A system and method for calibrating the discharge capacity of a reservoir dam

Abstract

The present invention discloses a method and system for calibrating the discharge capacity of a reservoir dam, specifically related to the technical field of dam monitoring. First, a CFD model of the reservoir discharge system is constructed, and the adaptive grid technology is used to optimize the calculation accuracy of key areas. Then, machine learning algorithms are used to calculate the error sensitivity coefficient and the dynamic grid adjustment coefficient respectively, automatically detect the area affected by numerical diffusion, and determine whether to trigger optimization and adjustment. In the high-error area, adaptive grid encryption, dynamic time step adjustment, and turbulence model optimization are adopted to effectively reduce errors and improve the accuracy of discharge capacity calibration. In addition, the discharge capacity curve is generated through multiple rounds of dynamic adjustment, and the discharge capacity under future working conditions is predicted by combining with a deep learning model, optimizing the calculation efficiency and reducing the CFD calculation cost. Finally, a high-precision discharge capacity curve and a flow velocity distribution map are output, providing reliable data support for reservoir operation and improving the accuracy and safety of flood control operation.

Description

Technical Field

[0001] The present invention relates to the technical field of dam monitoring, and particularly to a system and method for calibrating the discharge capacity of a reservoir dam. Background Art

[0002] The discharge capacity of a reservoir dam is directly related to reservoir operation, flood control safety, and the downstream ecological environment. Traditional methods for calibrating discharge capacity mainly rely on on-site measurements, physical model tests, and empirical formula calculations. However, these methods have problems such as long test cycles, high costs, and limited applicability. In recent years, the development of computational fluid dynamics (CFD) technology has provided an efficient and accurate numerical simulation method for calibrating discharge capacity, which can be used to predict the discharge characteristics under different water levels, gate openings, and complex working conditions.

[0003] The existing technology has the following deficiencies:

[0004] In the process of calibrating discharge capacity based on CFD, numerical diffusion is a problem that is not easily noticed but may seriously affect the calculation accuracy. Numerical diffusion is an artificial viscosity effect caused by discretization error, which over-smooths the velocity gradient and free surface fluctuations in the flow field, thus underestimating the kinetic energy and turbulent characteristics of high-speed discharge. In the calibration of reservoir discharge capacity, numerical diffusion may lead to the following serious consequences: 1) Underestimating the actual discharge capacity of the flood discharge channel and spillway, making the reservoir operation plan too conservative and affecting the flood control efficiency; 2) Misjudging the hydraulic jump position of the energy dissipation pool, resulting in the failure of the optimal design of the energy dissipation structure and causing downstream riverbed scouring or structural damage. Summary of the Invention

[0005] The purpose of the present invention is to provide a system and method for calibrating the discharge capacity of a reservoir dam to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A method for calibrating the discharge capacity of a reservoir dam, comprising:

[0007] Obtaining the geometric parameters of the discharge facilities of the reservoir dam, including the structural dimensions of the spillway, flood discharge tunnel, energy dissipation pool, and bottom outlet, constructing a CFD model of the reservoir dam discharge system, and using adaptive meshing to optimize the calculation accuracy of key areas;

[0008] Calculating the error sensitivity coefficient and dynamic mesh adjustment coefficient in each key area based on a machine learning algorithm, and detecting the numerical diffusion influence area through the calculated error sensitivity coefficient to determine whether to trigger optimization and adjustment;

[0009] For high-error areas, using the dynamic mesh adjustment coefficient for adaptive mesh refinement, dynamic time step adjustment, and turbulence model optimization to reduce errors and improve calculation accuracy;

[0010] Perform multiple rounds of dynamic adjustment under different working conditions to generate a discharge capacity curve, optimize the calculation efficiency in combination with a deep learning prediction model, and output the discharge capacity curve and the flow velocity distribution map to support the optimization of reservoir operation.

[0011] Preferably, the calculation method of the error sensitivity coefficient is as follows: Define error characteristic variables and construct a data matrix X: ; m is the number of grid cells, and n is the number of error influence variables; since the value ranges of different variables are different, standardization processing is required to make their mean 0 and variance 1: Calculate the covariance matrix C of the standardized data matrix X': ; where: C is an n×n-dimensional covariance matrix, and T is the matrix transpose;

[0012] Perform eigenvalue decomposition on the covariance matrix C to obtain eigenvalues and the corresponding eigenvectors , and the expression is: ; the eigenvalue : represents the variance of the i-th principal component, and the eigenvector represents the direction of the i-th principal component; Select the first k principal components with a cumulative contribution rate reaching 95% for calculation, and calculate the principal component scores: ; where: V is a matrix composed of the selected k eigenvectors, and Z is the data matrix after dimensionality reduction, containing the principal component scores; Define the error sensitivity coefficient as ESC, and the expression is: ; where: is the eigenvalue of the j-th principal component, is the weight coefficient corresponding to the eigenvector.

[0013] Preferably, set the error influence region threshold TESC. If ESC≥TESC, it is considered that the numerical diffusion error in the region is large, and it is marked as a high-error region; if ESC<TESC, it is considered that the numerical diffusion error in the region is small, and it is marked as a low-error region, and record the index set of the grid regions that need to be optimized , and calculate the proportion of the high-error region : ; N represents the total number of grid cells in the CFD calculation model. If the calculated proportion of the high-error region is greater than or equal to the set high-error region proportion threshold, trigger an optimization adjustment.

[0014] Preferably, the method for obtaining the dynamic grid adjustment coefficient is as follows: Construct a data set Y, including local grid scale, turbulent kinetic energy, free surface fluctuation, and calculation error; Determine the optimal number of clusters w, using the elbow method: ; in the formula, represents the data point belonging to the q-th cluster, is the sum of squared errors within the cluster, represents the set of grid points of the p-th cluster, is the center point of the p-th cluster;

[0015] Randomly select w initial clustering centers, and calculate the Euclidean distance from each grid point to all clustering centers , and assign it to the nearest cluster : ; e represents the number of the e-th grid cell in the CFD calculation model, and N represents all the grid cells in the CFD calculation model. For each cluster , update the mean center: ; If the clustering center no longer changes or reaches the maximum number of iterations, terminate the iteration;

[0016] Assign a grid encryption factor to each cluster : For the clustering center error perform normalization: ; where represents the error characteristic component of the p-th clustering, and h is the number of clusters; Combine the weights of each cluster , calculate the dynamic mesh adjustment coefficient DMRC: DMRC .

[0017] Preferably, the adaptive grid encryption controls the grid optimization through the dynamic mesh adjustment coefficient DMRC, and the calculation formula for the optimized grid size is: ; where: is the optimized grid cell size, is the initial grid cell size, is the dynamic mesh adjustment coefficient of the e-th grid cell.

[0018] Preferably, the dynamic time step adjustment calculates the optimized time step through DMRC, and the calculation formula for the optimized time step is: ; where: is the optimized time step, is the original time step, is the maximum DMRC value in the high-error region.

[0019] Preferably, the deep learning prediction model is based on a long short-term memory network and includes:

[0020] Train the LSTM model using historical discharge capacity data, and the input features include water level, gate opening, discharge flow rate, and velocity distribution;

[0021] The LSTM layer extracts time series features and learns the changing trend of the discharge capacity curve;

[0022] Calculate the mean square error. If the error exceeds the set threshold, optimize the CFD calculation to improve the prediction accuracy;

[0023] Update the LSTM training data in combination with the CFD calculation results.

[0024] The present invention also provides a system for calibrating the discharge capacity of a reservoir dam, including a parameter acquisition module, a data calculation module, a grid adjustment module, and a calculation efficiency optimization module;

[0025] Parameter acquisition module: Acquire the geometric parameters of the discharge facilities of the reservoir dam, including the structural dimensions of the spillway, flood discharge tunnel, energy dissipation pool, and bottom outlet, construct a CFD model of the reservoir dam discharge system, and adopt an adaptive grid to optimize the calculation accuracy of key areas;

[0026] Data calculation module: Calculate the error sensitivity coefficient and dynamic grid adjustment coefficient in each key area respectively based on the machine learning algorithm, and detect the numerical diffusion influence area through the calculated error sensitivity coefficient to judge whether to trigger the optimization adjustment;

[0027] Grid adjustment module: For high-error areas, use the dynamic grid adjustment coefficient to perform adaptive grid encryption, dynamic time step adjustment, and turbulence model optimization to reduce errors and improve the calculation accuracy;

[0028] Calculation efficiency optimization module: Perform multiple rounds of dynamic adjustment under different working conditions to generate a discharge capacity curve, optimize the calculation efficiency in combination with the deep learning prediction model, and output the discharge capacity curve and the flow velocity distribution map to support the optimization of reservoir operation.

[0029] In the above technical solution, the technical effects and advantages provided by the present invention:

[0030] The present invention optimizes the calculation accuracy of key areas through an adaptive grid, calculates the error sensitivity coefficient using principal component analysis, identifies the numerical diffusion influence area, and combines K-Means clustering to calculate the dynamic grid adjustment coefficient to automatically optimize the grid division and calculation parameters. In high-error areas, dynamically adjust the grid density, time step, and turbulence model to reduce the calculation error and improve the accuracy of discharge capacity calibration. In addition, use the long short-term memory network to predict the discharge capacity curve, optimize the CFD calculation efficiency, reduce the calculation cost, and output a high-precision discharge capacity curve and flow velocity distribution map to provide data support for reservoir operation. Overall, the present invention improves the accuracy, calculation stability, and operation optimization level of discharge capacity evaluation, and has wide application value in aspects such as flood control safety and water resource operation. Description of the Drawings

[0031] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other accompanying drawings can also be obtained based on these drawings.

[0032] Figure 1 It is a flowchart of the method of the present invention.

[0033] Figure 2 It is a system module diagram of the present invention. Detailed implementation manners

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0035] Embodiment 1. Please refer to Figure 1 As shown, a method for calibrating the discharge capacity of a reservoir dam includes:

[0036] Obtain the geometric parameters of the discharge facilities of the reservoir dam, including the structural dimensions of the spillway, flood discharge tunnel, energy dissipation pool, and bottom outlet, construct a CFD model of the reservoir dam discharge system, and adopt adaptive meshing to optimize the calculation accuracy of key areas;

[0037] Based on the machine learning algorithm, calculate the error sensitivity coefficient and dynamic mesh adjustment coefficient in each key area respectively, and detect the numerical diffusion influence area through the calculated error sensitivity coefficient to judge whether to trigger optimization adjustment;

[0038] For high-error areas, use the dynamic mesh adjustment coefficient for adaptive mesh encryption, dynamic time step adjustment, and turbulence model optimization to reduce errors and improve calculation accuracy;

[0039] Perform multiple rounds of dynamic adjustments under different working conditions to generate a discharge capacity curve, optimize the calculation efficiency in combination with a deep learning prediction model, and output the discharge capacity curve and flow velocity distribution map to support reservoir operation optimization.

[0040] The steps for constructing the CFD model of the reservoir dam discharge system and optimizing the key areas with adaptive meshing include:

[0041] Step 1: Obtain the geometric parameters of the discharge facilities: Obtain the key parameters such as the structural dimensions, boundary shapes, slopes, and cross-section forms of the discharge facilities such as spillways, flood discharge tunnels, energy dissipation basins, and bottom outlets. Refer to the dam construction drawings, topographic survey data, and 3D laser scanning data to improve the geometric accuracy. Statistically analyze parameters such as different water levels, gate opening angles, and flow rates to clarify the calculation boundary conditions. Combine historical water flow observation data to optimize the model input parameters.

[0042] Step 2: Construct a CFD model of the reservoir dam discharge system: Use modeling software such as CAD, SolidWorks, and ANSYS SpaceClaim to create a 3D geometric model based on the structural data of the discharge facilities. Simplify the details of non-critical areas (such as small auxiliary structures) to improve the calculation efficiency. Determine the calculation range, including the discharge facilities and the surrounding water area, and ensure that the boundaries are far from the key flow areas to reduce the reflection effect. Set the inflow boundary (reservoir area), outflow boundary (downstream river channel), and atmospheric boundary (free surface) to ensure the calculation stability. Use tools such as ICEM CFD, Gambit, and Ansys Meshing for preliminary mesh generation. Adopt unstructured mesh to improve the adaptability to complex geometric areas.

[0043] Step 3: Determine the key optimization areas (mesh refinement areas) including: High-gradient change areas: The spillway inlet, bottom outlet inlet, and around the gates, where the water flow velocity and pressure change suddenly. Turbulent and recirculation areas: The bends of the flood discharge channel, energy dissipation basins, and drop sections, where the flow patterns are complex. Free surface areas: The top of the overflow weir, the surface of the flood discharge channel, where the water-air interaction is obvious. Negative pressure and cavitation risk areas: The high-speed discharge jet area, the bottom of the energy dissipation basin, where cavitation may occur.

[0044] Apply adaptive mesh technology (AMR) to optimize the mesh density: Adopt local mesh refinement to refine the mesh in key areas to improve the flow field analysis ability. Use dynamic mesh adjustment for the free surface and turbulent eddy areas to optimize the mesh in real time. Adopt boundary layer refined mesh to improve the calculation accuracy of the near-wall flow and optimize the calculation of energy loss.

[0045] Optimize the time step and calculation stability: Adopt adaptive time step control to optimize the calculation accuracy and stability. Select a suitable turbulence model (such as the RANS-LES hybrid model) to ensure the turbulence analysis accuracy.

[0046] Calculate the error sensitivity coefficients in the key areas of the reservoir dam discharge system (such as spillways, flood discharge tunnels, energy dissipation basins, and bottom outlets) through the PCA algorithm, identify the variables that mainly affect the errors, reduce the data dimension, and improve the calculation efficiency.

[0047] The calculation method of the error sensitivity coefficient is as follows: Define error characteristic variables, including: Grid scale: The size of the grid cell, which affects the calculation accuracy; Flow velocity gradient: , which affects the turbulence accuracy; Pressure gradient: , which affects the calculation of energy loss; Time step: A parameter related to calculation stability; Turbulence model error: The difference in calculation results of different turbulence models; Free surface fluctuation: Numerical error at the water-air interface.

[0048] Construct the data matrix X: ; m is the number of grid cells, and n is the number of error influence variables; Since the value ranges of different variables are different, standardization processing is required to make their mean 0 and variance 1: Calculate the covariance matrix C of the standardized data matrix X′: ; where: C is an n×n-dimensional covariance matrix, and T is the matrix transpose;

[0049] Perform eigenvalue decomposition on the covariance matrix C to obtain the eigenvalues and the corresponding eigenvectors , and the expression is: ; The eigenvalue : represents the variance (contribution rate) of the i-th principal component, and the eigenvector represents the direction of the i-th principal component; Usually, the first k principal components with a cumulative contribution rate reaching 95% are selected for calculation, and calculate the principal component scores (dimensionality reduction transformation): ; where: V is a matrix composed of the selected k eigenvectors (dimensionality reduction transformation matrix), and Z is the data matrix after dimensionality reduction, containing the principal component scores. Define the error sensitivity coefficient as ESC, and the error sensitivity coefficient represents the influence degree of the key area on the overall error, and the expression is: ; where: is the eigenvalue of the j-th principal component, is the weight coefficient corresponding to the eigenvector.

[0050] Set the error influence area threshold TESC (empirical value, such as 0.05~0.1). If ESC≥TESC, it is considered that the numerical diffusion error in the area is large, and it is marked as a high-error area; if ESC<TESC, it is considered that the numerical diffusion error in the area is small, and it is marked as a low-error area, and record the set of grid area indices that need to be optimized .

[0051] Calculate the proportion of the high-error area : ; N represents the total number of grid cells in the CFD calculation model. If the proportion of the calculated high-error region is greater than or equal to the set threshold of the proportion of the high-error region, optimization adjustment is triggered. Perform K-Means clustering on the high-error region to automatically identify the grid optimization strategy.

[0052] Calculate the dynamic grid adjustment coefficient of the key area of the reservoir dam discharge system through the K-Means clustering algorithm, automatically identify the high-error region, and allocate appropriate grid densities to improve the CFD calculation accuracy and efficiency.

[0053] Define characteristic variables and construct the data set Y: Local grid scale: the grid size of the current area, Turbulent kinetic energy: an index of local turbulence intensity, reflecting the flow complexity; Free surface fluctuation: the rate of change of the water surface height at the water-air interface, affecting the numerical diffusion error; Calculation error: a local error evaluation index based on historical CFD calculations.

[0054] Determine the optimal number of clusters w, and the elbow method can be used: ; In the formula, is the sum of squared errors within the cluster, represents the data points belonging to the qth cluster, represents the set of grid points in the pth cluster, is the center point of the pth cluster. When the downward trend slows down, select this w value as the optimal number of clusters.

[0055] Perform K-Means iterative calculation, specifically: randomly select w initial cluster centers, calculate the Euclidean distance from each grid point to all cluster centers , and assign it to the nearest cluster : ; e represents the number of the e-th grid cell in the CFD calculation model, and N represents the total number of grid cells in the CFD calculation model. For each cluster , update the mean center: ; If the cluster center no longer changes or reaches the maximum number of iterations, terminate the iteration.

[0056] Allocate a grid encryption factor for each cluster : Normalize the cluster center error : ; Among them represents the error characteristic component of the pth cluster, and h is the number of clusters.

[0057] Combine the weights of each cluster (Based on characteristics such as flow velocity gradient and turbulent energy), calculate the Dynamic Mesh Refinement Coefficient (DMRC): DMRC The larger the DMRC value, the higher the mesh density required in that area.

[0058] Compare the obtained Dynamic Mesh Refinement Coefficient with a preset threshold. If the Dynamic Mesh Refinement Coefficient is greater than or equal to the preset threshold, perform adaptive mesh encryption, dynamic time step adjustment, and turbulence model optimization on the high-error area, specifically including:

[0059] Calculate the adaptive mesh size based on DMRC: ; where: is the optimized mesh cell size, is the initial mesh cell size, is the Dynamic Mesh Refinement Coefficient of the e-th mesh cell. The larger the DMRC value, the greater the error impact and the higher the mesh encryption degree.

[0060] Perform mesh refinement in the high-error area to improve local calculation accuracy. Use adaptive mesh refinement to dynamically optimize the mesh division during the calculation process.

[0061] Dynamic time step adjustment includes: calculating a new time step using DMRC : ; where: is the optimized time step, is the original time step, is the maximum DMRC value in the high-error area. Narrow the time step in the high-error area to improve time discretization accuracy and reduce errors. Use adaptive time step control to automatically adjust the calculation stability.

[0062] Turbulence model optimization includes: for the high-error area: use LES (Large Eddy Simulation) or RANS-LES hybrid model to improve calculation accuracy. Adopt a more refined turbulence wall function to improve the near-wall flow simulation ability. In the area where the Dynamic Mesh Refinement Coefficient is greater than or equal to the preset threshold, increase the resolution of the turbulence model to improve numerical stability. In the free water surface area, optimize the VOF (Volume of Fluid) free surface capture algorithm to reduce errors. Adopt WENO (Weighted Essentially Non-Oscillatory scheme) to reduce numerical diffusion errors in high-gradient areas.

[0063] Under different working conditions, predict the discharge capacity curve through the LSTM (Long Short-Term Memory Network) deep learning model, reduce the number of CFD calculations, improve the calculation efficiency, and optimize the reservoir operation in combination with the flow velocity distribution data.

[0064] Collect and organize the historical discharge capacity data of the reservoir discharge system, including: Water level (H): The change of the reservoir water level under different working conditions. Gate opening degree (G): The opening percentage of the gate (0% - 100%). Discharge flow (Q): The amount of water passing through the discharge facility per unit time. Flow velocity distribution (V(x,y)): The flow velocity field in key areas such as the spillway and energy dissipation pool. Historical CFD calculation results: Discharge capacity data under different grid densities and time steps.

[0065] Due to the different numerical ranges of different parameters, standardization is required to make the data have the same scale, improving the training accuracy and stability of the model.

[0066] Build an LSTM deep learning model: Input layer: Receive historical discharge capacity data, including features such as water level, gate opening, and flow velocity. LSTM layer: Extract time series features and learn the changing trend of the discharge capacity curve. Fully connected layer: Used to output the future discharge capacity curve. Activation function: Use ReLU for non-linear mapping to improve the prediction accuracy.

[0067] Use historical data to train the model to learn the changing law of the discharge capacity. Use validation data to evaluate the prediction ability of the model and adjust the model parameters to improve the generalization ability.

[0068] Predict the discharge capacity under future working conditions. Input new data such as water level, gate opening, and flow velocity, and the model predicts the future discharge capacity curve. Use the mean square error to evaluate the error between the predicted discharge capacity curve by the model and the real CFD calculation results. Set the error threshold TMSE (such as 0.05 - 0.1). If the prediction error exceeds the threshold, it is necessary to optimize the CFD calculation.

[0069] Combine CFD calculation to optimize the discharge capacity curve:

[0070] Optimize the grid density: Refine the grid in the high-error area to improve the local calculation accuracy.

[0071] Optimize the time step: Adjust the time discretization to improve the calculation stability.

[0072] Optimize the turbulence model: Improve the turbulence calculation to reduce the error influence.

[0073] Rerun the CFD calculation to obtain the optimized discharge capacity curve and update the LSTM training data to make the model prediction more accurate.

[0074] Compare the discharge capacity curve predicted by LSTM with the discharge capacity curve calculated by CFD and analyze the prediction accuracy. When the error requirement is met, directly use the LSTM prediction result to reduce the number of CFD calculations and improve the calculation efficiency.

[0075] Analyze the water flow characteristics of the spillway facilities by combining CFD calculations with deep learning predictions of the flow velocity distribution. Identify key areas such as water flow scouring and turbulent regions to provide reference for reservoir operation scheduling.

[0076] Example 2, please refer to Figure 2 As shown, a system for calibrating the discharge capacity of a reservoir dam in this embodiment includes a parameter acquisition module, a data calculation module, a grid adjustment module, and a calculation efficiency optimization module;

[0077] Parameter acquisition module: Obtain the geometric parameters of the spillway facilities of the reservoir dam, including the structural dimensions of the spillway, flood discharge tunnel, energy dissipation pool, and bottom outlet, construct a CFD model of the reservoir dam spillway system, and adopt adaptive meshing to optimize the calculation accuracy of key areas;

[0078] Data calculation module: Calculate the error sensitivity coefficient and dynamic grid adjustment coefficient in each key area based on machine learning algorithms respectively, and detect the numerical diffusion influence area through the calculated error sensitivity coefficient to determine whether to trigger optimization adjustment;

[0079] Grid adjustment module: For high-error areas, use the dynamic grid adjustment coefficient to perform adaptive grid encryption, dynamic time step adjustment, and turbulence model optimization to reduce errors and improve calculation accuracy;

[0080] Calculation efficiency optimization module: Perform multiple rounds of dynamic adjustment under different working conditions, generate a discharge capacity curve, optimize the calculation efficiency in combination with a deep learning prediction model, and output the discharge capacity curve and flow velocity distribution map to support reservoir operation scheduling optimization.

[0081] All the above formulas are dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0082] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application.

Claims

1. A method for grading the discharge capacity of a reservoir dam, characterized in that: include: Obtain the geometric parameters of the reservoir dam discharge facilities, including the structural dimensions of the spillway, spillway tunnel, energy dissipation pool and bottom holes, build a CFD model of the reservoir dam discharge system, and use adaptive grids to optimize the calculation accuracy of key areas; Based on the machine learning algorithm, the error sensitivity coefficient and dynamic grid adjustment coefficient in each key area are calculated respectively, and the area affected by numerical diffusion is detected by the calculated error sensitivity coefficient to determine whether to trigger optimization adjustment; The method for obtaining the dynamic grid adjustment coefficient is as follows: constructing a data set Y, including local grid scale, turbulent kinetic energy, free water surface fluctuation and calculation error; determining the optimal clustering number w, using the elbow method: ; In the formula, represents the data point belonging to the qth cluster, is the intra-cluster error sum of squares, represents the set of grid points of the p-th cluster, is the center point of the pth cluster; Randomly select w initial cluster centers and calculate the Euclidean distance from each grid point to all cluster centers , and assign it to the nearest cluster : ; e represents the number of the e-th grid unit in the CFD calculation model, N represents the number of all grid units in the CFD calculation model, and for each cluster , update the mean center: ; If the cluster center no longer changes or the maximum number of iterations is reached, the iteration is terminated; Assign a mesh refinement factor to each cluster : Cluster center error Normalize: ;in Represents the error characteristic component of the pth cluster, h is the number of clusters; combined with the weights of each cluster , calculate the dynamic grid adjustment coefficient DMRC: ; For high error areas, dynamic grid adjustment coefficients are used to perform adaptive grid encryption, dynamic time step adjustment, and turbulence model optimization to reduce errors and improve calculation accuracy. Perform multiple rounds of dynamic adjustments under different operating conditions to generate a discharge capacity curve, combine deep learning prediction models to optimize computing efficiency, and output the discharge capacity curve and flow velocity distribution map to support reservoir scheduling optimization.

2. A method for grading the discharge capacity of a reservoir dam according to claim 1, characterized in that: The key areas include high gradient change areas, turbulence and backflow areas, free water surface evolution areas and local negative pressure areas.

3. A method for grading the discharge capacity of a reservoir dam according to claim 2, characterized in that: The calculation method of the error sensitivity coefficient is: define the error characteristic variable and construct the data matrix X: ; m is the number of grid cells, n is the number of error-affecting variables; Since different variables have different value ranges, they need to be standardized so that their mean is 0 and their variance is 1: Calculate the covariance matrix C of the standardized data matrix X′: ; Where: C is the n×n dimensional covariance matrix, T is the matrix transpose; Perform eigenvalue decomposition on the covariance matrix C and obtain the eigenvalue and the corresponding eigenvector , the expression is: ; Eigenvalue : represents the variance of the i-th principal component, eigenvector Indicates the direction of the i-th principal component; select the first k principal components whose cumulative contribution rate reaches 95% for calculation, and calculate the principal component score: ; Where: V is a matrix composed of the selected k eigenvectors, Z is the reduced-dimensional data matrix, including the principal component scores; the error sensitivity coefficient is defined as ESC, and the expression is: ;in: is the eigenvalue of the jth principal component, is the weight coefficient corresponding to the eigenvector.

4. A method for grading the discharge capacity of a reservoir dam according to claim 3, characterized in that: Set the threshold TESC for the error influence area. If ESC ≥ TESC, it is considered that the numerical diffusion error in the area is large, and the area is marked as a high-error area; if ESC < TESC, it is considered that the numerical diffusion error in the area is small, and the area is marked as a low-error area, and record the set of grid area index numbers that need to be optimized. , calculate the proportion of the high-error area ; N represents the total number of grid cells in the CFD calculation model. If the calculated proportion of the high-error area is greater than or equal to the set threshold for the proportion of the high-error area, trigger the optimization adjustment.

5. A method for grading the discharge capacity of a reservoir dam according to claim 4, characterized in that: The adaptive grid encryption controls the grid optimization through the dynamic grid adjustment coefficient DMRC, and the optimized grid size calculation formula is: ;in: is the optimized grid cell size, is the initial grid cell size, is the dynamic grid adjustment coefficient of the e-th grid cell.

6. A method for grading the discharge capacity of a reservoir dam according to claim 5, characterized in that: The dynamic time step adjustment optimizes the time step by DMRC calculation, and the optimized time step calculation formula is: ;in: is the optimized time step, is the original time step, is the maximum DMRC value in the high error region.

7. A method for grading the discharge capacity of a reservoir dam according to claim 6, characterized in that: The deep learning prediction model is based on a long short-term memory network and includes: The LSTM model was trained using historical discharge capacity data, with input features including water level, gate opening, discharge flow, and flow velocity distribution; The LSTM layer extracts time series features and learns the changing trend of the discharge capacity curve; Calculate the mean square error. If the error exceeds the set threshold, optimize the CFD calculation to improve the prediction accuracy. Update LSTM training data based on CFD calculation results.

8. A reservoir dam discharge capacity rating system, used to implement a reservoir dam discharge capacity rating method according to any one of claims 1 to 7, characterized in that: It includes parameter acquisition module, data calculation module, grid adjustment module and calculation efficiency optimization module; Parameter acquisition module: obtains the geometric parameters of the reservoir dam discharge facilities, including the structural dimensions of the spillway, spillway tunnel, energy dissipation pool and bottom hole, builds the CFD model of the reservoir dam discharge system, and uses adaptive grids to optimize the calculation accuracy of key areas; Data calculation module: Based on the machine learning algorithm, the error sensitivity coefficient and dynamic grid adjustment coefficient in each key area are calculated respectively, and the area affected by numerical diffusion is detected through the calculated error sensitivity coefficient to determine whether to trigger optimization adjustment; Grid adjustment module: For high error areas, dynamic grid adjustment coefficients are used to perform adaptive grid encryption, dynamic time step adjustment, and turbulence model optimization to reduce errors and improve calculation accuracy; Computational efficiency optimization module: Perform multiple rounds of dynamic adjustments under different working conditions to generate a discharge capacity curve, combine deep learning prediction models to optimize computational efficiency, and output discharge capacity curves and flow velocity distribution maps to support reservoir scheduling optimization.

Images