Face leakage prediction method and system suitable for concrete face rockfill dam

Abstract

The invention provides a face leakage prediction method suitable for a concrete face rockfill dam, which comprises the following steps: S1, counting first crack parameter information of a face of the concrete face rockfill dam, and then obtaining probability distribution information corresponding to the first crack parameter information through a nuclear density estimation method; s2, establishing a plurality of optimized water conservancy professional agent models in one-to-one correspondence with each small block panel of the concrete face rockfill dam; s3, performing one-to-one correspondence prediction through each optimized water conservancy professional agent model to obtain the leakage amount of each small block panel; s4, summing the leakage amounts of the panels of all the small blocks obtained in the step S3 so as to obtain the total leakage amount of the panels of the concrete face rockfill dam under the condition that the cracks exist; the invention further provides a face leakage prediction system suitable for the concrete face rockfill dam. The method can accurately and efficiently predict the face leakage of the concrete face rockfill dam with the face cracks.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent analysis of concrete face slab leakage of rockfill dams, and specifically relates to a method and system for predicting the leakage volume of the face slab applicable to concrete face rockfill dams. Background Art

[0002] Concrete face rockfill dams have become one of the most widely used dam types in water conservancy and hydropower projects due to their advantages such as simple construction, short engineering cycle, strong seismic resistance, and low cost. However, under the influence of water level, environmental temperature, complex geological conditions, and dam filling quality, the concrete face slab may produce a complex stress-strain state, ultimately leading to the generation of face slab cracks. Face slab cracks will have a greater impact on the integrity and working state of the concrete face slab structure, and will greatly reduce the anti-seepage performance of the concrete face slab. At the same time, in recent years, with the rapid development of digital twin technology, higher requirements have been put forward for the finite element calculation of dam seepage under different working conditions. It is necessary to quickly complete the calculation and analysis of reservoir dam seepage based on engineering measured data to judge the safety state of the dam in real time. Therefore, establishing a surrogate model that can accurately and quickly calculate the leakage volume in the face slab crack area under the condition of face slab cracks and realizing the prediction of the overall face slab leakage volume of the dam is of great significance for analyzing the operation state of concrete face rockfill dams and the establishment of digital twin systems.

[0003] For the calculation of the leakage volume of concrete face rockfill dams with face slab cracks, common numerical calculation methods include the finite element method (FEM), finite difference method (FDM), and finite volume method (FVM), etc. These methods are based on Darcy's law and the continuity equation. By discretizing the calculation area and solving the control equation, they can simulate the distribution of complex seepage fields. For the treatment of cracks, the equivalent permeability coefficient method and the discrete crack model are mainly used. In the equivalent permeability coefficient method, the crack area of the concrete face slab is regarded as a high-permeability material and an equivalent permeability coefficient is given; the discrete crack model regards the face slab crack as an independent entity, models it separately, and considers its geometric characteristics and permeability characteristics. Although the existing methods have made significant progress in seepage analysis, there are still some limitations. For example, problems such as the complexity of crack geometry, the uncertainty of material properties, and multi-physical field coupling limit the calculation accuracy and efficiency. In addition, when dealing with large-scale engineering problems, the existing methods have a high calculation cost and are difficult to meet the actual engineering needs. Therefore, developing an efficient and accurate calculation method for predicting the leakage volume of concrete face rockfill dams with face slab cracks has important engineering significance and application value. Summary of the Invention

[0004] In view of this, it is necessary to address the above problems and propose a method and system for predicting the leakage volume of the face slab applicable to concrete face rockfill dams to overcome several disadvantages in the above background art, thereby solving the following technical problems:

[0005] How to accurately and efficiently predict the leakage volume of the concrete face slab of a concrete face rockfill dam with face slab cracks, so as to provide a precise and reliable data basis for the digital twin model or operation state analysis involving the concrete face rockfill dam.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] The present invention proposes a method for predicting the leakage volume of the face slab of a concrete face rockfill dam, which respectively conducts statistical analysis on the face slabs of each small block of the concrete face rockfill dam. It is characterized in that the method for predicting the leakage volume of the face slab includes:

[0008] Step S1, statistically analyze a first crack parameter information of the face slab of the concrete face rockfill dam, and then obtain the probability distribution information corresponding to the first crack parameter information through a kernel density estimation method; the first crack parameter information includes the total number of cracks on the face slab of the concrete face rockfill dam and the crack shape parameters of the face slab of the concrete face rockfill dam; the crack shape parameters of the face slab of the concrete face rockfill dam include the face slab crack length, the equivalent width of the face slab crack, and the absolute roughness of the face slab crack surface;

[0009] Step S2, establish a plurality of optimized water conservancy professional proxy models respectively corresponding to the face slabs of each small block of the concrete face rockfill dam; the optimized water conservancy professional proxy models are optimized and adjusted through a co-kriging model and a Genghis Khan shark optimizer algorithm, and are used to predict the leakage volume of the face slabs of the small blocks of the concrete face rockfill dam;

[0010] Step S3, respectively predict and obtain the leakage volume of each small block face slab through each of the optimized water conservancy professional proxy models;

[0011] Step S4, sum up the leakage volumes of each small block face slab obtained in Step S3, so as to obtain the total leakage volume of the face slab of the concrete face rockfill dam under the condition of cracks.

[0012] Further, in Step S2, the establishment process of the optimized water conservancy professional proxy model includes the following steps:

[0013] Step S21, according to the probability distribution information obtained in Step S1 and using a Latin hypercube sampling method to sample the face slabs of the small blocks of the concrete face rockfill dam with respect to the number of cracks, so as to obtain a first data set including the number of cracks on the face slabs of the small blocks of the concrete face rockfill dam;

[0014] Step S22, sampling crack shape parameters of the small block panels of the concrete face rockfill dam according to the total number of cracks of the panels of the concrete face rockfill dam obtained by statistics in step S1 and using the Latin hypercube sampling method, thereby obtaining a second data set including crack shape parameters of the small block panels of the concrete face rockfill dam; the small block panel crack shape parameters include small block panel crack length, small block panel crack equivalent width and small block panel crack surface absolute roughness;

[0015] Step S23, combining the first data set and the second data set to establish a proxy model input parameter data set;

[0016] Step S24, obtaining the equivalent permeability coefficient of the small block panel area corresponding to the concrete face rockfill dam according to the proxy model input parameter data set obtained in step S23;

[0017] Step S25, obtaining the finite element calculated leakage of the small block panel of the concrete face rockfill dam by a finite element method based on the equivalent permeability coefficient obtained in step S23;

[0018] Step S26, coordinate the number of cracks in the small block panels, the crack shape parameters of the small block panels and the finite element calculated leakage of the small block panels to obtain coordinated data including a training set and a test set, input the coordinated data into and adjust the co-kriging model, and then optimize the adjusted co-kriging model hyperparameters through a Genghis Khan shark optimizer algorithm, thereby establishing multiple optimized water conservancy professional agent models for predicting the leakage of small block panels of concrete panel rockfill dams.

[0019] Furthermore, step S25 includes the following sub-steps:

[0020] Step S251, obtaining a COMSOL calculation file of a nonlinear finite element analysis software;

[0021] Step S252, calling the COMSOL calculation file, recording the finite element calculation leakage of the small block panel of the concrete face rockfill dam, and merging it with the proxy model input parameter data set generated in step S23;

[0022] Step S253, determining whether the number of times the COMSOL calculation file is currently called reaches a preset threshold, if so, executing step S26, otherwise returning to executing step S252.

[0023] Furthermore, between step S25 and step S26, the panel leakage prediction method applicable to the concrete panel rockfill dam further includes:

[0024] Step S2526: Combine the number of small-block panel cracks obtained in step S21, the small-block panel crack shape parameters obtained in step S22, and the finite element calculated leakage amount of the small-block panel obtained in step S25 into a set of panel rockfill dam small-block panel crack parameters - panel rockfill dam small-block panel leakage amount data set.

[0025] Step S26 includes the following sub-steps:

[0026] Step S261: Pool the panel rockfill dam small-block panel crack parameters - panel rockfill dam small-block panel leakage amount data set obtained in step S2526 into a training set and a test set, so as to obtain training set and test set data; the training set and test set data include the second crack parameter information after pooling and the finite element calculated leakage amount of the small-block panel corresponding to the second crack parameter information after pooling; the second crack parameter information includes the number of small-block panel cracks after pooling and the small-block panel crack shape parameters after pooling.

[0027] Step S262: Take the second crack parameter information obtained in step S261 as the independent variable, take the finite element calculated leakage amount of the small-block panel corresponding to the second crack parameter information after pooling as the dependent variable, and input the independent variable and the dependent variable into a first co-kriging model, so as to establish an adjusted second co-kriging model for expressing the relationship between the leakage amount of the small-block panel with panel cracks and the crack parameters, and calculate the root mean square error of the leakage amount between the second co-kriging model and the test set.

[0028] Step S263: Take the root mean square error obtained in step S262 as the fitness function value, and use the Genghis Khan shark optimizer algorithm to optimize the hyperparameters of the second co-kriging model several times, so as to obtain a third co-kriging model with the smallest root mean square error of the test set under the condition of the optimal number of optimizations.

[0029] Furthermore, in step S263, determine the upper and lower limits of the hyperparameter values of the second co-kriging model.

[0030] Furthermore, step S263 includes the following sub-steps:

[0031] Step S2631: Determine the maximum number of iterations k in the Genghis Khan shark optimizer algorithm max , and set the number of shark populations to S n ;

[0032] Step S2632: Use the Genghis Khan shark optimizer algorithm to continuously iterate and call the relationship between the input and output sample data, and determine the optimal hyperparameters of the co-kriging model by solving the optimal solution of an objective function, so as to obtain an optimal optimized water conservancy professional agency model.

[0033] Furthermore, the objective function in the step S2632 is as follows:

[0034]

[0035] In formula (1), n1 is the number of data in the test set; h i is the finite element calculated value; h i ' is the surrogate model calculated value.

[0036] Furthermore, in step S24, when it is considered that there is no water flow exchange in the horizontal direction of the concrete panel, for an equal-width crack with length a and width b, the water flow through the crack presents laminar flow characteristics, and the water flow characteristics in the crack are shown as follows:

[0037]

[0038] In formulas (2) and (3), v x (y) is the water flow velocity in the x direction of the crack length; p is the water flow fluid pressure; μ is the dynamic viscosity coefficient of the water flow; q is the water flow rate per unit width of the crack; J is the hydraulic gradient; γ is the unit weight of water; y is the longitudinal coordinate value in the coordinate system of the equal-width fissure water flow;

[0039] Formulas (2) and (3) are derived based on the assumption of a smooth surface crack. The calculation methods of the roughness correction coefficient C and the equivalent crack width b e are as follows:

[0040]

[0041] In formulas (4) and (5), b0 and b t are the inlet width and outlet width of the crack; Δ is the absolute roughness of the crack surface; is the relative roughness of the crack;

[0042] The equivalent permeability coefficient K of a single crack is calculated through formulas (2) to (5) fe The calculation formula is as follows:

[0043]

[0044] In formula (6), if there are a large number of cracks on the concrete panel, by selecting a small-size area on the panel, assuming the length of the area is l, the width is d, the number of cracks in the area is n, the length of the crack is m, and γ is the unit weight of water; according to the principle that the seepage flow through the cracks on the small-size area panel is equal to the seepage flow through the equivalent intact panel, the permeability coefficient K of the equivalent small-area panel can be obtained y The calculation formula is as follows:

[0045]

[0046] In formula (7), Ci is the roughness correction coefficient of the i-th crack; b ei is the equivalent crack width of the i-th crack; since the length m of the crack on the panel may not be equal to the length l of the selected small-size area, the calculation formula for the equivalent permeability coefficient for different panel crack lengths in the small-size area of the panel is as follows:

[0047]

[0048] In formula (8), m i is the length of the i-th crack; γ is the unit weight of water.

[0049] The present invention further provides a panel leakage prediction system applicable to a concrete face rockfill dam, including:

[0050] A probability distribution information analysis module, which statistically analyzes a first crack parameter information of the panel of the concrete face rockfill dam, and then obtains the probability distribution information corresponding to the first crack parameter information through a kernel density estimation method; the first crack parameter information includes the total number of cracks on the panel of the concrete face rockfill dam and the crack shape parameter of the panel of the concrete face rockfill dam; the crack shape parameter of the panel of the concrete face rockfill dam includes the panel crack length, the equivalent width of the panel crack, and the absolute roughness of the panel crack surface;

[0051] A sampling analysis module, which is used to obtain a first data set and a second data set, and combines the first data set and the second data set to establish a proxy model input parameter data set; according to the probability distribution information obtained by the probability distribution information analysis module and using a Latin hypercube sampling method to sample the small-block panel of the concrete face rockfill dam with respect to the number of cracks, so as to obtain a first data set including the number of cracks on the small-block panel of the concrete face rockfill dam; according to the total number of cracks on the panel of the concrete face rockfill dam statistically obtained in step S1 and using the Latin hypercube sampling method to sample the small-block panel of the concrete face rockfill dam with respect to the crack shape parameter, so as to obtain a second data set including the crack shape parameter of the small-block panel of the concrete face rockfill dam; the crack shape parameter of the small-block panel includes the small-block panel crack length, the equivalent width of the small-block panel crack, and the absolute roughness of the small-block panel crack surface;

[0052] An equivalent permeability coefficient acquisition module, which is used to obtain the equivalent permeability coefficient corresponding to the small-block panel area of the concrete face rockfill dam according to the proxy model input parameter data set obtained by the sampling analysis module;

[0053] A finite element analysis module, used for obtaining the finite element calculated leakage of the small block panel of the concrete face rockfill dam through a finite element method according to the equivalent permeability coefficient obtained by the equivalent permeability coefficient acquisition module;

[0054] An optimized water conservancy professional agent model acquisition module is used to coordinate the number of cracks in the small block panel, the crack shape parameters of the small block panel and the finite element calculated leakage of the small block panel to obtain coordinated data including a training set and a test set, input the coordinated data into and adjust the co-kriging model, and then optimize the adjusted co-kriging model hyperparameters through a Genghis Khan shark optimizer algorithm, so as to establish multiple optimized water conservancy professional agent models for predicting the leakage of the small block panel of the concrete panel rockfill dam; the co-kriging model is used to establish a prediction model for the leakage of the small block panel of the rockfill dam; the Genghis Khan shark optimizer algorithm is used to optimize the hyperparameters of the co-kriging model, so as to improve the prediction accuracy of the co-kriging model;

[0055] A leakage prediction module for small block panels, used to predict the leakage of each small block panel one by one through each optimized water conservancy professional agent model obtained by the optimized water conservancy professional agent model acquisition module;

[0056] The total leakage acquisition module is used to sum the leakage of each small block panel obtained by the leakage prediction module of the small block panel, so as to obtain the total leakage of the panel of the concrete panel rockfill dam under the condition of cracks.

[0057] The present invention further proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the panel leakage prediction method applicable to concrete panel rockfill dams as described in any one of the above items are implemented.

[0058] The beneficial effects of the present invention are:

[0059] The present invention can accurately and efficiently predict the panel leakage of a concrete panel rockfill dam with panel cracks, and can also quickly complete the calculation and analysis of the reservoir dam seepage based on the actual engineering data, so as to make real-time judgment on the safety status of the dam, thereby providing an accurate and reliable data basis for the digital twin model or operation status analysis involving the concrete panel rockfill dam; the present invention greatly improves the calculation accuracy and efficiency of the panel leakage of a concrete panel rockfill dam with panel cracks, and reduces the calculation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are included to provide a further understanding of the present invention, and are incorporated into and constitute a part of this specification. The accompanying drawings illustrate exemplary embodiments of the present invention and, together with the description, are used to explain the principles of the present invention. These drawings are for illustration only and are not intended to limit the present invention.

[0061] Figure 1 It is a work flow chart of the panel leakage prediction method applicable to concrete panel rockfill dam of the present invention;

[0062] Figure 2 It is a structural dissection demonstration diagram of a concrete face rockfill dam corresponding to the calculation of equivalent permeability coefficient of face plate crack area involved in the present invention;

[0063] Figure 3 It is a structural schematic diagram of two models for comparing concrete face rockfill dams involved in the present invention;

[0064] Figure 4 It is a schematic diagram of a three-dimensional simulation model under different water head pressures applicable to a concrete face rockfill dam according to the present invention;

[0065] Figure 5 It corresponds to Figure 4 A cross-sectional view showing the maximum cross-section of the three-dimensional simulation model, which is used to reflect the seepage calculation results when cracks exist in the panel;

[0066] Figure 6 The invention relates to a fitness function process line diagram of a Genghis Khan shark optimizer algorithm for optimizing a collaborative Kriging model;

[0067] Figure 7 The present invention relates to a comparative analysis diagram of leakage prediction value based on a water conservancy professional proxy model and a finite element calculation value;

[0068] Figure 8 It is a structural principle diagram of a panel leakage prediction system applicable to a concrete panel rockfill dam of the present invention;

[0069] Description of reference numerals:

[0070] Concrete face rockfill dam 10 ; face plate 101 ; crack 1011 ; water load F1 ; equivalent concrete face plate 102 ; crack region 104 ; cushion layer 103 ; transition layer 105 ; dam body 100 . DETAILED DESCRIPTION

[0071] To make the objectives, technical solutions and advantages of the present invention clearer, the following will, in combination with the embodiments of the present invention, further clearly and completely describe the technical solutions of the present invention. It should be noted that the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0072] Terms such as "first", "second", "third", "fourth", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", "third", "fourth" may explicitly or implicitly include one or more of such features.

[0073] The following is a detailed description of the embodiments of the present invention depicted in the accompanying drawings. The embodiments are detailed to clearly convey the present invention. However, the quantity of details provided is not intended to limit the expected variations of the embodiments; on the contrary, the aim is to cover all modifications, equivalents and alternatives that fall within the spirit and scope of the present invention defined by the appended claims.

[0074] In the following description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present invention. It will be apparent to those skilled in the art that embodiments of the present invention can be practiced without some of these specific details.

[0075] The embodiments of the present invention include various steps, which will be described below. These steps can be executed by hardware components or can be included in machine-executable instructions, which can be used to program a general or special-purpose processor with instructions to execute these steps. Alternatively, the steps can be executed by a combination of hardware, software and firmware and / or an artificial operator.

[0076] The various methods described herein can be practiced by combining one or more machine-readable storage media containing code according to the present invention with appropriate standard computer hardware to execute the code contained therein. The apparatus for implementing the various embodiments of the present invention can include one or more computers (or one or more processors within a single computer) and a storage system having network access and containing or having a computer program encoded with the various methods described herein, and the method steps of the present invention can be completed by modules, routines, subroutines or sub-parts of a computer program product.

[0077] If the specification states that a component or feature "may", "is capable of", "can" or "might" include or have a feature, it is not necessary to include that particular component or feature or have that feature.

[0078] As used in the specification of the present application and the following claims, the meanings of "a", "an" and "the" include plural referents unless the context clearly dictates otherwise. Further, as used in the description herein, unless the context clearly dictates otherwise, the meaning of "in" includes "in" and "on".

[0079] Exemplary embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments are shown. These exemplary embodiments are provided for illustrative purposes only and so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those of ordinary skill in the art. However, the disclosed invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Various modifications will be readily apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present invention. In addition, all statements herein reciting embodiments of the present invention and specific examples thereof are intended to cover their structural and functional equivalents. Additionally, these equivalents are intended to include both currently known equivalents as well as equivalents developed in the future (i.e., any elements developed that perform the same function regardless of structure). Moreover, the terminology and phraseology used herein is for the purpose of describing exemplary embodiments and should not be regarded as limiting. Accordingly, the present invention is to be accorded the broadest scope, including various substitutions, modifications and equivalents consistent with the disclosed principles and features. For the sake of clarity, details of technical materials known in the technical fields related to the present invention have not been described in detail so as not to unnecessarily obscure the present invention.

[0080] Thus, for example, those of ordinary skill in the art will understand that diagrams, schematics, illustrations, etc. represent conceptual views or processes of systems and methods embodying the present invention. The functions of the various elements shown in the figures can be provided by using dedicated hardware as well as hardware capable of executing associated software. Similarly, any switches shown in the figures are merely conceptual. Their functions can be performed by the operation of program logic, by dedicated logic, by the interaction of program control and dedicated logic, or even manually, with the particular technique being selectable by the entity implementing the present invention. Those of ordinary skill in the art should further understand that the exemplary hardware, software, processes, methods and / or operating systems described herein are for illustrative purposes and are thus not intended to be limited to any particular named elements.

[0081] Embodiments of the present invention may provide a computer program product, which may include a machine-readable storage medium having instructions tangibly implemented thereon, which may be used to program a computer (or other electronic device) to perform a process. The term "machine-readable storage medium" or "computer-readable storage medium" includes, but is not limited to, fixed (hardware) drives, magnetic tapes, floppy disks, optical disks, compact disk read-only memory (CD-ROMs), and magneto-optical disks, semiconductor memories such as ROMs, PROMs, random access memories (RAMs), programmable read-only memories (PROMs), erasable PROMs (EPROMs), electrically erasable PROMs (EEPROMs), flash memories, magnetic or optical cards, or other types of media / machine-readable media suitable for storing electronic instructions (e.g., computer programming code such as software or firmware). The machine-readable medium may include non-transitory media, where data may be stored and does not include carrier waves and / or transient electronic signals propagated by wireless or wired connections. Examples of non-transitory media may include, but are not limited to, magnetic disks or tapes, optical storage media such as compact disks (CDs) or digital versatile disks (DVDs), flash memories, memories or memory devices. The computer program product may include code and / or machine-executable instructions, which may represent any combination of processes, functions, subroutines, programs, routines, subroutines, modules, software packages, classes, or instructions, data structures, or program statements. By passing and / or receiving information, data, variables, parameters, or memory contents, a code segment may be coupled to another code segment or a hardware circuit. The information, variables, parameters, data, etc. may be passed, forwarded, or transmitted by any suitable means, including memory sharing, message passing, token passing, network transmission, etc.

[0082] In addition, embodiments may be implemented by hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof. When implemented in software, firmware, middleware, or microcode, the program code or code segments (e.g., computer program product) for performing the necessary tasks may be stored in a machine-readable medium. The processor may execute the necessary tasks.

[0083] The systems depicted in some of the figures may be provided in various configurations. In some embodiments, the system may be configured as a distributed system, where one or more components of the system are distributed across one or more networks in a cloud computing system.

[0084] Each of the appended claims defines a separate invention, which for purposes of infringement is considered to include equivalents of the various elements or limitations specified in the claim. Depending on the context, all references to "the invention" in the following may in some cases refer only to certain specific embodiments. In other cases, it should be recognized that references to "the invention" will refer to the subject matter described in one or more but not necessarily all of the claims.

[0085] Unless otherwise specified herein or clearly contradicted by the context, all methods described herein can be performed in any suitable order. The use of any and all examples or exemplary language (e.g., "such as") provided with respect to certain embodiments herein is merely intended to better illustrate the invention and does not limit the scope of the claimed invention. Any language in the specification should not be construed as indicating any unclaimed element essential to the practice of the invention.

[0086] The various terms used herein are shown below. In the case where terms used in the claims are not defined below, the broadest definition should be given, which has been reflected in printed publications and issued patents at the time of filing the application by those skilled in the relevant art.

[0087] Embodiment 1

[0088] As Figures 1 - 7 shown:

[0089] where Figure 2 the graph of area (g) is used to display the cracks of the face slab of the concrete face rockfill dam, Figure 2 the graph of area (a) is used to locally magnify and display Figure 2 an area of the graph of area (g), Figure 2 the graph of area (b) is used to reflect the equivalent permeability coefficient of the face slab of the concrete face rockfill dam; where Figure 3 the graph of area (c) is used to display the model of the concrete face rockfill dam, Figure 3 the graph of area (d) is used to display the sectional structure of the model of the concrete face rockfill dam, Figure 3 the graph of area (e) is used to display the overall finite element model of the concrete face rockfill dam, Figure 3 the graph of area (f) is used to display the crack model of a local area of the overall finite element model of the concrete face rockfill dam; where Figure 4 and Figure 5 "Water Head" of is the water head; where Figure 6 the horizontal axis coordinate of is the number of iterations, Figure 6 the vertical axis coordinate of is the fitness function value; where Figure 7 the horizontal axis coordinate of is the finite element calculated value, Figure 7 the vertical axis coordinate of is the surrogate model calculated value, Figure 7 "Scope" of is the scope;

[0090] This embodiment proposes a method for predicting the leakage volume of the face slab of a concrete face rockfill dam. Statistical analysis is performed on each small-block face slab of the concrete face rockfill dam 10 respectively. The method for predicting the leakage volume of the face slab includes:

[0091] Step S1, count the first crack parameter information of the concrete face slab 101 of the concrete face rockfill dam 10, and then obtain the probability distribution information corresponding to the first crack parameter information through a kernel density estimation method; the first crack parameter information includes the total number of cracks n of the concrete face slab 101 of the concrete face rockfill dam 10 and the crack shape parameter of the concrete face slab 101 of the concrete face rockfill dam 10; the crack shape parameter of the concrete face slab 101 of the concrete face rockfill dam 10 includes the face slab crack length m, the equivalent width b of the face slab crack e and the absolute roughness Δ of the face slab crack surface c ;

[0092] Step S2, establish a plurality of optimized water conservancy professional agent models corresponding to each small-block face slab of the concrete face rockfill dam 10 one by one; the optimized water conservancy professional agent model is optimized and adjusted through a co-kriging model and a Genghis Khan shark optimizer algorithm, and is used to predict the leakage volume of the small-block face slab of the concrete face rockfill dam

[0093] Step S3, predict and obtain the leakage volume of each small-block face slab through each of the optimized water conservancy professional agent models one by one

[0094] Step S4, sum up the leakage volumes of each small-block face slab obtained in Step S3, so as to obtain the total leakage volume of the concrete face slab 101 of the concrete face rockfill dam 10 under the condition of cracks

[0095] After obtaining accurate face slab crack information, the present invention can quickly and accurately calculate the leakage volume of the face rockfill dam in the small-block face slab area, and then obtain the total leakage volume of the face slab of the concrete face rockfill dam under the condition of cracks, which provides strong support for the prediction of the leakage volume of the concrete face rockfill dam and the establishment of the digital twin system

[0096] Optimally, in Step S2, the establishment process of the optimized water conservancy professional agent model includes the following steps

[0097] Step S21, according to the probability distribution information obtained in Step S1 and using a Latin hypercube sampling method to sample the small-block face slab of the concrete face rockfill dam 10 with respect to the number of cracks, so as to obtain a first data set including the number of cracks of the small-block face slab of the concrete face rockfill dam 10

[0098] Step S22, sampling the crack shape parameters of the small block panels of the concrete face rockfill dam 10 according to the total number of cracks of the panel 101 of the concrete face rockfill dam 10 obtained by statistics in step S1 and using the Latin hypercube sampling method, thereby obtaining a second data set including the crack shape parameters of the small block panels of the concrete face rockfill dam 10; the small block panel crack shape parameters include the small block panel crack length, the equivalent width of the small block panel crack and the absolute roughness of the small block panel crack surface;

[0099] Step S23, combining the first data set and the second data set to establish a proxy model input parameter data set;

[0100] Step S24, obtaining the equivalent permeability coefficient of the small block panel area corresponding to the concrete face rockfill dam 10 according to the proxy model input parameter data set obtained in step S23;

[0101] Step S25, obtaining the finite element calculated leakage of the small block panel of the concrete face rockfill dam 10 by a finite element method based on the equivalent permeability coefficient obtained in step S23;

[0102] Step S26, coordinate the number of cracks in the small block panels, the crack shape parameters of the small block panels and the finite element calculated leakage of the small block panels to obtain coordinated data including a training set and a test set, input the coordinated data into and adjust the co-kriging model, and then optimize the adjusted co-kriging model hyperparameters through a Genghis Khan shark optimizer algorithm, thereby establishing multiple optimized water conservancy professional agent models for predicting the leakage of small block panels of concrete panel rockfill dams.

[0103] Optimally, step S25 includes the following sub-steps:

[0104] Step S251, obtaining a COMSOL calculation file of a nonlinear finite element analysis software;

[0105] Step S252, calling the COMSOL calculation file, recording the finite element calculation leakage of the small block panel of the concrete face rockfill dam 10, and merging it with the proxy model input parameter data set generated in step S23;

[0106] Step S253, determining whether the number of times the COMSOL calculation file is currently called reaches a preset threshold, if so, executing step S26, otherwise returning to executing step S252.

[0107] Specifically, the COMSOL calculation file involves the entire process of model construction and calculation. The COMSOL calculation file includes preprocessing information: dam model, dam body partition, material parameter information, boundary condition information, etc.

[0108] Preferably, between step S25 and step S26, the method for predicting the leakage volume of the concrete face slab of a concrete face rockfill dam further includes:

[0109] Step S2526: Combine the number of cracks in the small-block face slab obtained in step S21, the crack shape parameters of the small-block face slab obtained in step S22, and the finite element calculated leakage volume of the small-block face slab obtained in step S25 into a set of data on the crack parameters of the small-block face slab of the concrete face rockfill dam - the leakage volume of the small-block face slab of the concrete face rockfill dam.

[0110] Step S26 includes the following sub-steps:

[0111] Step S261: Coordinate the data on the crack parameters of the small-block face slab of the concrete face rockfill dam - the leakage volume of the small-block face slab of the concrete face rockfill dam obtained in step S2526 into a training set and a test set, so as to obtain the training set and test set data; the training set and test set data include the second crack parameter information after coordination and the finite element calculated leakage volume of the small-block face slab corresponding to the coordinated second crack parameter information; the second crack parameter information includes the number of cracks in the small-block face slab after coordination and the crack shape parameters of the small-block face slab after coordination.

[0112] Step S262: Use the second crack parameter information obtained in step S261 as the independent variable, use the finite element calculated leakage volume of the small-block face slab corresponding to the coordinated second crack parameter information as the dependent variable, and input the independent variable and the dependent variable into a first co-Kriging model, so as to establish an adjusted second co-Kriging model for expressing the relationship between the leakage volume of the small-block face slab with panel cracks and the crack parameters, and calculate the root mean square error of the leakage volume between the second co-Kriging model and the test set.

[0113] Step S263: Use the root mean square error obtained in step S262 as the fitness function value, and use the Genghis Khan shark optimizer algorithm to optimize the hyperparameters of the second co-Kriging model several times, so as to obtain a third co-Kriging model with the smallest root mean square error of the test set under the condition of the optimal number of optimizations.

[0114] Specifically, in step S2, by calling the COMSOL calculation file to record the leakage volume of the small-block face slab, combining the generated panel crack parameters, merging to obtain a panel crack parameter - leakage volume data set, and then using the co-Kriging method to construct a surrogate model for calculating the panel crack parameter - seepage flow, and combining the Genghis Khan shark optimizer to optimize the hyperparameters of the surrogate model to obtain an optimal fitting model, which can not only quickly and reliably obtain the optimal surrogate model, thus ensuring the accuracy of the subsequent calculation of the leakage volume of the concrete face rockfill dam 10 with panel cracks.

[0115] Optimally, in step S263, the upper and lower limits of the value of the hyperparameter θ of the second co-kriging model are determined.

[0116] Optimally, step S263 includes the following sub-steps:

[0117] Step S2631, determining the maximum number of iterations k in the Genghis Khan Shark Optimizer algorithm max , set the shark population to S n ;

[0118] Step S2632, using the Genghis Khan Shark Optimizer algorithm to continuously iterate and call the relationship between the input and output sample data, and by solving the optimal solution of an objective function, determine the optimal hyperparameters of the co-kriging model, thereby obtaining the optimal optimized water conservancy professional agent model.

[0119] Optimally, the objective function in step S2632 is:

[0120]

[0121] In formula (1), n1 is the number of test set data; h i is the finite element calculation value; h i 'Calculate values for the proxy model.

[0122] Optimally, in step S24, when it is considered that no water flow exchange occurs in the horizontal direction of the concrete panel 101, for equal-width cracks with a length of a and a width of b, the water flow through the crack exhibits laminar flow characteristics, and the water flow characteristics in the crack are shown as follows:

[0123]

[0124]

[0125] In formula (2) and formula (3), v x (y) is the flow velocity of the water in the fracture length direction x; p is the water flow fluid pressure; μ is the dynamic viscosity coefficient of the water flow; q is the water flow rate per unit width of the fracture; J is the hydraulic gradient; γ is the specific gravity of water; y is the longitudinal coordinate value in the coordinate system of the water flow in the fracture with equal width;

[0126] Formula (2) and Formula (3) are derived based on the assumption of smooth surface cracks. The roughness correction coefficient C and equivalent crack width b are e The calculation method is as follows:

[0127]

[0128] In formula (4) and formula (5), b0 and b tare the inlet width and outlet width of the crack; Δ is the absolute roughness of the crack surface; is the relative roughness of the crack; however, in actual engineering, for the horizontal through-cracks in the concrete slab, the crack width may change along the water flow direction, and there are rough undulations on the crack surface. Therefore, an equivalent crack width and roughness correction method is adopted to correct the water flow characteristics in the actual crack;

[0129] The equivalent permeability coefficient K of a single crack is calculated through formulas (2) to (5) fe The calculation formula is as follows:

[0130]

[0131] In formula (6), if there are a large number of cracks on the concrete slab 101, by selecting a small-size area on the slab 101, assuming the length of this area is l, the width is d, the number of cracks in the area is n, the length of the crack is m, and γ is the unit weight of water; according to the principle that the seepage flow through the cracks in the small-size area of the slab is equal to the seepage flow through the equivalent intact slab, the permeability coefficient K of the small area slab after equivalence can be obtained y The calculation formula is as follows:

[0132]

[0133] In formula (7), Ci is the roughness correction coefficient of the i-th crack; b ei is the equivalent crack width of the i-th crack; since the length m of the crack on the slab 101 may not be equal to the length l of the selected small-size area, the calculation formula for the equivalent permeability coefficient for different crack lengths in the small-size area of the slab 101 is as follows:

[0134]

[0135] In formula (8), m i is the length of the i-th crack; γ is the unit weight of water.

[0136] Embodiment 2

[0137] As Figures 2 - 8 shown:

[0138] This embodiment proposes a panel leakage prediction system applicable to concrete face rockfill dams, including:

[0139] The probability distribution information analysis module statistically analyzes the first crack parameter information of the concrete face slab 101 of the concrete face rockfill dam 10, and then obtains the probability distribution information corresponding to the first crack parameter information through a kernel density estimation method; the first crack parameter information includes the total number of cracks in the concrete face slab 101 of the concrete face rockfill dam 10 and the crack shape parameter of the concrete face slab 101 of the concrete face rockfill dam 10; the crack shape parameter of the concrete face slab 101 of the concrete face rockfill dam 10 includes the length of the face slab crack, the equivalent width of the face slab crack, and the absolute roughness of the face slab crack surface;

[0140] The sampling analysis module is used to obtain a first data set and a second data set, and combines the first data set and the second data set to establish a proxy model input parameter data set; according to the probability distribution information obtained by the probability distribution information analysis module and using a Latin hypercube sampling method, sampling is performed on the small-block face slabs of the concrete face rockfill dam 10 regarding the number of cracks, so as to obtain a first data set including the number of cracks in the small-block face slabs of the concrete face rockfill dam 10; according to the total number of cracks in the concrete face slab 101 of the concrete face rockfill dam 10 statistically obtained in step S1 and using the Latin hypercube sampling method, sampling is performed on the small-block face slabs of the concrete face rockfill dam 10 regarding the crack shape parameter, so as to obtain a second data set including the crack shape parameter of the small-block face slabs of the concrete face rockfill dam 10; the crack shape parameter of the small-block face slab includes the length of the small-block face slab crack, the equivalent width of the small-block face slab crack, and the absolute roughness of the small-block face slab crack surface;

[0141] The equivalent permeability coefficient acquisition module is used to obtain the equivalent permeability coefficient corresponding to the small-block face slab area of the concrete face rockfill dam 10 according to the proxy model input parameter data set obtained by the sampling analysis module;

[0142] The finite element analysis module is used to obtain the finite element calculated leakage volume of the small-block face slabs of the concrete face rockfill dam 10 according to the equivalent permeability coefficient obtained by the equivalent permeability coefficient acquisition module and through a finite element method;

[0143] An optimized water conservancy professional agent model acquisition module is used to coordinate the number of cracks in the small block panel, the crack shape parameters of the small block panel and the finite element calculated leakage of the small block panel to obtain coordinated data including a training set and a test set, input the coordinated data into and adjust the co-kriging model, and then optimize the adjusted co-kriging model hyperparameters through a Genghis Khan shark optimizer algorithm, so as to establish multiple optimized water conservancy professional agent models for predicting the leakage of the small block panel of the concrete panel rockfill dam; the co-kriging model is used to establish a prediction model for the leakage of the small block panel of the rockfill dam; the Genghis Khan shark optimizer algorithm is used to optimize the hyperparameters of the co-kriging model, so as to improve the prediction accuracy of the co-kriging model;

[0144] A leakage prediction module for small block panels, used to predict the leakage of each small block panel one by one through each optimized water conservancy professional agent model obtained by the optimized water conservancy professional agent model acquisition module;

[0145] The total leakage acquisition module is used to sum the leakage of each small block panel obtained by the leakage prediction module of the small block panel, so as to obtain the total leakage of the panel of the concrete panel rockfill dam under the condition of cracks.

[0146] Further optimized, each software module of the panel leakage prediction system applicable to a concrete panel rockfill dam of this embodiment correspondingly executes the steps of the panel leakage prediction method applicable to a concrete panel rockfill dam 10 as described in any one of the first embodiments.

[0147] Example 3

[0148] This embodiment further proposes a computer-readable storage medium, which stores a computer program, characterized in that: when the computer program is executed by a processor, the steps of the panel leakage prediction method applicable to the concrete panel rockfill dam 10 as described in any one of Embodiment 1 are implemented.

[0149] Example 4

[0150] Embodiment 4 is a further optimized design of Embodiment 1;

[0151] In step S1, basic information on the number of panel cracks and the range of crack morphology parameters is determined by summarizing a large number of literature and engineering examples.

[0152] In step S21, a Latin hypercube sampling method is used to generate a combination of crack quantity parameters that matches the number of panels in the small block; and a specified number of parameter data sets are generated according to the sum of the crack quantity parameters using the Latin hypercube sampling method.

[0153] In step S252, call the COMSOL software to calculate the file, and record the leakage amount of the small-block panel and the calculation result of the leakage amount of the overall panel area.

[0154] In step S261, set 80% of the panel rockfill dam small-block panel crack parameters - the finite element calculated seepage flow data set of the panel rockfill dam small-block panel as the training set of the co-Kriging model, and set 20% of the panel rockfill dam small-block panel crack parameters - the finite element calculated seepage flow data set of the panel rockfill dam small-block panel as the test set of the model, so as to complete the division of the panel rockfill dam small-block panel crack parameters - the finite element calculated seepage flow data set of the panel rockfill dam small-block panel.

[0155] In step S262, through the co-Kriging algorithm, establish the relationship between the input and output sample data, so as to construct a surrogate model of the crack parameters and the leakage amount of the small-block panel, and calculate the root mean square error between the predicted value of the surrogate model and the calculated value by the finite element method.

[0156] In step S263, taking the root mean square error calculated in step S262 as the fitness function value, use the Genghis Khan shark optimizer algorithm to optimize and select the hyperparameters of the co-Kriging model. Figure 6 Specifically, it is the change curve of the fitness function value during the optimization process; after reaching the maximum number of optimization times, complete the construction of the surrogate model for calculating the leakage amount of the small-block panel of the concrete face rockfill dam based on the co-Kriging model. The prediction results of the surrogate model are shown in Figure 7 , and finally calculate the prediction of the leakage amount of the concrete face rockfill dam under the condition of panel cracks.

[0157] Example 5

[0158] Example 5 is a further optimized design of Example 1;

[0159] In step S2, set the number of calculations in step S2 to W. When constructing the water conservancy professional surrogate model, it is necessary to establish a data set for training the model. Here, the set number of calculations W is the number of groups of data in the training data set; preferably, W is the value 1000.

[0160] In step S21, use the Latin hypercube sampling method to sample the number of panel cracks. The number of samples is the number of small-block panels of the concrete face rockfill dam, and the total number of cracks is N.

[0161] In step S22, use the Latin hypercube sampling method to sample the crack shape parameters, and sample and generate N combinations of crack shape parameters to generate the data set S = {S1, S2, S3,..., S N}, where the i-th group of data in the data set S is S i, where \(i = 1, 2, 3, \cdots, N\). where \(m\) i is the length of the \(i\)-th crack, is the equivalent width of the \(i\)-th crack, and \(\Delta\) c is the relative roughness of the \(i\)-th crack.

[0162] Specifically, 80% of the data groups in the dataset \(S\) * are selected as the training set, and 20% of the data groups in the dataset \(S\) * are selected as the test set.

[0163] In step S26, the upper limit range of the hyperparameter \(\theta\) is set to \([1e - 7, 1]\) and the lower limit range is \([1e2, 1e4]\), the maximum number of iterations \(k\) max is 200 times, and the number of shark populations is set to \(S_n = 50\).

[0164] Example 6

[0165] Example 6 is a further optimized design of Example 5;

[0166] In step S24, according to the data group \(S\) i , the equivalent permeability coefficient set \(D\) of the panel crack area is calculated i ;

[0167] In step S25, the calculated equivalent permeability coefficient set \(D\) of the panel crack area i is input into the nonlinear finite element analysis software COMSOL for numerical calculation to obtain the COMSOL calculation file, and the leakage volume of the small-block panel is extracted from the calculation file, and the total leakage volume of the dam panel is calculated.

[0168] In step S263, taking the root mean square error obtained in step S262 as the fitness function value, the hyperparameters of the co-kriging model are optimized using the Genghis Khan shark optimizer algorithm. After reaching the maximum number of iterations, a hydraulic professional proxy model for calculating the leakage volume of the concrete face rockfill dam panel crack area is established. Finally, the predicted leakage flow values of each small block are summed to realize the prediction of the leakage volume of the concrete face rockfill dam under the condition of panel cracks.

[0169] Specifically, determine the maximum number of iterations \(k\) in the Genghis Khan shark optimizer algorithm max , set the number of shark populations to \(S\) n , and continuously iterate and call the relationship between the input and output sample data using the Genghis Khan shark optimizer algorithm. By solving the optimal solution of the objective function, the optimal hyperparameters of the proxy model are determined, that is, the optimal proxy model is obtained.

[0170] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

Claims

1. A method for predicting the leakage volume of the concrete face slab of a concrete face rockfill dam, which respectively conducts statistical analysis on the face slabs of each small block of the concrete face rockfill dam, is characterized in that The method for predicting the leakage volume of the panel includes: Step S1, statistically analyze the first crack parameter information of the panel of the concrete face rockfill dam, and then obtain the probability distribution information corresponding to the first crack parameter information through a kernel density estimation method; the first crack parameter information includes the total number of cracks on the panel of the concrete face rockfill dam and the crack shape parameters of the panel of the concrete face rockfill dam; the crack shape parameters of the panel of the concrete face rockfill dam include the crack length of the panel, the equivalent width of the panel crack, and the absolute roughness of the panel crack surface; Step S2, establish a plurality of optimized water conservancy professional proxy models corresponding to each small-block panel of the concrete face rockfill dam one by one; the optimized water conservancy professional proxy model is optimized and adjusted through a co-kriging model and a Genghis shark optimizer algorithm, and is used to predict the leakage volume of the small-block panel of the concrete face rockfill dam; Step S3, predict the leakage volume of each small-block panel one by one through each of the optimized water conservancy professional proxy models; Step S4, sum up the leakage volumes of each small-block panel obtained in Step S3, so as to obtain the total leakage volume of the panel of the concrete face rockfill dam under the condition of cracks.

2. The method for predicting the leakage volume of the concrete face slab applicable to a concrete face rockfill dam according to claim 1, wherein In Step S2, the establishment process of the optimized water conservancy professional proxy model includes the following steps: Step S21, according to the probability distribution information obtained in Step S1 and using a Latin hypercube sampling method, sample the small-block panels of the concrete face rockfill dam with respect to the number of cracks, so as to obtain a first data set including the number of cracks on the small-block panels of the concrete face rockfill dam; Step S22, according to the total number of cracks on the panel of the concrete face rockfill dam statistically obtained in Step S1 and using the Latin hypercube sampling method, sample the small-block panels of the concrete face rockfill dam with respect to the crack shape parameters, so as to obtain a second data set including the crack shape parameters of the small-block panels of the concrete face rockfill dam; the crack shape parameters of the small-block panel include the crack length of the small-block panel, the equivalent width of the small-block panel crack, and the absolute roughness of the small-block panel crack surface; Step S23, combine the first data set and the second data set to establish a proxy model input parameter data set; Step S24, according to the proxy model input parameter data set obtained in Step S23, obtain the equivalent permeability coefficient corresponding to the small-block panel area of the concrete face rockfill dam; Step S25, according to the equivalent permeability coefficient obtained in Step S23, and through a finite element method, obtain the finite element calculated leakage volume of the small-block panel of the concrete face rockfill dam; Step S26, overall plan the number of cracks on the small-block panel, the crack shape parameters of the small-block panel, and the finite element calculated leakage volume of the small-block panel to obtain overall data including a training set and a test set, input the overall data into and adjust the co-kriging model, and then optimize the hyperparameters of the adjusted co-kriging model through a Genghis shark optimizer algorithm, so as to establish a plurality of optimized water conservancy professional proxy models for predicting the leakage volume of the small-block panel of the concrete face rockfill dam.

3. The method for predicting the leakage volume of the concrete face slab applicable to a concrete face rockfill dam according to claim 2, wherein Step S25 includes the following sub-steps: Step S251, obtaining the COMSOL calculation file of the nonlinear finite element analysis software; Step S252, calling the COMSOL calculation file, recording the finite element calculated leakage volume of the small-block face slab of the concrete face rockfill dam, and merging and processing it with the proxy model input parameter data set generated in Step S23; Step S253, judging whether the number of times of currently calling the COMSOL calculation file reaches a preset threshold. If the judgment is yes, execute Step S26; otherwise, return to execute Step S252.

4. The method for predicting the leakage volume of the concrete slab in a concrete face rockfill dam according to claim 2 or 3, characterized in that, Between Step S25 and Step S26, the face slab leakage volume prediction method applicable to the concrete face rockfill dam further includes: Step S2526, merging the small-block face slab crack number obtained in Step S21, the small-block face slab crack shape parameter obtained in Step S22, and the finite element calculated leakage volume of the small-block face slab obtained in Step S25 into a set of face rockfill dam small-block face slab crack parameter - face rockfill dam small-block face slab leakage volume data set; Step S26 includes the following sub-steps: Step S261, overall planning the face rockfill dam small-block face slab crack parameter - face rockfill dam small-block face slab leakage volume data set obtained in Step S2526 into a training set and a test set, so as to obtain training set and test set data; the training set and test set data include the overall planned second crack parameter information and the finite element calculated leakage volume of the small-block face slab corresponding to the overall planned second crack parameter information; the second crack parameter information includes the overall planned small-block face slab crack number and the overall planned small-block face slab crack shape parameter; Step S262, taking the second crack parameter information obtained in Step S261 as the independent variable, taking the finite element calculated leakage volume of the small-block face slab corresponding to the overall planned second crack parameter information as the dependent variable, and inputting the independent variable and the dependent variable into a first co-kriging model, so as to establish an adjusted second co-kriging model for expressing the relationship between the leakage volume of the small-block face slab with face slab cracks and the crack parameters, and calculating the root mean square error of the leakage volume between the second co-kriging model and the test set; Step S263, taking the root mean square error obtained in Step S262 as the fitness function value, and using the Genghis Khan shark optimizer algorithm to optimize the hyperparameters of the second co-kriging model for several times, so as to obtain a third co-kriging model with the smallest root mean square error of the test set under the condition of the optimal number of optimization times.

5. The method for predicting the leakage volume of the concrete face slab applicable to a concrete face rockfill dam according to claim 4, wherein In Step S263, determine the upper and lower limits of the hyperparameter values of the second co-kriging model.

6. The method for predicting the leakage volume of the concrete face slab applicable to a concrete face rockfill dam according to claim 4, characterized in that, Step S263 includes the following sub-steps: Step S2631, determining the maximum number of iterations k in the Genghis Khan Shark Optimizer algorithm max , set the shark population to S n ; Step S2632, continuously iteratively calling the relationship between the input and output sample data by using the Genghis Khan shark optimizer algorithm, and determining the optimal hyperparameters of the co-kriging model by solving the optimal solution of an objective function, so as to obtain an optimal optimized water conservancy professional proxy model.

7. The method for predicting the leakage volume of the concrete face slab applicable to the concrete face rockfill dam according to claim 6, wherein The objective function in Step S2632 is: In formula (1), n1 is the number of test set data; h i is the finite element calculation value; h i ' is the surrogate model calculation value.

8. The method for predicting the leakage volume of the concrete face slab applicable to the concrete face rockfill dam according to claim 4, characterized in that, In step S24, when it is considered that no water flow exchange occurs in the horizontal direction of the concrete panel, for equal-width cracks with length a and width b, the water flow through the cracks presents laminar flow characteristics, and the water flow characteristics in the cracks are shown as follows: In Formulas (2) and (3), v x (y) is the water flow velocity in the x direction of the crack length; p is the water flow fluid pressure; μ is the dynamic viscosity coefficient of the water flow; q is the water flow rate per unit width of the crack; J is the hydraulic gradient; γ is the unit weight of water; y is the longitudinal coordinate value in the coordinate system of the water flow in the equal-width crack; Formulas (2) and (3) are derived based on the assumption of smooth surface cracks. The calculation methods for the roughness correction coefficient C and the equivalent crack width b e are as follows: In formulas (4) and (5), b0 and b t are the inlet width and outlet width of the crack; Δ is the absolute roughness of the crack surface; is the relative roughness of the crack; The equivalent permeability coefficient K of a single crack is calculated by formulas (2) to (5). fe The calculation formula is as follows: In formula (6), if there are a large number of cracks on the concrete slab, by selecting a small-size area on the slab, assuming the length of the area is l, the width is d, the number of cracks in the area is n, the length of the cracks is m, and γ is the unit weight of water; according to the principle that the seepage flow through the cracks in the small-size area of the slab is equal to the seepage flow through the equivalent intact slab, the permeability coefficient K of the small-area slab after equivalence can be obtained. y The calculation formula is as follows: In formula (7), Ci is the roughness correction coefficient of the i-th crack; b ei is the equivalent crack width of the i-th crack; since the length m of the crack on the panel may not be equal to the length l of the selected small-size area, the calculation formula for the equivalent permeability coefficient considering different panel crack lengths in the small-size area of the panel is as follows: In formula (8), m i is the length of the i-th crack; γ is the unit weight of water.

9. A prediction system for the leakage volume of the concrete face slab of a concrete face rockfill dam, characterized in that, include: The probability distribution information analysis module counts the first crack parameter information of the panel of the concrete panel rockfill dam, and then obtains the probability distribution information corresponding to the first crack parameter information by a kernel density estimation method; the first crack parameter information includes the total number of cracks on the panel of the concrete panel rockfill dam and the crack shape parameters of the panel of the concrete panel rockfill dam; the crack shape parameters of the panel of the concrete panel rockfill dam include the panel crack length, the equivalent width of the panel crack and the absolute roughness of the panel crack surface; A sampling analysis module, used to obtain a first data set and a second data set, and combine the first data set and the second data set to establish an agent model input parameter data set; based on the probability distribution information obtained by the probability distribution information analysis module and using a Latin hypercube sampling method, the small block panels of the concrete panel rockfill dam are sampled for the number of cracks, thereby obtaining a first data set including the number of cracks in the small block panels of the concrete panel rockfill dam; based on the total number of cracks in the panels of the concrete panel rockfill dam obtained by statistics in step S1 and using the Latin hypercube sampling method, the small block panels of the concrete panel rockfill dam are sampled for crack shape parameters, thereby obtaining a second data set including crack shape parameters of the small block panels of the concrete panel rockfill dam; the small block panel crack shape parameters include small block panel crack length, small block panel crack equivalent width and small block panel crack surface absolute roughness; An equivalent permeability coefficient acquisition module, used to acquire an equivalent permeability coefficient of a small block panel area corresponding to a concrete face rockfill dam according to the proxy model input parameter data set obtained by the sampling analysis module; A finite element analysis module, used for obtaining the finite element calculated leakage of the small block panel of the concrete face rockfill dam through a finite element method according to the equivalent permeability coefficient obtained by the equivalent permeability coefficient acquisition module; An optimized water conservancy professional agent model acquisition module is used to coordinate the number of cracks in the small block panel, the crack shape parameters of the small block panel and the finite element calculated leakage of the small block panel to obtain coordinated data including a training set and a test set, input the coordinated data into and adjust the co-kriging model, and then optimize the adjusted co-kriging model hyperparameters through a Genghis Khan shark optimizer algorithm, so as to establish multiple optimized water conservancy professional agent models for predicting the leakage of the small block panel of the concrete panel rockfill dam; the co-kriging model is used to establish a prediction model for the leakage of the small block panel of the rockfill dam; the Genghis Khan shark optimizer algorithm is used to optimize the hyperparameters of the co-kriging model, so as to improve the prediction accuracy of the co-kriging model; The leakage volume prediction module for small block panels is used to predict the leakage volumes of each small block panel one by one through each of the optimized water conservancy professional agent models obtained by the optimized water conservancy professional agent model acquisition module; The total leakage volume acquisition module is used to sum up the leakage volumes of each small block panel obtained by the leakage volume prediction module of the small block panel, so as to obtain the total leakage volume of the panel of the concrete face rockfill dam under the condition of cracks.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the steps of the method for predicting the leakage volume of the panel of the concrete face rockfill dam as described in any one of claims 1 to 8.

Images