Mining rock mass deformation damage prediction method and device based on digital rock mechanics

Abstract

The invention provides a mining rock mass deformation damage prediction method and device based on digital rock mechanics. The method comprises the steps that the historical mining technological process of a to-be-mined area is obtained; according to the historical mining technological process, through a preset digital rock mechanics solver, obtaining at least one group of analog data values; for each step of historical mining process flow, acquiring an actual data value of the to-be-mined area when each step of historical mining process flow is executed; and according to the simulation data value and the corresponding actual data value, training the rock mass deformation and damage prediction model to obtain a target rock mass deformation and damage prediction model, thereby training the rock mass deformation and damage prediction model according to the simulation data value and the actual data value obtained through a preset digital rock mechanics solver to obtain the target rock mass deformation and damage prediction model. According to the invention, the accuracy of the target rock mass deformation and damage prediction model is improved, so that the rock mass deformation and damage after the execution of the mining process flow can be accurately predicted.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics. Background Art

[0002] During the mining process, the rock medium begins to show characteristics such as "brittle-ductile" transformation and enhanced rheology, and the rock will deform and be damaged. In order to ensure the safety of the mining process and provide intuitive understanding for the quantitative evaluation of the hazards of ore mining and the formulation of differentiated prevention and control measures, a simplified stratigraphic model is usually used in related technologies to predict the deformation and damage of the rock mass during the mining process. However, the simplified stratigraphic model is used to perform numerical simulation of the underground rock mass response. Due to the gap between the simulation model and the actual stratigraphic model, it is difficult to simulate the real dynamic destruction process, and the prediction accuracy is often inaccurate. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, the first purpose of the present application is to propose a method for predicting deformation and failure of mining rock mass based on digital rock mechanics, so as to predict deformation and failure of mining rock mass during the mining process.

[0005] The second purpose of the present application is to propose a device for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics.

[0006] The third objective of the present application is to provide an electronic device.

[0007] A fourth objective of the present application is to provide a computer-readable storage medium.

[0008] A fifth object of the present application is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first aspect of the present application proposes a method for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics, including: obtaining a historical mining process flow of the area to be mined; wherein the historical mining process flow includes at least one mining distance and a corresponding mining time; according to the historical mining process flow, at least one set of simulation data values ​​is obtained through a preset digital rock mechanics solver; wherein the simulation data values ​​include the spatial position of the mining face and the corresponding stress state simulation value of a preset measuring point in the area to be mined when executing the mining distance included in a step of the historical mining process flow at the mining time. , displacement simulation values ​​and rock deformation and damage simulation values; for each step of the historical mining process, obtaining the actual data values ​​of the area to be mined when each step of the historical mining process has been executed; wherein the actual data values ​​include the spatial position of the mining face when the mining distance included in a step of the historical mining process is executed at the mining time, and the corresponding actual values ​​of the stress state, displacement and rock deformation and damage of the preset measuring points in the area to be mined; according to the simulated data values ​​and the corresponding actual data values, the rock deformation and damage prediction model is trained to obtain the target rock deformation and damage prediction model.

[0010] To achieve the above-mentioned purpose, the second aspect of the present application proposes a device for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics, including: a first acquisition module, used to obtain the historical mining process flow of the area to be mined; wherein the historical mining process flow includes at least one mining distance and a corresponding mining time; a first acquisition module, used to obtain at least one set of simulation data values ​​according to the historical mining process flow through a preset digital rock mechanics solver; wherein the simulation data values ​​include the spatial position of the mining face and the corresponding stress state simulation of the preset measuring point in the area to be mined when executing the mining distance included in a step of the historical mining process flow at the mining time. value, displacement simulation value and rock deformation and damage simulation value; a second acquisition module, used to obtain, for each step of the historical mining process, the actual data value of the area to be mined when each step of the historical mining process has been executed; wherein the actual data value includes the spatial position of the mining face when the mining distance included in a step of the historical mining process is executed at the mining time, and the corresponding actual value of the stress state, actual value of displacement and actual value of rock deformation and damage of preset measuring points in the area to be mined; a training module, used to train the rock deformation and damage prediction model according to the simulated data value and the corresponding actual data value, so as to obtain the target rock deformation and damage prediction model.

[0011] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics disclosed in the embodiment of the present application.

[0012] To achieve the above-mentioned objectives, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the method for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics disclosed in the embodiment of the present application.

[0013] To achieve the above-mentioned purpose, the fifth aspect embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the method for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics disclosed in the embodiment of the present application.

[0014] The method and device for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics provided in the present application obtain the historical mining process flow of the area to be mined; wherein the historical mining process flow includes at least one mining distance and the corresponding mining time; according to the historical mining process flow, at least one set of simulation data values ​​is obtained through a preset digital rock mechanics solver; wherein the simulation data values ​​include the spatial position of the mining face when executing the mining distance included in one mining process flow at the mining time, and the corresponding stress state simulation value, displacement simulation value and rock deformation and damage simulation value of the preset measuring point in the area to be mined; for each step of the historical mining process flow, the actual data value of the area to be mined when each step of the historical mining process flow has been executed is obtained; wherein the actual data values ​​include the spatial position of the mining face when executing the mining distance included in one historical mining process flow at the mining time, and the corresponding actual value of the stress state, actual value of the displacement and actual value of the rock deformation and damage of the preset measuring point in the area to be mined; According to the simulated data values ​​and the corresponding actual data values, the rock deformation and failure prediction model is trained to obtain the target rock deformation and failure prediction model. Thus, through the preset digital rock mechanics solver, according to the spatial position of the mining face after the execution of the mining process and the corresponding mining time, the corresponding rock deformation and failure in the whole process of the mining process is obtained, which not only takes into account the heterogeneity of the ore body strata, but also takes into account the changes in the intrinsic physical logic of the ore body when the pressure and displacement distribution of the ore body changes under the mining conditions. Therefore, according to the simulated data values ​​and actual data values ​​obtained by the preset digital rock mechanics solver, the rock deformation and failure prediction model is trained to obtain the target rock deformation and failure prediction model, which improves the accuracy of the target rock deformation and failure prediction model, so that the mining rock deformation and failure after the execution of the mining process can be accurately predicted, providing intuitive cognition for the quantitative evaluation of the impact hazard of the ore body and the formulation of differentiated prevention and control measures, and improving the safety of the mining process.

[0015] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A flowchart of a method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in an embodiment of the present application Figure 1 ;

[0018] Figure 2A flowchart of a method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in an embodiment of the present application Figure 2 ;

[0019] Figure 3 An example diagram of a process for determining a stress state simulation value and a rock mass deformation and failure simulation value provided in an embodiment of the present application;

[0020] Figure 4 A flowchart of a method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in an embodiment of the present application Figure 3 ;

[0021] Figure 5 This is an example diagram corresponding to the rock mass deformation and failure prediction model training process provided in the embodiment of the present application;

[0022] Figure 6 A flowchart of a method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in an embodiment of the present application Figure 4 ;

[0023] Figure 7 A schematic diagram of the structure of a device for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in an embodiment of the present application;

[0024] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0026] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations.

[0027] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0028] Figure 1 A flowchart of a method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in an embodiment of the present application Figure 1 .

[0029] Step 101, obtaining a historical mining process flow of the area to be mined; wherein the historical mining process flow includes at least one step of mining distance and corresponding mining time.

[0030] It should be noted that the method for predicting the deformation and failure of rock mass due to mining based on digital rock mechanics provided in the embodiment of the present application can be performed by a device for predicting the deformation and failure of rock mass due to mining based on digital rock mechanics (also referred to as a device for predicting the deformation and failure of rock mass due to mining based on digital rock mechanics), wherein the device for predicting the deformation and failure of rock mass due to mining based on digital rock mechanics can be implemented by software and / or hardware. The device for predicting the deformation and failure of rock mass due to mining based on digital rock mechanics can be an electronic device, or can be configured in an electronic device to implement the function of predicting the deformation and failure of rock mass due to mining based on digital rock mechanics.

[0031] Among them, the embodiment of the present application is explained by taking the mining rock deformation and failure prediction method based on digital rock mechanics as an example configured in an electronic device.

[0032] Among them, the electronic device can be any device with computing capabilities, such as a personal computer, a mobile terminal, a server, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and other hardware devices with various operating systems, touch screens and / or display screens.

[0033] It can be understood that the area to be mined can be a partial area of ​​the ore body, or the entire area, which is not specifically limited in this embodiment.

[0034] Among them, it should be noted that the historical mining process flow can be the mining process flow that has been executed on the area to be mined in any time period before the current moment. The specific value of the time period can be determined according to actual needs. For example, the mining process flow that has been executed on the area to be mined within three months before the current moment. This embodiment does not specifically limit the value of the time span of the time period.

[0035] Step 102, based on the historical mining process, at least one set of simulation data values ​​is obtained through a preset digital rock mechanics solver; wherein the simulation data values ​​include the spatial position of the mining face when executing a mining distance included in a step of the mining process at the mining time, and the corresponding stress state simulation value, displacement simulation value and rock deformation and failure simulation value of the preset measuring point in the area to be mined.

[0036] It should be noted that after executing the mining distance included in a step of historical mining process, the spatial position of the mining working face is determined by the set spatial coordinates. For example, the spatial position of the mining working face can be expressed as coordinates (x, y, z).

[0037] In order to accurately and quickly obtain the stress state simulation value, displacement simulation value and rock deformation and failure simulation value of the preset measuring points in the area to be mined, as a possible implementation method, according to the mining distance and mining time included in the execution of the historical mining process, the stress state simulation value, displacement simulation value and rock deformation and failure simulation value of the preset measuring points in the area to be mined are obtained through a preset digital rock mechanics solver.

[0038] As an example, for each step of the historical mining process, the mining distance and mining time included in the execution of the historical mining process are obtained; a preset digital rock mechanics solver is used to determine the stress state simulation value of the preset measuring point in the to-be-mined area when executing the historical mining process based on the mining distance and mining time when executing the historical mining process; when executing the mining distance included in the historical mining process, the spatial position of the mining working face in the spatial coordinate system at the corresponding mining time is obtained, and at the spatial position of the mining working face, the corresponding stress state simulation value of the preset measuring point in the to-be-mined area is determined; based on the mining distance when executing the historical mining process and the spatial position of the mining working face, the corresponding displacement simulation value of the preset measuring point in the to-be-mined area is determined; based on the stress state simulation value and displacement simulation value of the preset measuring point in the to-be-mined area when executing the historical mining process, the rock deformation and damage simulation value of the to-be-mined area after the execution of the historical mining process is determined.

[0039] In order to accurately determine the stress state simulation value of the preset measuring point in the area to be mined when executing the historical mining process, as a possible implementation method, a preset digital rock mechanics solver is used to determine the maximum principal stress value and stress flow vector of the preset measuring point in the area to be mined according to the mining distance and mining time when executing the historical mining process, and determine the stress state simulation value of the preset measuring point in the area to be mined according to the maximum principal stress value and the stress flow vector.

[0040] As an example, a preset digital rock mechanics solver is used to determine the maximum principal stress value of a preset measuring point in the area to be mined when executing the historical mining process based on the mining distance and mining time when executing the historical mining process; the maximum principal stress value is calculated to determine the stress flow vector of the preset measuring point in the area to be mined when executing the historical mining process; and based on the stress flow vector, the stress state simulation value of the preset measuring point in the area to be mined when executing the historical mining process is determined.

[0041] It can be understood that the maximum principal stress value can be calculated according to the public mathematical calculation formula to determine the stress flow vector of the preset measuring point in the area to be mined when executing the historical mining process, which will not be repeated in this embodiment.

[0042] Step 103, for each step of the historical mining process, obtain the actual data value of the area to be mined when each step of the historical mining process has been executed; wherein the actual data value includes the spatial position of the mining working face when executing the mining distance included in a step of the historical mining process at the mining time, and the corresponding actual value of the stress state, actual value of the displacement and actual value of the rock deformation and damage of the preset measuring point in the area to be mined.

[0043] It should be noted that the preset measuring points in the area to be mined can be set according to actual needs, and this embodiment does not specifically limit this.

[0044] Step 104: training a rock mass deformation and failure prediction model according to the simulated data values ​​and the corresponding actual data values ​​to obtain a target rock mass deformation and failure prediction model.

[0045] The method for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics provided in the embodiment of the present application obtains a historical mining process flow of the area to be mined; wherein the historical mining process flow includes at least one mining distance and a corresponding mining time; according to the historical mining process flow, at least one set of simulation data values ​​is obtained through a preset digital rock mechanics solver; wherein the simulation data values ​​include the spatial position of the mining face when executing the mining distance included in one mining process flow at the mining time, and the corresponding stress state simulation value, displacement simulation value and rock deformation and damage simulation value of the preset measuring point in the area to be mined; for each step of the historical mining process flow, the actual data value of the area to be mined when each step of the historical mining process flow has been executed is obtained; wherein the actual data values ​​include the spatial position of the mining face when executing the mining distance included in one historical mining process flow at the mining time, and the corresponding actual value of the stress state, actual value of the displacement and actual value of the rock deformation and damage of the preset measuring point in the area to be mined; According to the simulated data values ​​and the corresponding actual data values, the rock deformation and failure prediction model is trained to obtain the target rock deformation and failure prediction model. Thus, through the preset digital rock mechanics solver, according to the spatial position of the mining face after the execution of the mining process and the corresponding mining time, the corresponding rock deformation and failure in the whole process of the mining process is obtained, which not only takes into account the heterogeneity of the ore body strata, but also takes into account the changes in the intrinsic physical logic of the ore body when the pressure and displacement distribution of the ore body changes under the mining conditions. Therefore, according to the simulated data values ​​and actual data values ​​obtained by the preset digital rock mechanics solver, the rock deformation and failure prediction model is trained to obtain the target rock deformation and failure prediction model, which improves the accuracy of the target rock deformation and failure prediction model, so that the mining rock deformation and failure after the execution of the mining process can be accurately predicted, providing intuitive cognition for the quantitative evaluation of the impact hazard of the ore body and the formulation of differentiated prevention and control measures, and improving the safety of the mining process.

[0046] In the embodiment of the present application, in order to clearly understand how the preset digital rock mechanics solver is obtained, the following is combined with Figure 2 A possible implementation of a preset digital rock mechanics solver is described exemplarily. Figure 2 The process of the method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in the embodiment of the present application Figure 2 .

[0047] like Figure 2 As shown, the method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics may include the following steps:

[0048] Step 201, obtaining standardized mine structure information and a three-dimensional geological model of the area to be mined.

[0049] It can be understood that the mine structure information at least includes the geological structure and geological body boundary of the area to be mined.

[0050] It is important to understand that the initially collected mine structure information of the area to be mined is relatively complex, which is not conducive to storage and sharing, nor is it conducive to the subsequent establishment of a three-dimensional geological model based on the mine structure information.

[0051] In order to obtain standardized mine structure information, as a possible implementation method, the mine structure information of the area to be mined is obtained, and the mine structure information of the area to be mined is standardized to obtain the standardized mine structure information.

[0052] As an example, the mine structure information of the area to be mined is obtained, and the mine structure information of the area to be mined is subjected to terminology standardization, data standardization and data set standardization to obtain standardized mine structure information.

[0053] For example, terminology standardization refers to the use of standardized professional terms to represent the nouns and concepts related to mine structure information, in accordance with national standards or industry standards, to avoid ambiguity; for example, basic terms related to mine rock mechanics are specified, including mining working faces, tunnels, stress monitoring, rock burst, dynamic disasters, etc.

[0054] As an example, based on the mine structure information, three-dimensional geological modeling is performed on the area to be mined to determine a three-dimensional geological model of the area to be mined.

[0055] Step 202: transform the three-dimensional geological model based on a triangulation algorithm and a spatial interpolation algorithm to determine a triangular mesh model for numerical analysis corresponding to the area to be mined.

[0056] It should be noted that the triangular mesh model is composed of three data structures: triangle vertices, edges and units.

[0057] In order to accurately establish a triangular mesh model, as an example, based on a three-dimensional geological model, an incremental method is used to establish a triangular mesh, and the mine structure information including the geological structure of the area to be mined, or the boundary of the geological body is embedded in the triangular mesh. The data of the triangle vertices is calculated through a spatial interpolation algorithm.

[0058] Step 203, determining a first theoretical formula for describing the physical logic of the rock mass in the area to be mined based on the elastic constitutive equation for describing the stress state of the area to be mined and the peridynamics and finite element coupling theoretical formula.

[0059] It can be understood that the elastic constitutive equation and the peridynamics and finite element coupling theory formula can be obtained according to public physical principles and mathematical formulas, and will not be described in detail in this embodiment.

[0060] It should be understood that since the elastic constitutive equation is generally applicable to the case of rock stability or dynamic equilibrium, and the peridynamics and finite element coupling theoretical formula is generally applicable to the case when the rock mass is fractured or dynamically unstable and the basic equations of elasticity are no longer applicable, the first theoretical formula determined according to the elastic constitutive equation and the peridynamics and finite element coupling theoretical formula can not only describe the stress state when the rock mass is stable, but also describe the stress state when the rock mass is fractured.

[0061] Step 204, obtaining a digital rock mechanics solver according to the triangular mesh model and the first theoretical formula.

[0062] In this example, after the mining face executes the mining distance, in the set spatial coordinate system, the spatial position of the mining face and the corresponding mining time are calculated through the preset digital rock mechanics solver to obtain the stress state simulation value, displacement simulation value and rock deformation and damage simulation value of the preset measuring points in the area to be mined.

[0063] For example, the example diagram of the process for determining the stress state simulation value and the rock deformation and failure simulation value is as follows: Figure 3 As shown, a theoretical formula for coupling peridynamics and finite elements is established, a first theoretical formula is determined according to the elastic constitutive equation and the theoretical formula for coupling peridynamics and finite elements, a digital rock mechanics solver is obtained according to the triangular mesh model and the first theoretical formula, a measuring point is set in the area to be mined, and a preset digital rock mechanics solver is used to determine the maximum principal stress value of the preset measuring point in the area to be mined according to the mining distance and mining time; the maximum principal stress value is calculated to determine the stress flow vector of the preset measuring point in the area to be mined; according to the stress flow vector, the stress state simulation value of the preset measuring point in the area to be mined when executing the historical mining process is determined; according to the maximum principal stress value of the preset measuring point in the area to be mined during the mining process, the rock deformation and damage simulation value of the area to be mined after the mining process is performed is determined.

[0064] The method for predicting deformation and failure of rock mass caused by mining based on digital rock mechanics provided in the embodiment of the present application obtains standardized mine structure information and a three-dimensional geological model of the area to be mined, transforms the three-dimensional geological model based on a triangulation algorithm and a spatial interpolation algorithm to determine a triangular mesh model for numerical analysis corresponding to the area to be mined, determines a first theoretical formula for describing the physical logic of the rock mass in the area to be mined based on the elastic constitutive equation for describing the stress state of the area to be mined and the theoretical formula for coupling peridynamics and finite elements, and obtains a digital rock mechanics solver based on the triangular mesh model and the first theoretical formula. Thus, through the first theoretical formula, the change of the intrinsic physical logic of the ore body under mining conditions is taken into account, and by combining the triangular mesh model with the first theoretical formula, it can be considered that the response of the rock mass in the mine to external disturbances during the mining process will undergo elastic, brittle fracture, dynamic ejection and other processes, so as to obtain a more comprehensive and accurate stress state of preset measuring points in the area to be mined during the mining process and the deformation and failure trend of the rock mass. When the rock mass deformation and failure prediction model is subsequently trained, a large number of training samples are not required to improve the accuracy of the prediction of the rock mass deformation and failure prediction model.

[0065] In the embodiment of the present application, in order to clearly understand that the rock deformation and failure prediction model is trained according to the simulated data value and the corresponding actual data value to obtain the target rock deformation and failure prediction model, the following is combined with Figure 4 A possible implementation method of the rock mass deformation and failure prediction model is described exemplarily. Figure 4 The process of the method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in the embodiment of the present application Figure 3 .

[0066] like Figure 4 As shown, the method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics may include the following steps:

[0067] Step 401, determining a first loss value of the rock deformation and failure prediction model according to a first loss function of the rock deformation and failure prediction model, a rock deformation and failure simulation value included in the simulation data value, and a rock deformation and failure actual value included in the corresponding actual data value.

[0068] It should be noted that the first loss function includes the corresponding first target recognition parameter.

[0069] In order to obtain the first identification parameter, as a possible implementation method, the first identification parameter corresponding to the first loss function is determined based on the first relationship between the mining distance and the corresponding mining time included in the execution of the historical mining process and the rock deformation and failure, as well as the total number of mining steps in the historical mining process.

[0070] As an example, for each step of the historical mining process, the mining distance and the corresponding mining time included in the execution of the historical mining process are obtained; based on the mining distance and the corresponding mining time, the first relationship between the mining distance and the corresponding mining time and the deformation and damage of the rock mass is determined; based on the first relationship and the total number of mining steps in the historical mining process, the first identification parameter corresponding to the first loss function is determined.

[0071] In order to select the optimal first target recognition parameter, as a possible implementation method, the first recognition parameter is adjusted according to the first loss value to obtain the first target recognition parameter corresponding to the first loss function.

[0072] As an example, the first recognition parameter is adjusted according to the first loss value until the adjustment is terminated when the first loss value meets a preset condition; the first recognition parameter obtained when the adjustment is terminated is used as the first target recognition parameter corresponding to the first loss function.

[0073] For example, the first relational expression can be expressed as F=N(Y,T;θ), and the optimal value of the first recognition parameter θ (the first target recognition parameter) can be expressed as It should be noted that θ is used to represent the first identification parameter, F is used to represent rock mass deformation and damage, mining distance Y and mining time T, N m Represents the total number of mining steps in the historical mining process, Represents a set of training samples including mining distance, mining time and rock deformation and failure.

[0074] Step 402, determining a second loss value of the rock deformation and failure prediction model according to the second loss function of the rock deformation and failure prediction model, the rock deformation and failure simulation values ​​included in the simulation data values, and the rock deformation and failure actual values ​​included in the corresponding actual data values.

[0075] It should be noted that the second loss function includes the corresponding second target recognition parameter.

[0076] In order to obtain the second identification parameter, as a possible implementation method, the second identification parameter corresponding to the second loss function is determined based on the spatial position of the mining working face and the corresponding second relationship between the mining time and the stress state, displacement and rock deformation and failure, as well as the total number of mining steps in the historical mining process.

[0077] As an example, for each step of the historical mining process, the mining distance and the corresponding mining time included in the execution of the historical mining process are obtained; when executing the mining distance included in the historical mining process, the spatial position of the mining face at the corresponding mining time is obtained, and based on the spatial position of the mining face and the corresponding mining time, the second relationship between the spatial position of the mining face and the corresponding mining time and the stress state, displacement and rock deformation and failure is determined; based on the second relationship and the total number of mining steps in the historical mining process, the second identification parameter corresponding to the second loss function is determined.

[0078] As an example, the second recognition parameter is adjusted according to the second loss value until the adjustment is ended when the second loss value meets a preset condition; the second recognition parameter obtained when the adjustment is ended is used as the second target recognition parameter corresponding to the second loss function.

[0079] For example, the second relationship can be expressed as G(σ,u,F)=N(X,Y,Z,T;θ * ), the optimal value of the second recognition parameter θ* (the second target recognition parameter) can be expressed as

[0081] Among them, it should be noted that is a neural network operator, the first term is a data-driven term, represents a set of training samples including the spatial position of the mining face, mining time, and rock deformation and damage; the second item is the mine physical logic information item, which is the residual item of the physical equation. The model parameters are Time and space position The stress-strain relationship in the area, the total number of mining steps is N n .

[0082] Step 403, adjusting the model parameters of the rock deformation and failure prediction model according to the first loss value and the second loss value, and continuing to train the adjusted rock deformation and failure prediction model until the first loss value and the second loss value meet the preset conditions and the training is terminated.

[0083] It should be noted that the preset condition is the condition for the end of model training. The preset condition can be configured accordingly according to actual needs. For example, the preset condition can be that the loss value is less than the preset value, or that the change of the loss value tends to be stable, that is, the difference between the loss values ​​corresponding to two or more consecutive trainings is less than the set value, that is, the loss value basically does not change.

[0084] Step 404: The rock mass deformation and failure prediction model obtained when the training is finished is used as the target rock mass deformation and failure prediction model.

[0085] The mining rock deformation and failure prediction method based on digital rock mechanics provided in the embodiment of the present application determines the first loss value of the rock deformation and failure prediction model according to the first loss function of the rock deformation and failure prediction model, the rock deformation and failure simulation value included in the simulation data value and the rock deformation and failure actual value included in the corresponding actual data value; determines the second loss value of the rock deformation and failure prediction model according to the second loss function of the rock deformation and failure prediction model, the rock deformation and failure simulation value included in the simulation data value and the rock deformation and failure actual value included in the corresponding actual data value; adjusts the model parameters of the rock deformation and failure prediction model according to the first loss value and the second loss value, and continues to train the adjusted rock deformation and failure prediction model until the first loss value and the second loss value meet the preset conditions, and the training is terminated; the rock deformation and failure prediction model obtained at the end of the training is used as the target rock deformation and failure prediction model; thereby, the rock deformation and failure prediction model is continuously adjusted according to the first loss function and the second loss function; the optimal first target recognition parameter and the second target recognition parameter are determined by adjusting the first recognition parameter and the second recognition parameter, thereby improving the prediction accuracy of the rock deformation and failure prediction model.

[0086] For example, the example diagram corresponding to the rock deformation and failure prediction model training process is as follows: Figure 5 As shown, the three-dimensional geological model of the ore body is built, and the mining distance and mining time are determined based on the three-dimensional geological model modeling. The rock deformation and damage simulation value is obtained through the preset digital rock mechanics solver, and the mining condition is digitally expressed. It is judged whether the difference between the rock deformation and damage simulation value and the rock deformation and damage actual value meets the error. If the error is met, the termination condition of the rock deformation and damage prediction model training is simulated. If the termination condition is met, the training of the rock deformation and damage prediction model is terminated; if the termination condition is not met, the training is repeated. If the error is not met, the training is repeated.

[0087] Figure 6 A flowchart of a method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics provided in an embodiment of the present application Figure 4 .

[0088] Step 601, obtaining a mining process flow preset for the mining area to be executed; wherein the mining process flow includes at least one mining distance and a corresponding mining time.

[0089] Step 602, for each step of the mining process to be executed, obtain the spatial position of the mining face and the corresponding mining time when executing the mining distance included in the mining process.

[0090] Step 603, using the target rock mass deformation and failure prediction model, according to the spatial position of the mining working face and the corresponding mining time, predict the mining-induced rock mass deformation and failure in the to-be-mined area after the mining process is executed.

[0091] It should be noted that for the specific description of steps 601 to 603, reference can be made to other descriptions of this embodiment, which will not be repeated here.

[0092] In this embodiment, a mining process to be executed that is preset for the area to be mined is obtained; wherein the mining process includes at least one mining distance and a corresponding mining time; for each step of the mining process to be executed, the spatial position of the mining face and the corresponding mining time when executing the mining distance included in the mining process are obtained, and the target rock deformation and damage prediction model is adopted. According to the spatial position of the mining face and the corresponding mining time, the rock deformation and damage of the area to be mined after the mining process is executed are predicted. Thus, according to the target rock deformation and damage prediction model, the deformation and damage of the mining-induced rock after the mining process is executed can be accurately predicted, providing intuitive cognition for the quantitative evaluation of the ore body impact hazard and the formulation of differentiated prevention and control measures.

[0093] In order to implement the above-mentioned embodiments, the present application also proposes a device for predicting deformation and damage of rock mass caused by mining based on digital rock mechanics.

[0094] Figure 7 A schematic diagram showing the structure of a device for predicting rock deformation and failure caused by mining based on digital rock mechanics provided in an embodiment of the present application.

[0095] like Figure 7 As shown, the mining rock deformation and failure prediction device 700 based on digital rock mechanics includes: a first acquisition module 701, a first obtaining module 702, a second acquisition module 703 and a training module 704.

[0096] The first acquisition module 701 is used to acquire the historical mining process flow of the area to be mined; wherein the historical mining process flow includes at least one step of mining distance and the corresponding mining time;

[0097] The first obtaining module 702 is used to obtain at least one set of simulation data values ​​through a preset digital rock mechanics solver according to the historical mining process; wherein the simulation data values ​​include the spatial position of the mining face and the corresponding stress state simulation value, displacement simulation value and rock deformation and failure simulation value of the preset measuring point in the to-be-mined area when the mining distance included in the historical mining process is executed at the mining time;

[0098] The second acquisition module 703 is used to acquire, for each step of the historical mining process, the actual data value of the area to be mined when each step of the historical mining process has been executed; wherein the actual data value includes the spatial position of the mining face when the mining distance included in the step of the historical mining process is executed at the mining time, and the corresponding actual value of the stress state, the actual value of the displacement, and the actual value of the rock deformation and damage of the preset measuring point in the area to be mined;

[0099] The training module 704 is used to train the rock mass deformation and failure prediction model according to the simulated data values ​​and the corresponding actual data values ​​to obtain the target rock mass deformation and failure prediction model.

[0100] In one embodiment of the present application, the digital rock mechanics solver module is specifically used to:

[0101] Obtain standardized mine structure information and 3D geological models of the area to be mined;

[0102] Based on the triangulation algorithm and the spatial interpolation algorithm, the three-dimensional geological model is transformed to determine the triangular mesh model for numerical analysis corresponding to the area to be mined;

[0103] Determine a first theoretical formula for describing the physical logic of the rock mass in the area to be mined based on an elastic constitutive equation for describing the stress state of the area to be mined and a coupling theoretical formula of peridynamics and finite element analysis;

[0104] According to the triangular mesh model and the first theoretical formula, a digital rock mechanics solver is obtained.

[0105] In one embodiment of the present application, the first obtaining module 702 is specifically used to:

[0106] For each step of the historical mining process, obtain the mining distance and mining time included in the execution of the historical mining process;

[0107] Using a preset digital rock mechanics solver, according to the mining distance and mining time when executing the historical mining process, the stress state simulation value of the preset measuring point in the to-be-mined area when executing the historical mining process is determined;

[0108] When executing the mining distance included in the historical mining process, the spatial position of the mining working face in the spatial coordinate system at the corresponding mining time is obtained, and the corresponding stress state simulation value of the preset measuring point in the area to be mined is determined at the spatial position of the mining working face;

[0109] Determine the displacement simulation value of the corresponding preset measuring point in the area to be mined according to the mining distance when executing the historical mining process and the spatial position of the mining working face;

[0110] According to the stress state simulation value and displacement simulation value of the preset measuring point in the to-be-mined area when executing the historical mining process, the rock deformation and damage simulation value of the to-be-mined area after executing the historical mining process is determined.

[0111] In one embodiment of the present application, the first obtaining module 702 is specifically used to:

[0112] Using a preset digital rock mechanics solver, according to the mining distance and mining time when executing the historical mining process, the maximum principal stress value of the preset measuring point in the to-be-mined area when executing the historical mining process is determined;

[0113] The maximum principal stress value is calculated to determine the stress flow vector of the preset measuring point in the area to be mined when executing the historical mining process;

[0114] According to the stress flow vector, the stress state simulation value of the preset measuring point in the to-be-mined area when executing the historical mining process is determined.

[0115] In one embodiment of the present application, the training module 704 is specifically used to:

[0116] Determine a first loss value of the rock mass deformation and failure prediction model according to a first loss function of the rock mass deformation and failure prediction model, a rock mass deformation and failure simulation value included in the simulation data value, and a rock mass deformation and failure actual value included in the corresponding actual data value;

[0117] Determine a second loss value of the rock mass deformation and failure prediction model according to a second loss function of the rock mass deformation and failure prediction model, a rock mass deformation and failure simulation value included in the simulation data value, and a rock mass deformation and failure actual value included in the corresponding actual data value;

[0118] According to the first loss value and the second loss value, the model parameters of the rock deformation and failure prediction model are adjusted, and the adjusted rock deformation and failure prediction model is continuously trained until the first loss value and the second loss value meet the preset conditions and the training is terminated;

[0119] The rock mass deformation and failure prediction model obtained at the end of training is used as the target rock mass deformation and failure prediction model.

[0120] In one embodiment of the present application, the training module 704 is specifically used to:

[0121] For each step of the historical mining process, obtain the mining distance and corresponding mining time included in the execution of the historical mining process;

[0122] According to the mining distance and the corresponding mining time, a first relationship between the mining distance and the corresponding mining time and the deformation and failure of the rock mass is determined;

[0123] A first identification parameter corresponding to the first loss function is determined based on the first relationship and the total number of mining steps in the historical mining process.

[0124] In one embodiment of the present application, the training module 704 is specifically used to:

[0125] According to the first loss value, the first identification parameter is adjusted until the adjustment is terminated when the first loss value satisfies a preset condition;

[0126] The first recognition parameter obtained when the adjustment is finished is used as the first target recognition parameter corresponding to the first loss function.

[0127] In one embodiment of the present application, the training module 704 is specifically used to:

[0128] For each step of the historical mining process, obtain the mining distance and corresponding mining time included in the execution of the historical mining process;

[0129] When executing the mining distance included in the historical mining process, obtain the spatial position of the mining face at the corresponding mining time

[0130] According to the spatial position of the mining face and the corresponding mining time, a second relationship between the spatial position of the mining face and the corresponding mining time and the stress state, displacement and rock mass deformation and failure is determined;

[0131] A second identification parameter corresponding to the second loss function is determined based on the second relationship and the total number of mining steps in the historical mining process.

[0132] In one embodiment of the present application, the training module 704 is specifically used to:

[0133] According to the second loss value, the second identification parameter is adjusted until the adjustment is terminated when the second loss value satisfies a preset condition;

[0134] The second recognition parameter obtained when the adjustment is finished is used as the second target recognition parameter corresponding to the second loss function.

[0135] In addition, in one embodiment of the present application, the device also includes a rock deformation and failure prediction module, which is specifically used to:

[0136] Obtaining a mining process to be executed preset for the mining area; wherein the mining process includes at least one mining distance and a corresponding mining time;

[0137] For each step of the mining process to be executed, the spatial position of the mining face and the corresponding mining time when the mining distance included in the mining process is executed are obtained;

[0138] The target rock deformation and failure prediction model is used to predict the rock deformation and failure in the to-be-mined area after the mining process is executed according to the spatial position of the mining working face and the corresponding mining time.

[0139] The mining rock deformation and destruction prediction device based on digital rock mechanics provided in the embodiment of the present application obtains the historical mining process of the area to be mined; wherein the historical mining process includes at least one mining distance and the corresponding mining time; according to the historical mining process, at least one set of simulation data values ​​is obtained through a preset digital rock mechanics solver; wherein the simulation data values ​​include the spatial position of the mining face when executing the mining distance included in one mining process step at the mining time, and the corresponding stress state simulation value, displacement simulation value and rock deformation and destruction simulation value of the preset measuring point in the area to be mined; for each step of the historical mining process, the actual data value of the area to be mined when each step of the historical mining process has been executed is obtained; wherein the actual data values ​​include the spatial position of the mining face when executing the mining distance included in one historical mining process step at the mining time, and the corresponding stress state actual value, displacement actual value and rock deformation and destruction actual value of the preset measuring point in the area to be mined; According to the simulated data values ​​and the corresponding actual data values, the rock deformation and failure prediction model is trained to obtain the target rock deformation and failure prediction model. Thus, through the preset digital rock mechanics solver, according to the spatial position of the mining face after the execution of the mining process and the corresponding mining time, the corresponding rock deformation and failure in the whole process of the mining process is obtained, which not only takes into account the heterogeneity of the ore body strata, but also takes into account the changes in the intrinsic physical logic of the ore body when the pressure and displacement distribution of the ore body changes under the mining conditions. Therefore, according to the simulated data values ​​and actual data values ​​obtained by the preset digital rock mechanics solver, the rock deformation and failure prediction model is trained to obtain the target rock deformation and failure prediction model, which improves the accuracy of the target rock deformation and failure prediction model, so that the mining rock deformation and failure after the execution of the mining process can be accurately predicted, providing intuitive cognition for the quantitative evaluation of the impact hazard of the ore body and the formulation of differentiated prevention and control measures, and improving the safety of the mining process.

[0140] It should be noted that the aforementioned explanation of the embodiment of the method for predicting deformation and failure of rock mass due to mining based on digital rock mechanics is also applicable to the device for predicting deformation and failure of rock mass due to mining based on digital rock mechanics of this embodiment, and will not be repeated here.

[0141] In order to implement the above embodiments, the present application also proposes an electronic device.

[0142] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0143] like Figure 8 As shown, the electronic device 800 may include: a processor 802, and a memory 803 communicatively connected to the processor 802; the memory 803 stores computer-executable instructions; the processor 802 executes the computer-executable instructions stored in the memory 803 to implement the method provided in the aforementioned embodiment.

[0144] Furthermore, the electronic device 800 further includes:

[0145] The transceiver 801 is used for communication between the memory 803 and the processor 802 .

[0146] The memory 803 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0147] If the memory 803, the processor 802 and the transceiver 801 are implemented independently, the transceiver 801, the memory 803 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0148] Optionally, in a specific implementation, if the memory 803, the processor 802 and the transceiver 801 are integrated on a chip, the memory 803, the processor 802 and the transceiver 801 can communicate with each other through an internal interface.

[0149] The processor 802 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0150] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0151] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0152] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0153] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0154] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0155] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0156] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0157] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0158] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0159] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0160] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0161] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0162] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for predicting rock mass deformation and failure caused by mining based on digital rock mechanics, characterized in that: The following steps are involved: Obtaining a historical mining process flow of the area to be mined; wherein the historical mining process flow includes at least one step of mining distance and corresponding mining time; According to the historical mining process, at least one set of simulation data values ​​is obtained through a preset digital rock mechanics solver; wherein the simulation data values ​​include the spatial position of the mining face and the corresponding stress state simulation value, displacement simulation value and rock deformation and failure simulation value of the preset measuring point in the area to be mined when the mining distance included in the historical mining process is executed at the mining time; For each step of the historical mining process, the actual data value of the area to be mined when each step of the historical mining process has been executed is obtained; wherein the actual data value includes the spatial position of the mining face when the mining distance included in one step of the historical mining process is executed at the mining time, and the corresponding actual value of the stress state, actual value of the displacement and actual value of the rock deformation and damage of the preset measuring point in the area to be mined; The rock mass deformation and failure prediction model is trained according to the simulated data values ​​and the corresponding actual data values ​​to obtain a target rock mass deformation and failure prediction model.

2. The method according to claim 1, characterized in that: The preset digital rock mechanics solver is obtained as follows: Obtaining standardized mine structure information and a three-dimensional geological model of the area to be mined; Based on a triangulation algorithm and a spatial interpolation algorithm, the three-dimensional geological model is transformed to determine a triangular mesh model for numerical analysis corresponding to the area to be mined; Determine a first theoretical formula for describing the physical logic of the rock mass in the area to be mined based on an elastic constitutive equation for describing the stress state of the area to be mined and a peridynamics and finite element coupling theoretical formula; The digital rock mechanics solver is obtained according to the triangular mesh model and the first theoretical formula.

3. The method according to claim 1, characterized in that According to the historical mining process, at least one set of simulation data values ​​is obtained through a preset digital rock mechanics solver; wherein the simulation data values ​​include the spatial position of the mining face and the corresponding stress state simulation value, displacement simulation value and rock deformation and failure simulation value of the preset measuring point in the to-be-mined area when the mining distance included in the historical mining process is executed at the mining time, including: For each step of the historical mining process, obtaining the mining distance and mining time included in executing the historical mining process; Using the preset digital rock mechanics solver, according to the mining distance and mining time when executing the historical mining process, determine the stress state simulation value of the preset measuring point in the to-be-mined area when executing the historical mining process; Determine the displacement simulation value of the corresponding preset measuring point in the area to be mined according to the mining distance when executing the historical mining process and the spatial position of the mining working face; The rock deformation and damage simulation value of the to-be-mined area after the historical mining process is executed is determined according to the stress state simulation value and the displacement simulation value of the preset measuring point in the to-be-mined area when the historical mining process is executed.

4. The method according to claim 3, characterized in that The method of using the preset digital rock mechanics solver to determine the stress state simulation value of the preset measuring point in the to-be-mined area when executing the historical mining process according to the mining distance and mining time when executing the historical mining process comprises: Using the preset digital rock mechanics solver, according to the mining distance and mining time when executing the historical mining process, determine the maximum principal stress value of the preset measuring point in the to-be-mined area when executing the historical mining process; Calculating the maximum principal stress value to determine the stress flow vector of a preset measuring point in the to-be-mined area when executing the historical mining process; According to the stress flow vector, the stress state simulation value of the preset measuring point in the to-be-mined area when executing the historical mining process is determined.

5. The method according to claim 1, characterized in that: The step of training the rock mass deformation and failure prediction model according to the simulated data value and the corresponding actual data value to obtain the target rock mass deformation and failure prediction model includes: Determine a first loss value of the rock mass deformation and failure prediction model according to a first loss function of the rock mass deformation and failure prediction model, the rock mass deformation and failure simulation value included in the simulation data value, and the rock mass deformation and failure actual value included in the corresponding actual data value; Determine a second loss value of the rock mass deformation and failure prediction model according to a second loss function of the rock mass deformation and failure prediction model, the rock mass deformation and failure simulation value included in the simulation data value, and the rock mass deformation and failure actual value included in the corresponding actual data value; According to the first loss value and the second loss value, the model parameters of the rock deformation and failure prediction model are adjusted, and the adjusted rock deformation and failure prediction model is continuously trained until the training is terminated when the first loss value and the second loss value meet a preset condition; The rock mass deformation and failure prediction model obtained at the end of the training is used as the target rock mass deformation and failure prediction model.

6. The method according to claim 5, characterized in that The first loss function includes a corresponding first target recognition parameter, and the first target recognition parameter is obtained as follows: For each step of the historical mining process, obtaining the mining distance and the corresponding mining time included in executing the historical mining process; Determine, according to the mining distance and the corresponding mining time, a first relationship between the mining distance and the corresponding mining time and rock mass deformation and failure; A first identification parameter corresponding to the first loss function is determined based on the first relationship and the total number of mining steps in the historical mining process. According to the first loss value, the first identification parameter is adjusted until the first loss value satisfies a preset condition and the adjustment is terminated; The first recognition parameter obtained when the adjustment is finished is used as the first target recognition parameter corresponding to the first loss function.

7. The method according to claim 5, characterized in that The second loss function includes a corresponding second target recognition parameter, and the second target recognition parameter is obtained as follows: For each step of the historical mining process, obtaining the mining distance and the corresponding mining time included in executing the historical mining process; When executing the mining distance included in the historical mining process, the spatial position of the mining face at the corresponding mining time is obtained. Determine, according to the spatial position of the mining face and the corresponding mining time, a second relationship between the spatial position of the mining face and the corresponding mining time and the stress state, displacement and rock mass deformation and failure; A second identification parameter corresponding to the second loss function is determined based on the second relationship and the total number of mining steps in the historical mining process. According to the second loss value, adjusting the second identification parameter until the second loss value satisfies a preset condition and the adjustment is terminated; The second recognition parameter obtained when the adjustment is finished is used as the second target recognition parameter corresponding to the second loss function.

8. The method according to any one of claims 1 to 7, characterized in that: After training the rock mass deformation and failure prediction model according to the simulated data values ​​and the corresponding actual data values ​​to obtain the target rock mass deformation and failure prediction model, the method further includes: Obtaining a mining process to be executed preset for the mining area; wherein the mining process includes at least one mining distance and a corresponding mining time; For each step of the mining process to be executed, obtaining the spatial position of the mining face and the corresponding mining time when executing the mining distance included in the mining process; The target rock deformation and failure prediction model trained by the method described in any one of claims 1 to 7 is used to predict the deformation and failure of the rock mass in the to-be-mined area after executing the mining process according to the spatial position of the mining working face and the corresponding mining time.

9. A device for predicting rock mass deformation and failure caused by mining based on digital rock mechanics, characterized in that: The following steps are involved: A first acquisition module is used to acquire a historical mining process flow of the area to be mined; wherein the historical mining process flow includes at least one step of mining distance and corresponding mining time; The first obtaining module is used to obtain at least one set of simulation data values ​​through a preset digital rock mechanics solver according to the historical mining process; wherein the simulation data values ​​include the spatial position of the mining face and the corresponding stress state simulation value, displacement simulation value and rock deformation and failure simulation value of the preset measuring point in the to-be-mined area when the mining distance included in the historical mining process is executed at the mining time; A second acquisition module is used to acquire, for each step of the historical mining process, the actual data value of the area to be mined when each step of the historical mining process has been executed; wherein the actual data value includes the spatial position of the mining face when the mining distance included in a step of the historical mining process is executed at the mining time, and the corresponding actual value of the stress state, actual value of the displacement and actual value of the rock deformation and damage of the preset measuring point in the area to be mined; The training module is used to train the rock mass deformation and failure prediction model according to the simulated data values ​​and the corresponding actual data values ​​to obtain a target rock mass deformation and failure prediction model.

Images