Simulation method of rock and soil strength change during engineering disasters and grouting reinforcement

By combining machine learning with DEM models, the problems of long parameter calibration time and poor universality in DEM software for soil and rock strength simulation are solved, and efficient and accurate simulation of soil and rock strength changes is achieved.

CN113722981BActive Publication Date: 2024-11-29SHANDONG UNIV

Patent Information

Application Number
CN202110901713.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-06
Publication Date
2024-11-29
Estimated Expiration
2041-08-06

AI Technical Summary

Technical Problem

Existing DEM software requires extensive parameter calibration during the simulation of soil and rock strength evolution, which is time-consuming and lacks universality, making it difficult to adapt to the simulation needs of different soil and rock masses.

Method used

A DEM model is established using machine learning methods. By acquiring data on the changes in macroscopic mechanical parameters of soil and rock, the microscopic mechanical parameters are predicted, and the DEM contact strength evolution model is embedded to achieve a realistic simulation of the strength changes of soil and rock.

Benefits of technology

It improves the accuracy of simulating changes in soil and rock strength, enabling it to more realistically reflect the evolution of soil and rock strength, and reducing the workload and time required for parameter calibration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113722981B_ABST
    Figure CN113722981B_ABST
Patent Text Reader

Abstract

The present disclosure provides a method for simulating the strength change of rock and soil during engineering disasters and grouting reinforcement, and obtains the data of the macroscopic mechanical parameters of the rock and soil sample to be tested during the engineering disasters and grouting reinforcement over time; obtains the data of the microscopic mechanical parameters of the rock and soil sample to be tested over time based on the data of the macroscopic mechanical parameters over time and a preset machine learning model; obtains the simulation results of the strength change of rock and soil during engineering disasters and grouting reinforcement based on the data of the microscopic mechanical parameters over time and a preset DEM calculation model; The present disclosure provides a DEM simulation calculation method for the strength evolution during engineering rock disasters and grouting reinforcement, so that the DEM model can more realistically reflect the strength evolution law of the rock and soil, and greatly improves the accuracy of the simulation results of the strength change of the rock and soil.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of rock and soil strength simulation, and in particular to a method for simulating rock and soil strength changes during engineering disasters and grouting reinforcement. Background Art

[0002] The statements in this section merely provide background art related to the present disclosure and do not necessarily constitute prior art.

[0003] The strength of the surrounding rock of underground engineering directly affects the safety and stability of the project. Factors such as weathering, earthquake action, and construction disturbance can cause surrounding rock deterioration, fragmentation, and an increase in through cracks, thereby reducing the strength of the surrounding rock. On the contrary, surrounding rock reinforcement technologies such as grouting reinforcement and anchor reinforcement can improve the integrity of the surrounding rock by filling cracks and connecting discontinuous rock masses, thereby increasing the strength of the surrounding rock. In the process of underground engineering disaster evolution, the reduction in the strength of the rock and soil mass will breed unfavorable geological bodies that are extremely prone to induce disasters, and ultimately cause a series of engineering disasters such as tunnel entrance landslides, tunnel collapses, and sudden water inrush, causing significant casualties, economic losses, and project delays. In the process of engineering disaster prevention and control, grouting and other reinforcement technologies effectively reduce the risk of disasters induced by faults, broken zones, and other disaster-causing structures from the perspective of improving the strength of the surrounding rock, ensuring the safety of underground engineering construction. Therefore, studying the strength evolution process of the rock and soil mass is the key to revealing the mechanism of engineering disasters and the mechanism of grouting reinforcement.

[0004] At present, in addition to traditional theoretical analysis, numerical simulation methods are widely used in the study of rock and soil strength evolution. Among them, the basic idea of ​​discrete element method (DEM) is to regard the medium as composed of a series of discrete particles. The particles follow Newton's second law, are good at dealing with non-continuous problems, and have the characteristics of being able to calculate rock fracture and large rock deformation. Therefore, it has great advantages in analyzing geotechnical engineering problems.

[0005] At present, a series of simulations of rock and soil weakening during disaster evolution and grouting reinforcement during disaster prevention and control have been carried out based on various DEM software, and a method of multiple parameter calibration has been proposed. By continuously adjusting the micromechanical parameters of the DEM model during the simulation process, the changes can be controlled. However, this method requires a lot of parameter calibration work for each simulation, and a set of calibrated parameters can only be used to simulate specific rock and soil bodies, which is time-consuming and has poor universality. Summary of the invention

[0006] In order to address the deficiencies of the prior art, the present disclosure provides a method for simulating the strength changes of rock and soil during engineering disasters and grouting reinforcement, and provides a DEM simulation calculation method for the strength evolution during engineering rock disasters and grouting reinforcement, so that the DEM model can truly reflect the strength evolution law of the rock and soil.

[0007] In order to achieve the above objectives, the present disclosure adopts the following technical solutions:

[0008] A first aspect of the present disclosure provides a method for simulating changes in rock and soil strength during engineering disasters and grouting reinforcement.

[0009] A method for simulating the strength change of rock and soil during engineering disasters and grouting reinforcement includes the following processes:

[0010] Obtain the time-varying data of the macroscopic mechanical parameters of the rock and soil samples to be tested during the engineering disaster and grouting reinforcement process;

[0011] According to the macroscopic mechanical parameter variation data over time and the preset machine learning model, the microscopic mechanical parameter variation data of the rock and soil sample to be tested over time is obtained;

[0012] According to the data of micromechanical parameters changing with time and the preset DEM calculation model, the simulation results of rock and soil strength change during engineering disasters and grouting reinforcement are obtained.

[0013] Furthermore, the data of each micro-parameter changing with time are embedded into the existing particle contact model to obtain the DEM contact strength evolution model, and the DEM contact strength evolution model is embedded in the DEM calculation model to perform numerical simulation of rock and soil strength changes.

[0014] Furthermore, the particle contact model is a contact bonding model.

[0015] Furthermore, the particle contact model is a parallel bonding model.

[0016] Furthermore, the macroscopic mechanical parameters at least include elastic modulus, Poisson's ratio, compressive strength, internal friction angle and cohesion of the rock and soil specimen.

[0017] Furthermore, the micromechanical parameters at least include the particle effective modulus, particle density, bond effective modulus and bond strength of the rock and soil sample.

[0018] Furthermore, the data of micromechanical parameter variations over time are functional expressions of each microscopic parameter over time.

[0019] A second aspect of the present disclosure provides a method for simulating changes in rock and soil strength during engineering disasters and grouting reinforcement.

[0020] A method for simulating the strength change of rock and soil during engineering disasters and grouting reinforcement, comprising:

[0021] The data acquisition module is configured to: acquire the data of macroscopic mechanical parameters of the rock and soil sample to be tested changing with time during the engineering disaster and grouting reinforcement process;

[0022] The data processing module is configured to: obtain the data of the micromechanical parameters of the rock and soil sample to be tested changing with time according to the data of the macromechanical parameters changing with time and the preset machine learning model;

[0023] The strength simulation module is configured to obtain the simulation results of the strength change of rock and soil during engineering disasters and grouting reinforcement according to the data of micromechanical parameters changing with time and the preset DEM calculation model.

[0024] The third aspect of the present disclosure provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the method for simulating changes in rock and soil strength during engineering disasters and grouting reinforcement as described in the first aspect of the present disclosure.

[0025] The fourth aspect of the present disclosure provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for simulating changes in rock and soil strength during engineering disasters and grouting reinforcement as described in the first aspect of the present disclosure are implemented.

[0026] Compared with the prior art, the beneficial effects of the present invention are:

[0027] The simulation method, system, medium or electronic device disclosed in the present invention provides a DEM simulation calculation method for the strength evolution during engineering rock mass disasters and grouting reinforcement, so that the DEM model can more realistically reflect the strength evolution law of the rock mass, greatly improving the accuracy of the simulation results of the strength change of the rock mass. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0029] Figure 1 A flow chart of a rock and soil mass strength weakening simulation method provided in Example 1 of the present disclosure is disclosed.

[0030] Figure 2 A schematic diagram of the changing rules of macroscopic mechanical parameters of rock and soil during engineering disasters and grouting reinforcement provided by Example 1 of the present disclosure is disclosed.

[0031] Figure 3 A schematic diagram of the variation of the microscopic parameters of the DEM model during the evolution of the strength of the rock and soil mass provided in Example 1 of the present disclosure is disclosed. DETAILED DESCRIPTION

[0032] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0033] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0034] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0035] In the absence of conflict, the embodiments in the present disclosure and the features in the embodiments may be combined with each other.

[0036] Embodiment 1:

[0037] Embodiment 1 of the present disclosure provides a DEM rock and soil strength weakening simulation calculation method based on machine learning, and its specific process is as follows: Figure 1 As shown, the following steps are included:

[0038] S1: Establish a machine learning mesoscopic parameter calibration model.

[0039] S1.1: Establish a machine learning sample library.

[0040] Based on the DEM calculation method, a large number of numerical simulations of basic mechanical tests (uniaxial compression, Brazilian splitting test, etc.) were carried out, and the macro- and micro-mechanical parameters in the test were recorded. The parameters of each test are a set of samples. Based on the above parameter samples, a DEM macro- and micro-parameter calibration database was established as a learning sample for machine learning.

[0041] S1.2: Train the machine learning model.

[0042] A model for macro-micro parameter calibration was developed based on the XGBoost algorithm. The samples in the database established in step 1.1 were divided into two groups, of which 80% of the samples were used as training sets for the machine learning model to analyze and learn data features, and the remaining 20% ​​of the samples were used as test sets to verify the accuracy of the model learning results. The macroscopic mechanical parameters (elastic modulus, Poisson's ratio, compressive strength, internal friction angle, cohesion, etc.) in the training set were used as characteristic values, and the microscopic mechanical parameters (particle effective modulus, particle density, bonding effective modulus, bonding strength, etc.) were imported into the model as target values. The model training was completed by adjusting the number of regression trees K, the regression tree iteration step η, the regularization coefficients γ, λ and other parameters in the model.

[0043] S1.3: Verify model accuracy.

[0044] The macroscopic mechanical parameters in the test set are used as characteristic values ​​and imported into the parameter calibration model established in S1.2. The model is run to predict the microscopic mechanical parameter values ​​and the evaluation index R is calculated. 2 , as shown in formula (1):

[0045]

[0046] Among them, y i is the actual value of the i-th test sample, is the i-th sample value predicted by the model, is the average of the actual values ​​of the test samples.

[0047] S1.4: Repeat the above steps until R 2 >0.95, and a machine learning model for mesoscopic parameter calibration was established.

[0048] S2: Obtain the evolution law of macroscopic strength of rock and soil.

[0049] The rock and soil mass of the required simulation area is obtained from the engineering site, and standard specimens for rock and soil mechanics tests are prepared. Multiple groups of indoor tests (such as penetration damage test, dynamic triaxial test, etc.) or model tests (such as model test of excavation process, model test of grouting process) are carried out to obtain rock and soil samples of different test time periods.

[0050] The rock and soil samples were re-sampled and subjected to triaxial compression and direct shear tests respectively. The mechanical parameters of the samples in each time period were measured, and then the change law of the macroscopic mechanical parameters of the rock and soil (such as macroscopic elastic modulus, macroscopic compressive strength, macroscopic shear strength, etc.) over time under the action of penetration damage, excavation disturbance, grouting reinforcement, etc. was obtained. Figure 2 .

[0051] S3: Get the DEM micro-parameter function expression.

[0052] The macroscopic strength of the rock mass at each time period obtained in S2 is imported as an input parameter into the microscopic parameter calibration model established in step 1 to obtain the microscopic mechanical parameters (such as particle effective modulus, particle density, bonding strength, etc.) corresponding to each time period. The function expression of each microscopic parameter over time is fitted by the regression analysis method in machine learning as shown in formula (2):

[0053]

[0054] In the formula, E ball is the effective modulus of the particle, ρ ball is the particle density, E bond is the effective bonding modulus, S bondis the bonding strength, and t is the time. From this, we can get the change law of microscopic parameters over time as follows: Figure 3 .

[0055] S4: Establish a DEM contact strength evolution model.

[0056] Through the secondary development of the contact model in DEM calculation, the functional expressions of the time-varying microscopic parameters obtained in S3 are embedded into the existing particle contact models (such as contact bonding model, parallel bonding model, etc.), and a DEM contact strength evolution model is established. In this way, the strength of the contact between particles in the DEM simulation can be weakened or increased over time, thereby truly reflecting the evolution of the macroscopic strength of the model.

[0057] S5: Establish a DEM calculation model, add the DEM contact strength evolution model established in S4 to the model, carry out numerical experiments, and simulate the strength changes of rock and soil during engineering disasters and grouting reinforcement.

[0058] Embodiment 2:

[0059] Embodiment 2 of the present disclosure provides a method for simulating the strength change of rock and soil during engineering disasters and grouting reinforcement, including:

[0060] The data acquisition module is configured to: acquire the data of macroscopic mechanical parameters of the rock and soil sample to be tested changing with time during the engineering disaster and grouting reinforcement process;

[0061] The data processing module is configured to: obtain the data of the micromechanical parameters of the rock and soil sample to be tested changing with time according to the data of the macromechanical parameters changing with time and the preset machine learning model;

[0062] The strength simulation module is configured to obtain the simulation results of the strength change of rock and soil during engineering disasters and grouting reinforcement according to the data of micromechanical parameters changing with time and the preset DEM calculation model.

[0063] Embodiment 3:

[0064] Embodiment 3 of the present disclosure provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the method for simulating changes in rock and soil strength during engineering disasters and grouting reinforcement as described in Embodiment 1 of the present disclosure.

[0065] Embodiment 4:

[0066] Embodiment 4 of the present disclosure provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for simulating changes in rock and soil strength during engineering disasters and grouting reinforcement as described in Embodiment 1 of the present disclosure are implemented.

[0067] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0068] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0071] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0072] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for simulating the strength change of rock and soil during engineering disasters and grouting reinforcement, characterized in that: The process includes: Establish a machine learning mesoscopic parameter calibration model, including: Establish a machine learning sample library, carry out numerical simulation of basic mechanical tests based on DEM calculation methods, record the macro and micro mechanical parameters in the test, and use the parameters of each test as a set of samples. Establish a DEM macro and micro parameter calibration database based on the above parameter samples as learning samples for machine learning. Train the machine learning model and develop a model for macro- and micro-parameter calibration based on the XGBoost algorithm. Divide the samples in the established database into two groups, 80% of which are used as training sets for the machine learning model to analyze and learn data features, and the remaining 20% ​​of the samples are used as test sets to verify the accuracy of the model learning results. The macroscopic mechanical parameters in the training set are used as characteristic values, and the microscopic mechanical parameters are used as target values. Import them into the model by adjusting the number of regression trees in the model. K , regression tree iteration step η , regularity coefficients γ and λ, complete the model training; the macroscopic mechanical parameters include elastic modulus, Poisson's ratio, compressive strength, internal friction angle and cohesion of the rock and soil sample, and the microscopic mechanical parameters include particle effective modulus, particle density, bonding effective modulus and bonding strength; Verify the accuracy of the model, take the macroscopic mechanical parameters in the test set as characteristic values, import them into the established machine learning microscopic parameter calibration model, run the machine learning microscopic parameter calibration model to predict the microscopic mechanical parameter values, and calculate the evaluation index of the calculation results R 2 , as follows: ; in, For the i The actual value of the test samples, The model predicts i Sample values, is the average of the actual values ​​of the test samples; Repeat the above steps. R 2 >0.95, establish a machine learning mesoscopic parameter calibration model; Obtain the data of macroscopic mechanical parameters of the rock and soil samples to be tested changing with time during engineering disasters and grouting reinforcement processes; According to the macroscopic mechanical parameter variation data over time and the preset machine learning model, the microscopic mechanical parameter variation data of the rock and soil sample to be tested over time are obtained, including: The macroscopic strength of the rock mass at each time period is imported as the input parameter into the established machine learning microscopic parameter calibration model to obtain the microscopic mechanical parameters corresponding to each time period. The function expression of each microscopic parameter over time is fitted by the regression analysis method in machine learning as shown below: , , , , where E ball is the effective modulus of the particle, ρ ball is the particle density, E bond is the effective modulus of bonding, S bond is the bonding strength, t For time; According to the data of micromechanical parameters changing with time and the preset DEM calculation model, the simulation results of rock and soil strength change during engineering disasters and grouting reinforcement are obtained; The data of each microscopic parameter changing with time are embedded into the existing particle contact model to obtain the DEM contact strength evolution model, including: Through the secondary development of the contact model in DEM calculation, the function expressions of the obtained microscopic parameters changing with time are embedded into the existing particle contact model, and the DEM contact strength evolution model is established, so that the strength of the contact between particles can be weakened or increased over time in the DEM simulation, thereby truly reflecting the evolution of the macroscopic strength of the model; The DEM contact strength evolution model is embedded in the DEM calculation model to perform numerical simulation of rock and soil strength changes, so that the DEM calculation model can truly reflect the strength evolution law of rock and soil.

2. The method for simulating the change of rock and soil strength during engineering disasters and grouting reinforcement as claimed in claim 1, characterized in that: The particle contact model is a contact bonding model.

3. The method for simulating the change of rock and soil strength during engineering disasters and grouting reinforcement as claimed in claim 1, characterized in that: The particle contact model is a parallel bonding model.

4. The method for simulating the change of rock and soil strength during engineering disasters and grouting reinforcement as claimed in claim 1, characterized in that: The data of micromechanical parameter variation over time is a function expression of each micromechanical parameter over time.

5. A simulation system for the change of rock and soil strength during engineering disasters and grouting reinforcement, characterized in that: The method for simulating the change in strength of rock and soil during engineering disaster and grouting reinforcement according to any one of claims 1 to 4 comprises: The data acquisition module is configured to: acquire the data of macroscopic mechanical parameters of the rock and soil sample to be tested changing with time during the engineering disaster and grouting reinforcement process; The data processing module is configured to: obtain the data of the micromechanical parameters of the rock and soil sample to be tested changing with time according to the data of the macromechanical parameters changing with time and the preset machine learning model; The strength simulation module is configured to obtain the simulation results of the strength change of rock and soil during engineering disasters and grouting reinforcement according to the data of micromechanical parameters changing with time and the preset DEM calculation model.

6. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for simulating the change in strength of rock and soil during engineering disasters and grouting reinforcement as described in any one of claims 1 to 4 are implemented.

7. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the method for simulating changes in rock and soil strength during engineering disasters and grouting reinforcement as described in any one of claims 1 to 4 are implemented.

Citation Information

Patent Citations

  • DEM contact model construction method capable of reflecting weakening of seepage to rock-soil mass strength

    CN111024588A

Cited By

  • Intelligent construction control method and system for jet grouting pile based on stratum information inversion

    US12559897B2

  • Intelligent construction control method and system for jet grouting pile based on stratum information inversion

    US20250092627A1