Modular flood prevention dam intelligent arrangement method and system

Abstract

The application provides a kind of modularization flood prevention dam intelligent layout method and system, it is related to flood control and intelligent equipment technical field.The method steps include: S1, acquisition multi-source data and carry out preprocessing operation;S2, extract secondary characteristic parameters from multi-source data;S3, determine optimization target and divide distribution scene;S4, build layout area global simulation model;S5, use particle swarm algorithm to determine modularization flood prevention dam layout scheme;S6, according to final scheme, layout modularization flood prevention dam, and according to monitoring data, dynamically adjust the inflation pressure of module;S7, based on the air pressure of module, carry out early warning operation.The beneficial effect is: optimization target improves the comprehensiveness of layout method selection;Particle swarm algorithm determines the final scheme to reduce labor cost;According to the air pressure of dynamic determination standard module according to comprehensive influence factor, so that the air pressure of each standard module meets the real-time requirement;Early warning considers the size dimension and time dimension of air pressure deviation, avoids the situation of missing report.

Description

Technical Field

[0001] This invention relates to the field of flood control and disaster relief and intelligent equipment technology, specifically to a modular intelligent deployment method and system for flood control dikes. Background Technology

[0002] Floods are one of the most common natural disasters in my country. Traditional dikes, mostly earth-rock or concrete, suffer from long construction periods, difficulties in dismantling and transportation, and lack of reusability, making them unsuitable for rapid deployment during sudden floods and emergency rescue operations. Therefore, modular inflatable flood control dikes, with their advantages of easy assembly and disassembly, rapid deployment, recyclability, and strong adaptability, are gradually becoming the mainstream facility for emergency flood control and river overflow prevention. However, while traditional flood control dike devices can alleviate flood damage, they generally suffer from the following problems: Traditional flood control dikes lack real-time response capabilities and rely solely on manual experience for deployment, making them difficult to adapt to complex flood scenarios. The lack of an intelligent operation and maintenance mechanism and the fixed air pressure of each standard module make it impossible to monitor the status and risks of the standard modules. The setup and scheduling rely heavily on manpower and lack scientific decision-making tools. Summary of the Invention

[0003] The main objective of this invention is to provide a modular intelligent deployment method and system for flood control dikes, thereby solving the problems mentioned in the background art.

[0004] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: a modular intelligent deployment method for flood control dikes, comprising the following steps: S1. Collect multi-source data and perform preprocessing operations; S2. Extract secondary feature parameters from multi-source data; S3. Determine the optimization objectives and divide the deployment scenarios; S4. Build a full-area simulation model of the deployment area; S5. Use particle swarm optimization algorithm to determine the modular flood control dike layout scheme; S6. Deploy modular flood control dikes according to the final plan, and dynamically adjust the inflation pressure of the modules based on monitoring data; S7. Perform early warning operations based on the module's air pressure.

[0005] Furthermore, the multi-source data includes: topographic and foundational data of the deployment area, hydrological forecast data, and real-time on-site environmental monitoring data; The topographic and foundation data of the deployment area include: ground friction coefficient, foundation bearing properties, river channel cross-sectional width and riverbed elevation; foundation bearing properties include: hard paving, silty soft soil, and gravel riverbed; Hydrological forecast data includes: predicted extreme water levels for each time period from 1 to 24 hours, predicted maximum instantaneous flow velocity, predicted rainfall intensity, and theoretical arrival time of flood peak; Real-time environmental monitoring data at the site includes: instantaneous water level at the monitoring points, measured water flow velocity, and ambient temperature.

[0006] Furthermore, the secondary feature parameters include: The rate of water level rise is used to determine the speed at which a floodwater rises. The predicted peak water level for the next hour will be used to determine the baseline height for the dike layout. The remaining time before the flood peak arrives is used to constrain the upper limit of the on-site deployment period; The impact energy of the cross-section water flow is used to determine the layout density of the modules on the water-facing side and the initial inflation pressure; The dam body has a pre-set internal and external pressure difference benchmark value, which serves as the pressure benchmark for zoned layout; The theoretical stress concentration of the splice joint is used to determine the anchorage density at the splice location. The predicted seepage velocity growth rate is used to determine the number of bottom anti-seepage auxiliary accessories to be installed.

[0007] Furthermore, the detailed process of step S3 is as follows: S301. Determine a unified optimization objective function; The expression for the objective function to be optimized is as follows: (1); in, For the target score, , , , , These are the overall stiffness uniformity of the dam, the deviation of the pressure differential safety margin, the system dynamic response hysteresis, the deployment time, and the deployment cost. , , , , They are respectively , , , , The corresponding influence weights; the sum of the influence weights is 1; S302. Divide the layout scenarios; The layout scenarios include: hard paving scenario, silty soft soil scenario and gravel river beach scenario, which correspond to the three foundation bearing properties of hard paving, silty soft soil and gravel river beach respectively. S303. Set the influence weight values ​​corresponding to the deployment scene.

[0008] Furthermore, the expression for the overall stiffness uniformity of the dam is as follows: (2); in, The standard deviation of the internal pressure of the entire dam module. This represents the arithmetic mean of the internal pressures of all dam modules; The expression for the differential pressure safety margin deviation is as follows: (3); in, , The internal pressure of the module layout and the water pressure outside the layout location are calculated respectively. To preset a safety pressure margin; The expression for the system dynamic response lag is as follows: (4); in, , These are the module pressure regulation response time and the duration of regional water level rise, respectively.

[0009] Furthermore, the deployment area-wide simulation model includes: a site-wide sub-model and a modular dam assembly sub-model; The input parameters for the site-wide sub-model include: foundation bearing capacity properties, additional parameters of foundation bearing capacity properties, inherent parameters of the river channel, and secondary characteristic parameters; Additional parameters for foundation bearing capacity include: ground friction coefficient, foundation constraint conditions, soil permeability coefficient, and elastic modulus; The inherent parameters of the river channel include, but are not limited to: the cross-sectional width of the river channel, the elevation of the riverbed, and the location of the boundary line of the deployment area; The input parameters for the modular dam assembly sub-model are the modular flood control dam layout scheme, including the following dam design parameters: dam layout start coordinates, dam layout end coordinates, size of a single standard module, number of standard module layers, number of standard modules per layer, standard module spacing, anchoring component layout spacing, preset inflation internal pressure of each standard module, and counterweight layout specifications. The input parameters for the modular dam assembly sub-model also include: basic structure and splicing rules; The basic structure includes: the cross-sectional configuration of a single standard module, the form of the module water-stopping structure, the pre-embedded location of anchoring points, and the connection form between the dam body and the foundation. The splicing rules include: the axial docking method of adjacent modules, the constraint form of joints at the segmentation, and the assembly and binding logic of the counterweight and the dam body; The output of the global simulation model of the deployment area includes the overall stiffness uniformity of the dam, the pressure difference safety margin deviation, the system dynamic response hysteresis, deployment time, and deployment cost.

[0010] Furthermore, the particle swarm optimization algorithm optimizes the dam design parameters in the modular flood control dam layout scheme, and the optimization objective of the particle swarm algorithm is to minimize the objective score of the optimization objective function. The detailed process of this step is as follows: S501. Randomly sample within the legal value range of each optimization variable to generate an initial particle population; S502. Input the secondary features into the global simulation model of the deployment area; S503. Input the dam design parameters of the modular flood control embankment layout scheme corresponding to each particle into the global simulation model of the layout area in sequence to obtain the overall stiffness uniformity of the dam, the pressure difference safety margin deviation, the system dynamic response lag, the layout time and the layout cost. S504. Calculate the target score of the optimization objective function based on the obtained dam overall stiffness uniformity, pressure difference safety margin deviation, system dynamic response hysteresis, deployment time and deployment cost. S505: The particle with the lowest target score is taken as the global optimal particle; S506. Update the particle position according to the particle velocity, execute steps S503~S504, and take the particle with the lowest target score as the current optimal particle; each new particle position corresponds to a new modular flood control dike layout scheme. S507. Compare the target score values ​​of the global best particle and the current best particle. When the target score value of the current best particle is less than the target score value of the global best particle, update the current best particle to the global best particle. S508. Repeat steps S506 to S507. When any of the termination conditions is met, the process ends. At this time, the modular flood control dike layout scheme corresponding to the globally optimal particle is the final scheme. The termination conditions include: Set a maximum number of iterations, and update the particle position until the maximum number of iterations is reached; Set an early stopping threshold number of iterations, which is the number of consecutive early stopping iterations after the global optimal particle has not been updated. During the above adjustment process, when the position of a particle in a certain dimension exceeds its legal value range, the position of that dimension is modified to be within the legal value range.

[0011] Furthermore, the module's inflation pressure adjustment process is as follows: S601. Set the inflation pressure adjustment boundary conditions for the standard module as follows: Set upper and lower inflation limits. All modules must have an inflation pressure greater than or equal to the lower inflation limit and less than or equal to the upper inflation limit. Set the inflation step size. The air pressure value of all modules during each inflation or deflation is the inflation step size. Only during the last inflation or deflation is it allowed to be less than the inflation step size. Set the inflation rate to the rated value, and the inflation and deflation rates of all modules are the rated inflation rate. S602. Determine the operating condition impact factors, and calculate the comprehensive impact factor by weighting the operating condition impact factors. Operating condition influencing factors include: water level influencing factor, flow velocity influencing factor, and deformation influencing factor; The water level impact factor is used to characterize the air pressure demand caused by rising water levels; the higher the water level, the larger the factor. The flow velocity impact factor is used to characterize the air pressure demand of water flow impact; the higher the flow velocity, the larger the factor. The deformation influence factor is used to characterize the reinforcement requirement of air pressure due to module deformation; the larger the deformation, the larger the factor. The expression for the comprehensive impact factor is as follows: (5); in, As a comprehensive impact factor, , , These are the water level influencing factor, the flow velocity influencing factor, and the deformation influencing factor, respectively. , , These are the weighting coefficients for the water level influence factor, flow velocity influence factor, and deformation influence factor, respectively, and the sum of the three is 1. The larger the comprehensive influence factor, the more severe the comprehensive working conditions, and the higher the required inflation pressure. S603. Determine the target pressure value based on comprehensive influencing factors; The expression for the target value of pressure adjustment is as follows: (6); in, For the target pressure value, This is the module's air pressure reference value, i.e., the preset internal inflation pressure after assembly; the target value for pressure adjustment must meet the constraints of the upper and lower inflation limits.

[0012] S604. Adjust the module's air pressure to the target pressure value according to the set inflation step length and inflation rate rating.

[0013] Furthermore, the detailed process of step S7 is as follows: Set the pressure regulation period, stabilization time limit, and regulation threshold. When the pressure regulation period is reached, if the absolute value of the difference between the module's pressure and the target pressure value should be less than or equal to the regulation threshold, and the duration should be greater than or equal to the stabilization time limit, the module is determined to be in a risk-free state and monitoring continues; otherwise, the module is determined to be in a risk state and an early warning is issued to the management personnel.

[0014] This invention also provides a modular intelligent deployment system for flood control dikes, used to implement the steps in the above method, including: The data acquisition and preprocessing module is used to acquire multi-source data and perform preprocessing operations on the multi-source data; The feature extraction module, connected to the data acquisition and preprocessing module, is used to extract secondary feature parameters from the preprocessed multi-source data. The target and scene configuration module, connected to the feature extraction module, is used to construct the optimization objective function, divide the deployment scenes, and configure corresponding weight base values ​​for the deployment scenes; The global simulation modeling module, connected to the target and scene configuration module, is used to receive the target function, scene parameters and secondary feature parameters sent by the target and scene configuration module, build a global sub-model of the site and a modular dam assembly sub-model to complete rapid modeling and simulation calculation, and output evaluation index values. The intelligent optimization module is connected to the global simulation modeling module. It receives the evaluation index data sent by the global simulation modeling module, and uses the particle swarm algorithm to randomly generate an initial particle population within the legal interval. It then combines the simulation index to iteratively optimize and solve for the final solution. The on-site deployment and air pressure regulation module is connected to the intelligent optimization module. It is used to receive the final deployment plan sent by the intelligent optimization module and complete the modular dam physical construction according to the optimal deployment plan. At the same time, the inflation pressure regulation boundary, working condition influence factor and weighted calculation rules are set. Combined with real-time monitoring data, the comprehensive influence factor and pressure target value are solved, and the module inflation pressure is dynamically adjusted according to a fixed step size and rate. The status monitoring and early warning module is connected to the field deployment and air pressure regulation module. It is used to receive real-time air pressure, operating condition data and pressure target values ​​of the standard module sent by the field deployment and air pressure regulation module. It determines the air pressure operation status based on the preset air pressure regulation period, stabilization time limit and regulation threshold. When the module determines that the status is risky, it issues an early warning to the management personnel.

[0015] The beneficial effects of this application are as follows: (1) Using the second-order characteristic parameter layout as the input of the global simulation model of the design area can more accurately characterize the environmental parameters during floods; (2) The optimization objectives take into account the dimensions of safety, cost and time, which improves the comprehensiveness of the deployment method selection; (3) Dividing the deployment scenarios and determining the corresponding influence weight values ​​can improve the applicability of the method; (4) The particle swarm optimization algorithm is used to determine the final solution, which avoids the limitations of manual solutions and reduces labor costs. (5) Dynamically determine the air pressure of the standard module based on the comprehensive influencing factors so that the air pressure of each standard module meets the real-time requirements; (6) The early warning takes into account both the magnitude and time dimension of the pressure deviation to avoid missed reports. Attached Figure Description

[0016] The present invention will be further described below with reference to the accompanying drawings and embodiments: Figure 1 These are the steps of the method of the present invention. Detailed Implementation

[0017] Example 1 like Figure 1 As shown, a modular intelligent deployment method for flood control dikes includes the following steps: S1. Collect multi-source data and perform preprocessing operations; The multi-source data includes: topographic and foundational data of the deployment area, hydrological forecast data, and real-time environmental monitoring data from the field; The topographic and foundation data of the deployment area include: ground friction coefficient, foundation bearing properties, river channel cross-sectional width and riverbed elevation; foundation bearing properties include: hard paving, silty soft soil, and gravel riverbed; Hydrological forecast data includes: predicted extreme water levels for each time period from 1 to 24 hours, predicted maximum instantaneous flow velocity, predicted rainfall intensity, and theoretical arrival time of the flood peak; the flow velocity here includes: the longitudinal mainstream flow velocity of the river channel and the flow velocity towards the embankment. The real-time environmental monitoring data includes: instantaneous water level at the monitoring points, measured water flow velocity, and ambient temperature. It should be noted that all water level data collected uses the same elevation datum as the riverbed elevation datum. In addition, the monitoring area is not limited to natural river channels, but also includes flood-affected areas around the river that are prone to overflow. Preprocessing operations include: noise reduction, outlier removal, and missing value imputation. The processing methods commonly used in practical applications meet the requirements of this application, such as using Kalman filtering for noise reduction and selecting 3 The criteria include outlier removal and missing value imputation using linear interpolation.

[0018] S2. Extract secondary feature parameters from multi-source data; secondary feature parameters include: The rate of water level rise is calculated from the difference in water levels between adjacent time series forecasts and the time interval, and is used to determine the speed of the flood rise. The predicted water level peak value for the next hour, which is the difference between the predicted water level and the design benchmark water level, is used to determine the benchmark layout height of the dike. The remaining time until the flood peak arrives is the difference between the arrival time of the flood peak and the current time, used to constrain the upper limit of the on-site deployment period; The cross-sectional water flow impact energy is used to determine the module layout density and initial inflation pressure on the water-facing side; the expression for the cross-sectional water flow impact energy is as follows: (1); in, The impact energy of the water flow at the cross section. The density of water, The width of the embankment is defined laterally. The cross-sectional water depth is the difference between the instantaneous water level and the riverbed elevation at the designated monitoring point. The lateral overflow impact velocity is the velocity of the water flowing towards the dam, not the longitudinal mainstream velocity of the river channel. The dam body has a preset internal and external pressure difference benchmark value, which is the sum of the predicted external water pressure value and the safety margin. This value is selected manually and serves as the pressure benchmark for zoned layout. The theoretical stress concentration at the splice joint is calculated from the simulated lateral water flow load and is used to determine the anchorage density at the splice location. The expression for the theoretical stress concentration at the splice joint is as follows: (2); in, The theoretical stress concentration of the splice joint. This represents the peak stress at the corner of the splice joint. These represent the average stress at the splice joint section; due to the abrupt structural changes at the splice corner, therefore... Since the stress cannot be directly calculated using formulas, the individual dam sections and splicing corners can be broken down into numerous micro-units. The stress distribution across the entire field can then be iteratively solved based on the elasticity equilibrium equations. A sudden increase in stress occurs at the splicing corners where geometric changes occur; the maximum stress at these points is extracted. The termination condition for the above iteration is that the external water pressure of all micro-units equals the elastic force of their internal materials. This can be understood as all micro-units satisfying the elasticity equilibrium equations. Stress is defined as the elastic force of the internal material per unit cross-sectional area. Therefore, extracting the maximum stress is equivalent to finding the unit with the largest internal elastic force; the ratio of the internal elastic force of this unit to its cross-sectional area is then calculated. The average stress at the splice joint section can be obtained by dividing the sum of the internal elastic forces of all elements on the section by the cross-sectional area. The predicted seepage velocity growth rate, derived using Darcy's formula based on the site permeability coefficient and head difference, is used to determine the number of bottom seepage prevention auxiliary components to be installed. The predicted seepage velocity growth rate is the predicted increase in seepage rate per unit time, and the expression for the predicted seepage rate is as follows: (3); in, To predict the permeation rate, This refers to the soil permeability coefficient, a value related to the bearing capacity of the foundation. It is the difference between the water level elevation and the ground elevation on the back side of the dam. It is the length of the seepage path of water from the water-facing side of the dam to the soil-facing side.

[0019] S3. Determine the optimization objectives and divide the deployment scenarios. The detailed process is as follows: S301. Determine a unified optimization objective function and optimization objective; The expression for the objective function to be optimized is as follows: (4); in, For the target score, , , , , These are the overall stiffness uniformity of the dam, the deviation of the pressure differential safety margin, the system dynamic response hysteresis, the deployment time, and the deployment cost. , , , , They are respectively , , , , The corresponding influence weights; the sum of the influence weights is 1; The overall stiffness uniformity of the dam is used to characterize the dispersion of air pressure in each section of the dam. The smaller the value, the more evenly the pressure is distributed across the dam sections. The expression for the overall stiffness uniformity of the dam is as follows: (5); in, The standard deviation of the internal pressure of the entire dam module. The arithmetic mean of the internal pressure of all dam modules; the overall stiffness uniformity of the dam is controlled by the module arrangement density and inflation pressure in different sections to avoid local layout that is too soft or too hard; The differential pressure safety margin deviation is used to control the baseline layout pressure of dam modules, preventing them from being flattened by water pressure due to excessively low pressure or bulging and breaking due to excessively high pressure. The expression for the differential pressure safety margin deviation is as follows: (6); in, , The internal pressure of the module layout and the water pressure outside the layout location are calculated respectively. To preset a safety pressure margin, this value is typically taken as 0.02~0.05MPa; The system dynamic response hysteresis is used to reserve a margin for dynamic reinforcement deployment, thus allowing for rapid pressure replenishment and reinforcement deployment during sudden flood surges; the expression for the system dynamic response hysteresis is as follows: (7); in, , These are the module pressure regulation response time and the duration of regional water level rise, respectively. S302. Divide the layout scenarios; the layout scenarios include: hard paving scenario, silty soft soil scenario and gravel river beach scenario, which correspond to the three foundation bearing properties of hard paving, silty soft soil and gravel river beach respectively; S303. Set the influence weight values ​​corresponding to the deployment scene; This embodiment provides an example of how the weight value is influenced: For hard paved areas , , , , The values ​​are 0.2, 0.4, 0.25, 0.1, and 0.05, respectively. For silty soft soil scenarios , , , , The values ​​are 0.5, 0.15, 0.2, 0.1, and 0.05, respectively. For sandy and gravelly riverbed scenes , , , , The values ​​are 0.28, 0.29, 0.28, 0.1, and 0.05, respectively.

[0020] S4. Build a full-area simulation model of the deployment area; simulation software such as COMSOL Multiphysics and PLAXIS3D can be selected. The deployment area simulation model includes: a site-wide sub-model and a modular dam assembly sub-model; The input parameters for the site-wide sub-model include: foundation bearing capacity properties, additional parameters of foundation bearing capacity properties, inherent parameters of the river channel, and secondary characteristic parameters; The foundation bearing capacity here is one of the following types: hard paving, silty soft soil, or gravelly riverbed. Additional parameters for foundation bearing capacity include: ground friction coefficient, foundation constraints, soil permeability coefficient, and elastic modulus; the foundation constraints are used to determine whether the model boundaries can be displaced, and include: Let X be the horizontal direction, Y be the vertical direction, and Z be the vertical direction; preset displacement thresholds in the XYZ directions; the displacement of the dam body in the XYZ directions is not allowed to exceed the displacement thresholds in the corresponding directions; This embodiment provides a displacement threshold value selection scheme, specifically as follows: For hard paved surfaces, the displacement threshold in the XYZ directions is 0. For sandy riverbed scenarios, the displacement threshold in the XY direction is 20mm, and the displacement threshold in the Z direction is 3mm. For silty soft soil scenarios, the displacement threshold in the XY direction is 50mm, and the displacement threshold in the Z direction is 8mm. The inherent parameters of the river channel include, but are not limited to: the cross-sectional width of the river channel, the elevation of the riverbed, and the location of the boundary line of the deployment area; The input parameters for the modular dam assembly sub-model are the modular flood control dam layout scheme, including the following dam design parameters: dam layout start coordinates, dam layout end coordinates, size of a single standard module, number of standard module layers, number of standard modules per layer, standard module spacing, anchoring component layout spacing, preset inflation internal pressure of each standard module, and counterweight layout specifications. The dam design parameters are to be supplemented; here, "to be supplemented" means that the model only has the position of the parameter, but not the specific value of the parameter. The specific value of the parameter to be supplemented will be given and imported later. The input parameters for the modular dam assembly sub-model also include: basic structure and splicing rules; The basic structure includes: the cross-sectional configuration of a single standard module, the form of the module water-stopping structure, the pre-embedded location of anchoring points, and the connection form between the dam body and the foundation. The splicing rules include: the axial docking method of adjacent modules, the constraint form of joints at the segmentation, and the assembly and binding logic of the counterweight and the dam body; The modular dam assembly sub-model construction process is as follows: using the river channel layout boundary line of the site global sub-model as the positioning reference, the geometric splicing model of the dam body is completed within the legal layout range of the global base, and a continuous flexible dam entity structure is generated according to the module assembly sequence; the dam sub-model and the lower site global sub-model are geometrically coupled and bound, and the load transfer relationship between the bottom of the dam body and the foundation contact surface is automatically established. After the modeling of a single scheme is completed, the model assembly configuration is retained. When changing the candidate scheme, only the original dam sub-model is deleted and the bottom site global sub-model is retained, so as to realize the rapid rotation modeling of multiple schemes. The output of the global simulation model of the deployment area includes the overall stiffness uniformity of the dam, the pressure difference safety margin deviation, the system dynamic response hysteresis, deployment time, and deployment cost. This embodiment also presents a process for building a global simulation model based on PLAXIS 3D as follows: S401. Open PLAXIS 3D, create a new 3D project file, and set the unit system, including: length unit is mm; pressure unit is MPa. Import basic data: riverbed elevation, river channel cross-section width, and layout boundary coordinates to determine the overall modeling scope; Globally preset XYZ three-dimensional displacement thresholds are used as the standard for foundation deformation control.

[0021] S402, Site-wide Sub-model Modeling, specifically: Use terrain generation tools to draw the riverbed base terrain based on the riverbed elevation; Soil layers are created in layers / regions according to the bearing capacity of the foundation: hard pavement layer, silty soft soil layer, and sand and gravel riverbed layer are established respectively; Assign values ​​to the parameters of each soil layer, including: soil permeability coefficient, surface friction coefficient, and elastic modulus; The boundary conditions are set to be fully fixed constraints at the bottom and lateral outer boundaries of the model; The displacement constraint is as follows: the displacement limitation function is enabled for all soil areas, and the maximum deformation is locked according to the XYZ threshold of different foundations; The initial seepage setting is: the groundwater level is set according to the water depth of the cross section.

[0022] S403, Modular dam assembly sub-model modeling, specifically: Create new components in the structure library: standard modules, anchoring components, and counterweight components; Define the mechanical properties of the components: the stiffness of the standard module varies with the internal air pressure, and an interface for variable internal air pressure is reserved; The dam body position is located based on the start and end coordinates of the dam body layout, and aligned with the riverbank line as a reference. Standard modules are arranged in an array according to the number of module layers, the number of modules per layer, and the module spacing. Arrange the anchoring structure according to the anchoring spacing and assemble the counterweight components; Set up splice joint constraints, water-stop structures, and dam-foundation interface contact relationships to establish load transfer paths.

[0023] Set the dam layout coordinates, number of standard modules, internal pressure, anchorage spacing, etc. as global variables, and support batch import and modification of external parameters.

[0024] S404. Applying an external load corresponds to the following secondary characteristic parameters: Dynamic water impact load is applied based on the cross-sectional water flow impact energy; the cross-sectional water flow impact energy is the core secondary characteristic parameter. Combined with the lateral overflow impact velocity perpendicular to the dam body, a uniformly distributed dynamic water impact load is applied to the upstream side of the dam body to simulate the continuous impact of water flow; the load magnitude is calculated from the cross-sectional water flow impact energy, and the calculation result of the characteristic parameter is directly used as the load input value.

[0025] Hydrostatic pressure load is applied based on water level-related characteristic parameters; the total head on the upstream side is calculated by combining the predicted water level freeboard value in the next 1 hour and the real-time cross-sectional water depth, and a linearly distributed hydrostatic pressure is applied along the height of the dam; at the same time, the load variation gradient with time is set with reference to the water level rise rate to simulate the dynamic rise of the water level. The module's internal pressure is applied based on the preset internal and external pressure difference benchmark value of the dam body; the preset internal inflation pressure of the module is calculated based on the preset internal and external pressure difference benchmark value of the dam body; this pressure value is set as the model variable interface and applied to the inner wall of the inflation module to simulate the module's inflation and pressure-bearing state, and at the same time, it serves as the variable entry point for subsequent air pressure optimization. Seepage boundary conditions are set based on the predicted seepage velocity growth rate; the seepage velocity growth rate is predicted using secondary characteristic parameters, and seepage boundaries are set at the bottom of the dam, the module splicing joint, and the backwater side of the dam, combined with the site soil permeability coefficient and water head difference, to define the seepage rate variation law and simulate the seepage evolution process at the splicing position of the soil and the dam under flood conditions. Local stress constraints are added based on the theoretical stress concentration of splice seams; based on the secondary characteristic parameter theoretical stress concentration of splice seams, local stress monitoring and constraint conditions are added to stress concentration areas such as module splice seams and corners to limit the stress peak value at the splice position and match the theoretical stress distribution law. The simulation is based on time-related secondary feature parameters. Two types of time-related secondary feature parameters, namely the remaining time of the flood peak and the rate of water level rise, are used to set the total simulation duration and load loading sequence, match the rhythm of the flood evolution on site, and ensure that the simulation conditions are consistent with the actual flood peak process.

[0026] S405. Perform mesh generation, specifically as follows: For the site soil, standard soil and rock grids are used, with local densification of the grid on the riverbank slope; For dam structures, joints, and anchor points, the mesh is densified to ensure the accuracy of stress and deformation calculations.

[0027] S406, Multiple setting schemes can be quickly switched, specifically: Lock in the site's soil layers, topography, and boundary conditions as a permanent foundation model; The modular dam structure is set as a "component group", which supports overall deletion and replacement; The configuration parameters can be imported into the template, and the layout scheme output by the particle swarm algorithm can be updated with one click to update the dam body variables without having to build the site repeatedly.

[0028] S407, Calculation and Operating Condition Analysis, specifically: Select the combined load case of plasticity calculation and seepage calculation, and enable structure-soil coupling calculation; Click to run the calculation to solve for dam deformation, foundation settlement, structural stress, and seepage distribution.

[0029] S408. Extract simulation data from the post-processing interface, calculate and output the model's output parameters as follows: The internal pressure of all standard modules is statistically analyzed, and the overall stiffness uniformity of the dam is calculated. Read the internal pressure and external water pressure of the standard module, and calculate the pressure difference safety margin deviation; Extract time parameters and calculate the system's dynamic response lag. Calculate the workload and output the deployment time and cost.

[0030] S5. Use particle swarm optimization (PSO) to determine the modular flood control dike layout scheme; the PSO optimization variable is the dam design parameters in the modular flood control dike layout scheme, and the optimization objective of the PSO is to minimize the objective score of the optimization objective function in step S3. The detailed process of this step is as follows: S501. Randomly sample within the legal value range of each optimization variable to generate an initial particle population. Each particle in the population represents a complete modular flood control dike layout scheme. S502. Input the secondary features into the global simulation model of the deployment area; S503. Input the dam design parameters of the modular flood control embankment layout scheme corresponding to each particle into the global simulation model of the layout area in sequence to obtain the overall stiffness uniformity of the dam, the pressure difference safety margin deviation, the system dynamic response lag, the layout time and the layout cost. S504. Calculate the target score of the optimization objective function based on the obtained dam overall stiffness uniformity, pressure difference safety margin deviation, system dynamic response hysteresis, deployment time and deployment cost. S505: The particle with the lowest target score is taken as the global optimal particle; S506. Update the particle position according to the particle velocity, execute steps S503~S504, and take the particle with the lowest target score as the current optimal particle; each new particle position corresponds to a new modular flood control dike layout scheme. S507. Compare the target score values ​​of the global best particle and the current best particle. When the target score value of the current best particle is less than the target score value of the global best particle, update the current best particle to the global best particle. S508. Repeat steps S506 to S507. When any of the termination conditions is met, the process ends. At this time, the modular flood control dike layout scheme corresponding to the globally optimal particle is the final scheme. The termination conditions include: Set a maximum number of iterations, and update the particle position until the maximum number of iterations is reached; Set an early stopping threshold number of iterations, which is the number of consecutive early stopping iterations after the global optimal particle has not been updated. During the above adjustment process, when the position of a particle in a certain dimension exceeds its legal value range, the position of that dimension is modified to be within the legal value range.

[0031] S6. Deploy modular flood control dikes according to the final plan, and dynamically adjust the inflation pressure of the modules based on monitoring data; The module inflation pressure adjustment process is as follows: S601. Set the inflation pressure adjustment boundary conditions for the standard module as follows: Set upper and lower inflation limits. All modules must have an inflation pressure greater than or equal to the lower inflation limit and less than or equal to the upper inflation limit. Set the inflation step size. The air pressure value of each inflation or deflation of all modules is the inflation step size. Only during the last inflation or deflation is it allowed to be less than the inflation step size. Here, the last inflation means that the target air pressure of the module will be reached after this inflation. Set the inflation rate to the rated value, and the inflation and deflation rates of all modules are the rated inflation rate. S602. Determine the operating condition impact factors, and calculate the comprehensive impact factor by weighting the operating condition impact factors. Operating condition influencing factors include: water level influencing factor, flow velocity influencing factor, and deformation influencing factor; The water level impact factor is used to characterize the air pressure demand caused by rising water levels; the higher the water level, the larger the factor. An expression for the water level impact factor is given below: (8); in, Water level influencing factors This refers to the cross-sectional water depth mentioned earlier. , These are the baseline water level and the maximum extreme water level, respectively. The flow velocity impact factor is used to characterize the air pressure demand of water flow impact; the higher the flow velocity, the larger the factor. An expression for the flow velocity impact factor is given below: (9); in, For flow velocity influencing factors, This refers to the lateral overflow impact velocity of the vertical dam body mentioned earlier. , These are the baseline flow velocity and the maximum extreme value of the flow velocity, respectively. The deformation influence factor is used to characterize the pressure reinforcement requirement of module deformation. The larger the deformation, the larger the factor. An expression for the deformation influence factor is given below: (10); in, Deformation influencing factor For the current form variable, , These are the baseline allowable deformation and the maximum extreme value of deformation, respectively. The expression for the comprehensive impact factor is as follows: (11); in, As a comprehensive impact factor, , , These are the weighting coefficients for the water level influence factor, flow velocity influence factor, and deformation influence factor, respectively, and the sum of the three is 1. The larger the comprehensive influence factor, the more severe the comprehensive working conditions, and the higher the required inflation pressure. S603. Determine the target pressure value based on comprehensive influencing factors; The expression for the target value of pressure adjustment is as follows: (12); in, For the target pressure value, This is the module's air pressure reference value, i.e., the preset internal inflation pressure after assembly; the target value for pressure adjustment must meet the constraints of the upper and lower inflation limits. S604. Adjust the module's air pressure to the target pressure value according to the set inflation step length and inflation rate rating.

[0032] S7. Early warning operation based on module air pressure, detailed process as follows: Set the pressure regulation period, stabilization time limit, and regulation threshold. When the pressure regulation period is reached, if the absolute value of the difference between the module's pressure and the target pressure value should be less than or equal to the regulation threshold, and the duration should be greater than or equal to the stabilization time limit, the module is determined to be in a risk-free state and monitoring continues; otherwise, the module is determined to be in a risk state and an early warning is issued to the management personnel.

[0033] Example 2 A modular intelligent deployment system for flood control dikes includes: The data acquisition and preprocessing module is used to acquire multi-source data and perform preprocessing operations such as noise reduction, outlier removal, and missing value imputation on the multi-source data.

[0034] The feature extraction module, connected to the data acquisition and preprocessing module, is used to extract secondary feature parameters from the preprocessed multi-source data.

[0035] The target and scenario configuration module, connected to the feature extraction module, is used to construct and optimize the objective function, divide the deployment scenarios into three categories: hard paving, silty soft soil, and gravel riverbed, and configure corresponding weight base values ​​for different scenarios.

[0036] The global simulation modeling module, connected to the target and scene configuration module, is used to receive the target function, scene parameters and secondary feature parameters sent by the target and scene configuration module. It builds a global sub-model of the site and a modular dam assembly sub-model to complete rapid modeling and simulation calculations, and outputs evaluation index values ​​such as the overall stiffness uniformity of the dam, the pressure difference safety margin deviation, the system dynamic response lag, the deployment time, and the deployment cost.

[0037] The intelligent optimization module is connected to the global simulation modeling module. It receives the evaluation index data sent by the global simulation modeling module, and uses the particle swarm optimization algorithm to randomly generate an initial particle population within the legal interval. It then combines the simulation index to iteratively optimize and solve for the final solution.

[0038] The on-site deployment and air pressure regulation module is connected to the intelligent optimization module. It is used to receive the final deployment plan sent by the intelligent optimization module and complete the modular dam construction according to the optimal deployment plan. At the same time, it sets the inflation pressure regulation boundary, working condition influence factor and weighted calculation rules, and solves the comprehensive influence factor and pressure target value by combining real-time monitoring data. It completes the dynamic adjustment of module inflation pressure according to fixed step size and rate.

[0039] The status monitoring and early warning module is connected to the field deployment and air pressure regulation module. It is used to receive real-time air pressure, operating condition data and pressure target values ​​of the standard module sent by the field deployment and air pressure regulation module. It determines the air pressure operation status based on the preset air pressure regulation period, stabilization time limit and regulation threshold. When the module determines that the status is risky, it issues an early warning to the management personnel.

[0040] The above embodiments are merely preferred technical solutions of the present invention and should not be considered as limitations on the present invention. The scope of protection of the present invention should be limited to the technical solutions described in the claims, including equivalent substitutions of the technical features described in the claims. That is, equivalent substitutions and improvements within this scope are also within the scope of protection of the present invention.

Claims

1. A modular intelligent deployment method for flood control dikes, characterized in that, Includes the following steps: S1. Collect multi-source data and perform preprocessing operations; S2. Extract secondary feature parameters from multi-source data; S3. Determine the optimization objectives and divide the deployment scenarios; S4. Build a full-area simulation model of the deployment area; S5. Use particle swarm optimization algorithm to determine the modular flood control dike layout scheme; S6. Deploy modular flood control dikes according to the final plan, and dynamically adjust the inflation pressure of the modules based on monitoring data; S7. Perform early warning operations based on the module's air pressure.

2. The modular flood control dike intelligent deployment method according to claim 1, characterized in that, The multi-source data includes: topographic and foundational data of the deployment area, hydrological forecast data, and real-time environmental monitoring data from the field; The topographic and foundation data of the deployment area include: ground friction coefficient, foundation bearing properties, river channel cross-sectional width and riverbed elevation; foundation bearing properties include: hard paving, silty soft soil, and gravel riverbed; Hydrological forecast data includes: predicted extreme water levels for each time period from 1 to 24 hours, predicted maximum instantaneous flow velocity, predicted rainfall intensity, and theoretical arrival time of flood peak; Real-time environmental monitoring data at the site includes: instantaneous water level at the monitoring points, measured water flow velocity, and ambient temperature.

3. The modular flood control dike intelligent deployment method according to claim 1, characterized in that, Secondary feature parameters include: The rate of water level rise is used to determine the speed at which a floodwater rises. The predicted peak water level for the next hour will be used to determine the baseline height for the dike layout. The remaining time before the flood peak arrives is used to constrain the upper limit of the on-site deployment period; The impact energy of the cross-section water flow is used to determine the layout density of the modules on the water-facing side and the initial inflation pressure; The dam body has a pre-set internal and external pressure difference benchmark value, which serves as the pressure benchmark for zoned layout; The theoretical stress concentration of the splice joint is used to determine the anchorage density at the splice location. The predicted seepage velocity growth rate is used to determine the number of bottom anti-seepage auxiliary accessories to be installed.

4. The modular flood control dike intelligent deployment method according to claim 1, characterized in that, The detailed process of step S3 is as follows: S301. Determine a unified optimization objective function; The expression for the objective function to be optimized is as follows: （1）； in, For the target score, , , , , These are the overall stiffness uniformity of the dam, the deviation of the pressure differential safety margin, the system dynamic response hysteresis, the deployment time, and the deployment cost. , , , , They are respectively , , , , The corresponding influence weight; S302. Divide the layout scenarios; The layout scenarios include: hard paving scenario, silty soft soil scenario and gravel river beach scenario, which correspond to the three foundation bearing properties of hard paving, silty soft soil and gravel river beach respectively. S303. Set the influence weight values ​​corresponding to the deployment scene.

5. The modular flood control dike intelligent deployment method according to claim 4, characterized in that, The expression for the overall stiffness uniformity of the dam is as follows: （2）； in, The standard deviation of the internal pressure of the entire dam module. This represents the arithmetic mean of the internal pressures of all dam modules; The expression for the differential pressure safety margin deviation is as follows: （3）； in, , The internal pressure of the module layout and the water pressure outside the layout location are calculated respectively. To preset a safety pressure margin; The expression for the system dynamic response lag is as follows: （4）； in, , These are the module pressure regulation response time and the duration of regional water level rise, respectively.

6. The modular flood control dike intelligent deployment method according to claim 4, characterized in that, The deployment area simulation model includes: a site-wide sub-model and a modular dam assembly sub-model; The input parameters for the site-wide sub-model include: foundation bearing capacity properties, additional parameters of foundation bearing capacity properties, inherent parameters of the river channel, and secondary characteristic parameters; Additional parameters for foundation bearing capacity include: ground friction coefficient, foundation constraint conditions, soil permeability coefficient, and elastic modulus; The inherent parameters of the river channel include, but are not limited to: the cross-sectional width of the river channel, the elevation of the riverbed, and the location of the boundary line of the deployment area; The input parameters for the modular dam assembly sub-model are the modular flood control dam layout scheme, including the following dam design parameters: dam layout start coordinates, dam layout end coordinates, standard module size, number of standard module layers, number of standard modules per layer, standard module spacing, anchoring component layout spacing, preset inflation internal pressure of each standard module, and counterweight layout specifications. The input parameters for the modular dam assembly sub-model also include: basic structure and splicing rules; The basic structure includes: the cross-sectional configuration of a single standard module, the form of the module water-stopping structure, the pre-embedded location of anchoring points, and the connection form between the dam body and the foundation. The splicing rules include: the axial docking method of adjacent modules, the constraint form of joints at the segmentation, and the assembly and binding logic of the counterweight and the dam body; The output of the global simulation model of the deployment area includes the overall stiffness uniformity of the dam, the pressure difference safety margin deviation, the system dynamic response hysteresis, deployment time, and deployment cost.

7. The modular flood control dike intelligent deployment method according to claim 6, characterized in that, The particle swarm optimization algorithm optimizes the dam design parameters in the modular flood control dam layout scheme, and the optimization objective of the particle swarm optimization algorithm is to minimize the objective score of the optimization objective function. The detailed process of this step is as follows: S501. Randomly sample within the legal value range of each optimization variable to generate an initial particle population; S502. Input the secondary features into the global simulation model of the deployment area; S503. Input the dam design parameters of the modular flood control embankment layout scheme corresponding to each particle into the global simulation model of the layout area in sequence to obtain the overall stiffness uniformity of the dam, the pressure difference safety margin deviation, the system dynamic response lag, the layout time and the layout cost. S504. Calculate the target score of the optimization objective function based on the obtained dam overall stiffness uniformity, pressure difference safety margin deviation, system dynamic response hysteresis, deployment time and deployment cost. S505: The particle with the lowest target score is taken as the global optimal particle; S506. Update the particle position according to the particle velocity, execute steps S503~S504, and take the particle with the lowest target score as the current optimal particle; each new particle position corresponds to a new modular flood control dike layout scheme. S507. Compare the target score values ​​of the global best particle and the current best particle. When the target score value of the current best particle is less than the target score value of the global best particle, update the current best particle to the global best particle. S508. Repeat steps S506 to S507. When any of the termination conditions is met, the process ends. At this time, the modular flood control dike layout scheme corresponding to the globally optimal particle is the final scheme. The termination conditions include: Set a maximum number of iterations, and update the particle position until the maximum number of iterations is reached; Set an early stopping threshold number of iterations, which is the number of consecutive early stopping iterations after the global optimal particle has not been updated. During the above adjustment process, when the position of a particle in a certain dimension exceeds its legal value range, the position of that dimension is modified to be within the legal value range.

8. The modular flood control dike intelligent deployment method according to claim 1, characterized in that, The module inflation pressure adjustment process is as follows: S601. Set the inflation pressure adjustment boundary conditions for the standard module as follows: Set upper and lower inflation limits. All modules must have an inflation pressure greater than or equal to the lower inflation limit and less than or equal to the upper inflation limit. Set the inflation step size. The air pressure value of all modules during each inflation or deflation is the inflation step size. Only during the last inflation or deflation is it allowed to be less than the inflation step size. Set the inflation rate to the rated value, and the inflation and deflation rates of all modules are the rated inflation rate. S602. Determine the operating condition impact factors, and calculate the comprehensive impact factor by weighting the operating condition impact factors. Operating condition influencing factors include: water level influencing factor, flow velocity influencing factor, and deformation influencing factor; The water level impact factor is used to characterize the air pressure demand caused by rising water levels; the higher the water level, the larger the factor. The flow velocity impact factor is used to characterize the air pressure demand of water flow impact; the higher the flow velocity, the larger the factor. The deformation influence factor is used to characterize the reinforcement requirement of air pressure due to module deformation; the larger the deformation, the larger the factor. The expression for the comprehensive impact factor is as follows: （5）； in, As a comprehensive impact factor, , , These are the water level influencing factor, the flow velocity influencing factor, and the deformation influencing factor, respectively. , , These are the weighting coefficients for the water level influence factor, flow velocity influence factor, and deformation influence factor, respectively. S603. Determine the target pressure value based on comprehensive influencing factors; The expression for the target value of pressure adjustment is as follows: （6）； in, The target pressure value, This is the module's air pressure reference value; the target value for pressure adjustment must meet the constraints of the upper and lower inflation limits. S604. Adjust the module's air pressure to the target pressure value according to the set inflation step length and inflation rate rating.

9. The modular flood control dike intelligent deployment method according to claim 8, characterized in that, The detailed process of step S7 is as follows: Set the pressure regulation period, stabilization time limit, and regulation threshold. When the pressure regulation period is reached, if the absolute value of the difference between the module's pressure and the target pressure value should be less than or equal to the regulation threshold, and the duration should be greater than or equal to the stabilization time limit, the module is judged to be in a risk-free state and monitoring continues. Otherwise, the module is deemed to be in a risky state, and an alert is sent to the management personnel.

10. A modular intelligent deployment system for flood control dikes, used to implement the steps in the method described in any one of claims 1 to 9, characterized in that, include: The data acquisition and preprocessing module is used to acquire multi-source data and perform preprocessing operations on the multi-source data; The feature extraction module, connected to the data acquisition and preprocessing module, is used to extract secondary feature parameters from the preprocessed multi-source data. The target and scene configuration module, connected to the feature extraction module, is used to construct the optimization objective function, divide the deployment scenes, and configure corresponding weight base values ​​for the deployment scenes; The global simulation modeling module, connected to the target and scene configuration module, is used to receive the target function, scene parameters and secondary feature parameters sent by the target and scene configuration module, build a global sub-model of the site and a modular dam assembly sub-model to complete rapid modeling and simulation calculation, and output evaluation index values. The intelligent optimization module is connected to the global simulation modeling module. It receives the evaluation index data sent by the global simulation modeling module, and uses the particle swarm algorithm to randomly generate an initial particle population within the legal interval. It then combines the simulation index to iteratively optimize and solve for the final solution. The on-site deployment and air pressure regulation module is connected to the intelligent optimization module. It is used to receive the final deployment plan sent by the intelligent optimization module and complete the modular dam physical construction according to the optimal deployment plan. At the same time, the inflation pressure regulation boundary, working condition influence factor and weighted calculation rules are set. The comprehensive influence factor and pressure target value are solved by combining real-time monitoring data. The module inflation pressure is dynamically adjusted according to a fixed step size and rate. The status monitoring and early warning module is connected to the field deployment and air pressure regulation module. It is used to receive real-time air pressure, operating condition data and pressure target values ​​of the standard module sent by the field deployment and air pressure regulation module. It determines the air pressure operation status based on the preset air pressure regulation period, stabilization time limit and regulation threshold. When the module determines that the status is risky, it issues an early warning to the management personnel.

Images