Inversion prediction method and system for seepage parameters of core-wall rockfill dam

Abstract

The invention relates to the technical field of dam seepage, in particular to a core-wall rockfill dam seepage parameter inversion prediction method and system, and the method comprises the steps: obtaining a target seepage performance score of a dam body; according to a preset collection time interval, collecting operation data of the core wall rock-fill dam to obtain a dam body seepage characteristic data set; based on the obtained multiple dam body seepage characteristic data sets, real-time seepage performance scores of the dam body are obtained through analysis; based on the dam body real-time seepage performance score and the dam body target seepage performance score, whether seepage inversion prediction needs to be carried out or not is judged; when seepage inversion prediction needs to be carried out, model parameters of a preset seepage parameter inversion prediction model are determined; and inputting the newly obtained dam body seepage characteristic data set into the seepage parameter inversion prediction model of which the model parameters have been confirmed, and obtaining an inversion prediction result of the seepage parameters of the core-wall rockfill dam. The accuracy of seepage parameter inversion prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of dam seepage, and particularly to a method and system for inverse prediction of seepage parameters of a core wall rockfill dam. Background Art

[0002] As a widely used dam type in water conservancy projects, the seepage safety of a core wall rockfill dam is directly related to the stability and long-term service performance of the dam body structure; seepage parameters are the core indicators for evaluating the seepage state of the dam body, and changes in seepage parameters may cause problems such as dam leakage and seepage deformation, and in severe cases, even threaten the safety of the dam; the inverse prediction of seepage parameters aims to reverse the internal seepage characteristics of the dam body through monitoring data, providing a scientific basis for project safety.

[0003] Existing inversion methods usually rely on historical data or calibration parameters under specific working conditions, lacking the dynamic response ability to real-time operation data. When the dam body encounters extreme working conditions or local damage, existing models are difficult to adjust parameters in a timely manner, resulting in lagging or deviating from actual requirements in prediction results. Summary of the Invention

[0004] The present invention provides a method for inverse prediction of seepage parameters of a core wall rockfill dam that improves the accuracy of inverse prediction of seepage parameters, which can effectively solve the problems in the background art.

[0005] To achieve the above object, the present invention provides a method for inverse prediction of seepage parameters of a core wall rockfill dam, including:

[0006] Obtaining the target seepage performance score of the dam body;

[0007] Collecting the operation data of the core wall rockfill dam according to a preset collection time interval to obtain a set of dam body seepage characteristic data;

[0008] Based on the obtained multiple sets of dam body seepage characteristic data, analyzing to obtain the real-time seepage performance score of the dam body;

[0009] Based on the real-time seepage performance score of the dam body and the target seepage performance score of the dam body, determining whether seepage inverse prediction is required; and when seepage inverse prediction is required, determining the model parameters of a preset seepage parameter inverse prediction model;

[0010] Inputting the latest obtained set of dam body seepage characteristic data into the seepage parameter inverse prediction model with confirmed model parameters to obtain the inverse prediction result of the seepage parameters of the core wall rockfill dam.

[0011] Further, obtaining the target seepage performance score of the dam body includes:

[0012] Obtaining the design standard of the core wall rockfill dam to be inverted, and identifying and extracting seepage parameter data therefrom to obtain a set of target seepage parameters;

[0013] Perform seepage performance analysis on the target seepage parameter set to obtain the target seepage performance score of the dam body.

[0014] Furthermore, the target seepage parameter set includes the target permeability coefficient and the target hydraulic gradient.

[0015] Furthermore, the dam body seepage characteristic data set includes the water head, seepage flow rate, and pore water pressure at the set position of the dam body.

[0016] Furthermore, based on the obtained multiple dam body seepage characteristic data sets, analyze to obtain the real-time seepage performance score of the dam body, including:

[0017] Sort and align the set number of dam body seepage characteristic data sets in the order of the acquisition timestamps to obtain the dam body seepage characteristic matrix;

[0018] Input the dam body seepage environment characteristic matrix into the pre-constructed seepage performance evaluation model to obtain the real-time seepage performance score of the dam body.

[0019] Furthermore, based on the real-time seepage performance score of the dam body and the target seepage performance score of the dam body, determine whether seepage inversion prediction is required; and when seepage inversion prediction is required, determine the model parameters of the preset seepage parameter inversion prediction model, including:

[0020] Calculate the seepage performance deviation amount according to the real-time seepage performance score of the dam body and the target seepage performance score of the dam body;

[0021] Compare the seepage performance deviation amount with the preset error range:

[0022] If the seepage performance deviation amount is within the preset error range, it indicates that the current seepage state is close to the ideal state and no inversion prediction is required;

[0023] If the seepage performance deviation amount exceeds the preset error range, seepage inversion prediction is required, and determine the model parameters of the preset seepage parameter inversion prediction model according to the seepage performance deviation amount.

[0024] Furthermore, the seepage performance evaluation model is constructed using a multi-layer perceptron architecture. The number of input layer nodes is equal to the dimension of the seepage characteristic matrix. The hidden layer contains neurons with ReLU activation functions, and the output layer generates a normalized score value through the Sigmoid function.

[0025] Furthermore, the preset acquisition time interval is dynamically adjusted according to the environmental conditions of the dam body, seasonal changes, and extreme working conditions monitored in real time.

[0026] Further, the preset error range is comprehensively determined based on the historical operation data, design standards, and safety margin of the core wall rockfill dam, and is regularly optimized and adjusted according to the latest obtained operation data.

[0027] On the other hand, the present invention also provides a seepage parameter inversion prediction system for a core wall rockfill dam, including:

[0028] A target score acquisition module for acquiring the target seepage performance score of the dam body;

[0029] A data acquisition module for collecting the operation data of the core wall rockfill dam at a preset collection time interval to obtain a dam body seepage characteristic data set;

[0030] A real-time analysis module for analyzing and obtaining the real-time seepage performance score of the dam body based on the obtained multiple dam body seepage characteristic data sets;

[0031] A decision-making module for judging whether seepage inversion prediction is required according to the real-time seepage performance score of the dam body and the target seepage performance score of the dam body; and when seepage inversion prediction is required, determining the model parameters of a preset seepage parameter inversion prediction model;

[0032] An inversion prediction module for inputting the latest obtained dam body seepage characteristic data set into the seepage parameter inversion prediction model with confirmed model parameters to obtain the inversion prediction result of the seepage parameters of the core wall rockfill dam.

[0033] Through the technical solution of the present invention, the following technical effects can be achieved: By collecting the dam body seepage characteristic data at a preset collection time interval, the operation data of the dam body can be obtained in real time; Based on the operation data of the dam body, the real-time seepage performance score is obtained. Compared with the traditional method that relies on historical data or specific working conditions to calibrate parameters, it can quickly respond to the change of the seepage state of the dam body. Especially in extreme working conditions or local damage, it can timely detect seepage anomalies and avoid the lag of prediction results; By comparing the real-time seepage performance score of the dam body with the target seepage performance score, it is judged whether to carry out seepage inversion prediction, avoiding unnecessary waste of computing resources and improving efficiency; Only when the seepage performance significantly deviates from the target, the inversion prediction is started to ensure that the inversion prediction is aimed at the actual demand and the resources are concentrated on the key issues; According to the judgment result, the parameters of the seepage parameter inversion prediction model are determined, which can make the model better adapt to the current actual situation of the dam body; By inputting the latest data into the model with confirmed parameters, the real-time information can be fully utilized, improving the accuracy of the seepage parameter inversion prediction, and providing a more reliable scientific basis for the dam safety assessment and decision-making. Description of the Drawings

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0035] Figure 1 It is a flowchart of the seepage parameter inversion prediction method for the central core rockfill dam of the present invention;

[0036] Figure 2 It is a structural block diagram of the seepage parameter inversion prediction system for the central core rockfill dam of the present invention. Detailed implementation manners

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments.

[0038] As Figure 1 shown, the seepage parameter inversion prediction method for the central core rockfill dam of the present invention specifically includes the following steps:

[0039] Step S1, obtain the target seepage performance score of the dam body;

[0040] Step S2, collect the operation data of the central core rockfill dam according to the preset acquisition time interval to obtain the dam body seepage characteristic data set; the dam body seepage characteristic data set includes the water head, seepage flow rate, and pore water pressure at the set position of the dam body;

[0041] Step S3, analyze the obtained multiple dam body seepage characteristic data sets to obtain the real-time seepage performance score of the dam body;

[0042] Step S4, based on the real-time seepage performance score of the dam body and the target seepage performance score of the dam body, determine whether seepage inversion prediction is required; and when seepage inversion prediction is required, determine the model parameters of the preset seepage parameter inversion prediction model;

[0043] Step S5, input the latest obtained dam body seepage characteristic data set into the seepage parameter inversion prediction model with confirmed model parameters to obtain the inversion prediction result of the seepage parameters of the central core rockfill dam.

[0044] In this embodiment, through the technical solution of the present invention, the following technical effects can be achieved: By collecting the dam seepage characteristic data at a preset collection time interval, the operation data of the dam can be obtained in real time; Based on the dam operation data, a real-time seepage performance score is obtained. Compared with the traditional method that relies on historical data or calibrated parameters under specific working conditions, it can quickly respond to the change of the dam seepage state. Especially in extreme working conditions or local damage, seepage anomalies can be detected in time to avoid lagging prediction results; By comparing the real-time seepage performance score of the dam with the target seepage performance score, it is used to judge whether to perform seepage inversion prediction, avoiding unnecessary waste of computing resources and improving efficiency; Only when the seepage performance shows a significant deviation from the target, the inversion prediction is started to ensure that the inversion prediction is targeted at the actual needs and the resources are concentrated on key issues; According to the judgment result, the parameters of the seepage parameter inversion prediction model are determined, which can make the model better adapt to the current actual situation of the dam; By inputting the latest data into the model with confirmed parameters, real-time information can be fully utilized to improve the accuracy of seepage parameter inversion prediction, providing a more reliable scientific basis for dam safety assessment and decision-making.

[0045] In addition, the above method realizes the systematic upgrade of the traditional seepage analysis method through a closed-loop architecture of "dynamic monitoring - intelligent evaluation - adaptive inversion". The coordinated action of each link produces a significant composite effect. By continuously collecting operation data and comparing the real-time and target seepage performance scores, seepage anomalies of the dam can be sensitively captured, and an overall closed-loop is formed from data collection, anomaly judgment, model adaptation to accurate prediction, effectively overcoming the disadvantages of the traditional method relying on historical data and having a lagging response.

[0046] In some embodiments of the present invention, the method for specifically obtaining the target seepage performance score of the dam includes:

[0047] Step S11: Obtain the design standards of the core wall rockfill dam to be inverted. At the design stage of each core wall rockfill dam, a complete set of design standards will be formulated based on relevant engineering specifications, geological conditions, hydrological conditions, and expected functional requirements, etc.; The design standards include parameter requirements for dam design and operation. Specifically, the design standards include the following contents:

[0048] Dam dimensions and structural types: For example, geometric parameters such as the height, width, and length of the dam, as well as the specific rockfill materials and technologies used;

[0049] Hydraulic parameters: Such as design head, maximum allowable seepage flow rate, pore water pressure distribution, etc.;

[0050] Safety indicators: Such as the designed safety factor, maximum allowable deformation, etc.;

[0051] Step S12: Identify and extract seepage parameter data from the design criteria to obtain a target seepage parameter set. The parameters related to seepage identified and extracted from the design criteria constitute the target seepage parameter set, which mainly includes the target permeability coefficient and the target hydraulic gradient. The permeability coefficient reflects the ability of the dam body material to allow water flow through, usually measured in cm / s, and is an important parameter for calculating the seepage path and velocity. The hydraulic gradient represents the pressure gradient of the water flow through the dam body and is used to evaluate the hydrodynamic characteristics of the water flow at different positions inside the dam body.

[0052] Step S13: Analyze the seepage performance of the target seepage parameter set to obtain the target seepage performance score of the dam body. After obtaining the target seepage parameter set, use seepage theory and analysis methods to comprehensively evaluate it, including mathematical models established based on seepage mechanics principles, and simulate and analyze the seepage conditions of the dam body under different working conditions through computer simulation software; or combine the practical experience and theoretical knowledge of previous similar projects to conduct qualitative and quantitative analysis and judgment on the target seepage parameters. According to the results of the seepage performance analysis, determine the target seepage performance score of the dam body according to the pre-set scoring rules or standards. The scoring rules are obtained based on a large number of experimental studies, engineering case statistics, and expert experience summaries, comprehensively considering the influence degree of seepage parameters on the safety and stability of the dam body. For example, the closer the target permeability coefficient and the target hydraulic gradient are to the ideal values or within the safe range, the better the seepage performance of the dam body and the higher the corresponding score; on the contrary, if these parameters deviate greatly from the ideal values and exceed the safe range, it indicates that there may be potential seepage risks in the dam body and the score will be lower.

[0053] In this embodiment, starting from the design criteria of the core rockfill dam to be inverted, the process of obtaining the target seepage performance score can comprehensively consider all key elements of the dam body design and operation, avoiding the problem of incomplete evaluation caused by only focusing on a single factor, and laying a solid foundation for accurately obtaining the seepage performance score in the follow-up. By specifically identifying and extracting seepage parameter data from the design criteria, clearly focusing on the two key parameters directly related to seepage, namely the target permeability coefficient and the target hydraulic gradient, to form the target seepage parameter set, it can exclude the interference of irrelevant information, make the subsequent analysis process more targeted, and improve the efficiency and accuracy of obtaining the target seepage performance score of the dam body.

[0054] In some embodiments of the present invention, the dam body seepage characteristic data set includes the water head, seepage flow rate, and pore water pressure at the set position of the dam body.

[0055] The water head refers to the energy possessed by a unit weight of liquid. In the scenario of seepage in a dam body, the water head at a set position in the dam body represents the energy height of the water at that specific position, measured as the height relative to a certain reference plane, such as the bottom of the dam foundation; the water head is the driving force factor for seepage; differences in water heads at different positions cause water to flow within the dam body, and its magnitude and distribution directly affect parameters such as the seepage velocity, direction, and flow rate; by monitoring the water head at a set position in the dam body, the distribution of the water head inside the dam body can be understood, and then the driving force of seepage can be analyzed to determine whether there are potential seepage problems caused by unreasonable water head distribution, such as excessive local seepage velocity, etc.;

[0056] The seepage flow rate refers to the amount of water passing through a certain cross-section or specific area of the dam body per unit time, usually expressed in volume flow rate units such as cubic meters per second (m 3 / s); the seepage flow rate is an important indicator for measuring the leakage degree of the dam body; under normal circumstances, the seepage flow rate of the dam body should be controlled within a reasonable range; if the seepage flow rate suddenly increases or continuously exceeds the design allowable value, it may mean that there are problems such as leakage channels in the dam body, changes in the performance of the dam body materials, or damage to the dam body structure; therefore, real-time monitoring of the seepage flow rate is crucial for timely detecting the leakage hidden dangers of the dam body and evaluating the safety of the dam body;

[0057] The pore water pressure refers to the pressure generated by the water existing in the pores inside the dam body; in granular structure dam bodies such as earth-rock dams, the pore water pressure has an important impact on the stability and seepage characteristics of the dam body; it is usually expressed as the pressure value relative to the atmospheric pressure; changes in the pore water pressure will affect the effective stress between the dam body particles, and thus affect the shear strength and stability of the dam body; when the pore water pressure increases, it will reduce the effective stress between the dam body particles, lower the shear strength of the dam body, and increase the risk of instability such as sliding and collapse of the dam body; when the pore water pressure data is different from the expected value obtained by simulating and analyzing according to the target seepage parameter set, it can be judged whether the dam body is in a stable seepage state, providing key information for scoring the real-time seepage performance of the dam body, helping to timely detect potential seepage safety hidden dangers and taking corresponding measures to ensure the safe operation of the dam body.

[0058] In this embodiment, by clarifying the definitions and functions of the three core parameters of water head, seepage flow rate, and pore water pressure in the dam seepage characteristic data set, a multi-dimensional and high-precision seepage monitoring system is constructed. Its advantages are reflected in the following aspects: First, as the core parameter of seepage flow power, the water head directly reflects the distribution of seepage driving force by quantifying the energy differences at different positions. Combining spatial monitoring can accurately identify local water head anomalies, providing dynamic data support for analyzing seepage paths and velocities. Second, as an intuitive quantification index, the seepage flow rate can quickly capture abnormal seepage exceeding the design threshold by monitoring the change of leakage scale in real time. Combining historical data comparison can judge the degree of material aging or structural damage, significantly improving the timeliness of hidden danger identification. Third, pore water pressure monitoring combines seepage analysis with dam stability, evaluates the risk of shear strength attenuation through effective stress changes, compensates for the defect that traditional methods only focus on flow rate and ignore mechanical effects, and at the same time realizes the multi-criterion joint diagnosis of seepage state through dynamic comparison with the simulated values of target parameters. In addition, the coordinated acquisition and fusion of the three parameters in the time and space dimensions form a closed-loop analysis chain from "driving force - seepage scale - structural response", which not only ensures that the data covers the key links of the entire seepage process, but also provides high-information-density input for model inversion, taking into account both monitoring comprehensiveness and calculation efficiency.

[0059] In some embodiments of the present invention, a method for obtaining the real-time seepage performance score of a dam includes:

[0060] After obtaining multiple dam seepage characteristic data sets (including water head, seepage flow rate, and pore water pressure), these data need to be processed first. Since the data changes dynamically over time, these data need to be sorted according to the collection timestamps. This step ensures the time continuity and logical consistency of the data. To ensure the effectiveness of the analysis, a reasonable amount of data is usually selected for analysis. For example, the data of the past 24 hours or within a week can be selected to capture enough change trends. Different types of seepage characteristic data may be collected at different time points, so these data need to be aligned. The aligned data can form a unified time series for subsequent analysis. A structured dam seepage characteristic matrix can be obtained. The dam seepage characteristic matrix contains information such as water head, seepage flow rate, and pore water pressure at various positions of the dam during a specific time period.

[0061] Input the processed dam seepage characteristic matrix into a pre - constructed seepage performance evaluation model to obtain the real - time seepage performance score of the dam. The seepage performance evaluation model is a pre - trained mathematical model used to evaluate the current seepage state of the dam based on the input seepage characteristic data. The seepage performance evaluation model can be constructed based on various technologies, such as machine learning algorithms, numerical simulation methods, or other statistical analysis methods. As input data, the seepage characteristic matrix undergoes calculations and analyses within the model and finally outputs a standardized score value, which is the real - time seepage performance score of the dam. The real - time seepage performance score of the dam reflects the degree of deviation of the current seepage state of the dam from the ideal state.

[0062] On the other hand, the seepage performance evaluation model can also be constructed using a multi - layer perceptron architecture. The number of nodes in the input layer is equal to the dimension of the seepage characteristic matrix. The hidden layer contains neurons with ReLU activation functions, and the output layer generates a standardized score value through the Sigmoid function.

[0063] In this embodiment, by sorting and aligning the data in terms of time, the consistency and accuracy of the data are ensured, and errors caused by inconsistent time are avoided. Selecting a reasonable time period for analysis can capture sufficient change trends and improve the reliability and stability of the evaluation results. The model constructed based on seepage theory and a large amount of experimental data has high scientificity and accuracy. Through the model, complex seepage phenomena can be quantitatively evaluated to provide objective score results. The model not only considers the changes in a single parameter but also combines data from multiple dimensions such as water head, seepage flow rate, and pore water pressure to comprehensively reflect the seepage state of the dam.

[0064] In some embodiments of the present invention, step S4 triggers the inversion prediction through a dynamic deviation analysis and threshold decision mechanism, solving the problem in traditional methods that model updates rely on fixed cycles or manual intervention. Through the calculation of the deviation amount between the real - time score and the target score and the comparison of the error range, the adaptive triggering of the inversion prediction is achieved, and the model parameters are optimized based on the degree of deviation, thereby improving the response speed and prediction accuracy under extreme working conditions. The specific implementation is as follows:

[0065] Calculate the seepage performance deviation based on the real-time seepage performance score of the dam body and the target seepage performance score of the dam body. The target seepage performance score of the dam body is obtained by analyzing the target seepage parameter set through scientific and rigorous methods, such as using seepage theory, mathematical models, and simulation software, or combining past engineering experience, based on the design standards of the core wall rockfill dam, which reflects the seepage performance of the dam body under the ideal design state. The real-time seepage performance score of the dam body is obtained by processing and analyzing the seepage characteristic data (such as the water head, seepage flow rate, and pore water pressure at the set positions of the dam body) collected during the real-time operation of the dam body, using the pre-constructed seepage performance evaluation model, which reflects the current actual seepage performance of the dam body. By calculating the difference between the two, the seepage performance deviation is obtained, which can intuitively reflect the deviation degree of the current seepage state of the dam body from the design expectation. For example, if the target seepage performance score of the dam body is 90 points (assuming a full score of 100 points represents the ideal state), and the real-time seepage performance score of the dam body is 70 points, then the seepage performance deviation is 20 points, indicating that there is a certain gap between the current seepage state and the ideal state.

[0066] After obtaining the seepage performance deviation, it is necessary to compare it with the preset error range. The preset error range is comprehensively determined based on the historical operation data, design standards, and safety margin of the core wall rockfill dam, and will be optimized and adjusted regularly according to the newly obtained operation data. The preset error range provides a reasonable reference interval for judging the seepage state of the dam body. If the seepage performance deviation is within the preset error range, it means that although there is a certain difference between the current seepage state of the dam body and the target state, it is still within the acceptable range and close to the ideal state. At this time, there is no need to perform seepage inversion prediction. Because in this case, the seepage situation of the dam body is relatively stable, and there is no obvious sign indicating that it is necessary to perform seepage parameter inversion prediction to adjust the model. However, if the seepage performance deviation exceeds the preset error range, it means that the current seepage state of the dam body deviates greatly from the design expectation, and there may be potential seepage problems, such as the risk of dam body leakage and seepage deformation. At this time, seepage inversion prediction is required.

[0067] After determining the need for inversion prediction, the model parameters of the preset seepage parameter inversion prediction model are determined based on the deviation of seepage performance. When determining the model parameters, the physical mechanisms during the seepage process are fully considered. For example, according to basic seepage principles such as Darcy's law (when water seeps through a porous medium, the flow rate is proportional to the hydraulic gradient), the relationship between the deviation and factors such as the water flow velocity and pressure distribution inside the dam body is analyzed. If the deviation is large and shows an upward trend, it means that significant changes have occurred in the water flow velocity or pressure distribution inside the dam body. At this time, the parameters representing these physical quantities in the model need to be adjusted accordingly. Mathematical optimization algorithms are used to determine the model parameters, and common ones include the least squares method, genetic algorithm, particle swarm algorithm, etc. Taking the least squares method as an example, its basic idea is to adjust the model parameters to minimize the sum of the squares of the errors between the model prediction results and the actual observed data. The specific process is as follows:

[0068] Taking the seepage performance deviation and related observed data (such as water head, seepage flow rate, pore water pressure, etc. in the dam seepage characteristic data set) as inputs, a target function is constructed, which represents the degree of difference between the model prediction value and the actual observed value;

[0069] A set of initial values is set for the model parameters, and the initial values can be obtained based on experience, historical data, or simple theoretical calculations;

[0070] By continuously adjusting the model parameters and recalculating the value of the target function until the target function reaches the minimum value or meets certain convergence conditions. In each iteration process, according to the gradient information of the target function (reflecting the direction in which the target function changes fastest), the adjustment direction and step size of the parameters are determined to gradually approach the optimal solution.

[0071] In this embodiment, by calculating the seepage performance deviation, the gap between the current seepage state of the dam body and the ideal state can be quantified, providing an objective evaluation basis. The preset error range is based on a large amount of historical data and engineering practices, with high scientificity and accuracy, ensuring the reliability of the evaluation results. By regularly calculating the seepage performance deviation and comparing it with the preset error range, changes in the seepage state of the dam body can be detected in a timely manner, providing an effective early warning mechanism. Dynamically adjusting the error range and model parameters according to the actual monitoring data ensures that the evaluation results always conform to the actual operating state of the dam body. When the seepage performance deviation is within the error range, there is no need to start a complex seepage parameter inversion prediction model, saving computing resources and time. When the seepage performance deviation exceeds the error range, by starting the seepage parameter inversion prediction model, potential safety hazards can be more accurately identified, and corresponding prevention and repair measures can be formulated. According to different situations of the deviation, the model parameters are flexibly selected and adjusted, improving the adaptability and prediction accuracy of the model. Not only considering the changes in a single parameter, but also combining data in multiple dimensions such as water head, seepage flow rate, and pore water pressure to comprehensively reflect the seepage state of the dam body.

[0072] In some embodiments of the present invention, the preset acquisition time interval is dynamically adjusted according to the environmental conditions of the dam body, seasonal changes, and extreme working conditions monitored in real time. Specifically:

[0073] The environmental conditions of the dam body are complex and diverse, including geological conditions (such as the geotechnical properties and geological structures of the dam foundation), hydrological conditions (such as changes in upstream and downstream water levels, rainfall, evaporation, etc.), and meteorological conditions (such as temperature, wind speed, etc.); the above environmental factors will all affect the seepage characteristics of the dam body; different environmental conditions will lead to differences in the seepage state of the dam body; for example, in areas with relatively complex geological conditions and large differences in the permeability of rock and soil, the seepage situation inside the dam body may be more complex and changeable, and at this time, it is necessary to collect data more frequently, that is, shorten the preset acquisition time interval, so as to capture the changes in the seepage state in time; while in areas with relatively simple and stable geological conditions, the seepage changes are relatively slow, and the acquisition time interval can be appropriately extended; similarly, when significant changes occur in hydrological conditions, such as a sudden increase in rainfall or a sharp change in the upstream and downstream water levels, parameters such as the seepage flow rate and water head of the dam body may change rapidly, and in order to accurately grasp the above changes, it is also necessary to shorten the acquisition time interval;

[0074] Seasonal changes will cause a series of factors related to the seepage of the dam body to change; for example, in the rainy season, the rainfall increases, the water head pressure borne by the dam body increases, and the seepage flow rate may increase significantly; while in the dry season, the rainfall decreases, and the seepage situation of the dam body is relatively stable; in addition, seasonal changes may also affect the physical properties of the rock and soil of the dam foundation, such as temperature changes may cause changes in the porosity and permeability of the rock and soil; based on the impact of seasonal changes on the seepage of the dam body, it is reasonable to adopt different preset acquisition time intervals in different seasons; in the rainy season or special periods such as floods that may occur, in order to timely grasp the seepage condition of the dam body and prevent safety accidents such as leakage and landslides, the acquisition time interval should be shortened; while in the dry season, the seepage of the dam body is relatively stable, and the acquisition time interval can be appropriately extended, which can not only meet the needs of monitoring the seepage state of the dam body, but also reduce the workload of data collection and processing;

[0075] During the real-time monitoring process, various extreme working conditions may be encountered, such as earthquakes, debris flows caused by heavy rainfall impacting the dam body, local damage to the dam body, etc.; the above extreme working conditions will have a serious impact on the structure and seepage characteristics of the dam body, and may cause the seepage state of the dam body to change violently in a short time; in order to cope with the above extreme working conditions and ensure the safety of the dam body, when an extreme working condition is monitored in real time, it is necessary to immediately adjust the preset acquisition time interval and shorten it; it can collect the seepage characteristic data of the dam body more intensively, capture the details of the seepage changes of the dam body under extreme working conditions in time, provide accurate data support for subsequent analysis and decision-making, so as to take effective emergency measures to ensure the safety of the dam body.

[0076] In some embodiments of the present invention, the seepage parameter inversion prediction model realizes the accurate prediction of the seepage characteristics of the dam body by combining the latest monitoring data (such as water head, seepage flow rate, and pore water pressure) and the optimized model parameters.

[0077] The seepage parameter inversion prediction model is mainly based on the seepage mechanics theory; this theory describes the flow law of fluids in porous media (such as the dam body material of a core rock-fill dam), including basic principles such as Darcy's law; Darcy's law states that the seepage velocity is proportional to the hydraulic gradient, and the proportionality coefficient is the permeability coefficient; through the above theory, the mathematical relationship between the seepage state of the dam body and the seepage parameters can be established, providing a theoretical basis for model construction;

[0078] The construction of the seepage parameter inversion prediction model relies on a large amount of monitoring data, including the water head, seepage flow rate, and pore water pressure at the set positions of the dam body; the above data is not only used for model training, enabling it to learn the characteristic patterns under different seepage states, but also serves as input during the model operation to drive the model to perform the inversion prediction of seepage parameters.

[0079] Specifically, the seepage parameter inversion prediction model adopts a model based on numerical simulation. Taking the finite element model as an example, by discretizing the dam body into a finite number of elements, establishing seepage control equations for each element, such as the continuity equation and the momentum equation, and solving them in combination with the boundary conditions; during the solution process, according to the input seepage characteristic data and model parameters, calculate the seepage variables (such as water head, flow velocity, etc.) within each element, and then obtain the seepage field distribution of the entire dam body; by continuously adjusting the model parameters, making the simulation results as consistent as possible with the actual monitoring data, thereby realizing the inversion of seepage parameters;

[0080] On the other hand, the seepage parameter inversion prediction model can also adopt a model based on machine learning. Taking the artificial neural network model as an example, it consists of an input layer, a hidden layer, and an output layer, and the layers are connected by neurons; during the training process, a large amount of dam body seepage characteristic data and their corresponding actual seepage parameters are used as training samples and input into the model. By adjusting the weights and thresholds between neurons, the model can learn the complex non-linear relationship between the input data and the seepage parameters; when a new set of dam body seepage characteristic data is input, the model can output the corresponding seepage parameter prediction values according to the learned relationship.

[0081] For a model based on numerical simulation, the training process mainly involves adjusting the model parameters to minimize the error between the simulation results and the actual monitoring data. Usually, optimization algorithms such as gradient descent method and Newton method are used to find the optimal combination of model parameters. For a model based on machine learning, the training process is to use a large number of training samples to train the model, adjust the weights and parameters of the model, so that it can accurately classify or regress the input data to obtain accurate prediction results of seepage parameters.

[0082] In actual engineering, the seepage parameter inversion prediction model can receive the seepage monitoring data of the dam in real time, and obtain the current seepage parameters of the dam through inversion prediction. Compare the above parameters with the preset safety thresholds. If it is found that the seepage parameters exceed the safety range, the model can send out early warning signals in time to remind engineering personnel to take corresponding measures, such as checking whether there is leakage in the dam and evaluating the risk of seepage deformation, etc., to ensure the safe operation of the dam. The prediction results can also provide support for engineering decisions. For example, in the dam maintenance and reinforcement project, according to the seepage parameters predicted by the model, engineering personnel can evaluate the impact of different maintenance plans on the seepage state of the dam and select the optimal plan. At the same time, in the design stage of a newly built core wall rockfill dam, referring to the results of the seepage parameter inversion prediction model of similar projects can optimize the design parameters of the dam and improve the anti-seepage performance and stability of the dam.

[0083] As Figure 2 shown, the seepage parameter inversion prediction system for the core wall rockfill dam of the present invention specifically includes the following modules;

[0084] The target score acquisition module is used to acquire the target seepage performance score of the dam.

[0085] The data acquisition module is used to collect the operation data of the core wall rockfill dam according to the preset acquisition time interval to obtain the dam seepage characteristic data set.

[0086] The real-time analysis module is used to analyze and obtain the real-time seepage performance score of the dam based on the obtained multiple dam seepage characteristic data sets.

[0087] The decision-making module is used to judge whether seepage inversion prediction is needed according to the real-time seepage performance score of the dam and the target seepage performance score of the dam; and when seepage inversion prediction is needed, determine the model parameters of the preset seepage parameter inversion prediction model.

[0088] The inversion prediction module is used to input the latest obtained dam seepage characteristic data set into the seepage parameter inversion prediction model with confirmed model parameters to obtain the inversion prediction result of the seepage parameters of the core wall rockfill dam.

[0089] In this embodiment, first, the data acquisition module collects data at preset intervals, and the real-time analysis module obtains the real-time seepage performance score based on this. Compared with the traditional method that relies on historical data, it can detect seepage anomalies in a timely manner and can also respond quickly under extreme working conditions or local damage, avoiding prediction lag. Second, the decision-making module improves the prediction accuracy and resource utilization efficiency. By comparing the real-time and target seepage performance scores, it only performs inversion prediction and determines the model parameters when necessary, avoiding unnecessary waste of computing resources and optimizing the model according to actual needs, making the inversion prediction more in line with the actual seepage situation of the dam and improving the prediction accuracy. Finally, the inversion prediction module ensures the safety of the dam. By inputting the latest data into the model with adapted parameters, the obtained inversion prediction results can provide a scientific basis for the seepage safety assessment of the dam, helping the staff to timely master the changes in the seepage characteristics of the dam, discover potential safety hazards in advance, and take effective measures to ensure the structural stability and long-term service performance of the dam.

[0090] The various variations and specific embodiments of the core wall rockfill dam seepage parameter inversion prediction method in the foregoing Embodiment 1 are equally applicable to the core wall rockfill dam seepage parameter inversion prediction system in this embodiment. Through the foregoing detailed description of the core wall rockfill dam seepage parameter inversion prediction method, those skilled in the art can clearly know the implementation method of the core wall rockfill dam seepage parameter inversion prediction system in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0091] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A seepage parameter inversion prediction method for a core rockfill dam, characterized in that Including: Obtain the target seepage performance score of the dam body; Collect the operation data of the core wall rockfill dam according to the preset acquisition time interval to obtain the dam body seepage characteristic data set; Based on the obtained multiple dam body seepage characteristic data sets, analyze and obtain the real-time seepage performance score of the dam body; Based on the real-time seepage performance score of the dam body and the target seepage performance score of the dam body, determine whether seepage inversion prediction is required; And when seepage inversion prediction is required, determine the model parameters of the preset seepage parameter inversion prediction model; Input the latest obtained dam body seepage characteristic data set into the seepage parameter inversion prediction model with confirmed model parameters to obtain the inversion prediction result of the seepage parameters of the core wall rockfill dam.

2. The seepage parameter inversion prediction method for core rock-fill dams according to claim 1, characterized in that Obtain the target seepage performance score of the dam body, including: Obtain the design standard of the core wall rockfill dam to be inverted, identify and extract the seepage parameter data thereof to obtain the target seepage parameter set; Conduct seepage performance analysis on the target seepage parameter set to obtain the target seepage performance score of the dam body.

3. The seepage parameter inversion prediction method for the core rockfill dam according to claim 2, characterized in that, The target seepage parameter set includes the target permeability coefficient and the target hydraulic gradient.

4. The seepage parameter inversion prediction method for the core wall rockfill dam according to claim 3, characterized in that, The dam body seepage characteristic data set includes the water head, seepage flow rate and pore water pressure at the set position of the dam body.

5. The seepage parameter inversion prediction method for the core rockfill dam according to claim 4, characterized in that Based on the obtained multiple dam body seepage characteristic data sets, analyze and obtain the real-time seepage performance score of the dam body, including: Sort and align the set number of dam body seepage characteristic data sets in the order of acquisition timestamps to obtain the dam body seepage characteristic matrix; Input the dam body seepage environment characteristic matrix into the pre-constructed seepage performance evaluation model to obtain the real-time seepage performance score of the dam body.

6. The seepage parameter back-analysis and prediction method for the core rock-fill dam according to claim 5, characterized in that, Based on the real-time seepage performance score of the dam body and the target seepage performance score of the dam body, determine whether seepage inversion prediction is required; And when seepage inversion prediction is required, determine the model parameters of the preset seepage parameter inversion prediction model, including: Calculate the seepage performance deviation amount according to the real-time seepage performance score of the dam body and the target seepage performance score of the dam body; Compare the seepage performance deviation amount with the preset error range: If the seepage performance deviation amount is within the preset error range, it indicates that the current seepage state is close to the ideal state and no inversion prediction is required; If the seepage performance deviation amount exceeds the preset error range, seepage inversion prediction is required, and the model parameters of the preset seepage parameter inversion prediction model are determined according to the seepage performance deviation amount.

7. The seepage parameter inversion prediction method for core rock-fill dams according to claim 5, characterized in that The seepage performance evaluation model is constructed using a multi-layer perceptron architecture. The number of input layer nodes is equal to the dimension of the seepage characteristic matrix. The hidden layer contains neurons with ReLU activation functions, and the output layer generates a normalized score value through the Sigmoid function.

8. The seepage parameter inversion prediction method for the core rockfill dam according to claim 1, characterized in that The preset acquisition time interval is dynamically adjusted according to the environmental conditions of the dam body, seasonal changes and extreme working conditions monitored in real time.

9. The seepage parameter inversion prediction method for the core rockfill dam according to claim 6, characterized in that The preset error range is comprehensively determined according to the historical operation data, design standard and safety margin of the core wall rockfill dam, and is regularly optimized and adjusted according to the latest obtained operation data.

10. A seepage parameter inversion prediction system for a core wall rockfill dam, characterized in that, Including: A target score acquisition module for obtaining the target seepage performance score of the dam body; A data acquisition module, which is used to collect the operation data of the core wall rockfill dam according to a preset acquisition time interval, and obtain a set of dam seepage characteristic data; A real-time analysis module, which is used to analyze and obtain the real-time seepage performance score of the dam based on the obtained multiple sets of dam seepage characteristic data; A decision-making module, which is used to judge whether seepage inversion prediction is needed according to the real-time seepage performance score of the dam and the target seepage performance score of the dam; And when seepage inversion prediction is needed, determine the model parameters of a preset seepage parameter inversion prediction model; An inversion prediction module, which is used to input the latest obtained set of dam seepage characteristic data into the seepage parameter inversion prediction model with confirmed model parameters, and obtain the inversion prediction result of the seepage parameters of the core wall rockfill dam.

Images