A groundwater level dynamic regulation method and system based on digital twinning

Abstract

The present application belongs to the field of hydrogeology and intelligent control technology, and specifically relates to a groundwater level dynamic regulation method and system based on digital twinning, aiming to solve the problems of one-sidedness of traditional regulation and control perception, static model, extensive decision-making and single feedback. The method of the present application comprises: collecting multi-source monitoring data and constructing a data set through cross-scale calibration; constructing a multi-field dynamic coupling digital twinning model, introducing a dynamic coupling coefficient to deduce a risk evolution field; calculating the variation coefficient of the risk value of each physical field based on the risk evolution field to generate a comprehensive risk value; and matching the risk threshold to generate deep and shallow layer regulation instructions. The multi-field dynamic coupling of the present application breaks the static limitation of the model, and the dynamic weight based on the variation coefficient ensures that the regulation and control decision can preferentially respond to the key physical field with high absolute risk level and large spatial fluctuation, realizing the full-area visualization tracking and precise control of groundwater level and geological risk.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of hydrogeology and intelligent control technology, and particularly relates to a groundwater level dynamic regulation method and system based on digital twinning. BACKGROUND

[0002] The stability of groundwater level is crucial for the sustainable use of regional water resources, the safety of urban underground engineering, and the ecological maintenance of specific geological environments. Traditional groundwater level regulation methods, such as pumping or recharge based on empirical models, face a series of technical bottlenecks.

[0003] Traditional regulation methods rely heavily on discrete pressure tubes for data sensing. The "point" data provided by these pressure tubes cannot fully reflect the spatial and temporal distribution characteristics of regional groundwater levels. Moreover, there is a lack of effective cross-scale calibration mechanisms for macro and meso-scale monitoring data such as satellite remote sensing and unmanned aerial thermal infrared data, resulting in one-sided and error-prone sensing information. In the model simulation process, existing models often decouple multiple physical fields such as hydraulic, mechanical, chemical, and thermal fields for calculation, or use fixed coupling parameters, which cannot truly reflect the real-time and dynamic interaction between physical fields, leading to a significant decrease in model prediction accuracy over time. Furthermore, existing regulation strategies often use conventional control algorithms without fully considering the inherent hysteresis and nonlinearity of groundwater seepage, making it difficult to achieve ideal accuracy in regulation when dealing with the unique long hysteresis and nonlinear response of groundwater systems, and failing to meet the precise regulation needs under long-term and complex working conditions.

[0004] Therefore, how to build an intelligent closed-loop regulation system that can realize dynamic modeling, forward-looking decision-making, and precise execution has become a technical problem that needs to be solved in this field. SUMMARY

[0005] To solve the above problems in the prior art, i.e., one-sided sensing, static modeling, and extensive decision-making in traditional groundwater level regulation, the first aspect of the present application proposes a groundwater level dynamic regulation method based on digital twinning, which includes the following steps:

[0006] Collecting multi-source monitoring data of the target regional groundwater system to construct a multi-dimensional dynamic data set;

[0007] Constructing a multi-field dynamic coupling digital twinning model and using the multi-dimensional dynamic data set to drive the model for deduction to predict the future spatio-temporal distribution of multi-field parameters, and then quantify the evolution trend of key risk indicators to generate a risk evolution field;

[0008] Calculating the coefficient of variation of the risk value of each physical field based on the risk evolution field, and dynamically assigning decision weights to each physical field based on the coefficient of variation and the scene characteristics of the target region to generate a comprehensive risk value;

[0009] The comprehensive risk value is matched with a risk warning threshold to determine a risk assessment result; and a synergistic regulation instruction is generated for the shallow and deep aquifers according to the risk assessment result.

[0010] In some preferred embodiments, multi-source monitoring data of a groundwater system in a target area is collected, including:

[0011] The target area is monitored by satellite remote sensing equipment, unmanned aerial vehicle thermal infrared equipment, a ground sensor network, and an underground intelligent monitoring device to obtain multi-source and multi-scale monitoring data of the target area; wherein the satellite remote sensing equipment obtains original data of surface deformation rate, the unmanned aerial vehicle thermal infrared equipment obtains soil temperature and illumination deviation data, the ground sensor network obtains water level, structural stress, water quality parameters, formation temperature, and soil moisture content data, and the underground intelligent monitoring device obtains pore water pressure and deep water level data; the water quality parameters include pH value and concentration.

[0012] In some preferred embodiments, a multi-field dynamic coupling digital twin model is constructed, and the method is as follows:

[0013] A multi-field dynamic coupling model including a hydraulic field, a mechanical field, a chemical field, and a thermal field is constructed, and the mutual influence between at least two physical fields is quantified and updated in real time by introducing a dynamic coupling coefficient; wherein the hydraulic field parameters include shallow water level and deep water level, the mechanical field parameters include structural settlement and effective stress, the chemical field parameters include corrosion rate, and the thermal field parameters include thermal stress; the dynamic coupling coefficient includes influence sensitivity coefficient, pore pressure sensitivity coefficient, temperature sensitivity coefficient, and temperature corrosion coefficient.

[0014] In some preferred embodiments, the mutual influence between two physical fields is updated, specifically: according to the simulation output result of one physical field, the key model parameters of another physical field are dynamically updated;

[0015] The updating includes at least one of the following:

[0016] According to the solute concentration simulation result of the chemical field, the influence sensitivity coefficient is used to update the permeability coefficient value of the shallow aquifer;

[0017] According to the pore water pressure simulation result of the mechanical field, the pore pressure sensitivity coefficient and the temperature sensitivity coefficient are used to update the permeability coefficient value of the deep aquifer;

[0018] According to the temperature simulation result of the thermal field, the temperature corrosion coefficient is used to update the chemical reaction rate value of the chemical field.

[0019] In some preferred embodiments, the generating the comprehensive risk value specifically comprises:

[0020] For the state of the hydraulic field, the mechanical field, the chemical field and the thermal field in the risk evolution field, the independent risk evaluation values of each field at all monitoring points are counted respectively;

[0021] The average value and the standard deviation of the independent risk evaluation values of each physical field are calculated, and the coefficient of variation of each physical field is obtained based on the average value and the standard deviation;

[0022] The basic decision weight is proportionally distributed according to the coefficient of variation of each physical field, wherein the physical field with a higher coefficient of variation is allocated a larger basic decision weight;

[0023] The decision weight is corrected in combination with the scene characteristics of the target area;

[0024] The average independent risk evaluation value of each physical field is calculated, and the comprehensive risk value is generated by weighted summation based on the corrected decision weight.

[0025] In some preferred embodiments, the comprehensive risk value is matched with a risk warning threshold to determine a risk assessment result, and the method is as follows:

[0026] At least two risk warning thresholds are dynamically preset according to the engineering safety level of the target area and in combination with the operating conditions or environmental conditions, and different risk levels are divided according to the risk thresholds;

[0027] The comprehensive risk value is compared with the risk threshold, and the risk level to which the comprehensive risk value belongs is determined according to the comparison result;

[0028] The risk level is taken as the risk assessment result, which is used to trigger a control strategy corresponding to the risk level.

[0029] In some preferred embodiments, according to the risk assessment result, a coordinated control instruction is generated for the shallow and deep aquifers respectively, and specifically:

[0030] For the shallow aquifer, an extraction instruction is generated to maintain the dynamic water level stability of the key area or meet the engineering dewatering demand;

[0031] For the deep aquifer, a recharge instruction is generated to provide regional pore water pressure support and slow down land subsidence.

[0032] In some preferred embodiments, it further includes feedback data after the execution of the collection instruction, and a double-level closed-loop feedback mechanism is used to optimize the system to form a closed-loop control.

[0033] In some preferred embodiments, the double-level closed-loop feedback mechanism specifically includes the following contents:

[0034] The first level is an instruction feedback loop: according to the real-time deviation of the measured physical quantity in the feedback data from the predicted data, the calculation parameters of the regulation and control instruction are quickly adjusted to real-time correct and ensure accurate execution of the instruction; the calculation parameters include a lag compensation coefficient and a level coefficient;

[0035] The second level is a model evolution loop: when the comprehensive deviation exceeds a preset deviation threshold, historical monitoring data in a regulation and control period is periodically collected, the core physical parameters in the digital twin model are optimized and updated through a data inversion method, and the core physical parameters are at least one dynamic coupling coefficient, so that the periodic learning and evolution of the model are realized.

[0036] The second aspect of the application provides a groundwater level dynamic regulation and control system based on digital twinning, which comprises:

[0037] The data acquisition module is configured to acquire multi-source monitoring data of the target area groundwater system, and construct a multi-dimensional dynamic data set containing hydraulic, mechanical, chemical and thermal parameters;

[0038] The twin simulation and prediction module is configured to construct a multi-field dynamic coupling digital twin model, drive the multi-field dynamic coupling digital twin model using the multi-dimensional dynamic data set for simulation, simulate the state response of the groundwater system under the influence of multi-field interaction, predict the future spatio-temporal distribution of the multi-field parameters, and then quantify the evolution trend of the key risk indicators to generate a risk evolution field;

[0039] The data processing module is configured to calculate the variation coefficient of the risk value of each physical field based on the risk evolution field, and dynamically allocate decision weights to each physical field based on the variation coefficient and the scene characteristics of the target area to generate a comprehensive risk value;

[0040] The hierarchical regulation and control module is configured to match the comprehensive risk value with a preset risk warning threshold to determine a risk assessment result; and generate a cooperative regulation and control instruction for the shallow and deep aquifers according to the risk assessment result.

[0041] The feedback optimization module is configured to collect feedback data after the instruction is executed, and optimize the calculation parameters of the regulation and control instruction and the core physical parameters of the digital twin model through a double-level closed-loop feedback mechanism to form a closed-loop regulation and control.

[0042] The application has the following advantages:

[0043] (1) By fusing multi-source data, a multi-field coupled digital twin model is constructed, a three-dimensional risk dynamic evolution field is generated, a dynamic permeability coefficient is taken as a core physical parameter, and a risk quantization closed loop is taken as a decision core, so that the limitations of traditional point monitoring are broken through, and the visualization tracking of the risk hot area of the whole area groundwater level drawdown, water pollution diffusion and ground subsidence is realized.

[0044] (2) Breaking the static limitation of the model through multi-field dynamic coupling, dynamically allocating weights based on the coefficient of variation and scene characteristics, so that the integrated risk value reflects the physical field interaction effect (such as water level drop inducing dramatic increase of geological stress) and regional difference characteristics, improving the accuracy of regulation and control decision and the response priority of key risks, and avoiding the regulation and control deviation caused by static weight;

[0045] (3) The double-loop mechanism converts the feedback data deviation into a model calibration signal: using the deviation between the monitoring data and the predicted value, real-time correction of the key parameters such as the aquifer permeability coefficient, compensation of the prediction error to drive the model to continuously evolve, and guarantee the long-term reliability of the system under environmental disturbance. BRIEF DESCRIPTION OF DRAWINGS

[0046] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments, which is to be read in conjunction with the accompanying drawings:

[0047] Figure 1 is a flow chart of a groundwater level dynamic regulation method based on digital twinning provided by an embodiment of the present application;

[0048] Figure 2 is a structural schematic diagram of a computer system of a server for implementing the method, system and electronic device embodiments of the present application. DETAILED DESCRIPTION

[0049] The application will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related application, and not to limit the application. In addition, it should be noted that only the parts related to the application are shown in the drawings for ease of description.

[0050] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0051] In view of the one-sided perception, static model and extensive decision-making in traditional groundwater level regulation, the present application provides a groundwater level dynamic regulation method based on digital twinning, taking dynamic permeability coefficient as the core physical parameter and risk quantification closed loop as the decision-making core, and performing in four stages of "data collection→model simulation→regulation and execution→feedback optimization". It can be widely applied to sustainable management of regional groundwater resources (such as groundwater funnel control in North China Plain, paddy field waterlogging control in South China), safety control of urban underground engineering (such as subway tunnel anti-floating, deep and large foundation pit seepage prevention, underground comprehensive pipe gallery deformation control), and regulation and control of special environment groundwater system (such as chemical-hydraulic coupling control in high-salinity and alkaline area).

[0052] To more clearly explain the groundwater level dynamic control method based on digital twins of this invention, the following will be combined with... Figure 1 The steps in the embodiments of the present invention will be described in detail below.

[0053] Before proceeding with the specific implementation of this invention, some core terms involved in this invention will be defined as follows:

[0054] Risk evolution field: In this application, it refers to a four-dimensional dataset containing three-dimensional spatial coordinates and a future time axis, which stores the quantitative value or risk level of one or more key risk indicators predicted by the twin model at each spatiotemporal node.

[0055] Coefficient of variation: In this application, it refers to a standardized statistical index used to measure the relative dispersion of data. In this application, it is used as a comprehensive index to quantify the absolute level (mean) and spatial volatility (standard deviation) of a certain physical field risk. The higher the value, the higher the risk level of the physical field and the uneven spatial distribution, which requires priority intervention.

[0056] Scenario characteristics: In this application, it refers to the specific social, engineering or environmental attributes of the target area, such as whether the area is a "sensitive area for people's livelihood in the city", "ultra-deep foundation pit construction area" or "water source protection area", etc. These attributes will serve as the basis for modifying the control strategy.

[0057] A method for dynamic control of groundwater level based on digital twins according to the first embodiment of the present invention includes steps S100-S600, each step of which is described in detail below:

[0058] S100, the four-dimensional monitoring system collects multi-source monitoring data of the groundwater system in the target area:

[0059] Satellite remote sensing equipment InSAR (Interferometric Synthetic Aperture Radar): Acquires raw data on the rate of surface deformation. (mm / d), reflecting the settlement trend of the mechanical field structure; rainfall intensity P;

[0060] Drone thermal infrared equipment: to obtain soil temperature ( and illumination deviation coefficient (Dimensionless, 0~1), associated thermal field;

[0061] Ground sensor network: collecting shallow water level data (m), structural stress (kPa), ground concentration shallow formation temperature ), shallow pore water pressure ; ground soil moisture content ;

[0062] Downhole intelligent monitoring device: collect deep water level , deep concentration , deep pore water pressure , shallow formation temperature ), supplement the hydraulic field parameters.

[0063] Preferably, the following related basic data also need to be obtained:

[0064] 1) Obtain historical basic data, such as geological drilling data (three-dimensional geological structure and deep lithology distribution), hydrogeological test data (formation compression coefficient , soil saturated concentration , shallow initial permeability coefficient , deep initial permeability coefficient , soil saturated water content Poisson's ratio of rock-soil body , and water level fluctuation data and surface deformation history record in the past 5-10 years, to obtain the initial values including surface deformation, seepage lag time, for model initialization.

[0065] 2) Management constraint data of the target area, such as regional water resources planning documents (such as annual total exploitation limit), underground engineering safety standards (such as anti-floating safety factor ≥1.2, water level fluctuation control threshold ), to obtain deep water level allowed to drop threshold, water level control target value, allowed corrosion rate, and formation allowed effective stress, etc., for constraint conditions of subsequent optimization decision.

[0066] 3) Equipment parameter data: deep pumping area , recharge influence radius ; shallow pumping area , pumping influence radius , pumping pump rated flow , recharge pump rated flow .

[0067] Preferably, the obtained multi-source monitoring data is preprocessed, including the following contents:

[0068] Outlier cleaning: adopt the "three-sigma rule" to filter invalid values such as water level mutation and temperature anomaly caused by sensor failure;

[0069] ​​​Missing value completion: short-term missing values (<2 hours) are interpolated linearly, and long-term missing values (≥2 hours) are completed by an LSTM (Long Short-Term Memory Network) model based on historical sequence prediction;

[0070] Temporal and spatial alignment: all data are unified to the "WGS84 geographic coordinate system UTC timestamp", for example, the quarterly deformation rate data of satellite remote sensing equipment, the hourly thermal infrared data of unmanned aerial vehicles, and the minute-level water level data of intelligent wells are associated through time interpolation to ensure that the spatial position and time node correspond one by one.

[0071] Further preferably, the multi-source monitoring data after preprocessing are cross-scale data mutual calibration, which specifically includes the following contents:

[0072] Macroscopic layer (InSAR data) calibration: using the measured deep water level increment corresponding to the physical settlement model, the original ground deformation rate is corrected, and the noise caused by the change of unconfined aquifer is stripped, and the specific method is:

[0073] According to the increment of the deep water level in the time period , the settlement rate caused by it is calculated:

[0074] ;

[0075] The calibrated ground deformation rate is:

[0076] ;

[0077] Wherein, is the calibrated ground deformation rate ( ), is the collected ground deformation rate, , t is the current time, is the previous 1 hour (m); is the calibration coefficient (obtained by fitting the historical InSAR data and the measured deep water level value, and the preferred value range of this embodiment is ); is the compression layer thickness (m) (wherein, shallow , deep , ) is the stratum compression coefficient (kpa); ;

[0078] Mesoscopic layer (unmanned aerial vehicle thermal infrared data) calibration: correcting the thermal infrared temperature deviation caused by different illumination and ground water content:

[0079] ;

[0080] wherein, is the collected soil temperature of the waterlogged area, is the calibrated soil temperature of the waterlogged area (T ), is the light bias coefficient (real-time collected by the light sensor, the value range is 0-1, representing the maximum temperature deviation caused by light in the completely dry state), is the measured value of the soil water content (%), is the soil saturated water content (%). The calibrated seepage path recognition is more accurate. In some embodiments,

[0081] The calibration method of T is: in sunny and cloudless weather, select a dry bare land and a saturated wet land, measure the unmanned aerial vehicle thermal infrared temperature and the actual contact type thermometer temperature of the two land blocks at the same time when the light is the strongest at noon, is the difference between the two temperatures on the dry land.

[0082] In some embodiments, after the cross-scale data mutual calibration, the data adopts Kalman filtering algorithm, constructs a multi-parameter matrix containing time dimension t and spatial three-dimensional coordinates , generates a spatio-temporal four-dimensional data set, which specifically includes:

[0083] Dynamic parameter field: correct the ground deformation rate , calibrated soil temperature of the waterlogged area , shallow water level , deep water level , shallow pore water pressure , deep pore water pressure , ground Cl- concentration , deep concentration , etc.

[0084] Static parameter library: water density , gravitational acceleration , elastic modulus , normal temperature corrosion rate , formation compression coefficient , soil saturated concentration , thermal expansion coefficient , initial permeability coefficient of shallow and deep layers , , soil saturated water content , etc.

[0085] S200, construct a multi-field dynamic coupling digital twin model, use a multi-dimensional dynamic data set to drive the model for deduction to predict the future spatio-temporal distribution of multi-field parameters, and then quantify the evolution trend of key risk indicators to generate a risk evolution field.

[0086] Preferably, the multi-field dynamic coupling digital twin model is constructed, specifically including the following contents:

[0087] S201, construct a basic control equation based on the basic mechanism of the groundwater system, specifically including:

[0088] The hydraulic field is based on Darcy's law to construct a saturated-unsaturated seepage equation:

[0089] Darcy's law: ; continuity equation: ;

[0090] where q is the seepage velocity ( ); k is the permeability coefficient ( ); is the hydraulic gradient, h is the water level; is the water density ( ), n is the porosity, Q is the source and sink term (pumping / recharge amount); in the shallow state (pumping); in the deep state, (recharge);

[0091] The mechanical field is based on the finite element method to construct a soil constitutive model (such as the Mohr-Coulomb model), and the effective stress principle is used to calculate the soil deformation and structural stress:

[0092] Structural settlement: ; effective stress ;

[0093] where, is the effective stress (kPa); s is the settlement (mm); H is the thickness of the compression layer (m); is the compression modulus (kPa); in the shallow state: ; in the deep state: ;

[0094] The chemical field simulates the influence of Cl⁻ ions on soil permeability and structural corrosion rate through electrochemical corrosion kinetics equation;

[0095] Solute transport equation: ;

[0096] where: C is the solute concentration ( ); D is the dispersion coefficient ( ); R is the chemical reaction term ( ); in the shallow state: in the deep state: ;

[0097] Thermal field, based on heat conduction equation, simulates the influence of water temperature change on water flow viscosity coefficient and chemical reaction rate:

[0098] Heat conduction equation: ;

[0099] Thermal stress equation: ;

[0100] Wherein, E is the elastic modulus of rock-soil body; is the reference temperature (preferably taken as 20°C in the embodiment) ) ; is Poisson's ratio, is the absolute value of temperature deviation, ensuring that the thermal stress is positive; is the volume heat capacity of rock-soil body (J / m3·K) ) ; is the thermal conductivity (W / m·K) ) ; is the heat source term (W / m3) ; shallow layer: ; deep layer: .

[0101] Preferably, the specific numerical value of the static data in the embodiment can be calibrated according to local soil test data, and in the embodiment, only specific numerical values are selected for illustration.

[0102] S202, introduce dynamic coupling coefficient to quantify real-time interaction between fields, multi-field dynamic coupling simulation, including the following contents:

[0103] Chemical and hydraulic coupling: shallow layer Concentration couples hydraulic field by affecting permeability coefficient, and introduces dynamic permeability coefficient of shallow hydraulic field ;

[0104] ;

[0105] Wherein, is the dimensionless influence sensitivity coefficient, representing the sensitivity degree of permeability coefficient to concentration change; is the ground concentration, is the initial permeability coefficient of shallow layer, is the background concentration of shallow layer; is the soil saturated concentration, i.e. the characteristic chloride ion concentration in the shallow layer soil, which can be obtained by soil sample test or historical data statistics.

[0106] Mechanical, thermal and hydraulic coupling:

[0107] The deep lithology is mainly sandstone and limestone, which differs significantly from the seepage characteristics of the shallow silty clay; its dynamic permeability coefficient is independent of... The concentration is not determined by the dynamic influence of deep pore water pressure and formation temperature, but rather by the dynamic permeability coefficient introduced into the deep hydraulic field. ;

[0108] ;

[0109] in, The initial permeability coefficient at depth; The pore pressure sensitivity coefficient characterizes the degree to which permeability changes with effective stress. The temperature sensitivity coefficient characterizes the degree to which the permeability of a hydraulic field changes with temperature. , These are the real-time deep pore water pressure and temperature, respectively. , For reference pore water pressure and temperature.

[0110] Preferably, in the initial model construction stage, in this embodiment, the specific values ​​of the initial values ​​of the key parameters can be initially determined based on local soil test data. The specific method is as follows:

[0111] To ensure a high degree of consistency between the digital twin model and the real physical world, a method for determining multi-field dynamic coupling coefficients based on inversion of historical on-site monitoring data is proposed; the details are as follows:

[0112] Inversion objective: To determine key dynamic coupling coefficients, including but not limited to: Influence sensitivity coefficient ( ), pore pressure sensitivity coefficient ( Temperature sensitivity coefficient ( )wait;

[0113] Required data foundation: Historical monitoring data for at least one complete hydrological year for the target area, including hydrodynamic field data (such as... , ), chemical field data (such as ), mechanical field data (such as ) and thermal field data (such as );

[0114] The inversion method process is used to determine the sensitivity coefficient of Cl⁻ influence. For example:

[0115] Data filtering and matching: From the historical database, filter out N sets of data that correspond in time. , Data pairs. Among them, is the equivalent permeability coefficient of the shallow aquifer in this period, which can be obtained by the water level change data and pumping capacity data in this period according to Darcy's law;

[0116] An inversion optimization model is established: the determination of the coupling coefficient is converted into a nonlinear optimization problem, and the goal is to find the optimal , so that the overall error between the permeability coefficient calculated by the model and the equivalent permeability coefficient calculated on site is minimized;

[0117] Define the objective function, and construct the least squares objective function:

[0118]

[0119] Where n = 1... N; is the shallow background concentration;

[0120] Solve the optimal solution: use optimization algorithms (such as Levenberg-Marquardt algorithm or particle swarm optimization algorithm) to iteratively solve the objective function, and when the objective function J reaches the minimum value, the corresponding value is the optimal sensitive coefficient obtained by inversion of field data.

[0121] Similarly, this inversion method can be applied to the determination of other coupling coefficients, and when , , data pairs are selected based on the formula:

[0122] Construct the objective function and solve it.

[0123] As an option, a single numerical value is selected as the initial value in this embodiment for illustration, and the shallow = 0.5; = 200 mg / L, , .

[0124] In this embodiment, by setting the lower limit of the permeability coefficient (taking ), the physical contradiction that the concentration is too high to cause the sensitive coefficient to approach 0 is avoided (soil pores will not be completely closed, and the permeability coefficient has a minimum value). Thermal and chemical coupling: temperature couples the chemical field by affecting the corrosion rate, and introduces shallow and deep layer temperature to accelerate the corrosion rate ,

[0125] : ​​​

[0126] ;

[0127] ;

[0128] in, , The shallow and deep layers are respectively at the reference temperature ( The corrosion rate at room temperature under normal conditions; the shallow temperature-accelerated corrosion rate is related to the calibrated soil temperature monitored by the UAV, and the shallow temperature-accelerated corrosion rate is related to the deep formation temperature monitored downhole. Shallow temperature corrosion coefficient, The deep-layer temperature corrosion coefficient characterizes the effect of temperature on the chemical field reaction rate. The initial values ​​in this example are for the shallow layer. =0.1 deep = .

[0129] Hydraulic field and mechanical field (coupling of pore water pressure and effective stress): Changes in pore water pressure directly alter the effective stress. Formula: ;

[0130] The effective stress change This refers to the change in pore water pressure. When a control operation (pumping / recharge) is performed, the pore water pressure will change, resulting in a change in pore water pressure, which in turn changes the effective stress, causing changes in settlement and altering the mechanical field, thus triggering new control decisions.

[0131] S203, Numerical Iteration and Risk Prediction: This method utilizes a multidimensional dynamic dataset to drive model derivation, employing finite element software (such as COMSOL) for spatiotemporal iterative calculations. With a time step of 1 hour, iterates at least 24 times to solve multiple field control equations, predicting the future spatiotemporal distribution of multiple field parameters. The predicted values ​​of physical field parameters for the next 24 hours are output (time resolution 1 hour, spatial resolution...). Hydraulic field: water level Mechanical field: effective stress Thermal field: thermal stress Chemical field: concentration Corrosion rate The above predicted values ​​include both shallow and deep layers.

[0132] During the iteration process, with The sensitivity coefficient, pore pressure sensitivity coefficient, temperature sensitivity coefficient, and temperature corrosion coefficient are the core coupled variables, which drive each other to update.

[0133] In this embodiment, the convergence condition is the change in water level over adjacent time steps. , stress variation amount , and the convergence is determined.

[0134] S204, quantize the evolution trend of the key risk indicators, and generate a risk evolution field, specifically:

[0135] 1) Map the predicted physical field parameters to independent risk evaluation values:

[0136]

[0137] wherein, is the parameter value of the i-th field at the j-th monitoring point; is the safety interval of the i-th field parameter; is the limit threshold of the i-th field parameter (exceeding which =1), and the safety interval is set for shallow / deep parameters respectively.

[0138] Preferably, i=h represents the hydraulic field, i= represents the mechanical field, i=v represents the chemical field, represents the thermodynamic field, and when there are more than one risk indicators under a physical field, the risk evaluation is performed on the risk indicators respectively, and the maximum value of the two indicators is taken as the independent risk evaluation value of the physical field. For example: i=v corresponds to the chemical field, and the core risk indicators are concentration and corrosion rate, and the independent risk evaluation values of the two parameters are calculated respectively, and the maximum value of the two indicators is taken, that is, as long as concentration and corrosion rate exceed the limit, the risk of the chemical field is high.

[0139] 2) Map the dimensionless independent risk evaluation values to levels, as shown in Table 1, to solve the problems of abstract evaluation value, poor visualization, and non-comparison between fields in the prior art, and through spatial interpolation (Kriging interpolation method), the risk levels of discrete monitoring points are extended to continuous spatio-temporal distribution field, forming a three-dimensional risk evolution model of “location-time-risk level”.

[0140] Table 1

[0141]

[0142] S300, calculate the variation coefficient of each physical field based on the risk evolution field, and dynamically assign decision weights to each field based on the variation coefficient and the scene characteristics of the target area to generate a comprehensive risk value, specifically including the following steps:

[0143] S301, variation coefficient calculation: for each physical field in the risk evolution field, the independent risk evaluation values of all monitoring points of the physical field are counted respectively, and the average value of the risk value of the physical field is calculated​ and standard deviation ;

[0144] = / ;

[0145] Obtain the coefficient of variation of the physical field ; the coefficient of variation is high, indicating that the physical field has high average risk level and high spatial heterogeneity at the same time, and is the key field that needs to be intervened first.

[0146] S302, dynamically allocate basic weights based on the coefficient of variation, and modify them combined with the scene characteristics (such as urban life-sensitive areas) to ensure that high-risk fields and life-related fields are prioritized for regulation:

[0147] Basic weight calculation (coefficient of variation -> basic weight):

[0148] ;

[0149] Scene modification (basic weight -> maximum weight):

[0150] ;

[0151] In the formula, is the scene correction coefficient of the ith physical field, and the maximum weight is passed to the comprehensive risk calculation.

[0152] If the target area is a coastal area, = 1.2, based on the corrosion accident rate statistics of the coastal area up by 20%, if the target area is a city area, and is a city life-sensitive area (such as an old city area) = 1.2, = , = 1, based on the weight of the water field (to prevent foundation settlement) and the mechanical field (to prevent building cracking) up.

[0153] Preferably, a hierarchical importance coefficient is introduced, such as a shallow life area = 1.2, a deep engineering area .

[0154] S303, calculate the comprehensive value of multi-field risk, and determine the risk level:

[0155] ;

[0156] Wherein, is the average independent risk evaluation value of a single field, .​​

[0157] The coefficient of variation is a normalized, dimensionless measure of dispersion that can eliminate the incomparability of different physical fields (such as temperature and stress) due to different dimensions and numerical scales, thereby making the weight allocation based on the volatility of the risk space more fair and accurate, which cannot be achieved by using absolute dispersion indicators such as standard deviation or variance alone.

[0158] As can be understood by those skilled in the art, by using the average risk value for both the calculation of the coefficient of variation and the weighted summation of the comprehensive risk value, the method of the present application can realize a dynamic decision priority ranking that is highly sensitive to the risk pattern. This mechanism not only focuses on the average level of risk, but also prioritizes responding to physical fields with extremely uneven spatial distribution (high standard deviation) or local anomalies in the overall low-risk background (low average value leading to high coefficient of variation), thereby achieving early warning and precise intervention of potential risk points, and avoiding the decision lag or misjudgment that may be caused by traditional weighting methods.

[0159] S400, matching the comprehensive risk value with the risk warning threshold to determine the risk assessment result; generating a collaborative regulation instruction for the shallow and deep aquifers according to the risk assessment result.

[0160] S401, matching the comprehensive risk value with the risk warning threshold to determine the risk assessment result, including the comprehensive risk level, the risk area and the key control indicators, if a high risk level or a medium risk level appears, starting the layered regulation; otherwise, maintaining the status quo.

[0161] In some embodiments, three risk warning thresholds (0.3, 0.6, 0.8) are set according to the water level deviation and the allowable deviation, and the comprehensive risk level is divided as shown in Table 2 to assist in locating the high-risk area (such as "the southeast corner of the foundation pit is determined as a high-risk area due to high Cl⁻ concentration and sudden increase of the hydraulic variation coefficient").

[0162] Table 2

[0163]

[0164] The comprehensive risk value is the weighted summation result of the risk evaluation values of each physical field, and the threshold range thereof is different from that of the single-field risk evaluation value due to the weight allocation.

[0165] Preferably, before generating a collaborative regulation instruction for the shallow and deep aquifers according to the risk assessment result, it is determined to start the layered regulation, which specifically includes the following contents:

[0166] The comprehensive risk value is matched with the risk warning threshold to determine the comprehensive risk level, the comprehensive severity of the global risk is determined based on the comprehensive risk level, and it is determined whether global regulation is needed and the corresponding regulation intensity; based on the risk level of a single field, the priority of regulation is determined; the specific regulation parameters are determined by combining the single field risk level with the comprehensive risk level. For example = 0.7 (medium risk), hydraulic field 3, mechanical field 5, then regulation is needed, and deep recharge is preferentially started (to prevent mechanical field 5 settlement), and then shallow pumping is adjusted (to control hydraulic field 3 water level).

[0167] In this embodiment, the corresponding regulation intensity is determined based on the comprehensive risk level, specifically as follows:

[0168] The comprehensive risk level is low risk, indicating that the global risk is not over standard but needs to be vigilant, and full-load regulation is not needed; the comprehensive risk level is high risk, indicating that the global risk is on the verge of losing control, and full-load rapid intervention is needed; the comprehensive risk level is high risk, indicating that the global risk has lost control, and intervention beyond the design load is needed.

[0169] Based on the risk level of a single field, the priority of regulation is determined, and the specific rules are as follows:

[0170] Difference in level When the level difference is 1, the higher level field regulation resource proportion ;

[0171] Difference in level When the level difference is 1, the higher level field regulation resource proportion ;

[0172] The risk level of the livelihood sensitive area (old city area, school) is even low by 1 level, and each of the high risk level fields accounts for 50% of the resources.

[0173] Preferably, the regulation details are corrected based on the scene characteristics of the target scene, as shown in Table 3, and the time, range, and emergency plan are adjusted.

[0174] Table 3

[0175]

[0176] S402, cooperative regulation instructions are generated for shallow and deep aquifers, specifically including:

[0177] 1) Shallow pumping instruction (hydraulic field regulation):

[0178]

[0179] Wherein, is the dynamic permeability coefficient, is the current shallow water level; is the shallow water level target value; 、 is the shallow pumping area, and the pumping influence radius; is the hysteresis compensation coefficient, based on the feedback seepage hysteresis time fitting, seepage hysteresis time is calculated by the time difference between the pumping instruction issuing time and the peak time of the water level response curve, and is used to actively offset the seepage hysteresis effect; pumping flow needs to be combined with the shallow hydraulic field dynamic permeability coefficient , water level deviation and seepage hysteresis compensation to avoid water level overshoot.

[0180] In some embodiments, such as 2h, then = 0.04. is the hydraulic field level coefficient, and the system matches the risk level corresponding to the physical field in Table 1 according to and assigns an initial value from a preset mapping table. Specifically: the corresponding risk level is level 1, = 0.1; the corresponding risk level is level 2, = 0.3; the corresponding risk level is level 3, = 0.5; the corresponding risk level is level 4, = 0.8; the corresponding risk level is level 5, = 1.1.

[0181] 2) Deep recharge instruction (mechanical field regulation):

[0182] ;

[0183] ;

[0184] wherein, is the deep water level allowable decline threshold; is the settlement compensation coefficient (based on recharge data fitting, empirical value 0.5~0.8, adjusted based on subsequent feedback settlement data); is the deep pore water pressure, is the deep pore water pressure target value. 、 is the deep recharge area, and the recharge influence radius; recharge amount needs to compensate for the deep water level decline caused by shallow pumping to avoid ground subsidence; is the vertical distance from the wellhead of the recharge well to the center of the aquifer, is the frictional resistance coefficient (0.02-0.03 for steel pipes), L is the length of the pipeline (m), D is the pipe diameter (m), V is the recharge flow rate (m / s), and (e.g. = 0.025, L = 100 m, d = 0.2 m).

[0185] The calculated recharge pressure is used to check whether the selected recharge pump meets the requirements and serves as the upper limit of the safety monitoring of the device operation.

[0186] In the present embodiment, is the mechanical field level coefficient, and the system assigns an initial value to it according to the risk level corresponding to the physical field in Table 1 and from a preset mapping table. Specifically, the initial value is: corresponding to the risk level is level 1, = 0.1; corresponding to the risk level is level 2, = 0.3; corresponding to the risk level is level 3, = 0.5; corresponding to the risk level is level 4, = 0.8; corresponding to the risk level is level 5, = 1.1.

[0187] Preferably, the control instruction is transmitted to an execution unit to control the water level of the water pumping pump and the recharge pump.

[0188] Preferably, after the control instruction is generated, a feedback step is further included, specifically including:

[0189] The feedback data after the execution of the instruction is collected, and the model parameters are optimized through a double-level closed-loop feedback mechanism to form a closed-loop control; wherein the first loop calculates the parameters of the control instruction through parameter calibration, and the second loop optimizes and updates the core physical parameters in the digital twin model through a field data inversion method; when the deviation between the feedback data and the predicted data at the corresponding time node in the risk evolution field exceeds a preset deviation threshold, the second loop is started.

[0190] S501, collecting feedback data after the execution of the instruction, including device control instructions, control logs, field measurement data (water level, pore water pressure, ground deformation, and operating energy consumption within 1-24 hours after the execution of the instruction), and device operation state feedback.

[0191] The field measurement data includes actual pumping and drainage flow , actual recharge amount , water level after control , concentration after control ​​; corrosion rate after regulation ; thermal stress after regulation , pore water pressure after regulation ; and based on the thermal stress after regulation and pore water pressure after regulation obtain effective stress after regulation .

[0192] After the output of the regulation instruction, the specific instruction generated is added to the simulation calculation as a new boundary condition or source-sink term, and the model is again deduced for a future period of time (such as 72 hours) to see how the various physical fields should respond under strict implementation of this new instruction, updating the predicted values as target values:

[0193] Hydraulic field: water level ; mechanical field: effective stress ; thermodynamic field: thermal stress ; chemical field: concentration , corrosion rate ; the above predicted values include shallow and deep layers.

[0194] The equipment control instruction contains three types of core instructions:

[0195] Pumping / Recharge Wells: Target Flow Rate (Q), Start / Stop Time (e.g., 8:00-16:00 operation); Valve Regulation: Target Opening Degree (%), Adjustment Frequency (e.g., fine adjustment every 30 minutes), Maximum Engineering Allowable Error;

[0196] Emergency Instructions: When the risk level suddenly rises to "high", trigger the emergency instruction "maximum pumping + backup pump start".

[0197]

[0198] The regulation log includes the recording of instruction generation time, basis (e.g., "based on the risk evolution field at 8:00, the water level in A irrigation area is lower than 25m, start No. 2 recharge well"), and initial state of the execution unit, facilitating subsequent tracing and feedback optimization.

[0199] S502, optimize model parameters through a double-level closed-loop feedback mechanism:

[0200] 1) Calculate the single-field deviation of feedback data and the target data predicted at the corresponding time node in the risk evolution field.

[0201] Calculate single-dimensional deviation:

[0202] Water level deviation: ; Concentration deviation: ;

[0203] Thermal stress deviation:​ ; mechanical field deviation: .

[0204] Similarly, for other physical fields, the corresponding absolute error can also be defined. In multi-physical field coupling regulation, if the absolute error of different dimensions needs to be comprehensively evaluated, it can be standardized or introduced weight, but in precision regulation, usually more emphasis is placed on directly comparing the absolute error of each physical field with the respective engineering allowable error range.

[0205] Convert the absolute error to a dimensionless normalized value to represent the severity of the deviation relative to the allowable range:

[0206] ;

[0207] Where: The normalized deviation degree of the i-th physical field, The engineering allowable error of the i-th physical field (such as = 0.01m).

[0208] 2) Start a double-level closed-loop feedback mechanism:

[0209] The first level refers to the instruction feedback loop (reverse regulation): this loop aims to quickly respond to transient deviations and directly adjust the calculation parameters in the regulation instruction generation formula without changing the digital twin model itself. Its update frequency is high, usually evaluated every regulation period (for example, every hour):

[0210] 1) Update of the lag compensation coefficient:

[0211] Update the seepage lag time, based on the water level change curve of the field feedback, and through signal processing methods (such as cross-correlation analysis) to calculate a new seepage lag time , and then update the lag compensation coefficient:

[0212] ; Where, is an empirical coefficient, for example, 0.02. This is a direct update, using the newly observed physical properties to overwrite the old values.

[0213] 2) Update of the scene correction coefficient:

[0214] If the regulation effect of a specific scene (such as a livelihood sensitive area) is not good, such as ground subsidence, water level fluctuation, etc. Data has not met the standard for more than 1 regulation period), it indicates that the scene correction coefficient is set improperly and needs to be adjusted; for example, if the mechanical field risk control in the livelihood sensitive area is not ideal, adjust the mechanical field scene correction coefficient under the livelihood sensitive area:

[0215] ; wherein, is an empirical coefficient, for example 0.2, which can automatically increase the attention to the key field (such as the mechanical field) when the total risk prediction is low.

[0216] 3) Dynamic self-adaptive adjustment of the grade coefficient (G) , , which eliminates the static error, and the specific method is:

[0217] iterative fine-tuning is performed using the proportional-integral (PI) control idea:

[0218] ;

[0219] ;

[0220] wherein, is the initial grade coefficient of the shallow hydraulic field and the grade coefficient of the mechanical field, , is a preset proportional adjustment gain, is a preset integral adjustment gain; wherein is the time step of the control period, which is 1 hour in the present embodiment, represents the cumulative amount of error in the just past time step.

[0221] Output: updated instruction calculation parameters , , , , The instruction generation will be immediately used for the next control period, realizing fast closed-loop correction.

[0222] Preferably, if the current fine-tuning amplitude of the grade coefficient is much smaller than the minimum flow adjustment accuracy of the pumping station, the default is not to update and not to output adjustment.

[0223] In the iterative fine-tuning process, only when the single-dimension deviation of "2 consecutive control periods (1 period = 24h) ≥ ", the integral term is activated; otherwise, the integral term is zeroed and only the proportional term is retained.

[0224] Further preferably, in the present embodiment, the proportional adjustment gain and the integral adjustment gain are dynamically adjusted according to the risk grade; the dynamic adjustment satisfies the following rules: a smaller parameter is used for low risk or safety grade (preferably stable, avoiding overshoot); a larger parameter is used for medium or high risk grade (preferably fast response, suppressing risk); and the parameter of the people's livelihood sensitive area is 20% higher than that of the ordinary area under the same grade (preferably preventing settlement or sudden surge).

[0225] The second level is the model evolution loop (data inversion): this loop aims to solve the systematic bias of the model itself, by periodic (e.g., weekly or monthly) data inversion, optimizing the core physical parameters of the digital twin model, and realizing the self-evolution of the model.

[0226] The system presets the engineering allowable error of each key physical field (e.g., water level allowable error of ±0.01 m, i.e., 1 cm). When the absolute error of any key physical field continuously or significantly exceeds its corresponding preset allowable error threshold (or a portion of the allowable error threshold, such as 50% ), the system determines that there is a systematic error in the current model or a significant change in the external environment, and then starts the model evolution loop. At this time, the system will use the latest monitoring data to iteratively update and correct the core physical parameters (such as permeability coefficient, initial condition, boundary condition, etc.) of the model through inversion algorithms to make the model prediction more consistent with reality. If the absolute error of all key physical fields is within the allowable error threshold, the model evolution loop is not started, and the model parameters remain unchanged.

[0227] Preferably, the model evolution loop is started, specifically:

[0228] Collect historical feedback data within a period, and the inversion process uses the method described in S202 of the present application based on historical monitoring data and least squares optimization, taking the measured data within a new period as input to re-solve the core physical parameters such as sensitivity coefficient , , , , , etc., to realize the iterative evolution of the model. For example: if long-term monitoring finds that the predicted bias of deep permeability coefficient exceeds 5%, re-inversion , is performed to update the dynamic permeability coefficient of the deep water field in the formula, realizing the fundamental evolution of the model.

[0229] Below, taking a deep foundation pit project (excavation depth 28m) of a certain subway line 2 station in a certain city as the target area, combined with actual engineering parameters and monitoring data, the underground water level dynamic regulation method of the present application is described in detail. The foundation pit is located in an old urban area, surrounded by 50m of Minsheng sensitive buildings, the site has complex geology, shallow layer mainly layer miscellaneous fill and layer silty clay, poor permeability and high sensitivity; the deep layer is a confined aquifer with hydraulic connection to the foundation pit; the main risks faced by the project are: excessive ground settlement and pit bottom uplift caused by improper dewatering.

[0230] The regulation method of the embodiment is executed in five stages of "data collection → model construction (including coupling coefficient inversion) → risk quantification (including coefficient of variation weight) → regulation execution → double-level feedback", and the specific data and operation of each step are as follows:

[0231] S100: Multi-source monitoring data collection and preprocessing;

[0232] The monitoring data of 72 hours in June 2024 (flood season) is collected, as follows:

[0233] Satellite remote sensing: =0.8mm / d, P=8mm / d;

[0234] Unmanned aerial vehicle thermal infrared: , ;

[0235] Ground sensor network (20 monitoring points are laid out): 11.8-12.3m (average 12.05m), 120-150kPa (peripheral old building foundation stress), 330-370mg / L (average 350mg / L), 30-33 (average 31.5 ), 118-125kPa (average 121kPa);

[0236] Underground intelligent monitoring equipment (3 monitoring wells, depth 60m): 45-47m (average 46m), 480-520mg / L (average 500mg / L), 175-185kPa (average 180kPa), 23-24 (average 23.5 ).

[0237] Data preprocessing: 1 group of abnormal water level data ( =8.5m, judged as sensor failure) is removed by using criteria, 2 hours of missing concentration data is completed by using LSTM model, and finally a spatio-temporal four-dimensional data set of "WGS84 coordinate system + UTC timestamp" is formed.

[0238] S200: Multi-field dynamic coupling model construction (including dynamic coupling coefficient inversion);

[0239] S201: Construction of basic control equation;

[0240]

[0240] Hydraulic field, mechanical field, chemical field, and thermal field basic equations are the same as the original theoretical framework, and regional parameters (derived from geological survey reports and historical monitoring data) are substituted into them, including: = m / d, =8× m / d, =8000kPa, =600mg / L, =180kPa, .

[0241] S202: Dynamic coupling coefficient inversion;

[0242] 1) For key coupling coefficients , , , use the historical data of the complete hydrological year (June 2023-May 2024) in 2023 to invert:

[0243] Inversion : Select 30 groups of , } data pairs, where is calculated by Darcy's law (e.g., in August 2023: from 12.5m to 11.8m, pumping capacity =20 / d, and the calculated value =2.2× m / d);

[0244] Inversion , : Select 25 groups of , , } data pairs, with a calculated value range of 7.5× ~8.5× m / d.

[0245] 2) Objective function construction and solution:

[0246] Inversion , the objective function is:

[0247] ;

[0248] where is the background concentration, and the particle swarm optimization (PSO) algorithm is used for iterative solution. When reaches the minimum value, the value of =0.045L / mg is obtained;

[0249] Similarly, the inverse is derived , .

[0250] 3) Dynamic coupling equation update:

[0251] Shallow permeability coefficient substitution = 350 mg / L:

[0252] ;

[0253] Deep permeability coefficient substitution = 180 kPa, 23.5 :

[0254] .

[0255] S203: Risk evolution field generation:

[0256] Using COMSOL software, with a time step of 1 hour, iterating 24 times, to predict the physical field parameters in the next 24 hours:

[0257] Hydraulic field: predicted water level in shallow layer = 11.9-12.4 m, predicted water level in deep layer = 45.8-46.2 m; Mechanical field: predicted effective stress = 142 kPa ( kPa, total stress determined by geological conditions, short-term unchanged; = 322-180 kPa), predicted settlement = 0.3-0.5 mm / d; Chemical field: predicted shallow concentration = 340-360 mg / L, predicted corrosion rate = 0.02-0.03 mm / year; Thermal field: predicted shallow temperature = 31-32℃, predicted thermal stress = 5-8 kPa.

[0258] S300: Variance coefficient weight distribution and comprehensive risk value calculation:

[0259] 1) Calculate independent risk evaluation value and coefficient of variation;

[0260] According to the safety threshold of each physical field (such as the safety interval of shallow water level [10, 13] m, the limit threshold 8 m), the independent risk evaluation value of 20 monitoring points is calculated , and the mean value and standard deviation are calculated to calculate the coefficient of variation As shown in Table 4:

[0261] Table 4

[0262]

[0263] 2) Assign dynamic weights;

[0264] Basic weight calculation: ;

[0265] Hydraulic field: 0.286 / 1.242 0.230; Mechanical field: 0.429 / 1.242 0.345; Chemical field: 0227 / 1.242 0.183; Thermal field: 0.3 / 1.242 0.242;

[0266] Scene correction: Because the foundation pit is located in the sensitive area of Minsheng, the scene correction coefficient of hydraulic (to prevent sudden settlement caused by water level drop) is 1.25, the mechanical (correction of old building cracking) is 1.2, the chemical is 1, and the thermal is 1, the maximum weight is: ;

[0267] Hydraulic field:

[0268] ; Mechanical field: ; Chemical field: ; Thermal field: ;

[0269] Comprehensive risk value calculation:

[0270] .

[0271] S400: Generate control instructions:

[0272] According to the risk threshold (safe , low risk 0.3-0.6), =0.302 is determined as low risk level, shallow water level needs to be maintained to prevent and control the risk of sudden surge in high water period, and control instructions are generated:

[0273] Shallow layer pumping instruction:

[0274] ;

[0275] Substitute parameters: =0.3 (the risk level of the water field is 2), = 500 (pumping area), , = 11.5 m (target water level), = 20 m (influence radius), = 0.05 (hysteresis compensation coefficient), ;

[0276] (i.e. ); conventional large-flow pumps cannot meet the fine-tuning requirements, and small precise water pumps are actually used, with a precision of , only when the flow changes , the pump can be stable.

[0277] Deep recharge instruction: maintain stable deep pore water pressure, recharge = .

[0278] , , (in line with the measured ), ; ;

[0279] S500: double-level closed-loop feedback optimization;

[0280] 1) After 24 hours of instruction execution, collect measured data:

[0281] Within 72 hours after the instruction is executed, the system continuously monitors the changes in each physical field at high frequency (e.g., every 15 minutes). Due to the target soil layer being extremely poor permeability silty clay, the hydraulic field responds very slowly, which is an expected phenomenon consistent with physical laws.

[0282] Based on the parameters of , the multi-field coupling model predicts that after 72 hours of executing the instruction, the water level should drop to 12.043 m (predicted drop of 7 mm);

[0283] After 72 hours, the system found that:

[0284] The shallow water level synchronously dropped from 12.05 m to 12.045 m (the response peak appeared 3 hours after the instruction was issued), and at the same time, the mechanical field monitoring found that the deformation rate of the containment structure slowed down by 0.02 mm / d, proving that the micro-pumping played a positive role in stabilizing the earth pressure.

[0285] The system calculates the error between the predicted value and the actual value, the water level deviation:

[0286] = 12.045 - 12.043 = 0.002m; = 0.2;

[0287] 2) Double-level feedback optimization:

[0288] Conclusion: = 0.002m = 0.01m) (maximum allowable deviation), not reaching the trigger adjustment threshold, not starting the "model evolution ring" (no need to update the coupling coefficient by inversion).

[0289] "Instruction feedback ring" adjustment:

[0290] Update the lag compensation coefficient (based on cross-correlation analysis) = 3h, = 0.06), without changing the recharge amount (still 0) (original = 0.05, because the delay is prolonged, the compensation coefficient needs to be increased to avoid lagging water level overshoot);

[0291] The control effect meets the standard, the scene does not change, and the ;

[0292] As an example, in the present embodiment, it is set as shown in Table 5.

[0293] Table 5

[0294]

[0295] Further preferably, the above learning parameters are all based on conventional values of engineering practice, which can be adjusted according to the requirements of the target area.

[0296] Under the condition that the comprehensive risk value and risk level do not change, in the present control period, since it is the first time to deviate, the integral term is simplified to the for calculation, we can get:

[0297] ;

[0298] The purpose of PI fine-tuning is to "optimize the control accuracy", but it needs to meet the "adjustment has a perceptible impact on the actual control effect", the current fine-tuning amplitude is the change amount ( Based on the change from , the change amount is less than the minimum flow regulation accuracy of the pumping pump (the conventional pumping pump accuracy is ), and it is not updated; the recharge amount is still 0, and the change is less than the minimum flow regulation accuracy of the pumping pump, so it is not updated .

[0299] Implementation effect verification: through dynamic coupling coefficient inversion, coefficient of variation weight, double-level feedback, realize: shallow water level is stable at 11.5-11.7m, fluctuation range ; The settlement of the surrounding old building is controlled at 0.3-0.35mm / d, which is far lower than the specification limit of 1mm / d; The corrosion rate is maintained below 0.02mm / year, meeting the engineering durability requirements.

[0300] Finally, the goal of "minimizing regulation cost and ensuring maximum engineering safety" is achieved, providing a practical technical paradigm for groundwater level regulation in complex scenarios such as deep foundation pits in old urban areas and sensitive areas of people's livelihood.

[0301] Although the steps in the above examples are described in the order described above, those skilled in the art can understand that, in order to achieve the effects of the present embodiment, the different steps do not have to be executed in this order, they can be executed simultaneously (in parallel) or in reverse order, and these simple changes are within the scope of the present application.

[0302] The second embodiment of the present application is a digital twin-based dynamic groundwater level regulation system, which comprises:

[0303] A data acquisition module configured to acquire multi-source monitoring data of a target area groundwater system and construct a multi-dimensional dynamic data set containing hydraulic, mechanical, chemical and thermal parameters;

[0304] A twin simulation and prediction module configured to construct a multi-field dynamic coupling digital twin model, drive the multi-field dynamic coupling digital twin model with the multi-dimensional dynamic data set for simulation, simulate the state response of the groundwater system under the influence of multi-field interaction, predict the future spatio-temporal distribution of multi-field parameters, and further quantify the evolution trend of key risk indicators to generate a risk evolution field;

[0305] A data processing module configured to calculate the coefficient of variation of the risk value of each physical field based on the risk evolution field, and dynamically allocate decision weights to each physical field based on the coefficient of variation and the scene characteristics of the target area to generate a comprehensive risk value;

[0306] A hierarchical regulation module configured to match the comprehensive risk value with a preset risk warning threshold to determine a risk assessment result, and generate a coordinated regulation instruction for the shallow and deep aquifers according to the risk assessment result.

[0307] Preferably, the system further comprises a feedback optimization module configured to collect feedback data after the execution of the instruction, optimize the calculation parameters of the regulation instruction and the core physical parameters of the digital twin model through a double-level closed-loop feedback mechanism, and form a closed-loop regulation.

[0308] Further preferably, the feedback optimization module specifically comprises:

[0309] a physical model calibration unit configured to be started when the comprehensive deviation exceeds a preset deviation threshold, periodically collect historical monitoring data in a regulation period, and optimize and update core physical parameters in the digital twin model by a data inversion method, the core physical parameters being at least one dynamic coupling coefficient, to realize periodic learning and evolution of the model;

[0310] a prediction model optimization unit configured to quickly adjust calculation parameters of the regulation instruction according to real-time deviations of the measured physical quantity and the predicted data in the feedback data, to real-time correct and ensure accurate execution of the instruction; the calculation parameters including a lag compensation coefficient and a level coefficient.

[0311] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related description of the above-described method can refer to the corresponding process in the foregoing system embodiments, which will not be repeated here.

[0312] It should be noted that the above-described digital-twin-based groundwater level dynamic regulation method and system provided by the embodiments are only exemplified by the division of the above-described functional modules, and in actual application, the above-described functions can be completed by different functional modules according to needs, that is, the modules or steps in the embodiments of the present application are further decomposed or combined, for example, the modules of the above-described embodiments can be combined into one module, or can be further split into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present application are only for distinguishing the modules and steps, and should not be considered as an improper limitation of the present application.

[0313] A device of the third embodiment of the present application comprises:

[0314] at least one processor;

[0315] and a memory in communication connection with the at least one processor;

[0316] wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to realize the above-described digital-twin-based groundwater level dynamic regulation method.

[0317] A computer readable storage medium of the fourth embodiment of the present application, the computer readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to realize the above-described digital-twin-based groundwater level dynamic regulation method.

[0318] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the storage device and the processing device described above and the related descriptions can refer to the corresponding processes in the foregoing method embodiments, and will not be described here again.

[0319] Reference will be made to the following Figure 2 , which shows a structural schematic diagram of a computer system of a server for implementing the system, method and electronic device embodiments of the present application. Figure 2 The server shown is merely an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0320] As Figure 2 shown, the computer system includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 202 or loaded from a storage portion 208 into a random access memory (RAM) 203. In the RAM 203, various programs and data required for system operation are also stored. The CPU 201, the ROM 202 and the RAM 203 are connected to each other through a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0321] The following components are connected to the I / O interface 205: an input portion 206 including a keyboard, a mouse, etc.; an output portion 207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 208 including a hard disk, etc.; and a communication portion 209 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication portion 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as necessary. A removable medium 211 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 210 as necessary, so that a computer program read therefrom is installed into the storage portion 208 as necessary.

[0322] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 209, and / or installed from the detachable medium 211. When the computer program is executed by the central processing unit (CPU) 201, the above-described functions defined in the methods of the present application are executed. It should be noted that the computer readable medium of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable program code is carried. Such a propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the above.

[0323] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0324] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0325] The terms “first”, “second”, etc., are used to distinguish similar objects, not to describe or indicate a specific order or sequence.

[0326] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent in such process, method, article, or apparatus / device.

[0327] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A digital twin-based underground water level dynamic regulation method, characterized in that, The method comprises the following steps: Collecting multi-source monitoring data of the groundwater system in the target area, and constructing a multi-dimensional dynamic data set; Constructing a multi-field dynamic coupling digital twin model, and driving the model with the multi-dimensional dynamic data set to predict the future spatio-temporal distribution of multi-field parameters, and then quantize the evolution trend of key risk indicators to generate a risk evolution field; Based on the risk evolution field, the variation coefficient of the risk value of each physical field is calculated, and the decision weight of each physical field is dynamically allocated based on the variation coefficient and the scene characteristics of the target area to generate a comprehensive risk value; Matching the comprehensive risk value with the risk warning threshold to determine the risk assessment result; according to the risk assessment result, the collaborative control instructions are generated for the shallow and deep aquifers respectively; Wherein, the method for constructing the multi-field dynamic coupling digital twin model is: A multi-field dynamic coupling model including a hydraulic field, a mechanical field, a chemical field and a thermal field is constructed, and the mutual influence between at least two physical fields is quantified and updated in real time by introducing a dynamic coupling coefficient; wherein the hydraulic field parameters include shallow water level and deep water level, the mechanical field parameters include structure settlement and effective stress, the chemical field parameters include corrosion rate, and the thermal field parameters include thermal stress; the dynamic coupling coefficient includes influence sensitive coefficient, pore pressure sensitive coefficient, temperature sensitive coefficient and temperature corrosion coefficient.

2. The groundwater level dynamic regulation method based on digital twinning according to claim 1, characterized in that, Collecting multi-source monitoring data of the groundwater system in the target area, including: The target area is monitored by a satellite remote sensing device, a UAV thermal infrared device, a ground sensor network and an underground intelligent monitoring device to obtain multi-source and multi-scale monitoring data of the target area; wherein the satellite remote sensing device obtains original surface deformation rate data, the UAV thermal infrared device obtains soil temperature and illumination deviation data, the ground sensor network obtains water level, structural stress, water quality parameter, formation temperature and soil moisture content data, and the underground intelligent monitoring device obtains pore water pressure and deep water level data; the water quality parameter includes pH value and concentration. Concentration.

3. The groundwater level dynamic regulation method based on digital twinning according to claim 1, characterized in that, Updating the mutual influence between the two physical fields, specifically: according to the simulation output result of one physical field, dynamically updating the key model parameters of another physical field; The update includes at least one of the following: According to the simulation results of solute concentration in the chemical field, the permeability coefficient value of the shallow aquifer is updated by using The sensitive coefficient update influences the permeability coefficient value of the shallow aquifer; According to the simulation result of the pore water pressure of the mechanical field, the permeability coefficient value of the deep aquifer is updated by using the pore pressure sensitivity coefficient and the temperature sensitivity coefficient; According to the temperature simulation result of the thermal field, the chemical reaction rate value of the chemical field is updated by using the temperature corrosion coefficient.

4. The groundwater level dynamic regulation method based on digital twinning according to claim 1, characterized in that, The generation of the comprehensive risk value specifically includes: For the state of the hydraulic field, the mechanical field, the chemical field and the thermal field in the risk evolution field, the independent risk evaluation value of each field at all monitoring points is counted respectively; Calculate the mean and standard deviation of the independent risk evaluation value of each physical field, and obtain the variation coefficient of each physical field based on the mean and standard deviation; According to the variation coefficient of each physical field, the basic decision weight is allocated in proportion, wherein the physical field with higher variation coefficient is allocated with larger basic decision weight; Combine the scene characteristics of the target area to correct the decision weight; Calculate the average independent risk evaluation value of each physical field, and generate the comprehensive risk value by weighted sum based on the corrected decision weight.

5. The groundwater level dynamic regulation method based on digital twinning according to claim 1, characterized in that, Matching the comprehensive risk value with the risk warning threshold to determine the risk assessment result, the method is: According to the engineering safety level of the target area, at least two risk warning thresholds are dynamically preset according to the operating conditions or environmental conditions, and different risk levels are divided according to the risk thresholds; Compare the comprehensive risk value with the risk threshold, and determine the risk level to which the comprehensive risk value belongs according to the comparison result; The risk level is taken as the risk assessment result, which is used to trigger the control strategy corresponding to the risk level.

6. The groundwater level dynamic regulation method based on digital twinning according to claim 5, characterized in that, According to the risk assessment result, the collaborative control instructions are generated for the shallow and deep aquifers respectively, specifically: For the shallow aquifer, the pumping instruction is generated to maintain the dynamic water level stability of the key area or meet the engineering dewatering demand; For the deep aquifer, the recharge instruction is generated to provide regional pore water pressure support and slow down land subsidence.

7. The groundwater level dynamic regulation method based on digital twinning according to claim 1, characterized in that, It also includes collecting feedback data after the execution of the instructions, and optimizing the system through a double-level closed-loop feedback mechanism to form a closed-loop control.

8. The groundwater level dynamic regulation method based on digital twinning according to claim 7, characterized in that, The double-level closed-loop feedback mechanism specifically includes the following contents: The first level is an instruction feedback loop: according to the real-time deviation of the measured physical quantity in the feedback data and the predicted data, the calculation parameters of the regulation and control instruction are quickly adjusted to real-time correct and ensure accurate execution of the instruction; the calculation parameters include a lag compensation coefficient and a level coefficient; The second level is a model evolution loop: when the comprehensive deviation exceeds the preset deviation threshold, it is started, the historical monitoring data in a regulation and control period is periodically collected, the core physical parameters in the digital twin model are optimized and updated through the data inversion method, the core physical parameters are at least one dynamic coupling coefficient, to realize the periodic learning and evolution of the model.

9. A digital-twin-based underground water level dynamic regulation system, characterized in that, The system comprises: A data acquisition module configured to acquire multi-source monitoring data of a target area groundwater system, and to construct a multi-dimensional dynamic data set containing hydraulic, mechanical, chemical and thermal parameters; A twin simulation and prediction module configured to construct a multi-field dynamic coupling digital twin model, drive the multi-field dynamic coupling digital twin model using the multi-dimensional dynamic data set for simulation, simulate the state response of the groundwater system under the influence of multi-field interaction, predict the future spatio-temporal distribution of multi-field parameters, and then quantify the evolution trend of key risk indicators to generate a risk evolution field; A data processing module configured to calculate the variation coefficient of the risk value of each physical field based on the risk evolution field, and dynamically allocate decision weights to each physical field based on the variation coefficient and the scene characteristics of the target area to generate a comprehensive risk value; A hierarchical regulation and control module configured to match the comprehensive risk value with a preset risk warning threshold to determine a risk assessment result, and generate a collaborative regulation and control instruction for the shallow and deep aquifers according to the risk assessment result; A feedback optimization module configured to collect feedback data after the instruction is executed, and to optimize the calculation parameters of the regulation and control instruction and the core physical parameters of the digital twin model through a double-level closed-loop feedback mechanism to form a closed-loop regulation and control; Wherein, the method for constructing a multi-field dynamic coupling digital twin model is: A multi-field dynamic coupling model including a hydraulic field, a mechanical field, a chemical field and a thermal field is constructed, and the mutual influence between at least two physical fields is quantified and updated in real time by introducing a dynamic coupling coefficient; wherein the hydraulic field parameters include shallow water level and deep water level, the mechanical field parameters include structure settlement and effective stress, the chemical field parameters include corrosion rate, and the thermal field parameters include thermal stress; the dynamic coupling coefficient includes influence sensitive coefficient, pore pressure sensitive coefficient, temperature sensitive coefficient and temperature corrosion coefficient.

Images