Method, device and equipment for predicting residual shear strength of rock joint and readable storage medium

Through the training of deep learning models with three-dimensional laser scanner and experimental data, a nonlinear mapping relationship of residual shear intensity of jointed rocks was constructed, which solved the problems of insufficient factors and limited data in existing models, and achieved accurate prediction of residual shear intensity of rocks. .

CN119026463AInactive Publication Date: 2024-11-26BEIJING UNIV OF CIVIL ENG & ARCHITECTURE

Patent Information

Application Number
CN202411062919.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing jointed rock residual shear strength prediction models have fewer considerations and limited data sets, resulting in inaccurate prediction.

Method used

The three-dimensional morphology point cloud data set of rock structural surfaces is obtained through a three-dimensional laser scanner, and combined with experimental data, deep learning neural network model is trained to construct a nonlinear mapping relationship of residual shear intensity of rocks, including sampling intervals and joint surface roughness, , uniaxial tensile strength, uniaxial compressive strength, normal pressure, viscosity, internal friction angle and joint size.

Benefits of technology

Accurate prediction of the residual shear strength of jointed rocks is achieved, the prediction accuracy and accuracy are improved, and the dependence on a priori assumption conditions is avoided, and complex nonlinear mapping relationships are directly constructed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026463A_ABST
    Figure CN119026463A_ABST
Patent Text Reader

Abstract

The invention provides a method, device and equipment for predicting the residual shear strength of a rock joint and a readable storage medium, and the method comprises the steps: obtaining influence factor parameters of the residual shear strength of the rock joint to be predicted through a three-dimensional laser scanner and an experiment; and inputting the influence factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the to-be-predicted rock. By means of the method, the effect of accurately predicting the residual shear strength of the jointed rock can be achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of predicting the shear strength of rocks, and in particular, to a method, device, equipment and readable storage medium for predicting the residual shear strength of rock joints. Background Art

[0002] In the field of rock mechanics and engineering geology, rock mass is generally considered to have structural characteristics. It is well known that most rock engineering instability and failure are closely related to rock joints. The shear strength of joints is an important parameter that needs to be considered in joints. Therefore, accurately evaluating and predicting the shear strength of joints has always been a hot issue in geotechnical engineering. In past studies, researchers have proposed a large number of theoretical models of joint shear strength based on shear tests. The focus is on peak shear strength, and the prediction of shear strength can only be achieved through simple data and models.

[0003] However, the current prediction model for the residual shear strength of jointed rock has limitations: the model takes fewer factors into consideration; the data set used to train the model is relatively limited, resulting in inaccurate final prediction of the residual shear strength of jointed rock.

[0004] Therefore, how to accurately predict the residual shear strength of jointed rock is a technical problem that needs to be solved. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method for predicting the residual shear strength of rock joints. The technical solution of the embodiments of the present application can achieve the effect of accurately predicting the residual shear strength of jointed rock.

[0006] In a first aspect, an embodiment of the present application provides a method for predicting the residual shear strength of rock joints, comprising: obtaining parameters of influencing factors of the residual shear strength of rock joints to be predicted through a three-dimensional laser scanner and experiments, wherein the influencing factor parameters include: sampling interval, joint surface roughness parameters, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the rock to be predicted; inputting the influencing factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, wherein the residual shear strength prediction model is obtained by training a basic machine learning model with multiple factor parameters corresponding to multiple rocks, and the multiple factor parameters include obtaining a three-dimensional morphology point cloud data set of structural surfaces of multiple rocks through a three-dimensional laser scanner, and performing data processing on the three-dimensional morphology point cloud data set of the structural surfaces through a related program to obtain multiple joint surface roughness parameters, as well as sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks obtained through experiments.

[0007] In the above-mentioned embodiment of the present application, more factors affecting the residual shear strength of rock are obtained through three-dimensional laser scanners and experiments to train the basic machine model, so that the mapping relationship between different factor parameters and rock shear strength can be quickly constructed. The residual shear strength prediction model obtained through training can accurately predict the residual shear strength of jointed rock by processing the influencing factor parameters.

[0008] In some embodiments, before obtaining the parameters of influencing factors of the residual shear strength of rock joints to be predicted through a three-dimensional laser scanner and experiments, it also includes: obtaining a three-dimensional morphology point cloud data set of structural surfaces of multiple rocks through a three-dimensional laser scanner, and processing the three-dimensional morphology point cloud data set of structural surfaces through relevant programs to obtain multiple joint surface roughness parameters; obtaining the sampling interval, uniaxial tensile strength, and normal pressure of multiple rocks through Brazilian splitting experiments; obtaining the sampling interval, uniaxial tensile strength, and normal pressure of multiple rocks through Brazilian splitting experiments; obtaining the uniaxial compressive strength of multiple rocks through uniaxial compression tests; obtaining the cohesion and internal friction angle of multiple rocks through triaxial tests; training a basic machine learning model through multiple joint surface roughness parameters and the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle, and joint size of multiple rocks to obtain a residual shear strength prediction model, wherein the basic machine learning model includes a deep learning neural network and multiple functions.

[0009] In the above embodiments of the present application, more factors affecting the residual shear strength of rock are obtained through three-dimensional laser scanners and experiments to train the neural network and functions of the basic machine model, so as to obtain a residual shear strength prediction model covering multiple factors. The residual shear strength prediction model can accurately predict the shear strength of rock.

[0010] In some embodiments, after obtaining the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks through experiments, it also includes: constructing a nonlinear mapping relationship between multiple factor parameters corresponding to the multiple rocks and the residual shear strength of the joint surface; inputting the influencing factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, including: matching the residual shear strength corresponding to the influencing factor parameters through the nonlinear mapping relationship in the residual shear strength prediction model.

[0011] In the above embodiments of the present application, the residual shear strength prediction model established by machine learning may not rely on a priori assumptions like the prior art, and the specific expression form of the model may be determined in advance, and a complex nonlinear mapping between the residual shear strength of the joint surface and multiple factor parameters may be directly constructed. Therefore, the residual shear strength prediction model established by the machine learning model has higher precision and accuracy.

[0012] In some embodiments, parameters of influencing factors of the residual shear strength of rock joints to be predicted are obtained through a three-dimensional laser scanner and experiments, including: obtaining a three-dimensional morphology point cloud dataset of the structural surface of the rock to be predicted through a three-dimensional laser scanner, and processing the three-dimensional morphology point cloud dataset of the structural surface through a related program to obtain joint surface roughness parameters; obtaining the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the rock to be predicted through experiments.

[0013] In the above-mentioned embodiments of the present application, the influencing factor parameters of the rock to be predicted can be obtained through a three-dimensional laser scanner and experiments, and then the shear strength of the rock to be predicted can be accurately predicted based on the influencing factor parameters.

[0014] In a second aspect, an embodiment of the present application provides a device for predicting the residual shear strength of rock joints, comprising:

[0015] An acquisition module is used to acquire the influencing factor parameters of the residual shear strength of the rock joints to be predicted through a three-dimensional laser scanner and experiments, wherein the influencing factor parameters include: sampling interval of the rock to be predicted, joint surface roughness parameter, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size;

[0016] The prediction module is used to input the influencing factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, wherein the residual shear strength prediction model is obtained by training a basic machine learning model with multiple factor parameters corresponding to multiple rocks, and the multiple factor parameters include a three-dimensional morphological point cloud data set of structural surfaces of multiple rocks obtained by a three-dimensional laser scanner, and a plurality of joint surface roughness parameters obtained by data processing the three-dimensional morphological point cloud data set of the structural surface through a related program, as well as the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks obtained through experiments.

[0017] Optionally, the device further comprises:

[0018] The training module is used for obtaining the parameters of the influencing factors of the residual shear strength of the rock joints to be predicted by the acquisition module through the three-dimensional laser scanner and the experiment, obtaining the three-dimensional morphology point cloud data set of the structural surface of multiple rocks through the three-dimensional laser scanner, and performing data processing on the three-dimensional morphology point cloud data set of the structural surface through the relevant program to obtain multiple joint surface roughness parameters;

[0019] The sampling interval, uniaxial tensile strength, and normal pressure of multiple rocks were experimentally obtained through Brazilian splitting tests;

[0020] The sampling interval, uniaxial tensile strength, and normal pressure of multiple rocks were obtained through Brazilian splitting experiments;

[0021] The uniaxial compressive strength of multiple rocks can be obtained through uniaxial compression test; the cohesion and internal friction angle of multiple rocks can be obtained through triaxial test;

[0022] The basic machine learning model is trained by multiple joint surface roughness parameters and multiple rock sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size to obtain a residual shear strength prediction model, where the basic machine learning model includes a deep learning neural network and multiple functions.

[0023] Optionally, the device further comprises:

[0024] A construction module is used for constructing a nonlinear mapping relationship between multiple factor parameters corresponding to multiple rocks and residual shear strength of joint surfaces after the training module obtains sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks through experiments;

[0025] The prediction module is specifically used for:

[0026] The residual shear strength corresponding to the influencing factor parameters is matched through the nonlinear mapping relationship in the residual shear strength prediction model.

[0027] Optionally, the acquisition module is specifically used to:

[0028] The three-dimensional morphology point cloud data set of the structure surface of the rock to be predicted is obtained by a three-dimensional laser scanner, and the three-dimensional morphology point cloud data set of the structure surface is processed by a related program to obtain the roughness parameters of the joint surface;

[0029] Obtaining the sampling interval, uniaxial tensile strength, and normal pressure of the plurality of rocks through a Brazilian splitting test;

[0030] The uniaxial compressive strength of rock is obtained through uniaxial compression test;

[0031] Through triaxial tests, the Mohr strength envelope can be obtained, and the stress circle envelope can be solved to obtain the cohesion and internal friction angle of the rock.

[0032] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect are performed.

[0033] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0034] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A flow chart of a method for predicting the residual shear strength of rock joints provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of the prediction results of a ten-fold cross-validation residual shear strength prediction model provided in an embodiment of the present application;

[0038] Figure 3 A comparison chart of the experimental value and the predicted value of the residual shear strength provided in an embodiment of the present application;

[0039] Figure 4 A schematic block diagram of a device for predicting the residual shear strength of rock joints provided in an embodiment of the present application;

[0040] Figure 5 A schematic block diagram of the structure of a device for predicting the residual shear strength of rock joints provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0042] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0043] First, some terms involved in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0044] Rock shear strength: refers to the maximum shear stress that a rock can withstand when it is destroyed under shear load. Rock shear strength is divided into rock direct shear strength and rock triaxial shear strength according to different test methods. Rock direct shear strength is divided into shear strength and shear (friction) strength. Shear strength refers to the strength of rock when it is destroyed by shear, and shear (friction) strength refers to the shear strength of rock after it is sheared and subjected to friction test.

[0045] RBF in RBF neural network is the abbreviation of Radial Basis Function. Radial basis function is a type of function commonly used in machine learning and pattern recognition, and they are usually used to build nonlinear models.

[0046] Svr: (support vector regression) is the abbreviation of support vector regression, which is a machine learning algorithm used for regression analysis.

[0047] The Brazilian splitting test is a static mechanics test method, which is mainly used to determine the fracture strength and fracture toughness of materials such as rocks and concrete.

[0048] The uniaxial compression test is a common experimental method used to determine the strength and deformation characteristics of materials such as rock and concrete under a single axial load.

[0049] The triaxial test is an experimental method used to determine the mechanical properties of rocks, especially to evaluate the strength and deformation characteristics of rocks under complex stress states.

[0050] Barton-Bandis structural surface model module The Barton-Bandis model is obtained based on a large number of indoor / in-situ tests, and its description of the normal / tangential deformation and strength characteristics of the structural surface is more complete and accurate.

[0051] The present application is applied to the scenario of predicting the shear strength of rock. The specific scenario is to construct a complex nonlinear mapping of factor parameters affecting the shear strength of rock and the shear strength by training a machine learning model. The model obtained through training accurately predicts the residual shear strength of the rock to be predicted.

[0052] In the field of rock mechanics and engineering geology, rock masses are generally considered to have structural characteristics. It is well known that most rock engineering instabilities and failures are closely related to rock joints. The shear strength of joints is an important parameter that needs to be considered in joints. Therefore, accurately evaluating and predicting the shear strength of joints has always been a hot issue in geotechnical engineering. In past studies, researchers have proposed a large number of theoretical models of joint shear strength based on shear tests. The focus is on peak shear strength, and the prediction of shear strength can only be achieved through simple data and models. However, the current residual shear strength prediction model of jointed rock has limitations: the model considers fewer factors; the data set used to train the model is relatively limited, resulting in the final prediction of the residual shear strength of jointed rock is not accurate enough.

[0053] To this end, the present application obtains the influencing factor parameters of the residual shear strength of the rock joints to be predicted through a three-dimensional laser scanner and experiments, wherein the influencing factor parameters include: the sampling interval of the rock to be predicted, the joint surface roughness parameters, the uniaxial tensile strength, the uniaxial compressive strength, the normal pressure, the cohesion, the internal friction angle and the joint size; the influencing factor parameters are input into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, wherein the residual shear strength prediction model is obtained by training a basic machine learning model with multiple factor parameters corresponding to multiple rocks, and the multiple factor parameters include obtaining a three-dimensional morphology point cloud data set of the structural surfaces of multiple rocks through a three-dimensional laser scanner, and performing data processing on the three-dimensional morphology point cloud data set of the structural surfaces through relevant programs to obtain multiple joint surface roughness parameters, and obtaining the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks through a Brazilian splitting experiment. By using 3D laser scanners and experiments to obtain more factors that affect the residual shear strength of rock and train the basic machine model, the mapping relationship between different factor parameters and rock shear strength can be quickly constructed. The residual shear strength prediction model obtained through training can accurately predict the residual shear strength of jointed rock by processing the influencing factor parameters.

[0054] In the embodiment of the present application, the executing entity may be a device for predicting the residual shear strength of rock joints in a system for predicting the residual shear strength of rock joints. In actual applications, the device for predicting the residual shear strength of rock joints may be electronic devices such as terminal devices and servers, which are not limited here.

[0055] Combine the following Figure 1 The method for predicting the residual shear strength of rock joints in an embodiment of the present application is described in detail.

[0056] Please see Figure 1 , Figure 1 A flowchart of a method for predicting the residual shear strength of rock joints provided in an embodiment of the present application is shown in FIG. Figure 1 The methods shown for predicting the residual shear strength of rock joints include:

[0057] Step 110: Obtain the influencing factor parameters of the residual shear strength of the rock joints to be predicted through a three-dimensional laser scanner and experiments.

[0058] Among them, the influencing factor parameters include: sampling interval of the rock to be predicted, joint surface roughness parameters, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size.

[0059] In some embodiments of the present application, before obtaining the parameters of influencing factors of the residual shear strength of rock joints to be predicted through a three-dimensional laser scanner and experiments, it also includes: obtaining a three-dimensional morphology point cloud data set of structural surfaces of multiple rocks through a three-dimensional laser scanner, and performing data processing on the three-dimensional morphology point cloud data set of structural surfaces through relevant programs to obtain multiple joint surface roughness parameters; obtaining the sampling interval, uniaxial tensile strength, and normal pressure of multiple rocks through Brazilian splitting experiments; obtaining the sampling interval, uniaxial tensile strength, and normal pressure of multiple rocks through Brazilian splitting experiments; obtaining the uniaxial compressive strength of multiple rocks through uniaxial compression tests; and obtaining the cohesion and internal friction angle of multiple rocks through triaxial tests; training a basic machine learning model through multiple joint surface roughness parameters and the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle, and joint size of multiple rocks to obtain a residual shear strength prediction model, wherein the basic machine learning model includes a deep learning neural network and multiple functions.

[0060] In the above process, the present application obtains more factors affecting the residual shear strength of rock through three-dimensional laser scanners and experiments to train the neural network and functions of the basic machine model, and can obtain a residual shear strength prediction model covering multiple factors. The residual shear strength prediction model can accurately predict the shear strength of rock.

[0061] Among them, a three-dimensional morphological point cloud data set of structural surfaces of multiple rocks is obtained by a three-dimensional laser scanner, and the three-dimensional morphological point cloud data set of structural surfaces is processed through relevant programs to obtain multiple joint surface roughness parameters. I include: obtaining a three-dimensional morphological point cloud data set of structural surfaces through a three-dimensional laser scanner, and obtaining multiple joint surface roughness parameters through relevant programs (MATLAB program, i.e. commercial mathematical software).

[0062] Optionally, the basic machine learning model is trained by multiple joint surface roughness parameters and sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks to obtain a residual shear strength prediction model, including obtaining different parameter combinations of multiple joint surface roughness parameters and sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks and the corresponding rock shear strength, and constructing a mapping relationship between the parameter combination and the rock shear strength, inputting multiple joint surface roughness parameters and sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks into the basic machine learning model to obtain an output result, determining the difference between the output result and the expected output result and adjusting multiple functions and neural networks in the basic machine learning model until the difference between the output result and the expected output result is less than a preset value, and the preset value can be set according to demand.

[0063] Among them, multiple functions and neural networks include linear, polynomial and radial basis function (RBF), support vector regression (SVR), and deep learning. The basic machine model can include multiple models, for example, three models that rely on different kernel functions and a deep learning model. Different kernel functions include linear, polynomial and radial basis function (RBF) support vector regression (SVR).

[0064] In some embodiments of the present application, after obtaining the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks through the Brazilian splitting test, it also includes: constructing a nonlinear mapping relationship between multiple factor parameters corresponding to the multiple rocks and the residual shear strength of the joint surface; inputting the influencing factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, including: matching the residual shear strength corresponding to the influencing factor parameters through the nonlinear mapping relationship in the residual shear strength prediction model.

[0065] In the above process of the present application, the residual shear strength prediction model established by machine learning can determine the specific expression form of the model in advance, unlike the prior art, and directly construct a complex nonlinear mapping between the residual shear strength of the joint surface and multiple factor parameters. Therefore, the residual shear strength prediction model established by the machine learning model has higher precision and accuracy.

[0066] Among them, the nonlinear mapping relationship between multiple factor parameters and the residual shear strength of the joint surface includes the mapping relationship between different combinations of some or multiple factor parameters in the multiple factors and the corresponding residual shear strength. When the residual shear strength prediction model obtains the input factor parameters, the corresponding shear strength can be quickly matched through the constructed mapping relationship.

[0067] Optionally, after the basic machine learning model is trained by using multiple joint surface roughness parameters and multiple rock sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size to obtain the residual shear strength prediction model, it also includes:

[0068] The prediction results of the residual shear strength prediction model are verified by the cross-validation algorithm. For example, the prediction results of the model trained by the 10-fold cross-validation algorithm are used for verification, that is, the training set is further subdivided into 10 subsets without duplication, 9 of which are used as training subsets and the remaining one is used as a validation subset. The accuracy of the model is measured by calculating the average error of the 10 test sets. When the accuracy does not reach the preset threshold, the residual shear strength prediction model is retrained until the preset threshold is reached. The preset threshold can be set according to demand.

[0069] Specifically, the prediction results of the model trained by the 10-fold cross-validation algorithm can be verified by Figure 2 Schematic implementation of ten-fold cross validation is shown.

[0070] Please see Figure 2 , Figure 2 A schematic diagram of the prediction results of a ten-fold cross-validation residual shear strength prediction model provided in this application includes:

[0071] A dataset of rock influencing factors was obtained through 3D laser scanning and experiments. The dataset was divided into 10 parts on average. Ten rounds of cyclic verification and training were carried out. The 10 datasets were divided into 1 verification set and 1 dataset. Training and verification were carried out in each round. Finally, the error of each round was counted, and the average error of the ten rounds was calculated.

[0072] Specifically, the constructed influencing factor data set can be obtained through the following Table 1:

[0073] Table 1

[0074]

[0075]

[0076] Among them, the sampling interval l, the joint surface roughness parameter Uniaxial tensile strengthσ t , uniaxial compressive strengthσ c , normal pressure σ n , cohesion c, internal friction angle Joint size L.

[0077] Optionally, the prediction results of the residual shear strength prediction model can be verified by cross-validation algorithm. Figure 3 The comparison chart of the experimental and predicted values ​​of the residual shear strength is obtained.

[0078] Please see Figure 3 , Figure 3 A comparison chart of the experimental value and the predicted value of the residual shear strength provided in this application includes samples corresponding to different sample numbers and the corresponding residual shear strengths.

[0079] Among them, it can be seen that the experimental residual shear strength test value is well consistent with the predicted value of the machine learning model used in the present invention. This shows that the prediction result of the residual shear strength prediction model is highly reliable. The specific verification method can be obtained by the following formula:

[0080]

[0081] Among them, τ r is the residual shear strength, is the internal friction angle.

[0082] Optionally, the residual shear strength prediction model error results obtained through the machine learning model and deep learning network training of the present application can be shown in Table 2:

[0083] Table 2

[0084]

[0085] It can be seen that the table includes Barton type calculation results, three machine learning models (SVR model) and a deep learning model prediction results and experimental measured residual shear strength. The average estimation errors of the Barton model, three machine learning models and deep learning model are 19.3%, 8.8%, 8.2%, 7.9% and 5.56% respectively. The above models are effective in predicting the residual shear strength of natural rock structures. The residual shear strength prediction model constructed by the present invention is more accurate than the Barton model.

[0086] In some embodiments of the present application, parameters of influencing factors of the residual shear strength of rock joints to be predicted are obtained through a three-dimensional laser scanner and experiments, including: obtaining a three-dimensional morphology point cloud dataset of the structural surface of the rock to be predicted through a three-dimensional laser scanner, and processing the three-dimensional morphology point cloud dataset of the structural surface through a related program to obtain the joint surface roughness parameters; obtaining the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the rock to be predicted through a Brazilian splitting experiment.

[0087] In the above process, the present application can obtain the influencing factor parameters of the rock to be predicted through a three-dimensional laser scanner and a Brazilian splitting experiment, and then the shear strength of the rock to be predicted can be accurately predicted based on the influencing factor parameters.

[0088] Step 120: Input the influencing factor parameters into the preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted.

[0089] Among them, the residual shear strength prediction model is obtained by training the basic machine learning model with multiple factor parameters corresponding to multiple rocks. The multiple factor parameters include the three-dimensional morphology point cloud data set of the structural surfaces of multiple rocks obtained by a three-dimensional laser scanner, and the three-dimensional morphology point cloud data set of the structural surface obtained by data processing through relevant programs. The three-dimensional morphology point cloud data set of the structural surface is used to obtain multiple joint surface roughness parameters, and the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks are obtained through the Brazilian splitting test.

[0090] Optionally, the influencing factor parameters are input into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, including:

[0091] The complex mapping relationship between the influencing factor parameters and the residual shear strength stored in the residual shear strength prediction model is obtained, and the residual shear strength corresponding to the influencing factor parameters is matched through the mapping relationship.

[0092] In the above Figure 1In the process shown, the present application obtains the influencing factor parameters of the residual shear strength of the rock joints to be predicted through a three-dimensional laser scanner and experiments, wherein the influencing factor parameters include: the sampling interval of the rock to be predicted, the joint surface roughness parameters, the uniaxial tensile strength, the uniaxial compressive strength, the normal pressure, the cohesion, the internal friction angle and the joint size; the influencing factor parameters are input into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, wherein the residual shear strength prediction model is obtained by training a basic machine learning model with multiple factor parameters corresponding to multiple rocks, and the multiple factor parameters include obtaining a three-dimensional morphology point cloud data set of the structural surfaces of multiple rocks through a three-dimensional laser scanner, and performing data processing on the three-dimensional morphology point cloud data set of the structural surfaces through relevant programs to obtain multiple joint surface roughness parameters, and obtaining the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks through a Brazilian splitting experiment. By using 3D laser scanners and experiments to obtain more factors that affect the residual shear strength of rock and train the basic machine model, the mapping relationship between different factor parameters and rock shear strength can be quickly constructed. The residual shear strength prediction model obtained through training can accurately predict the residual shear strength of jointed rock by processing the influencing factor parameters.

[0093] Previous article Figure 1-Figure 3 A method for predicting the residual shear strength of rock joints is described below. Figure 4-Figure 5 Describe the apparatus for predicting the residual shear strength of rock joints.

[0094] Please refer to Figure 4 , is a schematic block diagram of a device 400 for predicting the residual shear strength of rock joints provided in an embodiment of the present application. The device 400 may be a module, program segment or code on an electronic device. The device 400 is similar to the above Figure 1 The method embodiment corresponds to and can be executed Figure 1 The various steps involved in the method embodiment and the specific functions of the device 400 can be found in the description below. To avoid repetition, the detailed description is appropriately omitted here.

[0095] Optionally, the device 400 includes:

[0096] The acquisition module 410 is used to acquire the influencing factor parameters of the residual shear strength of the rock joints to be predicted through a three-dimensional laser scanner and experiments, wherein the influencing factor parameters include: sampling interval of the rock to be predicted, joint surface roughness parameter, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size;

[0097] Prediction module 420 is used to input the influencing factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, wherein the residual shear strength prediction model is obtained by training a basic machine learning model with multiple factor parameters corresponding to multiple rocks, and the multiple factor parameters include a three-dimensional morphology point cloud data set of structural surfaces of multiple rocks obtained by a three-dimensional laser scanner, and a plurality of joint surface roughness parameters obtained by data processing the three-dimensional morphology point cloud data set of the structural surface through a related program, and a sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks obtained through a Brazilian splitting test.

[0098] Optionally, the device further comprises:

[0099] A training module is used for obtaining module 410, before obtaining the parameters of the influencing factors of the residual shear strength of the rock joints to be predicted through a three-dimensional laser scanner and experiments, obtaining a three-dimensional morphology point cloud data set of the structural surfaces of multiple rocks through a three-dimensional laser scanner, and processing the three-dimensional morphology point cloud data set of the structural surfaces through relevant programs to obtain multiple joint surface roughness parameters; obtaining the sampling interval, uniaxial tensile strength, and normal pressure of multiple rocks through Brazilian splitting experiments; obtaining the sampling interval, uniaxial tensile strength, and normal pressure of multiple rocks through Brazilian splitting experiments; obtaining the uniaxial compressive strength of multiple rocks through uniaxial compression tests; obtaining the cohesion and internal friction angle of multiple rocks through triaxial tests; training a basic machine learning model through multiple joint surface roughness parameters and the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle, and joint size of multiple rocks to obtain a residual shear strength prediction model, wherein the basic machine learning model includes a deep learning neural network and multiple functions.

[0100] Optionally, the device further comprises:

[0101] A construction module is used for training a module to construct a nonlinear mapping relationship between multiple factor parameters corresponding to multiple rocks and residual shear strength of joint surfaces after obtaining sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks through Brazilian splitting experiments;

[0102] The prediction module 420 is specifically used for:

[0103] The residual shear strength corresponding to the influencing factor parameters is matched through the nonlinear mapping relationship in the residual shear strength prediction model.

[0104] Optionally, the acquisition module 410 is specifically used for:

[0105] The three-dimensional morphology point cloud dataset of the structural surface of the rock to be predicted is obtained by a three-dimensional laser scanner, and the three-dimensional morphology point cloud dataset of the structural surface is processed through relevant programs to obtain the roughness parameters of the joint surface; the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the rock to be predicted are obtained through the Brazilian splitting test.

[0106] Please refer to Figure 5 1 is a schematic block diagram of a device for predicting the residual shear strength of rock joints provided in an embodiment of the present application. The device may include a memory 510 and a processor 520. Optionally, the device may also include: a communication interface 530 and a communication bus 540. The device and the above Figure 1 The method embodiment corresponds to and can be executed Figure 1 The various steps involved in the method embodiment and the specific functions of the device can be found in the description below.

[0107] Specifically, the memory 510 is used to store computer-readable instructions.

[0108] Processor 520, configured to process readable instructions stored in the memory, capable of executing Figure 1 The steps in the method.

[0109] The communication interface 530 is used for signaling or data communication with other node devices, for example, for communication with a server or a terminal, or for communication with other device nodes, but the embodiments of the present application are not limited thereto.

[0110] The communication bus 540 is used to realize direct connection and communication among the above components.

[0111] The communication interface 530 of the device in the embodiment of the present application is used to communicate signals or data with other node devices. The memory 510 can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The memory 510 can also be at least one storage device located away from the aforementioned processor. The memory 510 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 520, the electronic device executes the aforementioned Figure 1The method process shown. The processor 520 can be used on the device 400 and used to perform the functions in the present application. Exemplarily, the above-mentioned processor 520 can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and the embodiments of the present application are not limited thereto.

[0112] The embodiment of the present application also provides a readable storage medium, when the computer program is executed by a processor, Figure 1 The method process in the method embodiment shown is executed by the electronic device.

[0113] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0114] In summary, the embodiment of the present application provides a method, device, electronic device and readable storage medium for predicting the residual shear strength of rock joints, the method comprising: obtaining the influencing factor parameters of the residual shear strength of rock joints to be predicted through a three-dimensional laser scanner and an experiment, wherein the influencing factor parameters include: the sampling interval of the rock to be predicted, the roughness parameter of the joint surface, the uniaxial tensile strength, the uniaxial compressive strength, the normal pressure, the cohesion, the internal friction angle and the joint size; inputting the influencing factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, wherein the residual shear strength prediction model is obtained by training a basic machine learning model with multiple factor parameters corresponding to multiple rocks, and the multiple factor parameters include obtaining a three-dimensional morphology point cloud data set of the structural surface of multiple rocks through a three-dimensional laser scanner, and processing the three-dimensional morphology point cloud data set of the structural surface through a related program to obtain multiple joint surface roughness parameters and obtaining the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of multiple rocks through a Brazilian splitting experiment. Through this method, the effect of accurately predicting the residual shear strength of jointed rock can be achieved.

[0115] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0116] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0117] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0118] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0119] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0120] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for predicting the residual shear strength of rock joints, characterized in that: include: Obtaining the influencing factor parameters of the residual shear strength of the rock joints to be predicted by a three-dimensional laser scanner and experiments, wherein the influencing factor parameters include: the sampling interval of the rock to be predicted, the roughness parameter of the joint surface, the uniaxial tensile strength, the uniaxial compressive strength, the normal pressure, the cohesion, the internal friction angle and the joint size; The influencing factor parameters are input into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, wherein the residual shear strength prediction model is obtained by training a basic machine learning model with multiple factor parameters corresponding to multiple rocks, and the multiple factor parameters include a three-dimensional morphology point cloud data set of structural surfaces of the multiple rocks obtained by a three-dimensional laser scanner, and a plurality of joint surface roughness parameters obtained by processing the three-dimensional morphology point cloud data set of the structural surface through a related program, as well as the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the multiple rocks obtained through experiments.

2. The method according to claim 1, characterized in that: Before obtaining the influencing factor parameters of the residual shear strength of rock joints to be predicted by means of a three-dimensional laser scanner and experiments, the method further includes: Acquiring the three-dimensional topography point cloud data set of the structural surfaces of the multiple rocks by means of a three-dimensional laser scanner, and performing data processing on the three-dimensional topography point cloud data set of the structural surfaces by means of the relevant program to obtain the multiple joint surface roughness parameters; The experiment is used to obtain the sampling interval, uniaxial tensile strength, and normal pressure of the plurality of rocks through a Brazilian splitting test; Obtaining the sampling interval, uniaxial tensile strength, and normal pressure of the plurality of rocks through a Brazilian splitting test; Obtaining the uniaxial compressive strength of the plurality of rocks through a uniaxial compression test; The cohesion and internal friction angle of the rock can be obtained through triaxial test; The basic machine learning model is trained by the multiple joint surface roughness parameters and the sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the multiple rocks to obtain the residual shear strength prediction model, wherein the basic machine learning model includes a deep learning neural network and multiple functions.

3. The method according to claim 2, characterized in that After obtaining the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the plurality of rocks through the experiment, the method further includes: Constructing a nonlinear mapping relationship between a plurality of factor parameters corresponding to the plurality of rocks and the residual shear strength of the joint surface; The step of inputting the influencing factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted includes: The residual shear strength corresponding to the influencing factor parameters is matched through the nonlinear mapping relationship in the residual shear strength prediction model.

4. The method according to any one of claims 1 to 3, characterized in that: The parameters of influencing factors of the residual shear strength of rock joints to be predicted are obtained by three-dimensional laser scanner and experiment, including: Acquiring the three-dimensional topographic point cloud data set of the structural surface of the rock to be predicted by a three-dimensional laser scanner, and performing data processing on the three-dimensional topographic point cloud data set of the structural surface by the relevant program to obtain the roughness parameter of the joint surface; Obtaining the sampling interval, uniaxial tensile strength, and normal pressure of the plurality of rocks through a Brazilian splitting test; The uniaxial compressive strength of rock is obtained through uniaxial compression test; Through triaxial tests, the Mohr strength envelope can be obtained, and the stress circle envelope can be solved to obtain the cohesion and internal friction angle of the rock.

5. A device for predicting the residual shear strength of rock joints, characterized in that: include: An acquisition module is used to acquire the influencing factor parameters of the residual shear strength of the rock joints to be predicted through a three-dimensional laser scanner and experiments, wherein the influencing factor parameters include: the sampling interval of the rock to be predicted, the joint surface roughness parameter, the uniaxial tensile strength, the uniaxial compressive strength, the normal pressure, the cohesion, the internal friction angle and the joint size; A prediction module is used to input the influencing factor parameters into a preset residual shear strength prediction model to obtain the residual shear strength of the rock to be predicted, wherein the residual shear strength prediction model is obtained by training a basic machine learning model with multiple factor parameters corresponding to multiple rocks, and the multiple factor parameters include a three-dimensional morphology point cloud data set of structural surfaces of the multiple rocks obtained by a three-dimensional laser scanner, and a plurality of joint surface roughness parameters obtained by data processing the three-dimensional morphology point cloud data set of the structural surface through a related program, as well as a sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the multiple rocks obtained through experiments.

6. The device according to claim 5, characterized in that The device also includes: A training module, used for the acquisition module to acquire the three-dimensional morphology point cloud data set of the structural surfaces of the multiple rocks by a three-dimensional laser scanner before acquiring the influencing factor parameters of the residual shear strength of the rock joints to be predicted by a three-dimensional laser scanner and an experiment, and to perform data processing on the three-dimensional morphology point cloud data set of the structural surfaces by the relevant program to obtain the multiple joint surface roughness parameters; The experiment is used to obtain the sampling interval, uniaxial tensile strength, and normal pressure of the plurality of rocks through a Brazilian splitting test; Obtaining the sampling interval, uniaxial tensile strength, and normal pressure of the plurality of rocks through a Brazilian splitting test; Obtaining the uniaxial compressive strength of the plurality of rocks through a uniaxial compression test; The cohesion and internal friction angle of the rock can be obtained through triaxial test; The basic machine learning model is trained by the multiple joint surface roughness parameters and the sampling intervals, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the multiple rocks to obtain the residual shear strength prediction model, wherein the basic machine learning model includes a deep learning neural network and multiple functions.

7. The device according to claim 6, characterized in that The device also includes: A construction module, used for the training module to construct a nonlinear mapping relationship between a plurality of factor parameters corresponding to the plurality of rocks and residual shear strength of joint surfaces after the sampling interval, uniaxial tensile strength, uniaxial compressive strength, normal pressure, cohesion, internal friction angle and joint size of the plurality of rocks are obtained through the experiment; The prediction module is specifically used for: The residual shear strength corresponding to the influencing factor parameters is matched through the nonlinear mapping relationship in the residual shear strength prediction model.

8. The device according to any one of claims 5 to 7, characterized in that: The acquisition module is specifically used for: Acquiring the three-dimensional topographic point cloud data set of the structural surface of the rock to be predicted by a three-dimensional laser scanner, and performing data processing on the three-dimensional topographic point cloud data set of the structural surface by the relevant program to obtain the roughness parameter of the joint surface; Obtaining the sampling interval, uniaxial tensile strength, and normal pressure of the plurality of rocks through a Brazilian splitting test; The uniaxial compressive strength of rock is obtained through uniaxial compression test; Through triaxial tests, the Mohr strength envelope can be obtained, and the stress circle envelope can be solved to obtain the cohesion and internal friction angle of the rock.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 4 are executed.

10. A computer-readable storage medium, characterized in that: include: A computer program, when the computer program is run on a computer, causes the computer to execute the method according to any one of claims 1 to 4.

Citation Information

Patent Citations

  • Computing method for representative elementary volume of jointed rock

    CN103197042A

  • Method, device and equipment for predicting peak shear strength of rock joint and readable storage medium

    CN119026407A

Cited By

  • Joint residual shear strength quantification method, device and equipment and storage medium

    CN120297167A

  • A method, device, equipment and storage medium for quantifying residual shear strength of joints

    CN120297167B

  • Rock shear strength prediction method and system based on improved machine learning algorithm

    CN120409262A

  • A Method and System for Predicting Rock Shear Strength Based on Improved Machine Learning Algorithm

    CN120409262B