Urban life body complete cycle monitoring system based on digital twinborn technology

Abstract

The invention discloses an urban life body full-cycle monitoring system based on a digital twinborn technology, relates to the technical field of urban governance, integrates multi-source data such as GIS data, remote sensing information, surface permeability data and an underground drainage pipe network structure, quantifies a flood high-risk area, and provides an urban life body full-cycle monitoring system based on the digital twinborn technology. The AI flood prediction module deduces the ponding range and the drainage capacity under different rainfall situations by adopting extreme weather analogue simulation based on a historical rainfall trend, a current meteorological condition and a drainage network state, and dynamically adjusts a flood diffusion trend prediction model, so that the flood risk identification is more accurate; the intelligent emergency scheduling module automatically matches flood control resources, combines flood high-risk areas, ponding point locations and traffic flow analysis, optimizes a drainage pump station start-stop strategy, remotely regulates and controls an underground drainage gate, dynamically adjusts the overflow adjustment capability of a sewage treatment plant, and optimizes an emergency risk avoiding route in combination with an intelligent traffic management system. And the accuracy and the execution efficiency of the flood control scheduling scheme are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban governance, and in particular to a full-cycle monitoring system for urban life forms based on digital twin technology. Background Art

[0002] Modern urban governance relies on a full-cycle monitoring system to identify risks and optimize resource allocation, so as to improve the emergency response ability.

[0003] However, most current monitoring methods rely on fixed stations and distributed sensors, which can provide relatively stable data support in normal management. However, in the face of emergencies and rapidly changing environmental factors, it is difficult to achieve accurate prediction and rapid response; although the monitoring network covers some key areas, limited by deployment conditions, it is difficult to comprehensively grasp the overall operation situation, resulting in single-point monitoring as the main data acquisition method, and it is impossible to accurately predict potential threats; in addition, various monitoring data are scattered in different systems, forming information islands, lacking unified standards, resulting in difficulties in data integration and sharing, and reducing the overall monitoring efficiency.

[0004] In the context of urban flood disasters, traditional drainage systems mainly rely on static rainwater pipe network models, which cannot effectively combine meteorological changes, surface permeability and drainage capacity for dynamic simulation, and it is difficult to predict the waterlogging range and pipe network bearing capacity under extreme precipitation; at the same time, flood emergency dispatch still relies on manual experience and lacks intelligent data support, resulting in a lag in flood control resource allocation.

[0005] To address these problems, some traditional monitoring systems enhance the environmental perception ability by increasing the density of monitoring points, introducing meteorological forecast and remote sensing monitoring data, and at the same time integrate cross-departmental data through an information platform to achieve a certain degree of resource optimization; however, most of these measures belong to local optimization and still cannot break through the bottlenecks of lagging monitoring data, insufficient prediction accuracy and slow response to decision-making; therefore, there is an urgent need for a full-cycle monitoring system for urban life forms based on digital twin technology to improve the flood disaster prediction ability, optimize the emergency response strategy, and achieve more efficient and accurate urban flood control management. Summary of the Invention

[0006] In view of the above existing problems, the present invention is proposed.

[0007] The present invention provides a full-cycle monitoring system for urban life forms based on digital twin technology to solve

[0008] the problems of scattered data, lagging prediction, and manual dependence in emergency response in the traditional monitoring system, and it is difficult to accurately give early warnings and optimize flood control resource scheduling.

[0009] To solve the above technical problems, the present invention provides the following technical solutions:

[0010] An embodiment of the present invention provides a full-cycle monitoring system for urban life forms based on digital twin technology, which includes:

[0011] A digital twin modeling module, which is used to construct a digital twin of urban drainage based on geographic information system (GIS), remote sensing data, surface permeability information, historical rainfall data, and urban drainage network, and generate a flood risk assessment model;

[0012] A real-time monitoring module, which is used to collect rainfall data, underground drainage network flow, surface water accumulation depth, and surface permeability data based on Internet of Things sensors, and perform data preprocessing through edge computing technology to form a dynamic hydrological monitoring network;

[0013] An AI flood prediction module, which is used to run extreme weather simulation based on historical rainfall data, current meteorological conditions, and the operation status of the drainage system, deduce the water accumulation range and drainage capacity under different precipitation intensities, and predict the evolution trend of urban floods;

[0014] An intelligent emergency dispatching module, which is used to automatically match flood control resources based on flood prediction data, combined with water accumulation points, road traffic flow analysis, and the status of urban infrastructure, and dispatch drainage pumping stations, underground drainage gates, and overflow regulation measures of sewage treatment plants;

[0015] A dynamic early warning and recovery optimization module, which is used to update the digital twin based on post-disaster data backtracking.

[0016] As a preferred solution of the full-cycle monitoring system for urban life forms based on digital twin technology described in the present invention, wherein: the operation steps of the system include:

[0017] Step S1, using the digital twin modeling module, based on GIS data, remote sensing data, surface permeability information, underground drainage network structure, historical rainfall data, and urban drainage capacity, construct a digital twin of urban drainage, and calculate flood high-risk areas based on the hydrodynamic model to generate a risk assessment model for flood-prone areas;

[0018] Step S2, based on the Internet of Things sensor network, collect rainfall data, underground pipe network flow, surface water accumulation depth, and surface permeability parameters, perform data preprocessing using edge computing technology, and transmit the monitoring data to the AI flood prediction module through the 5G network;

[0019] Step S3, based on the monitoring data described in Step S2, combined with historical precipitation trends, current rainfall intensity, and the status of the urban drainage network, run extreme weather simulation, calculate the water accumulation depth, drainage capacity, and flood evolution trend under different precipitation scenarios, form an urban-level flood risk prediction model, and provide the prediction results to the intelligent emergency dispatching module;

[0020] Step S4: Based on the prediction results described in S3, the intelligent emergency dispatching module automatically matches flood control resources, and combines the analysis of waterlogging points and traffic flow to dynamically optimize flood control measures;

[0021] Step S5: Based on the dispatching execution results of the flood control measures described in S4, combined with the actual impact data of the disaster, the backtracking monitoring system monitors the waterlogging points, infrastructure damage conditions and public feedback, and updates the digital twin.

[0022] As a preferred solution of the urban life form full-cycle monitoring system based on digital twin technology of the present invention, wherein: the system adopts an AI-based multi-modal data fusion algorithm, and combines dynamic meteorological data, historical flood data and surface change information to correct the calculation deviation of the flood prediction model.

[0023] As a preferred solution of the urban life form full-cycle monitoring system based on digital twin technology of the present invention, wherein: the steps of constructing the urban drainage digital twin and calculating the flood high-risk area based on the hydrodynamic model to generate the flood-prone area risk assessment model are as follows

[0024] Based on GIS data, remote sensing images, and underground drainage pipe network structures, construct an urban drainage network topology diagram, expressed as:

[0025] Among them, G represents the urban drainage network, is the set of drainage nodes, ε is the set of drainage pipes,

[0026] Each drainage node n i has the following attributes:

[0027] n i =(X i , Y i , Φ i , C i , Z i ),

[0028] Among them, X i is the lateral geographical coordinate at node i, Y i is the longitudinal geographical coordinate at node i,

[0029] Φ i is the pipe diameter at this node, C i is the drainage flow capacity of this node, Z i is the elevation of the node,

[0030] The parameters of the drainage pipe e ij include:

[0031] e ij =(L ij , Sij , Φ ij , η ij ),

[0032] Among them, L ij is the length of pipeline e ij , S ij is the slope,

[0033] Φ ij is the pipe diameter, η ij is the roughness coefficient of the pipeline;

[0034] Based on remote sensing data, surface types, and soil infiltration characteristics, calculate the surface permeability matrix. The calculation formula is:

[0035] P = {p a,b}},

[0036] Among them, P is the surface permeability matrix, and p a,b is the surface permeability of region (a, b),

[0037] Calculate the total surface infiltration. The calculation formula is:

[0038]

[0039] Among them, Q s is the total infiltration, A a,b is the area of region (a, b), P r (a, b, t) is the precipitation in region (a, b) at time t, and A and B are the maximum row and column numbers of the urban area grid division.

[0040] As an optimal solution of the urban life - form full - cycle monitoring system based on digital twin technology described in the present invention, where: the steps of constructing the urban drainage digital twin body, calculating the flood - high - risk area based on the hydrodynamic model, and generating the flood - prone area risk assessment model further include,

[0041] Construct a hydrodynamic model, calculate the water accumulation depth distribution, and describe the hydrodynamic characteristics of the drainage pipe network and surface water accumulation using the following equation:

[0042]

[0043] Among them, H is the water accumulation depth, t is the time, U x , U y are the velocity components of the water flow in the X and Y directions, P r is the precipitation, Q s is the surface infiltration, Q d is the drainage flow rate,

[0044] Hydrodynamic momentum equation:

[0045]

[0046] Among them, g is the acceleration of gravity, Z is the terrain elevation, and f is the friction coefficient.

[0047] Calculate the waterlogging depth, and the calculation formula is:

[0048] H sim (a, b, t) = H sim (a, b, y - Δt) + Δt(P r (a, b, t) - Q s (a, b, t) - Q d (a, b, y)),

[0049] Among them, H sim (a, b, t) is the simulated waterlogging depth of the area (a, b) at time t, and H sim (a, b, t - Δt) is the waterlogging depth at the previous time step t - Δt, and Δt is the time step.

[0050] If the waterlogging depth exceeds the allowable threshold of the ground surface, it is judged as a high-risk area, and the judgment formula is:

[0051] Ω flood = {(a, b) | H sim (a, b, t) > H c}}, where

[0052] Ω flood is the set of flood areas, and H c is the critical threshold of surface waterlogging.

[0053] Calculate the high-risk flood areas and generate a risk assessment model. The calculation formula is:

[0054]

[0055] Among them, R f is the flood risk index, ω k is the weight of the influencing factor F k and K is the total number of influencing factors.

[0056] Calculate the main influencing factors, including:

[0057] Waterlogging depth factor: F1 = H sim / H max ,

[0058] Among them, H max is the historical maximum waterlogging depth.

[0059] Drainage capacity factor: F2 = Q d / Q max ,

[0060] Among them, Q max Maximum drainage capacity

[0061] Terrain factor:

[0062]

[0063] Among them, Z min and Z max are the lowest and highest elevations of the region respectively

[0064] The final high flood risk area is:

[0065] Ω risk ={(a, b) | R f (a, b)>R th}

[0066] Among them,

[0067] Ω risk is the flood risk area set, and R th is the flood risk threshold

[0068] As a preferred solution of the urban life - body full - cycle monitoring system based on digital twin technology described in the present invention, among them: The step of running an extreme weather simulation based on the monitoring data described in step S2, combining historical precipitation trends, current rainfall intensity, and the state of the urban drainage network, and calculating the waterlogging depth, drainage capacity, and flood evolution trend under different precipitation scenarios to form an urban - level flood risk prediction model is as follows

[0069] Combining the real - time monitoring data and historical data obtained in step S2, establish a precipitation - drainage multi - modal fusion data set, denoted as: D fusion ={D hist , D real , D GIS , D drain}}

[0070] Among them, D fusion is the fusion data set, D hist represents historical rainfall data, D real represents current rainfall monitoring data, D GIS represents urban GIS geographic information data, D drain represents the current state of the urban drainage network

[0071] Use the sliding window filtering method to smooth the data, and the processing formula is:

[0072]

[0073] Among them, is the current rainfall data smoothed at time t, W is the size of the time window, and D real (j) is the original rainfall data at time step j,

[0074] Based on historical data and current meteorological conditions, construct the probability distribution of precipitation intensity:

[0075]

[0076] where P(P r ) is the probability density of precipitation intensity P r , μ P is the historical average precipitation intensity, σ P is the standard deviation of precipitation intensity,

[0077] Set different extreme precipitation scenarios:

[0078]

[0079] where represents the precipitation intensity under the extreme precipitation scenario, and λ is an adjustment factor, which is set according to different precipitation scenarios,

[0080] Adopt the hydrodynamic simulation based on the extreme precipitation scenario to calculate the ponding depth of each region. The calculation formula is:

[0081] H sim (a, b, t) = H sim (a, b, t - Δt) + Δt(P r (a, b, t) - Q s (a, b, t) - Q d (a, b, t)),

[0082] where H sim (a, b, t) is the simulated ponding depth of region (a, b) at time t, H sim (a, b, t - Δt) is the ponding depth at the previous time step t - Δt, Δt is the time step, P r (a, b, t) is the precipitation of the region, Q s (a, b, t) is the surface infiltration, Q d (a, b, t) is the drainage flow,

[0083] If the ponding depth exceeds the surface allowable threshold, it is judged as a high-risk area:

[0084] Ω flood = {(a, b) | H sim (a, b, t) > H c}},

[0085] where

[0086] Ω flood is the set of flood areas, H c is the critical threshold of surface water accumulation,

[0087] Based on the drainage pipe network topology, calculate the drainage network flux. The calculation formula is:

[0088]

[0089] where Q pipe (i,j) is the drainage flow of pipe (i,j), C ij is the pipe flow coefficient, Z i ,Z j is the elevation of the two ends of the pipe node, L ij is the length of pipe (i,j), and α is the empirical coefficient,

[0090] Calculate the overall drainage capacity of the city. The calculation formula is:

[0091] Q total =∑ (i,j)∈ε Q pipe (i,j),

[0092] where Q total is the total drainage capacity of the entire city, ε is the set of pipes in the city's drainage pipe network,

[0093] If Q total <Q rain , then it is determined that flooding may occur:

[0094]

[0095] where Q rain is the total precipitation of the entire urban area, A a,b is the area of region (a,b),

[0096] Calculate the flood diffusion speed:

[0097]

[0098] where V flood is the flood water accumulation growth rate,

[0099] Calculate the flood propagation radius:

[0100]

[0101] where R flood represents the flood propagation radius within the prediction time T, R max is the maximum possible flood propagation radius,

[0102] Construct a flood evolution trend diagram, expressed as:

[0103] M flood ={(a, b) | R flood (a, b) > R safe},

[0104] where M flood is the flood risk prediction matrix, and R safe is the safety propagation radius threshold.

[0105] As a preferred solution of the urban life - body full - cycle monitoring system based on digital twin technology described in the present invention, wherein: the dynamic optimized flood control measures include:

[0106] Adjust the start - stop strategy of drainage pumping stations,

[0107] Remotely control the underground drainage gates,

[0108] Link with sewage treatment plants and adjust the overflow regulation plan,

[0109] And combine with the traffic control system to guide the traffic flow in the disaster - affected area.

[0110] As a preferred solution of the urban life - body full - cycle monitoring system based on digital twin technology described in the present invention, wherein: based on the prediction result described in S3, the steps for the intelligent emergency dispatch module to automatically match flood control resources, combine the analysis of waterlogging points and traffic flow, and dynamically optimize flood control measures are as follows:

[0111] Based on the flood - high - risk areas obtained in step S3, combine the analysis of the importance of urban infrastructure to determine the flood control priority:

[0112]

[0113] where is the set of areas that need to be flood - controlled first, R f (a, b) is the flood risk index of area (a, b), R th is the flood risk threshold, W a,b is the infrastructure weight of area (a, b), W min is the minimum threshold of the infrastructure weight,

[0114] Based on the set of available flood control resources in the city including:

[0115] Drainage pumping station R pump , underground drainage gate R gate , sewage treatment plant scheduling capacity R sewage and emergency supplies R material ;

[0116] For each flood control area to be protected Solve for the nearest flood control resources:

[0117]

[0118] Among them, R match (a, b) represents the flood control resources that are optimally matched for the area (a, b), and d(a, b, r) is the spatial distance from the area (a, b) to the resource r. The geographical path is calculated based on GIS.

[0119] As an optimal solution of the urban life - body full - cycle monitoring system based on digital twin technology described in the present invention, wherein: the steps of dynamically optimizing flood control measures further include:

[0120] Dynamically optimize the drainage system and adjust the urban drainage capacity, including:

[0121] Adjust the start - stop strategy of drainage pumping stations, and the adjustment formula is:

[0122]

[0123] Among them, Q pump (t) is the total drainage capacity of the drainage pumping stations started at time t, and δ p (t) is the start - stop state of the drainage pumping station p, 1 means running, and 0 means closed. is the maximum drainage capacity of the pumping station p.

[0124] Remotely control the underground drainage gates, and the control formula is:

[0125]

[0126] Among them, S gate (t) is the total flow - through area of the drainage gates opened at time t, and γ g (t) is the opening - closing state of the drainage gate g, 1 means open, and 0 means closed. is the maximum flow - through area of the gate g.

[0127] Link with the sewage treatment plant and adjust the overflow regulation plan, and the adjustment formula is:

[0128]

[0129] Among them, Q sewage (t) is the total scheduling flow of the sewage treatment plant at time t, and β s (t) is the scheduling state of the sewage treatment plant s, 1 means increasing the treatment volume, and 0 means maintaining the current treatment capacity. is the maximum treatment capacity of the sewage treatment plant s;

[0130] In combination with the traffic control system, guide the traffic flow in the disaster-stricken area, including:

[0131] Calculate the traffic passability rate, and the calculation formula is:

[0132]

[0133] where T safe (a, b) is the passability rate of area (a, b), and H sim (a, b, t) is the water accumulation depth of this area at time t, and H max is the maximum water accumulation depth threshold for traffic to pass,

[0134] Adjust the traffic signal priority, and the adjustment formula is:

[0135]

[0136] where,

[0137] Θ traffic (a, b) is the traffic signal adjustment priority of area (a, b),

[0138] ∈ is the minimum value.

[0139] As a preferred solution of the urban life form full-cycle monitoring system based on digital twin technology described in the present invention, among them: the dynamic early warning and recovery optimization module adopts a self-learning AI algorithm, and according to the actual impact data of each flood disaster, iteratively optimizes the flood evolution simulation.

[0140] The beneficial effects of the present invention are as follows: The present invention integrates multi-source data such as GIS data, remote sensing information, surface permeability data, and underground drainage pipe network structure, quantifies high-risk flood areas, and improves the cognitive ability of the overall urban hydrological environment; the AI flood prediction module is based on historical rainfall trends, current meteorological conditions, and drainage network status, and uses extreme weather simulation to deduce the water accumulation range and drainage capacity under different precipitation scenarios, dynamically adjusts the flood diffusion trend prediction model, and makes the identification of flood risks more accurate.

[0141] In the present invention, the intelligent emergency dispatching module automatically matches flood control resources, combines the analysis of high-risk flood areas, water accumulation points, and traffic flow, optimizes the start-stop strategy of drainage pump stations, remotely controls underground drainage gates, dynamically adjusts the overflow regulation capacity of sewage treatment plants, and combines the intelligent traffic management system to optimize the emergency evacuation route, improving the accuracy and execution efficiency of the flood control dispatching plan.

[0142] The present invention constructs a dynamic optimization mechanism based on multi-modal data fusion and AI self-learning algorithms. After a disaster occurs, it traces back flood waterlogging points, infrastructure damage conditions and feedback, dynamically updates the digital twin of urban drainage, continuously optimizes the prediction accuracy and flood control planning strategies, and improves the long-term flood resistance resilience of the city.

[0143] In summary, the present invention effectively solves the problems of data lag, insufficient prediction, and inefficient emergency dispatching in the traditional monitoring system, enabling the city to issue more accurate early warnings and respond more quickly in the face of extreme weather and sudden disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0144] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0145] Figure 1 Schematic diagram of the framework of the urban life cycle monitoring system based on digital twin technology of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0146] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following will give a detailed description of the specific embodiments of the present invention with reference to the drawings in the specification.

[0147] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0148] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments.

[0149] Embodiment 1 provides a urban life cycle monitoring system based on digital twin technology, including: a digital twin modeling module for constructing a digital twin of urban drainage based on geographic information system (GIS), remote sensing data, surface permeability information, historical rainfall data, and urban drainage network, and generating a flood risk assessment model.

[0150] A real-time monitoring module, which is used to collect rainfall data, the flow of the underground drainage pipe network, the depth of surface water accumulation and the surface permeability data based on Internet of Things sensors, and perform data preprocessing through edge computing technology to form a dynamic hydrological monitoring network;

[0151] An AI flood prediction module, which is used to run extreme weather simulation based on historical rainfall data, current meteorological conditions and the operation status of the drainage system, deduce the water accumulation range and drainage capacity under different precipitation intensities, and predict the evolution trend of urban floods;

[0152] An intelligent emergency dispatch module, which is used to automatically match flood control resources based on flood prediction data, combined with water accumulation points, road traffic flow analysis and the status of urban infrastructure, and dispatch drainage pump stations, underground drainage gates and overflow regulation measures of sewage treatment plants;

[0153] A dynamic warning and recovery optimization module, which is used to update the digital twin based on post-disaster data backtracking.

[0154] This embodiment also provides a monitoring method for the above-mentioned urban life body full-cycle monitoring system based on digital twin technology, including:

[0155] Step S1, using the digital twin modeling module, based on GIS data, remote sensing data, surface permeability information, underground drainage pipe network structure, historical rainfall data and urban drainage capacity, construct a digital twin of the urban drainage system, and calculate the flood high-risk areas based on the hydrodynamic model to generate a risk assessment model for flood-prone areas;

[0156] The system adopts an AI-based multi-modal data fusion algorithm, and combines dynamic meteorological data, historical flood data and surface change information to correct the calculation deviation of the flood prediction model;

[0157] The steps of constructing the digital twin of the urban drainage system and calculating the flood high-risk areas based on the hydrodynamic model to generate a risk assessment model for flood-prone areas are as follows:

[0158] Based on GIS data, remote sensing images, and the structure of the underground drainage pipe network, construct a topological map of the urban drainage network, expressed as:

[0159] Among them, G represents the urban drainage network, is the set of drainage nodes, and ε is the set of drainage pipes,

[0160] Each drainage node n i has the following attributes:

[0161] n i =(X i , Y i , Φ i , Ci , Z i ),

[0162] Among them, X i is the horizontal geographical coordinate at node i, Y i is the vertical geographical coordinate at node i,

[0163] Φ i is the pipe diameter at this node, C i is the drainage flow capacity of this node, Z i is the elevation of the node terrain,

[0164] Drainage pipe e ij parameters include:

[0165] e ij =(L ij , S ij , Φ ij , η ij ),

[0166] Among them, L ij is the length of pipe e ij , S ij is the slope,

[0167] Φ ij is the pipe diameter, η ij is the roughness coefficient of the pipe;

[0168] Based on remote sensing data, surface types, and soil infiltration characteristics, calculate the surface permeability matrix. The calculation formula is:

[0169] P = {p a,b},

[0170] Among them, P is the surface permeability matrix, p a,b is the surface permeability of region (a, b),

[0171] Calculate the total surface infiltration. The calculation formula is:

[0172]

[0173] Among them, Q s is the total infiltration, A a,b is the area of region (a, b), P r (a, b, t) is the precipitation in region (a, b) at time t, and A and B are the maximum row and column numbers of the urban area grid division;

[0174] The steps of constructing the urban drainage digital twin body, calculating the flood high-risk area based on the hydrodynamic model, and generating the flood-prone area risk assessment model also include,

[0175] Build a hydrodynamic model to calculate the distribution of ponding depth. The hydrodynamic characteristics of the drainage pipe network and surface ponding are described by the following equations:

[0176]

[0177] where H is the ponding depth, t is the time, U x , U y are the velocity components of the water flow in the X and Y directions, P r is the precipitation, Q s is the surface infiltration, Q d is the drainage flow rate,

[0178] Hydrodynamic momentum equation:

[0179]

[0180] where g is the acceleration due to gravity, Z is the terrain elevation, f is the friction coefficient,

[0181] Calculate the ponding depth. The calculation formula is:

[0182] H sim (a, b, t) = H sim (a, b, t - Δt) + Δt(P r (a, b, t) - Q s (a, b, t) - Q d (a, b, t)),

[0183] where H sim (a, b, t) is the simulated ponding depth in the region (a, b) at time t, H sim (a, b, t - Δt) is the ponding depth at the previous time step t - Δt, and Δt is the time step,

[0184] If the ponding depth exceeds the surface allowable threshold, it is judged as a high-risk area. The judgment formula is:

[0185] Ω flood = {(a, b) | H sim (a, b, t) > H c}, where,

[0186] Ω flood is the set of flood areas, and H c is the critical threshold of surface ponding,

[0187] Calculate the high-risk flood areas and generate a risk assessment model. The calculation formula is:

[0188]

[0189] where R fis the flood risk index, ω k is the influence factor F k 's weight, K is the total number of influence factors,

[0190] Calculate the main influence factors, including:

[0191] Waterlogging depth factor: F1 = H sim / H max ,

[0192] where, H max historical maximum waterlogging depth,

[0193] Drainage capacity factor: F2 = Q d / Q max ,

[0194] where, Q max maximum drainage capacity,

[0195] Terrain factor:

[0196]

[0197] where, Z min and Z max are the lowest and highest elevations of the area respectively,

[0198] The final high flood risk area is:

[0199] Ω risk = {(a,b)∣R f (a,b)>R th}

[0200] where,

[0201] Ω risk is the flood risk area set, R th is the flood risk threshold;

[0202] Specifically, in this step, a risk assessment model for flood-prone areas is constructed to accurately simulate flood risks;

[0203] Step S2, based on the Internet of Things sensing network, collect rainfall data, underground pipe network flow, surface waterlogging depth and surface permeability parameters, use edge computing technology for data preprocessing, and transmit the monitoring data to the AI flood prediction module through the 5G network;

[0204] Step S3, based on the monitoring data described in Step S2, combined with historical precipitation trends, current rainfall intensity and urban drainage network status, run extreme weather simulation, calculate the waterlogging depth, drainage capacity and flood evolution trend under different precipitation scenarios, form a city-level flood risk prediction model, and provide the prediction results to the intelligent emergency dispatch module;

[0205] The steps of running an extreme weather simulation based on the monitoring data described in step S2, combining historical precipitation trends, current rainfall intensity, and the status of the urban drainage network, calculating the waterlogging depth, drainage capacity, and flood evolution trend under different precipitation scenarios, and forming an urban-level flood risk prediction model are as follows:

[0206] Combining the real-time monitoring data and historical data obtained in step S2, establish a precipitation-drainage multi-modal fusion dataset, denoted as: D fusion ={D hist , D real , D GIS , D drain},

[0207] where D fusion is the fusion dataset, D hist represents historical rainfall data, D real represents current rainfall monitoring data, D GIS represents urban GIS geographic information data, D drain represents the current status of the urban drainage network,

[0208] Use a sliding window filtering method to smooth the data, and the processing formula is:

[0209]

[0210] where is the current rainfall data smoothed at time t, W is the time window size, and D real (j) is the original rainfall data at time step j,

[0211] Based on historical data and current meteorological conditions, construct a precipitation intensity probability distribution:

[0212]

[0213] where P(P r ) is the probability density of precipitation intensity P r , μ P is the historical average precipitation intensity, and σ P is the standard deviation of precipitation intensity,

[0214] Set different extreme precipitation scenarios:

[0215]

[0216] where represents the precipitation intensity under the extreme precipitation scenario, and λ is an adjustment factor, which is set according to different precipitation scenarios,

[0217] Adopt hydrodynamic simulation based on extreme precipitation scenarios to calculate the ponding depth of each area. The calculation formula is:

[0218] H sim (a,b,t) = H sim (a,b,t - Δt) + Δt(P r (a,b,t) - Q s (a,b,t) - Q d (a,b,t)),

[0219] where H sim (a,b,t) is the simulated ponding depth of area (a,b) at time t, H sim (a,b,t - Δt) is the ponding depth at the previous time step t - Δt, Δt is the time step, P r (a,b,t) is the precipitation of the area, Q s (a,b,t) is the surface infiltration, Q d (a,b,t) is the drainage flow rate,

[0220] If the ponding depth exceeds the surface allowable threshold, it is judged as a high-risk area:

[0221] Ω flood = {(a,b) | H sim (a,b,t) > H c}},

[0222] where,

[0223] Ω flood is the flood area set, H c is the critical threshold of surface ponding,

[0224] Based on the drainage pipe network topology, calculate the drainage network flux. The calculation formula is:

[0225]

[0226] where Q pipe (i,j) is the drainage flow rate of pipe (i,j), C ij is the pipe flow coefficient, Z i ,Z j is the elevation of the two ends of the pipe node, L ij is the length of pipe (i,j), α is the empirical coefficient,

[0227] Calculate the overall drainage capacity of the city. The calculation formula is:

[0228] Q total = ∑ (i,j)∈ε Q pipe (i,j),

[0229] Among them, Q total is the total drainage capacity of the entire city, and ε is the set of pipelines in the urban drainage network.

[0230] If Q total < Q rain , it is determined that flooding may occur:

[0231]

[0232] Among them, Q rain is the total precipitation in the entire urban area, and A a,b is the area of the region (a, b).

[0233] Calculate the flood diffusion speed:

[0234]

[0235] Among them, V flood is the floodwater accumulation growth rate.

[0236] Calculate the flood propagation radius:

[0237]

[0238] Among them, R flood represents the flood propagation radius within the prediction time T, and R max is the maximum possible flood propagation radius.

[0239] Construct a flood evolution trend diagram, expressed as:

[0240] M flood ={(a, b) | R flood (a, b) > R safe},

[0241] Among them, M flood is the flood risk prediction matrix, and R safe is the safety propagation radius threshold;

[0242] Specifically, flood prediction at the city level is carried out here. Multimodal data fusion is introduced to improve the accuracy of precipitation prediction. Combining historical trends and real-time monitoring data improves prediction accuracy; extreme precipitation scenarios are generated based on probability models to enhance disaster prevention planning capabilities. At the same time, a hydrodynamic model is used to calculate the flood diffusion trend to improve the accuracy of flood evolution prediction;

[0243] Step S4, based on the prediction results described in S3, the intelligent emergency dispatching module automatically matches flood control resources, and combines the analysis of waterlogging points and traffic flow to dynamically optimize flood control measures;

[0244] The dynamic optimization of flood control measures includes:

[0245] Adjust the start-stop strategy of the drainage pump station,

[0246] Remotely control the underground drainage gate,

[0247] Link with the sewage treatment plant and adjust the overflow regulation plan,

[0248] And in combination with the traffic control system, guide the traffic flow in the disaster-stricken area;

[0249] Based on the prediction results described in S3, the steps for the intelligent emergency dispatching module to automatically match flood control resources, analyze the water accumulation points and traffic flow, and dynamically optimize flood control measures are as follows:

[0250] Based on the flood-prone areas obtained in step S3, combined with the analysis of the importance of urban infrastructure, determine the flood control priority:

[0251]

[0252] Among them, is the set of areas that need to be flood-controlled first, R f (a, b) is the flood risk index of area (a, b), R th is the flood risk threshold, W a,b is the infrastructure weight of area (a, b), W min is the minimum threshold of the infrastructure weight,

[0253] Based on the set of available flood control resources in the city including:

[0254] Drainage pump station R pump , underground drainage gate R gate , sewage treatment plant dispatching capacity R sewage and emergency supplies R material ;

[0255] For each area to be flood-controlled Solve for the nearest flood control resource:

[0256]

[0257] Among them, R match (a, b) represents the flood control resource that is optimally matched for area (a, b), and d(a, b, r) is the spatial distance from area (a, b) to resource r. Calculate the geographical path based on GIS,

[0258] The steps for the above-mentioned dynamic optimization of flood control measures also include:

[0259] Dynamically optimize the drainage system and adjust the urban drainage capacity, including:

[0260] Adjust the start-stop strategy of the drainage pump station, and the adjustment formula is:

[0261]

[0262] Among them, Q pump (t) is the total drainage capacity of the drainage pump stations started at time t, and δ p (t) is the start-stop state of drainage pump station p, 1 means running, 0 means closed, is the maximum drainage capacity of pump station p,

[0263] Remotely control the underground drainage gate, and the control formula is:

[0264]

[0265] Among them, S gate (t) is the total flow-through area of the drainage gates opened at time t, and γ g (t) is the opening and closing state of drainage gate g, 1 means open, 0 means closed, is the maximum flow-through area of gate g,

[0266] Link with the sewage treatment plant and adjust the overflow regulation plan. The adjustment formula is:

[0267]

[0268] Among them, Q sewage (t) is the total dispatching flow of the sewage treatment plant at time t, and β s (t) is the dispatching state of sewage treatment plant s, 1 means increasing the treatment volume, 0 means maintaining the current treatment capacity, is the maximum treatment capacity of sewage treatment plant s;

[0269] Combine with the traffic control system to guide the traffic flow in the disaster area, including:

[0270] Calculate the traffic passability rate, and the calculation formula is:

[0271]

[0272] Among them, T safe (a,b) is the passability rate of area (a,b), and H sim (a,b,t) is the water accumulation depth of this area at time t, and H max is the maximum water accumulation depth threshold for traffic passability,

[0273] Adjust the traffic signal priority, and the adjustment formula is:

[0274]

[0275] Among them,

[0276] Θ traffic (a, b) is the traffic signal adjustment priority of area (a, b).

[0277] ∈ is the minimum value;

[0278] Specifically, in this step, intelligent emergency dispatching is carried out to optimize the allocation of urban flood control resources, improve the flood response ability, based on the flood control priority model of flood risk index and infrastructure weight, to ensure that key areas can obtain resources preferentially; combining GIS and real-time traffic flow data to improve the accuracy of flood control dispatching plans and reduce the impact on urban operations, and adopting the linkage optimization model of drainage pump stations, underground drainage gates, and sewage treatment plants to enhance the drainage capacity.

[0279] Step S5, based on the dispatching execution results of the flood control measures described in S4, combined with the actual impact data of the disaster, trace back the water accumulation points of the monitoring system, the damage situation of infrastructure and the feedback from the masses, and update the digital twin.

[0280] The dynamic early warning and recovery optimization module adopts a self-learning AI algorithm to iteratively optimize the flood evolution simulation according to the actual impact data of each flood disaster.

[0281] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A full-cycle monitoring system for urban life based on digital twin technology, characterized by: include, Digital twin modeling module, which is used to build urban drainage digital twins and generate flood risk assessment models based on geographic information system (GIS), remote sensing data, surface permeability information, historical rainfall data, and urban drainage networks; The real-time monitoring module is used to collect rainfall data, underground drainage network flow, surface water depth and surface permeability data based on IoT sensors, and pre-process the data through edge computing technology to form a dynamic hydrological monitoring network; AI flood prediction module, which runs extreme weather simulations based on historical rainfall data, current meteorological conditions, and drainage system operation status, deduce the waterlogging range and drainage capacity under different precipitation intensities, and predict the evolution trend of urban floods; Intelligent emergency dispatch module, which is used to automatically match flood control resources and dispatch drainage pump stations, underground drainage gates and sewage treatment plant overflow regulation measures based on flood prediction data, combined with waterlogging points, road traffic flow analysis and urban infrastructure status; The dynamic early warning and recovery optimization module is used to update the digital twin based on post-disaster data backtracking.

2. The urban life cycle monitoring system based on digital twin technology as claimed in claim 1, characterized in that: The system operation steps include: Step S1, using the digital twin modeling module, based on GIS data, remote sensing data, surface permeability information, underground drainage network structure, historical rainfall data and urban drainage capacity, constructing a digital twin of urban drainage, and calculating high-risk areas for flooding based on a hydrodynamic model to generate a risk assessment model for flood-prone areas; Step S2, based on the IoT sensor network, collect rainfall data, underground pipe network flow, surface water depth and surface permeability parameters, use edge computing technology to pre-process the data, and transmit the monitoring data to the AI ​​flood prediction module through the 5G network; Step S3, based on the monitoring data described in step S2, combined with historical precipitation trends, current rainfall intensity and the status of the urban drainage network, run extreme weather simulation, calculate the water depth, drainage capacity and flood evolution trend under different precipitation scenarios, form a city-level flood risk prediction model, and provide the prediction results to the intelligent emergency dispatch module; Step S4, based on the prediction results described in S3, the intelligent emergency dispatch module automatically matches flood control resources, combines waterlogging points and traffic flow analysis, and dynamically optimizes flood control measures; Step S5, based on the scheduling and execution results of the flood control measures described in S4, combined with the actual impact data of the disaster, trace back the waterlogging points in the monitoring system, the damage to the infrastructure and the feedback from the public, and update the digital twin.

3. The urban life cycle monitoring system based on digital twin technology as claimed in claim 2, characterized in that: The system uses an AI-based multimodal data fusion algorithm, and combines dynamic meteorological data, historical flood data and surface change information to correct the calculation deviation of the flood prediction model.

4. The urban life cycle monitoring system based on digital twin technology as claimed in claim 3 is characterized by: The steps of constructing the urban drainage digital twin, calculating the high-risk flood areas based on the hydrodynamic model, and generating the flood-prone area risk assessment model are as follows: Based on GIS data, remote sensing images, and underground drainage pipe network structure, the urban drainage network topology map is constructed, which is expressed as: Where G represents the urban drainage network, is the set of drainage nodes, ε is the set of drainage pipes, Each drainage node n i The properties include: n i (X i ,Y i ,Φ i ,C i ,Z i ), Among them, X i is the horizontal geographic coordinate of node i, Y i is the vertical geographic coordinate of node i, Φ i is the pipe diameter at the node, C i is the drainage capacity of the node, Z i is the node terrain elevation, Drainage pipe ij Parameters include: e ij =(L ij ,S ij ,F ij ,or ij ), Among them, L ij For pipeline ij Length, S ij is the slope, Φ ij is the pipe diameter, η ij is the roughness coefficient of the pipeline; Based on remote sensing data, surface type and soil permeability characteristics, the surface permeability matrix is ​​calculated using the following formula: P={p a,b }, Where P is the surface permeability matrix, p a,b is the surface permeability of region (a, b), Calculate the total surface infiltration using the following formula: Among them, Q s is the total permeability, A a,b is the area of ​​region (a, b), P r (a,b,t) is the precipitation in area (a,b) at time t, and A,B are the maximum number of rows and columns for the grid division of the urban area.

5. The urban life cycle monitoring system based on digital twin technology as claimed in claim 4, characterized in that: The steps of constructing a digital twin of urban drainage, calculating high-risk flood areas based on a hydrodynamic model, and generating a risk assessment model for flood-prone areas also include: A hydrodynamic model was constructed to calculate the distribution of water depth, and the following equation was used to describe the hydrodynamic characteristics of the drainage network and surface water: Among them, H is the depth of water, t is the time, U x ,U y is the velocity component of the water flow in the X and Y directions, P r is the precipitation, Q s is the surface infiltration, Q d is the drainage flow rate, The hydrodynamic momentum equation is: Among them, g is the acceleration of gravity, Z is the terrain elevation, f is the friction coefficient, Calculate the depth of water accumulation using the following formula: H sim (a,b,t)=H sim (a,b,y-Δt)+Δt(P r (a,b,t)-Q s (a,b,t)-Q d (a,b,y)), Among them, H sim (a,b,t) is the simulated water depth of area (a,b) at time t, H sim (a,b,t-Δt) is the water depth at the previous time step t-Δt, Δt is the time step, If the depth of water accumulation exceeds the allowable threshold of the surface, it is judged as a high-risk area. The judgment formula is: Oh flood ={(a,b)∣H sim (a,b,t)>H c }, among them, Ω flood is the flood area collection, H c is the critical threshold of surface waterlogging, Calculate the high-risk flood areas and generate a risk assessment model. The calculation formula is: Among them, R f is the flood risk index, ω k The impact factor F k The weight of K is the total number of influencing factors. Calculate the main impact factors, including: Water depth factor: F1 = H sim / H max , Among them, H max The maximum depth of flooding in history, Drainage capacity factor: F2 = Q d / Q max , Among them, Q max Maximum drainage capacity, Topographic factors: Among them, Z min and Z max are the lowest and highest elevations of the region, The final high-risk flood areas are: Oh risk ={(a,b)∣R f (a,b)>R th }, in, Ω risk is the flood risk area set, R th is the flood risk threshold.

6. The urban life cycle monitoring system based on digital twin technology as claimed in claim 5, characterized in that: The steps of running extreme weather simulation based on the monitoring data described in step S2, combining historical precipitation trends, current rainfall intensity and the status of the urban drainage network, calculating the water depth, drainage capacity and flood evolution trend under different precipitation scenarios, and forming a city-level flood risk prediction model are as follows: Combined with the real-time monitoring data and historical data obtained in step S2, a multimodal fusion dataset of precipitation and drainage is established, which is expressed as: D fusion ={D hist ,D real ,D GIS ,D drain }, Among them, D fusion is the fusion data set, D hist represents historical rainfall data, D real Indicates the current rainfall monitoring data, D GIS Represents urban GIS geographic information data, D drain Indicates the current status of the urban drainage network. The sliding window filtering method is used to smooth the data. The processing formula is: in, is the current rainfall data after smoothing at time t, W is the time window size, D real (j) is the original rainfall data at time step j, Based on historical data and current meteorological conditions, construct a probability distribution of precipitation intensity: Among them, P(P r ) is the precipitation intensity P r The probability density of P is the historical average precipitation intensity, σ P is the standard deviation of precipitation intensity, Set different extreme precipitation scenarios: in, represents the precipitation intensity under extreme precipitation scenarios, λ is the adjustment factor, which is set according to different precipitation scenarios. The water depth in each area is calculated by hydrodynamic simulation based on extreme precipitation scenarios. The calculation formula is: H sim (a,b,t)=H sim (a,b,t-Δt)+Δt(P r (a,b,t)-Q s (a,b,t)-Q d (a,b,t)), Among them, H sim (a,b,t) is the simulated water depth of area (a,b) at time t, H sim (a,b,t-Δt) is the water depth at the previous time step t-Δt, Δt is the time step, P r (a, b, t) is the regional precipitation, Q s (a, b, t) is the surface infiltration, Q d (a, b, t) is the drainage flow rate, If the depth of water accumulation exceeds the allowable threshold of the surface, it is judged as a high-risk area: Ω flood ={(a,b)∣H sim (a,b,t)>H c }, in, Ω flood is the flood area collection, H c is the critical threshold of surface waterlogging, Based on the drainage network topology, the drainage network flux is calculated using the following formula: Among them, Q pipe (i,j) is the drainage flow of pipe (i,j), C ij is the pipe flow coefficient, Z i ,Z j is the terrain elevation of the nodes at both ends of the pipeline, L ij is the length of pipeline (i, j), α is the empirical coefficient, Calculate the overall drainage capacity of the city using the following formula: Q total =∑ (i,j)∈ε Q pipe (i,j), Among them, Q total is the total drainage capacity of the entire city, ε is the pipe collection of the urban drainage network, If Q total rain , then it is determined that flooding may occur:​ Among them, Q rain is the total precipitation in the entire urban area, A a,b is the area of ​​region (a,b), Calculate flood spread speed: Among them, V flood is the flood water growth rate, Calculate the flood propagation radius: Among them, R flood represents the flood propagation radius within the forecast time T, R max is the maximum possible flood propagation radius, The flood evolution trend diagram is expressed as: M flood ={(a,b)∣R flood (a,b)>R safe }, Among them, M flood is the flood risk prediction matrix, R safe is the safe propagation radius threshold.

7. The urban life cycle monitoring system based on digital twin technology as claimed in claim 6, characterized in that: The dynamic optimized flood control measures include: Adjust the start and stop strategy of drainage pump stations, Remote control of underground drainage gates, Linking with sewage treatment plants, adjusting overflow regulation plans, And combined with the traffic control system, it can guide the traffic flow in the affected areas.

8. The urban life cycle monitoring system based on digital twin technology as claimed in claim 7, characterized in that: Based on the prediction results described in S3, the intelligent emergency dispatch module automatically matches flood control resources, combines waterlogging points and traffic flow analysis, and dynamically optimizes flood control measures. Based on the high-risk flood areas obtained in step S3 and combined with the importance analysis of urban infrastructure, the flood control priority is determined: in, is the set of areas that need priority flood control, R f (a, b) is the flood risk index of region (a, b), R th is the flood risk threshold, W a,b is the infrastructure weight of region (a, b), W min is the minimum value threshold of infrastructure weight, Based on the collection of flood control resources available in the city include: Drainage pump station R pump , underground drainage gate R gate , the dispatching capacity of the sewage treatment plant R sewage And emergency supplies material ; For each flood protection area Find the nearest flood control resource: Among them, R match (a, b) represents the optimal matching flood control resource in region (a, b), d(a, b, r) is the spatial distance from region (a, b) to resource r, and the geographical path is calculated based on GIS.

9. The urban life cycle monitoring system based on digital twin technology as claimed in claim 8, characterized in that: The step of dynamically optimizing flood control measures also includes: Dynamically optimize the drainage system and adjust the city's drainage capacity, including: Adjust the start and stop strategy of the drainage pump station. The adjustment formula is: Among them, Q pump (t) is the total drainage capacity of the drainage pump station started at time t, δ p (t) is the start / stop status of the drainage pump station p, 1 means running, 0 means shut down, is the maximum drainage capacity of pumping station p, Remote control of underground drainage gate, the control formula is: Among them, S gate (t) is the total flow area of ​​the drainage gate opened at time t, γ g (t) is the opening and closing status of the drainage gate g, 1 means open, 0 means closed, is the maximum flow area of ​​gate g, Link the sewage treatment plant and adjust the overflow regulation plan. The adjustment formula is: Among them, Q sewage (t) is the total dispatch flow of the sewage treatment plant at time t, β s (t) is the scheduling status of sewage treatment plant s, 1 means increasing the treatment capacity, 0 means maintaining the current treatment capacity, is the maximum treatment capacity of the sewage treatment plant s; Combined with the traffic control system, guide the traffic flow in the disaster area, including: Calculate the traffic accessibility rate using the following formula: Among them, T safe (a,b) is the passability rate of area (a,b), H sim (a, b, t) is the water depth of the area at time t, H max is the maximum water depth threshold for traffic, Adjust the traffic signal priority, the adjustment formula is: in, Θ traffic (a,b) is the traffic signal adjustment priority of area (a,b), ∈ is a minimum value.

10. The urban life cycle monitoring system based on digital twin technology according to claim 9, characterized in that: The dynamic early warning and recovery optimization module adopts a self-learning AI algorithm to iteratively optimize the flood evolution simulation based on the actual impact data of each flood disaster.

Images