Dynamic prediction method and device for water seepage amount of cavern

Abstract

The invention provides a dynamic prediction method and device for the water seepage amount of a cavern, and relates to the technical field of engineering prediction.The method comprises the steps that a fracture network dynamic evolution model is established based on underground cavern seepage influence factor data so as to dynamically update fractal characteristic parameters of fractal fracture elements; establishing an anisotropic permeability tensor model according to the seepage influence factor data of the underground cavern; constructing a depth physical constraint type geographically weighted regression model based on the anisotropic permeability tensor model and the seepage core parameters; inputting the new underground cavern seepage influence factor data into the deep physical constraint type geographically weighted regression model; and outputting the obtained water seepage amount prediction value of each fractal fracture element and the whole-cavern water seepage amount spatial and temporal distribution as a cavern water seepage amount dynamic prediction result. According to the method, fracture network multi-scale characteristics, spatio-temporal dynamic evolution and seepage physical constraints can be considered at the same time, so that the precision, stability and engineering applicability of seepage prediction are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering prediction, in particular to a dynamic prediction method and device for seepage quantity of a cavern. BACKGROUND

[0002] Underground caverns (such as underground power plant, diversion tunnel, traffic tunnel, underground storage and mine roadway, etc.) generally face seepage action during excavation and operation. The seepage field of the surrounding rock of the cavern is not only affected by groundwater recharge, water head boundary and permeability of the rock-soil medium, but also significantly controlled by the degree of fracture development, fracture connectivity structure and anisotropy characteristics; at the same time, construction measures such as excavation unloading, blasting disturbance, support and grouting will cause the time evolution of the stress field and fracture aperture / connectivity of the surrounding rock, and further cause the obvious spatiotemporal dynamic change of the seepage channel and seepage quantity. Therefore, accurate prediction of the seepage quantity of the underground cavern is an important technical basis for optimization of the drainage system layout, early warning of water inrush risk and engineering safety operation control, and directly affects the construction cost, construction safety and operation stability of the project.

[0003] In engineering practice, fitting methods based on existing monitoring data or numerical simulation techniques are often used for seepage quantity prediction. Conventional data fitting methods, such as statistical fitting and regression analysis, are simple and fast, but are suitable for short-term trend prediction, are not sensitive to the complexity of geological conditions, have no mechanism relationship, only know the data relationship and do not know why the seepage occurs; numerical simulation techniques have clear mechanism, but are complex in modeling, have large workload and high calculation cost, and are difficult to meet the timely response prediction demand in the construction process. At present, with the development of science and technology, the engineering field has been exploring a better way to use the current mature basic models and techniques to study the method to meet the prediction demand of the seepage quantity of the cavern. SUMMARY

[0004] In order to overcome the problems in the related art, the present application provides a dynamic prediction method and device for seepage quantity of a cavern, which can simultaneously consider the multi-scale characteristics of the fracture network, the spatiotemporal dynamic evolution and the seepage physical constraints, so as to improve the accuracy, stability and engineering applicability of the prediction of the seepage quantity.

[0005] According to a first aspect of an embodiment of the present application, a dynamic prediction method for seepage quantity of a cavern is provided, comprising: obtaining seepage influence factor data of an underground cavern; establishing a dynamic evolution model of a fracture network based on the seepage influence factor data of the underground cavern, to dynamically update the fractal characteristic parameters of each fractal fracture element; establishing an anisotropic permeability tensor model according to the seepage influence factor data of the underground cavern; constructing a deep physical constraint type geographic weighted regression model based on the anisotropic permeability tensor model and seepage core parameters; input the new underground cavern seepage influence factor data into the deep physical constraint type geographic weighted regression model to obtain a seepage amount prediction value of each fractal fissure element and a full-cavern seepage amount spatiotemporal distribution; output the seepage amount prediction value of each fractal fissure element and the full-cavern seepage amount spatiotemporal distribution as the dynamic prediction result of the cavern seepage amount.

[0006] In some example embodiments of the present application, based on the foregoing scheme, the underground cavern seepage influence factor data comprises rock mass stress monitoring data; establishing a fissure network dynamic evolution model based on the underground cavern seepage influence factor data to dynamically update fractal characteristic parameters of each fractal fissure element comprises: extracting fissure geometric characteristic parameters from the underground cavern seepage influence factor data; extracting fractal characteristic parameters in the fissure geometric characteristic parameters by using a multifractal detrended fluctuation analysis method; based on the fractal characteristic parameters, using a clustering algorithm to divide the underground cavern into a plurality of fractal fissure elements that are internally homogeneous and externally significantly different; according to the rock mass stress monitoring data, combining the principle of effective stress to calculate the change amount of rock mass stress in the construction excavation and support process, and then deducing the change rule of fissure opening to dynamically update the fractal characteristic parameters of each fractal fissure element.

[0007] In some example embodiments of the present application, based on the foregoing scheme, the underground cavern seepage influence factor data comprises fissure occurrence data; establishing an anisotropic permeability tensor model according to the underground cavern seepage influence factor data comprises: determining a seepage dominant direction of the underground cavern according to the fissure occurrence data; establishing a principal direction coordinate system of permeability based on the seepage dominant direction; establishing the anisotropic permeability tensor model in the principal direction coordinate system.

[0008] In some example embodiments of the present application, based on the foregoing scheme, constructing a deep physical constraint type geographic weighted regression model based on the anisotropic permeability tensor model and seepage core parameters comprises: constructing a permeability coefficient power coupling formula based on the fractal fissure element and the fractal characteristic parameters of each fractal fissure element; assigning values to the anisotropic permeability tensor model according to the permeability coefficient power coupling formula to obtain an anisotropic permeability tensor of each fractal fissure element; calculating a theoretical seepage amount of each fractal fissure element by using the anisotropic permeability tensor of each fractal fissure element and the seepage core parameters; The basic spatial weights between different fractal fracture elements are calculated using a Gaussian kernel function. At the same time, construction disturbance factors and geological similarity factors are introduced to dynamically adjust the basic spatial weights to obtain the spatial weights. Based on the spatial weights of all fractal fracture elements, a spatial weight matrix is ​​obtained; Based on the theoretical seepage volume of each fractal fracture element and the spatial weight matrix, a deep physical constraint-based geographically weighted regression model is established, using a geographically weighted regression model as the foundation.

[0009] In some exemplary embodiments of the present invention, based on the foregoing scheme, the spatial weights include: in, For the first The fractal fracture element and the first The spatial Euclidean distance between the centers of each fractal fracture element. For bandwidth parameters; The construction disturbance weight is dynamically adjusted based on the distance between the excavation face and the fractal fracture element. The smaller The larger; The geological similarity weight is determined based on the similarity measure of the lithology and / or fracture characteristics of fractal fracture elements; the higher the similarity, the greater the weight. The larger.

[0010] In some exemplary embodiments of the present invention, based on the foregoing scheme, and according to the theoretical seepage volume of each fractal fracture element and the spatial weight matrix, the deep physical constraint-based geographically weighted regression model is established based on the geographically weighted regression model, including: in, For the first Measured water seepage of each fractal fracture element; For constant terms; For the first The fractal fracture element corresponding to the first One effective influencing factor, The number of effective impact factors; For the first The fractal fracture element corresponding to the first The spatial local regression coefficients are obtained by using the same method as the first... The spatial weight matrix corresponding to each fractal fracture element The weighted least squares solution is obtained, and it satisfies: , For the first The regression coefficient vector of each fractal fracture element For an effective influence factor matrix, This is the measured seepage vector; These are adaptive physical constraint weights used to balance the contribution of data-driven regression fitting and physical constraints, and satisfy the following conditions: , The maximum weight value and , For the weight growth rate, The number of training iterations for the model; For the first The theoretical seepage volume of each fractal fracture element, and satisfying the following conditions: in, For the first The components or equivalent permeability parameters of the anisotropic permeability tensor of a fractal fracture element. For hydraulic gradient, The cross-sectional area of ​​the water passage. The water content of the fractal fracture element.

[0011] In some exemplary embodiments of the present invention, based on the foregoing scheme, before inputting the new underground cavern seepage influencing factor data into the depth-physical-constrained geographic-weighted regression model to obtain the predicted seepage volume of each fractal fracture element and the spatiotemporal distribution of the total cavern seepage volume, the cavern seepage volume dynamic prediction method further includes: Extract the geometric features of fractures and the seepage-related features from the seepage influencing factor data of the underground cavern; Screening effective influencing factors of cavern seepage volume from the fracture geometry features and the seepage-related features; Collinearity factors were eliminated using a variance inflation factor, and an influence factor matrix was constructed based on the remaining factors. The deep physical constraint geographic weighted regression model is trained using the aforementioned influence factor matrix and measured infiltration volume to obtain a well-trained deep physical constraint geographic weighted regression model. The new underground cavern seepage influencing factor data are input into the deep physical constraint geographic weighted regression model to obtain the predicted seepage volume for each fractal fracture element and the spatiotemporal distribution of the total cavern seepage volume, including: The new data on seepage influencing factors in underground caverns are input into the trained deep physical constraint geographic weighted regression model to obtain the predicted seepage volume of each fractal fracture element and the spatiotemporal distribution of seepage volume in the entire cavern.

[0012] According to a second aspect of the present invention, a device for dynamically predicting cavern seepage is provided, comprising: The data acquisition module is used to acquire data on the influencing factors of seepage in underground caverns; The first modeling module is configured to establish a fracture network dynamic evolution model based on the underground cavern seepage influencing factor data, so as to dynamically update the fractal characteristic parameters of each fractal fracture element. The second modeling module is configured to establish an anisotropic permeability tensor model according to the underground cavern seepage influencing factor data. The third modeling module is configured to construct a deep physical constraint type geographically weighted regression model based on the anisotropic permeability tensor model and seepage core parameters. The running module is configured to input new underground cavern seepage influencing factor data into the deep physical constraint type geographically weighted regression model, so as to obtain the water seepage amount prediction value of each fractal fracture element and the spatiotemporal distribution of the total cavern water seepage amount. The result output module is configured to output the water seepage amount prediction value of each fractal fracture element and the spatiotemporal distribution of the total cavern water seepage amount as the dynamic prediction result of the cavern water seepage amount.

[0013] According to a third aspect of the embodiments of the present application, an electronic device is provided, comprising a processor and a memory having computer readable instructions stored thereon, which, when executed by the processor, implement the method in the first aspect.

[0014] According to a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, having a computer program stored thereon, which, when executed by a processor, implements the method in the first aspect.

[0015] The technical solutions provided by the embodiments of the present application can include the following beneficial effects: The dynamic prediction method of the cavern water seepage amount provided by the present application can unify key information such as hydrological recharge, fracture structure and construction disturbance into the prediction input by obtaining underground cavern seepage influencing factor data, and can update the fractal fracture element characteristics in real time by establishing a fracture network dynamic evolution model based on the data, and can accurately represent the difference in fracture water conducting direction by constructing an anisotropic permeability tensor model, and then can establish a deep physical constraint type geographically weighted regression model combined with seepage core parameters, so as to depict the spatial non-stationarity of water seepage amount while suppressing anti-physical fitting; therefore, the method can realize fast, stable and physically consistent prediction output of the water seepage amount of each fractal fracture element and the spatiotemporal distribution of the total cavern water seepage amount under the condition of continuous changes in the working conditions during the excavation-operation period, so as to provide quantitative support for early warning of water inrush risk, optimization of drainage design and engineering safety control, and reduce the time and cost overhead caused by traditional numerical iteration calculation.

[0016] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are incorporated herein and constitute part of this specification, illustrate embodiments consistent with the application and, together with the description, further serve to explain the principles of the application.

[0018] Figure 1 A schematic diagram of a system architecture showing an exemplary application environment in which a method and apparatus according to embodiments of the application can be applied is shown; Figure 2 A flowchart schematically showing a method according to some embodiments of the application is shown; Figure 3 A schematic diagram of an apparatus according to some embodiments of the application is shown; Figure 4 A schematic diagram of a computer system of an electronic device according to some embodiments of the application is shown.

[0019] Figure 5 A schematic diagram of a computer readable storage medium according to some embodiments of the application is shown. DETAILED DESCRIPTION

[0020] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The description of the exemplary embodiments is intended to apply to all alternative embodiments, unless otherwise indicated. It is to be understood that other equipment and processes can be utilized, and changes can be made without departing from the scope of the present application. The following detailed description is not to be taken in a limiting sense, and is understood that the scope of the present application is limited only by the claims.

[0021] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0022] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It is to be further understood that the terms "comprise", "comprising", "comprises", "including", "includes" or "contain" or "containing" when used in this specification, specify the presence of stated features, integers, steps, operations, elements, or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or groups thereof. It is to be understood that where the application, or portions thereof, is implemented using hardware, software, or a combination thereof, the various hardware and software described herein can be replaced with alternative hardware and software without departing from the scope of the present application.

[0023] Figure 1A schematic diagram of a system architecture of an exemplary application environment of a dynamic prediction method and device of a cavern water seepage amount to which embodiments of the present application can be applied is shown.

[0024] As shown in Figure 1 , the system architecture 100 can include one or more of terminal devices such as a desktop computer 101, a portable computer 102, a smart phone 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or fiber optic cables, etc. The terminal device can be various electronic devices with data processing functions, which have a display screen for showing the dynamic prediction result of the cavern water seepage amount to the user, including but not limited to the desktop computer, the portable computer, the smart phone, etc. It should be understood that Figure 1 the number of terminal devices, networks, and servers in is only illustrative. According to the implementation needs, there can be any number of terminal devices, networks, and servers. For example, the server 105 can be a sub-server cluster composed of multiple sub-servers, etc.

[0025] The dynamic prediction method of the cavern water seepage amount provided by the embodiments of the present application can generally be executed by the terminal device, and accordingly, the dynamic prediction device of the cavern water seepage amount is generally provided in the terminal device. However, it is easy for those skilled in the art to understand that the dynamic prediction method of the cavern water seepage amount provided by the embodiments of the present application can also be executed by the server 105, and accordingly, the dynamic prediction device of the cavern water seepage amount can also be provided in the server 105, which is not specially limited in the present exemplary embodiment.

[0026] In addition, it should be understood that the dynamic prediction method of the cavern water seepage amount of the present embodiment can be configured as a software module. In some implementation scenarios, the dynamic prediction method of the cavern water seepage amount of the present application can be deployed separately to be able to dynamically predict the water seepage amount of different caverns. In other implementation scenarios, the dynamic prediction method of the cavern water seepage amount of the present application can be deployed in other software as a functional module of the software, such as being deployed in the analysis software of the underground cavern, and the application mode of the dynamic prediction method of the cavern water seepage amount of the present application is not specially limited.

[0027] Next, the embodiments of the present application will be described in detail.

[0028] As shown in Figure 2 , Figure 2 is a flowchart of a dynamic prediction method of a cavern water seepage amount according to an exemplary embodiment of the present application, which includes: S210: acquiring underground cavern seepage influencing factor data; S220: Establish a fracture network dynamic evolution model based on the underground cavern seepage influence factor data to dynamically update the fractal characteristic parameters of each fractal fracture element; S230: Establish an anisotropic permeability tensor model according to the underground cavern seepage influence factor data; S240: Construct a deep physically constrained geographic weighted regression model based on the anisotropic permeability tensor model and seepage core parameters; S250: Input new underground cavern seepage influence factor data into the deep physically constrained geographic weighted regression model to obtain the seepage amount prediction value of each fractal fracture element and the spatiotemporal distribution of the total cavern seepage amount; S260: Output the seepage amount prediction value of each fractal fracture element and the spatiotemporal distribution of the total cavern seepage amount as the dynamic prediction result of the cavern seepage amount.

[0029] By obtaining the underground cavern seepage influence factor data, the information relied on by the seepage amount prediction is expanded from a single seepage monitoring quantity to a multi-dimensional input including hydrological recharge, fracture structure, and construction conditions, thereby reducing the influence of information loss and input deviation on the prediction result and improving the interpretability and effectiveness of the prediction.

[0030] Based on the underground cavern seepage influence factor data, a fracture network dynamic evolution model is established, and the fractal characteristic parameters of each fractal fracture element are dynamically updated, so that the spatial heterogeneity of the fracture network and the temporal changes during the excavation-operation period can be explicitly characterized, thereby overcoming the problem that static fracture parameters are difficult to adapt to construction disturbance and working condition changes, and improving the stability and consistency of seepage amount prediction in dynamic scenarios.

[0031] According to the underground cavern seepage influence factor data, an anisotropic permeability tensor model is established, which quantitatively expresses the directional difference of the fracture rock mass water conductivity, so that the permeability parameters can reflect both spatial and directional differences, thereby overcoming the problem that the homogeneous / single-value equivalent permeability coefficient is difficult to describe the anisotropy of fractures, leading to prediction bias, and improving the spatial precision and engineering checkability of seepage amount prediction.

[0032] Based on the anisotropic permeability tensor model and seepage core parameters, a deep physically constrained geographic weighted regression model is constructed, which not only describes the spatial non-stationarity of seepage amount but also introduces seepage physical constraints to suppress anti-physical fitting, thereby improving the robustness, generalization ability, and physical consistency of the prediction under conditions of noise, missing data, or insufficient samples.

[0033] The new underground cavern seepage influence factor data is input into the deep physical constraint type geographic weighted regression model to obtain a seepage amount prediction value of each fractal fissure element and a time-space distribution of total cavern seepage amount, so that the prediction result can be quickly updated according to a new working condition, high calculation cost caused by repeated reconstruction and iterative solving of a traditional numerical model is avoided, and local high-risk seepage area identification and global waterproof and drainage design optimization support are realized at the same time.

[0034] The seepage amount prediction value of each fractal fissure element and the time-space distribution of total cavern seepage amount are output as dynamic prediction results of cavern seepage amount, so that the prediction results can be directly used for water inrush risk early warning, waterproof and drainage capacity configuration, construction organization adjustment and operation period safety control, thereby reducing water inrush disaster risk and reducing engineering cost redundancy caused by conservative design.

[0035] In S210, underground cavern seepage influence factor data is acquired.

[0036] In the embodiment, the underground cavern seepage influence factor data is used to represent control conditions, medium structure characteristics, construction disturbance processes and seepage response results of a cavern seepage field, and at least includes traditional geological hydrological data, construction data and monitoring data. The seepage influence factor data is organized in a unified time-space coordinate system, so as to subsequently establish a fissure network dynamic evolution model, an anisotropic permeability tensor model and a deep physical constraint type geographic weighted regression model.

[0037] The traditional geological hydrological data is used to represent cavern surrounding rock medium properties, groundwater recharge and boundary conditions and fissure occurrence states, and can include but is not limited to: borehole exploration data such as borehole columnar graph, lithology stratification, rock mass quality index (Rock Quality Designation, RQD), rock mass integrity index, fissure development grade, permeability segmentation information corresponding to hole depth, etc.; fissure sketch map such as cavern working face / wall fissure sketch, joint strike and dip angle statistics, fissure density, fissure length distribution, through-going fissure identification, etc.; geophysical prospecting data such as abnormal body position, water-bearing structure indication information, fracture zone range obtained by seismic wave method, electrical method, transient electromagnetic method, geological radar, etc.; water pressure test data such as Lugeon value at different depths or different paragraphs, equivalent permeability coefficient distribution, segmented permeability evaluation results, etc.; groundwater level data such as observation hole water level, hole pressure monitoring data, recharge head boundary change process, etc.; rainfall data such as rainfall intensity, cumulative rainfall, rainfall duration, and lag characteristic quantity related to groundwater level / seepage amount response, etc.

[0038] Construction data is used to characterize the disturbance process of the stress field and fracture channel in the surrounding rock during excavation and its evolution over time, which can include but is not limited to excavation steps such as excavation method (drilling and blasting / mechanical excavation), cycle footage, excavation section shape, excavation sequence and sub-excavation strategy, etc.; supporting measures such as anchor rod / anchor cable arrangement, shotcrete thickness and age, steel arch arrangement, secondary lining construction time, water stop curtain arrangement, etc.; construction timing data such as the position of the working face advancing over time, key construction node timestamps (excavation completion, primary support completion, grouting completion, etc.), blasting parameters or disturbance intensity indicators, etc. In some embodiments, construction data can also include grouting parameters (slurry ratio, grouting pressure, grouting volume, grouting segment position) and drainage measures parameters to depict the dynamic influence of plugging and drainage on seepage channels.

[0039] Monitoring data is used to characterize the response state of the surrounding rock during construction and operation and the seepage output, which can include but is not limited to rock mass stress such as stress meter data, anchor stress, support structure stress, surrounding rock deformation / convergence, etc., which can be used to reflect the stress adjustment and fracture opening change trend; seepage amount such as time series monitoring values of seepage amount at different measuring points of the cavern, catchment / drainage system flow data, etc., which are used as dependent variables or verification indicators for model training.

[0040] In some embodiments, the underground cavern seepage influence factor data can be obtained by preprocessing the above-mentioned traditional geological hydrological data, construction data and monitoring data. Specifically, the preprocessing at least includes: outlier identification and elimination of the original data to eliminate outliers caused by sensor drift, false alarm codes or input errors; missing data completion to ensure data integrity at each time step / each spatial unit; normalization or standardization of data with different dimensions and value ranges to avoid unreasonable dominance of a single high-dimensional feature on model training; and spatio-temporal registration of data from different sources to map drilling, geophysical prospecting, fracture sketching, water pressure test, groundwater level, rainfall, excavation steps, supporting measures, construction timing, and rock mass stress, seepage amount, etc. to a unified spatial coordinate and a unified time scale, thereby forming an underground cavern seepage influence factor data set that can be used for subsequent fracture network dynamic evolution modeling, anisotropic permeability tensor construction and deep physical constraint type geographically weighted regression model training / prediction calls.

[0041] In S220, a fracture network dynamic evolution model is established based on the underground cavern seepage influence factor data to dynamically update the fractal characteristic parameters of each fractal fracture element.

[0042] In some embodiments, the underground cavern seepage influence factor data comprises rock mass stress monitoring data, which can be obtained by surrounding rock stress meters, anchor stress meters, steel arch stress monitoring devices and / or support stress monitoring devices, and the rock mass stress monitoring data comprises stress magnitude, stress direction and / or time series data of stress change over time.

[0043] A fracture network dynamic evolution model is established based on the underground cavern seepage influence factor data to dynamically update the fractal feature parameters of each fractal fracture element, which can be implemented in the following manner: First, fracture geometric features are extracted from the underground cavern seepage influence factor data. The fracture geometric features can be determined jointly by drilling log data, fracture sketch maps and geophysical interpretation results, and the fracture geometric features include one or more of fracture strike, fracture dip angle, fracture length, fracture dip angle, fracture spacing, fracture density, fracture opening and fracture connectivity. For the convenience of subsequent modeling, the fracture geometric features can be spatially mapped according to the axial mileage of the cavern, the location of the section and the depth of the surrounding rock, and time series alignment can be performed at a predetermined time step (e.g., daily, weekly or construction cycle) to obtain a fracture feature sequence or a fracture feature field for multi-scale analysis.

[0044] Secondly, the fractal feature parameters in the fracture geometric features are extracted by using a multi-fractal detrended fluctuation analysis method (MF-DFA). In one example, the fracture density sequence, the fracture spacing sequence and / or the fracture opening sequence within a certain spatial window or a certain candidate unit are taken as the input of MF-DFA, and through detrended processing, scale segmentation, fluctuation function calculation and scale index fitting, the fractal dimension , multi-fractal spectrum parameters (including generalized fractal dimension and singular spectrum ) and / or connectivity rate and other fractal feature parameters related to multi-scale heterogeneity are obtained. The fractal feature parameters can represent the complexity and local enrichment / thinning differences of the fracture network at different scales, and provide structural basis for subsequent fractal fracture element division and dynamic update.

[0045] The traditional fracture fractal dimension is calculated by using the box counting method. In one example, a grid with a box side length of is selected to cover the statistical domain, the number of boxes required to cover all fractures is counted, and the fracture fractal dimension is calculated according to the following formula: wherein is the calculation box side length (unit: m), which can be manually selected in engineering implementation, and the range is m, and can be adjusted according to the density of the fissures; The number of boxes required to cover all the fissures can be obtained by statistical analysis of the fissure sketch or by professional software. For reflecting the complexity of fissure development, The greater the value, the more developed the fissures, the denser the seepage channels, and the stronger the equivalent permeability of the rock mass.

[0046] Fissure connectivity For characterizing the ability of fissures to form continuous seepage channels, the following formula is used: wherein, is the total length of the through fissures that can form continuous seepage channels (unit: m), is the total length of all fissures in the statistical domain (unit: m), and the and can be obtained by geological logging, fissure network diagram or fissure sketch statistical analysis; , and The greater the value, the better the connectivity of the fissures, the stronger the ability to form effective seepage channels, and the stronger the water seepage capacity.

[0047] In one example, the quality index function is obtained based on MF-DFA, and the following is calculated: and the singularity index is obtained from and the singularity spectrum: wherein, is a degree parameter for adjusting the contribution of different intensity fissure sets to multi-scale statistics; and the and are used to characterize the multi-scale distribution heterogeneity and structural complexity of the fissure network. By combining and , the fissure network can be characterized from three dimensions of multi-fractal heterogeneity, overall geometric complexity and channel connectivity, thereby providing characteristic support for subsequent fractal fissure element division, fissure dynamic updating and permeability assignment.

[0048] Then, based on the fractal feature parameters, a clustering algorithm is used to divide the underground cavern into several fractal fracture elements that are internally homogeneous and externally significantly different. In some implementations, each candidate spatial unit (e.g., a spatial unit formed by mileage segments along the cavern axis and grid units along the cross-section) is first taken as the object, and multifractal spectrum parameters and traditional fractal / connectivity indices are extracted from the fracture information corresponding to the candidate spatial unit to form a clustering feature set. For example, in one example, for the first... Construct feature vectors from candidate spatial units Each feature can be standardized to eliminate the influence of differences in dimensions and scales on the clustering results. Then, the underground cavern is segmented along the axial direction (e.g., segmented by equidistant distance or by construction cycle), and within each mileage segment, it is discretized into a grid along the cross-sectional direction to obtain a set of candidate spatial units covering the cavern space; and the feature vectors are used to... As input to the clustering algorithm, based on the principle of density attainability and density connectivity, candidate spatial units with similar fractal characteristics and relatively continuous spatial distribution are clustered into the same class, while discrete units that cannot be classified into any high-density class are identified as noise points or boundary points. Through the density clustering mechanism of the clustering algorithm, partitions with significant differences in fracture fractal characteristics can be automatically identified without pre-specifying the number of clusters, suitable for engineering scenarios where underground cavern fractures exhibit non-uniform distributions such as local enrichment zones and fracture zones. Subsequently, the spatial region corresponding to each clustering result is defined as a fractal fracture element, making the fractal fracture element the basic unit for seepage prediction, and satisfying the requirements of internal homogeneity and significant external differences. To ensure relatively uniform permeability within the fractal fracture element, the following partitioning criteria are set in some implementations: for any fractal fracture element, the fractal characteristic parameters of its internal candidate spatial units are statistically analyzed, and the corresponding coefficient of variation is calculated. The coefficient of variation satisfies When a clustering result does not meet the aforementioned coefficient of variation threshold, it can be further subdivided by adjusting the parameters of the clustering algorithm (e.g., neighborhood radius and minimum number of samples), or further divided into smaller fractal fracture elements along the axial / cross-sectional direction, until the coefficient of variation threshold is met. This subdivision ensures that the fractal characteristic parameters within each fractal fracture element fluctuate minimally, making the rock mass permeability approximately uniform within the element. This provides a reliable foundation for subsequent dynamic permeability coefficient assignment based on element differences and local modeling using geographic weighted regression.

[0049] Finally, based on the rock mass stress monitoring data and the effective stress principle, the change in rock mass stress during construction excavation and support is calculated, and the variation law of fracture aperture is derived to dynamically update the fractal characteristic parameters of each fractal fracture element. In one example, for the first... A fractal fracture element, at time... Obtain the stress monitoring value of the rock mass and calculate the stress change amount compared with the previous time step , and convert the total stress change amount into the effective stress change amount based on the effective stress principle , wherein the effective stress can be obtained by subtracting the pore water pressure from the total stress; then, according to the fracture normal stress-opening degree response relationship (linear compression relationship, exponential closure relationship or empirical fitting relationship can be used), the update amount of the fracture opening degree is determined , so that when the effective stress decreases due to excavation unloading or support stress adjustment, the fracture opening degree increases; when the effective stress increases due to support compression or grouting consolidation, the fracture opening degree decreases. Further, the updated fracture opening degree is used to correct the fracture geometric feature sequence (such as the opening degree sequence, the equivalent connectivity index), and the corresponding fractal feature parameters are recalculated or recursively updated, thereby realizing the dynamic update of the fractal fracture element feature parameters with the construction disturbance and stress evolution.

[0050] Through the above implementation, the fracture network dynamic evolution model can associate the multi-scale structural features of the fracture with the stress changes caused by the construction disturbance, realize the continuous update of the fractal fracture element features, and enable the anisotropic permeability tensor model and the depth physically constrained geographically weighted regression model to be established subsequently to use time-varying fracture structure inputs that are more in line with the engineering practice, thereby improving the accuracy and stability of the water seepage amount prediction in the construction period and the operation period.

[0051] In S230, an anisotropic permeability tensor model is established according to the underground cavern seepage influence factor data.

[0052] The underground cavern seepage influence factor data includes fracture occurrence data. The fracture occurrence data is used to represent the spatial orientation features of the fractures, and at least one of the fracture strike and the fracture dip angle is included, and preferably the fracture strike, the fracture dip angle and the fracture trend are included; the fracture occurrence data can be obtained from the drilling log, the fracture sketch of the cavern wall / working face, the three-dimensional laser scanning, the photogrammetry modeling and / or the geophysical prospecting interpretation results such as the geological radar, and can further include the fracture set division results and the statistical distribution parameters (such as the average strike, the average dip angle and the dispersion) of each set. In some embodiments, the fracture occurrence data is statistically summarized according to the fractal fracture elements to obtain the dominant fracture orientation and the direction distribution of each fractal fracture element, which is used to determine the dominant seepage direction and provide a basis for the principal axis direction determination of the anisotropic permeability tensor model.

[0053] In some implementations, firstly, within each fractal fracture element, the dominant orientation parameter and permeability parameter of the fracture are determined based on the underground cavern seepage influence factor data. The dominant orientation parameter includes at least the dominant fracture orientation, dominant dip angle, and their directional statistical distribution. The permeability parameter includes at least fracture aperture, fracture density, fracture connectivity, and / or fractal dimension. Then, the dominant orientation parameter is used to determine the principal axis direction of anisotropic permeability, and the permeability parameter is used to determine the permeability components of anisotropic permeability along each principal axis direction, thereby constructing an anisotropic permeability tensor at the fractal fracture element scale.

[0054] In one example, for the first A fractal fracture element is used to construct a local coordinate system, such that the first principal axis is aligned with the dominant water-conducting direction of the fracture, the second principal axis is orthogonal to the first principal axis, and the third principal axis is along the radial or vertical direction of the cavern. Within this local coordinate system, the principal values ​​of the anisotropic permeability tensor are determined. , and The principal value can be determined based on the combined characteristics of the equivalent permeability coefficient, fracture aperture, and connectivity obtained from pressure water tests, as well as fractal characteristic parameters. The conversion from fractal characteristic parameters to the principal permeability value can be achieved using power function coupling or empirical mapping relationships. Subsequently, the principal permeability value and the principal axis direction are assembled into a permeability tensor in a global coordinate system through rotation transformation. In order to obtain the first Anisotropic permeability tensor model of a fractal fracture element.

[0055] Furthermore, at different time steps during the construction or operation period, the fracture aperture and connectivity can be updated by combining rock mass stress monitoring data, groundwater level changes, and construction disturbance intensity, and the principal value of the anisotropic permeability tensor can be updated simultaneously. This allows the anisotropic permeability tensor model to dynamically evolve with changes in operating conditions, thereby providing a time-varying, directionally relevant, and geologically compatible permeability parameter field for subsequent calculation of core seepage parameters and depth-physically constrained geographic weighted regression models.

[0056] In some implementations, the anisotropic permeability tensor model is represented in three-dimensional tensor form as follows: in, ( () represents the components of the permeability tensor, with units of m / d. Specifically, ( The permeability component in the corresponding principal direction is used to characterize the difference in water conductivity of the rock mass in different principal directions (e.g., the dominant seepage direction, the direction perpendicular to the dominant seepage direction, and the third orthogonal direction). Typically, the dominant seepage direction can be determined by statistical analysis of the dominant strike / dip angle of fractures within fractal fracture elements, or by seepage observations and geological structural indications.

[0057] also, ( The permeability coupling effect coefficient reflects the coupling effect and mutual influence between seepage processes in different directions, such as anisotropic coupling effects caused by the intersection of fracture systems, non-orthogonal water-conducting channels, or structural shear. In engineering implementation, the coupling effect coefficient can be determined by fitting field-measured permeability coefficient data (e.g., pressure water tests, pumping tests, or inverted seepage parameters), and can be corrected as construction / operation data are updated to make the permeability tensor model more closely fit actual seepage conditions.

[0058] In S240, a deep physical constraint geographic weighted regression model is constructed based on the anisotropic permeability tensor model and the core parameters of seepage.

[0059] In some implementations, the core seepage parameters include at least the hydraulic gradient. With the cross-sectional area of ​​water passage .

[0060] Among them, hydraulic gradient The head loss per unit seepage path length is characterized by the following formula: In the formula, The difference in water head at both ends of the fractal fracture element can be calculated based on the elevation benchmark determined by the geological profile and combined with groundwater level data. The seepage path length can be determined based on the relationship between the geological profile and the spatial location of the cavern, or based on the equivalent path length of the dominant seepage direction within the fractal fracture element. This can be achieved by introducing a hydraulic gradient. It can explicitly quantify the impact of groundwater recharge intensity, water level boundary changes, and seepage driving force on seepage volume.

[0061] Cross-sectional area of ​​water flow The equivalent flow rate used to characterize seepage at the cavern-surrounding rock interface is calculated using the following formula: The perimeter of the cavern is determined by its designed shape; the length of the fractal fracture element is its length along the cavern's axis, which can be obtained from the spatial division of the fractal fracture element. This is achieved by introducing the cross-sectional area of ​​the water passage. The influence of the cavity size and the length difference of the segments on the catchment capacity and the seepage amount can be taken into account in the calculation of the seepage core parameters, thereby providing a calculable and engineering-geometry-consistent input for the physical constraint term of the theoretical seepage amount .

[0062] On this basis, a deep physical constraint type geographic weighted regression model is constructed based on the anisotropic permeability tensor model and the seepage core parameters, and can be implemented in the following manner: First, a power coupling formula of the permeability coefficient is constructed based on the fractal fracture element and the fractal characteristic parameters thereof. In some embodiments, the fractal characteristic parameters of each fractal fracture element are taken as independent variables to establish a power coupling relationship between the permeability coefficient and the fractal characteristics, which is used to map the multi-scale structural characteristics of the fracture into an equivalent permeability. For example, the first principal direction permeability component of the first fractal fracture element in the principal direction coordinate system can be expressed as follows: The following power coupling form is adopted: wherein, is the reference permeability coefficient of the first principal direction, is a power index coefficient, which can be calibrated through a water pressure test, a water pumping test or historical inversion data; in some embodiments, the width, peak value and other statistics of the fracture can also be introduced into the above coupling formula to enhance the characterization ability of the multi-fractal heterogeneity of the fracture. Second, the anisotropic permeability tensor of each fractal fracture element is obtained by assigning values to the anisotropic permeability tensor model according to the power coupling formula of the permeability coefficient. In some embodiments, for the first fractal fracture element, the tensor diagonal elements

[0063] corresponding to the dominant seepage direction, the direction perpendicular to the dominant direction and the third orthogonal direction, respectively) are first determined in the principal direction coordinate system and are calculated by the above power coupling formula; at the same time, the off-diagonal elements are taken as the permeability coupling effect coefficient to reflect the mutual influence of seepage in different directions, which can be determined by fitting the measured permeability coefficient data. Thus, the anisotropic permeability tensor of the first fractal fracture element is obtained as follows: , whose unit is m / d Then, the theoretical seepage amount of each fractal fracture element is calculated by using the anisotropic permeability tensor of each fractal fracture element and the seepage core parameters. In some embodiments, the water content is introduced to reflect the saturated-unsaturated seepage characteristics, wherein ​​​​​​The van Genuchten unsaturated flow model can be combined with the pore pressure / water content monitoring or boundary conditions to obtain the theoretical water seepage amount of the first fractal fracture element : : wherein, represents the equivalent permeability component of the permeability tensor of the first fractal fracture element in the seepage direction (in engineering implementation, the principal value of the dominant seepage direction or the equivalent projection of the direction cosine on the permeability tensor can be obtained) . The unit of is m³ / d.

[0064] Next, the spatial weight is constructed and the spatial weight matrix is formed. In some embodiments, the Gaussian kernel function is used to calculate the basic spatial weight between different fractal fracture elements, and the construction disturbance factor and the geological similarity factor are introduced to dynamically adjust the basic spatial weight, so as to obtain the spatial weight : wherein, is the spatial Euclidean distance between the center of the first fractal fracture element and the center of the second fractal fracture element (unit: m), is a bandwidth parameter; is a construction disturbance weight, which is used to reflect the disturbance influence of the excavation face advancement, support and grouting on the fracture water conductivity, and is preferably dynamically determined according to the distance from the fractal fracture element to the excavation face, so that the closer the distance, the larger the . is a geological similarity weight, which is used to reflect the stronger correlation between the units with similar lithology, fractal characteristics and fracture parameters, and is preferably determined based on the similarity measurement of the lithology category, fractal dimension , connectivity rate and multi-fractal spectrum parameters, so that the higher the similarity, the larger the . In order to ensure that the weight can be used for local regression solution, in some embodiments, the is normalized, so that the sum of the weights corresponding to the first fractal fracture element and the second fractal fracture element is 1, that is: wherein is the total number of fractal fracture elements. Further, the normalized weight is constructed as a dimensional diagonal weight matrix corresponding to the first fractal fracture element: wherein is the total number of fractal fracture elements. Further, the normalized weight is constructed as a dimensional diagonal weight matrix corresponding to the first fractal fracture element: ​​​To achieve spatially weighted regression where near elements are larger than far elements, fractal fracture elements with closer spatial locations or more similar geological structures are paired with the first element. The local coefficients of each fractal fracture element contribute more significantly.

[0065] Finally, based on the theoretical seepage volume and spatial weight matrix of each fractal fracture element, a deep physical constraint-based geographically weighted regression model is established, using a geographically weighted regression model as the foundation. In some implementations, the first... The effective influence factors of each fractal fracture element are composed of a vector. and based on the actual measured seepage volume As the dependent variable, a deep physical-constrained geographic-weighted regression model is established: in, This is a spatial local constant term (taken as 0 in some implementations). For the first The fractal fracture element pairs with the first Spatial local regression coefficients of each influencing factor This is the residual term. The spatial local regression coefficients are calculated using weighted least squares and a weight matrix. The solution can be specifically expressed as: in, For the first The coefficient vector of each fractal fracture element. For an effective influence factor matrix, This is the measured seepage vector. As adaptive physical constraint weights, used to dynamically balance the contribution of data-driven regression fitting and physical constraints (theoretical seepage), in some implementations: The maximum weight value, For the weight growth rate, The number of training iterations for the model; and This can be determined through error feedback and convergence optimization during the training process. (This is achieved by adjusting the theoretical seepage volume.) Introducing local regression as a physical constraint term can enhance physical consistency while maintaining the spatial non-stationarity of GWR, thereby suppressing inverse physical fitting and improving the stability and engineering applicability of seepage prediction.

[0066] In S250, the new underground cavern seepage influencing factor data are input into the deep physical constraint geographic weighted regression model to obtain the predicted seepage volume of each fractal fracture element and the spatiotemporal distribution of the total cavern seepage volume.

[0067] The new underground cavern seepage influence factor data refers to updated data collected at a new time step or a new construction stage relative to the data already used in the model training stage, and the updated data at least includes one or more of the underground water level, rainfall, construction advancement position and support / grouting timing, and seepage quantity or monitoring quantity related to seepage. Before inputting the updated data into the model, the updated data is preferably subjected to outlier rejection, missing value completion, normalization processing and spatio-temporal registration according to the data preprocessing procedure of step S210, so that the updated data can be mapped to a unified spatio-temporal framework of each fractal fissure element, forming a first influence factor vector of the

[0068] In some embodiments, the predicted values of each fractal fissure element can be projected and spliced according to the cavern axial mileage and the spatial position of the cross section, to obtain the seepage quantity distribution curve of the cavern along the axial direction and the cross section distribution map; and the predicted values of all fractal fissure elements at the same time can be summarized to obtain the total seepage quantity prediction value of the whole cavern , so as to form a spatio-temporal dynamic prediction result of fractal fissure element level prediction and cavern level summary.

[0069] In some embodiments, before inputting the new underground cavern seepage influence factor data into the deep physically constrained geographic weighted regression model to obtain the seepage quantity prediction value of each fractal fissure element and the spatio-temporal distribution of the whole cavern seepage quantity, the cavern seepage quantity dynamic prediction method further includes the steps of screening the influence factors and training the model, which are as follows: First, the fissure geometric features and seepage related features in the underground cavern seepage influence factor data are extracted. The fissure geometric features can include fissure trend, dip angle, length, spacing, density, opening, connectivity rate, fractal dimension / multifractal spectrum parameters, etc.; the seepage related features can include underground water level, rainfall, pore water pressure, water content, equivalent permeability coefficient of pressure water test, construction disturbance intensity index, rock mass stress change amount, hydraulic gradient and water passing section area, etc. In order to ensure that the features can be used for regression modeling, the above features are preferably summarized and spatio-temporally registered according to the fractal fissure element and the time step, to form a candidate feature set with fractal fissure element as the sample granularity.

[0070] ​​​Secondly, effective influencing factors on cavern seepage volume are screened from the aforementioned fracture geometry features and seepage-related features. In some embodiments, correlation analysis, significance testing, stepwise regression, or feature selection methods based on information criteria can be used to screen candidate features, eliminating features with weak correlation or poor stability with seepage volume, and retaining effective influencing factors that can explain changes in seepage volume. These effective influencing factors serve as input variables for geographically weighted regression, characterizing the intensity of the effects of seepage driving force, permeability, and construction disturbance on seepage volume at different spatial locations.

[0071] Then, the variance inflation factor (VIF) is used to eliminate collinear factors, and an impact factor matrix is ​​constructed based on the remaining factors. In some implementations, the VIF value is calculated for each of the selected candidate effective impact factors. When the VIF value of an impact factor exceeds a preset threshold (e.g., 10 or 5), it is identified as a collinear factor and removed from the candidate set or merged with related factors. After processing the collinear factors, the remaining impact factors are used to construct an impact factor matrix in a sample-factor manner. Each row corresponds to a sample of a fractal fracture element at a certain time step, and each column corresponds to an influence factor.

[0072] Furthermore, the deep physical constraint geographic weighted regression model is trained using the aforementioned influence factor matrix and measured infiltration volume to obtain a trained deep physical constraint geographic weighted regression model. In some embodiments, the measured infiltration volume is used as the dependent variable vector. By combining the spatial weight matrix and the physical constraint term of theoretical infiltration, a weighted least squares and adaptive physical constraint weight strategy is adopted to solve the parameters and iteratively optimize the deep physical constraint geographic weighted regression model. This yields a set of model parameters that converge on the training data and meet the error index requirements, thus obtaining a well-trained deep physical constraint geographic weighted regression model.

[0073] Finally, the new underground cavern seepage influencing factor data is input into the deep physical constraint geographic weighted regression model to obtain the predicted seepage volume of each fractal fracture element and the spatiotemporal distribution of the total cavern seepage volume. This includes generating an input vector / input matrix consistent with the influencing factor matrix by processing the new underground cavern seepage influencing factor data according to the same preprocessing, feature extraction, and factor construction process as in the training phase, and inputting the new underground cavern seepage influencing factor data into the trained deep physical constraint geographic weighted regression model, thereby outputting the predicted seepage volume of each fractal fracture element and the spatiotemporal distribution of the total cavern seepage volume obtained by summing the predicted values.

[0074] In S260, the predicted seepage volume of each fractal fracture element and the spatiotemporal distribution of the total seepage volume of the cavern are output as the dynamic prediction result of the cavern seepage volume.

[0075] In some embodiments, the output is provided in electronic data form, which at least includes tabular output and spatial distribution output. The tabular output is used to record the predicted values of each fracturing fissure element at different time steps and its corresponding influence factor state; the spatial distribution output is used to present the spatial and temporal distribution of cavern seepage in the form of a curve, a heat map or a zoning color map. Through the above output mode, the prediction results can be directly used for cavern waterproof and drainage design optimization, water inrush risk early warning and engineering safety control decision-making, and the dynamic prediction results of cavern seepage can be realized.

[0076] The underground main powerhouse cavern of a large pumped storage power station is selected as an experimental carrier, the excavation size of the underground powerhouse main engine room is 110.0m*25.4m*55.5m (length* width*height), the overlying rock mass of this part is about 313m-464m thick, the surface bedrock is exposed, and the vegetation is dense. According to the geological exposure, the fissure development is uneven, and there are through fissure zones in some parts, and the seepage characteristics show obvious anisotropy and dynamic change (significantly affected by construction excavation disturbance), which is consistent with the typical characteristics of complex fissured rock mass underground engineering. The underground water is mainly seepage-dripping water, and it is estimated that the groundwater level in the powerhouse area is about 180m deep, and the water level difference above the powerhouse roof is about 235m. The rock quality is relatively hard, the fissures are well developed, and the surrounding rock is relatively complete to locally broken. The surrounding rock is mainly type III, and the fault or fissure dense zone is type IV. During the construction period, 15 seepage monitoring points and 5 rock mass stress monitoring points are arranged; 180 days of continuous measured data are collected, covering all types of data such as geological hydrology, construction disturbance and seepage monitoring, providing sufficient data support for verification.

[0077] The 30-day measured seepage of a monitoring point is compared with the predicted value of the model of the application, and part of the data is shown in the following table: Table 1 Comparison of actual monitoring value and predicted value of a monitoring point In addition, the existing monitoring value at a certain position is selected, and if the commonly used data fitting method (least square method) is used to fit and calculate the existing original data, the fitting coefficient is obtained, and the fitting equation is: Based on the above fitting equation, the cavern seepage in the next 10 days and 20 days is predicted, as shown in Table 2. Obviously, only data fitting is considered, without considering the physical equation and geological conditions, the prediction error is large, and the prediction error becomes larger as the prediction days increase.

[0078] Table 2 Comparison of cavern seepage obtained by different methods within a predetermined number of days Therefore, the application can realize rapid and stable prediction output of the cavern seepage water under the condition of continuous change of the excavation-operation period working condition, provide quantitative support for early warning of water inrush risk, optimization of drainage design and engineering safety control, and reduce time and cost overheads caused by traditional numerical iterative calculation.

[0079] According to the second aspect of the embodiment of the application, a cavern seepage water dynamic prediction device 300 is further provided, as shown in the figure, the cavern seepage water dynamic prediction device 300 comprises: Figure 3 A data acquisition module 310, configured to acquire underground cavern seepage influencing factor data; A first modeling module 320, configured to establish a fracture network dynamic evolution model based on the underground cavern seepage influencing factor data, so as to dynamically update fractal characteristic parameters of each fractal fracture element; A second modeling module 330, configured to establish an anisotropic permeability tensor model according to the underground cavern seepage influencing factor data; A third modeling module 340, configured to construct a deep physical constraint type geographic weighted regression model based on the anisotropic permeability tensor model and seepage core parameters; An operation module 350, configured to input new underground cavern seepage influencing factor data into the deep physical constraint type geographic weighted regression model, so as to obtain a seepage water prediction value of each fractal fracture element and a full-cavern seepage water spatio-temporal distribution; A result output module 360, configured to output the seepage water prediction value of each fractal fracture element and the full-cavern seepage water spatio-temporal distribution as the cavern seepage water dynamic prediction result. It should be noted that although several modules of the cavern seepage water dynamic prediction device are mentioned in the foregoing detailed description, such division is not mandatory. In fact, according to the embodiments of the application, the features and functions of two or more modules described above can be embodied in one module or unit. Conversely, the features and functions of one module described above can be further divided into a plurality of modules or sub-modules.

[0080] In addition, in the exemplary embodiments of the application, an electronic device capable of realizing the above-mentioned cavern seepage water dynamic prediction method is further provided.

[0081] Those skilled in the art can understand that each aspect of the application can be implemented as a system, a method or a program product. Therefore, each aspect of the application can be embodied as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" here.

[0082] ​

[0083] The electronic device 400 according to this embodiment of the present application will be described below with reference to Figure 4 FIG. 4. Figure 4 The electronic device 400 shown is merely one example and should not be taken as limiting the scope of the present application embodiments.

[0084] As shown, the electronic device 400 is in the form of a general computing device. The components of the electronic device 400 can include, but are not limited to, the at least one processing unit 410 described above, the at least one storage unit 420 described above, a bus 430 that connects the various system components including the storage unit 420 and the processing unit 410, a display unit 440. Figure 4 The storage unit 420 can include a readable medium in the form of volatile storage such as random access memory (RAM) 421 and / or cache memory 422, and can further include non-volatile storage such as read-only memory (ROM) 423.

[0085] The storage unit 420 can include a readable medium in the form of volatile storage such as random access memory (RAM) 421 and / or cache memory 422, and can further include non-volatile storage such as read-only memory (ROM) 423. Figure 2 The storage unit 420 can include a readable medium in the form of volatile storage such as random access memory (RAM) 421 and / or cache memory 422, and can further include non-volatile storage such as read-only memory (ROM) 423. The storage unit 420 can include a readable medium in the form of volatile storage such as random access memory (RAM) 421 and / or cache memory 422, and can further include non-volatile storage such as read-only memory (ROM) 423.

[0086] The storage unit 420 can include a readable medium in the form of volatile storage such as random access memory (RAM) 421 and / or cache memory 422, and can further include non-volatile storage such as read-only memory (ROM) 423. The storage unit 420 can include a readable medium in the form of volatile storage such as random access memory (RAM) 421 and / or cache memory 422, and can further include non-volatile storage such as read-only memory (ROM) 423.

[0087] The storage unit 420 can include a readable medium in the form of volatile storage such as random access memory (RAM) 421 and / or cache memory 422, and can further include non-volatile storage such as read-only memory (ROM) 423. The storage unit 420 can include a readable medium in the form of volatile storage such as random access memory (RAM) 421 and / or cache memory 422, and can further include non-volatile storage such as read-only memory (ROM) 423.

[0088] Bus 430 can be one or more of several types of bus structure including a memory bus or memory controller, a peripheral bus, a graphics bus, a processor or local bus using any of a variety of bus architectures.

[0089] Electronic device 400 can also communicate with one or more external devices 470 such as a keyboard or pointing device, a Bluetooth device, etc.; other devices that enable a user to interact with electronic device 400; and / or any devices (e.g., a router, a modem, a printer, etc.) that enable electronic device 400 to communicate with one or more other computing devices. Such communication can occur via input / output (I / O) interface 450. Still yet, electronic device 400 can communicate with one or more networks, such as a local area network (LAN), a general wide area network (WAN), and / or a public network such as the Internet, via network adapter 460. As depicted, network adapter 460 communicates with the other components of electronic device 400 via bus 430. It should be appreciated that although not shown, other hardware and / or software components could be used in conjunction with electronic device 400. These include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0090] Those skilled in the art will readily understand that the example embodiments described herein can be implemented by software and / or by hardware coupled with software, as described above. Thus, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which can be stored in an non-volatile storage medium (which can be a CD-ROM, a USB flash disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present application.

[0091] In the example embodiments of the present application, a computer readable storage medium is also provided, which stores the program product capable of implementing the above-mentioned method of the present application. In some possible embodiments, various aspects of the present application can also be implemented in the form of a program product, which includes program codes for causing a terminal device to perform the steps according to various example embodiments of the present application described in the above-mentioned "example method" section when the program product is run on the terminal device.

[0092] Reference Figure 5As shown, a program product 500 for implementing the above-mentioned dynamic prediction method of the amount of water seepage in a cavern according to an embodiment of the present application is described, which can adopt a portable compact disc read-only memory (CD-ROM) and include program codes, and can be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto, and in the present application, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus or device.

[0093] The program product can adopt any combination of one or more readable storage media. The readable storage media can be, for example but not limited to, an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples (non-exhaustive list) of the readable storage media include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0094] The program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, C++, etc., and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0095] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended for limiting purposes. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of the processes. In addition, it is also easy to understand that the processes can be executed synchronously or asynchronously, for example, in multiple modules.

[0096] Those skilled in the art can easily understand, through the above description of the embodiments, that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0097] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The present application is intended to cover any variations, uses or adaptations of the application following, in general, the principles of the application and including such

[0098] It should be understood that the application is not limited to the precise construction that has been described above and shown in the accompanying drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application is limited only by the appended claims.

Claims

1. A method for dynamically predicting the amount of water seepage in a cavern, characterized in that, The method comprises the following steps: obtaining underground cavern seepage influencing factor data; establishing a fracture network dynamic evolution model based on the underground cavern seepage influencing factor data to dynamically update the fractal characteristic parameters of each fractal fracture element; establishing an anisotropic permeability tensor model according to the underground cavern seepage influencing factor data; constructing a deep physical constraint type geographically weighted regression model based on the anisotropic permeability tensor model and seepage core parameters; inputting new underground cavern seepage influencing factor data into the deep physical constraint type geographically weighted regression model to obtain the predicted value of the seepage amount of each fractal fracture element and the spatio-temporal distribution of the total cavern seepage amount; outputting the predicted value of the seepage amount of each fractal fracture element and the spatio-temporal distribution of the total cavern seepage amount as the dynamic prediction result of the cavern seepage amount.

2. The method of claim 1, wherein, The underground cavern seepage influencing factor data comprises rock mass stress monitoring data; establishing a fracture network dynamic evolution model based on the underground cavern seepage influencing factor data to dynamically update the fractal characteristic parameters of each fractal fracture element comprises the following steps: extracting fracture geometric characteristics from the underground cavern seepage influencing factor data; extracting fractal characteristic parameters in the fracture geometric characteristics by using a multi-fractal detrended fluctuation analysis method; based on the fractal characteristic parameters, using a clustering algorithm to divide the underground cavern into a plurality of fractal fracture elements which are internally homogeneous and externally significantly different; according to the rock mass stress monitoring data, combining the principle of effective stress to calculate the change amount of rock mass stress in the process of construction excavation and support, and then deducing the change rule of fracture opening to dynamically update the fractal characteristic parameters of each fractal fracture element.

3. The method of claim 2, wherein, The underground cavern seepage influencing factor data comprises fracture occurrence data; establishing an anisotropic permeability tensor model according to the underground cavern seepage influencing factor data comprises the following steps: determining the seepage dominant direction of the underground cavern according to the fracture occurrence data; establishing a principal direction coordinate system of permeability based on the seepage dominant direction; establishing the anisotropic permeability tensor model in the principal direction coordinate system.

4. The method of claim 2, wherein, constructing a deep physical constraint type geographically weighted regression model based on the anisotropic permeability tensor model and seepage core parameters comprises the following steps: based on the fractal fracture elements and the fractal characteristic parameters of each fractal fracture element, constructing a permeability coefficient power coupling formula; according to the permeability coefficient power coupling formula, assigning values to the anisotropic permeability tensor model to obtain the anisotropic permeability tensor of each fractal fracture element; using the anisotropic permeability tensor of each fractal fracture element and the seepage core parameters to calculate the theoretical seepage amount of each fractal fracture element; using a Gaussian kernel function to calculate the basic spatial weight between different fractal fracture elements, and introducing a construction disturbance factor and a geological similarity factor to dynamically adjust the basic spatial weight to obtain a spatial weight; based on the spatial weight of all fractal fracture elements, obtaining a spatial weight matrix; based on the theoretical seepage amount of each fractal fracture element and the spatial weight matrix, establishing the deep physical constraint type geographically weighted regression model based on a geographically weighted regression model.

5. The method of claim 4, wherein, The spatial weight comprising: in, For the first The fractal fracture element and the first The spatial Euclidean distance between the centers of each fractal fracture element. For bandwidth parameters; The construction disturbance weight is dynamically adjusted based on the distance between the excavation face and the fractal fracture element. The smaller The larger; The geological similarity weight is determined based on the similarity measure of the lithology and / or fracture characteristics of fractal fracture elements; the higher the similarity, the greater the weight. The larger.

6. The method of claim 4, wherein, According to the theoretical seepage amount of each fractal fissure element and the spatial weight matrix, a deep physical constraint type geographically weighted regression model is established based on a geographically weighted regression model, and the deep physical constraint type geographically weighted regression model comprises: wherein, is the measured infiltration of the th fractal fracture element; is the constant term; is the measured infiltration of the th fractal fracture element; is the th effective influence factor corresponding to the th fractal fracture element, is the number of effective influence factors; is the th spatial local regression coefficient corresponding to the th fractal fracture element, which is obtained by using the weighted least squares of the spatial weight matrix , is the regression coefficient vector of the th fractal fracture element, is the effective influence factor matrix, is the measured infiltration vector; is the adaptive physical constraint weight, which is used to balance the data-driven regression fitting and the contribution of physical constraints, and satisfies , is the maximum weight value and , is the weight growth rate, is the number of model training iterations; is the theoretical infiltration of the th fractal fracture element, and satisfies wherein, is the component of the anisotropic permeability tensor or the equivalent permeability parameter of the th fractal fracture element, is the hydraulic gradient, is the water cross-sectional area, is the water content of the fractal fracture element.

7. The method of claim 1-6, wherein Before inputting new underground cavern seepage influence factor data into the deep physical constraint type geographically weighted regression model to obtain the seepage amount prediction value of each fractal fissure element and the spatiotemporal distribution of the total cavern seepage amount, the cavern seepage amount dynamic prediction method further comprises: extracting fissure geometric features and seepage related features in the underground cavern seepage influence factor data; screening effective influence factors of cavern seepage amount from the fissure geometric features and the seepage related features; adopting a variance inflation factor to remove collinear factors and constructing an influence factor matrix based on the remaining factors; training the deep physical constraint type geographically weighted regression model using the influence factor matrix and the measured seepage amount to obtain a trained deep physical constraint type geographically weighted regression model; inputting new underground cavern seepage influence factor data into the deep physical constraint type geographically weighted regression model to obtain the seepage amount prediction value of each fractal fissure element and the spatiotemporal distribution of the total cavern seepage amount comprises: inputting new underground cavern seepage influence factor data into the trained deep physical constraint type geographically weighted regression model to obtain the seepage amount prediction value of each fractal fissure element and the spatiotemporal distribution of the total cavern seepage amount.

8. A device for dynamically predicting the amount of water seepage in a cavern, characterized by, comprises: a data acquisition module configured to acquire underground cavern seepage influence factor data; a first modeling module configured to establish a fissure network dynamic evolution model based on the underground cavern seepage influence factor data to dynamically update fractal feature parameters of each fractal fissure element; a second modeling module configured to establish an anisotropic permeability tensor model according to the underground cavern seepage influence factor data; a third modeling module configured to construct a deep physical constraint type geographically weighted regression model based on the anisotropic permeability tensor model and seepage core parameters; a running module configured to input new underground cavern seepage influence factor data into the deep physical constraint type geographically weighted regression model to obtain a seepage amount prediction value of each fractal fissure element and a spatiotemporal distribution of the total cavern seepage amount; a result output module configured to output the seepage amount prediction value of each fractal fissure element and the spatiotemporal distribution of the total cavern seepage amount as the cavern seepage amount dynamic prediction result.

9. An electronic device, comprising: comprises: a processor; and a memory having computer readable instructions stored thereon, the computer readable instructions being executed by the processor to implement the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, a computer program stored thereon, the computer program being executed by a processor to implement the method of any one of claims 1 to 7.

Images