlogged area of ​​the i-th important infrastructure in the fitness function, D i is the water depth of the i-th important infrastructure, d i is the water depth target of the i-th important infrastructure, A i is the waterlogged area of ​​the i-th important infrastructure, a i is the target waterlogging area of ​​the i-th important infrastructure, A t is the total waterlogged area excluding the waterlogged buffer zone, A tr is the total waterlogged area target excluding the waterlogged buffer zone, and K is the weight of the total waterlogged area; Step S443: constructing a control parameter constraint condition function according to the pump station control parameter data and the valve control parameter data, thereby obtaining a constraint condition function.

10. The intelligent dispatching method for urban waterlogging and important infrastructure according to claim 8 is characterized in that: Step S45 is specifically as follows: Step S451: performing random combinations of scheduling parameters based on the constraint condition function, the pump station control parameter data, and the valve control parameter data, thereby obtaining control scheduling parameter combination data; Step S452: Initialize particles according to the control scheduling parameter combination data to obtain an initialized particle swarm; Step S453: performing urban waterlogging simulation on the urban area rainfall data and the initialized particle swarm using the urban waterlogging model, thereby obtaining initialized particle simulation data; Step S454: performing particle initialization fitness calculation on the initialized particle simulation data using a fitness function, thereby obtaining the particle initial fitness value; Step S455: performing individual optimal solution selection on the initial fitness value of the particle to obtain the individual optimal solution of the particle, and performing global optimal solution screening based on the individual optimal solution of the particle to obtain the global optimal particle.

Images