High-density urban ponding evolution and early warning method based on digital twinning

Abstract

The invention relates to the technical field of digital twinning, in particular to a high-density urban ponding evolution and early warning method based on digital twinning. The method comprises the following steps: real-time ponding depth, real-time river water level, real-time meteorological conditions and real-time drainage pipe network water level conditions corresponding to a city are collected in real time through ponding depth, river water level, meteorological monitoring and drainage pipe network sensors installed in the city, digital twinborn construction is carried out, and an urban inland inundation digital twinborn model is generated; obtaining drainage pipe network distribution and carrying out drainage grid division to generate an urban drainage grid model; acquiring a historical ponding event rule, and performing ponding area prediction analysis and ponding evolution coupling analysis to generate an urban ponding evolution distribution field; performing ponding space-time evolution analysis and ponding early warning processing on the urban ponding evolution distribution field so as to execute corresponding urban ponding emergency response work. According to the invention, accurate ponding evolution prediction and effective early warning can be provided.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a high-density urban waterlogging evolution and early warning method based on digital twin. Background Art

[0002] The frequency and intensity of extreme climate events such as rainstorms and typhoons are increasing, which has a huge impact on urban infrastructure, residents' lives and economic activities. Especially in high-density cities, due to the tight land use, heavy drainage system load and complex underground facilities, waterlogging is more serious and often difficult to predict and respond to in time. In this context, digital twin technology, as an advanced urban management tool, has gradually been introduced into the field of urban water affairs and disaster management. By creating a virtual copy of the physical world, digital twin technology can simulate and monitor various changes in the urban environment in real time, especially in complex hydrological and drainage systems. By integrating multi-dimensional data such as urban geographic information, meteorological data, drainage facilities, traffic flow, terrain, etc. into digital models, digital twins can realize real-time dynamic simulation of the evolution of urban waterlogging, thereby improving the timeliness and accuracy of waterlogging warnings. However, although there are some waterlogging prediction and management methods based on hydrological models, these methods still have certain limitations when facing the complex environment of high-density cities. They find it difficult to handle real-time changing meteorological data and the operating status of drainage networks, and cannot fully consider the mutual influence between different factors. As a result, there is a lack of global analysis of the waterlogging evolution process, making waterlogging warning inefficient. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a high-density urban waterlogging evolution and early warning method based on digital twins to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above purpose, a high-density urban waterlogging evolution and early warning method based on digital twins includes the following steps: Step S1: The real-time waterlogging depth, real-time river water level, real-time meteorological conditions and real-time drainage network water level of the city are collected in real time by installing waterlogging depth sensors, river water level sensors, meteorological monitoring equipment and drainage network sensors in the city, and a digital twin is constructed based on the real-time waterlogging depth, real-time meteorological conditions and real-time drainage network water level of the city in combination with the land use type, terrain and geomorphology data and building road information model of the city, so as to generate a digital twin model of urban waterlogging; Step S2: Obtain the drainage network distribution corresponding to the city, and divide the urban waterlogging digital twin model into drainage grids based on the drainage network distribution corresponding to the city and the real-time river water level to generate an urban drainage grid model; obtain the historical waterlogging event pattern corresponding to the city, and perform waterlogging area prediction and analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event pattern corresponding to the city to obtain the urban waterlogging prediction area; Step S3: The current measured waterlogging depth, river water level, rainfall process in the past period, and drainage network status corresponding to the urban waterlogging prediction area are obtained through the urban waterlogging digital twin model as real-time monitoring data corresponding to the urban waterlogging prediction area, and waterlogging evolution coupling analysis is performed on the urban waterlogging prediction area based on the real-time monitoring data corresponding to the urban waterlogging prediction area to generate an urban waterlogging evolution distribution field; Step S4: Analyze the spatiotemporal evolution of urban waterlogging evolution distribution field to obtain the evolution and development trend of urban waterlogging at different spatiotemporal nodes; perform waterlogging early warning processing on the corresponding urban waterlogging evolution distribution field based on the evolution and development trend of urban waterlogging at different spatiotemporal nodes to generate an urban waterlogging early warning distribution field to execute corresponding urban waterlogging emergency response work.

[0005] Further, step S1 includes the following steps: Step S11: performing real-time monitoring of urban waterlogging by installing waterlogging depth sensors at various location nodes in the city to obtain the corresponding real-time waterlogging depth of the city; Step S12: Real-time monitoring of the river water level in the city is performed by installing river water level sensors at various river locations in the city to obtain the real-time river water level corresponding to the city, including the water level height and the corresponding time; Step S13: Performing real-time weather monitoring of the city through weather monitoring equipment installed at various location nodes in the city to obtain real-time weather conditions corresponding to the city, including rainfall and rainfall duration; Step S14: The drainage network of the city is monitored in real time by means of the drainage network liquid level and flow rate sensors installed at various location nodes of the city, so as to obtain the real-time drainage network water level status corresponding to the city, including the liquid level and drainage flow rate corresponding to the drainage network nodes; Step S15: Obtain the land use type, terrain and geomorphology data, and building road information model corresponding to the city, and construct a digital twin based on the real-time waterlogging depth, real-time meteorological conditions, and real-time drainage network water level conditions corresponding to the city in combination with the land use type, terrain and geomorphology data, and building road information model corresponding to the city to generate a digital twin model of urban waterlogging.

[0006] Further, step S2 includes the following steps: Step S21: Obtain the topography, building density and drainage facility layout of the city, and obtain the drainage network distribution of the city according to the topography, building density and drainage facility layout of the city; Step S22: Based on the drainage network distribution corresponding to the city and the real-time river water level, the drainage carrying capacity of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model is evaluated to obtain the urban drainage network carrying capacity matrix; Step S23: obtaining the geographic space, drainage network layout and water flow characteristics at the corresponding distribution location through the urban waterlogging digital twin model, and performing water flow load assessment and analysis based on the geographic space, drainage network layout and water flow characteristics at the corresponding distribution location to obtain the drainage water flow load at the corresponding distribution location of the city; Step S24: performing drainage grid load matching and division on the urban waterlogging digital twin model based on the drainage network load capacity at the corresponding distribution position in the urban drainage network load capacity matrix and the drainage flow load at the corresponding distribution position in the city, so as to generate an urban drainage grid model; Step S25: Obtain the historical waterlogging event patterns corresponding to the city, and perform waterlogging area prediction analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event patterns corresponding to the city, so as to obtain the urban waterlogging prediction area.

[0007] Further, step S22 includes the following steps: Obtain the drainage network pipe diameter and drainage network pipe slope at the corresponding distribution location through the drainage network distribution of the city; Conduct a statistical analysis of the drainage flow rate of the drainage network at the corresponding distribution locations in the urban waterlogging digital twin model to obtain the drainage network flow rate at the corresponding distribution locations in the city; The real-time river water level corresponding to the city is used to obtain the time-series fluctuation of the river water level at the corresponding distribution position in the urban waterlogging digital twin model, and based on the time-series fluctuation of the river water level at the corresponding distribution position in the city, the outlet flow constraint analysis of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model is performed to obtain the time-varying constraint of the corresponding river water level in the city on the outlet flow of the drainage network; Based on the time-varying constraints of the drainage network pipe diameter, drainage network pipe slope, drainage network flow rate and the corresponding river water level in the city on the drainage network outlet flow, the drainage network carrying capacity measurement calculation formula is used to evaluate and calculate the carrying capacity of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model, so as to obtain the drainage network carrying capacity coefficient at the corresponding distribution position in the city; According to the carrying capacity coefficient of the drainage network at the corresponding distribution location in the city, the drainage capacity matrix of the drainage network at the corresponding distribution location in the urban waterlogging digital twin model is constructed to obtain the carrying capacity matrix of the urban drainage network.

[0008] Furthermore, the calculation formula for measuring the carrying capacity of the drainage network is specifically: ; ; In the formula, The coordinates of the city's distribution location The carrying capacity coefficient of the drainage network at It is the three-dimensional space area covered by the drainage network. is the horizontal coordinate parameter of the distribution position, is the ordinate parameter of the distribution location, is the vertical coordinate parameter of the distribution location, is the time variable parameter, To constrain the initial time of the integration, To constrain the end time of the integration, For the city in time The time-varying constraint of the river water level on the outlet flow of the drainage network at the time. The coordinates of the city's distribution location and in time The river water level at the time, is the linear influence coefficient of the river water level on the outlet flow of the drainage network, is the quadratic nonlinear influence coefficient of the river water level on the outlet flow of the drainage network, is an exponential function, For the city in time The drainage network outlet flow at time, is the initial flow rate at the outlet of the drainage network, is the drainage network flow response time attenuation control parameter, The coordinates of the city's distribution location The water flow rate at The coordinates of the city's distribution location The maximum permissible water flow rate at The coordinates of the city's distribution location The diameter of the drainage network pipe at is the weight factor affecting the pipe diameter load, The coordinates of the city's distribution location The slope of the drainage network pipes at is the weight factor affecting the pipeline slope load, The coordinates of the city's distribution location The flow rate of the drainage network at is the flow velocity bearing weight factor, It is the correction factor of the drainage network bearing capacity coefficient.

[0009] Further, the water flow load assessment analysis in step S23 based on the geographical space, drainage network layout and water flow characteristics at the corresponding distribution location includes the following steps: According to the geographical space and drainage network layout at the corresponding distribution location, drainage space layout load constraint analysis is carried out to obtain the drainage space layout load constraint conditions at the corresponding distribution location of the city; According to the water flow characteristics at the corresponding distribution positions, the water flow dynamic distribution analysis is performed to generate the water flow dynamic distribution flow field at the corresponding distribution positions in the city; Based on the drainage space layout load constraints at the corresponding distribution locations in the city, the water flow load evaluation and analysis is carried out on the dynamic distribution flow field of the water flow at the corresponding distribution locations in the city to obtain the drainage water flow load at the corresponding distribution locations in the city.

[0010] Further, step S24 includes the following steps: Step S241: Based on the drainage pipe network carrying capacity at the corresponding distribution position in the urban drainage pipe network carrying capacity matrix, the drainage water flow load at the corresponding distribution position of the city is subjected to drainage bearing matching analysis. If the drainage pipe network carrying capacity at the corresponding distribution position is greater than or equal to the drainage water flow load, it is determined as the drainage bearing balance matching point of the corresponding drainage pipe network carrying capacity; if the drainage pipe network carrying capacity at the corresponding distribution position is less than the drainage water flow load, a new bearing matching analysis is performed at a distribution position parallel to the outside until a drainage bearing balance matching point is determined. Step S242: connecting equal-value drainage grids according to drainage load balance matching points of different drainage network carrying capacities to generate urban drainage grid boundaries corresponding to different drainage network carrying capacities; Step S243: Based on the urban drainage grid boundaries corresponding to different drainage network carrying capacities, the urban waterlogging digital twin model is divided into drainage grid carrying capacity matching to generate an urban drainage grid model.

[0011] Further, the step S25 of performing waterlogging area prediction analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event law corresponding to the city includes the following steps: A two-dimensional surface model of waterlogging diffusion is constructed based on the historical waterlogging events corresponding to the city, so as to reflect the diffusion of surface waterlogging after overflow in each drainage grid partition in the city and its impact on the distribution of waterlogging in the surrounding areas, and generate a two-dimensional surface law model of urban waterlogging diffusion; Based on the two-dimensional surface law model of urban waterlogging diffusion, the frequency of waterlogging events is measured for each urban drainage grid partition in the urban drainage grid model to obtain the frequency of waterlogging events corresponding to each urban drainage grid partition; Based on the frequency of waterlogging events corresponding to each urban drainage grid partition, the corresponding urban drainage grid partitions in the urban drainage grid model are connected to the high-incidence waterlogging grid areas to obtain the high-incidence waterlogging grid areas in the city; According to the high-incidence waterlogging grid areas in the city, the terrain slope distribution and ground water infiltration efficiency between the corresponding drainage grid partitions in the urban drainage grid model are obtained; Based on the terrain slope distribution and ground infiltration efficiency between the corresponding drainage grid divisions, a waterlogging area prediction analysis is conducted on the high-incidence waterlogging grid areas in the city to obtain the urban waterlogging prediction area.

[0012] Further, step S3 includes the following steps: Step S31: The current measured water depth, river water level, rainfall process in the past period, and drainage network status corresponding to the urban waterlogging prediction area are obtained through the urban waterlogging digital twin model as real-time monitoring data corresponding to the urban waterlogging prediction area, and the real-time monitoring data corresponding to the simulation start time is used as the initial condition data of the waterlogging prediction area; Step S32: Obtain the rainfall amount and rainfall duration in the urban waterlogging prediction area corresponding to the future forecast time through the urban waterlogging digital twin model to determine the rainfall time series, and obtain the rainfall time series in the urban waterlogging prediction area corresponding to the future forecast time; Step S33: obtaining the terrain, drainage capacity and climate conditions corresponding to the urban waterlogging prediction area through the urban waterlogging digital twin model, wherein the climate conditions include rainfall, evaporation and river soil permeability, and estimating the river water level change of the corresponding urban waterlogging prediction area at the future forecast time according to the terrain, drainage capacity and climate conditions corresponding to the urban waterlogging prediction area, so as to obtain the river water level change data corresponding to the urban waterlogging prediction area at the future forecast time; Step S34: Based on the initial condition data of the waterlogging prediction area, the rainfall time series and the river water level change data of the urban waterlogging prediction area corresponding to the future forecast time are used as input data to run the urban waterlogging digital twin model in step S2 to generate a future forecast simulation process corresponding to the urban waterlogging model; Step S35: using the real-time monitoring data corresponding to the urban waterlogging prediction area to perform real-time correction and waterlogging rolling forecast on the urban waterlogging digital twin model in the future forecast simulation process corresponding to the urban waterlogging model, so as to generate an urban waterlogging waterlogging rolling forecast digital model; Step S36: obtaining the water level and drainage network status corresponding to the urban waterlogging prediction area through the urban waterlogging waterlogging rolling forecast digital model, and performing rainfall-water level spatiotemporal correlation analysis on the rainfall time series corresponding to the future forecast time in the urban waterlogging prediction area based on the water level corresponding to the urban waterlogging prediction area, so as to generate a rainfall-water level spatiotemporal correlation distribution field corresponding to the urban waterlogging prediction area; Step S37: Based on the drainage pipe network status corresponding to the urban waterlogging prediction area, drainage efficiency attenuation analysis is performed on the urban waterlogging prediction area corresponding to the urban waterlogging prediction digital model, and a drainage pipe network efficiency attenuation distribution field corresponding to the urban waterlogging prediction area is generated; Step S38: Based on the rainfall-water level spatiotemporal correlation distribution field corresponding to the urban waterlogging prediction area and the drainage network efficiency attenuation distribution field, a waterlogging evolution coupling analysis is performed on the urban waterlogging prediction area corresponding to the urban waterlogging rolling forecast digital model to generate an urban waterlogging evolution distribution field.

[0013] Further, step S37 includes the following steps: Step S371: obtaining the drainage network pressure and drainage treatment efficiency at the corresponding distribution location through the drainage network status corresponding to the urban waterlogging prediction area; Step S372: performing drainage network performance evaluation and analysis on the drainage network pressure and drainage treatment efficiency at the corresponding distribution positions in the urban waterlogging prediction area, and obtaining the drainage network drainage efficiency at the corresponding distribution positions in the urban waterlogging prediction area; Step S373: obtaining the sediment accumulation amount and the drainage pipe damage rate at the corresponding distribution position of the urban waterlogging prediction area, and performing drainage efficiency attenuation analysis on the drainage efficiency of the drainage pipe network at the corresponding distribution position of the urban waterlogging prediction area based on the sediment accumulation amount and the drainage pipe damage rate, to obtain the drainage efficiency attenuation degree at the corresponding distribution position of the urban waterlogging prediction area; Step S374: performing an efficiency attenuation distribution analysis on the urban waterlogging prediction area based on the drainage efficiency attenuation degree at the corresponding distribution positions in the urban waterlogging prediction area, and generating a drainage network efficiency attenuation distribution field corresponding to the urban waterlogging prediction area.

[0014] Beneficial effects of the present invention: Compared with the prior art, the high-density urban waterlogging evolution and early warning method based on digital twin proposed in the present invention has the beneficial effect that in urban waterlogging prediction and management, real-time data of waterlogging depth, river water level, meteorological monitoring and drainage network are crucial. By installing various sensors in the city (waterlogging depth sensors, river water level sensors, meteorological monitoring equipment and drainage network sensors), these data can be obtained in real time, thereby providing reliable input information for subsequent waterlogging predictions, and by combining these real-time data with urban land use types, terrain and geomorphological data, and building road information models, an accurate urban waterlogging digital twin model can be generated. Digital twin technology can connect the physical world of cities and their basic Infrastructure virtualization dynamically reflects the changing trends and influencing factors of urban waterlogging, and establishes a two-way interaction between virtual and reality. Through the digital twin model, urban managers can observe the occurrence and development of waterlogging more intuitively and in real time, so that the evolution of waterlogging in different geographical environments can be simulated more accurately. The construction of the digital twin model makes the city not just a static physical entity, but a dynamic system that can provide real-time feedback and prediction. This real-time, global and accurate data support can help decision makers understand the health of the urban drainage system in a timely manner, so that they can fully consider the mutual influence between different factors, and can process real-time changing meteorological data and drainage network operation status, reducing the frequency and impact of waterlogging disasters. Secondly, by obtaining and analyzing the distribution of urban drainage networks, the urban waterlogging digital twin model can be further refined, especially based on drainage network and river water level drainage grid division. This grid model divides the city into multiple drainage units, which is convenient for separate analysis and monitoring of the waterlogging situation in each area. By analyzing the laws of historical waterlogging events in each drainage grid area, more accurate prediction of waterlogging areas can be achieved, thereby providing refined guidance for the prevention and control of urban waterlogging. Specifically, based on the distribution of the city's drainage network, the drainage capacity and efficiency of each area can be accurately simulated. By dividing the city into multiple grids, the risk of urban flooding in a single area can be accurately determined, and potential waterlogging risks can be discovered in a timely manner, especially in areas with weak drainage systems or prone to waterlogging. The analysis of the patterns of historical waterlogging events, combined with the regional meteorological conditions and drainage capacity, can help to accurately predict possible waterlogging areas in the future and reduce losses and impacts when waterlogging occurs.Then, by combining real-time monitoring data (such as waterlogging depth, river water level, rainfall process, etc.) with the status of the urban drainage network, the evolution process of waterlogging and possible future waterlogging scenarios can be predicted more accurately. The coupled analysis of waterlogging evolution can reveal the entire process of urban waterlogging from formation to development, and predict the distribution of waterlogging at different time nodes. The generated waterlogging evolution distribution field provides a scientific basis for emergency response to urban waterlogging, and can help decision makers to timely understand the evolution trend of waterlogging in different regions, so as to take targeted drainage measures and diversion plans. The key to this analysis method lies in its multi-dimensional analysis ability, which can comprehensively consider multiple factors (such as rainfall intensity, river water level changes, drainage network conditions, etc.) to make more accurate evolution predictions of waterlogging. Through the generation of waterlogging evolution distribution field, urban managers can clearly see the changing trend of waterlogging in the future, and then make corresponding emergency measures, such as dispatching drainage systems, diverting traffic, setting up warnings for waterlogged areas, etc. Especially when cities face extreme weather events (such as heavy rains, typhoons, etc.), waterlogging evolution analysis can provide early warning, avoid the spread of disasters, and reduce the difficulty of post-disaster recovery. Finally, by analyzing the spatiotemporal evolution of the waterlogging evolution distribution field and generating a waterlogging warning distribution field, the key to this analysis is that it can help decision makers fully understand the spatiotemporal characteristics of waterlogging phenomena, identify the high-incidence time, location and development trend of waterlogging, thereby improving the timeliness and efficiency of waterlogging warning. The spatiotemporal evolution analysis of waterlogging can reveal the dynamic changes of waterlogging areas at different time nodes, provide decision-making basis for urban managers, and enable disaster prevention measures to be deployed at the best time. By combining the trend of waterlogging evolution and development, urban management departments can formulate targeted emergency response plans for different time periods and regions, make flood prevention preparations in advance, and promptly initiate emergency diversion, drainage acceleration and other measures. This analysis not only helps identify the current risk areas of waterlogging, but also predicts the possible development of waterlogging in the future, thereby providing a long-term planning basis for disaster prevention and mitigation work in high-density cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings: Figure 1 It is a schematic flow chart of the steps of the high-density urban waterlogging evolution and early warning method based on digital twins of the present invention. DETAILED DESCRIPTION

[0016] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0017] To achieve this, please refer to Figure 1 The present invention provides a high-density urban waterlogging evolution and early warning method based on digital twins. In the embodiments of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the steps of the high-density urban waterlogging evolution and early warning method based on digital twins of the present invention. In this example, the high-density urban waterlogging evolution and early warning method based on digital twins includes the following steps: Step S1: The real-time waterlogging depth, real-time river water level, real-time meteorological conditions and real-time drainage network water level of the city are collected in real time by installing waterlogging depth sensors, river water level sensors, meteorological monitoring equipment and drainage network sensors in the city, and a digital twin is constructed based on the real-time waterlogging depth, real-time meteorological conditions and real-time drainage network water level of the city in combination with the land use type, terrain and geomorphology data and building road information model of the city, so as to generate a digital twin model of urban waterlogging; In an embodiment of the present invention, a variety of sensor devices are deployed in the city, including water depth sensors, river water level sensors, meteorological monitoring equipment and drainage pipe network sensors, to collect water level data of the city in real time. These data include: real-time water depth of various areas of the city, real-time water level of various rivers, local meteorological conditions (such as rainfall, wind speed, temperature, etc.), and water level status of the drainage pipe network. The real-time collection of this information is achieved through the Internet of Things (IoT) system. The sensor transmits the data to the central data processing platform in real time through a wireless network. In addition, it is necessary to obtain the topography and landform data of the city, as well as land use types (such as residential areas, commercial areas, green spaces, etc.) and building and road layout information through geographic information system (GIS) technology. This information helps to better understand the waterlogging risk of the city. By integrating these multi-source data, a digital twin model is constructed to simulate the possible occurrence of urban waterlogging. The digital twin model is a virtual mapping of the real environment of the city, which includes the above-mentioned sensor data, geographic information data and a functional model of the urban drainage system. The model provides a tool for subsequent waterlogging prediction, analysis and early warning that is dynamically updated and reflects the state of urban waterlogging in real time, and finally generates a digital twin model of urban waterlogging.

[0018] Step S2: Obtain the drainage network distribution corresponding to the city, and divide the urban waterlogging digital twin model into drainage grids based on the drainage network distribution corresponding to the city and the real-time river water level to generate an urban drainage grid model; obtain the historical waterlogging event pattern corresponding to the city, and perform waterlogging area prediction and analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event pattern corresponding to the city to obtain the urban waterlogging prediction area; In an embodiment of the present invention, it is necessary to obtain the city's drainage network distribution information, which is usually provided by the city planning department or obtained through survey and modeling of the existing pipe network system. Based on the distribution of these drainage pipe networks and combined with real-time river water level data, drainage grids are divided. The drainage grid division is to divide the city into multiple small areas according to the watershed of the drainage network. The drainage performance and waterlogging risk of each area are analyzed independently. Through grid management, more accurate emergency plans and waterlogging risk assessments can be formulated for each small area. Then, combined with the laws of historical urban waterlogging events, a corresponding two-dimensional surface model of urban waterlogging diffusion is constructed to reflect the diffusion of surface water after overflow in each drainage grid partition in the city and its impact on the waterlogging distribution in the surrounding areas, to analyze historical rainfall data, waterlogging depth data and the response of the drainage system, and to achieve waterlogging area prediction analysis for each drainage grid area. The extraction of historical waterlogging event laws can be completed through big data analysis and machine learning technology. The city’s historical meteorological data, waterlogging data and pipe network response data are used to construct a waterlogging prediction model to predict the possibility and depth of waterlogging in a specific area under specific rainfall or river water level conditions. The results of this predictive analysis will be further refined to the drainage grid, indicating which areas may experience waterlogging, and conducting a waterlogging risk assessment on each grid, ultimately obtaining the urban waterlogging prediction area.

[0019] Step S3: The current measured waterlogging depth, river water level, rainfall process in the past period, and drainage network status corresponding to the urban waterlogging prediction area are obtained through the urban waterlogging digital twin model as real-time monitoring data corresponding to the urban waterlogging prediction area, and waterlogging evolution coupling analysis is performed on the urban waterlogging prediction area based on the real-time monitoring data corresponding to the urban waterlogging prediction area to generate an urban waterlogging evolution distribution field; In the embodiment of the present invention, the real-time monitoring data corresponding to the waterlogging prediction area is obtained through the waterlogging digital twin model, including the measured waterlogging depth, real-time river water level, historical rainfall process and the current status of the drainage network. These data are monitored in real time by sensors and meteorological stations and other equipment and input into the data platform. Then, based on these real-time monitoring data, a hydrological and hydraulic model (such as SWMM or MIKE21) is used to perform a coupled analysis of the evolution of waterlogging. The analysis model combines multiple factors such as rainfall, river water level, drainage network status and geographical characteristics to simulate the entire process of waterlogging from rainfall to flowing into the river or being discharged by the drainage system. Through numerical calculation and dynamic simulation, the distribution of waterlogging at different time points and in different regions is predicted, and a waterlogging evolution distribution field is generated, the temporal and spatial variation trend of the waterlogging area is clarified, and finally the urban waterlogging evolution distribution field is generated.

[0020] Step S4: Analyze the spatiotemporal evolution of urban waterlogging evolution distribution field to obtain the evolution and development trend of urban waterlogging at different spatiotemporal nodes; perform waterlogging early warning processing on the corresponding urban waterlogging evolution distribution field based on the evolution and development trend of urban waterlogging at different spatiotemporal nodes to generate an urban waterlogging early warning distribution field to execute corresponding urban waterlogging emergency response work.

[0021] In an embodiment of the present invention, a spatiotemporal evolution analysis is performed on the distribution field of waterlogging evolution after waterlogging evolution, with the purpose of revealing the changing trend of waterlogging areas at different time nodes. Through the spatiotemporal evolution analysis, the expansion trend of waterlogging, the peak water level and the key affected areas can be obtained. This analysis adopts a spatiotemporal data modeling method, combines historical waterlogging data with real-time data, and uses time series analysis and spatial interpolation methods to predict the changing trajectory of waterlogging, and performs early warning processing on the evolution of waterlogging at each time node. By setting parameters such as waterlogging level, waterlogging range, and urban drainage capacity, combined with real-time monitoring data, an urban waterlogging early warning distribution field is dynamically generated. The early warning distribution field will point out the severity of waterlogging in different areas and the impact on infrastructure such as transportation and buildings, and trigger emergency response measures through an intelligent decision-making system. For example, when the waterlogging risk in a certain area reaches a preset threshold, the emergency response process is automatically started, such as arranging emergency repairs to the drainage network, diverting traffic, or starting emergency drainage equipment, etc., to reduce the impact of waterlogging on urban operations, and finally perform corresponding urban waterlogging emergency response work.

[0022] Further, step S1 includes the following steps: Step S11: performing real-time monitoring of urban waterlogging by installing waterlogging depth sensors at various location nodes in the city to obtain the corresponding real-time waterlogging depth of the city; In an embodiment of the present invention, water depth sensors are first deployed in major waterlogging-prone areas, low-lying areas, transportation hubs and other location nodes in the city. These sensors measure the depth of waterlogging and upload data to the city management center in real time. The specific installation method is to fix the sensor at a predetermined position underground or below the road surface to ensure that changes in water depth can be detected in time during rainfall. The sensor usually uses ultrasonic or laser ranging technology to accurately measure the water surface height of the waterlogging to ensure the accuracy and real-time nature of the data. The monitoring system can transmit data to the data center through wireless transmission technology (such as LoRa, NB-IoT, etc.), and conduct comprehensive analysis combined with data from other sensors to understand the waterlogging conditions in different locations in real time. The water depth data will be updated once a minute and transmitted to the control platform to finally obtain the corresponding real-time water depth of the city.

[0023] Step S12: Real-time monitoring of the river water level in the city is performed by installing river water level sensors at various river locations in the city to obtain the real-time river water level corresponding to the city, including the water level height and the corresponding time; In an embodiment of the present invention, river water level sensors are installed at the main river locations in the city (including rivers, lakes and their tributaries, etc.). These sensors can be water level gauges, pressure sensors or buoy sensors. Each sensor continuously monitors the changes in the river water level according to its installation location and records real-time water level data. These sensors are set in different depth areas of the water body, and the water level is calculated by the water pressure changes of the sensors. After data collection, the water level data is transmitted to the data center through wireless communication technology. In the collected data, in addition to the water level height, a timestamp is also recorded to form a set of time series data, which is used to analyze the changing trend of the water level and finally obtain the real-time river water level corresponding to the city, including the water level height and the corresponding time.

[0024] Step S13: Performing real-time weather monitoring of the city through weather monitoring equipment installed at various location nodes in the city to obtain real-time weather conditions corresponding to the city, including rainfall and rainfall duration; In an embodiment of the present invention, meteorological monitoring equipment is deployed in different areas of the city, especially in areas with frequent rainfall or prone to extreme weather. These devices include rain gauges, temperature and humidity sensors, wind speed and direction meters, etc. The rain gauges measure the intensity and duration of rainfall in real time in an automated manner, and the data is uploaded to the meteorological monitoring system in real time via a wireless network. During the rainfall monitoring process, the system will record the time when the rainfall starts, the intensity of the rainfall, and the duration of the rainfall, providing basic data for subsequent water level monitoring and early warning. In addition, the meteorological monitoring equipment will also record real-time meteorological data such as temperature, humidity, and wind speed. This information plays an important role in predicting rain evaporation and other climate change factors, and ultimately obtains the corresponding real-time meteorological conditions of the city, including rainfall and rainfall duration.

[0025] Step S14: The drainage network of the city is monitored in real time by means of the drainage network liquid level and flow rate sensors installed at various location nodes of the city, so as to obtain the real-time drainage network water level status corresponding to the city, including the liquid level and drainage flow rate corresponding to the drainage network nodes; In an embodiment of the present invention, the drainage network system of a city is monitored in real time by installing liquid level sensors and flow rate sensors at different key nodes (such as pipeline branches, intersections of important road sections, etc.). The liquid level sensor can measure the water level inside the pipeline, usually using a pressure sensor or a floating liquid level gauge. The flow rate sensor measures the speed of the water flow in the pipeline and calculates the drainage volume in combination with the cross-sectional area of ​​the pipeline. These sensors are installed at key positions in the pipeline system to ensure that the drainage status of the pipeline network can be monitored. Real-time data is sent to the data center via a wireless communication network. The system can predict the load and possible blockage of the drainage network based on the flow rate and liquid level change trends. During rainfall, it can evaluate the operation of each drainage network node in real time, predict which areas may have poor drainage or waterlogging problems, and finally obtain the real-time drainage network water level status corresponding to the city, including the liquid level and drainage flow rate corresponding to the drainage network node.

[0026] Step S15: Obtain the land use type, terrain and geomorphology data, and building road information model corresponding to the city, and construct a digital twin based on the real-time waterlogging depth, real-time meteorological conditions, and real-time drainage network water level conditions corresponding to the city in combination with the land use type, terrain and geomorphology data, and building road information model corresponding to the city to generate a digital twin model of urban waterlogging.

[0027] In an embodiment of the present invention, by integrating real-time data from water accumulation depth, meteorological monitoring and drainage network, these data are gathered to the data processing platform, and after data preprocessing, cleaning and fusion, a unified urban hydrological and meteorological data set is formed. In addition, in order to achieve accurate digital twin modeling, it is also necessary to collect urban geographic information data, such as land use type, topography, geomorphological data and building road information. These data can be obtained through remote sensing satellite images, geographic information systems (GIS) and ground surveys. Based on these multi-source data, a virtual city model is established using digital twin technology, and the urban hydrological environment under different scenarios is simulated by combining physical models and data-driven models. By simulating and analyzing the evolution of water accumulation in the city under different rainfall intensities, meteorological conditions and drainage network conditions, possible waterlogging areas can be accurately predicted, early warning information can be issued in a timely manner, and urban managers can be guided to make emergency decisions. The digital twin model can not only reflect the current state of urban waterlogging in real time, but also provide the evolution trend of waterlogging in the future based on historical data and predicted data, assist urban flood control planning and construction, and finally generate a digital twin model of urban waterlogging.

[0028] Further, step S2 includes the following steps: Step S21: Obtain the topography, building density and drainage facility layout of the city, and obtain the drainage network distribution of the city according to the topography, building density and drainage facility layout of the city; In an embodiment of the present invention, the topographic information of the city is obtained by remote sensing image data and geographic information system (GIS) technology, and by using laser radar (LiDAR) data or digital elevation model (DEM), the city's terrain undulations, mountains, hills, low-lying areas and other features can be accurately extracted to form a topographic map of the city. Then, combined with the building density information, the building coverage of each area can be calculated through urban planning data or building outline data, and the distribution of high-density building areas and low-density building areas can be determined. The acquisition of building density data can rely on high-resolution satellite images or three-dimensional models of buildings. For the arrangement of drainage facilities, the layout information of the drainage network can be obtained through the city's infrastructure database. If there is no complete network information in the database, the spatial distribution of urban drainage facilities can be gradually constructed by combining remote sensing images with ground surveys. By analyzing the relationship between the layout of the drainage network and the topography and building density of the city, the drainage network distribution model of the city can be further derived. The model will reflect the distribution, size, flow and other important information of the drainage pipes in detail, and finally the corresponding drainage network distribution of the city is obtained.

[0029] Step S22: Based on the drainage network distribution corresponding to the city and the real-time river water level, the drainage carrying capacity of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model is evaluated to obtain the urban drainage network carrying capacity matrix; In an embodiment of the present invention, by combining real-time meteorological data with river water level monitoring data, real-time hydrological information is obtained through Internet of Things (IoT) devices. This information includes precipitation, river water level, water flow rate, etc. Then, based on the real-time river water level data, the urban drainage pipe network distribution model is used to evaluate the drainage carrying capacity. Specifically, factors such as the pipe diameter, material, slope and geographical location of each drainage pipe need to be considered first, and the water flow carrying capacity of each pipe is calculated through a hydraulic model (such as the Saint-Venant equation or the Manning formula). The carrying capacity assessment of the drainage network should also be corrected in combination with the blockage of the drainage network and the aging of the pipes. Through this assessment, a detailed drainage network carrying capacity matrix can be obtained. Each item in the matrix represents the water flow processing capacity of the drainage network at the current river water level, and finally the urban drainage network carrying capacity matrix is ​​obtained.

[0030] Step S23: obtaining the geographic space, drainage network layout and water flow characteristics at the corresponding distribution location through the urban waterlogging digital twin model, and performing water flow load assessment and analysis based on the geographic space, drainage network layout and water flow characteristics at the corresponding distribution location to obtain the drainage water flow load at the corresponding distribution location of the city; In an embodiment of the present invention, by utilizing the previously constructed digital twin model of urban waterlogging, detailed information on each drainage network distribution location is obtained, including the geographic spatial characteristics of the location (such as slope, terrain type, etc.), the layout of the drainage network (such as the location, quantity and status of pipelines, diversion wells, inspection wells, etc.), and related water flow characteristics (such as water flow velocity, flow rate, precipitation intensity, etc.), and computational fluid dynamics (CFD) simulation is used in combination with the hydraulic model of the drainage network to simulate the water flow behavior under different precipitation conditions, and evaluate the flow velocity and flow rate changes when the water flows through different pipe network sections, thereby obtaining the water flow load. In this process, hydraulic analysis software for urban drainage systems (such as MIKE 21, HEC-RAS, etc.) is used to perform water flow load analysis, generate drainage water flow load data for each location, and finally obtain the drainage water flow load at the corresponding distribution location of the high-density city.

[0031] Step S24: performing drainage grid load matching and division on the urban waterlogging digital twin model based on the drainage network load capacity at the corresponding distribution position in the urban drainage network load capacity matrix and the drainage flow load at the corresponding distribution position in the city, so as to generate an urban drainage grid model; In an embodiment of the present invention, by combining the drainage network carrying capacity matrix with the water flow load data, a carrying capacity matching analysis is performed on each drainage network node. Specifically, in the digital twin model, for each drainage grid (i.e., a small area in the city), a matching analysis of the carrying capacity and load is performed in combination with the drainage network carrying capacity of the grid and the actual water flow load. If the drainage network carrying capacity of a certain area is greater than or equal to the water flow load of the area, it is necessary to grid the area, adjust the drainage network design or strengthen the drainage facilities. In this process, GIS can be combined with a hydraulic model, and machine learning or optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) can be used to perform optimal drainage grid division to generate a drainage grid model corresponding to the city. Each drainage grid corresponds to a specific carrying capacity and load condition, and ultimately a city drainage grid model is generated.

[0032] Step S25: Obtain the historical waterlogging event patterns corresponding to the city, and perform waterlogging area prediction analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event patterns corresponding to the city, so as to obtain the urban waterlogging prediction area.

[0033] In an embodiment of the present invention, data on waterlogging events in the city's history are collected, including information such as waterlogging time, waterlogging depth, and waterlogging duration. These data can be obtained through channels such as the city meteorological bureau, drainage management department, ground monitoring system, and historical flood archives. By analyzing these historical data, the patterns of waterlogging events can be extracted, such as which areas are susceptible to heavy rains, which areas have the most serious waterlogging overflows, etc., and by combining these historical patterns of waterlogging events, waterlogging prediction analysis can be performed on the urban drainage grid model. Specifically, by constructing a two-dimensional surface model of waterlogging diffusion, the diffusion of waterlogging in different geographic spatial areas is simulated. This model can predict the diffusion and spread of waterlogging in different areas by considering factors such as overflow of the drainage network, surface morphology, and precipitation intensity. Based on this model, the waterlogging area can be predicted for each drainage grid, and areas where waterlogging may occur can be identified to help deploy drainage facilities in advance. This process will generate an accurate urban waterlogging prediction area, and ultimately obtain an urban waterlogging prediction area.

[0034] Further, step S22 includes the following steps: Obtain the drainage network pipe diameter and drainage network pipe slope at the corresponding distribution location through the drainage network distribution of the city; In an embodiment of the present invention, the specific location distribution of each drainage pipe is extracted through the spatial information of the drainage network in the digital twin model of the city. This process uses geographic information system (GIS) data and the design drawings of the urban drainage system to map the specific location, pipeline direction and related pipeline characteristics of the urban drainage network onto the digital twin platform. Based on these data, the pipe diameter and slope of each pipe can be accurately identified. Specifically, laser scanning data (LIDAR) or high-definition satellite images are used, combined with on-site measured data, to calculate the diameter, slope and elevation difference of each pipe between upstream and downstream, and finally obtain the drainage network pipe diameter and drainage network pipe slope at the corresponding distribution position.

[0035] Preferably, a drainage flow rate statistical analysis is performed on the drainage network at the corresponding distribution position in the urban waterlogging digital twin model to obtain the drainage network flow rate at the corresponding distribution position in the city; In an embodiment of the present invention, a statistical analysis of the drainage flow rate is performed through real-time monitoring data of the urban drainage network. The acquisition of flow rate data depends on flow meters, pressure sensors and water level monitoring instruments in the pipelines. These devices will regularly feed back real-time data in the drainage network to the digital twin platform. In the system, the water flow velocity in each pipeline is first monitored and recorded in real time, and the instantaneous flow rate is obtained by the flow meter. The flow velocity is calculated based on the cross-sectional area of ​​the pipeline. Then, the flow velocity statistical analysis algorithm is used to perform statistical analysis on the flow velocity at each position, such as the mean, maximum, minimum and fluctuation value, so as to obtain the flow velocity data of each pipe section, and finally obtain the flow velocity of the drainage network at the corresponding distribution position in the city.

[0036] Preferably, the time series fluctuation of the river water level at the corresponding distribution position in the urban waterlogging digital twin model is obtained through the real-time river water level corresponding to the city, and the outlet flow constraint restriction analysis of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model is performed based on the time series fluctuation of the river water level at the corresponding distribution position in the city, so as to obtain the time-varying constraint of the corresponding river water level in the city on the outlet flow of the drainage network; In an embodiment of the present invention, the real-time water level changes of the river are used to simulate and analyze its impact on the outlet flow of the drainage network. First, by connecting with the urban hydrological monitoring system, the water level data of the river is obtained in real time. These data can reflect the temporal fluctuations of the river water level. In specific implementation, high-precision water level monitoring instruments and sensors are used to regularly obtain real-time water level information of the river. In the digital twin model, these real-time river water level data are connected to the outlet of the drainage network to analyze the flow carrying capacity of the drainage network under different water level conditions. If the river water level rises, the flow of the drainage network will be restricted, especially when the river water level approaches or exceeds the outlet of the pipeline, the water flow will flow in the opposite direction or the flow will decrease. Therefore, based on the data of time-series fluctuations, a time-varying flow constraint model is constructed. Through mathematical analysis and numerical simulation, the constraints that the outlet flow of the drainage network should be subject to under different river water level conditions are determined, and finally the time-varying constraints of the corresponding river water level in the city on the outlet flow of the drainage network are obtained.

[0037] Preferably, based on the time-varying constraints of the drainage network pipe diameter, drainage network pipe slope, drainage network flow rate and the city's corresponding river water level on the drainage network outlet flow, the drainage network carrying capacity measurement calculation formula is used to evaluate and calculate the drainage network at the corresponding distribution position in the urban waterlogging digital twin model, so as to obtain the drainage network carrying capacity coefficient at the corresponding distribution position in the city; In an embodiment of the present invention, a suitable drainage network carrying capacity measurement calculation formula is formed by combining the three-dimensional spatial area covered by the drainage network, the horizontal coordinate parameter of the distribution position, the vertical coordinate parameter of the distribution position, the time-varying constraint of the river water level on the drainage network outlet flow, the river water level, the linear influence coefficient of the river water level on the drainage network outlet flow, the quadratic nonlinear influence coefficient, the drainage network outlet flow, the drainage network outlet initial flow, the drainage network flow response time attenuation control parameter, the water flow, the maximum allowable water flow, the drainage network pipe diameter, the pipe diameter bearing influence weight factor, the drainage network pipe slope, the pipe slope bearing influence weight factor, the drainage network flow velocity, the flow velocity bearing influence weight factor and related parameters to perform a carrying capacity evaluation calculation on the drainage network at the corresponding distribution position in the urban waterlogging digital twin model to calculate the carrying capacity coefficient of the drainage pipe at each position. The carrying capacity coefficient represents the maximum drainage flow that the section of the drainage pipe can withstand under normal operation, and finally the drainage network carrying capacity coefficient at the corresponding distribution position in the city is obtained.

[0038] Preferably, a drainage capacity matrix of the drainage network at the corresponding distribution positions in the urban waterlogging digital twin model is constructed according to the drainage network carrying capacity coefficient at the corresponding distribution positions in the city to obtain the urban drainage network carrying capacity matrix.

[0039] In an embodiment of the present invention, a city-level drainage capacity matrix is ​​constructed based on the drainage network carrying capacity coefficients at the corresponding distribution locations of the city obtained by previous quantification. The rows and columns of the matrix represent the drainage network locations in different areas, and each element in the matrix represents the carrying capacity of the drainage network at that location under different scenarios. These scenarios include drainage needs under various climatic conditions such as normal rainfall, heavy rainfall, and typhoons. In the process of matrix construction, the drainage network is first divided into several regional units according to geographical regions, and then the drainage capacity of each unit under various climatic scenarios is evaluated in combination with historical precipitation data and the actual performance of the drainage network. The drainage capacity matrix shows the drainage network carrying capacity of the entire city at different locations and under different weather conditions, and finally the city drainage network carrying capacity matrix is ​​obtained.

[0040] Furthermore, the calculation formula for measuring the carrying capacity of the drainage network is specifically: ; ; In the formula, The coordinates of the city's distribution location The carrying capacity coefficient of the drainage network at It is the three-dimensional space area covered by the drainage network. is the horizontal coordinate parameter of the distribution position, is the ordinate parameter of the distribution location, is the vertical coordinate parameter of the distribution location, is the time variable parameter, To constrain the initial time of the integration, To constrain the end time of the integration, For the city in time The time-varying constraint of the river water level on the outlet flow of the drainage network at the time. The coordinates of the city's distribution location and in time The river water level at the time, is the linear influence coefficient of the river water level on the outlet flow of the drainage network, is the quadratic nonlinear influence coefficient of the river water level on the outlet flow of the drainage network, is an exponential function, For the city in time The drainage network outlet flow at time, is the initial flow rate at the outlet of the drainage network, is the drainage network flow response time attenuation control parameter, The coordinates of the city's distribution location The water flow rate at The coordinates of the city's distribution location The maximum permissible water flow rate at The coordinates of the city's distribution location The diameter of the drainage network pipe at is the weight factor affecting the pipe diameter load, The coordinates of the city's distribution location The slope of the drainage network pipes at is the weight factor affecting the pipeline slope load, The coordinates of the city's distribution location The flow rate of the drainage network at is the flow velocity bearing weight factor, It is the correction factor of the drainage network bearing capacity coefficient.

[0041] The present invention obtains a drainage network carrying capacity measurement calculation formula by using a specific mathematical model and verification, which is used to evaluate and calculate the carrying capacity of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model. The drainage network carrying capacity measurement calculation formula plays a very critical role in the urban waterlogging digital twin model. It comprehensively considers the physical properties of the drainage network (such as pipe diameter, slope, flow rate) and external factors (such as river water level and time-varying constraints on the drainage network outlet flow), and evaluates the carrying capacity of the drainage network under different time and space conditions through these factors. Specifically, the formula includes a variety of factors that affect the carrying capacity of the drainage network, the physical properties of the drainage network (pipe diameter, pipe slope and flow rate: pipe diameter , a larger pipe diameter can provide more drainage flow, so its impact on the carrying capacity of the drainage network is linear, and the weight factor Indicates the extent of this effect; the pipe slope The greater the slope, the higher the flow rate and the stronger the drainage capacity. The influence of the slope is measured by the weight factor Adjust the flow rate , flow rate directly affects drainage capacity, higher flow rate indicates stronger drainage capacity, and the effect of flow rate is measured through the weight factor To measure the temporal fluctuation of river water level , through the constraint of the time-varying river water level on the flow of the drainage network, it can more truly reflect the impact of the external water environment on the drainage network. The fluctuation of the river water level will not only affect the flow, but also the pressure and flow conditions of the drainage network; the ratio of water flow to maximum flow directly affects the working state of the drainage network, and excessive water flow will cause the network to overload. The carrying capacity of the drainage network is affected by time and the external environment, especially the changes in river water level and drainage flow. By introducing time-varying constraints, the formula can consider the dynamic impact of river water level on the drainage network in different time periods. In addition, the integral term ∫_A in the formula represents the distribution of the carrying capacity of the drainage network in the three-dimensional space area A. By considering the physical characteristics, flow velocity and constraint factors of the drainage network at different spatial locations, the carrying capacity of the drainage network at different locations in the entire urban area can be obtained. This spatial evaluation is of great significance for the prevention of urban waterlogging and the optimal design of the drainage system. In summary, this formula fully considers the distribution of the city in the coordinates of the distribution location. The carrying capacity coefficient of the drainage network at , the three-dimensional space area covered by the drainage network , distribution position horizontal coordinate parameter , distribution location ordinate parameter , distribution location vertical coordinate parameter , time variable parameter , constraints affect the initial time of integration , constraints affect the integration end time , the city in time Time-varying constraints of the river water level at the time on the outlet flow of the drainage network , the city's distribution location coordinates and in time River water level at time , the linear influence coefficient of river water level on the outlet flow of the drainage network , the quadratic nonlinear influence coefficient of river water level on the outlet flow of the drainage network , exponential function , the city in time Drainage network outlet flow at time , initial flow rate at the outlet of the drainage network , drainage network flow response time attenuation control parameters , the city distribution location coordinates Water flow at , the city distribution location coordinates Maximum allowable water flow at , the city distribution location coordinates The diameter of the drainage network pipes at , Pipeline diameter load-bearing influence weight factor , the city's distribution location coordinates The slope of the drainage network pipes , Pipeline slope load-bearing influence weight factor , the city's distribution location coordinates Flow rate of drainage network at , flow velocity bearing weight factor , correction factor for the bearing capacity coefficient of the drainage network , where the horizontal coordinate parameter of the distribution position , distribution location ordinate parameter , distribution location vertical coordinate parameter , time variable parameter , constraints affect the initial time of integration , constraints affect the integration end time , the city's distribution location coordinates and in time River water level at time , the linear influence coefficient of river water level on the outlet flow of the drainage network , the quadratic nonlinear influence coefficient of river water level on the outlet flow of the drainage network , exponential function , the city in time Drainage network outlet flow at time , initial flow rate at the outlet of the drainage network , drainage network flow response time attenuation control parameters It constitutes a city in time Time-varying constraints of the river water level at the time on the outlet flow of the drainage network Functional relationship , according to the city's distribution location coordinates The carrying capacity coefficient of the drainage network at The correlation between the above parameters forms a functional relationship: ; This formula can realize the evaluation and calculation process of the carrying capacity of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model. At the same time, the correction coefficient of the drainage network carrying capacity coefficient is The introduction of can be adjusted according to the errors that occur in the calculation process, thereby improving the accuracy and applicability of the calculation formula for measuring the carrying capacity of the drainage network.

[0042] Further, the water flow load assessment analysis in step S23 based on the geographical space, drainage network layout and water flow characteristics at the corresponding distribution location includes the following steps: According to the geographical space and drainage network layout at the corresponding distribution location, drainage space layout load constraint analysis is carried out to obtain the drainage space layout load constraint conditions at the corresponding distribution location of the city; In an embodiment of the present invention, by using the geographic spatial data of the urban area, a comprehensive analysis is performed in combination with a detailed drainage network layout. The specific operation includes obtaining the digital elevation model (DEM) data of the area to accurately obtain the topographic information, and using the GIS (geographic information system) tool to accurately spatially locate the drainage network of the city, and obtain the direction, diameter, depth and outlet position of each drainage pipe. In addition, it is necessary to obtain the layout of drainage pipes such as rainwater pipe networks and sewage pipe networks in the city through the basic data of municipal drainage planning. Based on the above data, a fluid mechanics model is used to perform a constraint analysis of the drainage space layout load. The process involves inputting the capacity limit of the drainage network, such as the water flow capacity of the drainage pipe (usually determined by the cross-sectional area, slope, material, etc. of the pipe), and the influence of the topography, such as the risk of water accumulation that low-lying areas may face. By simulating different precipitation intensities and drainage needs, the load conditions of each area under different precipitation conditions are determined, thereby clarifying the load bearing limit of the drainage system in the high-density area in the city, and finally obtaining the drainage space layout load constraint conditions at the corresponding distribution positions in the city.

[0043] Preferably, a water flow dynamic distribution analysis is performed according to the water flow characteristics at the corresponding distribution positions to generate a water flow dynamic distribution flow field at the corresponding distribution positions in the city; In an embodiment of the present invention, by obtaining the precipitation, drainage network layout, topography and other hydrological data of the area, these data will be used as input parameters for the dynamic distribution analysis of water flow. In this process, a numerical simulation method is used to study the dynamic distribution of water flow. Commonly used numerical simulation tools include SWMM (Storm Water Management Model) or HEC-RAS and other water flow simulation software. These software can simulate water flow behaviors under different precipitation scenarios in urban areas. First, it is necessary to define the simulated water flow characteristics, including the intensity and timing changes of precipitation, ground infiltration characteristics, and surface runoff characteristics. By inputting these characteristics into the model, the flow process after the precipitation reaches the ground is simulated and analyzed, and the flow direction, speed and change trend of the water flow are determined, especially the flow pattern in the urban area. These dynamic water flow characteristics will be presented as a water flow field in space, including flow velocity distribution, flow distribution and low-lying areas with water accumulation. During the analysis process, the water flow field will be continuously iterated and updated to reflect the changes in water flow under different precipitation conditions, and finally generate a dynamic distribution flow field of water flow at the corresponding distribution position of the city.

[0044] Preferably, a water flow load assessment and analysis is performed on the water flow dynamic distribution flow field at the corresponding distribution locations in the city based on the drainage space layout load constraints at the corresponding distribution locations in the city to obtain the drainage water flow load at the corresponding distribution locations in the city.

[0045] In an embodiment of the present invention, a load assessment analysis is performed on the flow field of the dynamic distribution of water flow based on previously obtained data and analysis results, combined with the layout load constraints of the drainage network. The specific operation steps include matching the flow field of the dynamic distribution of water flow with the load constraints of the drainage network, simulating the load conditions of the drainage network under different scenarios, and firstly, combining the dynamic change factors such as the flow velocity, flow rate, precipitation intensity of the water flow with the spatial layout constraints of the drainage network, and inputting them into the fluid mechanics simulation system to calculate the flow capacity and drainage load of each drainage pipe. In this process, the load limitations of the pipes in urban areas are focused on. For example, drainage pipes with smaller diameters cannot effectively handle a large amount of runoff after heavy rain, thereby leading to the risk of waterlogging in local areas. The drainage loads of different areas under specific precipitation conditions can be quantified, and finally the drainage water flow loads at the corresponding distribution positions in the city are obtained.

[0046] Further, step S24 includes the following steps: Step S241: Based on the drainage pipe network carrying capacity at the corresponding distribution position in the urban drainage pipe network carrying capacity matrix, the drainage water flow load at the corresponding distribution position of the city is subjected to drainage bearing matching analysis. If the drainage pipe network carrying capacity at the corresponding distribution position is greater than or equal to the drainage water flow load, it is determined as the drainage bearing balance matching point of the corresponding drainage pipe network carrying capacity; if the drainage pipe network carrying capacity at the corresponding distribution position is less than the drainage water flow load, a new bearing matching analysis is performed at a distribution position parallel to the outside until a drainage bearing balance matching point is determined. In the embodiment of the present invention, by combining the previously established urban drainage network carrying capacity matrix, the matrix shows the drainage network carrying capacity of each location in the city. The carrying capacity value of each location is based on factors such as the design standard of the network, historical carrying data and future load forecasts. Then, the city's drainage water flow load is matched with the network carrying capacity one by one. Each drainage water flow load value is calculated based on factors such as rainfall, geographical location, and historical water flow in the drainage pipe. For each distribution location, if the drainage network carrying capacity is greater than or equal to the drainage water flow load at the location, then the location is the drainage load balance matching point, indicating that the The drainage network at the location can bear the water flow load. If the drainage network bearing capacity at the corresponding location is less than the drainage water flow load at that location, the bearing analysis of that location will be automatically moved to an adjacent or parallel distribution location. The new bearing capacity of that location will be matched with the water flow load at that location again. This process will be repeated until a drainage network location that can bear the water flow load is found. This re-bearing matching process involves optimizing and adjusting multiple surrounding network connection points, and automatically adjusting through algorithms to ensure that all areas can match the appropriate drainage capacity, thereby avoiding the phenomenon of excessive drainage pressure in local areas.

[0047] Step S242: connecting equal-value drainage grids according to drainage load balance matching points of different drainage network carrying capacities to generate urban drainage grid boundaries corresponding to different drainage network carrying capacities; In an embodiment of the present invention, drainage grids are connected by drainage load-bearing balance matching points according to different drainage network carrying capacities. The core of this step is to divide areas with different carrying capacities into a number of drainage grids. First, the drainage load-bearing balance matching points previously identified are used as the boundaries of the drainage grids. The urban area is divided into a plurality of grid units by processing using geographic information system (GIS) tools. The carrying capacity of each grid is adjusted according to the network carrying capacity and water flow load within the grid. Based on these load-bearing matching points, the boundaries of different grids are connected to ensure that the drainage network can smoothly transfer and distribute water flow between different areas, thereby forming an urban drainage grid boundary that can reflect the actual drainage network, and finally connecting and generating the urban drainage grid boundaries corresponding to different drainage network carrying capacities.

[0048] Step S243: Based on the urban drainage grid boundaries corresponding to different drainage network carrying capacities, the urban waterlogging digital twin model is divided into drainage grid carrying capacity matching to generate an urban drainage grid model.

[0049] In an embodiment of the present invention, the urban waterlogging digital twin model is divided into drainage grid load matching based on the established drainage grid boundary. First, the digital twin model of the city is imported into the simulation software. The software can simulate the city's drainage network, topography, climate conditions, etc. in real time. According to the previously obtained drainage grid boundary, each area in the digital twin model is matched with the corresponding drainage grid, and the carrying capacity of each drainage grid is accurately mapped to the corresponding area in the digital twin model. In the process of drainage grid division, spatial analysis and optimization algorithms are used to accurately match the city's drainage network with the carrying capacity of each drainage grid to ensure that the drainage capacity of each grid unit is not less than the load demand of the area, especially in densely populated urban areas or areas with large drainage loads. A higher density grid division is adopted to ensure the efficiency and early warning capability of the drainage system. Through these precise grid divisions, the refined management level of the drainage system can be effectively improved, and potential areas with excessive drainage pressure or insufficient drainage can be discovered in time, thereby dividing a drainage grid model with efficient drainage capacity, and finally generating an urban drainage grid model.

[0050] Further, the step S25 of performing waterlogging area prediction analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event law corresponding to the city includes the following steps: A two-dimensional surface model of waterlogging diffusion is constructed based on the historical waterlogging events corresponding to the city, so as to reflect the diffusion of surface waterlogging after overflow in each drainage grid partition in the city and its impact on the distribution of waterlogging in the surrounding areas, and generate a two-dimensional surface law model of urban waterlogging diffusion; In an embodiment of the present invention, by collecting and analyzing historical waterlogging event data, a two-dimensional surface model of waterlogging diffusion based on the laws of historical urban waterlogging events is established. First, urban waterlogging event data within a certain time range (for example, the past five or ten years) is selected, including information such as the time, location, depth and duration of waterlogging. These data will be used as input, and modeling is performed using multi-dimensional urban data such as meteorology, geography, and drainage systems. In specific implementation, numerical simulation methods such as finite element method (FEM) or finite difference method (FDM) can be used to simulate the diffusion process of waterlogging by constructing a two-dimensional grid model of the city. Each grid represents an area in the city, and how the waterlogging expands along the ground to the surrounding areas after overflowing from the source is simulated. The diffusion of surface waterlogging is mainly affected by multiple factors, including terrain slope, soil permeability, degree of urban hardening, etc. All of these factors need to be accurately described and calculated through physical models. The model also needs to consider the influence of precipitation intensity, drainage capacity and drainage facilities, and use a hydrodynamic model to calculate the distribution and diffusion trend of waterlogging in different areas after overflow, and finally generate a two-dimensional surface law model of urban waterlogging diffusion.

[0051] Preferably, the frequency of waterlogging events is measured for each urban drainage grid partition corresponding to the urban drainage grid model based on the two-dimensional surface law model of urban waterlogging diffusion, so as to obtain the frequency of waterlogging events corresponding to each urban drainage grid partition; In an embodiment of the present invention, a previously generated two-dimensional surface law model of urban waterlogging diffusion is used in combination with an urban drainage gridding model to measure the frequency of waterlogging events for each drainage grid partition. The drainage gridding model divides the city into a number of small grid units, each unit representing a drainage area. Generally, considering the functional division and drainage capacity differences of urban areas, the grid division should have a certain degree of precision. In specific operations, the two-dimensional waterlogging diffusion model is used to simulate and analyze the historical waterlogging events of each drainage grid partition, and the frequency of waterlogging in the grid partition within a specific period of time is calculated. The frequency of waterlogging in each grid partition can be obtained by statistically analyzing the spatiotemporal distribution of waterlogging events. In this process, attention should be paid to the duration of waterlogging in different drainage areas, the depth of waterlogging and the degree of its impact on neighboring areas. For example, if a grid has experienced five waterlogging events in the past ten years, the frequency of waterlogging events in the grid is 0.5 times / year. This frequency value can reflect the load of the drainage system in the area and possible drainage risks, and finally the frequency of waterlogging events corresponding to each urban drainage grid partition is obtained.

[0052] Preferably, based on the frequency of waterlogging events corresponding to each urban drainage grid partition, the corresponding urban drainage grid partitions in the urban drainage grid model are connected to the high-incidence waterlogging grid areas to obtain the high-incidence waterlogging grid areas in the city; In an embodiment of the present invention, high-incidence areas of drainage grids are identified and connected according to the frequency of waterlogging events. The specific implementation method is to sort all grids according to the frequency of waterlogging events in each drainage grid, and select grids with higher frequencies as "high-incidence areas of waterlogging". A threshold can be set. When the frequency of waterlogging events in the drainage grid exceeds the threshold, the grid is identified as a high-incidence grid area of ​​waterlogging. In order to further identify high-incidence areas of waterlogging, a spatial clustering algorithm (such as DBSCAN, K-means, etc.) can be used to connect adjacent high-frequency waterlogging grids to form a connected area. For example, the distribution of grids with a high frequency of waterlogging events shows a certain spatial coherence. The clustering algorithm can merge these high-frequency grids into a whole, called a "high-incidence grid area of ​​waterlogging". This area reflects the area in the city where the waterlogging problem is more serious, and finally the high-incidence grid area of ​​the city is obtained.

[0053] Preferably, the terrain slope distribution and ground water infiltration efficiency between corresponding drainage grid partitions in the urban drainage grid model are obtained according to the high-incidence waterlogging grid areas in the city; In an embodiment of the present invention, by analyzing the terrain slope and ground water infiltration efficiency of the grid areas with high incidence of waterlogging in the city, the specific operation is to first extract the terrain data of the urban area from the digital elevation model (DEM), and calculate the terrain slope distribution of each drainage grid partition. The area with a larger slope value causes the water flow to accelerate, affecting the drainage effect, while the area with a smaller slope is prone to waterlogging. Then, by using soil permeability data or ground cover data (for example: the coverage of grass, roads, buildings, etc.), combined with the permeability coefficient of soil and buildings, the ground water infiltration efficiency of each drainage grid partition is calculated. The water in the area with high water infiltration efficiency is easier to penetrate into the ground, while the area with low water infiltration efficiency is prone to waterlogging. This process usually uses GIS technology, remote sensing data and soil data to analyze the characteristics of the urban ground, and performs spatial distribution calculations in the drainage grid, and finally obtains the terrain slope distribution and ground water infiltration efficiency between the drainage grid partitions.

[0054] Preferably, based on the terrain slope distribution and ground water infiltration efficiency between the corresponding drainage grid divisions, a waterlogging area prediction analysis is performed on the urban high-incidence waterlogging grid areas to obtain the urban waterlogging prediction area.

[0055] In an embodiment of the present invention, the data obtained by the previous analysis are integrated to perform a prediction analysis on the waterlogging area. First, according to the distribution of the grid areas with high incidence of waterlogging, combined with the terrain slope and ground water infiltration efficiency information of each grid, the physical model and the statistical model are used to predict the waterlogging risk. For example, a hydrological model (such as a SWMM model or a HEC-HMS model) is used to simulate the flow direction and waterlogging under different slopes and water infiltration efficiency conditions under heavy rain conditions. The model input includes the slope of the drainage grid partition, the water infiltration rate and the frequency data of historical waterlogging events, and the output is the waterlogging depth and water flow path of each drainage grid under a specific precipitation. Furthermore, the waterlogging areas that can be identified by the simulation results are usually associated with low-lying areas with small slopes and low water infiltration rates. In order to improve the prediction accuracy, machine learning algorithms such as random forests, support vector machines (SVM), etc. can be combined to train historical data to predict possible waterlogging areas in the future. In addition, the changing trend of the waterlogging area can be determined through multiple scenario simulations and risk assessments, and finally the urban waterlogging prediction area is obtained.

[0056] Further, step S3 includes the following steps: Step S31: The current measured water depth, river water level, rainfall process in the past period, and drainage network status corresponding to the urban waterlogging prediction area are obtained through the urban waterlogging digital twin model as real-time monitoring data corresponding to the urban waterlogging prediction area, and the real-time monitoring data corresponding to the simulation start time is used as the initial condition data of the waterlogging prediction area; In an embodiment of the present invention, data is collected for the urban waterlogging prediction area through the urban waterlogging digital twin model. This step includes four main parts: the waterlogging depth at the current moment, the river water level, the rainfall process, and the drainage network status. For the waterlogging depth, the waterlogging situation in the area is obtained with the help of ground measurement sites and remote sensing technology (such as lidar, satellite images or drone scanning), and the depth is estimated in combination with the known drainage outlet flow data. For the river water level, real-time water level data is collected by water level monitoring sensors installed in the river and drainage system. These data are synchronously updated with the digital twin system through the Internet of Things technology. In terms of the rainfall process in the past period of time, the historical precipitation data provided by the meteorological station is combined with the real-time precipitation data of the ground meteorological sensor to help estimate the precipitation situation at the current moment. The drainage network status is obtained through the sensor data of the urban drainage network system, the intelligent flow monitoring system and the data transmitted back by the online sensor to understand the current flow and blockage status of the drainage network. All the above real-time monitoring data will be used as input to determine the initial conditions of the urban waterlogging prediction area, and finally obtain the initial condition data of the waterlogging prediction area.

[0057] Step S32: Obtain the rainfall amount and rainfall duration in the urban waterlogging prediction area corresponding to the future forecast time through the urban waterlogging digital twin model to determine the rainfall time series, and obtain the rainfall time series in the urban waterlogging prediction area corresponding to the future forecast time; In an embodiment of the present invention, the rainfall forecast for future periods is processed through the urban waterlogging digital twin model. Specifically, the future rainfall, rainfall duration and other information are obtained through a meteorological forecast model (such as a high-resolution weather forecast model or a regional climate model). These data are usually obtained through meteorological satellites or meteorological radars, and combined with the precipitation forecast generated by the meteorological forecast system to determine the rainfall time series. For the determination of rainfall duration, the future rainfall time series is calculated based on the analysis of rainfall events by historical meteorological data and forecast models, combined with the climate characteristics of specific regions, such as common rainfall patterns (short-term heavy rainfall or long-term weak rainfall) and other factors. These rainfall time series data will be converted into precipitation predictions of time steps and used as input data for subsequent steps, and finally the rainfall time series corresponding to the future forecast time in the urban waterlogging prediction area is obtained.

[0058] Step S33: obtaining the terrain, drainage capacity and climate conditions corresponding to the urban waterlogging prediction area through the urban waterlogging digital twin model, wherein the climate conditions include rainfall, evaporation and river soil permeability, and estimating the river water level change of the corresponding urban waterlogging prediction area at the future forecast time according to the terrain, drainage capacity and climate conditions corresponding to the urban waterlogging prediction area, so as to obtain the river water level change data corresponding to the urban waterlogging prediction area at the future forecast time; In an embodiment of the present invention, a detailed analysis is performed on the geographical environment and climatic conditions that affect urban waterlogging. In this process, it is first necessary to obtain the terrain data of the urban waterlogging prediction area, obtain the elevation data of the area through remote sensing technology (such as drones, aerial photography, lidar, etc.), and digitally process it in combination with the topographic map to construct an accurate digital elevation model (DEM). Secondly, the drainage capacity is evaluated by the data of the municipal drainage system, focusing on analyzing the carrying capacity, flow and blockage of the drainage network. The drainage efficiency is evaluated based on the existing urban drainage network model and online monitoring data. For climatic conditions, the historical meteorological data of the area is first obtained, including rainfall, evaporation, temperature, humidity, etc., and the future climate conditions are predicted by using meteorological station data and historical records combined with climate change models. The soil permeability is analyzed in detail, and accurate evaluation can be performed through soil permeability testing, groundwater monitoring and geological exploration data. All these data will be passed into the digital twin model as input to estimate the river water level changes at future forecast times, and finally the river water level change data corresponding to the future forecast time in the urban waterlogging prediction area is obtained.

[0059] Step S34: Based on the initial condition data of the waterlogging prediction area, the rainfall time series and the river water level change data of the urban waterlogging prediction area corresponding to the future forecast time are used as input data to run the urban waterlogging digital twin model in step S2 to generate a future forecast simulation process corresponding to the urban waterlogging model; In an embodiment of the present invention, the monitoring data, rainfall time series and river water level change data in steps S31 and S32 are taken as input to execute the urban waterlogging digital twin model for simulation and prediction. The model is based on a combination of a basin hydrological model, a terrain model, a drainage capacity model and a meteorological forecast model, and takes into account multiple factors such as terrain, climate, precipitation, etc. to dynamically simulate the waterlogged area. During the simulation process, the digital twin model will predict the changes in waterlogging after future rainfall events through numerical calculation and time series analysis. Specifically, the model numerically simulates the evolution process of urban waterlogging based on the input rainfall time series and real-time river water level change data, calculates the diffusion of waterlogging, waterlogging depth, and changes in drainage capacity, and combines the simulated water level changes to obtain a waterlogging distribution map at the future forecast time. The output data in the simulation process is the simulation result of urban waterlogging at the future forecast time, and finally generates a future forecast simulation process corresponding to the urban waterlogging model.

[0060] Step S35: using the real-time monitoring data corresponding to the urban waterlogging prediction area to perform real-time correction and waterlogging rolling forecast on the urban waterlogging digital twin model in the future forecast simulation process corresponding to the urban waterlogging model, so as to generate an urban waterlogging waterlogging rolling forecast digital model; In an embodiment of the present invention, real-time correction of the urban waterlogging digital twin model is performed by using real-time monitoring data. As the actual rainfall process progresses, real-time monitoring data (such as precipitation, water level changes, etc.) will be continuously provided to the digital twin system. At this time, the model will compare the new real-time data with the previous simulation data, detect differences and automatically adjust the model parameters to ensure the accuracy and timeliness of the model. This process is achieved through data assimilation technology, that is, the observed data is input into the model in a timely manner, and the model state is corrected through optimization algorithms (such as Kalman filtering or particle filtering). Based on the correction of these real-time data, the model will generate a rolling forecast, that is, through continuously updated data input, the urban waterlogging situation in the future period of time is continuously calculated to provide more accurate real-time warning information. This real-time correction process will ensure that the waterlogging model is always calculated based on the latest monitoring data, improve the accuracy of the forecast, and then realize dynamic warning of the waterlogged area, and finally generate a digital model of urban waterlogging rolling forecast.

[0061] Step S36: obtaining the water level and drainage network status corresponding to the urban waterlogging prediction area through the urban waterlogging waterlogging rolling forecast digital model, and performing rainfall-water level spatiotemporal correlation analysis on the rainfall time series corresponding to the future forecast time in the urban waterlogging prediction area based on the water level corresponding to the urban waterlogging prediction area, so as to generate a rainfall-water level spatiotemporal correlation distribution field corresponding to the urban waterlogging prediction area; In an embodiment of the present invention, the current status of the water level and the drainage network is obtained based on the generated digital model for rolling forecast of urban waterlogging. The digital model determines the water level in various areas of the city and evaluates the operating status of the drainage network by integrating data such as real-time water depth, pressure and flow of the drainage network. Afterwards, a rainfall-water level spatiotemporal correlation analysis is performed based on the water level in the urban waterlogging prediction area and the rainfall time series of the area at the future forecast time. This analysis adopts time series data analysis technology and establishes a spatiotemporal correlation model between rainfall and water level based on the correlation data of historical rainfall and water level through regression analysis or machine learning algorithms (such as random forests, support vector machines, etc.). Through these models, the water level of different areas at a specific time in the future can be predicted, and then the impact of future rainfall can be predicted. This analysis not only considers the intensity of rainfall, but also the spatial distribution characteristics of rainfall and the response of the drainage network, further improves the accuracy of water level prediction, and finally generates a rainfall-water level spatiotemporal correlation distribution field corresponding to the urban waterlogging prediction area.

[0062] Step S37: Based on the drainage pipe network status corresponding to the urban waterlogging prediction area, drainage efficiency attenuation analysis is performed on the urban waterlogging prediction area corresponding to the urban waterlogging prediction digital model, and a drainage pipe network efficiency attenuation distribution field corresponding to the urban waterlogging prediction area is generated; In an embodiment of the present invention, firstly, based on the actual operation of the drainage network in the urban waterlogging prediction area, including data such as pipe diameter, flow velocity, slope, blockage and overload degree, a mathematical model of the drainage system is established, and then these data are used to evaluate the drainage efficiency of the drainage network under different rainfall intensities, focusing on analyzing the extent of the decrease in the drainage capacity of the network under extreme weather conditions, that is, the attenuation of drainage efficiency. The attenuation analysis can simulate the flow change of the drainage network under a specific rainfall by establishing a hydraulic model, and use methods such as hydraulic hydrological models (such as SWMM models) to predict the working status of the drainage network at different locations in the waterlogging area, and then analyze the efficiency attenuation distribution of the drainage network. The purpose of this step is to evaluate the drainage capacity of drainage networks of different regions and types under extreme rainfall conditions, generate a drainage efficiency attenuation distribution field, and finally generate a drainage network efficiency attenuation distribution field corresponding to the urban waterlogging prediction area.

[0063] Step S38: Based on the rainfall-water level spatiotemporal correlation distribution field corresponding to the urban waterlogging prediction area and the drainage network efficiency attenuation distribution field, a waterlogging evolution coupling analysis is performed on the urban waterlogging prediction area corresponding to the urban waterlogging rolling forecast digital model to generate an urban waterlogging evolution distribution field.

[0064] In an embodiment of the present invention, the evolution process of waterlogging is predicted by combining the rainfall-water level spatiotemporal correlation distribution field and the drainage network efficiency attenuation distribution field, and then the waterlogging distribution of each area in the future is deduced. In this step, the rainfall-water level spatiotemporal correlation distribution field obtained in the previous stage is first used to clarify the influence of different rainfall intensities on the water levels of various areas in the city, and the attenuation effect of the drainage network on the evolution of waterlogging under future rainfall conditions is evaluated by combining the drainage network efficiency attenuation distribution field. The coupled analysis of waterlogging evolution uses a multidimensional hydraulic model or a multi-field coupled simulation model to comprehensively consider factors such as rainfall, water level changes, and drainage network efficiency. The dynamic simulation method is used to predict the changing trend of waterlogging in various regions in the future. This analysis relies on the continuous input of real-time monitoring data. The model dynamically updates the waterlogging evolution results based on the latest rainfall forecast and the efficiency status of the drainage network. Through coupling analysis, it can generate the distribution field of waterlogging evolution in the next few hours to days, identify potential waterlogging risk areas, and present the analysis results in the form of spatial distribution maps to help decision makers understand the evolution trend of urban waterlogging. Through rolling forecasts, it can not only provide accurate warnings for the current waterlogging evolution, but also provide support for future rainfall and waterlogging risk assessments, and ultimately generate an urban waterlogging evolution distribution field.

[0065] Further, step S37 includes the following steps: Step S371: obtaining the drainage network pressure and drainage treatment efficiency at the corresponding distribution location through the drainage network status corresponding to the urban waterlogging prediction area; In an embodiment of the present invention, a digital model of a city's drainage network is constructed by using digital twin technology. The model should have the spatial layout and physical parameters of drainage pipes, pump stations, inspection wells and other facilities in the entire network. Then, based on remote sensing data and geographic information system (GIS) technology, real-time rainfall data and waterlogging area information of the urban waterlogging prediction area are obtained. On this basis, a hydrological and hydraulic model is used for real-time simulation to calculate the pressure distribution of the drainage network. This simulation model takes into account factors such as different rainfall intensities, terrains, and the diameter, slope, and flow rate of drainage pipes, and combines the influence of obstacles such as urban roads and buildings on water flow to obtain the drainage pressure and drainage capacity of each pipe network distribution location. At the same time, combined with the design standards, operating status and past drainage records of the drainage pipes, the processing efficiency of each drainage point is calculated through data analysis tools (such as Python, MATLAB, etc.). Specifically, a linear regression or machine learning model can be used to combine historical rainfall and actual drainage to obtain the processing efficiency of the drainage system under different conditions, and finally the drainage network pressure and drainage processing efficiency at the corresponding distribution location are obtained.

[0066] Step S372: performing drainage network performance evaluation and analysis on the drainage network pressure and drainage treatment efficiency at the corresponding distribution positions in the urban waterlogging prediction area, and obtaining the drainage network drainage efficiency at the corresponding distribution positions in the urban waterlogging prediction area; In an embodiment of the present invention, a comprehensive analysis is performed on the network pressure and drainage efficiency data of each drainage distribution location point previously obtained, and the performance of each drainage node is evaluated using an urban hydraulic model. The specific method is to quantitatively analyze the drainage capacity of the drainage network through the relationship between pressure and flow, using fluid mechanics equations (such as the Bernoulli equation) and the control volume method. The key to the performance evaluation of the drainage network is to perform a dynamic analysis of pressure-flow-time on each node, and evaluate the flow velocity, flow rate and drainage capacity of the pipeline in combination with the actual drainage task volume. In order to more accurately evaluate the drainage performance, it is also necessary to introduce different types of drainage pipe materials, pipe age and other factors, and use operation and maintenance data and historical monitoring data for comparison and verification. Numerical simulation tools (such as OpenFOAM, SWMM, etc.) can be used to simulate drainage performance under different conditions, evaluate the drainage performance of the drainage network in each area under existing conditions, and finally obtain the drainage performance of the drainage network at the corresponding distribution position in the urban waterlogging prediction area.

[0067] Step S373: obtaining the sediment accumulation amount and the drainage pipe damage rate at the corresponding distribution position of the urban waterlogging prediction area, and performing drainage efficiency attenuation analysis on the drainage efficiency of the drainage pipe network at the corresponding distribution position of the urban waterlogging prediction area based on the sediment accumulation amount and the drainage pipe damage rate, to obtain the drainage efficiency attenuation degree at the corresponding distribution position of the urban waterlogging prediction area; In the embodiment of the present invention, the sediment accumulation of the drainage network in the urban waterlogging prediction area is obtained by combining remote sensing monitoring and manual inspection, and the sediment thickness and accumulation amount of the pipeline are obtained through sensors in the pipeline, inspection well monitoring and regular inspection reports. Then, combined with historical data such as flow rate and pressure, hydraulic simulation is used to model the impact of sediment on flow in the drainage network, and the degree of impact on the drainage efficiency of the pipeline network is calculated. Next, combined with the damage rate data of the drainage pipeline, the impact of pipeline damage on drainage capacity is evaluated. The damage rate can be obtained by relying on on-site detection (such as acoustic wave detection, endoscope detection, etc.) and historical data. Maintenance records are collected, and the attenuation effect of damage on drainage capacity is obtained by comparing and analyzing the local repair of damaged pipes with the drainage efficiency of the entire pipe network. The corrosion-damage model is combined with the fluid mechanics model to evaluate the specific attenuation degree of drainage efficiency caused by pipe damage and sediment accumulation. On this basis, numerical simulation technology is used to consider the drainage efficiency attenuation under different damage rates and sediment accumulation conditions, and the drainage efficiency attenuation value of each area is obtained. These attenuation values ​​reflect the actual efficiency loss degree of the drainage network in different regions and under different conditions, and finally the drainage efficiency attenuation degree at the corresponding distribution position in the urban waterlogging prediction area is obtained.

[0068] Step S374: performing an efficiency attenuation distribution analysis on the urban waterlogging prediction area based on the drainage efficiency attenuation degree at the corresponding distribution positions in the urban waterlogging prediction area, and generating a drainage network efficiency attenuation distribution field corresponding to the urban waterlogging prediction area.

[0069] In an embodiment of the present invention, the drainage efficiency attenuation data previously obtained at each distribution position is spatially processed, and the attenuation degree is mapped to the city map using geographic information system (GIS) technology. Combined with the spatial distribution of high-density urban waterlogging prediction areas, a spatial distribution field of drainage network efficiency attenuation is generated. This distribution field will show which areas are greatly affected by the drainage network efficiency attenuation, as well as high-risk areas for waterlogging. When performing efficiency attenuation distribution analysis, heat maps or contour maps can be used to intuitively present the distribution of attenuation, helping city managers identify areas with weak drainage systems and provide data support for the next step of waterlogging warning and network optimization. At the same time, weather forecasts and precipitation models can be combined to simulate future precipitation events, predict which areas of the drainage network will experience more serious efficiency attenuation under future precipitation conditions, and ultimately generate a drainage network efficiency attenuation distribution field corresponding to the urban waterlogging prediction area.

[0070] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A high-density urban waterlogging evolution and early warning method based on digital twins, characterized in that: The following steps are involved: Step S1: The real-time waterlogging depth, real-time river water level, real-time meteorological conditions and real-time drainage network water level of the city are collected in real time by installing waterlogging depth sensors, river water level sensors, meteorological monitoring equipment and drainage network sensors in the city, and a digital twin is constructed based on the real-time waterlogging depth, real-time meteorological conditions and real-time drainage network water level of the city in combination with the land use type, terrain and geomorphology data and building road information model of the city, so as to generate a digital twin model of urban waterlogging; Step S2: Obtain the drainage network distribution corresponding to the city, and divide the urban waterlogging digital twin model into drainage grids based on the drainage network distribution corresponding to the city and the real-time river water level to generate an urban drainage grid model; obtain the historical waterlogging event pattern corresponding to the city, and perform waterlogging area prediction and analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event pattern corresponding to the city to obtain the urban waterlogging prediction area; Step S3: The current measured waterlogging depth, river water level, rainfall process in the past period, and drainage network status corresponding to the urban waterlogging prediction area are obtained through the urban waterlogging digital twin model as real-time monitoring data corresponding to the urban waterlogging prediction area, and waterlogging evolution coupling analysis is performed on the urban waterlogging prediction area based on the real-time monitoring data corresponding to the urban waterlogging prediction area to generate an urban waterlogging evolution distribution field; Step S4: Performing spatiotemporal evolution analysis on the urban waterlogging evolution distribution field to obtain the urban waterlogging evolution development trend at different spatiotemporal nodes in the city; Based on the evolution and development trend of urban waterlogging at different time and space nodes in the city, the corresponding urban waterlogging evolution distribution field is processed for waterlogging warning, and an urban waterlogging warning distribution field is generated to perform corresponding urban waterlogging emergency response work.

2. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: performing real-time monitoring of urban waterlogging by installing waterlogging depth sensors at various location nodes in the city to obtain the corresponding real-time waterlogging depth of the city; Step S12: monitoring the river water level in the city in real time by installing river water level sensors at various river locations in the city to obtain the real-time river water level corresponding to the city, including the water level height and the corresponding time; Step S13: Performing real-time weather monitoring of the city through weather monitoring equipment installed at various location nodes in the city to obtain real-time weather conditions corresponding to the city, including rainfall and rainfall duration; Step S14: The drainage network of the city is monitored in real time by means of the drainage network liquid level and flow rate sensors installed at various location nodes of the city, so as to obtain the real-time drainage network water level status corresponding to the city, including the liquid level and drainage flow rate corresponding to the drainage network nodes; Step S15: Obtain the land use type, terrain and geomorphology data, and building road information model corresponding to the city, and construct a digital twin based on the real-time waterlogging depth, real-time meteorological conditions, and real-time drainage network water level conditions corresponding to the city in combination with the land use type, terrain and geomorphology data, and building road information model corresponding to the city to generate a digital twin model of urban waterlogging.

3. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Obtain the topography, building density and drainage facility layout of the city, and obtain the drainage network distribution of the city according to the topography, building density and drainage facility layout of the city; Step S22: Based on the drainage network distribution corresponding to the city and the real-time river water level, the drainage carrying capacity of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model is evaluated to obtain the urban drainage network carrying capacity matrix; Step S23: obtaining the geographic space, drainage network layout and water flow characteristics at the corresponding distribution location through the urban waterlogging digital twin model, and performing water flow load assessment and analysis based on the geographic space, drainage network layout and water flow characteristics at the corresponding distribution location to obtain the drainage water flow load at the corresponding distribution location of the city; Step S24: performing drainage grid load matching and division on the urban waterlogging digital twin model based on the drainage network load capacity at the corresponding distribution position in the urban drainage network load capacity matrix and the drainage flow load at the corresponding distribution position in the city, so as to generate an urban drainage grid model; Step S25: Obtain the historical waterlogging event patterns corresponding to the city, and perform waterlogging area prediction analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event patterns corresponding to the city, so as to obtain the urban waterlogging prediction area.

4. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 3 is characterized in that: Step S22 includes the following steps: Obtain the drainage network pipe diameter and drainage network pipe slope at the corresponding distribution location through the drainage network distribution of the city; Conduct a statistical analysis of the drainage flow rate of the drainage network at the corresponding distribution locations in the urban waterlogging digital twin model to obtain the drainage network flow rate at the corresponding distribution locations in the city; The real-time river water level corresponding to the city is used to obtain the time-series fluctuation of the river water level at the corresponding distribution position in the urban waterlogging digital twin model, and based on the time-series fluctuation of the river water level at the corresponding distribution position in the city, the outlet flow constraint analysis of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model is performed to obtain the time-varying constraint of the corresponding river water level in the city on the outlet flow of the drainage network; Based on the time-varying constraints of the drainage network pipe diameter, drainage network pipe slope, drainage network flow rate and the corresponding river water level in the city on the drainage network outlet flow, the drainage network carrying capacity measurement calculation formula is used to evaluate and calculate the carrying capacity of the drainage network at the corresponding distribution position in the urban waterlogging digital twin model, so as to obtain the drainage network carrying capacity coefficient at the corresponding distribution position in the city; According to the carrying capacity coefficient of the drainage network at the corresponding distribution location in the city, the drainage capacity matrix of the drainage network at the corresponding distribution location in the urban waterlogging digital twin model is constructed to obtain the carrying capacity matrix of the urban drainage network.

5. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 4 is characterized in that: The specific calculation formula for the drainage network carrying capacity measurement is: ； ； In the formula, The coordinates of the city's distribution location The carrying capacity coefficient of the drainage network at It is the three-dimensional space area covered by the drainage network. is the horizontal coordinate parameter of the distribution position, is the ordinate parameter of the distribution location, is the vertical coordinate parameter of the distribution location, is the time variable parameter, To constrain the initial time of the integration, To constrain the impact of the integral end time, For the city in time The time-varying constraint of the river water level on the outlet flow of the drainage network at the time. The coordinates of the city's distribution location and in time The river water level at the time, is the linear influence coefficient of the river water level on the outlet flow of the drainage network, is the quadratic nonlinear influence coefficient of the river water level on the outlet flow of the drainage network, is an exponential function, For the city in time The drainage network outlet flow at time, is the initial flow rate at the outlet of the drainage network, is the drainage network flow response time attenuation control parameter, The coordinates of the city's distribution location The water flow rate at The coordinates of the city's distribution location The maximum permissible water flow rate at The coordinates of the city's distribution location The diameter of the drainage network pipe at is the weight factor affecting the pipe diameter load, The coordinates of the city's distribution location The slope of the drainage network pipes at is the weight factor affecting the pipeline slope load, The coordinates of the city's distribution location The flow rate of the drainage network at is the flow velocity bearing weight factor, It is the correction factor of the drainage network bearing capacity coefficient.

6. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 3 is characterized in that: The water flow load assessment analysis in step S23 according to the geographical space, drainage network layout and water flow characteristics at the corresponding distribution location includes the following steps: According to the geographical space and drainage network layout at the corresponding distribution location, drainage space layout load constraint analysis is carried out to obtain the drainage space layout load constraint conditions at the corresponding distribution location of the city; According to the water flow characteristics at the corresponding distribution positions, the water flow dynamic distribution analysis is performed to generate the water flow dynamic distribution flow field at the corresponding distribution positions in the city; Based on the drainage space layout load constraints at the corresponding distribution locations in the city, the water flow load evaluation and analysis is carried out on the dynamic distribution flow field of the water flow at the corresponding distribution locations in the city to obtain the drainage water flow load at the corresponding distribution locations in the city.

7. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: Based on the drainage pipe network carrying capacity at the corresponding distribution position in the urban drainage pipe network carrying capacity matrix, the drainage water flow load at the corresponding distribution position of the city is subjected to drainage bearing matching analysis. If the drainage pipe network carrying capacity at the corresponding distribution position is greater than or equal to the drainage water flow load, it is determined as the drainage bearing balance matching point of the corresponding drainage pipe network carrying capacity; if the drainage pipe network carrying capacity at the corresponding distribution position is less than the drainage water flow load, a new bearing matching analysis is performed at a distribution position parallel to the outside until a drainage bearing balance matching point is determined. Step S242: connecting equal-value drainage grids according to drainage load balance matching points of different drainage network carrying capacities to generate urban drainage grid boundaries corresponding to different drainage network carrying capacities; Step S243: Based on the urban drainage grid boundaries corresponding to different drainage network carrying capacities, the urban waterlogging digital twin model is divided into drainage grid carrying capacity matching to generate an urban drainage grid model.

8. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 3 is characterized in that: The step S25 of performing waterlogging area prediction analysis on each urban drainage grid partition in the urban drainage grid model based on the historical waterlogging event law corresponding to the city includes the following steps: A two-dimensional surface model of waterlogging diffusion is constructed based on the historical waterlogging events corresponding to the city, so as to reflect the diffusion of surface waterlogging after overflow in each drainage grid partition in the city and its impact on the distribution of waterlogging in the surrounding areas, and generate a two-dimensional surface law model of urban waterlogging diffusion; Based on the two-dimensional surface law model of urban waterlogging diffusion, the frequency of waterlogging events is measured for each urban drainage grid partition in the urban drainage grid model to obtain the frequency of waterlogging events corresponding to each urban drainage grid partition; Based on the frequency of waterlogging events corresponding to each urban drainage grid partition, the corresponding urban drainage grid partitions in the urban drainage grid model are connected to the high-incidence waterlogging grid areas to obtain the high-incidence waterlogging grid areas in the city; According to the high-incidence waterlogging grid areas in the city, the terrain slope distribution and ground water infiltration efficiency between the corresponding drainage grid partitions in the urban drainage grid model are obtained; Based on the terrain slope distribution and ground infiltration efficiency between the corresponding drainage grid divisions, a waterlogging area prediction analysis is conducted on the high-incidence waterlogging grid areas in the city to obtain the urban waterlogging prediction area.

9. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: The current measured water depth, river water level, rainfall process in the past period, and drainage network status corresponding to the urban waterlogging prediction area are obtained through the urban waterlogging digital twin model as real-time monitoring data corresponding to the urban waterlogging prediction area, and the real-time monitoring data corresponding to the simulation start time is used as the initial condition data of the waterlogging prediction area; Step S32: Obtain the rainfall amount and rainfall duration in the urban waterlogging prediction area corresponding to the future forecast time through the urban waterlogging digital twin model to determine the rainfall time series, and obtain the rainfall time series in the urban waterlogging prediction area corresponding to the future forecast time; Step S33: obtaining the terrain, drainage capacity and climate conditions corresponding to the urban waterlogging prediction area through the urban waterlogging digital twin model, wherein the climate conditions include rainfall, evaporation and river soil permeability, and estimating the river water level change of the corresponding urban waterlogging prediction area at the future forecast time according to the terrain, drainage capacity and climate conditions corresponding to the urban waterlogging prediction area, so as to obtain the river water level change data corresponding to the urban waterlogging prediction area at the future forecast time; Step S34: Based on the initial condition data of the waterlogging prediction area, the rainfall time series and the river water level change data of the urban waterlogging prediction area corresponding to the future forecast time are used as input data to run the urban waterlogging digital twin model in step S2 to generate a future forecast simulation process corresponding to the urban waterlogging model; Step S35: using the real-time monitoring data corresponding to the urban waterlogging prediction area to perform real-time correction and waterlogging rolling forecast on the urban waterlogging digital twin model in the future forecast simulation process corresponding to the urban waterlogging model, so as to generate an urban waterlogging waterlogging rolling forecast digital model; Step S36: obtaining the water level and drainage network status corresponding to the urban waterlogging prediction area through the urban waterlogging waterlogging rolling forecast digital model, and performing rainfall-water level spatiotemporal correlation analysis on the rainfall time series corresponding to the future forecast time in the urban waterlogging prediction area based on the water level corresponding to the urban waterlogging prediction area, so as to generate a rainfall-water level spatiotemporal correlation distribution field corresponding to the urban waterlogging prediction area; Step S37: Based on the drainage pipe network status corresponding to the urban waterlogging prediction area, drainage efficiency attenuation analysis is performed on the urban waterlogging prediction area corresponding to the urban waterlogging prediction digital model, and a drainage pipe network efficiency attenuation distribution field corresponding to the urban waterlogging prediction area is generated; Step S38: Based on the rainfall-water level spatiotemporal correlation distribution field corresponding to the urban waterlogging prediction area and the drainage network efficiency attenuation distribution field, a waterlogging evolution coupling analysis is performed on the urban waterlogging prediction area corresponding to the urban waterlogging rolling forecast digital model to generate an urban waterlogging evolution distribution field.

10. The high-density urban waterlogging evolution and early warning method based on digital twin according to claim 9 is characterized in that: Step S37 includes the following steps: Step S371: obtaining the drainage network pressure and drainage treatment efficiency at the corresponding distribution location according to the drainage network status corresponding to the urban waterlogging prediction area; Step S372: performing drainage network performance evaluation and analysis on the drainage network pressure and drainage treatment efficiency at the corresponding distribution positions in the urban waterlogging prediction area, and obtaining the drainage network drainage efficiency at the corresponding distribution positions in the urban waterlogging prediction area; Step S373: obtaining the sediment accumulation amount and the drainage pipe damage rate at the corresponding distribution position of the urban waterlogging prediction area, and performing drainage efficiency attenuation analysis on the drainage efficiency of the drainage pipe network at the corresponding distribution position of the urban waterlogging prediction area based on the sediment accumulation amount and the drainage pipe damage rate, to obtain the drainage efficiency attenuation degree at the corresponding distribution position of the urban waterlogging prediction area; Step S374: performing an efficiency attenuation distribution analysis on the urban waterlogging prediction area based on the drainage efficiency attenuation degree at the corresponding distribution positions in the urban waterlogging prediction area, and generating a drainage network efficiency attenuation distribution field corresponding to the urban waterlogging prediction area.

Images