Engineering surrounding rock intelligent rapid grading method and system

Abstract

The invention relates to the field of intelligent and rapid classification of engineering surrounding rocks, in particular to an intelligent and rapid classification method and system for engineering surrounding rocks. The method comprises the following steps: acquiring three-dimensional characteristic parameters of a surrounding rock structural surface according to stereophotogrammetry; acquiring a comprehensive quality index of the surrounding rock according to a dynamic response test; on the basis of the three-dimensional characteristic parameters and the comprehensive quality indexes, acquiring the uniaxial compressive strength and the integrity coefficient of the rock mass; constructing an evolutionary support vector regression model by using a support vector regression algorithm and an evolutionary algorithm; constructing an intelligent grading model based on the evolution support vector regression model; and through the intelligent grading model, intelligent and rapid grading of the engineering surrounding rock is realized. By establishing the function relation model of the surrounding rock grade and the nondestructive testing index, the field data acquisition process is simplified, the dependence on the experience of operators is reduced, the rapid and accurate detection of the surrounding rock grade is realized, the construction cost is greatly reduced, and the engineering period is shortened.

Description

Technical Field

[0001] The present invention relates to the field of intelligent rapid classification of engineering surrounding rocks, and in particular to an intelligent rapid classification method and system for engineering surrounding rocks. Background Art

[0002] In engineering geological exploration and underground engineering design, surrounding rock classification is an important basis for evaluating the stability of underground structures and guiding the formulation of construction plans. Traditional surrounding rock classification methods mainly rely on the experience and judgment of on-site engineers and geological survey data. It is not only time-consuming, but also easily affected by the personal experience level of engineers, resulting in high subjectivity and uncertainty in the classification results. In recent years, with the rapid development of stereo photogrammetry technology and dynamic response testing technology, new technical approaches have been provided for the intelligent and rapid classification of surrounding rock.

[0003] In the existing technology, surrounding rock classification mainly relies on manual observation and engineer experience, which has the following shortcomings: First, it is highly subjective and lacks unified standards and objective quantitative indicators. The classification results are affected by the personal experience of engineers, resulting in uncertainty and inconsistency, affecting accuracy and construction safety management; second, data collection and processing are cumbersome, requiring on-site investigation, sampling and laboratory testing, which is time-consuming and labor-intensive, increases construction costs, prolongs the work cycle, and affects project progress and efficiency; third, the technical means are single, focusing on the application of a single technical means, such as geological survey and mechanical testing, and ignoring the comprehensive application of multiple technical means, resulting in incomplete and inaccurate surrounding rock quality assessment, which is difficult to meet the high requirements of modern underground engineering.

[0004] At present, there is not enough research work on the intelligent and rapid classification of engineering surrounding rocks, and there is no specific intelligent and rapid classification method for engineering surrounding rocks based on stereo photogrammetry and dynamic response testing. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides a method and system for intelligent and rapid classification of surrounding rocks in an engineering project.

[0006] In a first aspect, the present invention provides a method for intelligent and rapid grading of engineering surrounding rock, comprising the following steps: obtaining three-dimensional characteristic parameters of the surrounding rock structural surface based on stereophotogrammetry; obtaining comprehensive quality indicators of the surrounding rock based on dynamic response testing; obtaining the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient based on the three-dimensional characteristic parameters and the comprehensive quality indicators; constructing an evolutionary support vector regression model based on the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient using a support vector regression algorithm and an evolutionary algorithm; constructing an intelligent grading model for outputting the surrounding rock grade based on the evolutionary support vector regression model; and realizing intelligent and rapid grading of engineering surrounding rock through the intelligent grading model. The present invention uses stereophotogrammetry technology to efficiently and accurately obtain three-dimensional characteristic parameters of surrounding rock structural surfaces, significantly improving the accuracy and efficiency of data acquisition; through dynamic response testing, the surrounding rock quality is comprehensively evaluated, enriching the dimensions of surrounding rock quality evaluation, and making the evaluation results more comprehensive and reliable; by obtaining the uniaxial compressive strength of rock mass and rock integrity coefficient, key parameters are provided for constructing an intelligent grading model, enhancing the prediction accuracy and applicability of the model; by constructing an intelligent grading model, rapid and intelligent grading of engineering surrounding rock quality is achieved, greatly improving grading efficiency and accuracy, and providing strong technical support for the design and construction of tunnel surrounding rock engineering.

[0007] Optionally, the three-dimensional characteristic parameters of the surrounding rock structural surface obtained based on stereo photogrammetry include: using a total station to obtain the real-world coordinates of the surrounding rock; based on the real-world coordinates, using a binocular vision camera to obtain a rock image; based on the rock image, using three-dimensional real-scene modeling software, constructing a sparse point cloud model based on a motion recovery structure algorithm; based on the sparse point cloud model, using a three-dimensional multi-view stereo vision algorithm, constructing a high-density point cloud model; based on the high-density point cloud model, using the triangular mesh editing function of the three-dimensional real-scene modeling software, constructing a three-dimensional digital surface model; based on the three-dimensional digital surface model, using a clustering algorithm to classify the structural surface point cloud data and obtain classification results; based on the classification results, calculating the structural surface spacing and the number of rock volume joints. The present invention uses a total station to obtain the real-world coordinates of the surrounding rock, and then combines it with a binocular vision camera to capture rock images, thereby significantly improving the accuracy and efficiency of data acquisition and ensuring the reliability of structural surface characteristic parameters; by constructing a sparse point cloud model based on a motion recovery structure algorithm, and further using a three-dimensional multi-view stereo vision algorithm to generate a high-density point cloud model, the generation of point cloud data from sparse to dense, from rough to fine is achieved, laying a solid foundation for building an accurate three-dimensional digital surface model; the structural surface point cloud data is classified through the triangular mesh editing function and clustering algorithm of the three-dimensional real-scene modeling software, and the structural surface spacing and the number of rock volume joints are accurately calculated, providing a key basis for evaluating the stability of the surrounding rock and formulating engineering measures.

[0008] Optionally, the method of obtaining the comprehensive quality index of the surrounding rock based on the dynamic response test includes: obtaining the comprehensive stress wave velocity index of the surrounding rock based on the dynamic response test, and the comprehensive stress wave velocity index is used to characterize the quality of the surrounding rock; obtaining the comprehensive rebound strength index of the surrounding rock based on the dynamic response test, and the comprehensive rebound strength index is used to characterize the strength of the surrounding rock. The present invention obtains the comprehensive stress wave velocity index of the surrounding rock through the dynamic response test, which intuitively and quickly reflects the overall quality and internal defects of the surrounding rock, provides a scientific basis for evaluating the stability of the surrounding rock, and significantly improves the accuracy and efficiency of the surrounding rock quality assessment; by introducing the comprehensive rebound strength index, the strength characteristics of the surrounding rock are effectively characterized, which provides an important reference for judging the bearing capacity and deformation characteristics of the surrounding rock, further enriches the dimension of the surrounding rock quality assessment, and enhances the reliability and practicality of the assessment results.

[0009] Optionally, the comprehensive stress wave velocity index satisfies the following relationship: , in, is the comprehensive stress wave velocity index, is the distance between the center points of the two sensors, is the propagation time difference; the comprehensive rebound strength index satisfies the following relationship: , in, It is a comprehensive rebound strength index. For the lithology measurement area Lithology measurement area The rebound strength of each measuring point, For the Lithology measurement area The rebound strength of each measuring point, For the The area of ​​lithology measurement area, For the The present invention provides a theoretical basis for accurately measuring and analyzing the stress wave propagation characteristics of the surrounding rock by correlating wave velocity, sensor spacing and propagation time difference, which helps to accurately evaluate the overall quality and internal structure of the surrounding rock; by combining the rebound strength with the area of ​​different rock type measurement areas, the influence of rock type differences on the rebound strength is comprehensively considered, making the evaluation of the rebound strength more comprehensive and accurate, and providing a scientific basis for judging the strength characteristics of the surrounding rock.

[0010] Optionally, the obtaining of the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient based on the three-dimensional characteristic parameters and the comprehensive quality index includes: obtaining the uniaxial compressive strength of the rock mass based on the comprehensive rebound strength index; obtaining the rock mass integrity coefficient based on the comprehensive stress wave velocity index and the three-dimensional characteristic parameters. The present invention provides strong support for the design and construction of tunnel surrounding rock engineering by obtaining the uniaxial compressive strength of the rock mass; by obtaining the rock mass integrity coefficient, the internal structure of the surrounding rock and the stress wave propagation characteristics are comprehensively considered, making the evaluation of the integrity coefficient more accurate and scientific.

[0011] Optionally, the method of constructing an evolutionary support vector regression model based on the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient using a support vector regression algorithm and an evolutionary algorithm includes: constructing a support vector regression model based on the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient using a support vector regression algorithm; and constructing an evolutionary support vector regression model using a particle swarm optimization algorithm based on the support vector regression model. The present invention accurately captures the complex relationship between the mechanical properties of the rock mass and the parameters by constructing a support vector regression model, improves the prediction accuracy, and provides a scientific basis for rock mass classification and stability assessment; optimizes the support vector regression model by introducing a particle swarm optimization algorithm, effectively solves the problem of model parameter selection, improves the generalization ability and robustness of the model, and enables the model to perform well under different geological conditions; through the evolutionary support vector regression model, not only the accuracy of rock mass classification and stability assessment is improved, but also a more reliable prediction tool is provided for engineering practice, which helps to optimize engineering plans and reduce safety risks, and has significant innovation and practical value.

[0012] Optionally, the method of constructing an evolutionary support vector regression model by using a particle swarm optimization algorithm based on the support vector regression model includes: selecting a radial function kernel as a kernel function based on the support vector regression model; setting hyperparameters based on the kernel function, wherein the hyperparameters include a penalty parameter and a width parameter of the radial function kernel; searching for the optimal value of the hyperparameter using the particle swarm optimization algorithm to obtain the optimal hyperparameter; and constructing an evolutionary support vector regression model by using the optimal hyperparameter. The present invention flexibly captures the nonlinear relationship between data by selecting a radial function kernel as a kernel function, improves the prediction accuracy of the model, and provides a more accurate tool for rock mass classification and stability assessment under complex geological conditions; by setting hyperparameters and searching for the optimal value using a particle swarm optimization algorithm, the problem of hyperparameter selection is effectively solved, the cumbersomeness and subjectivity of parameter debugging in traditional methods are avoided, and the automation and efficiency of the model are improved; the evolutionary support vector regression model constructed by the optimal hyperparameters not only improves the prediction performance, but also enhances the generalization ability of the model, so that it can perform well in different geological environments and engineering conditions, and has significant innovation and practical value.

[0013] Optionally, the construction of an intelligent grading model for outputting surrounding rock grade based on the evolutionary support vector regression model includes: integrating the acquired three-dimensional feature parameters and the comprehensive quality index into a first data sample; obtaining a second data sample of the surrounding rock grade after basic quality sub-grade classification corresponding to the three-dimensional feature parameters and the comprehensive quality index; integrating the first data sample and the second data sample into a comprehensive data sample; using the comprehensive data sample, training the evolutionary support vector regression model to obtain training results; based on the training results, establishing a functional relationship between the three-dimensional feature parameters, the comprehensive quality index and the surrounding rock grade; and constructing an intelligent grading model for outputting the surrounding rock grade through the functional relationship. The present invention integrates three-dimensional characteristic parameters and comprehensive quality indicators as data samples, makes full use of multiple information sources, improves the comprehensiveness and accuracy of surrounding rock quality assessment, and lays a solid foundation for the construction of an intelligent grading model; by using comprehensive data samples to train the evolutionary support vector regression model, not only the prediction ability of the model is enhanced, but also a functional relationship between three-dimensional characteristic parameters, comprehensive quality indicators and surrounding rock grade is established; through the intelligent grading model, the surrounding rock grade is automatically output, which greatly improves the assessment efficiency and accuracy, and provides a more scientific and convenient surrounding rock quality assessment tool for engineering practice.

[0014] Optionally, the second data sample of the surrounding rock grade after obtaining the basic quality sub-grade classification corresponding to the three-dimensional characteristic parameters and the comprehensive quality index includes: substituting the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient into the surrounding rock basic quality classification formula to obtain a classification index; judging the surrounding rock grade according to the classification index; integrating the classification index and the surrounding rock grade into a second data sample. The present invention accurately calculates the classification index by substituting the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient into the surrounding rock basic quality classification formula, provides a scientific basis for the classification of surrounding rock grades, and effectively avoids the subjectivity and uncertainty of the classification standards in traditional methods; by judging the surrounding rock grade through the classification index, a quantitative assessment of the surrounding rock quality is achieved, and the accuracy and objectivity of the assessment are improved; by integrating the classification index and the surrounding rock grade into the second data sample, rich data support is provided for the training of the intelligent classification model, which helps to improve the prediction ability and generalization performance of the model, and lays a solid foundation for the intelligent assessment of the surrounding rock quality grade.

[0015] In a second aspect, the present invention provides a system for intelligent and rapid grading of surrounding rock for engineering, comprising an input device, a processor, an output device and a memory, wherein the input device, the processor, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, the processor is configured to call the program instructions, and the system uses the method for intelligent and rapid grading of surrounding rock for engineering. The system integrates binocular vision cameras and total station equipment to achieve rapid and accurate collection of field data; by constructing a high-density point cloud model based on motion recovery structure algorithm and three-dimensional multi-view stereo vision algorithm, the efficiency of data collection and processing is greatly improved, providing a solid foundation for surrounding rock classification; by adopting a clustering algorithm to classify the structural surface point cloud, and accurately calculating the structural surface spacing and the number of rock volume joints, combined with non-destructive testing indicators such as rebound strength and stress wave velocity, the system achieves intelligent and objective judgment of surrounding rock grade, effectively reducing the dependence on the operator's work experience; the application of the system significantly simplifies the surrounding rock classification process, shortens the work cycle, reduces construction costs, and at the same time improves the accuracy and reliability of the classification results, providing a strong guarantee for the safe construction of the project, and demonstrating its great potential and application value in engineering practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the intelligent and rapid classification method of engineering surrounding rock according to an embodiment of the present invention; Figure 2 A flowchart of three-dimensional digital model reconstruction according to an embodiment of the present invention; Figure 3 A diagram of a method for arranging measuring points of a rebound hammer according to an embodiment of the present invention; Figure 4 It is a diagram of an echo detector device according to an embodiment of the present invention; Figure 5 This is a flow chart of constructing an optimal support vector regression model using a particle swarm optimization algorithm according to an embodiment of the present invention; Figure 6 It is a structural schematic diagram of an intelligent rapid grading system for engineering surrounding rock according to an embodiment of the present invention; Figure 7 This is an operation flow chart of the intelligent rapid grading system for engineering surrounding rock according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0018] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0019] See also Figure 1 The embodiment of the present invention provides a method for intelligent and rapid classification of surrounding rocks in an engineering project, the method comprising the following steps: S1. Based on stereophotogrammetry, obtain the three-dimensional characteristic parameters of the surrounding rock structure surface.

[0020] In one embodiment, the real world coordinates of the surrounding rock are firstly acquired using a total station.

[0021] Specifically, a certain number of control points are arranged on the surface of the tunnel surrounding rock measurement area; the equipment is checked and parameters are set, and then the instrument is calibrated; after selecting a suitable measurement method, the total station is placed and aimed at the target point, and the angle, height and slope distance data are recorded; the data is sorted, and error analysis is performed to ensure accuracy; and reliable real-world coordinates of the surrounding rock are obtained.

[0022] Furthermore, a binocular vision camera is used to capture images of the tunnel face and side wall surrounding rock.

[0023] Specifically, the two cameras are first calibrated to obtain internal and external parameters and homography matrices for distortion correction; the cameras are fixed and the same rock area is photographed synchronously to obtain two images; image matching is performed based on epipolar constraints to establish the correspondence between feature points; the position deviation between corresponding points in the image is calculated and combined with the camera parameters to restore the three-dimensional geometric information of the rock mass, thereby obtaining a detailed rock image.

[0024] Furthermore, based on the 3D real-scene modeling software platform, a sparse point cloud model based on the structure from motion (SFM) algorithm was constructed.

[0025] Specifically, the rock mass image is imported into the 3D real-scene modeling software to extract and match feature points and estimate the camera posture; a preliminary sparse point cloud is obtained through triangulation, and the bundle adjustment (BA) method is used to optimize the camera parameters and point cloud coordinates to improve the accuracy; a sparse point cloud model is generated to provide a basis for subsequent 3D reconstruction.

[0026] Furthermore, based on the sparse point cloud model, a high-density point cloud model is constructed using a three-dimensional multi-view stereo vision (PMVS) algorithm.

[0027] Specifically, based on the sparse point cloud model, the sparse point cloud is expanded to generate more candidate points; matching features are searched in multi-view images, and the depth value of each candidate point is calculated through the depth map fusion strategy; the depth map is filtered and optimized to obtain more accurate point cloud data; the optimized point cloud data is integrated to construct a high-density, high-precision three-dimensional point cloud model.

[0028] It should be noted that the PMVS algorithm includes the following detailed steps: For images Each feature point f on is associated with an array containing all feature points of the same type on the same epipolar line on other images; A feature point f' is selected from the array to form a pair of image points (f, f') with the same name, and the three-dimensional coordinates of the object point are obtained through the forward intersection in triangulation; Initialize the three basic properties of the patch: the object point coordinate c(p) as the center point of the patch, the image As a reference image, the unit normal vector n(p) is constructed according to the direction of the line connecting the object point coordinates and the photography center; The visible set V(p) is determined by the angle between the object point and the line connecting the other photographic centers and their unit normal vectors, which is within the range of plus or minus 60 degrees. Based on the visible set, the updated visible set V*(p) is further determined. There is a threshold α, which is taken as 0.6, that is, the imaging difference coefficient h(p, I, R(p)) between the reference image and the image should be less than 0.6. The goal is to minimize the total imaging difference function g*(p) of the patch; change the position and posture of the patch through the conjugate gradient method; When the facet pose changes, the updated visible set V*(p) will also change accordingly. At this time, α is set to 0.3. If the number of images in the updated visible set V*(p) is greater than the threshold γ, it means that the facet appears in at least γ images with low imaging differences. The facet is reconstructed successfully and stored in the corresponding grid unit, and the relevant data structure is updated. For the new patch p', initialize its c(p'), n(p') and V(p') attributes. n(p') and V(p') can use the corresponding attributes of patch p as initial values. c(p') is the intersection of the line connecting the photographic center of the reference image and the center of the grid unit and the plane where patch p is located. V*(p') is obtained from V(p'). Given the updated visible set V*(p'), determine the total imaging difference function g*(p') of the new face, and use the conjugate gradient method to change the position and posture of the face with the goal of minimizing g*(p'); Since the patch p' is different from p, we can add a new image to V(p') through the disparity map test and find V*(p') from V(p') again; If the number of images in the updated visible set V*(p') is greater than the threshold γ, it means that the new patch is reconstructed successfully, stored in the corresponding grid unit, and the relevant data structure is updated.

[0029] Furthermore, based on the high-density point cloud model, a three-dimensional digital surface model is constructed using the triangular mesh editing function of the three-dimensional real scene modeling software. The reconstruction process of the three-dimensional digital surface model is as follows: Figure 2 shown.

[0030] Specifically, the point cloud data is first imported into the 3D real-scene modeling software, and a suitable mesh resolution is set; an initial triangular mesh is generated using a triangulation algorithm, and the mesh is optimized using a smoothing algorithm to reduce noise and unevenness; mesh holes are repaired manually or automatically to ensure model integrity; and a detailed 3D digital surface model is generated to provide a basis for subsequent analysis and application.

[0031] Furthermore, based on the three-dimensional digital surface model, a density-based clustering algorithm with noise (DBSCAN) is used to classify the structural surface point cloud data and obtain a classification result.

[0032] Specifically, first load the point set to be clustered; calculate the number of points in each point's neighborhood. The process is described by the following mathematical expression: , in, Representative Points The set of points in the neighborhood of represents the set of all points, Indicate point and The distance between is the threshold of the distance between neighboring points of the detection object; the core points are identified according to the number of points in the neighborhood of each point calculated. A point is regarded as a core point if the number of points in its neighborhood is greater than or equal to a preset minimum number of points; the structural surface is refined into multiple clusters using the identified core points, that is, starting from a core point, other points whose density can be reached are continuously searched to form a set of density-connected points, i.e. a cluster; then the next core point that has not been classified into any cluster is searched, and the above process is repeated until all core points are classified into a cluster or all points are processed.

[0033] Furthermore, based on the classification results, the spacing between structural planes and the number of rock volume joints are calculated.

[0034] Specifically, the normal vector and horizontal vector of the structural surface are obtained by principal component analysis, and the classification cluster is projected onto the plane along the horizontal projection direction; the linear regression equation of the scattered points is obtained and fitted into line segments on the projection plane; the spacing of the fitted line segments is calculated on the plane, where the normal distance between each group of structural surfaces is calculated along the normal direction of the structural surface (i.e., the survey line); in addition, the calculation formula for the number of rock volume joints is as follows:

[0035] in, is the number of structural planes per cubic meter of rock mass volume, For the The number of structural surfaces per meter along the normal direction of the group structure surface, It is the number of non-grouped joints per cubic meter of rock mass.

[0036] S2. Obtain comprehensive quality indicators of surrounding rock based on dynamic response test.

[0037] Among them, S2 includes the following steps: S21. Based on the dynamic response test, obtain the comprehensive stress wave velocity index of the surrounding rock.

[0038] In one embodiment, based on the dynamic response test, a comprehensive stress wave velocity index for characterizing the surrounding rock quality is obtained; the comprehensive stress wave velocity index satisfies the following relationship:

[0039] in, It is a comprehensive stress wave velocity index, accurate to 1ms. is the distance between the center points of the two sensors (mm). Generally, it is 300mm. is the propagation time difference (μs).

[0040] Furthermore, the comprehensive stress wave velocity index of the surrounding rock is calculated through the above expression.

[0041] S22. Based on the dynamic response test, obtain the comprehensive rebound strength index of the surrounding rock.

[0042] In one embodiment, based on the dynamic response test, a comprehensive rebound strength index for characterizing the strength of the surrounding rock is obtained.

[0043] Specifically, after each cycle of tunnel excavation construction, clean up the rock debris and pumice on the newly exposed surrounding rock, arrange rebound measuring points, and pay attention to the changes in the lithology of the surrounding rock. Generally, no less than 5 measuring points should be arranged on the surrounding rock of the same lithology, and the distance between adjacent measuring points should be within the range of 0.2m~2m.

[0044] Furthermore, a rebound test was used to test the rebound response of the surrounding rock of the tunnel on site. The measurement points were arranged as follows: Figure 3 As shown, each measuring point is measured 10 times, the highest value and the two lowest values ​​are removed, and the arithmetic mean is taken as the rebound strength of the measuring point.

[0045] Furthermore, based on the rebound strength of the measuring point, the comprehensive rebound strength index of the surrounding rock on the tunnel surface of a single cycle footage is obtained, and the comprehensive rebound strength index satisfies the following relationship:

[0046] in, It is a comprehensive rebound strength index. For the Lithology measurement area The rebound strength of each measuring point, For the Lithology measurement area The rebound strength of each measuring point, For the The area of ​​lithology measurement area, For the The area of ​​​​the lithology measurement area.

[0047] S3. Based on the three-dimensional characteristic parameters and the comprehensive quality index, obtain the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient.

[0048] Among them, S3 includes the following steps: S31. Obtain the uniaxial compressive strength of rock mass.

[0049] In one embodiment, the uniaxial compressive strength of the rock mass is estimated from the measured rebound value using the following formula:

[0050] in, is the uniaxial compressive strength of rock mass, , is the weight coefficient, is the measured rebound value.

[0051] S32. Obtain rock mass integrity coefficient.

[0052] In one embodiment, first, based on the rebound measuring points arranged in step S22, measuring points are arranged again, and a wireless echo detector is used to detect the wave velocity of stress waves on the newly exposed surrounding rock, and the wave velocity of stress waves is recorded. The relevant equipment of the echo detector is as follows: Figure 4 shown.

[0053] Furthermore, the rock mass integrity coefficient is characterized by the comprehensive data obtained from the wave velocity and point cloud model. .

[0054] S4. Based on the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient, an evolutionary support vector regression model is constructed.

[0055] In one embodiment, firstly, based on the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient, a support vector regression (SVR) algorithm is used to construct an objective function, and the objective function is as follows:

[0056] in, is the weight vector, is the bias vector, is the sample size, is the penalty parameter, is the sample serial number, and is a slack variable used to handle inseparable situations. The objective function has the minimum model complexity under the condition of satisfying the existing insensitive loss function. This objective function is also called SVR model.

[0057] Further, based on the objective function, a radial basis function (RBF) kernel is selected as the kernel function.

[0058] Furthermore, based on the kernel function, hyper parameters are set, and the hyper parameters include a penalty parameter and a width parameter of the radial function kernel.

[0059] Furthermore, the particle swarm optimization (PSO) algorithm is used to search for the optimal value of the hyperparameter and obtain the optimal hyperparameter. The PSO algorithm searches for the optimal solution by simulating the foraging behavior of a flock of birds and iteratively updating the speed and position of each particle. Each particle represents a potential solution, and its speed and position represent the search direction and the current solution respectively. The algorithm tracks the individual optimal solution of each particle ( pbest ) and the group optimal solution ( gbest ) to guide the particles to move towards the optimal solution.

[0060] Specifically, the group position and velocity are initialized first, the initial position of the particles is randomly generated in the solution space, and then the initial velocity is generated. The velocity update formula is as follows:

[0061] The position update formula is as follows:

[0062] in, Indicates Particles in The speed of time, Indicates Particles in The location at the moment, Indicates Particles in The speed of time, Indicates Particles in The location at the moment; The inertia weight controls the degree to which the particle inherits the previous velocity; and is the acceleration factor, controlling the particle pbest and gbest degree of mobility; and is a random number between [0, 1].

[0063] Furthermore, the PSO algorithm is applied to SVR parameter optimization. The specific process is as follows: Figure 5 shown.

[0064] Specifically, a swarm of particles is randomly initialized, each particle represents a set of SVR parameters, and the prediction accuracy of the SVR parameters corresponding to each particle is evaluated by cross-validation and other methods, such as the root mean square error (RMSE) or mean absolute error (MAE), and the prediction accuracy is used as the fitness value of the particle; the speed and position of each particle are updated according to the update formula of the PSO algorithm to search for new SVR parameter combinations; the above steps are repeated until the termination condition is met, the maximum number of iterations is reached, or the preset accuracy requirement is met; the SVR parameters corresponding to the particle with the highest fitness value are selected as the optimal parameters, and the parameters are used to construct the final SVR model, that is, the evolutionary support vector regression model.

[0065] S5. According to the evolutionary support vector regression model, an intelligent grading model based on the evolutionary support vector regression algorithm is constructed.

[0066] In one embodiment, firstly based on step S1, data samples of nondestructive testing indicators such as three-dimensional characteristic parameters of surrounding rock structural surface, surrounding rock comprehensive rebound strength index and surrounding rock comprehensive stress wave velocity index are obtained and named as the first data sample.

[0067] Further, the surrounding rock grade after basic quality (BQ) sub-grade classification corresponding to the non-destructive testing index is obtained, and a data sample is formed, which is named as the second data sample; Specifically, the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient are substituted into the surrounding rock basic quality classification formula to obtain a classification index; the surrounding rock basic quality formula is as follows:

[0068] in, It is the basic quality index of rock mass. is the saturated uniaxial compressive strength of rock mass (unit: MPa), is the rock mass integrity coefficient, dimensionless; Furthermore, the surrounding rock grade is determined according to the classification index; specifically as follows: when When the surrounding rock is of excellent grade, it is extremely stable and requires almost no support; when When the surrounding rock is of good grade, it has high stability and requires a small amount of support; when When the surrounding rock is of medium grade, the stability is average and proper support is required; when When the surrounding rock is of poor grade, the stability is poor and more support is required; when When the surrounding rock is of extremely poor grade, its stability is extremely poor and requires a lot of support and special treatment.

[0069] Furthermore, the classification index and the surrounding rock grade are integrated into a data sample, which is named as a second data sample.

[0070] Further, the first data sample and the second data sample are combined to form a comprehensive data sample, and the comprehensive data sample includes a training set, a test set and a validation set. It should be noted that the surrounding rock grade corresponding to the non-destructive testing indicator is determined according to the BQ sub-classification standard.

[0071] Furthermore, the evolutionary support vector regression model is trained using the comprehensive data samples to establish a functional relationship model between nondestructive testing indicators and surrounding rock grades. The functional relationship model is an intelligent grading model based on the evolutionary support vector regression algorithm.

[0072] S6. Through the intelligent grading model, intelligent and rapid grading of the surrounding rock of the project is achieved.

[0073] In one embodiment, the obtained nondestructive testing indicators are substituted into the intelligent grading model to quickly obtain the surrounding rock grade, thereby realizing intelligent and rapid grading of the surrounding rock of the project.

[0074] See also Figure 6 , Figure 6 The structure diagram of an intelligent rapid classification system for engineering surrounding rocks in an embodiment of the present invention is shown in FIG. The system includes an input device, a processor, an output device, and a memory. The input device, the processor, the output device, and the memory are interconnected. The memory is used to store a computer program. The computer program includes program instructions. The processor is configured to call the program instructions. The system uses the intelligent rapid classification method for engineering surrounding rocks. The specific operation process is as follows: Figure 7 shown.

[0075] In this embodiment, the input device includes a wave velocity testing device, an energy rebound test device, a binocular vision camera and a total station, which are used to obtain characteristic parameters of surrounding rock strength and quality.

[0076] The processor is the core component of the system, with built-in PSO, SVR and intelligent classification models, and is responsible for executing various algorithms and programs to achieve data processing and analysis; The output device is another important interface for the system to interact with the user, including a display and a printer. The display is used to visually display the results of surrounding rock classification, including classification levels, related parameters and charts; Automatically generate detailed reports based on the grading results, including grading basis and recommended measures, to facilitate users' subsequent decision-making and management; send grading results and related data to external systems or devices, such as databases and remote servers, through data interfaces to achieve data sharing and exchange.

[0077] The memory adopts a high-speed solid-state hard disk, which has the characteristics of fast reading and writing speed, large capacity and high reliability. It is mainly used to store data obtained by the input device and the result data processed by the processor, and can meet the needs of large data storage.

[0078] In summary, the intelligent and rapid classification method for engineering surrounding rock provided by the present invention integrates three-dimensional characteristic parameters and comprehensive quality indicators as data samples, makes full use of multiple information sources, improves the comprehensiveness and accuracy of surrounding rock quality assessment, and lays a solid foundation for the construction of an intelligent classification model; by using comprehensive data samples to train the evolutionary support vector regression model, not only the prediction ability of the model is enhanced, but also the functional relationship between the three-dimensional characteristic parameters, comprehensive quality indicators and surrounding rock grade is established; through the intelligent classification model, the surrounding rock grade is automatically output, which greatly improves the evaluation efficiency and accuracy, and provides a more scientific and convenient surrounding rock quality assessment tool for engineering practice.

[0079] The invention provides an intelligent rapid grading system for engineering surrounding rocks, which realizes rapid and accurate collection of field data by integrating binocular vision cameras and total station equipment; by constructing a high-density point cloud model based on motion recovery structure algorithm and three-dimensional multi-view stereo vision algorithm, the efficiency of data collection and processing is greatly improved, providing a solid foundation for surrounding rock classification; by adopting a clustering algorithm to classify the structural surface point cloud, and accurately calculating the structural surface spacing and the number of rock volume joints, combined with non-destructive testing indicators such as rebound strength and stress wave velocity, the intelligent and objective judgment of the surrounding rock grade is realized, and the dependence on the work experience of the operator is effectively reduced; the application of the system significantly simplifies the surrounding rock classification process, shortens the work cycle, reduces the construction cost, and at the same time improves the accuracy and reliability of the classification results, providing a strong guarantee for the safe construction of the project, and demonstrating its great potential and application value in engineering practice.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. An intelligent and rapid classification method for engineering surrounding rocks, characterized in that: The method comprises the following steps: Based on stereophotogrammetry, the three-dimensional characteristic parameters of the surrounding rock structure surface are obtained; Obtain comprehensive quality indicators of surrounding rock based on dynamic response tests; Based on the three-dimensional characteristic parameters and the comprehensive quality index, obtaining the uniaxial compressive strength and the rock mass integrity coefficient of the rock mass; Based on the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient, an evolutionary support vector regression model is constructed using a support vector regression algorithm and an evolutionary algorithm; Based on the evolutionary support vector regression model, construct an intelligent classification model for outputting surrounding rock grades; The intelligent classification model can realize the intelligent and rapid classification of the surrounding rock of the project.

2. The method for intelligent rapid classification of surrounding rock in an engineering project according to claim 1, characterized in that: The three-dimensional characteristic parameters of the surrounding rock structure surface obtained based on stereophotogrammetry include: Using a total station, obtain the real-world coordinates of the surrounding rock; Based on the real-world coordinates, using a binocular vision camera, acquiring a rock mass image; Based on the rock mass image, a sparse point cloud model based on a motion recovery structure algorithm is constructed using three-dimensional real scene modeling software; Based on the sparse point cloud model, a high-density point cloud model is constructed using a three-dimensional multi-view stereo vision algorithm; Based on the high-density point cloud model, a three-dimensional digital surface model is constructed using the triangular mesh editing function of the three-dimensional real scene modeling software; Based on the three-dimensional digital surface model, a clustering algorithm is used to classify the structural surface point cloud data and obtain a classification result; Based on the classification results, the spacing between structural planes and the number of rock volume joints are calculated.

3. The method for intelligent rapid classification of surrounding rock in an engineering project according to claim 1, characterized in that: The comprehensive quality indicators of surrounding rock obtained by the dynamic response test include: Based on the dynamic response test, a comprehensive stress wave velocity index of the surrounding rock is obtained, and the comprehensive stress wave velocity index is used to characterize the quality of the surrounding rock; Based on the dynamic response test, the comprehensive rebound strength index of the surrounding rock is obtained, and the comprehensive rebound strength index is used to characterize the strength of the surrounding rock.

4. The method for intelligent rapid classification of surrounding rock in an engineering project according to claim 3, characterized in that: The comprehensive stress wave velocity index satisfies the following relationship: ， in, is the comprehensive stress wave velocity index, is the distance between the center points of the two sensors, is the propagation time difference; the comprehensive rebound strength index satisfies the following relationship: , in, It is a comprehensive rebound strength index. For the lithology measurement area Lithology measurement area The rebound strength of each measuring point, For the Lithology measurement area The rebound strength of each measuring point, For the The area of ​​lithology measurement area, For the The area of ​​​​the lithology measurement area.

5. The method for intelligent rapid classification of surrounding rock in an engineering project according to claim 1, characterized in that: The obtaining of the uniaxial compressive strength and the rock mass integrity coefficient based on the three-dimensional characteristic parameters and the comprehensive quality index comprises: Based on the comprehensive rebound strength index, the uniaxial compressive strength of the rock mass is obtained; Based on the comprehensive stress wave velocity index and the three-dimensional characteristic parameters, the rock mass integrity coefficient is obtained.

6. The method for intelligent rapid classification of surrounding rock in an engineering project according to claim 1, characterized in that: The constructing of the evolutionary support vector regression model based on the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient by using a support vector regression algorithm and an evolutionary algorithm comprises: Based on the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient, a support vector regression model is constructed using a support vector regression algorithm; According to the support vector regression model, an evolutionary support vector regression model is constructed using a particle swarm optimization algorithm.

7. The method for intelligent rapid classification of surrounding rock in an engineering project according to claim 6, characterized in that: The method of constructing an evolutionary support vector regression model based on the support vector regression model and using a particle swarm optimization algorithm includes: According to the support vector regression model, a radial function kernel is selected as a kernel function; Based on the kernel function, setting hyperparameters, the hyperparameters including a penalty parameter and a width parameter of a radial function kernel; Using a particle swarm optimization algorithm, searching for the optimal value of the hyperparameter to obtain the optimal hyperparameter; An evolutionary support vector regression model is constructed using the optimal hyperparameters.

8. The method for intelligent rapid classification of surrounding rock in an engineering project according to claim 1, characterized in that: The step of constructing an intelligent classification model for outputting surrounding rock grades based on the evolutionary support vector regression model includes: Integrate the acquired three-dimensional feature parameters and the comprehensive quality index into a first data sample; Acquire a second data sample of the surrounding rock grade after basic quality sub-grade classification corresponding to the three-dimensional characteristic parameters and the comprehensive quality index; integrating the first data sample and the second data sample into a composite data sample; Using the comprehensive data sample, training the evolutionary support vector regression model to obtain a training result; According to the training results, a functional relationship among the three-dimensional characteristic parameters, the comprehensive quality index and the surrounding rock grade is established; Through the functional relationship, an intelligent classification model for outputting surrounding rock grades is constructed.

9. The method for intelligent rapid classification of surrounding rock in an engineering project according to claim 8, characterized in that: The second data sample of the surrounding rock grade after the basic quality sub-grade classification corresponding to the three-dimensional characteristic parameters and the comprehensive quality index is obtained includes: Substituting the uniaxial compressive strength of the rock mass and the rock mass integrity coefficient into the basic quality classification formula of the surrounding rock to obtain a classification index; According to the classification index, the surrounding rock grade is determined; The classification index and the surrounding rock grade are integrated into a second data sample.

10. An intelligent rapid classification system for engineering surrounding rocks, the system using an intelligent rapid classification method for engineering surrounding rocks according to any one of claims 1 to 9, characterized in that: The system includes an input device, a processor, an output device and a memory, wherein the input device, the processor, the output device and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions.

Images