Rock mass structure modeling method, device and equipment based on drilling data and medium

Abstract

The invention discloses a rock mass structure modeling method, device and equipment based on drilling data and a medium, and relates to the technical field of geotechnical engineering, through effective utilization of the drilling data and a reconstruction algorithm considering geological variability characteristics, even under the condition that the data have inherent defects, the rock mass structure modeling efficiency is improved, and the rock mass structure modeling efficiency is improved. A model capable of more accurately reflecting the actual structure of the rock mass can be established on the basis of the data, high-precision fitting with the drilling data is achieved, meanwhile, high-precision retention and reasonable extrapolation of the variability characteristics of the regional rock mass structure are achieved, and the problem that a traditional method is insufficient in model precision in a drilling data sparse region is effectively solved; and high-precision modeling of the rock mass structure in a global range is realized. And moreover, when the rock mass structure model is constructed, the spatial variability of the drilling data is fully considered, the rock mass structure model conforming to the actual situation can be flexibly generated and fitted according to the characteristics of the drilling data no matter in an area with relatively simple geological conditions or under complex geological conditions, and the generalization ability is high.

Description

Technical Field

[0001] This application relates to the technical field of geotechnical engineering, and particularly to a method, device, equipment and medium for modeling rock mass structures based on borehole data. Background Technique

[0002] With the development of geotechnical engineering, the refined characterization and modeling of rock mass structures are crucial. In engineering practice, discrete data obtained from geological exploration (including borehole cores, geophysical profiles, and surface mapping information) need to be systematically integrated through spatial algorithms. However, existing spatial interpolation algorithms are insufficient in capturing the spatial variability characteristics of various structural planes within the rock mass, and it is difficult to accurately reproduce the spatial distribution law of the rock mass structure during the three-dimensional reconstruction process, resulting in inaccurate zoning of rock mass quality and regional assignment of mechanical parameters.

[0003] In related technologies, traditional rock mass structure modeling methods mainly rely on geological exploration data, and often use interpolation methods such as the inverse distance power method and Kriging method to construct block models. However, in some complex geological conditions, such as karst areas and fault-developed areas, the detection accuracy of geophysical exploration means such as ground-penetrating radar will be severely affected, resulting in incomplete and inaccurate data obtained. Moreover, existing rock mass structure modeling methods also have problems such as lack of data at the distal end of the model, large inference deviation, insufficient interpretability, and limited generalization ability, making it difficult to comprehensively and accurately reflect the true three-dimensional rock mass structure characteristics and geological correlation characteristics. Summary of the Invention

[0004] In view of this, this application provides a method, device, equipment and medium for modeling rock mass structures based on borehole data, mainly aiming to solve problems such as lack of data at the distal end of the model, large inference deviation, insufficient interpretability, and limited generalization ability.

[0005] According to the first aspect of this application, a method for modeling rock mass structures based on borehole data is provided. The method includes: Obtain the original borehole data, and model the original borehole data after uniform discretization processing to obtain an initial borehole attribute model; Calculate a plurality of distance-weighted variation coefficients for characterizing the spatial variability of the initial borehole attribute model, and generate a plurality of heterogeneous block model samples by using the bubble method based on the initial borehole attribute model and the plurality of distance-weighted variation coefficients; Taking the initial borehole attribute model as a constraint condition, solve the weight coefficient matrix of the plurality of heterogeneous block model samples by the least squares method, and perform weighted superposition fitting on the plurality of heterogeneous block model samples by using the weight coefficient matrix to generate a target rock mass structure attribute model.

[0006] According to the second aspect of this application, a device for modeling rock mass structures based on borehole data is provided. The device includes: An initial model construction module, configured to obtain original drilling data, model the original drilling data after uniform discretization processing, and obtain an initial drilling property model; A heterogeneous sample generation module, configured to calculate a plurality of distance weighted variation coefficients for characterizing the spatial variability of the initial drilling property model, and generate a plurality of heterogeneous block model samples by using the bubbling method based on the initial drilling property model and the plurality of distance weighted variation coefficients; A weight fitting and modeling module, configured to solve a weight coefficient matrix of the plurality of heterogeneous block model samples by using the least squares method with the initial drilling property model as a constraint condition, and perform weighted superposition fitting on the plurality of heterogeneous block model samples by using the weight coefficient matrix to generate a target rock mass structure property model.

[0007] According to a third aspect of the present application, there is provided a device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method according to any one of the first aspects described above are implemented.

[0008] According to a fourth aspect of the present application, there is provided a medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method according to any one of the first aspects described above are implemented.

[0009] By means of the above technical solutions, the technical solutions provided by the embodiments of the present application at least have the following advantages: A rock mass structure modeling method, device, equipment and medium based on borehole data provided by the present application. The present application obtains original borehole data, models the original borehole data after uniform discretization processing to obtain an initial borehole attribute model, then calculates a plurality of distance-weighted variation coefficients used to characterize the spatial variability of the initial borehole attribute model, generates a plurality of heterogeneity block model samples by the bubble method based on the initial borehole attribute model and the plurality of distance-weighted variation coefficients, and then, with the initial borehole attribute model as a constraint condition, solves the weight coefficient matrix of the plurality of heterogeneity block model samples by the least squares method, and performs weighted superposition fitting on the plurality of heterogeneity block model samples by using the weight coefficient matrix to generate a target rock mass structure attribute model. Through the effective utilization of borehole data and a reconstruction algorithm considering geological variability characteristics, even in the case of inherent defects in the data, a model that more accurately reflects the actual structure of the rock mass can be established based on these data, achieving high-precision fitting with the borehole data while realizing high-precision retention and reasonable extrapolation of the regional rock mass structure variability characteristics, effectively solving the problem of insufficient model accuracy in the sparse borehole data area of traditional methods, and realizing high-precision modeling of the rock mass structure globally. Moreover, when constructing the rock mass structure model, the spatial variability of the borehole data is fully considered, which can better adapt to the rock mass structure characteristics under different geological conditions. Whether in a region with relatively simple geological conditions or under complex geological conditions, a rock mass structure model that conforms to the actual situation can be flexibly generated and fitted according to the characteristics of the borehole data, and has strong generalization ability.

[0010] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the specific implementation manners of the present application. Brief Description of the Drawings

[0011] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 It shows a schematic flow chart of a method for rock mass structure modeling based on borehole data provided by an embodiment of the present application; Figure 2 Brief Description of the Drawings

[0011] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 It shows a schematic flow chart of a method for rock mass structure modeling based on borehole data provided by an embodiment of the present application; Figure 2 It shows another schematic flow chart of a method for rock mass structure modeling based on borehole data provided by an embodiment of the present application; Figure 3 It shows a schematic diagram of uniform discretization processing provided by an embodiment of the present application; Figure 4Shows a schematic diagram of an initial model of drilling attributes provided by an embodiment of the present application; Figure 5 Shows a schematic diagram of the spatial variability of drilling provided by an embodiment of the present application; Figure 6 Shows a schematic diagram of the zoning of RQD data of drill holes in a certain mine provided by an embodiment of the present application; Figure 7 Shows a schematic diagram of a target rock mass structure attribute model provided by an embodiment of the present application; Figure 8 Shows a schematic diagram of the superposition of multiple blocks provided by an embodiment of the present application; Figure 9 Shows a schematic diagram of the distance-weighted coefficient of variation of RQD of the new model provided by an embodiment of the present application; Figure 10 Shows a schematic diagram of the comparison of cross-validated drill hole RQD provided by an embodiment of the present application; Figure 11 Shows a schematic flow diagram of a method for refined modeling of rock mass structure based on drill hole data provided by an embodiment of the present application; Figure 12 Shows a schematic structural diagram of rock mass structure modeling based on drill hole data provided by an embodiment of the present application; Figure 13 Shows another schematic structural diagram of rock mass structure modeling based on drill hole data provided by an embodiment of the present application; Figure 14 Shows a schematic diagram of the device structure of a device provided by an embodiment of the present application. Detailed implementation manners

[0012] In the description of the present application, it should be understood that the orientation or positional relationship indicated by terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application.

[0013] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality" means two or more unless otherwise specifically defined.

[0014] Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0015] Traditional rock mass structure modeling methods mainly rely on geological exploration data and often use interpolation methods such as the inverse distance power method and the Kriging method to construct block models. However, there are obvious limitations in the geological exploration process. Drilling, as the main way to obtain rock mass information, plays a key role in the collection of rock mass information, but its limitations are also obvious. Traditional methods can only obtain rock mass information within a local range and insufficiently consider the spatial variability characteristics of the deep rock mass structure and the potential geological correlation between borehole attributes. In addition, in some complex geological conditions, such as karst areas and fault-developed areas, the detection accuracy of geophysical exploration means such as ground penetrating radar will be seriously affected, resulting in incomplete and inaccurate data. These factors make it difficult for the generated three-dimensional model to comprehensively and accurately reflect the rock mass structure characteristics and geological correlation characteristics, especially at the model boundary far from the sampling point, where the model accuracy is significantly reduced. Therefore, in practical applications, traditional modeling methods often fail to meet the expected accuracy requirements, greatly limiting their effectiveness and reliability in engineering practice.

[0016] With the rapid development of computer technology, especially the major breakthroughs in the field of artificial intelligence, rock mass modeling technology based on deep learning has emerged. Such technologies have shown significant advantages in processing complex geological data and improving modeling accuracy. However, they have disadvantages such as large data requirements, insufficient model interpretability, and limited model generalization ability, which limit their wide application in the geotechnical engineering field and are difficult to meet the actual needs of theoretical research and engineering practice.

[0017] To solve this problem, the present application proposes a rock mass structure modeling method based on borehole data. First, the borehole data is preprocessed and its spatial variability is characterized. Then, multiple heterogeneous block models are generated through an algorithm. On this basis, reconstruction fitting is performed. The fitting model result not only coincides with the borehole data but also fully conforms to the spatial variability at the corresponding position, enabling a globally optimal refined model of the rock mass structure and solving problems such as low accuracy, large data requirements, insufficient interpretability, and limited generalization ability of existing models. The execution entity of the present application can be a rock mass structure modeling system, which relies on the computing power of a server to provide services for users. The server can be an independent server or a server providing basic cloud computing such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms.

[0018] An embodiment of the present application provides a rock mass structure modeling method based on borehole data, as Figure 1 shown, the method includes: 101. Obtain the original borehole data, perform modeling on the uniformly discretized original borehole data to obtain an initial model of borehole attributes.

[0019] In the embodiment of the present application, the original borehole data carries the true physical and mechanical properties of the rock mass and is a direct reflection of the characteristics of the rock mass at the engineering site. Through uniform discretization processing and modeling, the actual rock mass properties at the borehole position can be accurately transformed into a model-based expression, providing a true and reliable basic data source for subsequent rock mass structure modeling, ensuring that the model construction is based on objective engineering facts from the data input layer, avoiding information distortion caused by data abstraction, and maintaining the physical consistency between the model and the actual rock mass.

[0020] 102. Calculate multiple distance-weighted variation coefficients used to characterize the spatial variability of the initial model of borehole attributes. Based on the initial model of borehole attributes and the multiple distance-weighted variation coefficients, use the bubble method to generate multiple heterogeneous block model samples.

[0021] In the embodiments of the present application, the distance-weighted coefficient of variation is an index used to measure the spatial variability of the initial model of borehole attributes. Its core logic is to quantify the degree of variation of borehole attributes on the basis of considering spatial distance. By assigning different weights to the attributes of adjacent boreholes at different distances, a coefficient that can reflect the variation of attribute values with distance in space is calculated, so as to characterize the variability characteristics such as inhomogeneity and discreteness of rock mass attributes in spatial distribution. The introduction of spatial distance weights in the distance-weighted coefficient of variation makes it more in line with the actual situation of the spatial distribution of rock mass attributes compared with the ordinary coefficient of variation. It can accurately capture the variation law of rock mass attributes at different spatial positions, making the subsequent generated block model samples more truly reflect the actual heterogeneity of the rock mass and improving the reduction degree of the model to the complex spatial characteristics of the rock mass.

[0022] The bubbling method is a modeling method for simulating the inhomogeneous distribution of rock mass. Based on the initial model of borehole attributes and multiple distance-weighted coefficients of variation calculated above, the bubbling method can be understood as randomly generating blocks that conform to the spatial attribute change characteristics according to the variability law by simulating a random distribution process similar to "bubbling", and constructing multiple block model samples with different inhomogeneous distributions. These samples can reflect the possible diverse inhomogeneous distributions of rock mass attributes in space.

[0023] 103. Taking the initial model of borehole attributes as a constraint condition, solve the weight coefficient matrix of multiple inhomogeneous block model samples by the least squares method, and use the weight coefficient matrix to perform weighted superposition fitting on multiple inhomogeneous block model samples to generate the target rock mass structure attribute model.

[0024] In the embodiments of the present application, the core logic of the least squares method is to minimize the sum of the squared residuals between the model prediction value and the actual borehole data, which can make the weighted superposed target model fit the rock mass attributes reflected by the real boreholes to the greatest extent, ensure the high-precision fitting of the model to the actual engineering data, and improve the consistency between the model and the in-situ rock mass. The rock mass structure has high inhomogeneity, and multiple inhomogeneous block model samples can reflect the possible distribution of rock mass attributes from different angles. Through the solution and weighted superposition of the weight coefficient matrix, the advantages of multiple samples, such as the accurate characterization of different regions and different variability characteristics of the rock mass by different samples, can be scientifically integrated, and the one-sidedness of a single model can be discarded, so as to construct a target model that integrates multi-dimensional information and more comprehensively reflects the rock mass structure attributes.

[0025] The embodiment of the present application provides a method for modeling the rock mass structure based on borehole data. Compared with the prior art, the embodiment of the present application obtains the original borehole data, models the original borehole data after uniform discretization processing to obtain an initial borehole attribute model, then calculates a plurality of distance-weighted variation coefficients used to characterize the spatial variability of the initial borehole attribute model, generates a plurality of heterogeneity block model samples by the bubbling method based on the initial borehole attribute model and the plurality of distance-weighted variation coefficients, and then takes the initial borehole attribute model as a constraint condition, solves the weight coefficient matrix of the plurality of heterogeneity block model samples by the least squares method, and performs weighted superposition fitting on the plurality of heterogeneity block model samples by using the weight coefficient matrix to generate a target rock mass structure attribute model. Through the effective utilization of borehole data and the reconstruction algorithm considering the characteristics of geological variability, even in the case of inherent defects in the data, a model that more accurately reflects the actual structure of the rock mass can be established based on these data, achieving high-precision fitting with the borehole data while realizing high-precision retention and reasonable extrapolation of the variability characteristics of the regional rock mass structure, effectively solving the problem of insufficient model accuracy in the sparse area of borehole data, and realizing high-precision modeling of the rock mass structure globally. Moreover, when constructing the rock mass structure model, fully considering the spatial variability of the borehole data can better adapt to the rock mass structure characteristics under different geological conditions. Whether in a region with relatively simple geological conditions or in complex geological conditions, a rock mass structure model that conforms to the actual situation can be flexibly generated and fitted according to the characteristics of the borehole data, with strong generalization ability.

[0026] Further, as a refinement and extension of the specific implementation manner of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, the embodiment of the present application provides another method for modeling the rock mass structure based on borehole data, as Figure 2 shown, this method includes: 201. Obtain the original borehole data, and perform uniform discretization processing on the original borehole data to obtain a plurality of discretized blocks.

[0027] In the embodiment of the present application, the original borehole data is preprocessed to remove the data with data missing and data anomalies in the original borehole data to obtain the target borehole data. Taking Borehole 1 as an example, the original borehole data is as shown in Table 1 and Table 2 below: Table 1

[0028] Table 2

[0029] Next, the target drilling data is converted into multiple three-dimensional drilling coordinates and the corresponding attribute values for each three-dimensional drilling coordinate. Uniform discretization processing is performed on the multiple three-dimensional drilling coordinates and the corresponding attribute values. For example, the data after uniform discretization processing of Borehole 1 is shown in Table 3 below. Finally, multiple discretized blocks of the same size as shown in Figure 3 are obtained. The left cube in the figure represents the original rock mass space and the distribution of drilling data, which is an abstract representation of the three-dimensional space at the engineering site. The discrete points inside it correspond to the three-dimensional space data samples collected from the actual drilling. The coordinates of each point reflect the physical position of the sample in the rock mass space, and the attributes of the points imply the rock mass characteristics at the corresponding positions. In the scenario of rock mass structure modeling, these discrete points are the original data for subsequent analysis. However, due to their large quantity and scattered distribution, when directly used for complex model construction, the high data dimension and large redundancy will increase the calculation cost and difficulty. The right cube in the figure is the result presentation after uniform discretization processing of the left original data, reflecting the process of data simplification and structuring. After discretization processing, the original scattered drilling data is integrated into regularly arranged discretized blocks according to a unified spatial interval. Each block can be regarded as a basic analysis unit, and its attribute value is obtained by statistically analyzing the original discrete point data, representing the comprehensive characteristics of the rock mass attributes within the spatial block. The role of the right cube is to convert the complex and disordered original data into structured data that meets the requirements of the modeling algorithm, facilitating subsequent operations such as rock mass spatial variability analysis, block model construction, and weighted fitting, significantly reducing the modeling calculation complexity while retaining the spatial distribution trend of the rock mass attributes. The formula meanvalue in the figure is the calculation method for the attribute value of the discretized block. By taking the arithmetic mean of the n original discrete point data within the discretized block, a characteristic value representing the rock mass attributes of the discretized block is obtained, which can effectively integrate the information of multiple original data within the block and reflect the rock mass attribute level of the local space with a concise characteristic value, making the discretized block data both simplified and retaining the statistical characteristics of the original data.

[0030] Table 3

[0031] The first column of data in Table 3 represents the X coordinate, the second column represents the Y coordinate, and the third column represents the Z coordinate. The three columns of data together form the three-dimensional drilling coordinates, and the RQD value is the attribute value corresponding to the three-dimensional drilling coordinates.

[0032] 202. Use multiple discretized blocks for modeling to obtain an initial model of drilling attributes.

[0033] In the embodiments of the present application, for each discretized block, multiple three-dimensional drilling coordinates included in the discretized block are determined, the centroid coordinates of the discretized block are calculated and determined using the multiple three-dimensional drilling coordinates included in the discretized block, the attribute values corresponding to the multiple three-dimensional drilling coordinates included in the discretized block are determined, and the mean value of the attribute values corresponding to the multiple three-dimensional drilling coordinates included in the discretized block is used as the attribute value of the discretized block. Based on this process, each discretized block is processed separately to obtain the centroid coordinates and attribute values of each discretized block. Then, the centroid coordinates and attribute values of multiple discretized blocks are used for modeling to obtain the initial drilling attribute model as shown in Figure 4 . By refining the complex data of each discretized block into two sets of key features, namely centroid coordinates and mean attributes, the data dimension is greatly simplified. It can not only retain the spatial position and attribute characteristics of the block but also reduce the computational amount of subsequent modeling.

[0034] 203. Calculate multiple distance-weighted variation coefficients used to characterize the spatial variability of the initial drilling attribute model.

[0035] In the embodiments of the present application, the characterization of spatial variability is an important part of this method. First, a spherical domain centered on the discretized block with a radius of r, i.e., a three-dimensional spatial neighborhood, is selected, and the set of discretized blocks participating in the calculation within the neighborhood is determined. Then, the multiple discretized blocks included in the initial drilling attribute model are determined, and the distance-weighted variation coefficient of each discretized block is calculated. The calculation formula is Formula 1 below: Formula 1:

[0036]

[0037]

[0038]

[0039] Where, represents the distance-weighted variation coefficient of the th discretized block, represents the weighted standard deviation of the th discretized block, which is used to measure the dispersion degree of the attribute values within the neighborhood relative to the weighted mean value and reflects the fluctuation amplitude of the spatial variability. represents the weighted average value of the th discretized block. The attribute values of the discretized blocks within the neighborhood are weighted and averaged using the distance weight , which can highlight the attribute influence of the blocks near the center and better conform to the spatial characteristics of the rock mass attribute being related in the short range and weakened in the long range. n represents the total number of discretized blocks in the spherical domain with a radius of r, represents the weight of the i-th discretized block within the spherical domain, represents the attribute value of the i-th discretized block within the spherical domain, represents the distance from the i-th discretized block within the spherical domain to the -th discretized block, where the -th discretized block is the center point of the spherical domain. Finally, the distance-weighted coefficient of variation of multiple discretized blocks is used to characterize the spatial variability of the initial model of borehole attributes.

[0040] In an alternative embodiment, a borehole spatial variability map as shown in Figure 5 can be drawn based on the calculated distance-weighted coefficient of variation. This map can intuitively reflect the variability of RQD attribute values in different directions and distances in each region, and this variability information can provide a reference for the geological correlation between boreholes in subsequent model generation. Among them, the regions are divided according to the attributes and spatial positions of boreholes using the K-Means clustering algorithm, such as the Figure 6 borehole RQD data partition map of a certain mine shown in the figure. The entire rock mass region is divided into 10 different regions based on the spatial position and rock mass attribute relationship of the borehole rock mass structure attribute values.

[0041] 204. Based on the initial model of borehole attributes and multiple distance-weighted coefficients of variation, multiple heterogeneous block model samples are generated using the bubbling method.

[0042] In the embodiment of the present application, target borehole data is obtained, and the initial model of borehole attributes is partitioned according to the target borehole data using a clustering algorithm to obtain multiple partitions of the initial model of borehole attributes. Among them, the clustering algorithm can be the K-Means clustering algorithm. Different regions are divided according to the spatial position relationship and attribute size distribution of the model, so that different regions will be assigned different weights in the subsequent linear superposition process, which can improve the accuracy of the final model superposition. Then, the attribute value of each discretized block in the initial model of borehole attributes and the spatial size of the initial model of borehole attributes are obtained. Then, the bubbling method is used to calculate multiple partitions of the initial model of borehole attributes, the attribute value of each discretized block in the initial model of borehole attributes, the spatial size of the initial model of borehole attributes, and multiple distance-weighted coefficients of variation to generate multiple heterogeneous block model samples. Among them, the number of partitions of each heterogeneous block model sample is the same as the number of partitions of the initial model of borehole attributes. In this process, the bubbling generation needs to refer to the spatial size, number of partitions, attribute value, and coefficient of variation of the borehole model to ensure that the samples not only conform to the random simulation of non-uniformity but also fit the spatial characteristics of the actual rock mass, so that each sample retains the number of partitions and spatial framework of the initial model and can simulate the complex non-uniform distribution of the rock mass.

[0043] The bubbling method is a method based on stochastic simulation for generating block model samples with non-uniformity. Its basic idea is to randomly generate a series of "bubbles" in three-dimensional space and superimpose them on each other. By adjusting the size, quantity, and property distribution of the bubbles, the non-uniform characteristics of the rock mass are simulated. This method generates multiple block model samples with non-uniformity inside according to the spatial size of the borehole model, the RQD property values of the regional boreholes, and the spatial variability data. Each block model sample should have the same zoning as the original borehole model. The specific bubbling method parameters can be as shown in Table 4 below: Table 4

[0044] By adjusting the dispersion of the bubble radius, controlling the number of bubbles, the non-uniformity of the rock mass in different engineering scenarios can be simulated specifically. The size matches the actual engineering space range to ensure the engineering relevance of the model. Adjusting the discretization accuracy, controlling the number of samples, the model that best fits the actual borehole data can be selected, solving the problems of overly strong assumptions and poor adaptability of traditional single models.

[0045] 205. Taking the initial borehole attribute model as a constraint condition, the weight coefficient matrix of multiple non-uniform block model samples is solved by the least squares method.

[0046] In the embodiment of the present application, obtaining the multiple discretized blocks included in the initial borehole attribute model, and the multiple discretized blocks included in each non-uniform block model sample. Among them, the total number of the multiple discretized blocks included in the initial borehole attribute model is the same as the total number of the multiple discretized blocks included in each non-uniform block model sample. The multiple discretized blocks included in the initial borehole attribute model and the multiple discretized blocks included in each non-uniform block model sample are in one-to-one correspondence, that is, the spatial positions and zoning are consistent. Then, determine the multiple zoning included in the initial borehole attribute model, and the multiple zoning included in each non-uniform block model sample. Among them, the multiple zoning of the initial borehole attribute model and the multiple zoning of each non-uniform block model sample are in one-to-one correspondence. Then calculate the sum of squared residuals of each zoning.

[0047] Specifically, for each zoning, determine the multiple discretized blocks of the initial borehole attribute model in its zoning, and the multiple discretized blocks of each non-uniform block model sample in its zoning. Use the attribute values of the multiple discretized blocks of the initial borehole attribute model in its zoning, and the attribute values of the multiple discretized blocks of each non-uniform block model sample in its zoning to calculate the sum of squared residuals of its zoning. The calculation formula is Formula 2 below: Formula 2:

[0048]

[0049]

[0050] Among them, represents the residual sum of squares of its partition, which is used to measure the overall deviation between the sample and the initial model. m represents the number of multiple discretized blocks in its partition. represents the error between the k-th discretized block in the partition of the multiple heterogeneity block models and the k-th discretized block in the partition of the initial model of borehole attributes. represents the attribute value of the k-th discretized block in the partition of the initial model of borehole attributes. represents the predicted attribute value of the k-th discretized block in the partition of the multiple heterogeneity block models. represents the weight coefficient of the i-th heterogeneity block model sample in its partition. s represents the total number of multiple heterogeneity block models. represents the attribute value of the k-th discretized block in the partition of the i-th heterogeneity block model sample. Finally, the least squares method is used to solve the residual sum of squares of multiple partitions to obtain the weight coefficient matrix, making the target model fit the actual borehole data to the greatest extent and improving the model accuracy. Since the rock mass properties naturally have spatial variability, such as the different partition characteristics between the fault zone and the intact rock area, optimizing the weights independently for each partition can make the sample weights in each area more conform to their own geological laws.

[0051] 206. Use the weight coefficient matrix to perform weighted superposition fitting on multiple heterogeneity block model samples to generate a target rock mass structure attribute model.

[0052] In the embodiment of the present application, determine the attribute value matrix of each heterogeneity block model sample in each partition, and perform weight coefficient superposition fitting using the weight coefficient matrix and the attribute value matrix of each heterogeneity block model sample in each partition to generate a Figure 7 target rock mass structure attribute model as shown in Formula 3:

[0053] Among them, represents the target attribute value matrix of the j-th partition in the target rock mass structure attribute model. s represents the total number of multiple heterogeneity block models. represents the weight coefficient of the i-th heterogeneity block model sample in the j-th partition. It represents the attribute value matrix of the i-th heterogeneity block model sample in the j-th partition. The partition result is obtained through the spatial attribute characteristics of the rock mass, and then the weights are obtained through an optimization algorithm. The weights of different partitions are optimized independently. When superimposing, the partition characteristics are strictly retained, making the target model highly consistent with the geological variability of the actual rock mass in space and avoiding the loss of characteristics caused by global averaging.

[0054] In an optional embodiment, as Figure 8 shown, on the left side of the figure, n heterogeneity block model samples are shown, and each sample represents a possible distribution of the rock mass structure. Each sample corresponds to a weight coefficient , and the weight coefficient is solved through an optimization algorithm such as the least squares method, which reflects the contribution degree of the sample to the final model. The larger the weight, the stronger the influence of the sample on the final model. Then, the weighted sum of multiple block samples is calculated to integrate the advantages of multiple samples and generate a rock mass structure model. Then, virtual boreholes are used to extract the attribute data of the preliminary model and compare it with the original borehole data to check whether the model fits the rock mass characteristics of the actual borehole.

[0055] 207. Calculate the multiple correlation coefficient based on the target rock mass structure attribute model and the original rock mass structure attribute model. If it is detected and determined that the multiple correlation coefficient conforms to the multiple correlation coefficient determination rule, then store the target rock mass structure attribute model.

[0056] In the embodiment of the present application, the original rock mass structure attribute model is obtained, and the multiple correlation coefficient is calculated based on the target rock mass structure attribute model and the original rock mass structure attribute model. The calculation formula is the following formula 4: Formula 4:

[0057]

[0058]

[0059]

[0060] Where represents the multiple correlation coefficient, represents the sum of squared residuals, represents the regression sum of squares, represents the error between the p-th original block in the original rock mass structure attribute model and the p-th target block in the target rock mass structure attribute model, m represents the total number of multiple target blocks in the target rock mass structure attribute model, represents the attribute value of the p-th original block in the original rock mass structure attribute model, represents the attribute value of the p-th target block in the target rock mass structure attribute model, It represents the mean value of the attribute values of multiple original blocks in the original rock mass structure attribute model. Then, the multiple correlation coefficient detection rule is obtained. If it is detected and determined that the multiple correlation coefficient conforms to the multiple correlation coefficient determination rule, the target rock mass structure attribute model is stored. Among them, the range of the multiple correlation coefficient is between 0 and 1, and the closer the value is to 1, the better the correlation of the generated model.

[0061] In an alternative embodiment, multiple target distance weighted variation coefficients for characterizing the spatial variability of the target rock mass structure attribute model are calculated to generate a new model RQD distance weighted variation coefficient map as shown in Figure 9 It can be seen that the spatial variability is similar to the borehole spatial variability map as shown in Figure 5 This indicates that the generated rock mass structure model has achieved sufficient fitting accuracy and conforms to the spatial variability information of the borehole data.

[0062] In an alternative embodiment, the cross-validation method is used to test the target rock mass structure attribute model. The specific approach is to use some borehole data as validation data and the remaining data as modeling data. The target rock mass structure attribute model is constructed using the modeling data, and then the RQD attribute values of the validation data are predicted using this model. The predicted values are compared with the actual values to obtain a cross-validation borehole RQD comparison map as shown in Figure 10 The overall fluctuation trends of the RQD change curves of the original borehole and the generated borehole are similar. For example, the curve of the original borehole 1 has multiple peaks and valleys, and the curve of the generated borehole 1 also shows corresponding peak-valley changes; the fluctuation pattern of the curve of the original borehole 2 can also find a similar trend in the curve of the generated borehole 2, and the multiple correlation coefficient between the original borehole and the generated borehole reaches more than 0.6, which greatly improves the multiple correlation coefficient compared with other interpolation methods. This indicates that the model has captured the overall law of the change of the rock mass RQD with depth and reflects the heterogeneous distribution characteristics of the rock mass integrity in space. Moreover, the characteristic points in the curve, such as the obvious peak and valley positions, have a good correspondence between the original and the generated curves, and the multiple correlation coefficient has a better performance. Taking the original borehole 1 as an example, the sample point numbers at which the peaks and valleys appear in the original borehole 1 also have peak and valley fluctuations at similar numbered positions in the curve of the generated borehole 1, which means that the model can identify and simulate the key positions of the sudden change of the rock integrity in the rock mass.

[0063] In summary, the present application proposes a refined modeling method for rock mass structure based on borehole data, as shown in Figure 11As shown in the figure, first establish a drilling spatial distribution model. By collecting and integrating information such as the three-dimensional coordinates of on-site drill holes, outline the spatial position framework of rock mass drill holes; then perform uniform discretization processing on the drill hole model, split the continuous drill hole data at a unified spatial interval, and convert it into regular discrete blocks; then divide the engineering area according to the drill hole position and attribute values. Based on the association between rock mass attributes and spatial positions, use algorithms such as clustering to divide areas with similar geological characteristics; finally, characterize the spatial variability of engineering rock masses based on drill hole data, and use methods such as distance-weighted coefficient of variation to quantify the spatial fluctuation law of rock mass attributes in different partitions.

[0064] Based on the previous data and characteristics, first select the rock mass structure modeling parameters (such as the radius standard deviation and the number of blocks in the bubbling method), and clarify the modeling rules; then generate multiple block model samples with non-uniform attribute distributions, use the bubbling method to simulate the heterogeneity of the rock mass, and let the samples cover a variety of geological scenarios; then optimize the sample weights with the drill hole data as a constraint. Through the least squares method, make the weighted samples accurately fit the measured drill hole data after weighting, highlighting the contribution of key samples to the model; finally, superimpose and fit to generate a rock mass structure model, integrate the weighted samples, and construct a model that initially reflects the spatial distribution of rock mass attributes.

[0065] After the model construction is completed, carry out the fitting accuracy and spatial variability tests, compare the deviation between the model prediction value and the measured drill hole value, and evaluate whether the model fits the actual situation; if the test fails, trigger the feedback mechanism to correct the parameters, and adjust the modeling parameters in reverse (such as optimizing the sample weights and adjusting the discretization accuracy), and re-execute the process of parameter selection - sample generation - weighted fitting; if the test passes, confirm that the model is effective, establish a globally optimal refined rock mass structure model, and provide a high-precision basic basis for engineering analysis. This application uses the drill hole attribute values and spatial variability as constraint conditions, generates multiple rock mass structure model samples with non-uniform internal attributes using algorithms for reconstruction and fitting, obtains a rock mass structure model with high precision, can make up for the accuracy loss caused by data defects, and maximally excavate and utilize the effective information in the drill hole data. Based on the effective utilization of drill hole data and the spatial variability feature reconstruction algorithm, it achieves high-precision fitting with drill hole data in terms of accuracy, while completely retaining the variability features of the regional rock mass structure and realizing reasonable extrapolation; significantly reduces the dependence on densely sampled data in terms of data requirements; establishes a clear modeling process in terms of model interpretability; and can adapt to the modeling requirements under different geological conditions in terms of generalization ability. This application shows significant advantages in the rock mass structure modeling in the geotechnical engineering field, providing a more efficient and reliable technical approach that takes into account both high-precision modeling and maintaining geological relevance.

[0066] The embodiment of the present application provides a method for modeling rock mass structure based on borehole data. Compared with the prior art, in the embodiment of the present application, by obtaining the original borehole data, modeling the uniformly discretized original borehole data to obtain an initial borehole attribute model, then calculating a plurality of distance-weighted variation coefficients for characterizing the spatial variability of the initial borehole attribute model, generating a plurality of heterogeneous block model samples by using the bubbling method based on the initial borehole attribute model and the plurality of distance-weighted variation coefficients, and then taking the initial borehole attribute model as a constraint condition, solving the weight coefficient matrix of the plurality of heterogeneous block model samples by the least squares method, and performing weighted superposition fitting on the plurality of heterogeneous block model samples by using the weight coefficient matrix to generate a target rock mass structure attribute model. Through the effective utilization of borehole data and the reconstruction algorithm considering the characteristics of geological variability, even in the case of inherent defects in the data, a model that more accurately reflects the actual structure of the rock mass can be established based on these data, achieving high-precision fitting with the borehole data while realizing high-precision retention and reasonable extrapolation of the variability characteristics of the regional rock mass structure, effectively solving the problem of insufficient model accuracy in the sparse area of borehole data in the traditional method, and realizing high-precision modeling of the rock mass structure globally. Moreover, when constructing the rock mass structure model, fully considering the spatial variability of the borehole data can better adapt to the rock mass structure characteristics under different geological conditions. Whether in a region with relatively simple geological conditions or under complex geological conditions, it can flexibly generate and fit a rock mass structure model that conforms to the actual situation according to the characteristics of the borehole data, and has strong generalization ability.

[0067] Further, as Figure 1 a specific implementation of the method, the embodiment of the present application provides a device for modeling rock mass structure based on borehole data, as Figure 12 shown. The device includes: an initial model construction module 301, a heterogeneous sample generation module 302, and a weight fitting and modeling module 303.

[0068] The initial model construction module 301 is configured to obtain the original borehole data, model the uniformly discretized original borehole data to obtain an initial borehole attribute model; The heterogeneous sample generation module 302 is configured to calculate a plurality of distance-weighted variation coefficients for characterizing the spatial variability of the initial borehole attribute model, and generate a plurality of heterogeneous block model samples by using the bubbling method based on the initial borehole attribute model and the plurality of distance-weighted variation coefficients; The weight fitting and modeling module 303 is configured to take the initial borehole attribute model as a constraint condition, solve the weight coefficient matrix of the plurality of heterogeneous block model samples by the least squares method, and perform weighted superposition fitting on the plurality of heterogeneous block model samples by using the weight coefficient matrix to generate a target rock mass structure attribute model.

[0069] In a specific application scenario, the initial model construction module 301 is configured to preprocess the original drilling data, remove the data with missing data and data anomalies in the original drilling data, and obtain target drilling data; convert the target drilling data into a plurality of three-dimensional drilling coordinates and the attribute values corresponding to each of the three-dimensional drilling coordinates; perform uniform discretization processing on the plurality of three-dimensional drilling coordinates and the attribute values corresponding to the plurality of three-dimensional drilling coordinates to obtain a plurality of discretized blocks; for each of the discretized blocks, determine the plurality of three-dimensional drilling coordinates included in the discretized block, calculate and determine the centroid coordinates of the discretized block by using the plurality of three-dimensional drilling coordinates included in the discretized block, determine the attribute values corresponding to the plurality of three-dimensional drilling coordinates included in the discretized block, and use the average value of the attribute values corresponding to the plurality of three-dimensional drilling coordinates included in the discretized block as the attribute value of the discretized block; process each of the discretized blocks respectively to obtain the centroid coordinates and attribute values of each of the discretized blocks; perform modeling by using the centroid coordinates and attribute values of the plurality of discretized blocks to obtain the initial drilling attribute model.

[0070] In a specific application scenario, the heterogeneous sample generation module 302 is configured to determine the plurality of discretized blocks included in the initial drilling attribute model, and calculate the distance weighted variation coefficient of each of the discretized blocks.

[0071]

[0072]

[0073]

[0074] Wherein, represents the distance weighted variation coefficient of the th discretized block, represents the weighted standard deviation of the th discretized block, represents the weighted average value of the th discretized block, n represents the total number of discretized blocks in the spherical domain with a radius of r, represents the weight of the th discretized block in the spherical domain, represents the attribute value of the th discretized block in the spherical domain, represents the distance from the th discretized block to the th discretized block in the spherical domain, wherein the th discretized block is the center point of the spherical domain; the spatial variability of the initial drilling attribute model is characterized by using the distance weighted variation coefficients of the plurality of discretized blocks.

[0075] In a specific application scenario, the heterogeneous sample generation module 302 is configured to obtain target borehole data, partition the initial borehole attribute model according to the target borehole data by using a clustering algorithm to obtain multiple partitions of the initial borehole attribute model; obtain the attribute values of each discretized block in the initial borehole attribute model and the spatial dimensions of the initial borehole attribute model; calculate the multiple partitions of the initial borehole attribute model, the attribute values of each discretized block in the initial borehole attribute model, the spatial dimensions of the initial borehole attribute model, and the multiple distance weighted variation coefficients by using the bubbling method to generate multiple heterogeneous block model samples, and the number of partitions of each heterogeneous block model sample is the same as the number of partitions of the initial borehole attribute model.

[0076] In a specific application scenario, the weight fitting and modeling module 303 is configured to obtain multiple discretized blocks included in the initial borehole attribute model and multiple discretized blocks included in each heterogeneous block model sample, where the total number of multiple discretized blocks included in the initial borehole attribute model is the same as the total number of multiple discretized blocks included in each heterogeneous block model sample, and the multiple discretized blocks included in the initial borehole attribute model and the multiple discretized blocks included in each heterogeneous block model sample are in one-to-one correspondence; determine multiple partitions included in the initial borehole attribute model and multiple partitions included in each heterogeneous block model sample, where the multiple partitions of the initial borehole attribute model and the multiple partitions of each heterogeneous block model sample are in one-to-one correspondence; calculate the sum of squared residuals of each partition, solve the sum of squared residuals of the multiple partitions by using the least squares method to obtain the weight coefficient matrix; determine the attribute value matrix of each heterogeneous block model sample in each partition, and perform weight coefficient superposition fitting by using the weight coefficient matrix and the attribute value matrix of each heterogeneous block model sample in each partition to generate the target rock mass structure attribute model.

[0077] Among them, represents the target attribute value matrix of the jth partition in the target rock mass structure attribute model, s represents the total number of multiple heterogeneous block model samples, represents the weight coefficient of the ith heterogeneous block model sample in the jth partition, represents the attribute value matrix of the ith heterogeneous block model sample in the jth partition.

[0078] In a specific application scenario, the weight fitting and modeling module 303 is configured to, for each of the partitions, determine multiple discretized blocks of the initial borehole property model in the partition, and multiple discretized blocks of each of the heterogeneity block model samples in the partition; calculate the sum of squared residuals of the partition by using the property values of the multiple discretized blocks of the initial borehole property model in the partition and the property values of the multiple discretized blocks of each of the heterogeneity block model samples in the partition,

[0079]

[0080]

[0081] wherein, represents the sum of squared residuals of the partition, m represents the number of the multiple discretized blocks in the partition, represents the error between the k-th discretized block of the multiple heterogeneity block model samples in the partition and the k-th discretized block of the initial borehole property model in the partition, represents the property value of the k-th discretized block of the initial borehole property model in the partition, represents the predicted property value of the k-th discretized block of the multiple heterogeneity block model samples in the partition, represents the weight coefficient of the i-th heterogeneity block model sample in the partition, s represents the total number of the multiple heterogeneity block model samples, represents the property value of the k-th discretized block of the i-th heterogeneity block model sample in the partition.

[0082] In a specific application scenario, as Figure 13 shown, the device further includes: an inspection module 304.

[0083] The inspection module 304 is configured to obtain the original rock mass structure property model, and calculate the multiple correlation coefficient based on the target rock mass structure property model and the original rock mass structure property model,

[0084]

[0085]

[0086]

[0087] wherein, represents the multiple correlation coefficient, represents the sum of squared residuals, represents the regression sum of squares, represents the error between the p-th original block in the original rock mass structure attribute model and the p-th target block in the target rock mass structure attribute model, m represents the total number of multiple target blocks in the target rock mass structure attribute model, represents the attribute value of the p-th original block in the original rock mass structure attribute model, represents the attribute value of the p-th target block in the target rock mass structure attribute model, represents the mean value of the attribute values of multiple original blocks in the original rock mass structure attribute model; Obtain the multiple correlation coefficient detection rule. If it is detected and determined that the multiple correlation coefficient conforms to the multiple correlation coefficient determination rule, then store the target rock mass structure attribute model.

[0088] The embodiment of the present application provides a device. Compared with the prior art, the embodiment of the present application obtains the original drilling data, models the uniformly discretized original drilling data to obtain an initial model of drilling attributes, then calculates multiple distance-weighted variation coefficients used to characterize the spatial variability of the initial model of drilling attributes, based on the initial model of drilling attributes and multiple distance-weighted variation coefficients, uses the bubbling method to generate multiple non-homogeneity block model samples, and then takes the initial model of drilling attributes as a constraint condition, solves the weight coefficient matrix of multiple non-homogeneity block model samples by the least squares method, and uses the weight coefficient matrix to perform weighted superposition fitting on multiple non-homogeneity block model samples to generate a target rock mass structure attribute model. Through the effective utilization of drilling data and the reconstruction algorithm considering geological variability characteristics, even in the case of inherent defects in the data, a model that more accurately reflects the actual structure of the rock mass can be established based on these data, achieving high-precision fitting with the drilling data while realizing high-precision retention and reasonable extrapolation of the regional rock mass structure variability characteristics, effectively solving the problem of insufficient model accuracy in the sparse area of drilling data by the traditional method, and realizing high-precision modeling of the rock mass structure globally. Moreover, when constructing the rock mass structure model, fully considering the spatial variability of drilling data can better adapt to the rock mass structure characteristics under different geological conditions. Whether in a region with relatively simple geological conditions or under complex geological conditions, it can flexibly generate and fit a rock mass structure model that conforms to the actual situation according to the characteristics of drilling data, and has strong generalization ability.

[0089] It should be noted that for other corresponding descriptions of each functional unit involved in the rock mass structure modeling device based on drilling data provided by the embodiment of the present application, reference can be made to Figures 1 to 11 the corresponding description in, which will not be elaborated here.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0091] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0092] The above-described embodiments merely represent several implementation manners of this application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application should be subject to the appended claims.

[0093] In an exemplary embodiment, refer to Figure 14 , there is also provided a device, which includes a bus, a processor, a memory, and a communication interface, and may also include an input / output interface and a display device. Among them, each functional unit can complete mutual communication through the bus. The memory stores a computer program, and the processor is used to execute the program stored on the memory to execute the method for rock mass structure modeling based on drilling data in the above embodiments.

[0094] A medium, on which a computer program is stored, and when the computer program is executed by a processor, it realizes the steps of the method for rock mass structure modeling based on drilling data.

[0095] Through the description of the above implementation manners, those skilled in the art can clearly understand that this application can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of this application can be embodied in the form of a software product, and this software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of this application.

[0096] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily essential for implementing this application.

[0097] Those skilled in the art can understand that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the description of the implementation scenario, or can be correspondingly changed to be located in one or more devices different from this implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0098] The above serial numbers of the present application are only for description and do not represent the advantages or disadvantages of the implementation scenario.

[0099] The above discloses only several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present application.

Claims

1. A method for modeling rock mass structure based on drilling data, characterized in that, Including: Obtain the original drilling data, model the original drilling data after uniform discretization processing to obtain an initial drilling attribute model; Calculate a plurality of distance-weighted variation coefficients used to characterize the spatial variability of the initial drilling attribute model. Based on the initial drilling attribute model and the plurality of distance-weighted variation coefficients, use the bubbling method to generate a plurality of heterogeneous block model samples; Taking the initial drilling attribute model as a constraint condition, solve the weight coefficient matrix of the plurality of heterogeneous block model samples by the least square method, and use the weight coefficient matrix to perform weighted superposition fitting on the plurality of heterogeneous block model samples to generate a target rock mass structure attribute model.

2. The method according to claim 1, characterized in that, The modeling of the original drilling data after uniform discretization processing to obtain an initial drilling attribute model includes: Preprocess the original drilling data, remove the data with missing data and abnormal data in the original drilling data to obtain target drilling data; Convert the target drilling data into a plurality of three-dimensional drilling coordinates and the attribute values corresponding to each of the three-dimensional drilling coordinates; Perform uniform discretization processing on the plurality of three-dimensional drilling coordinates and the attribute values corresponding to the plurality of three-dimensional drilling coordinates to obtain a plurality of discretized blocks; For each of the discretized blocks, determine the plurality of three-dimensional drilling coordinates included in the discretized block, calculate and determine the centroid coordinates of the discretized block using the plurality of three-dimensional drilling coordinates included in the discretized block, determine the attribute values corresponding to the plurality of three-dimensional drilling coordinates included in the discretized block, and take the average value of the attribute values corresponding to the plurality of three-dimensional drilling coordinates included in the discretized block as the attribute value of the discretized block; Process each of the discretized blocks respectively to obtain the centroid coordinates and attribute values of each of the discretized blocks; Use the centroid coordinates and attribute values of the plurality of discretized blocks to perform modeling to obtain the initial drilling attribute model.

3. The method according to claim 1, wherein The calculation of a plurality of distance-weighted variation coefficients used to characterize the spatial variability of the initial drilling attribute model includes: Determine the plurality of discretized blocks included in the initial drilling attribute model, and calculate the distance-weighted variation coefficient of each of the discretized blocks; Among them, represents the distance weighted variation coefficient of the th discretized block, represents the weighted standard deviation of the th discretized block, represents the weighted average value of the th discretized block. n represents the total number of discretized blocks in the spherical domain with a radius of r. represents the weight of the th discretized block within the said spherical domain, represents the property value of the th discretized block within the said spherical domain, th discretized block is the center point of the said spherical domain; Use the distance-weighted variation coefficients of the plurality of discretized blocks to characterize the spatial variability of the initial drilling attribute model.

4. The method according to claim 1, characterized in that The generation of a plurality of heterogeneous block model samples by the bubbling method based on the initial drilling attribute model and the plurality of distance-weighted variation coefficients includes: Obtain target drilling data, and use a clustering algorithm to partition the initial drilling attribute model according to the target drilling data to obtain a plurality of partitions of the initial drilling attribute model; Obtain the attribute values of each discretized block in the initial drilling attribute model and the spatial dimensions of the initial drilling attribute model; Calculate the multiple partitions of the initial borehole attribute model, the attribute values of each discretized block in the initial borehole attribute model, the spatial dimensions of the initial borehole attribute model, and the multiple distance-weighted variation coefficients by using the bubble method, and generate the multiple inhomogeneous block model samples. The number of partitions of each inhomogeneous block model sample is the same as that of the initial borehole attribute model.

5. The method according to claim 1, characterized in that, Taking the initial borehole attribute model as a constraint condition, solve the weight coefficient matrix of the multiple inhomogeneous block model samples by the least squares method, and perform weighted superposition fitting on the multiple inhomogeneous block model samples by using the weight coefficient matrix to generate a target rock mass structure attribute model, including: Obtain the multiple discretized blocks included in the initial borehole attribute model and the multiple discretized blocks included in each inhomogeneous block model sample. Among them, the total number of the multiple discretized blocks included in the initial borehole attribute model is the same as the total number of the multiple discretized blocks included in each inhomogeneous block model sample, and the multiple discretized blocks included in the initial borehole attribute model and the multiple discretized blocks included in each inhomogeneous block model sample are in one-to-one correspondence; Determine the multiple partitions included in the initial borehole attribute model and the multiple partitions included in each inhomogeneous block model sample. Among them, the multiple partitions of the initial borehole attribute model and the multiple partitions of each inhomogeneous block model sample are in one-to-one correspondence; Calculate the sum of squared residuals of each partition, and solve the sum of squared residuals of the multiple partitions by using the least squares method to obtain the weight coefficient matrix; Determine the attribute value matrix of each inhomogeneous block model sample in each partition, and perform weight coefficient superposition fitting by using the weight coefficient matrix and the attribute value matrix of each inhomogeneous block model sample in each partition to generate the target rock mass structure attribute model. Among them, represents the target attribute value matrix of the j-th partition in the target rock mass structure attribute model, and s represents the total number of the multiple heterogeneous block model samples. represents the weight coefficient of the i-th heterogeneous block model sample in the j-th partition. represents the attribute value matrix of the i-th heterogeneous block model sample in the j-th partition.

6. The method according to claim 5, wherein The calculation of the sum of squared residuals of each partition includes: For each partition, determine the multiple discretized blocks of the initial borehole attribute model in the partition and the multiple discretized blocks of each inhomogeneous block model sample in the partition; Calculate the sum of squared residuals of the partition by using the attribute values of the multiple discretized blocks of the initial borehole attribute model in the partition and the attribute values of the multiple discretized blocks of each inhomogeneous block model sample in the partition. Among them, represents the sum of squared residuals of the partition, m represents the number of discretized blocks in the partition, represents the error between the k-th discretized block of the multiple heterogeneity block models samples in the partition and the k-th discretized block of the initial borehole property model in the partition, represents the property value of the k-th discretized block of the initial borehole property model in the partition, represents the predicted property value of the k-th discretized block of the multiple heterogeneity block models samples in the partition, represents the weight coefficient of the i-th heterogeneity block model sample in the partition, s represents the total number of the multiple heterogeneity block models samples, represents the property value of the k-th discretized block of the i-th heterogeneity block model sample in the partition.

7. The method according to claim 1, wherein The method further includes: Obtain the original rock mass structure attribute model, and calculate the multiple correlation coefficient based on the target rock mass structure attribute model and the original rock mass structure attribute model. Among them, represents the said multiple correlation coefficient, represents the sum of squared residuals, represents the regression sum of squares, represents the error between the p-th original block in the original rock mass structure attribute model and the p-th target block in the target rock mass structure attribute model, m represents the total number of multiple target blocks in the target rock mass structure attribute model, represents the attribute value of the p-th original block in the original rock mass structure attribute model, represents the attribute value of the p-th target block in the target rock mass structure attribute model, represents the mean of the attribute values of multiple original blocks in the original rock mass structure attribute model; Obtain the multiple correlation coefficient detection rule. If it is detected and determined that the multiple correlation coefficient conforms to the multiple correlation coefficient determination rule, then store the target rock mass structure attribute model.

8. A rock mass structure modeling device based on drilling data, characterized in that, Including: An initial model construction module, configured to obtain original borehole data, and perform modeling on the uniformly discretized original borehole data to obtain an initial borehole attribute model. A heterogeneous sample generation module, configured to calculate a plurality of distance-weighted variation coefficients for characterizing the spatial variability of the initial model of the borehole properties, and generate a plurality of heterogeneous block model samples by using the bubbling method based on the initial model of the borehole properties and the plurality of distance-weighted variation coefficients; A weight fitting and modeling module, configured to solve a weight coefficient matrix of the plurality of heterogeneous block model samples by using the least squares method with the initial model of the borehole properties as a constraint condition, and perform weighted superposition fitting on the plurality of heterogeneous block model samples by using the weight coefficient matrix to generate a target rock mass structure property model.

9. An apparatus, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A medium on which a computer program is stored, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images