Reservoir flood control monitoring system and method based on digital twinning

Abstract

The invention discloses a reservoir flood control monitoring system and method based on digital twinning, and relates to the technical field of reservoir flood control monitoring, and the system comprises a multi-source data collection module which is used for building a digital twinning model according to the real-time monitoring data of the multi-source data collection module, and transmitting the digital twinning model to a reservoir flood control monitoring module. The coupling module is used for receiving the fusion data set provided by the digital twin module, performing dynamic simulation on the fusion data set, and providing dynamic prediction results of dam seepage, deformation and flood routing; the dynamic early warning module comprises a dynamic threshold adjusting unit and an early warning unit; compared with a traditional early warning system with a fixed threshold value, the system can adapt to changes of dam body states and environmental conditions, identify potential abnormal events in advance, provide sufficient time for flood control of a reservoir to perform emergency response and scheduling decision making, and improve the flood control efficiency. Therefore, the disaster risk is effectively reduced, and the safety of reservoir operation is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir flood control monitoring, and more specifically, to a reservoir flood control monitoring system and method based on digital twins. Background Art

[0002] Reservoirs are one of the engineering facilities for flood control. Reservoirs are built at appropriate locations in the upstream river channels of flood control areas to regulate and store flood waters. Reservoirs are used to intercept and store flood waters, reduce the peak flow entering the downstream river channels, and achieve the purpose of reducing flood disasters. With the continuous development of reservoir flood control monitoring technology, in terms of perception layer technology, the existing monitoring system builds a three-dimensional monitoring network through sensors such as water level gauges, rain gauges, and piezometers, and combines satellite remote sensing and drone inspections to achieve full basin coverage. Data transmission technology uses 4G / 5G, Beidou satellites, etc. to achieve real-time transmission. Some systems introduce LoRa low-power wide area networks to improve the communication capabilities of edge nodes. The data analysis platform integrates GIS maps, BIM models, and IoT data to provide water level prediction, seepage analysis, dam deformation monitoring and other functions. Some systems introduce machine learning algorithms to optimize warning thresholds; However, in actual use, existing sensors are difficult to accurately detect hidden cracks inside the dam body (such as concrete stress cracks) and leakage points in deep water areas. Relying on manual diving operations is inefficient and risky. Old sensors are prone to data drift in extreme weather such as heavy rain and freezing, causing water level monitoring errors to exceed the critical value of ±5cm. Rainfall, water level, and geological displacement data still use independent analysis modes, lacking correlation modeling for cross-parameter coupling. Most systems only implement threshold alarms and lack dynamic risk predictions based on historical data. When flood control scheduling conflicts with power generation and irrigation needs, the existing systems are unable to provide multi-objective collaborative optimization solutions. The link from early warning to plan execution relies on manual decision-making, and in extreme cases the response delay exceeds 30 minutes. Summary of the invention

[0003] In order to solve the above problems, the present invention provides a reservoir flood control monitoring system and method based on digital twins.

[0004] The present invention provides a reservoir flood control monitoring system based on digital twins, comprising the following modules: A multi-source data acquisition module, which includes a quantum gyroscope seepage pressure sensor, a laser radar crack detector, and an underwater sonar array, and is deployed inside the dam of the reservoir to collect multi-source data of the reservoir. The multi-source data includes seepage pressure gradient data collected by the quantum gyroscope seepage pressure sensor, size data of cracks inside the dam body obtained by the laser radar crack detector, and terrain data under the reservoir. The multi-source data is used as real-time monitoring data and transmitted; A digital twin module, wherein the digital twin module is used to construct a digital twin model based on the real-time monitoring data of the multi-source data acquisition module, and output a fused data set through the data twin model, wherein the fused data set includes the distribution of seepage pressure field, crack extension vectors, and underwater terrain mutation hotspots; A coupling module, the coupling module is used to receive the fused data set provided by the digital twin module, and dynamically simulate the fused data set to provide dynamic prediction results of dam body seepage, deformation and flood evolution; A dynamic warning module, the dynamic warning module comprising a dynamic threshold adjustment unit and a warning unit, the dynamic threshold adjustment unit being used to dynamically optimize the warning threshold according to the dynamic prediction result of the coupling module; The early warning unit is used to calculate the flood control risk value of the reservoir, and trigger an early warning in real time based on the optimized early warning threshold value to obtain an early warning result.

[0005] Preferably, the specific working steps of the digital twin module are as follows: Acquire the real-time monitoring data of the multi-source data acquisition module, and perform spatiotemporal alignment between the real-time monitoring data and the static data in the data backplane; The historical flood evolution data was trained through the Transformer neural network to generate a data-driven model; Then the fused data is spatially aligned using Kriging interpolation to obtain a fused data set.

[0006] Preferably, the specific working steps of the coupling module are as follows: Firstly, the dam body is divided into Level element grid; Then solve the coupling equations of seepage field and stress field; Then, the cumulative effect of continuous rainfall for one week on the displacement of the dam is calculated based on the rainfall-deformation correlation matrix; Finally, the two-dimensional shallow water equation is used to simulate the flood evolution process, and the dynamic prediction results of dam seepage, deformation and flood evolution are obtained.

[0007] Preferably, the specific working steps of calculating the cumulative effect of continuous rainfall for one week on the displacement of the dam body based on the rainfall-deformation correlation matrix are as follows: According to the formula Calculate the first Detection of deformation within the band Sensitivity of regional rainfall , is the deformation variable, which comes from the real-time data of the laser radar crack detector. is the rainfall intensity, which comes from the real-time monitoring data of the meteorological station. is the attenuation coefficient, As the cumulative effect of a week of continuous rainfall on the dam displacement.

[0008] Preferably, the specific working steps of simulating the flood evolution process by combining the two-dimensional shallow water equation are as follows: The simulation process is to set the initial water depth and flow velocity, set the inflow, outflow and solid wall boundary conditions, select the appropriate time step according to the CFL condition, and gradually advance the time step through the finite volume method and Godunov format to calculate the flood evolution process; then, the real-time underwater sonar data is integrated with the historical flood pattern library, and the initial conditions are optimized through the data twin model output of the fused data set, and the source term correction driven by the fused data set is introduced into the shallow water equation.

[0009] Preferably, the specific working steps of the dynamic early warning module are as follows: First, the Bayesian network is trained through historical data to calculate the probability of abnormal events. Then the future parameter change trend is predicted based on the time series data.

[0010] Finally, the abnormal threshold is dynamically adjusted according to the predicted change trend.

[0011] Preferably, the specific steps of dynamically adjusting the abnormal threshold according to the predicted change trend are as follows: Set initial thresholds based on historical data or business needs as a baseline for adjustments; Through the prediction model, the prediction value of the next moment is obtained and the current measured value Take the difference and find the absolute value to quantify the fluctuation range of the current data; The statistical standard deviation of historical data is used as the benchmark volatility to standardize the current deviation; The adjustment factor is applied to the basic threshold, and the dynamically adjusted threshold is finally output.

[0012] Preferably, the specific working steps of the early warning unit are as follows: According to the formula , calculate and obtain the risk assessment value R, where The water level exceeds the limit. and is the indicator function; If the risk assessment value R is greater than , then trigger the warning.

[0013] Preferably, the specific working steps of the quantum gyroscope osmotic pressure sensor are as follows: The phase difference caused by the change in the refractive index of the medium is measured through an optical fiber loop. The phase difference is proportional to the osmotic pressure gradient, thereby achieving accurate measurement of the osmotic pressure.

[0014] Phase difference formula , where Ω is the angular velocity, A is the fiber loop area, λ is the wavelength, and c is the speed of light. The phase difference is calculated. ; The phase difference It is converted into osmotic pressure gradient, and the phase difference is associated with the osmotic pressure gradient through a calibration curve or a mathematical model to obtain the osmotic pressure distribution inside the dam body.

[0015] The present invention also proposes a reservoir flood control monitoring method based on digital twins, comprising the following steps: Step 1: Use quantum gyroscopic pressure sensors to measure the seepage pressure gradient inside the dam body, use lidar crack detectors to obtain the three-dimensional size data of the dam body cracks, and combine with underwater sonar arrays to scan the reservoir underground terrain data in real time. After all data are aligned in time and space, they are fused with static databases such as historical flood evolution data and static geological parameters to form a comprehensive data set containing seepage pressure fields, crack extension vectors, and terrain mutations; Step 2: Based on the rainfall-deformation correlation matrix, quantify the cumulative impact of continuous rainfall on the displacement of the dam body, combine the two-dimensional shallow water equation to simulate the flood evolution process, predict the future parameter change trend, and dynamically adjust the warning threshold through the formula; Step 3: Calculate the flood risk value and trigger an early warning when R exceeds the dynamically adjusted early warning threshold.

[0016] Beneficial effects: By deploying quantum gyroscope seepage pressure sensors, lidar crack detectors and underwater sonar arrays, comprehensive real-time monitoring of the seepage pressure inside the dam, surface cracks and underwater terrain is achieved. This multi-dimensional monitoring method ensures the comprehensiveness and real-time nature of the data, and can promptly detect potential safety hazards such as excessive seepage pressure, crack expansion and underwater obstacles. Compared with the traditional single data source monitoring method, it provides richer data support and provides a solid foundation for dam stability assessment and flood control decision-making; Through the dynamic threshold adjustment unit and the early warning unit, the early warning threshold is dynamically optimized according to the real-time monitoring data, and the early warning is triggered in real time. Compared with the traditional early warning system with fixed thresholds, this system can adapt to changes in the dam state and environmental conditions, identify potential abnormal events in advance, and provide sufficient time for emergency response and scheduling decisions for reservoir flood control, thereby effectively reducing disaster risks and ensuring the safety of reservoir operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of the system of the present invention. DETAILED DESCRIPTION

[0018] like Figure 1Shown: A reservoir flood control monitoring system based on digital twins, including the following modules: A multi-source data acquisition module, wherein the multi-source data acquisition module includes a quantum gyroscope seepage pressure sensor, a laser radar crack detector, and an underwater sonar array, which are deployed inside the dam body of the reservoir and are used to collect multi-source data of the reservoir. The multi-source data includes seepage pressure gradient data collected by the quantum gyroscope seepage pressure sensor, size data of cracks inside the dam body obtained by the laser radar crack detector, and terrain data under the reservoir. The multi-source data is used as real-time monitoring data and transmitted; it should be noted that the quantum gyroscope seepage pressure sensor monitors the seepage pressure at different depths and positions inside the dam body in real time, understands the water penetration in the dam body, and provides a basis for evaluating the stability of the dam body. For example, when the seepage pressure is too large, it may cause safety hazards such as dam landslides. By measuring the slight changes in the tilt angle of the dam body, the deformation trend of the dam body can be discovered in time, so that corresponding reinforcement measures can be taken to ensure the safety of the dam body; The laser radar crack detector can accurately detect the geometric parameters of the cracks on the dam surface, such as the position, length and width, to help workers quickly locate the cracks and assess their severity. For example, if the length and width of the cracks are increasing, it means that there may be structural hazards in the dam. The high-precision three-dimensional point cloud data obtained by the laser radar can be used to conduct a detailed analysis of the crack morphology, such as the direction and depth of the cracks and their relationship with the surrounding structures, to provide a scientific basis for the repair and reinforcement of the cracks. The underwater sonar array scans and maps the underwater terrain in the deep water area of ​​the reservoir, and obtains detailed data on the underwater terrain, including water depth, slope, and concavity, etc., to provide basic data for hydrological research and engineering planning of the reservoir. It can detect underwater obstacles such as rocks, sunken ships, and abandoned objects to prevent these obstacles from affecting the operation and maintenance of the reservoir, and also provide safety guarantees for underwater operations; Ensure the real-time and accuracy of the twin, and provide basic data support for subsequent analysis and decision-making; A digital twin module, wherein the digital twin module is used to construct a digital twin model based on the real-time monitoring data of the multi-source data acquisition module, and output a fused data set through the data twin model, wherein the fused data set includes the distribution of seepage pressure field, crack extension vectors, and underwater terrain mutation hotspots; A coupling module, the coupling module is used to receive the fused data set provided by the digital twin module, and dynamically simulate the fused data set to provide dynamic prediction results of dam body seepage, deformation and flood evolution; A dynamic warning module, the dynamic warning module comprising a dynamic threshold adjustment unit and a warning unit, the dynamic threshold adjustment unit being used to dynamically optimize the warning threshold according to the dynamic prediction result of the coupling module; The early warning unit is used to calculate the flood control risk value of the reservoir, and trigger an early warning in real time based on the optimized early warning threshold value to obtain an early warning result.

[0019] It should be noted that the multi-source data acquisition module collects real-time seepage pressure inside the dam, surface crack parameters and underwater terrain data through quantum gyroscope seepage pressure sensors, lidar crack detectors and underwater sonar arrays. This multi-dimensional monitoring method can fully perceive the physical state of the dam and promptly discover potential safety hazards, such as excessive seepage pressure, crack expansion and underwater obstacles. The digital twin module builds a high-precision digital twin model based on the L1-L3 data base and BIM model. The model can reflect the actual status of the dam in real time and provide reliable basic data support for subsequent dynamic simulation and analysis; The coupling module realizes dynamic prediction of dam body seepage, deformation and flood evolution through the seepage-stress coupling equation, rainfall-deformation correlation matrix and flood evolution hydrodynamic equation. This multi-physics field coupling simulation can identify potential risks in advance and provide a scientific basis for flood control decision-making; the dynamic warning module dynamically optimizes the warning threshold according to real-time monitoring data through the dynamic threshold adjustment unit and the warning unit, and triggers the warning in real time. This intelligent warning mechanism can significantly reduce the false alarm rate, improve the accuracy and timeliness of the warning, and ensure the safety of reservoir operation; The system can support the automatic generation of multi-objective optimization scheduling schemes, provide scientific decision-making support for reservoir flood control, and through dynamic simulation and prediction, the system can formulate emergency plans in advance and improve emergency response efficiency; Traditional monitoring methods usually rely on a single data source and cannot fully perceive the physical state of the dam body. This system uses a multi-source data acquisition module, combined with a quantum gyroscope seepage pressure sensor, a lidar crack detector and an underwater sonar array, to achieve comprehensive monitoring of the internal seepage pressure, surface cracks and underwater terrain of the dam body, solving the problem of incomplete data in traditional methods. Traditional monitoring systems often have problems with data delay and insufficient accuracy. The digital twin module of this system receives monitoring data from multi-source data acquisition modules in real time to ensure the real-time and accuracy of the twin model, providing reliable data support for subsequent analysis and decision-making; Traditional monitoring systems can usually only provide static data and cannot perform dynamic simulation and prediction. The coupling module of this system realizes dynamic prediction of dam seepage, deformation and flood evolution through multi-physics field coupling model, solving the problem that traditional systems cannot identify potential risks in advance; Traditional early warning systems usually use fixed thresholds, which can easily lead to false alarms or missed alarms. The dynamic early warning module of this system uses a dynamic threshold adjustment unit and an early warning unit to dynamically optimize the early warning threshold according to real-time data, significantly reducing the false alarm rate and improving the accuracy and timeliness of early warnings.

[0020] As an optional embodiment: the specific working steps of the digital twin module are as follows: The real-time monitoring data of the multi-source data acquisition module is obtained, and the real-time monitoring data and the static data in the data base are aligned in time and space; it should be noted that the data base includes an L1-level data base: as a terrain reference framework; L2 data base: integrates underwater terrain data collected by underwater sonar arrays to establish a spatial topological association network; Level 3 data base: embeds the structured parameters of the BIM model and associates historical hydrological archives and geological exploration data; The historical flood evolution data was trained through the Transformer neural network to generate a data-driven model; Then, the fused data is spatially registered by Kriging interpolation to obtain a fused data set. It should be noted that the continuous pressure field is constructed using the Kriging interpolation algorithm based on the discrete data of the seepage monitoring points (such as quantum gyroscope seepage pressure sensors); For the seepage pressure field distribution data, relying on the quantum gyroscope seepage pressure sensor network, the sliding window method is used to detect outliers and fill missing values ​​in the real-time monitoring data; For crack extension vector data, each crack is composed of several triangular facets, the facet normal vector points to the crack extension direction, the vertices are arranged counterclockwise, and a compact format of 50 bytes / triangular facet is used. The header contains 80 bytes of metadata (such as crack ID, scanning time), and the crack risk level (such as red warning area) is marked through the Attributebytecount field. For underwater terrain mutation hotspot data, ModelTransformationTag (affine transformation parameters) and ProjectedCSTypeGeoKey (projected coordinate system type) are embedded; Based on DEM data, the gdaldemslope tool of the GDAL library was used to generate a slope layer and mark high-risk areas with a slope ≥ 15°; It should be noted that the BIM model is used to provide detailed three-dimensional structural information of the dam body, including geometric shape, material properties and internal structure; the underwater terrain oblique photography data is used to describe the undulation, slope and obstacle distribution of the underwater terrain; the real-time monitoring parameters include data such as seepage pressure, displacement, settlement, stress and strain of the dam body; the millimeter-level crack dynamic mapping can accurately detect geometric parameters such as the position, length and width of cracks on the dam body surface, and conduct a detailed analysis of the morphology of the cracks; the three-dimensional visualization technology is used to display the physical state of the dam body and the surrounding environment in an intuitive three-dimensional form, which is convenient for management personnel to view and analyze; the three-dimensional dynamic twin can be combined with a multi-physics field coupling model to realize dynamic prediction of dam body seepage, deformation and flood evolution; The BIM model is used to provide detailed three-dimensional structural information of the dam body, including geometric shape, material properties and internal structure. The underwater terrain oblique photography data is used to describe the ups and downs, slope and obstacle distribution of the underwater terrain. The real-time monitoring parameters include data such as seepage pressure, displacement, settlement, stress and strain of the dam body. The millimeter-level crack dynamic mapping can accurately detect geometric parameters such as the position, length and width of cracks on the surface of the dam body, and conduct a detailed analysis of the morphology of the cracks. It should also be noted that traditional technologies have significant shortcomings in the spatiotemporal alignment, format unification, and transmission stability of multi-source heterogeneous data (such as sensor data, BIM models, and laser point clouds). For example, the inconsistent collection cycles and measurement units of multi-dimensional data (geometric data, time data, and physical parameters) in industrial scenarios make data fusion difficult; This technical solution realizes cross-scale data fusion by building a multi-level data base. For example, the L1 base integrates low-precision DOM / DEM as a reference framework, the L2 base integrates laser point cloud and underwater terrain data to establish spatial topological association, and the L3 base embeds BIM parametric models and associates historical data; Combining Kriging interpolation algorithm and Transformer neural network, discrete monitoring data (such as seepage pressure and fracture extension vector) are converted into continuous pressure field and dynamic prediction model to improve data utilization and prediction accuracy; Traditional digital twin models often fall into the misunderstanding of being "too simple or too complicated", resulting in the inability to accurately serve specific industrial problems. This technical solution adopts a digital-analog fusion drive method, combining industrial mechanisms with multi-source data (such as real-time sensor data and historical fault libraries) to build a high-fidelity model.

[0021] As an optional embodiment: the specific working steps of the coupling module are as follows: Firstly, the dam body is divided into Level element grid; it should be noted that the initial dam uses hexahedral grid, and the accumulation dam uses tetrahedral grid; Then solve the coupling equations of seepage field and stress field; Specifically, according to the formula Solved to get; in is the permeability tensor, obtained through the fusion data set provided by the digital twin module, is the water head, which comes from the real-time monitoring data of the seepage pressure sensor. is the water storage coefficient, which is derived from the geological parameters of the dam body. is the effective stress tensor, which comes from the mechanical model of the dam body. is the coupling coefficient, which comes from experiments or numerical simulations; In this embodiment, is a vector differential operator used to represent gradient operations; The head change rate is the change in head per unit time divided by the change in time. express, The seepage change caused by stress change is expressed by Operation can accurately describe the flow characteristics of water in the dam body and its interaction with the stress field; It should be noted that, in this embodiment, water head is an important concept in hydraulics, which indicates the mechanical energy of a unit weight of liquid, including position head, pressure head and velocity head. The unit of water head is usually meter (m). Specifically, position head (z): indicates the height of the liquid relative to a certain reference plane, reflecting the potential energy of the liquid. Pressure head (p / γ): indicates the value after the pressure of the liquid at a certain point is converted into the height of the liquid column, where p is the pressure and γ is the specific gravity of the liquid. Velocity head (v² / 2g): indicates the energy corresponding to the flow velocity of the liquid, where v is the flow velocity and g is the acceleration due to gravity. The initial value of is 0.5, and the value range is from 0 to 1, which is adjusted according to the actual situation; is the permeability tensor. In this embodiment, for homogeneous materials (such as concrete or homogeneous soil), the permeability is usually a scalar value, which can be directly measured by laboratory tests. In this embodiment, the scalar permeability (homogeneous material) measured in the laboratory is integrated with the material parameter library in the digital twin module, and the permeability tensor is dynamically adjusted through the Kalman filter algorithm to obtain it; Then, the cumulative effect of continuous rainfall for one week on the displacement of the dam is calculated based on the rainfall-deformation correlation matrix; Finally, the two-dimensional shallow water equation is used to simulate the flood evolution process, and the dynamic prediction results of dam seepage, deformation and flood evolution are obtained.

[0022] It should be noted that traditional methods usually analyze the seepage field or stress field independently, ignoring the dynamic interaction between the two (for example, changes in seepage pressure cause the dam body to deform, and the deformation further affects the seepage path). This scheme divides the dam body into hexahedron (initial dam) and tetrahedron accumulation dam and other parameters through finite element discretization, realizes dynamic coupling calculation of the two fields, and solves the prediction distortion problem of a single physical field model.

[0023] Moreover, environmental factors such as continuous rainfall and flood impact have time-lag and nonlinear characteristics in their damage to the dam body. The module uses the rainfall-deformation correlation matrix to correlate and analyze the rainfall intensity, duration and other data within a week with the dam displacement. For example, the sliding window algorithm is used to calculate the cumulative effect of rainfall gradient on pore water pressure, and the viscoelastic constitutive model is combined to predict the lagged deformation, thus solving the risk assessment lag problem under environmental dynamic loads.

[0024] As an optional embodiment: the specific working steps of calculating the cumulative effect of continuous rainfall for one week on the displacement of the dam body based on the rainfall-deformation correlation matrix are as follows: According to the formula , calculate the first Detection of deformation within the band Sensitivity of regional rainfall , is the deformation variable, which comes from the real-time data of the laser radar crack detector. is the rainfall intensity, which comes from the real-time monitoring data of the meteorological station. is the attenuation coefficient, As the cumulative effect of a week of continuous rainfall on the dam displacement. It should be noted that the attenuation coefficient The optimal value of the attenuation coefficient is determined by the least square method or other fitting methods, and the value range is 0.01 to 1. In this embodiment, the initial value is 0.5; It should be noted that by simulating the hysteresis of rainfall infiltration and constructing the objective function based on historical monitoring data, the prior art does not consider the time lag of rainfall infiltration, and this technical solution can comprehensively consider the time lag problem of rainfall infiltration; It should be noted that the instantaneous influence of the change in rainfall intensity in the jth region on the deformation of the i-th monitoring point is reflected in the formula: is the partial derivative of deformation with respect to rainfall, which indicates the change in deformation caused by a unit change in rainfall intensity; Indicates The slight change in the deformation of a monitoring point reflects the deformation of the dam at that monitoring point, which is usually monitored in real time by equipment such as laser radar crack detectors. Indicates The slight change in rainfall intensity in a region at time t reflects the dynamic change of rainfall intensity, which is usually provided by real-time monitoring data from meteorological stations. is the attenuation coefficient, through the exponential function Describes the time decay characteristics of the cumulative effect of rainfall, the decay coefficient The larger it is, the faster the cumulative effect of short-term rainfall on deformation decays; By sensitivity , the nonlinear relationship between rainfall intensity and dam deformation is identified. In the early stage of heavy rainfall, the attenuation coefficient has a weak effect, and the sensitivity is mainly driven by the instantaneous rainfall intensity; in long-term continuous rainfall, the attenuation effect dominates, and the sensitivity gradually decreases; Reveal the differences in the response of dam deformation under different rainfall patterns (such as heavy rain and continuous light rain), and provide quantitative basis for flood control strategies; Attenuation coefficient The optimal value of (e.g., λ=0.3 obtained through fitting) can reflect the permeability characteristics of the dam material; Partial derivatives It can itself reflect the sensitivity of dam deformation to changes in rainfall intensity, which may change with time or rainfall intensity, thus capturing the nonlinear relationship.

[0025] Time decay factor This makes the recent rainfall have a greater impact on the deformation of the dam body. This dynamic weighting can better reflect the dynamic response of the dam body to rainfall.

[0026] Comprehensive consideration of cumulative effects: By summing all time steps, the formula can comprehensively consider the cumulative effect of rainfall, further capture the complex nonlinear relationship between rainfall intensity and dam deformation, evaluate the cumulative amount of dam displacement under specific rainfall scenarios (such as continuous rainfall for a week), and predict the critical safety threshold.

[0027] As an optional embodiment: the specific working steps of simulating the flood evolution process by combining the two-dimensional shallow water equation are as follows: The simulation process is to set the initial water depth and flow velocity, set the inflow, outflow and solid wall boundary conditions, select the appropriate time step according to the CFL condition, and gradually advance the time step to calculate the flood evolution process through the finite volume method and Godunov format; It should be noted that, in this embodiment, according to the formula To simulate, are conserved variables, including water depth (h), horizontal velocity (hu), and vertical velocity (hv), which are derived from the real-time monitoring data of the underwater sonar array. is the flux term, which describes the horizontal flow of water. is the source term, including terrain slope and friction resistance; The first part of the equation Represents the rate of change of the conserved variable over time, ensuring that the total amount of flood remains conserved during the simulation; The second part of the equation represents the divergence of the flux term, describing the change of flood momentum in space, ensuring the conservation and correct propagation of momentum, Same as above, for gradient calculation; Source Term Taking into account factors such as terrain slope and friction resistance, the model can more accurately simulate the evolution of floods in complex terrain; Visualize simulation results to show flood propagation paths, flow velocity, and water depth changes; Through simulation, we can obtain the propagation path, flow velocity and water depth distribution of floods at different time steps. These results can be used to assess flood risks, optimize flood prevention measures and guide emergency responses; The real-time underwater sonar data is then fused with the historical flood pattern library, the initial conditions are optimized through the output of the fused data set through the data twin model, and the source term correction driven by the fused data set is introduced into the shallow water equation.

[0028] By The source term is multiplied by the data-driven correction and the correction factor to obtain the new source term , the new source term Add shallow water equations to simulate flood evolution; Specific data-driven corrections are generated by residual networks trained with historical flood data to compensate for The error in the source term, The specific acquisition method is to input the historical data into the shallow water equation (such as the S_phys term) to obtain the physical model prediction results. The historical data is the historical fusion data set; The residual block structure is adopted. Each residual block contains a convolutional layer, batch normalization and ReLU activation function. The residual mapping between input and output is learned through cross-layer connection. The correction factor is used to balance the contribution of the physical model and the data-driven correction term. In this embodiment, the correction factor is set to 0.5.

[0029] As an optional embodiment: the specific working steps of the dynamic warning module are as follows: First, the Bayesian network is trained through historical data to calculate the probability of abnormal events. In this embodiment, according to the formula , calculated, where A is the abnormal event and B is the detection parameter combination; Then the future parameter change trend is predicted based on the time series data.

[0030] It should be noted that, in this embodiment, specifically: ; Finally, the abnormal threshold is dynamically adjusted according to the predicted change trend. It should be noted that the Bayesian network is trained with historical data to calculate the probability of abnormal events, and the future parameter change trend is predicted based on time series data, so as to achieve dynamic adjustment of the abnormal threshold. This design has the following significant beneficial effects: Through the Bayesian network, the dynamic warning module can calculate the probability of abnormal events based on historical data and real-time monitoring parameters, significantly improving the accuracy and reliability of warnings. This method can effectively identify potential safety hazards and avoid false alarms and missed alarms; Based on the time series data, the dynamic warning module can predict the trend of parameter changes in the future, and adjust the abnormal threshold in real time according to the prediction results. This dynamic adjustment mechanism ensures that the warning threshold can adapt to the changes in the dam state and environmental conditions, and improves the flexibility and adaptability of the warning; By predicting future parameter change trends, the dynamic early warning module can identify potential abnormal events in advance, providing sufficient time for reservoir flood control to make emergency responses and dispatch decisions, thereby reducing disaster risks; The prediction and adjustment capabilities of the dynamic early warning module provide a scientific basis for reservoir flood control and support intelligent decision-making. By dynamically optimizing the early warning threshold, the system can more accurately assess the health of the dam and provide reliable data support for flood control scheduling and emergency response; In summary, the dynamic early warning module realizes accurate early warning and dynamic adjustment of abnormal events through the combination of Bayesian network and time series prediction, significantly improves the intelligence level and early warning capability of the reservoir flood control monitoring system, and provides a solid guarantee for the safe operation of the reservoir.

[0031] As an optional embodiment: the specific steps of dynamically adjusting the abnormal threshold according to the predicted change trend are as follows: Set initial thresholds based on historical data or business needs as a baseline for adjustments; Through the prediction model, the prediction value of the next moment is obtained and the current measured value Take the difference and find the absolute value to quantify the fluctuation range of the current data; The statistical standard deviation of historical data is used as the benchmark volatility to standardize the current deviation; The adjustment factor is applied to the basic threshold, and the dynamically adjusted threshold is finally output.

[0032] In this embodiment, the specific adjustment calculation steps are: According to the formula , calculate and obtain the adjusted threshold value; in is the initial threshold, is the standard deviation of historical data. It should be noted that the abnormal threshold is adjusted dynamically by combining the standard deviation of historical data and the trend of predicted parameter changes. This mechanism can flexibly optimize the warning threshold according to the actual operating status and environmental conditions of the dam body to ensure the accuracy and adaptability of the warning. By reducing the false alarm rate and missed alarm rate, the system can identify potential risks more timely and provide more reliable early warning support for reservoir flood control; It should be noted that the traditional method relies on fixed thresholds and is difficult to cope with the dynamic changes of system load and environmental conditions (such as rainfall and floods). For example, in the rainy season, the seepage of the dam body may surge due to continuous rainfall, and the fixed threshold is prone to missed reports; and normal fluctuations in the dry season may falsely trigger warnings; This scheme introduces the standard deviation of historical data to quantify the data fluctuation range, and dynamically adjusts the threshold value in combination with the predicted trend, so that the threshold range can be elastically expanded and contracted with the actual changes of parameters such as seepage pressure and deformation rate; For example, when the forecast model detects that the rainfall in the next 72 hours exceeds the historical average, it automatically reduces the sensitivity of the infiltration pressure threshold to capture potential risks in advance; Moreover, the anomalies of dam deformation, seepage and other parameters have a hysteresis (e.g., displacement response appears 1-3 days after heavy rainfall), and traditional methods are difficult to provide timely warnings because they ignore the cumulative effect of time series. This scheme can alleviate the above problems by correcting the threshold value through the trend of parameter changes (such as the seepage rate derivative ΔH / Δt); By capturing short-term fluctuation characteristics through forecasting deviations, the threshold can respond dynamically to changes in the environment, which is better than the fixed threshold strategy and converts the current deviation into a ratio relative to the historical fluctuation level.

[0033] As an optional embodiment: the specific working steps of the early warning unit are as follows: According to the formula , calculate and obtain the risk assessment value R, where The water level exceeds the limit. and is the indicator function; it should be noted that is the baseline value, indicating the initial risk threshold under ideal conditions, The water level exceeds the limit value, indicating that the current water level exceeds the safe water level. If the water level is higher, The larger the value of , the greater the contribution to risk, so in the formula The coefficient before is negative, which means that water level exceeding the limit will reduce the R value and increase the risk; Indicates that when a flooding event occurs, The value is 1, otherwise =0; flooding events will significantly increase the risk, so the coefficient of I before flooding in the formula is negative, indicating that flooding will reduce the R value; It means that when the power generation system is operating normally, The value indicating power generation is 1, otherwise it is 0; the normal operation of the power generation system helps to reduce risks, so the coefficient of I before power generation in the formula is positive, indicating that normal power generation will increase the R value; If the risk assessment value R is greater than , an early warning is triggered. It should be noted that the ability to quickly quantify risks ensures that the system responds promptly when potential threats occur, improving decision-making efficiency and system security.

[0034] As an optional embodiment: the specific working steps of the quantum gyroscope osmotic pressure sensor are as follows: The phase difference caused by the change in the refractive index of the medium is measured through an optical fiber loop. The phase difference is proportional to the osmotic pressure gradient, thereby achieving accurate measurement of the osmotic pressure.

[0035] Phase difference formula , where Ω is the angular velocity, A is the fiber loop area, λ is the wavelength, and c is the speed of light. The phase difference is calculated. ;This phase difference reflects the change in osmotic pressure gradient; The phase difference It is converted into osmotic pressure gradient, and the phase difference is associated with the osmotic pressure gradient through a calibration curve or a mathematical model to obtain the osmotic pressure distribution inside the dam body.

[0036] The present invention also proposes a reservoir flood control monitoring method based on digital twins, comprising the following steps: Step 1: Use quantum gyroscopic pressure sensors to measure the seepage pressure gradient inside the dam body, use lidar crack detectors to obtain the three-dimensional size data of the dam body cracks, and combine with underwater sonar arrays to scan the reservoir underground terrain data in real time. After all data are aligned in time and space, they are fused with static databases such as historical flood evolution data and static geological parameters to form a comprehensive data set containing seepage pressure fields, crack extension vectors, and terrain mutations; Step 2: Based on the rainfall-deformation correlation matrix, quantify the cumulative impact of continuous rainfall on the displacement of the dam body, combine the two-dimensional shallow water equation to simulate the flood evolution process, predict the future parameter change trend, and dynamically adjust the warning threshold through the formula; Step 3: Calculate the flood risk value and trigger an early warning when R exceeds the dynamically adjusted early warning threshold.

[0037] By deploying quantum gyroscope seepage pressure sensors, lidar crack detectors and underwater sonar arrays, comprehensive real-time monitoring of the seepage pressure inside the dam, surface cracks and underwater terrain is achieved. This multi-dimensional monitoring method ensures the comprehensiveness and real-time nature of the data, and can promptly detect potential safety hazards such as excessive seepage pressure, crack expansion and underwater obstacles. Compared with the traditional single data source monitoring method, it provides richer data support and provides a solid foundation for dam stability assessment and flood control decision-making; Through the dynamic threshold adjustment unit and the early warning unit, the early warning threshold is dynamically optimized according to the real-time monitoring data, and the early warning is triggered in real time. Compared with the traditional early warning system with fixed thresholds, this system can adapt to changes in the dam state and environmental conditions, identify potential abnormal events in advance, and provide sufficient time for emergency response and scheduling decisions for reservoir flood control, thereby effectively reducing disaster risks and ensuring the safety of reservoir operation.

[0038] The above are only preferred implementations of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical staff in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of this template.

Claims

1. A reservoir flood control monitoring system based on digital twins, characterized in that: Includes the following modules: The multi-source data acquisition module includes a quantum gyroscope seepage pressure sensor, a laser radar crack detector, and an underwater sonar array, which are deployed inside the dam of the reservoir to collect multi-source data of the reservoir. The multi-source data includes the seepage pressure gradient data collected by the quantum gyroscope seepage pressure sensor, the size data of the cracks inside the dam obtained by the laser radar crack detector, and the terrain data under the reservoir. The multi-source data is used as real-time monitoring data and transmitted; A digital twin module is used to construct a digital twin model based on the real-time monitoring data of the multi-source data acquisition module, and output a fused data set through the data twin model, wherein the fused data set includes the distribution of seepage pressure field, crack extension vectors, and underwater terrain mutation hotspots; A coupling module is used to receive the fused data set provided by the digital twin module, and dynamically simulate the fused data set to provide dynamic prediction results of dam body seepage, deformation and flood evolution; A dynamic warning module, comprising a dynamic threshold adjustment unit and a warning unit, wherein the dynamic threshold adjustment unit is used to dynamically optimize the warning threshold according to the dynamic prediction result of the coupling module; It is used to calculate the flood control risk value of the reservoir, and trigger the warning in real time according to the optimized warning threshold to obtain the warning result.

2. A reservoir flood control monitoring system based on digital twin according to claim 1, characterized in that: The specific working steps of the digital twin module are as follows: Acquire the real-time monitoring data of the multi-source data acquisition module, and perform spatiotemporal alignment between the real-time monitoring data and the static data in the data backplane; The historical flood evolution data was trained through the Transformer neural network to generate a data-driven model; Then the fused data is spatially aligned using Kriging interpolation to obtain a fused data set.

3. A reservoir flood control monitoring system based on digital twin according to claim 1, characterized in that: The specific working steps of the coupling module are as follows: Firstly, the dam body is divided into Level element grid; Then solve the coupling equations of seepage field and stress field; Then, the cumulative effect of continuous rainfall for one week on the displacement of the dam is calculated based on the rainfall-deformation correlation matrix; Finally, the two-dimensional shallow water equation is used to simulate the flood evolution process, and the dynamic prediction results of dam seepage, deformation and flood evolution are obtained.

4. A reservoir flood control monitoring system based on digital twin according to claim 3, characterized in that: The specific working steps of calculating the cumulative effect of continuous rainfall for one week on the dam displacement based on the rainfall-deformation correlation matrix are as follows: According to the formula , calculate the first Detection of deformation within the band Sensitivity of regional rainfall , is the deformation variable, which comes from the real-time data of the laser radar crack detector. is the rainfall intensity, which comes from the real-time monitoring data of the meteorological station. is the attenuation coefficient, As the cumulative effect of a week of continuous rainfall on the dam displacement.

5. A reservoir flood control monitoring system based on digital twin according to claim 3, characterized in that: The specific working steps of simulating the flood evolution process by combining the two-dimensional shallow water equation are as follows: The simulation process is to set the initial water depth and flow velocity, set the inflow, outflow and solid wall boundary conditions, select the appropriate time step according to the CFL condition, and gradually advance the time step to calculate the flood evolution process through the finite volume method and Godunov format; The real-time underwater sonar data is then fused with the historical flood pattern library, the initial conditions are optimized through the output of the fused data set through the data twin model, and the source term correction driven by the fused data set is introduced into the shallow water equation.

6. A reservoir flood control monitoring system based on digital twin according to claim 1, characterized in that: The specific working steps of the dynamic early warning module are as follows: First, the Bayesian network is trained through historical data to calculate the probability of abnormal events. Then predict the future parameter change trend based on the time series data; Finally, the abnormal threshold is dynamically adjusted according to the predicted change trend.

7. A reservoir flood control monitoring system based on digital twin according to claim 6, characterized in that: The specific steps of dynamically adjusting the abnormal threshold according to the predicted change trend are as follows: Set initial thresholds based on historical data or business needs as a baseline for adjustments; Through the prediction model, the prediction value of the next moment is obtained and the current measured value Take the difference and find the absolute value to quantify the fluctuation range of current data; The statistical standard deviation of historical data is used as the benchmark volatility to standardize the current deviation; The adjustment factor is applied to the basic threshold, and the dynamically adjusted threshold is finally output.

8. A reservoir flood control monitoring system based on digital twins according to claim 7, characterized in that: The specific working steps of the early warning unit are as follows: According to the formula , calculate and obtain the risk assessment value R, where The water level exceeds the limit. and is the indicator function; If the risk assessment value R is greater than , then trigger the warning.

9. A reservoir flood control monitoring system based on digital twin according to claim 1, characterized in that: The specific working steps of the quantum gyro osmotic pressure sensor are as follows: The phase difference caused by the change of the medium refractive index is measured through the optical fiber loop. The phase difference is proportional to the osmotic pressure gradient, thereby achieving accurate measurement of the osmotic pressure. Phase difference formula , where Ω is the angular velocity, A is the fiber loop area, λ is the wavelength, and c is the speed of light. The phase difference is calculated. ; The phase difference It is converted into osmotic pressure gradient, and the phase difference is associated with the osmotic pressure gradient through a calibration curve or a mathematical model to obtain the osmotic pressure distribution inside the dam body.

10. A reservoir flood control monitoring method based on digital twins, applicable to a reservoir flood control monitoring system based on digital twins as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Use quantum gyroscopic pressure sensors to measure the seepage pressure gradient inside the dam body, use lidar crack detectors to obtain the three-dimensional size data of the dam body cracks, and combine with underwater sonar arrays to scan the reservoir underground terrain data in real time. After all data are aligned in time and space, they are fused with static databases such as historical flood evolution data and static geological parameters to form a comprehensive data set including seepage pressure field, crack extension vectors and terrain mutations; Step 2: Based on the rainfall-deformation correlation matrix, quantify the cumulative impact of continuous rainfall on the displacement of the dam body, combine the two-dimensional shallow water equation to simulate the flood evolution process, predict the future parameter change trend, and dynamically adjust the warning threshold through the formula; Step 3: Calculate the flood risk value and trigger an early warning when R exceeds the dynamically adjusted early warning threshold.

Images