Attribute modeling method and system for joint constraints of tunnel surface and perimeter multi-source information

Abstract

The present invention discloses a tunnel surface-perimeter multi-source information joint constraint attribute modeling method and system, relating to the technical field of underground engineering geological modeling. The method comprises: obtaining spatial information and geological attribute information of the tunnel geological body area, using an adaptive network partitioning method based on local features to divide the area into several grids, and constructing a grid model; for each grid area, performing data preprocessing on the acquired geological attribute data, initially assigning geological attributes to the grid model based on the preprocessed data, modeling the spatial distribution of fractures, porosity, water-bearing bodies, and elasticity models in the model, thereby constructing an initial attribute model; based on the latest drilling data, calculating the correlation between the new and old drilling data, and fitting the drilling data based on the correlation. After fitting, the latest drilling data is integrated into the initial attribute model to obtain an updated tunnel geological attribute model. The present invention can achieve refined modeling of the geological attributes of the tunnel area.

Description

Technical Field

[0001] The present invention relates to the technical field of underground engineering geological modeling, and in particular to an attribute modeling method and system for jointly constraining tunnel surface-hole perimeter multi-source information. Background Art

[0002] Tunnels are essential components of underground engineering projects. Their safety, stability, and long-term performance are directly related to construction, operation, and subsequent maintenance. Modeling tunnel geological properties is particularly critical under complex geological conditions. Geotechnical properties surrounding tunnels, such as fractures, porosity, water content, and elastic modulus, profoundly impact key tunnel indicators such as permeability and stability. To accurately assess tunnel construction risks, long-term stability, and potential operational issues, precise modeling and dynamic prediction of the geological characteristics of the tunnel area are essential. With the continuous advancement of exploration technology, existing exploration methods such as borehole exploration, seismic waves, geological radar, and acoustic wave exploration are increasingly being applied to tunnel geological modeling. These exploration techniques can provide richer and more comprehensive geological information, helping to more accurately describe the complex geological features surrounding tunnels. However, the data obtained through these exploration techniques are often heterogeneous and diverse. Integrating these disparate data sources and effectively integrating them into a unified model remains a major challenge in the field of tunnel geological modeling.

[0003] Traditional tunnel geological modeling methods rely primarily on borehole exploration data, field tests, and empirical knowledge, typically constructing two-dimensional or three-dimensional geological models. While these methods have achieved some success in practical applications, their reliance on limited exploration data makes it difficult for these models to fully and accurately reflect the complex geological conditions of the tunnel area. This is particularly true when modeling complex geological structures (such as fractured zones, gravel layers, and water-bearing structures). Traditional methods have limited processing power and precision, which restricts the accuracy and reliability of the modeling results. Furthermore, spatial interpolation modeling using geostatistical methods based on limited borehole data, while capable of providing a certain degree of modeling accuracy in some cases, often fails to fully reflect the complex underground geological structures due to the limited number of boreholes and their spatial location. For example, when modeling complex geological structures such as fractures, water-bearing structures, and gravel layers, traditional interpolation results often suffer from inaccuracy or incompleteness, resulting in poor accuracy and reliability of tunnel geological models. Summary of the Invention

[0004] To address the deficiencies of the above-mentioned prior art, the present invention provides a tunnel surface-periphery multi-source information joint constraint attribute modeling method and system. Based on the information on cracks, porosity, water content, etc. revealed by drilling data, combined with spatial information provided by means such as geological radar and acoustic exploration, by integrating different exploration data and combining adaptive grid division technology, a refined modeling of the geological attributes of the tunnel area is achieved, thereby improving the accuracy and reliability of the tunnel geological model and enhancing the tunnel safety assessment and construction risk prediction capabilities.

[0005] In a first aspect, the present invention provides an attribute modeling method with joint constraints of tunnel surface and hole perimeter multi-source information.

[0006] A tunnel surface-perimeter multi-source information joint constraint attribute modeling method includes:

[0007] Obtain spatial information and geological attribute information of the tunnel geological area, divide the area into several grids using an adaptive network partitioning method based on local features, and construct a grid model. Geological attribute information includes fracture location and distribution, porosity, water seepage information, and elastic modulus.

[0008] For each grid area, the acquired geological attribute data is preprocessed, and the grid model is initially assigned geological attributes based on the preprocessed data. The spatial distribution of fractures, porosity, water-bearing bodies, and elasticity models are modeled in the model to construct an initial attribute model.

[0009] Based on the latest drilling data, the correlation between the new and old drilling data is calculated, and the drilling data is fitted based on the correlation. After fitting, the latest drilling data is integrated into the initial attribute model to obtain an updated tunnel geological attribute model.

[0010] In a second aspect, the present invention provides an attribute modeling system with joint constraints of tunnel surface and hole perimeter multi-source information.

[0011] A tunnel surface-perimeter multi-source information joint constraint attribute modeling system, comprising:

[0012] The gridding module is used to obtain spatial information and geological attribute information of the tunnel geological area. It uses an adaptive network partitioning method based on local characteristics to divide the area into several grids and construct a grid model. The geological attribute information includes the location and distribution of cracks, porosity, water seepage information, and elastic modulus.

[0013] The initial attribute model building module is used to preprocess the acquired geological attribute data for each grid area, and preliminarily assign geological attributes to the grid model based on the preprocessed data. The spatial distribution of fractures, porosity, water-bearing bodies, and elasticity models are modeled in the model to construct the initial attribute model.

[0014] The tunnel geological body attribute modeling module is used to calculate the correlation between the new and old drilling data based on the latest drilling data, and fit the drilling data based on the correlation. After fitting, the latest drilling data is integrated into the initial attribute model to obtain an updated tunnel geological attribute model.

[0015] In a third aspect, the present invention also provides an electronic device comprising: a memory for storing executable instructions; and a processor for implementing the above-mentioned attribute modeling method of joint constraints of tunnel surface-hole perimeter multi-source information when executing the executable instructions stored in the memory.

[0016] In a fourth aspect, the present invention further provides a computer-readable storage medium storing executable instructions for causing a processor to execute the executable instructions to implement the above-mentioned attribute modeling method of the joint constraint of tunnel surface-hole perimeter multi-source information.

[0017] In a fifth aspect, the present invention also provides a computer program product, which includes executable instructions stored in a computer-readable storage medium; wherein, when the processor of the electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the above-mentioned attribute modeling method of the joint constraint of tunnel surface-hole perimeter multi-source information is implemented.

[0018] One or more of the above technical solutions have the following beneficial effects:

[0019] 1. The present invention provides a tunnel surface-surrounding multi-source information joint constraint attribute modeling method and system. By using different exploration methods (such as drilling, seismic waves, geological radar, etc.) to obtain data on the complex geology of the tunnel and its surroundings, the method combines the information on cracks, pores, water content, etc. revealed by the drilling data with spatial information provided by geological radar and acoustic wave exploration, integrates these different exploration data, and combines them with adaptive grid division technology to achieve refined modeling of the geological attributes of the tunnel area, thereby improving the accuracy and reliability of the tunnel geological model and enhancing the tunnel safety assessment and construction risk prediction capabilities.

[0020] 2. Building on the aforementioned multi-source data-driven modeling, this invention also proposes a model update mechanism. With the continuous addition and update of borehole data, the tunnel geological model can be dynamically and iteratively optimized, achieving a more accurate prediction of the geological characteristics of the tunnel area. Compared to traditional methods, this modeling approach offers higher accuracy and greater adaptability, effectively addressing the need for tunnel safety and stability assessments under complex geological conditions, and possesses significant engineering application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0022] Figure 1 This is a flow chart of the attribute modeling method for joint constraints of tunnel surface and hole perimeter multi-source information according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] It should be noted that the following detailed descriptions are exemplary only and are intended to describe specific embodiments and provide further explanation of the present invention, and are not intended to limit the exemplary embodiments according to the present invention. Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as those commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0024] Example 1

[0025] This embodiment provides a tunnel surface-hole multi-source information joint constraint attribute modeling method, such as Figure 1 As shown, the specific steps include:

[0026] Step S1: Acquire spatial information and geological attribute information of the tunnel geological body area, divide the area into several grids using an adaptive network partitioning method based on local features, and construct a grid model; wherein the geological attribute information includes the location and distribution of cracks, porosity, water seepage information, elastic modulus, etc.

[0027] Specifically, through geological radar, sonic exploration, drilling, and other means, spatial information such as the stratigraphic structure of the tunnel geological area (hereinafter referred to as the tunnel area) is obtained, as well as geological attribute information such as the location and distribution of cracks, porosity, water seepage information, and elastic modulus. Among them, water seepage information generally includes the characteristics of water bodies near cracks, such as aquifer permeability and water seepage rate. On this basis, in order to efficiently describe the complex geological structure of the tunnel and its surroundings, this embodiment adopts an adaptive grid division method to divide the tunnel area into several grids, thereby constructing a grid model, including:

[0028] First, a rough initial grid is randomly defined;

[0029] Secondly, the grid is refined based on the information on crack distribution, porosity changes, and aquifer distribution obtained through drilling, radar, and acoustic waves. The grid division is dynamically adjusted according to the complexity of the geological area surrounding the tunnel. For example, near the tunnel surface and in areas with concentrated cracks, using a finer grid can ensure accurate capture of changes in these key areas. Therefore, by analyzing the characteristics of the crack distribution and porosity in the area around the tunnel, an adaptive grid division method based on local features is used to refine the grid. This method can be expressed as:

[0030]

[0031] Where Δx is the size of the grid, L is the length of the tunnel region, and N is the number of nodes in the grid.

[0032] Based on the above division method, for complex areas (such as areas with concentrated cracks), Δx takes a smaller value and N takes a larger value to ensure that details can be better captured; while in relatively simple areas, Δx is appropriately increased and N takes a smaller value.

[0033] Furthermore, based on local geological attribute information, the degree of mesh refinement can be dynamically adjusted. By adopting a finer mesh in areas with dense fractures or drastically varying porosity, these important physical properties can be fully reflected. In other words, different adaptive meshing algorithms are used based on the geological characteristics of the target area. The control criterion for mesh refinement can be expressed as:

[0034]

[0035] Here, G(x,y,z) represents the fineness of the mesh at the point (x,y,z), and f(x,y,z) is the value of the attribute function at that point (such as fracture density, porosity, aquifer permeability, etc.). In this way, the mesh will be refined in areas with dense fractures or aquifers to obtain more accurate modeling results.

[0036] Preferably, local error estimation is used to optimize mesh division, increasing the mesh density where regional characteristics vary greatly, and reducing the number of meshes where regional characteristics vary less. Specifically, the following adaptive mesh refinement criterion can be used for local error control:

[0037]

[0038] Among them, E local (x,y,z) represents the error estimate of the local area, Indicates the optimization, reduction or minimization of the current quantity or target. is the gradient of the point, Ω is the spatial region where G continues to generate, and G is a control parameter related to grid division, which represents the fineness or density of the grid and is used to guide the generation and adaptive division of the grid.

[0039] Step S2: For each grid area, the acquired geological attribute data is preprocessed, and geological attributes are preliminarily assigned to the grid model based on the preprocessed data. The spatial distribution of fractures, porosity, water-bearing bodies, and elasticity models are modeled in the model to construct an initial attribute model.

[0040] Step S2.1, data preprocessing. Considering that the different attribute data obtained from the borehole (such as cracks, water seepage information, porosity, etc.) may have different dimensions and spatial distributions, it is necessary to ensure that all data are compared under the same standard. In this embodiment, the obtained attribute data are first standardized, including: standardizing the data such as crack direction, crack dip, and permeability to have the same dimensions to avoid data inconsistency caused by different dimensions. The standardization formula is:

[0041]

[0042] Among them, X is the original data, μ is the mean, σ is the standard deviation, X std Represents the normalized data.

[0043] In addition, all the data obtained from the drilling are mapped into a unified three-dimensional spatial coordinate system, and the spatial unification ensures that different data can be directly compared and interpolated.

[0044] Step S2.2: Based on preliminary exploration data (e.g., fracture information and porosity data revealed by drilling), assign preliminary physical properties to the grid model. These properties include fracture distribution, porosity, water content, permeability, elastic modulus, etc. By assigning properties, model the fractures and their spatial distribution, porosity, water content, and elasticity model, including:

[0045] Step S2.2.1. Considering that the fracture information revealed by the borehole often includes the geometric shape of the fracture (such as strike, dip, size, etc.) and its distribution underground, in this embodiment, an interpolation method is used to assign fracture attributes to the grid model, model the fractures and their spatial distribution, and fit the geometric model of the fractures to identify coplanar fractures.

[0046] Specifically, assuming that the crack information is f(x), the interpolation function of the crack can be expressed using the interpolation formula:

[0047]

[0048] Among them, α iis the calculation coefficient, which is the initial setting value; φ(||·||) is the radial basis function; ||xx i || is the position x to the crack node x i The distance between the crack nodes is 0 and 1; N represents the total number of crack nodes.

[0049] Through the above methods, the cracks and their spatial distribution are modeled, and then the cracks are fitted. The crack geometry is analyzed through principal component analysis (PCA) or least squares fitting to identify the main directions of the cracks. Based on this information, the crack plane in three-dimensional space is generated.

[0050] For each crack data point P i =(x i ,y i ,z i ), a crack plane model is obtained by fitting, which can be expressed as:

[0051] ax+by+cz+d=0;

[0052] where a, b, and c are the normal vectors to the fracture plane, and d is the plane intercept. Fracture geometry can help understand the spatial distribution of fractures and their impact on the surrounding medium (e.g., aquifers).

[0053] Furthermore, multiple cracks often exhibit coplanarity. The angle between the normal vectors of each crack plane can be calculated to determine whether two cracks belong to the same crack plane. The calculation formula is:

[0054]

[0055] If the angle cosθ between the normal vectors is less than a certain set threshold, the two cracks can be considered to be coplanar cracks. In this embodiment, when cosθ is close to 1, it means that the normal vectors of the two cracks are almost parallel, indicating that the two cracks are coplanar.

[0056] By analyzing whether the cracks are coplanar, the extension of the cracks can be determined. When they are judged to be coplanar, the points through which the crack surfaces pass can be recorded as having cracks, which can be used to further analyze the crack situation.

[0057] Step S2.2.2: Use the interpolation method to assign porosity attributes to the grid model and model the porosity.

[0058] Specifically, porosity is an important physical quantity that describes the size and distribution of voids within a geological body. It has a significant impact on permeability, elastic modulus, etc. The correlation assessment between porosity and information such as fractures and aquifers is a key step in fusing different data sources. Furthermore, when modeling porosity, the distribution of porosity can be obtained by spatial interpolation of porosity data. Commonly used interpolation methods include Kriging interpolation and inverse distance weighted method. In this embodiment, when obtaining the borehole position (x i ,y i ,z i ) on the porosity data φ i Based on this, the interpolation method is used to generate the porosity distribution of the entire grid area space, which can be expressed as:

[0059]

[0060] Among them, φ i is the porosity data of each drilling point i, w i is the corresponding weight coefficient.

[0061] The porosity distribution obtained by the above interpolation can reflect the porosity differences between different geological bodies.

[0062] Step S2.2.3: Based on the seepage information, the interpolation method is used to assign water-bearing attributes to the grid model to obtain the distribution of groundwater information. Then, the fitted variation function is used in combination with spatial correlation to model the water body.

[0063] Specifically, water seepage information usually includes the characteristics of the water body near the crack, such as permeability, water seepage rate, etc., which is crucial for groundwater flow and water flow control during tunnel construction. For the water seepage information revealed by drilling, the distribution of the aquifer (i.e., water body) can be fitted in three-dimensional space to complete the modeling of the water body. In this embodiment, according to the obtained water seepage information k i , the spatial distribution of the water-bearing attribute, that is, the distribution of groundwater information k(x,y,z), is obtained by interpolation method, which can be expressed as:

[0064]

[0065] Among them, w i is the weight of each drilling point i, k i It is the water content data or seepage data corresponding to the drilling point, which can help identify the path of groundwater flow, etc.

[0066] Furthermore, the groundwater distribution k(x, y, z) revealed by the borehole is used to fit the water body, and the water-producing areas revealed by the borehole are marked to model the water body.

[0067] Specifically, based on the water-bearing body model constructed above, a fitting variogram is used to fit the water-bearing body. Based on spatial correlation modeling, the following formula is used to fit the spatial variogram:

[0068]

[0069] Where γ(h) is the variogram, which represents the spatial difference that changes with distance h; z(x) represents the attribute value at a certain spatial location x of the water body; h represents the distance between two spatial locations, which affects the calculation of the spatial variogram; Var is the variance.

[0070] Through the above fitting variation function, the interpolation results of water body information at different locations can be obtained.

[0071] Step S2.2.4: Use the interpolation method to assign elastic properties to the grid model and build an elastic model.

[0072] Specifically, finite element analysis (FEM) is used to interpolate the obtained formation elastic modulus, where the elastic modulus F(x, y, z) can be obtained by solving the following finite element formula:

[0073] [K]{u}={F};

[0074] In the above formula, [K] is the stiffness matrix, {u} is the node displacement vector, and {F} is the external force vector.

[0075] The elastic modulus distribution in different areas can be obtained by interpolating the elastic properties of the strata around the tunnel using the finite element method.

[0076] Preferably, correlation analysis is performed on the multi-attribute data, and the above modeling results are corrected based on the correlation analysis results, including:

[0077] (1) The relationship between aquifers and fractures is usually expressed as a coupling between fracture density and permeability. The relationship between fracture permeability and the permeability of the surrounding aquifers can be estimated using the following formula:

[0078] k 裂隙 =f(k 含水 ,ρ 裂隙 );

[0079] Among them, k 裂隙 is the permeability of the fracture, k 含水 is the permeability of the water-containing body, ρ 裂隙 is the density of the fractures, and f() is a nonlinear function. The permeability of fractures is affected by geometric characteristics such as fracture orientation and inclination. Therefore, it is necessary to comprehensively consider the coupling relationship between fracture geometry and the properties of the seepage body.

[0080] (2) Considering the correlation between porosity, permeability and fracture information, porosity directly affects permeability. Therefore, the relationship between porosity and permeability needs to be considered when fusion modeling. The relationship between porosity and permeability can be described by the following empirical formula:

[0081] k=k0·φ m ;

[0082] Where k is the permeability, k0 is the benchmark permeability, φ is the porosity, and m is the empirical exponent.

[0083] As porosity increases, permeability also increases. During the model fusion process, changes in porosity can directly affect the prediction of permeability, so the relationship between porosity and permeability needs to be calibrated.

[0084] Based on the above analysis results, the initial attribute model is corrected using the above relationship formula to ensure the accuracy of the relationship between the attributes and the accuracy of the final modeling.

[0085] Through the above step-by-step analysis of the distribution and correlation of various geological attributes, the final analysis results are combined and integrated into the grid model to build the initial attribute model.

[0086] Step S3: Calculate the correlation between the new and old drilling data based on the latest drilling data, and fit the drilling data based on the correlation. After fitting, integrate the latest drilling data into the initial attribute model to obtain an updated tunnel geological attribute model.

[0087] Step S3.1: Analyze and match the correlation between new and old drill hole data. Data revealed by new drill holes typically have a certain spatial relationship with previous drill hole data. However, how to reasonably evaluate the correlation between new and old data is a complex task. Based on the physical consistency of the data, this embodiment proposes the following standardized evaluation method:

[0088] (1) For the new borehole data, the spatial distance between it and all historical boreholes is calculated, and different weights are assigned according to the spatial distance; among them, the boreholes with closer distances are given a larger weight, and vice versa.

[0089] (2) Based on the above weights, the correlation between the new and old drill hole data can be evaluated using the following weighted formula:

[0090]

[0091] Among them, C new,old Indicates the correlation between new drilling data and historical drilling data, w i is the weight calculated based on the spatial distance, Cor(X new ,Xold,i ) is the correlation between the new drilling data and the i-th historical drilling data. In this embodiment, the correlation is calculated using a measurement method such as the Pearson correlation coefficient.

[0092] Step S3.2: spatial matching of crack information, and updating the initial attribute model according to the matching results.

[0093] For a newly discovered fracture, its relevance can be assessed by comparing its geometric morphology with that of existing fractures. In terms of fracture geometry, if the newly discovered fracture is similar in geometry to the fractures in the historical data and the angle between their normal vectors is less than a certain threshold, then these fractures can be considered to belong to the same fracture plane. For example, the angle θ of the fracture normal vector is evaluated as follows:

[0094]

[0095] When cosθ>0.95, the two cracks can be considered as coplanar cracks; otherwise, the cracks are considered as non-coplanar cracks.

[0096] Step S3.3: Based on the correlation between the new and old borehole data, the porosity, water content, and elastic modulus are fitted and updated to update the initial attribute model and obtain an updated tunnel geological attribute model.

[0097] Considering the correlation between new and old borehole data, the following method can be used to jointly fit the data to ensure that the newly revealed information can be effectively integrated into the initial attribute model and have a reasonable impact on the geological model. That is, the new and old borehole data are fitted using a nonlinear least squares method (such as the Levenberg-Marquardt algorithm) to extract physical properties such as fracture geometry, water seepage information (i.e., permeability), and porosity. Taking the fracture permeability model as an example:

[0098]

[0099] Among them, k 裂隙 is the permeability of the crack, L is the length of the crack, L0 is the reference length, and n is the fitting index, which is calculated based on the above correlation coefficient.

[0100] In addition, the water-bearing information revealed by new boreholes can be fitted using methods such as polynomial regression or support vector machine (SVM) to determine the spatial distribution of the aquifer. The aquifer information of new and old borehole data can be evaluated by spatial interpolation combined with relative humidity, porosity, water-bearing body and other characteristics.

[0101] As another implementation, consistency verification is required to ensure the physical consistency of the new and old data after merging. This physical consistency constraint can be implemented in the following ways:

[0102] (1) Consistency between permeability and porosity: According to the empirical formula k = k0·φ m , check whether the relationship between porosity and permeability is consistent;

[0103] (2) Consistency between fractures and seepage paths: Assess the compatibility between fracture geometry and seepage paths to ensure that the flow paths and fracture distribution are spatially matched;

[0104] (3) Comprehensive constraints: Combining information such as porosity, cracks, and water seepage, the fusion and consistency test of multi-source information are achieved through methods such as weighted average method and constrained optimization algorithm.

[0105] As another implementation method, a dynamic weighting mechanism is applied in the above process. Specifically, the geological characteristics of different regions vary greatly, and the geological conditions in different construction stages will also change. Therefore, it is necessary to dynamically adjust the weights of each attribute based on real-time data in order to more accurately evaluate the grouting needs. In this embodiment, spatial adaptive weighting is used to adjust the weights of different attributes, that is: based on drilling data and real-time monitoring data (such as pressure, flow, temperature, etc.), the weight of each area is dynamically adjusted. For example, in areas with dense fracture zones, the weight of fracture density can be appropriately increased, and in areas with more serious water seepage, the weight of water seepage intensity can be increased.

[0106] Example 2

[0107] This embodiment provides an attribute modeling system for tunnel surface and tunnel perimeter multi-source information joint constraints, including:

[0108] The gridding module is used to obtain spatial information and geological attribute information of the tunnel geological area. It uses an adaptive network partitioning method based on local characteristics to divide the area into several grids and construct a grid model. The geological attribute information includes the location and distribution of cracks, porosity, water seepage information, and elastic modulus.

[0109] The initial attribute model building module is used to preprocess the acquired geological attribute data for each grid area, and preliminarily assign geological attributes to the grid model based on the preprocessed data. The spatial distribution of fractures, porosity, water-bearing bodies, and elasticity models are modeled in the model to construct the initial attribute model.

[0110] The tunnel geological body attribute modeling module is used to calculate the correlation between the new and old drilling data based on the latest drilling data, and fit the drilling data based on the correlation. After fitting, the latest drilling data is integrated into the initial attribute model to obtain an updated tunnel geological attribute model.

[0111] Example 3

[0112] This embodiment provides an electronic device, including: a memory for storing executable instructions; and a processor for implementing the above method provided in this embodiment when executing the executable instructions stored in the memory.

[0113] Example 4

[0114] This embodiment further provides a computer-readable storage medium storing executable instructions. When the executable instructions are executed by a processor, the processor will be caused to execute the above method provided in this embodiment.

[0115] Example 5

[0116] This embodiment provides a computer program product including executable instructions, which are computer instructions stored in a computer-readable storage medium. When a processor of an electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the electronic device performs the method provided in this embodiment.

[0117] The steps involved in the above embodiments 2 to 5 correspond to those in embodiment 1. For detailed implementation, please refer to the relevant description of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media that includes one or more instruction sets; it should also be understood to include any medium that can store, encode, or carry an instruction set for execution by a processor and cause the processor to perform any method of the present invention.

[0118] Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computer device. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0119] The above description is only a preferred embodiment of the present invention. Although the specific implementation of the present invention is described in conjunction with the accompanying drawings, it does not limit the scope of protection of the present invention. Those skilled in the art should understand that on the basis of the technical solution of the present invention, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present invention.

Claims

1. A tunnel surface-hole perimeter multi-source information joint constraint attribute modeling method, characterized by: include: Obtain spatial information and geological attribute information of the tunnel geological area, divide the area into several grids using an adaptive network partitioning method based on local features, and construct a grid model. Geological attribute information includes fracture location and distribution, porosity, water seepage information, and elastic modulus. For each grid area, the acquired geological attribute data is preprocessed, and the grid model is initially assigned geological attributes based on the preprocessed data. The spatial distribution of fractures, porosity, water-bearing bodies, and elasticity models are modeled in the model to construct an initial attribute model. Based on the latest drilling data, the correlation between the new and old drilling data is calculated, and the drilling data is fitted based on the correlation. After fitting, the latest drilling data is integrated into the initial attribute model to obtain an updated tunnel geological attribute model; The attribute modeling method for tunnel surface and perimeter multi-source information joint constraint performs correlation analysis on multiple geological attribute data and corrects the modeling results based on the correlation analysis results, including: The relationship between the permeability of the fracture and the permeability of the surrounding water body, as well as the relationship between porosity and permeability, are clearly expressed as: k 裂隙 =f(k 含水 ,r 裂隙 ); k=k0·φ m ; Among them, k 裂隙 is the permeability of the fracture, k 含水 is the permeability of the water-containing body, ρ 裂隙 is the density of cracks, f() is a nonlinear function; k is permeability, k0 is the benchmark permeability, v is the porosity, and m is the empirical index; Based on the relationship formula obtained by analysis, the initial attribute model is corrected to obtain a corrected attribute model.

2. The attribute modeling method for tunnel surface-hole perimeter multi-source information joint constraint according to claim 1 is characterized in that: The adaptive network partitioning method based on local features is used to divide the area into several grids, including: Based on the length of the tunnel area and the number of grid nodes, the size of each grid is preliminarily determined; Adaptively adjust the size of the grid at the current location based on the geological attribute value of the current location; wherein the geological attribute value is inversely proportional to the grid size; The grid division is optimized according to the local error of the current regional characteristics; the degree of change of regional characteristics is proportional to the grid density.

3. The attribute modeling method for tunnel surface-hole perimeter multi-source information joint constraint according to claim 1, characterized in that: Interpolation is used to assign fracture properties to the grid model, model fractures and their spatial distribution, fit the fracture geometry model, and identify coplanar fractures, including: The interpolation method is used to assign preliminary fracture attributes, which can be expressed as: Among them, f(x) is the crack information, α i is the initial calculation coefficient, φ(||·||) is the radial basis function, ||xx i || is the position x to the crack node x i The distance between the crack nodes is 0. For each crack data point, the corresponding crack plane model is fitted, and the coplanarity of each crack is identified based on the crack plane model.

4. The attribute modeling method for tunnel surface-hole perimeter multi-source information joint constraint according to claim 1, characterized in that: The interpolation method is used to generate the porosity distribution of the entire grid area space, which is expressed as: Among them, φ i is the porosity data of each drilling point i, w i is the weight coefficient, and N represents the total number of drilling points.

5. The attribute modeling method of tunnel surface-hole perimeter multi-source information joint constraint according to claim 1, characterized in that: Based on the seepage information, the interpolation method is used to assign water-containing attributes to the grid model to obtain the distribution of groundwater information, which is expressed as: Among them, w i is the weight of each drilling point i, k i is the water content data corresponding to the drilling point; The fitted variogram is used to combine spatial correlation to model the water body, which is expressed as: Where γ(h) is the variogram, which represents the spatial difference that changes with distance h; z(x) represents the attribute value at a certain spatial location x of the water body; h represents the distance between two spatial locations, which affects the calculation of the spatial variogram; Var is the variance.

6. A tunnel surface-hole perimeter multi-source information joint constraint attribute modeling system, characterized by: include: The gridding module is used to obtain spatial information and geological attribute information of the tunnel geological area. It uses an adaptive network partitioning method based on local characteristics to divide the area into several grids and construct a grid model. The geological attribute information includes the location and distribution of cracks, porosity, water seepage information, and elastic modulus. The initial attribute model building module is used to preprocess the acquired geological attribute data for each grid area, and preliminarily assign geological attributes to the grid model based on the preprocessed data. The spatial distribution of fractures, porosity, water-bearing bodies, and elasticity models are modeled in the model to construct the initial attribute model. The tunnel geological body attribute modeling module is used to calculate the correlation between the new and old drilling data based on the latest drilling data, and fit the drilling data based on the correlation. After fitting, the latest drilling data is integrated into the initial attribute model to obtain an updated tunnel geological attribute model; The attribute modeling method for tunnel surface and perimeter multi-source information joint constraint performs correlation analysis on multiple geological attribute data and corrects the modeling results based on the correlation analysis results, including: The relationship between the permeability of the fracture and the permeability of the surrounding water body, as well as the relationship between porosity and permeability, are clearly expressed as: k 裂隙 =f(k 含水 ,r 裂隙 ); k=k0·φ m ; Among them, k 裂隙 is the permeability of the fracture, k 含水 is the permeability of the water-containing body, ρ 裂隙 is the density of cracks, f() is a nonlinear function; k is the permeability, k0 is the benchmark permeability, φ is the porosity, and m is the empirical index; Based on the relationship formula obtained by analysis, the initial attribute model is corrected to obtain a corrected attribute model.

7. An electronic device, characterized in that: include: a memory for storing executable instructions; The processor is configured to implement the attribute modeling method for joint constraints of tunnel surface-hole perimeter multi-source information as described in any one of claims 1 to 5 when executing the executable instructions stored in the memory.

8. A computer-readable storage medium, characterized in that Executable instructions are stored for causing a processor to execute the executable instructions to implement the attribute modeling method of tunnel surface-hole perimeter multi-source information joint constraint as described in any one of claims 1-5.

9. A computer program product, characterized in that The computer program product includes executable instructions stored in a computer-readable storage medium; When the processor of the electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the attribute modeling method of the tunnel surface-hole perimeter multi-source information joint constraint as described in any one of claims 1 to 5 is implemented.

Images