A seepage calculation parameter inversion method and device suitable for earth-rock dams
By combining the VG model and deep learning networks, the problem of seepage analysis bias in earth-rock dams was solved, accurate seepage calculations were achieved, and the safety of earth-rock dams was ensured.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 国网电力工程研究院有限公司
- Filing Date
- 2026-03-16
- Publication Date
- 2026-07-31
AI Technical Summary
Existing technologies cannot accurately analyze the seepage state of earth-rock dams, leading to biased seepage analysis results, failure to effectively identify hidden dangers, and risks such as dam leakage and instability.
Sensitivity analysis was performed using the VG model, and the relationship between seepage parameters was established by combining a deep learning network. The construction scheme of the earth-rock dam was processed in layers, and the unsaturated seepage parameters were analyzed by finite element simulation to improve the accuracy of seepage calculation.
It significantly improves the accuracy of seepage analysis results, ensures the safety and stability of the dam body, provides long-term operational data support, and is applicable to the inversion of seepage calculation parameters for earth-rock dams.
Smart Images
Figure CN122490874A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of seepage calculation technology for earth-rock dams, and specifically to a method and apparatus for inverting seepage calculation parameters applicable to earth-rock dams. Background Technology
[0002] Seepage analysis of earth-rock dams is a core component in ensuring the safety, stability, and long-term operation of the dam. Its purpose is to analyze the seepage state of the dam, identify and mitigate potential hazards in advance, and prevent serious engineering accidents. Failure to accurately analyze the seepage state of the earth-rock dam itself may lead to the overlooking of potential problems such as localized piping, seepage deformation, and hydraulic fracturing, resulting in serious risks such as abnormally increased dam leakage, slope instability, expansion of core wall cracks, and seepage damage to the dam shell.
[0003] In existing technologies, the finite element method is mostly used for seepage analysis. However, due to differences in construction compaction and local geological conditions, there is still heterogeneity at the microscale. The seepage characteristics inside the dam body show regional differences, which leads to deviations in the seepage analysis results and cannot accurately reflect the seepage state of the earth-rock dam. Summary of the Invention
[0004] This invention provides a method and apparatus for inverting seepage calculation parameters for earth-rock dams, thereby solving the problem that existing technologies cannot accurately perform seepage analysis.
[0005] In a first aspect, the present invention provides a method for inverting seepage calculation parameters applicable to earth-rock dams, the method comprising: Sensitivity analysis of the calculation parameters of unsaturated seepage in earth-rock dams was performed using the VG model. The calculation parameters of unsaturated seepage in earth-rock dams include parameters related to air inlet value, shape parameters, and saturated hydraulic conductivity. According to the earth-rock dam construction plan, the unsaturated seepage parameters of the earth-rock dam after sensitivity analysis are processed in layers. A deep learning network was used to establish the mathematical relationship between seepage values and unsaturated seepage parameters of earth-rock dams; Calculate the unsaturated seepage parameters for each region of the earth-rock dam; Finite element simulation analysis was performed on the unsaturated seepage parameters.
[0006] This invention uses a VG model to perform sensitivity analysis on unsaturated seepage calculation parameters, replacing the overall inversion of all seepage parameters. This solves the problems of parameter redundancy and inefficient inversion. It processes data in layers according to the earth-rock dam construction plan to accurately characterize local heterogeneity and eliminate calculation bias. It utilizes the fitting ability of deep learning networks to capture the relationship between seepage values and unsaturated seepage parameters of the earth-rock dam, effectively avoiding the problem of parameter coupling traps leading to local optima. It calculates the unsaturated seepage parameters in each region of the earth-rock dam, replacing the calculation of overall parameters across the entire region. Finite element simulation analysis of the unsaturated seepage parameters significantly improves the accuracy of seepage analysis results, providing data support for ensuring the safe, stable, and long-term operation of the dam.
[0007] In one alternative implementation, a sensitivity analysis of the unsaturated seepage calculation parameters of the earth-rock dam is performed using the VG model, including: The water content was calculated using the soil-water characteristic curve, and the unsaturated hydraulic conductivity was calculated using the Mualem-VG coupled model. The van Genuchten model was substituted into the Richards equation to construct a mathematical model for seepage calculation. Sensitivity analysis was performed on the parameters in the van Genuchten model and Richards equation using global sensitivity analysis.
[0008] This invention accurately describes the water-holding and water-conducting characteristics of earth-rock dams by calculating water content and hydraulic conductivity, constructs a mathematical model for seepage calculation, and uses a global sensitivity analysis method to perform sensitivity analysis on parameters in order to accurately identify core sensitive parameters, solve the problem of full parameter inversion, and make the inversion process more targeted.
[0009] In one alternative implementation, the soil-water characteristic curve is as follows:
[0010] in, Moisture content, Residual moisture content saturated moisture content These are parameters related to the intake air value. n For shape parameters, m For auxiliary parameters; The Mualem-VG coupling model is as follows:
[0011] in, Unsaturated hydraulic conductivity For saturated hydraulic conductivity, For effective saturation, l This is a parameter related to pore connectivity.
[0012] In one alternative implementation, the earth-rock dam construction scheme includes cyclically performing the steps of transporting earth and rock materials, unloading earth and rock materials, spreading earth and rock materials, and compacting earth and rock materials until the earth-rock dam compaction is completed.
[0013] This invention refines the construction steps of earth-rock dams according to the earth-rock dam construction scheme, so as to correspond seepage parameters and construction layers one by one, instead of uniformity across the entire area, in order to accurately characterize local non-uniformity.
[0014] In one optional implementation, the deep learning network is a BP deep learning network, which is used to establish a mathematical relationship between seepage values and unsaturated seepage parameters of the earth-rock dam, including: The input variables of the BP deep learning network are determined. The input variables include the layered compaction information of the earth-rock dam, the earth and rock material information, and the measured values of layered seepage of the earth-rock dam. The layered compaction information of the earth-rock dam includes the number of layers, layer thickness, compaction pressure, and number of compaction cycles. Determine the output variables of the BP deep learning network, including parameters related to the air intake value, shape parameters, and saturated hydraulic conductivity. The input and output variables are substituted into the BP deep learning network for training to construct the mathematical relationship between the input and output variables.
[0015] This invention utilizes the strong nonlinear fitting capability of BP deep learning networks to model the complex coupling relationship between input and output variables, thereby improving the accuracy of parameter inversion.
[0016] In one optional implementation, the unsaturated seepage parameters for each region of the earth-rock dam are calculated, including: Data from other areas of the earth-rock dam project are input into a BP deep learning network to output unsaturated seepage calculation parameters for each area of the earth-rock dam project.
[0017] This invention uses the logic of inputting data from other regions and outputting seepage parameters from other regions to achieve accurate output of regional-level parameters and reduce the deviation between inverted parameters and actual seepage characteristics.
[0018] In one alternative implementation, finite element simulation analysis is performed on the unsaturated seepage parameters, including: The unsaturated seepage calculation parameters output by the BP deep learning network are substituted into the finite element seepage calculation model for seepage simulation analysis.
[0019] This invention uses finite element simulation analysis to perform unsaturated seepage calculation parameters output by a BP deep learning network, replacing the traditional finite element seepage analysis based on globally homogenized parameters, thus truly reflecting the actual structure of the dam.
[0020] Secondly, the present invention provides a seepage calculation parameter inversion device suitable for earth-rock dams, the device comprising: The sensitivity analysis module is used to perform sensitivity analysis on the calculation parameters of unsaturated seepage in earth-rock dams using the VG model. The calculation parameters of unsaturated seepage in earth-rock dams include parameters related to air intake, shape parameters, and saturated hydraulic conductivity. The stratified processing module is used to perform stratified processing of the unsaturated seepage parameters of the earth-rock dam after sensitivity analysis, according to the earth-rock dam construction plan. The mathematical relationship establishment module is used to establish the mathematical relationship between seepage values and unsaturated seepage parameters of earth-rock dams using deep learning networks. The parameter calculation module is used to calculate the unsaturated seepage parameters in various areas of the earth-rock dam. The finite element simulation analysis module is used to perform finite element simulation analysis on unsaturated seepage parameters.
[0021] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the seepage calculation parameter inversion method applicable to earth-rock dams described in the first aspect or any corresponding embodiment.
[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the inversion method for seepage calculation parameters of earth-rock dams as described in the first aspect or any corresponding embodiment thereof. Attached Figure Description
[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0024] Figure 1 This is a flowchart illustrating the inversion method for seepage calculation parameters applicable to earth-rock dams according to an embodiment of the present invention. Figure 2 This is a schematic diagram of a homogeneous earth dam and a core wall dam according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a BP deep learning network according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the input parameters and output results of a BP deep learning network according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a seepage calculation parameter inversion device for earth-rock dams according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.
[0027] In earth-rock dams, the particle size distribution of the dam body material is relatively uniform, and the overall distribution is continuous. However, due to differences in construction compaction and local geological conditions, there is still heterogeneity at the microscale, which leads to regional differences in the seepage characteristics inside the dam body.
[0028] When using the finite element method for seepage analysis, the contradiction between "overall homogeneity" and "local heterogeneity" is difficult to accurately characterize, leading to frequent deviations in the calculation results. The core contradiction lies in the fact that the seepage model based on the homogeneity assumption cannot reflect the disturbance of the overall seepage field by local high / low permeability zones.
[0029] Most existing inversion algorithms are based on the assumption of global homogeneity, which makes it difficult to capture sudden changes in local parameters. This results in deviations between the inverted parameters and the actual observed values in terms of spatiotemporal distribution, especially in stress concentration areas such as the upstream and downstream toes and shoulders of the dam body, where the errors are more significant.
[0030] Clay-core dams in earth-rock dams exhibit significant material zoning, forming a composite structure of "clay core wall - transition - rockfill dam shell." The key issue is that traditional layered homogenization models cannot reflect the nonlinear seepage behavior at the interface between the core wall and the dam shell. Inversion analysis of clay-core dams requires simultaneous optimization of the seepage parameters of the core wall, dam shell, and transition layer. However, existing algorithms often fall into local optima due to strong parameter coupling and high inversion dimensionality, resulting in time lag deviations between the core wall seepage flow and the dam shell phreatic line position in seepage calculations and actual monitoring data. These errors are particularly pronounced under conditions of rapid rises and falls in reservoir water levels.
[0031] Current finite element inversion algorithms for seepage in earth-rock dams have room for improvement. When seepage calculation parameters are inverted and corrected as a whole, the overall seepage calculation parameters cannot well characterize the seepage characteristics of earth-rock dams in terms of space or time. In order to improve the accuracy of seepage analysis in earth-rock dams, this invention provides a seepage calculation parameter inversion method suitable for earth-rock dams. It adopts a seepage parameter inversion algorithm with higher accuracy, which significantly improves the accuracy of seepage calculation in earth-rock dams. It is also applicable to seepage calculation in pumped storage power station earth-rock dams and is applicable to the design of all earth-rock dam projects and the operation and maintenance management of existing earth-rock dams.
[0032] According to an embodiment of the present invention, an embodiment of a seepage calculation parameter inversion method suitable for earth-rock dams is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0033] This embodiment provides a method for inverting seepage calculation parameters applicable to earth-rock dams. Figure 1 This is a flowchart of a seepage calculation parameter inversion method applicable to earth-rock dams according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps: Step S101: Use the VG model to perform sensitivity analysis on the calculation parameters of unsaturated seepage in earth-rock dams.
[0034] In this embodiment of the invention, sensitivity analysis is performed on the parameters used in the calculation of unsaturated seepage in earth-rock dams. Specifically, the van Genuchten model (VG model) is used to perform sensitivity analysis on the parameters used in the calculation of unsaturated seepage in earth-rock dams. The VG model establishes the relationship between "water suction - water content - hydraulic conductivity" and performs sensitivity analysis on parameters related to air intake value, shape parameters, and saturated hydraulic conductivity.
[0035] Step S102: According to the earth-rock dam construction plan, the unsaturated seepage parameters of the earth-rock dam after sensitivity analysis are processed in layers.
[0036] In this embodiment of the invention, all earth-rock dams are constructed using the steps of transporting, unloading, spreading, and compacting earth and rock. The stratification of seepage parameters must correspond one-to-one with each construction layer to ensure that the seepage parameters of each layer reflect the characteristics of the construction materials, fundamentally solving the problem that traditional methods using "uniformly homogeneous parameters" cannot characterize local differences. Based on the earth-rock dam construction scheme, the unsaturated seepage parameters of the earth-rock dam after sensitivity analysis are stratified to provide data support for subsequent parameter inversion using deep learning networks.
[0037] Step S103: A deep learning network is used to establish a mathematical relationship between the seepage value and the unsaturated seepage parameters of the earth-rock dam.
[0038] In this embodiment of the invention, a BP (Backpropagation algorithm) deep learning network or other deep learning networks are used as modeling tools to establish a mathematical relationship between input variables and output variables. The input variables are the measured values of layered seepage, i.e., seepage values, and the output variables are important unsaturated seepage calculation parameters, i.e., parameters related to air intake values, shape parameters, and saturated hydraulic conductivity.
[0039] Step S104: Calculate the unsaturated seepage parameters for each region of the earth-rock dam.
[0040] In this embodiment of the invention, a trained deep learning network is used to calculate the unsaturated seepage parameters of each region of the earth-rock dam, using data from other regions of the earth-rock dam as input.
[0041] Step S105: Perform finite element simulation analysis on the unsaturated seepage parameters.
[0042] In this embodiment of the invention, the unsaturated seepage parameters obtained from the deep learning network are substituted into the finite element calculation model of the unsaturated seepage of the earth-rock dam to perform numerical simulation calculation of the seepage field of the dam body. This greatly improves the accuracy of the seepage calculation results and provides data support for the design optimization or operation and maintenance safety assessment of earth-rock dams.
[0043] The seepage calculation parameter inversion method for earth-rock dams provided in this embodiment uses a VG model to perform sensitivity analysis on unsaturated seepage calculation parameters, replacing the overall inversion of all seepage parameters. This solves the problems of parameter redundancy and inefficient inversion. Layered processing according to the earth-rock dam construction plan accurately characterizes local heterogeneity and eliminates calculation bias. The fitting ability of deep learning networks is used to capture the relationship between seepage values and unsaturated seepage parameters of the earth-rock dam, effectively avoiding the problem of parameter coupling traps leading to local optima. The unsaturated seepage parameters of each region of the earth-rock dam are calculated instead of calculating the overall parameters across the entire region. Finite element simulation analysis is then performed on the unsaturated seepage parameters, significantly improving the accuracy of seepage analysis results and providing data support for ensuring the safe, stable, and long-term operation of the dam.
[0044] This embodiment provides a method for inverting seepage calculation parameters suitable for earth-rock dams. The process includes the following steps: Step S201: Use the VG model to perform sensitivity analysis on the calculation parameters of unsaturated seepage in earth-rock dams.
[0045] Specifically, step S201 includes: Step S2011: Calculate the water content using the soil-water characteristic curve and calculate the unsaturated hydraulic conductivity using the Mualem-VG coupled model.
[0046] Step S2012: Substitute the van Genuchten model into the Richards equation to construct a mathematical model for seepage calculation.
[0047] Step S2013: Use global sensitivity analysis to perform sensitivity analysis on the parameters in the van Genuchten model and Richards equation.
[0048] In this embodiment of the invention, the VG model, or van Genuchten model, includes the Soil-Water Characteristic Curve (SWCC) and the unsaturated hydraulic conductivity curve.
[0049] The soil-water characteristic curve is used to describe the relationship between water content and soil-water potential in unsaturated soil, and is the key to determining whether the soil is saturated or unsaturated.
[0050] The soil-water characteristic curve is used to calculate the water content. The soil-water characteristic curve is as follows:
[0051] in, Moisture content, It is in an unsaturated state. It is in a saturated state. Residual moisture content saturated moisture content These are parameters related to the intake air value. n For shape parameters, m As auxiliary parameters, .
[0052] The unsaturated hydraulic conductivity curve is used to describe the relationship between the water content and hydraulic conductivity of unsaturated soil. The unsaturated hydraulic conductivity is calculated using the Mualem-VG coupled model. The formula for the Mualem-VG coupled model is as follows:
[0053] in, Unsaturated hydraulic conductivity For saturated hydraulic conductivity, For effective saturation, l This is a parameter related to pore connectivity.
[0054] Substituting the van Genuchten model into the Richards equation, we get:
[0055] in, , , .
[0056] A parameter sensitivity analysis was performed. Specifically, the Sobol's index method was used to analyze the sensitivity of the above parameters to obtain the relatively sensitive calculation parameters. , n, and Ks are the most sensitive core parameters.
[0057] Sobol's index method, as one of the most classic and widely used methods in global sensitivity analysis, is based on the idea of variance decomposition. It measures the importance of parameters by quantifying the contribution ratio of input parameters (and the interaction between parameters) to the total variance of the output results. It is a core tool for analyzing nonlinear and non-monotonic models and parameter interactions.
[0058] By calculating the water content and hydraulic conductivity, the water-holding and hydraulic conductivity characteristics of earth-rock dams are accurately described. A mathematical model for seepage calculation is constructed, and a global sensitivity analysis method is used to perform sensitivity analysis on the parameters in order to accurately identify the core sensitive parameters, solve the problem of full parameter inversion, and make the inversion process more targeted.
[0059] Step S202: According to the earth-rock dam construction plan, the unsaturated seepage parameters of the earth-rock dam after sensitivity analysis are processed in layers.
[0060] Specifically, such as Figure 2 As shown, taking homogeneous earth dams and core wall dams as examples, the treatment methods for these two dam types are introduced below.
[0061] According to the construction process of earth-rock dams, all procedures are carried out in accordance with the following steps: (1) Earthwork transport vehicles shall transport earth and rock materials that meet the requirements to the area where the dam needs to be filled; (2) The earthwork transport vehicle unloads the earth and stone materials; (3) The bulldozer spreads the earth and rock to the required thickness as designed; (4) Using a vibratory roller (similar in function to a road roller) to compact the soil and rock materials only achieves the required technical specifications; (5) Repeat steps (1)-(4) above until the dam compaction is completed.
[0062] According to the relevant technical specifications of the dam, the thickness of each layer is about 25cm.
[0063] According to the earth-rock dam construction plan, the construction steps of the earth-rock dam are refined so that the seepage parameters and construction layers can be matched one by one, instead of uniformity across the whole area, so as to accurately characterize the local non-uniformity.
[0064] Step S203: Use a deep learning network to establish the mathematical relationship between the seepage value and the unsaturated seepage parameters of the earth-rock dam.
[0065] Step S203 above includes: Step S2031: Determine the input variables of the BP deep learning network.
[0066] Step S2032: Determine the output variables of the BP deep learning network.
[0067] Step S2033: Substitute the input variables and output variables into the BP deep learning network for training to construct the mathematical relationship between the input variables and output variables.
[0068] In this embodiment of the invention, the input variables include layered compaction information of the earth-rock dam, earth and rock material information, and measured values of layered seepage in the earth-rock dam. The layered compaction information of the earth-rock dam includes information such as the number of layers, layer thickness, compaction pressure, and number of compaction cycles. The output variables include parameters related to air intake, shape parameters, and saturated hydraulic conductivity. The input and output variables are substituted into a BP deep learning network for training to construct the mathematical relationship between the input and output variables.
[0069] The BP deep learning network architecture diagram is as follows: Figure 3 As shown, the structure includes an input layer, a hidden layer, and an output layer, connected by weights. The input layer receives layered compaction information, soil and rock material information, and measured values of layered seepage in the earth-rock dam, corresponding to... Figure 3 Input nodes x1, x2...x n The hidden layer performs non-linear transformations on the input data, connects to the input layer through a weight matrix, and outputs intermediate variables y1, y2, ... y3. r The output layer outputs the core seepage parameters, corresponding to the output nodes α1(x), α2(x), ..., αm(x).
[0070] like Figure 4 As shown, Input 1 is the layered compaction information, with each row corresponding to one construction layer and each column corresponding to the layered compaction information. Input 2 is the soil and rock material information, with each layer corresponding to one construction layer and each column corresponding to the soil and rock material characteristics. Input 3 is the layered seepage information, with each layer corresponding to one construction layer and each column corresponding to the measured layered seepage value.
[0071] Output 1 is the α-parameter matrix, with each row corresponding to a construction layer and each column corresponding to the α-parameter of that layer. Output 2 is the n-parameter matrix, with each row corresponding to a construction layer and each column corresponding to the n-parameter of that layer. Output 3 is the Ks-parameter matrix, with each row corresponding to a construction layer and each column corresponding to the Ks-parameter of that layer.
[0072] Calculations and analysis show that the denser the compaction, the greater α and n become, and the significantly lower Ks becomes.
[0073] By leveraging the strong nonlinear fitting capability of BP deep learning networks, the complex coupling relationship between input and output variables is modeled to improve the accuracy of parameter inversion.
[0074] Step S204: Calculate the unsaturated seepage parameters for each region of the earth-rock dam.
[0075] Specifically, step S204 includes: Step S2041: Input the data of other areas of the earth-rock dam project into the BP deep learning network and output the unsaturated seepage calculation parameters of each area of the earth-rock dam project.
[0076] In this embodiment of the invention, a trained BP deep learning network is used to input data from other areas of the earth-rock dam project. The network is then used to perform calculations on this data to obtain the unsaturated seepage calculation parameters for each area of the earth-rock dam project. Essentially, this involves using a deep learning network to fit the relationship between construction parameters, measured seepage values, and seepage calculation parameters, thereby solving the problems of strong parameter coupling and susceptibility to local optima in traditional inversion algorithms.
[0077] By inputting data from other regions and outputting seepage parameters for those regions, the system achieves accurate output of regional parameters, reducing the deviation between inverted parameters and actual seepage characteristics.
[0078] Step S205: Perform finite element simulation analysis on the unsaturated seepage parameters.
[0079] Specifically, step S205 includes: Step S2051: Substitute the unsaturated seepage calculation parameters output by the BP deep learning network into the finite element seepage calculation model to perform seepage simulation analysis.
[0080] In this embodiment of the invention, the unsaturated seepage calculation parameters output by the BP deep learning network, namely the parameters related to the air intake value, shape parameters, and saturated hydraulic conductivity, are subjected to finite element analysis.
[0081] First, the unsaturated seepage calculation parameters output by the BP deep learning network are substituted into the aforementioned Genuchten model to generate the soil and rock seepage characteristic curves required for the finite element simulation model, providing a data foundation for finite element simulation analysis.
[0082] The construction of the finite element simulation model corresponds to the layered construction of the earth-rock dam. The material properties of each layer are assigned to the finite element model elements to achieve the unification of construction layer, finite element elements, and seepage parameters.
[0083] Using the modified Richards equation as the core governing equation, finite element simulation calculations were carried out. The entire earth-rock dam was simulated and analyzed using the finite element simulation method, and the key seepage indicators of the earth-rock dam were calculated, which greatly improved the accuracy of the seepage calculation results.
[0084] The seepage calculation parameter inversion method for earth-rock dams provided in this embodiment uses finite element simulation analysis to perform unsaturated seepage calculation parameters output by a BP deep learning network, replacing the traditional finite element seepage analysis based on globally homogenized parameters, thereby truly reflecting the actual structure of the dam.
[0085] This embodiment also provides a seepage calculation parameter inversion device suitable for earth-rock dams. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0086] This embodiment provides a seepage calculation parameter inversion device suitable for earth-rock dams, such as... Figure 5 As shown, it includes: Sensitivity analysis module 501 is used to perform sensitivity analysis on the calculation parameters of unsaturated seepage in earth-rock dams using the VG model. The calculation parameters of unsaturated seepage in earth-rock dams include parameters related to air intake value, shape parameters, and saturated hydraulic conductivity.
[0087] The stratified processing module 502 is used to perform stratified processing on the unsaturated seepage parameters of the earth-rock dam after sensitivity analysis, according to the earth-rock dam construction plan.
[0088] The mathematical relationship establishment module 503 is used to establish the mathematical relationship between seepage values and unsaturated seepage parameters of earth-rock dams using a deep learning network.
[0089] The parameter calculation module 504 is used to calculate the unsaturated seepage parameters of each region of the earth-rock dam.
[0090] The finite element simulation analysis module 505 is used to perform finite element simulation analysis on unsaturated seepage parameters.
[0091] In some optional implementations, the sensitivity analysis module 501 includes: The calculation unit is used to calculate the water content using the soil-water characteristic curve and to calculate the unsaturated hydraulic conductivity using the Mualem-VG coupled model.
[0092] The model building unit is used to substitute the van Genuchten model into the Richards equation to construct a mathematical model for seepage calculation.
[0093] The sensitivity analysis unit is used to perform sensitivity analysis on the parameters in the van Genuchten model and Richards equation using the global sensitivity analysis method.
[0094] In some alternative implementations, the soil-water characteristic curves are as follows:
[0095] in, Moisture content, Residual moisture content saturated moisture content These are parameters related to the intake air value. n For shape parameters, m For auxiliary parameters; The Mualem-VG coupling model is as follows:
[0096] in, Unsaturated hydraulic conductivity For saturated hydraulic conductivity, For effective saturation, l This is a parameter related to pore connectivity.
[0097] In some alternative implementations, the mathematical relation establishment module 503 includes: The input variable determination unit is used to determine the input variables of the BP deep learning network. The input variables include the layered compaction information of the earth-rock dam, the earth and rock material information, and the measured values of layered seepage of the earth-rock dam. The layered compaction information of the earth-rock dam includes the number of layers, layer thickness, compaction pressure, and number of compaction cycles.
[0098] The output variable determination unit is used to determine the output variables of the BP deep learning network. The output variables include parameters related to the intake value, shape parameters, and saturated water conductivity.
[0099] The mathematical relationship establishment unit is used to substitute the input and output variables into the BP deep learning network for training and to construct the mathematical relationship between the input and output variables.
[0100] In some alternative implementations, the parameter calculation module 504 includes: The parameter calculation unit is used to input data from other areas of the earth-rock dam project into the BP deep learning network and output the unsaturated seepage calculation parameters for each area of the earth-rock dam project.
[0101] In some alternative implementations, the finite element simulation analysis module 505 includes: The finite element simulation analysis unit is used to substitute the unsaturated seepage calculation parameters output by the BP deep learning network into the finite element seepage calculation model for seepage simulation analysis.
[0102] The seepage calculation parameter inversion device for earth-rock dams provided in this embodiment of the invention can execute the seepage calculation parameter inversion method for earth-rock dams provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.
[0103] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.
[0104] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0105] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.
[0106] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the seepage calculation parameter inversion method for earth-rock dams according to embodiments of the present invention.
[0107] Figure 6The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.
[0108] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the seepage calculation parameter inversion method for earth-rock dams shown in the above embodiments is implemented.
[0109] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0110] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended invention.
Claims
1. A seepage calculation parameter inversion method suitable for earth-rock dams, characterized in that, The method includes: Sensitivity analysis of unsaturated seepage calculation parameters of earth-rock dams was performed using the VG model. These unsaturated seepage calculation parameters include parameters related to air inlet value, shape parameters, and saturated hydraulic conductivity. According to the earth-rock dam construction plan, the unsaturated seepage parameters of the earth-rock dam after sensitivity analysis are processed in layers. A deep learning network was used to establish the mathematical relationship between seepage values and unsaturated seepage parameters of earth-rock dams; Calculate the unsaturated seepage parameters for each region of the earth-rock dam; Finite element simulation analysis was performed on the unsaturated seepage parameters.
2. The method of claim 1, wherein, The sensitivity analysis of the calculation parameters for unsaturated seepage in earth-rock dams using the VG model includes: The water content was calculated using the soil-water characteristic curve, and the unsaturated hydraulic conductivity was calculated using the Mualem-VG coupled model. Substitute the van Genuchten model into the Richards equation to construct a mathematical model for seepage calculation; Sensitivity analysis was performed on the parameters in the van Genuchten model and Richards equation using global sensitivity analysis.
3. The method according to claim 2, characterized in that, The soil-water characteristic curves are as follows: wherein, is the water content, is the residual water content, is the saturated water content, is a parameter related to the intake value, n is a shape parameter, m is an auxiliary parameter; The Mualem-VG coupling model is as follows: in, Unsaturated hydraulic conductivity For saturated hydraulic conductivity, For effective saturation, l This is a parameter related to pore connectivity.
4. The method according to claim 1, characterized in that, The earth-rock dam construction plan includes cyclically performing the steps of transporting earth and rock materials, unloading earth and rock materials, spreading earth and rock materials, and compacting earth and rock materials until the earth-rock dam is compacted.
5. The method according to claim 1, characterized in that, The deep learning network is a BP deep learning network. The step of using a deep learning network to establish the mathematical relationship between seepage values and unsaturated seepage parameters of the earth-rock dam includes: The input variables of the BP deep learning network are determined. The input variables include the layered compaction information of the earth-rock dam, the earth and rock material information, and the measured values of layered seepage of the earth-rock dam. The layered compaction information of the earth-rock dam includes the number of layers, the layer thickness, the compaction pressure, and the number of compaction cycles. Determine the output variables of the BP deep learning network, including parameters related to the air intake value, shape parameters, and saturated hydraulic conductivity; The input and output variables are substituted into the BP deep learning network for training to construct the mathematical relationship between the input and output variables.
6. The method according to claim 5, characterized in that, The calculation of unsaturated seepage parameters for each region of the earth-rock dam includes: Data from other areas of the earth-rock dam project are input into a BP deep learning network to output unsaturated seepage calculation parameters for each area of the earth-rock dam project.
7. The method according to claim 1, characterized in that, The finite element simulation analysis of the unsaturated seepage parameters includes: The unsaturated seepage calculation parameters output by the BP deep learning network are substituted into the finite element seepage calculation model for seepage simulation analysis.
8. A seepage calculation parameter inversion device suitable for earth-rock dams, characterized in that, The device includes: The sensitivity analysis module is used to perform sensitivity analysis on the unsaturated seepage calculation parameters of earth-rock dams using the VG model. The unsaturated seepage calculation parameters of earth-rock dams include parameters related to air inlet value, shape parameters, and saturated hydraulic conductivity. The stratified processing module is used to perform stratified processing of the unsaturated seepage parameters of the earth-rock dam after sensitivity analysis, according to the earth-rock dam construction plan. The mathematical relationship establishment module is used to establish the mathematical relationship between seepage values and unsaturated seepage parameters of earth-rock dams using deep learning networks. The parameter calculation module is used to calculate the unsaturated seepage parameters in various areas of the earth-rock dam. The finite element simulation analysis module is used to perform finite element simulation analysis on unsaturated seepage parameters.
9. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the seepage calculation parameter inversion method applicable to earth-rock dams as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the seepage calculation parameter inversion method applicable to earth-rock dams as described in any one of claims 1 to 7.