Underground engineering surrounding rock stability evaluation large model construction method and system

Abstract

The invention belongs to the technical field of underground engineering, and provides an underground engineering surrounding rock stability evaluation large model construction method and system in order to solve the problem that the calculation efficiency of numerical simulation cannot meet the timeliness of an engineering site construction stage. The underground engineering surrounding rock stability evaluation large model construction method comprises the following steps: constructing an underground engineering surrounding rock three-dimensional geologic model based on multi-source detection data of underground engineering surrounding rock; performing visual simulation on the underground engineering surrounding rock three-dimensional geologic model, and establishing a numerical simulation database; constructing a large geological environment inversion model, a surrounding rock stability prediction model and a catastrophe pre-judgment and pre-control model, and training the large geological environment inversion model, the surrounding rock stability prediction model and the catastrophe pre-judgment and pre-control model by using data in the numerical simulation database so as to optimize construction excavation support parameters; according to the method, accurate and real-time surrounding rock stability evaluation and catastrophe pre-judgment and pre-control measures can be realized, and the safety and economical efficiency of underground engineering are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of underground engineering, and particularly relates to a method and system for constructing a large model for evaluating the stability of surrounding rock of underground engineering. BACKGROUND

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

[0003] In traditional tunnel construction, the evaluation of surrounding rock stability mainly relies on experience and limited on-site monitoring data. These methods usually cannot fully reflect the complex geological conditions and dynamic changes during the construction process, resulting in limited accuracy and timeliness of the prediction. With the development of numerical simulation technology, although it is widely used in the design stage of engineering to predict the stability of surrounding rock and optimize the design scheme, due to the limitation of calculation efficiency, it is difficult to meet the real-time and dynamic needs of the construction stage.

[0004] In order to solve the above problems, the application of GPU parallel computing technology significantly improves the calculation speed of numerical simulation, but the calculation efficiency of numerical simulation cannot meet the timeliness of the construction stage of the engineering site, and how to realize the timely feedback of the numerical simulation results in the construction stage is still a challenge. SUMMARY

[0005] In order to solve the above technical problems, the present application provides a method and system for constructing a large model for evaluating the stability of surrounding rock of underground engineering, which can realize accurate and real-time evaluation of surrounding rock stability, as well as disaster prediction and pre-control measures, significantly improving the safety and economy of underground engineering.

[0006] In order to achieve the above purpose, the present application adopts the following technical solutions: The first aspect of the present application provides a method for constructing a large model for evaluating the stability of surrounding rock of underground engineering.

[0007] In one or more embodiments, a method for constructing a large model for evaluating the stability of surrounding rock of underground engineering is provided, comprising: Based on the multi-source detection data of the surrounding rock of underground engineering, a three-dimensional geological model of the surrounding rock of underground engineering is constructed; The three-dimensional geological model of the surrounding rock of underground engineering is visualized and simulated, and a numerical simulation simulation database is established; wherein the data in the numerical simulation simulation database includes construction excavation support parameters, support mechanical response parameters, on-site monitoring data, geological environment parameters, surrounding rock deformation parameters and surrounding rock mechanical response parameters; A geological environment inversion large model, a surrounding rock stability prediction model and a disaster prediction and pre-control model are constructed, and the data in the numerical simulation simulation database is used to train the geological environment inversion large model, the surrounding rock stability prediction model and the disaster prediction and pre-control model, so as to optimize the construction excavation support parameters; The inputs to the geological environment inversion model are construction excavation and support parameters, support mechanical response parameters, and field monitoring data, and the output is geological environment parameters; the inputs to the surrounding rock stability prediction model are construction excavation and support parameters and geological environment parameters, and the outputs are support mechanical response parameters and surrounding rock deformation parameters; the inputs to the disaster prediction and control model are support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters, and the output is construction excavation and support parameters.

[0008] The second aspect of the present invention provides a large-scale model construction system for evaluating the stability of surrounding rock in underground engineering.

[0009] In one or more embodiments, a large-scale model construction system for evaluating the stability of surrounding rock in underground engineering includes: The 3D geological model construction module is used to construct a 3D geological model of the surrounding rock of underground engineering based on multi-source detection data of the surrounding rock. The simulation database establishment module is used to perform visual simulation of the three-dimensional geological model of the surrounding rock of underground engineering and establish a numerical simulation database. The data in the numerical simulation database includes construction excavation support parameters, support mechanical response parameters, field monitoring data, geological environment parameters, surrounding rock deformation parameters, and surrounding rock mechanical response parameters. The model building and training module is used to build a large-scale geological environment inversion model, a surrounding rock stability prediction model, and a disaster prediction and control model. It also uses data from the numerical simulation database to train the large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model in order to optimize construction excavation and support parameters. The inputs to the geological environment inversion model are construction excavation and support parameters, support mechanical response parameters, and field monitoring data, and the output is geological environment parameters; the inputs to the surrounding rock stability prediction model are construction excavation and support parameters and geological environment parameters, and the outputs are support mechanical response parameters and surrounding rock deformation parameters; the inputs to the disaster prediction and control model are support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters, and the output is construction excavation and support parameters.

[0010] A third aspect of the present invention provides an electronic device.

[0011] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the above-described method for constructing a large model for evaluating the stability of surrounding rock in underground engineering.

[0012] Compared with the prior art, the beneficial effects of the present invention are: This invention utilizes multi-source detection data of the surrounding rock in underground engineering projects to construct a three-dimensional geological model of the surrounding rock, making the three-dimensional geological model of the surrounding rock more consistent with actual engineering. Based on the simulation of the three-dimensional geological model of the surrounding rock, a sample database, namely a numerical simulation database, is obtained for training the large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model. This provides as many samples as possible for model training, improving the accuracy of the model training results. Finally, using the trained large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model, geological environment inversion, surrounding rock stability prediction, and disaster prediction and control are performed sequentially to determine the optimal construction excavation and support parameters. This achieves accurate and real-time assessment of surrounding rock stability and disaster prediction and control measures, improving the safety and economy of underground engineering. Attached Figure Description

[0013] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0014] Figure 1 This is a flowchart illustrating the method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering, according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the large-scale model construction system for evaluating the stability of surrounding rock in underground engineering, according to an embodiment of the present invention. Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention; Figure 4 This is a flowchart illustrating the construction process of the multi-source detection database according to an embodiment of the present invention; Figure 5 This is a flowchart illustrating the simulation database construction process according to an embodiment of the present invention; Figure 6 This is a schematic diagram illustrating the principle of surrounding rock stability prediction in an embodiment of the present invention. Detailed Implementation

[0015] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0016] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0017] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0018] Figure 1 This is a flowchart illustrating a method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering, as described in an embodiment of the present invention. Figure 1 The method for constructing a large model for evaluating the stability of surrounding rock in underground engineering, as shown in this embodiment, may include the following steps S101 to S103.

[0019] The specific implementation process of steps S101 to S103 is as follows: Step S101: Based on the multi-source detection data of the surrounding rock of the underground engineering project, construct a three-dimensional geological model of the surrounding rock of the underground engineering project.

[0020] Based on multi-source detection data of surrounding rock in underground engineering projects, a multi-source detection database is constructed, such as... Figure 4 As shown.

[0021] First, a detailed geological structure survey is conducted, which includes macro-geological analysis, seismic wave detection, transient electromagnetic detection, and induced polarization detection. For example, macro-geological analysis is used to identify the types of hazard sources along the entire route, obtaining the distribution of surrounding rock grades in the site selection area for underground space engineering. Seismic wave detection is used to detect geological structures such as faults and karst caves over long distances (120m). Transient electromagnetic detection is used to locate water-bearing bodies at medium distances (60-80m). Induced polarization detection is used to estimate water content at short distances (30m).

[0022] Then, the main structural surface features were extracted. Structural surface features were extracted from 2D images and 3D point clouds using 3D laser scanning and panoramic imaging, forming a full-space fracture network database. Based on the aforementioned geological and geophysical exploration methods, a multi-source exploration database was constructed. This multi-source database comprises three categories: a geological information database (drill hole data), a geological structure database (digitized karst caves), and a full-space fracture network database.

[0023] This research focuses on data-driven modeling and the digitization of 3D geological models of surrounding rock in underground engineering projects. Data-driven technologies are applied to construct detailed 3D geological models of surrounding rock from limited geological data. Voxelization technology is used to convert these models into a digital format, enabling dynamic updates.

[0024] Step S102: Visualize and simulate the three-dimensional geological model of the surrounding rock of the underground project, and establish a numerical simulation database; wherein, the data in the numerical simulation database includes construction excavation support parameters, support mechanical response parameters, field monitoring data, geological environment parameters, surrounding rock deformation parameters and surrounding rock mechanical response parameters.

[0025] It should be noted that the on-site monitoring data includes: surrounding rock deformation data (such as arch crown settlement, arch shoulder convergence, arch foot convergence, and arch bottom heave) and stress monitoring data; among which, stress monitoring data includes surrounding rock-support contact pressure, support structure stress monitoring data (e.g., steel arch frame stress, anchor bolt stress, and secondary lining stress) and groundwater pressure.

[0026] In the process of establishing the numerical simulation database, based on the continuous-discontinuous coupled calculation model, numerical simulation calculations of the working condition combination are performed under the set working conditions including geological environment and construction support parameters to obtain the support mechanical response parameters, surrounding rock deformation parameters, and surrounding rock mechanical response parameters, such as... Figure 5 As shown.

[0027] First, a continuous-discontinuous coupled calculation model of FEM-DEM at the engineering scale is established. Then, the design includes geological conditions, environmental conditions, and engineering disturbance conditions. Geological conditions include surrounding rock parameters and geological structures. Surrounding rock parameters include cohesion, internal friction angle, elastic modulus, and Poisson's ratio. Geological structure parameters include rock layer distribution (single or multiple layers) and fault parameters (dip, dip angle, width, location, etc.). Environmental conditions include in-situ stress parameters and water stress parameters. In-situ stress parameters include burial depth, lateral pressure coefficient, and rock layer density. Water stress parameters include permeability coefficient and groundwater level. Engineering disturbance conditions include excavation parameters and support parameters. Excavation parameters include tunnel shape (circular, three-circular, horseshoe-shaped, etc.), construction method (two-stage, three-stage, full-face, CD method, etc.), excavation advance, and tunnel cross-section size. Support parameters include pre-embedded pipes, radial grouting, primary support and secondary lining, and anchor bolt support. Pre-embedded pipe parameters include pipe length and ring spacing. Radial grouting parameters include grouting depth and grouting spacing. Primary support and secondary lining parameters include steel arch frame spacing and primary support thickness. Anchor bolt support parameters include anchor bolt length and spacing.

[0028] Then, based on a continuous-discontinuous coupled computational model, numerical simulations were performed on tens of thousands of working condition combinations to obtain the support mechanical response and the surrounding rock mechanical response. The support mechanical response includes the secondary stress of the steel arch frame, the axial force of the secondary lining, and the bending moment of the secondary lining. The surrounding rock mechanical response includes the stress field, displacement field, plastic zone, and damage zone. The displacement field includes the arch crown settlement, arch shoulder convergence, arch waist convergence, and arch bottom heave at each monitoring section. The stress field includes the maximum principal stress and the minimum principal stress. The plastic zone and damage zone can be displayed by exporting the boundary points of the range. Finally, the above geological conditions, environmental conditions, engineering interference conditions, and the output surrounding rock mechanical response and support mechanical response data are summarized into a database. Each working condition corresponds to a set of data, establishing a simulation database of tens of thousands of data sets.

[0029] Step S103: Construct a large-scale geological environment inversion model, a surrounding rock stability prediction model, and a disaster prediction and control model, and use data from the numerical simulation database to train the large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model in order to optimize construction excavation and support parameters. The inputs to the geological environment inversion model are construction excavation and support parameters, support mechanical response parameters, and field monitoring data, and the output is geological environment parameters; the inputs to the surrounding rock stability prediction model are construction excavation and support parameters and geological environment parameters, and the outputs are support mechanical response parameters and surrounding rock deformation parameters; the inputs to the disaster prediction and control model are support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters, and the output is construction excavation and support parameters.

[0030] Based on the previously established database, a geological parameter inversion proxy model was constructed using a convolutional neural network (CNN) and an attention mechanism. The model input parameters include construction excavation and support parameters (including excavation methods such as full-section and bench methods), support types (such as steel arch supports and anchor bolt supports), and support parameters (such as steel arch spacing, anchor bolt length and spacing)) and surrounding rock displacement field parameters (including arch crown settlement, sidewall convergence, and arch waist convergence). The output is geological environmental parameters. These parameters include rock mechanical parameters (such as elastic modulus, Poisson's ratio, cohesion, and internal friction angle), geological structural parameters (such as fault location and rock stratum dip angle), and geostress parameters (such as surrounding rock lateral pressure coefficient and rock stratum density). The large-scale geological environmental inversion model aims to accurately obtain the geological environmental parameters of the current section, providing a basis for subsequent predictions.

[0031] When constructing a large-scale geological environment inversion model, displacement loss and spatial effects were considered. Due to limitations in the installation time or location of monitoring equipment, displacement loss occurs, meaning that the existing displacement of the rock before monitoring begins is not recorded. To address this issue, displacement loss is introduced and quantified by analyzing the differences between monitoring data and numerical simulation results. Specifically, the quantification of displacement loss includes two parts: monitoring distance and displacement loss parameters. Monitoring distance refers to the initial displacement value of the monitoring point, which is quantified by measuring the initial distance (d) between the monitoring point and the tunnel excavation face, as the monitoring equipment is typically installed at a certain distance after tunnel excavation. Displacement loss parameters refer to the displacement loss of the rock before the installation of monitoring equipment (such as displacement before excavation, displacement before the first lining after excavation, etc.), estimated through comparative analysis of numerical simulation and field monitoring data. Simultaneously, parameters describing the rock deformation process are introduced to more accurately describe the rock deformation process. Specifically, displacement change parameters refer to parameters such as displacement change rate and displacement gradient, obtained by fitting the displacement curve obtained from numerical simulation to obtain fitting parameters (such as coefficients in the fitting equation). The equation for fitting considering spatial effects is: (Logarithmic fitting equation) Where U is the rock displacement, a and b are fitting parameters, and d is the monitoring distance. These parameters serve as the model's output parameters to better account for spatial effects.

[0032] In the process of training the large-scale geological environment inversion model, the mean square error between the predicted and actual values ​​is calculated as the loss function, and the model parameters are gradually adjusted to minimize the loss function.

[0033] The large-scale geological environment inversion model is trained using historical data from a database. The deep neural network model is trained using this training data, and the model parameters are optimized by adjusting the network weights and biases to enable accurate prediction of geological environment parameters. Optimization algorithms (such as the Adam optimizer) are employed for training, using the mean squared error (MSE) between predicted and actual values ​​as the loss function. The model parameters are progressively adjusted to minimize this loss function. After training, the trained model is evaluated using independent validation datasets. Evaluation metrics include MSE and mean absolute error (MAE) to ensure the model's accuracy and generalization ability on unseen data. Based on the validation results, model parameters are further adjusted or the network structure is optimized to improve model performance. Cross-validation and other methods are used to optimize the model, adjusting hyperparameters to improve generalization ability and prediction accuracy. Ultimately, this model can quickly invert the geological environment parameters of the current cross-section based on real-time monitoring data and construction parameters, providing accurate geological information for surrounding rock stability prediction and disaster prevention and control, significantly improving the intelligence level of surrounding rock stability prediction and control in underground engineering.

[0034] Construct a surrounding rock stability prediction model based on the simulation database established above, such as... Figure 6 As shown, a rock mass stability prediction model is constructed using deep neural networks such as Convolutional Neural Networks (CNN) and Attention mechanisms. The model takes construction excavation and support parameters and geological environment parameters as inputs, and outputs rock mass mechanical response and support mechanical response parameters. The rock mass mechanical response parameters include displacement field, stress field, plastic zone, and damage zone. The support mechanical response parameters include secondary stress of the steel arch frame, axial force of the secondary lining, and bending moment of the secondary lining. Finally, based on relevant tunnel construction specifications, thresholds for rock mass mechanical response and support mechanical response are set, and the mechanical response data is updated and compared with the specifications in real time to establish an early warning system.

[0035] In the process of training the disaster prediction and control model, limits are set for the surrounding rock deformation parameters, safety factor and construction cost as constraints.

[0036] During the training of the disaster prediction and control model, the artificial fish swarm optimization algorithm is used to iteratively update the samples. The samples include the following parameters: support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters and their corresponding construction excavation and support parameters.

[0037] The disaster prediction and control model, based on the support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters, quickly provides the optimal combination of construction excavation support parameters through parameter optimization, thereby achieving proactive disaster prevention and control and ensuring safe, economical, and efficient tunnel construction.

[0038] Before training the disaster prediction and control model, random initial samples are generated. 100 sets of excavation and support parameter samples are randomly generated, including support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters and their corresponding construction excavation and support parameters.

[0039] Using the established disaster prediction and control model, the support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters are input, and numerical simulation calculations are performed to obtain the corresponding construction excavation support parameters.

[0040] Constraint settings: Determine the limits of surrounding rock deformation parameters (such as crown settlement, sidewall convergence, etc.), safety factors (such as support structure stability coefficient) and construction costs (such as support material usage and construction time) according to the specifications.

[0041] Preliminary screening: Compare the mechanical response of each sample group with the above constraints, and eliminate 25% of the samples that do not meet any of the conditions, i.e., eliminate 25 samples.

[0042] New Sample Generation and Replacement: Using the excavation and support parameters of the remaining 75 sample groups as input, and the corresponding surrounding rock mechanical response and support mechanical response as output, a random forest model is trained to learn the mapping relationship between sample parameters and mechanical responses. Using the trained random forest model, 25 new samples are generated, restoring the total number of samples to 100, ensuring sample diversity.

[0043] The artificial fish swarm optimization algorithm iteratively updates samples: 100 sets of samples are considered as an artificial fish swarm, with each set representing one fish. The swarm includes excavation and support parameters, and the fish are distributed in the parameter space. Mean squared error (MSE) is used as the fitness function to measure the deviation between the predicted and target values. The simulated fish swarm behavior includes: foraging behavior (each fish adjusts its parameters according to the fitness function, moving towards a better solution), swarming behavior (fish gather, share information, and improve search efficiency), and following behavior (some fish follow high-quality individuals, accelerating convergence). The fish swarm behavior simulation process is repeated to continuously optimize the sample parameters until the fitness function is satisfied (e.g., MSE is less than a set threshold) or the maximum number of iterations is reached.

[0044] Output the optimal parameter combination: From the samples that meet the conditions, comprehensively considering construction safety, cost, and efficiency, determine the optimal combination of construction excavation and support parameters, including excavation method, excavation advance, steel arch spacing, initial support thickness, anchor length and spacing, etc. Finally, based on actual construction conditions and real-time monitoring feedback, flexibly adjust the optimized parameter combination to ensure the model's effectiveness and adaptability in practice.

[0045] Specifically, based on the current construction excavation and support parameters, the current support mechanical response parameters, and the current on-site monitoring data, the geological environment parameters are inverted using a well-trained geological environment inversion model. Based on the current construction excavation and support parameters and the inverted geological environment parameters, the support mechanical response parameters and surrounding rock deformation parameters are predicted using a trained surrounding rock stability prediction model. Based on the predicted support mechanical response parameters and surrounding rock deformation parameters, the inverted geological environment parameters and the current surrounding rock mechanical response parameters, the optimal construction excavation support parameters are obtained using a trained disaster prediction and control model.

[0046] This embodiment utilizes multi-source detection data of the surrounding rock of underground engineering projects to construct a three-dimensional geological model of the surrounding rock, making the three-dimensional geological model of the surrounding rock of underground engineering projects more consistent with actual engineering. Based on the simulation of the three-dimensional geological model of the surrounding rock of underground engineering projects, a sample database, namely a numerical simulation database, is obtained for training the large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model. This provides as many samples as possible for model training, improving the accuracy of the model training results. Finally, using the trained large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model, geological environment inversion, surrounding rock stability prediction, and disaster prediction and control are performed sequentially to determine the optimal construction excavation and support parameters. This achieves accurate and real-time assessment of surrounding rock stability and disaster prediction and control measures, improving the safety and economy of underground engineering.

[0047] like Figure 2 As shown, the large-scale model construction system for assessing the stability of surrounding rock in underground engineering provided by this embodiment of the invention can be implemented in software. The large-scale model construction system for assessing the stability of surrounding rock in underground engineering includes the following software modules: The 3D geological model construction module 201 is used to construct a 3D geological model of the surrounding rock of underground engineering based on multi-source detection data of the surrounding rock of underground engineering. The simulation database establishment module 202 is used to perform visualization simulation of the three-dimensional geological model of the surrounding rock of underground engineering and establish a numerical simulation database. The data in the numerical simulation database includes construction excavation support parameters, support mechanical response parameters, field monitoring data, geological environment parameters, surrounding rock deformation parameters, and surrounding rock mechanical response parameters. The model building and training module 203 is used to build a large geological environment inversion model, a surrounding rock stability prediction model, and a disaster prediction and control model. It also uses data from the numerical simulation database to train the large geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model to optimize construction excavation and support parameters. The inputs to the geological environment inversion model are construction excavation and support parameters, support mechanical response parameters, and field monitoring data, and the output is geological environment parameters; the inputs to the surrounding rock stability prediction model are construction excavation and support parameters and geological environment parameters, and the outputs are support mechanical response parameters and surrounding rock deformation parameters; the inputs to the disaster prediction and control model are support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters, and the output is construction excavation and support parameters.

[0048] It should be noted that each module in the embodiments of the present invention corresponds one-to-one with each step in the above embodiments, and their specific implementation processes are the same, so they will not be repeated here.

[0049] This embodiment utilizes multi-source detection data of the surrounding rock of underground engineering projects to construct a three-dimensional geological model of the surrounding rock, making the three-dimensional geological model of the surrounding rock of underground engineering projects more consistent with actual engineering. Based on the simulation of the three-dimensional geological model of the surrounding rock of underground engineering projects, a sample database, namely a numerical simulation database, is obtained for training the large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model. This provides as many samples as possible for model training, improving the accuracy of the model training results. Finally, using the trained large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model, geological environment inversion, surrounding rock stability prediction, and disaster prediction and control are performed sequentially to determine the optimal construction excavation and support parameters. This achieves accurate and real-time assessment of surrounding rock stability and disaster prediction and control measures, improving the safety and economy of underground engineering.

[0050] The structure of the electronic device according to an embodiment of the present invention will be described in detail below. Figure 3 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present invention. It can be understood that... Figure 3 The diagram shows only an exemplary structure of the electronic device, not the entire structure. Some or all of the structures shown may be implemented as needed.

[0051] The electronic device provided in this embodiment of the invention includes: at least one processor 301, a memory 302, a user interface 303, and at least one network interface 304. The various components in the large-scale model construction system for assessing the stability of surrounding rock in underground engineering are coupled together via a bus system 305. It can be understood that the bus system 305 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 305 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 3 The general designated all buses as Bus System 305.

[0052] The user interface 303 may include a monitor, keyboard, mouse, trackball, click wheel, buttons, touchpad, or touch screen.

[0053] It is understood that memory 302 can be volatile memory or non-volatile memory, or both. In this embodiment of the invention, memory 302 is capable of storing data to support the operation of the terminal. Examples of this data include any computer programs used to operate on the terminal, such as operating systems and applications. The operating system includes various system programs, such as framework layers, core library layers, driver layers, etc., used to implement various basic services and handle hardware-based tasks. Applications can include various applications.

[0054] In some embodiments, the large-scale model construction system 300 for assessing the stability of surrounding rock in underground engineering provided by this invention can be implemented using a combination of hardware and software. For example, the large-scale model construction system 300 for assessing the stability of surrounding rock in underground engineering provided by this invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the large-scale model construction method for assessing the stability of surrounding rock in underground engineering provided by this invention. For example, the processor in the form of a hardware decoding processor can employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0055] As an example, processor 301 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., wherein the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0056] As an example of the hardware implementation of the large-scale model construction system 300 for assessing the stability of surrounding rock in underground engineering provided in this embodiment of the invention, the device provided in this embodiment of the invention can be directly executed by a processor 301 in the form of a hardware decoding processor. For example, it can be executed by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components to implement the large-scale model construction method for assessing the stability of surrounding rock in underground engineering provided in this embodiment of the invention.

[0057] The memory 302 in this embodiment of the invention is used to store various types of data to support the operation of the large model construction system for assessing the stability of surrounding rock in underground engineering, or to store data for execution. Figure 1The program code for the method shown. Examples of this data include: any executable instructions for operating on a large-scale model construction system for assessing the stability of surrounding rock in underground engineering, such as executable instructions that can be included in the executable instructions to implement the method for constructing a large-scale model for assessing the stability of surrounding rock in underground engineering according to embodiments of the present invention.

[0058] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including functions for executing... Figure 1 The program code for the method shown. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by the central processing unit, it performs the various functions defined in the apparatus of this application.

[0059] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0060] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering projects, characterized in that, include: Based on multi-source detection data of the surrounding rock of underground engineering, a three-dimensional geological model of the surrounding rock of underground engineering is constructed. A three-dimensional geological model of the surrounding rock of underground engineering is visualized and simulated to establish a numerical simulation database. The data in the numerical simulation database includes construction excavation and support parameters, support mechanical response parameters, field monitoring data, geological environment parameters, surrounding rock deformation parameters, and surrounding rock mechanical response parameters. A large-scale geological environment inversion model, a surrounding rock stability prediction model, and a disaster prediction and control model were constructed. Data from the numerical simulation database were used to train the large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model in order to optimize construction excavation and support parameters. The inputs to the geological environment inversion model are construction excavation and support parameters, support mechanical response parameters, and field monitoring data, and the output is geological environment parameters; the inputs to the surrounding rock stability prediction model are construction excavation and support parameters and geological environment parameters, and the outputs are support mechanical response parameters and surrounding rock deformation parameters; the inputs to the disaster prediction and control model are support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters, and the output is construction excavation and support parameters.

2. The method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering as described in claim 1, characterized in that, In the process of training the disaster prediction and control model, limits were also set for the surrounding rock deformation parameters, safety factor and construction cost as constraints.

3. The method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering as described in claim 1, characterized in that, During the training of the disaster prediction and control model, the artificial fish swarm optimization algorithm is used to iteratively update the samples. The samples include the following parameters: support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, surrounding rock mechanical response parameters, and corresponding labeled construction excavation and support parameters.

4. The method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering as described in claim 1, characterized in that, In the process of training a large-scale geological environment inversion model, the mean square error between the predicted and actual values ​​is calculated as the loss function, and the model parameters are gradually adjusted to minimize the loss function.

5. The method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering as described in claim 1, characterized in that, In the process of establishing the numerical simulation database, based on the continuous-discontinuous coupled calculation model, numerical simulation calculations of the working conditions combination are carried out under the set working conditions including geological environment and construction support parameters to obtain the support mechanical response parameters, surrounding rock deformation parameters and surrounding rock mechanical response parameters.

6. The method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering as described in claim 1, characterized in that, The construction excavation and support parameters include excavation method, excavation advance, steel arch spacing, initial support thickness, anchor length and spacing.

7. The method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering as described in claim 1, characterized in that, The surrounding rock mechanical response parameters include displacement field, stress field, plastic zone, and damage zone.

8. The method for constructing a large-scale model for evaluating the stability of surrounding rock in underground engineering as described in claim 1, characterized in that, The mechanical response parameters of the support include the secondary stress of the steel arch frame, the axial force of the secondary lining, and the bending moment of the secondary lining.

9. A large-scale model construction system for evaluating the stability of surrounding rock in underground engineering, characterized in that, include: The 3D geological model construction module is used to construct a 3D geological model of the surrounding rock of underground engineering based on multi-source detection data of the surrounding rock. The simulation database establishment module is used to perform visual simulation of the three-dimensional geological model of the surrounding rock of underground engineering and establish a numerical simulation database. The data in the numerical simulation database includes construction excavation support parameters, support mechanical response parameters, field monitoring data, geological environment parameters, surrounding rock deformation parameters, and surrounding rock mechanical response parameters. The model building and training module is used to build a large-scale geological environment inversion model, a surrounding rock stability prediction model, and a disaster prediction and control model. It also uses data from the numerical simulation database to train the large-scale geological environment inversion model, the surrounding rock stability prediction model, and the disaster prediction and control model in order to optimize construction excavation and support parameters. The inputs to the geological environment inversion model are construction excavation and support parameters, support mechanical response parameters, and field monitoring data, and the output is geological environment parameters; the inputs to the surrounding rock stability prediction model are construction excavation and support parameters and geological environment parameters, and the outputs are support mechanical response parameters and surrounding rock deformation parameters; the inputs to the disaster prediction and control model are support mechanical response parameters, surrounding rock deformation parameters, geological environment parameters, and surrounding rock mechanical response parameters, and the output is construction excavation and support parameters.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the method for constructing a large model for evaluating the stability of surrounding rock in underground engineering as described in any one of claims 1-8.

Images