Deep engineering complete surrounding rock rib caving damage depth prediction method, device, equipment, medium and product

Abstract

The invention discloses a method, a device, equipment, a medium and a product for predicting the fracture depth of a complete surrounding rock caving of deep engineering, and relates to the field of rock mechanics. The method comprises the following steps of: acquiring primary rock stress at a potential caving occurrence position of a deep engineering complete surrounding rock; calculating a crack splitting failure mode evaluation index and rock true triaxial crack initiation stress according to the primary rock stress; calculating the tunnel size and the height-span ratio of the deep engineering complete surrounding rock according to the overall structure of the deep engineering complete surrounding rock; calculating the maximum concentrated stress of the tunnel wall caving area of the complete surrounding rock of the deep engineering according to the primary rock stress and the height span ratio; and obtaining the caving failure depth of the complete surrounding rock of the deep engineering by using the caving failure depth prediction model. And accurate prediction of the caving damage depth is realized.

Description

Technical Field

[0001] The present application relates to the field of rock mechanics, and in particular to a method, device, equipment, medium and product for predicting the failure depth of intact surrounding rock spalling in deep engineering. Background Art

[0002] Spalling in deep engineering refers to the phenomenon of rock cracking inside the rock due to high ground stress, complex geological conditions, strong tectonic activities and other factors during deep underground mining or tunnel excavation, resulting in the formation of sheet or plate-like rock strata peeling or collapse on the side walls of the engineering structure. Spalling is more common in deep tunnels, mines, underground powerhouses and other projects, posing a serious threat to the safety and stability of the project. Therefore, the study of spalling in deep underground engineering is of great significance in ensuring engineering safety, improving economic benefits, protecting the environment, and promoting scientific theory and technological progress.

[0003] Traditional methods for assessing the depth of surrounding rock spalling failure mostly rely on empirical formulas, analog engineering or simple mechanical analysis. These methods often fail to fully consider the complex geological environment of deep underground projects and the mechanical behavior of rocks under multi-field coupling. Most existing assessment methods are based on one-dimensional / two-dimensional stress states for analysis, and fail to truly reflect the initiation strength of rocks under true triaxial stress conditions. In addition, in deep projects, rock failure forms a variety of ways, among which splitting failure and spalling failure have certain similarities in their manifestations. Existing assessment methods often fail to effectively distinguish between these two failure modes, resulting in deviations in the assessment results of spalling failure depth. In addition, traditional assessment methods have limitations when dealing with nonlinear, multi-factor coupled complex systems, and it is difficult to accurately predict the failure depth of surrounding rock spalling. Summary of the invention

[0004] The purpose of this application is to provide a method, device, equipment, medium and product for predicting the depth of failure of complete surrounding rock spalling in deep engineering, which can realize accurate prediction of the depth of failure of spalling.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for predicting the failure depth of complete surrounding rock spalling in deep engineering, the method comprising:

[0007] Obtain the original rock stress at the potential location of spalling of the intact surrounding rock of deep engineering projects;

[0008] Calculate the crack splitting failure mode evaluation index and the rock true triaxial crack initiation stress according to the original rock stress; the crack splitting failure mode evaluation index is an evaluation index of the crack splitting failure mode related to the splitting failure mode of the complete surrounding rock of the deep engineering under the three-dimensional stress state;

[0009] Calculate the tunnel size and height-to-span ratio of the deep engineering complete surrounding rock according to the overall structure of the deep engineering complete surrounding rock;

[0010] Calculate the maximum concentrated stress in the tunnel spalling area of ​​the complete surrounding rock of the deep engineering according to the original rock stress and the height-to-span ratio;

[0011] The original rock stress, crack splitting failure mode evaluation index, rock true triaxial crack initiation stress, tunnel size and height-span ratio are input into the spalling failure depth prediction model to obtain the spalling failure depth of the intact surrounding rock of the deep engineering; the spalling failure depth prediction model is obtained by training the random forest model.

[0012] In a second aspect, a device for predicting the damage depth of complete surrounding rock spalling in deep engineering is provided. The device for predicting the damage depth of complete surrounding rock spalling in deep engineering applies the above-mentioned method for predicting the damage depth of complete surrounding rock spalling in deep engineering. The device for predicting the damage depth of complete surrounding rock spalling in deep engineering comprises:

[0013] The original rock stress acquisition module is used to obtain the original rock stress at the potential location of spalling in the intact surrounding rock of deep engineering projects;

[0014] The first calculation module is used to calculate the crack splitting failure mode evaluation index and the rock true triaxial crack initiation stress according to the original rock stress; the crack splitting failure mode evaluation index is an evaluation index of the crack splitting failure mode related to the splitting failure mode of the complete surrounding rock of the deep engineering under the three-dimensional stress state;

[0015] The second calculation module is used to calculate the tunnel size and height-span ratio of the complete surrounding rock of the deep engineering according to the overall structure of the complete surrounding rock of the deep engineering;

[0016] A third calculation module is used to calculate the maximum concentrated stress in the tunnel spalling area of ​​the complete surrounding rock of the deep engineering according to the original rock stress and the height-to-span ratio;

[0017] The prediction module is used to input the original rock stress, crack splitting failure mode evaluation index, rock true triaxial crack initiation stress, tunnel size and height-span ratio into the spalling failure depth prediction model to obtain the spalling failure depth of the complete surrounding rock of the deep engineering; the spalling failure depth prediction model is obtained by training the random forest model.

[0018] In a third aspect, a computer device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for predicting the depth of complete surrounding rock fragmentation failure in deep engineering.

[0019] In a fourth aspect, a computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned method for predicting the depth of complete surrounding rock spalling failure in deep engineering.

[0020] In a fifth aspect, a computer program product includes a computer program, which, when executed by a processor, implements the above-mentioned method for predicting the depth of complete surrounding rock fragmentation failure in deep engineering.

[0021] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0022] The present application provides a method, device, equipment, medium and product for predicting the failure depth of complete surrounding rock spalling in deep engineering. The present application uses original rock stress, crack splitting failure mode evaluation index, rock true triaxial crack initiation stress, tunnel size and height-span ratio as prediction parameters, and uses the powerful nonlinear processing ability and good generalization performance of the random forest algorithm to achieve accurate judgment of the failure depth of complete surrounding rock spalling in underground engineering. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A schematic diagram of a flow chart of a method for predicting the depth of complete surrounding rock spalling failure in deep engineering provided in one embodiment of the present application;

[0025] Figure 2 A flowchart of training a random forest model to obtain a prediction model for the depth of chipping damage provided by an embodiment of the present application;

[0026] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0029] Based on the analysis of the existing evaluation methods in the above background technology, the existing evaluation methods have the following defects:

[0030] First, existing assessment methods often ignore the impact of the important factor of the plant height-to-span ratio on the depth of spalling failure. As a key parameter of the plant structure, the height-to-span ratio directly determines the distribution of stress on the surrounding rock, which in turn affects the depth and range of spalling failure. Secondly, the surrounding rock in deep engineering is often in a complex three-dimensional stress environment, and the rock's cracking strength is affected by the true triaxial stress.

[0031] Based on the above defects, in an exemplary embodiment, Figure 1 As shown, a method for predicting the failure depth of complete surrounding rock spalling in deep engineering is provided, comprising the following steps 101 to 105. Among them:

[0032] Step 101, obtaining the original rock stress at the potential location of spalling of the intact surrounding rock of the deep engineering.

[0033] Step 102, calculating the crack splitting failure mode evaluation index and the rock true triaxial crack initiation stress according to the original rock stress; the crack splitting failure mode evaluation index is an evaluation index of the crack splitting failure mode related to the splitting failure mode of the complete surrounding rock of the deep engineering under the three-dimensional stress state.

[0034] Step 103, calculating the tunnel size and height-to-span ratio of the complete surrounding rock of the deep engineering according to the overall structure of the complete surrounding rock of the deep engineering.

[0035] Step 104, calculating the maximum concentrated stress in the tunnel spalling area of ​​the complete surrounding rock of the deep engineering project based on the original rock stress and the height-to-span ratio.

[0036] Step 105, input the original rock stress, crack splitting failure mode evaluation index, rock true triaxial crack initiation stress, tunnel size and height-span ratio into the spalling failure depth prediction model to obtain the spalling failure depth of the intact surrounding rock of the deep engineering; the spalling failure depth prediction model is obtained by training the random forest model.

[0037] In another exemplary embodiment, in order to obtain the original rock stress, the above step 101 can be implemented by the following steps:

[0038] First, the type of surrounding rock, the overall structure and size of the project are determined based on the project address information and the project design document. The stress magnitude and direction in the project area are measured using a surrounding rock stress gauge, which serves as the stress boundary of numerical calculation models such as FLAC 3D to predict the potential occurrence location of deep project surrounding rock spalling relative to the project geometric section.

[0039] Then, the original rock stress (σ1, σ2, σ3) at the potential location of spalling is extracted according to the numerical simulation results (or measured using a surrounding rock stress gauge), where σ1, σ2, σ3 are the maximum principal stress, intermediate principal stress, and minimum principal stress in the original rock stress, respectively.

[0040] In another exemplary embodiment, in order to realize the calculation of the crack splitting failure mode evaluation index and the true triaxial crack initiation stress of rock, the above step 102 can be implemented by the following steps:

[0041] When the indoor true triaxial test conditions allow, indoor true triaxial tests under low (0-5 MPa) minimum principal stress and different intermediate principal stress conditions can be carried out to construct the stress-strain curve, and then the true triaxial crack initiation stress of rock can be calculated based on the stress-strain curve. and the peak intensity σ p , and then according to the crack growth capacity formula (σ p is the peak strength), and the crack splitting failure mode evaluation index c related to the splitting failure mode under the three-dimensional stress state is calculated. p In this embodiment, the true triaxial crack initiation stress of rock is calculated based on the stress-strain curve. The method is as follows: mark the origin of the curve and the damage stress point (the stress corresponding to the maximum value of the volume strain curve) in the strain curve where the stress of the rock is in the direction of the minimum principal stress, connect the origin and the damage stress point to obtain a reference line, calculate the difference between the measured strain in the direction of the minimum principal stress and the reference line, and the stress corresponding to the maximum point of the difference is the true triaxial cracking stress of the rock.

[0042] When the indoor true triaxial test conditions cannot be met, the "c p =0.3” is the critical condition for the occurrence of splitting failure of deep engineering hard rock under three-dimensional stress state, so as to estimate the crack extension capacity of relevant hard rock; when the indoor true triaxial test conditions cannot be met, the relevant formula can be used Crack initiation stress To estimate, where σ p is the peak intensity. At this time, the peak intensity can be expressed by the formula and Calculated, where σ m,2 is the effective mean stress, τ oct is the octahedral shear stress, is the internal friction angle of the complete surrounding rock of the deep engineering project, and the corresponding rock cohesion c and internal friction angle It can be obtained based on conventional triaxial tests.

[0043] In another exemplary embodiment, in order to calculate the tunnel size and the height-to-span ratio, the above step 103 may be implemented by the following steps:

[0044] The height-to-span ratio of the project is calculated based on the overall structure and size of the project. The radius r of a small circular tunnel is determined, the effective radius r of a medium-sized "D" type tunnel or a large main powerhouse is determined, and the height H and span D of each excavation layer of a large underground powerhouse under the layered and partial excavation method.

[0045] In this step, when the height-to-span ratio H / D≤2, the original value is used; when H / D>2, it is calculated as equal to 2. For a large underground powerhouse, H is the sum of the heights of each layer that has been excavated. For example, when the excavation of the first III layers of the underground powerhouse is completed, the excavated height H=H I +H II +H III .

[0046] In another exemplary embodiment, in order to calculate the maximum concentrated stress in the tunnel wall area, the above step 104 can be implemented by the following steps:

[0047] According to the formula σ max =(aσ2-σ3)ln(d)+(σ1+σ2+σ3), determine the maximum concentrated stress σ in the tunnel wall area max , where a is the coefficient. When σ2≠σ3, a=1; when σ2=σ3, a=1.1.

[0048] In another exemplary embodiment of the present application, in order to implement the training of the random forest model, as Figure 2 As shown, the following training process is set up:

[0049] The random forest algorithm is used to map the input features to the output variables (flaking damage depth) to build the model. The mathematical function expression of the model is:

[0050]

[0051] The parameters of the random forest model are: the number of decision trees (50), the maximum depth of the tree (10), the minimum number of samples required for node splitting (8), the minimum number of samples required for leaf nodes (5), and the number of features used by each decision tree (sqrt). These parameters can also be optimized through methods such as cross-validation.

[0052] From the monitoring records of multiple underground projects, relevant data such as the type of surrounding rock, the overall structure and size of the project, and the stress magnitude and direction in the project area were collected, and then the crack splitting failure mode evaluation index c was used. p , high span ratio, maximum concentrated stress at the sidewall σ max True triaxial crack initiation stress of surrounding rock The required data set is obtained by extracting and sorting the input features. Then, random sampling is used to determine the training set, validation set, and test set in a ratio of 70%:15%:15%.

[0053] The training set is used to train the random forest model. During the training process, the model learns the relationship between the input features and the output variable (slab failure depth) and builds multiple decision trees for prediction. The validation set data is used to evaluate the performance of the model, calculate indicators such as prediction error, mean square error (MSE), and root mean square error (RMSE), and adjust the parameters of the random forest model based on the performance on the validation set to optimize the performance of the model. Finally, the test set data is used to check whether the model can accurately predict the spall failure depth under different geological conditions and engineering environments.

[0054] In an exemplary embodiment, in order to illustrate the specific implementation of the method of the above embodiment, a specific example is provided:

[0055] Example:

[0056] The maximum principal stress of the original rock of the main powerhouse project on the left bank of Shuangjiangkou Hydropower Station is 16MPa~38MPa, 30MPa is taken, the intermediate principal stress is 9MPa~20MPa, 20MPa is taken, and the minimum principal stress is 3MPa~10MPa, 10MPa is taken.

[0057] The power building is 68.3m high. The first and second floors are located above the rock anchor beams with a span of 28.3m. Part of the third floor and the fourth floor are below the rock anchor beams with a span of 25.3m. The effective radius of the arc-shaped vault of the power building is r=17.4m.

[0058] Through indoor true triaxial test on the granite samples of the underground main powerhouse on the left bank of Shuangjiangkou Hydropower Station, it is found that the crack initiation stress of the granite of the underground main powerhouse on the left bank of Shuangjiangkou Hydropower Station under the original rock stress condition is 161MPa, and the evaluation index of the granite crack extension capacity related to splitting failure c p =0.15. After the excavation of the first, second, third and fourth floors of the powerhouse, the maximum concentrated stress in the spalling area was 47.29MPa, 52.40MPa, 58.03MPa and 61.20MPa respectively.

[0059] The quantitative results of the factors affecting the spalling depth of the left bank main powerhouse of Shuangjiangkou Hydropower Station were substituted into the prediction model of the spalling failure depth and position of underground engineering surrounding rock based on the random forest algorithm to calculate the spalling depth of the surrounding rock at the end of excavation of the I to IV layers, and the corresponding spalling failure depth d at the end of excavation of the I layer of the powerhouse was obtained. s =3.65m, which is basically consistent with the actual spalling depth of 3.6. Similarly, after the excavation of the II, III and IV layers of the factory building, the spalling damage depths are 4.12m, 4.66m and 4.96m respectively.

[0060] Based on the same inventive concept, the embodiment of the present application also provides a device for predicting the damage depth of complete surrounding rock spalling in deep engineering for realizing the above-mentioned method for predicting the damage depth of complete surrounding rock spalling in deep engineering. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the device for predicting the damage depth of complete surrounding rock spalling in deep engineering provided below can refer to the limitations of the method for predicting the damage depth of complete surrounding rock spalling in deep engineering above, and will not be repeated here.

[0061] In an exemplary embodiment, a device for predicting the failure depth of complete surrounding rock spalling in deep engineering is provided, comprising:

[0062] The original rock stress acquisition module is used to obtain the original rock stress at the potential location of spalling in the intact surrounding rock of deep engineering projects.

[0063] The first calculation module is used to calculate the crack splitting failure mode evaluation index and the rock true triaxial crack initiation stress according to the original rock stress; the crack splitting failure mode evaluation index is an evaluation index of the crack splitting failure mode related to the splitting failure mode of the complete surrounding rock of the deep engineering under the three-dimensional stress state.

[0064] The second calculation module is used to calculate the tunnel size and height-span ratio of the complete surrounding rock of the deep engineering according to the overall structure of the complete surrounding rock of the deep engineering.

[0065] The third calculation module is used to calculate the maximum concentrated stress in the tunnel spalling area of ​​the complete surrounding rock of the deep engineering project based on the original rock stress and the height-to-span ratio.

[0066] The prediction module is used to input the original rock stress, crack splitting failure mode evaluation index, rock true triaxial crack initiation stress, tunnel size and height-span ratio into the spalling failure depth prediction model to obtain the spalling failure depth of the complete surrounding rock of the deep engineering; the spalling failure depth prediction model is obtained by training the random forest model.

[0067] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data determined by complementarity. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the depth of complete surrounding rock slab destruction in deep engineering is implemented.

[0068] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0069] In an exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the above-mentioned embodiment of the method for predicting the depth of complete surrounding rock fragmentation failure in deep engineering are implemented.

[0070] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the steps in the above-mentioned method embodiment for predicting the depth of complete surrounding rock spalling failure in deep engineering.

[0071] In an exemplary embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in the above-mentioned method embodiment for predicting the depth of complete surrounding rock spalling failure in deep engineering.

[0072] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0073] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, etc., but is not limited thereto.

[0074] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0075] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting the failure depth of intact surrounding rock spalling in deep engineering, characterized in that: The method for predicting the failure depth of complete surrounding rock spalling in deep engineering includes: Obtain the original rock stress at the potential location of spalling of the intact surrounding rock of deep engineering projects; Calculate the crack splitting failure mode evaluation index and the rock true triaxial crack initiation stress according to the original rock stress; the crack splitting failure mode evaluation index is an evaluation index of the crack splitting failure mode related to the splitting failure mode of the complete surrounding rock of the deep engineering under the three-dimensional stress state; Calculate the tunnel size and height-to-span ratio of the deep engineering complete surrounding rock according to the overall structure of the deep engineering complete surrounding rock; Calculate the maximum concentrated stress in the tunnel spalling area of ​​the complete surrounding rock of the deep engineering according to the original rock stress and the height-to-span ratio; The original rock stress, crack splitting failure mode evaluation index, rock true triaxial crack initiation stress, tunnel size and height-span ratio are input into the spalling failure depth prediction model to obtain the spalling failure depth of the intact surrounding rock of the deep engineering; the spalling failure depth prediction model is obtained by training the random forest model.

2. The method for predicting the failure depth of complete surrounding rock spalling in deep engineering according to claim 1 is characterized in that: The crack splitting failure mode evaluation index and the rock true triaxial crack initiation stress are calculated according to the original rock stress, specifically including: Obtaining intact surrounding rock samples of deep engineering projects; Indoor true triaxial tests were carried out on surrounding rock samples with different stress loading or unloading to obtain stress-strain curves; Calculate the true triaxial crack initiation stress of rock according to the stress-strain curve and the peak intensity σ p ; According to the true triaxial crack initiation stress of rock and peak intensity σ p , using the crack growth capacity formula Calculate the evaluation index c of crack splitting failure mode p .

3. The method for predicting the failure depth of complete surrounding rock spalling in deep engineering according to claim 1 is characterized in that: The crack splitting failure mode evaluation index and the rock true triaxial crack initiation stress are calculated according to the original rock stress, specifically including: Using formula c p =0.3, calculate the evaluation index c of crack splitting failure mode p ; Using the formula Calculation of true triaxial crack initiation stress in rock Among them, σ p It is the peak strength of the intact surrounding rock of deep engineering; σ p It is obtained by solving the following formula; Among them, σ2 and σ3 are the intermediate principal stress and the minimum principal stress in the original rock stress, respectively, and σ m,2 is the effective mean stress, τ oct is the octahedral shear stress, It is the internal friction angle of the complete surrounding rock of deep engineering.

4. The method for predicting the failure depth of complete surrounding rock spalling in deep engineering according to claim 1 is characterized in that: The tunnel size and height-span ratio of the deep engineering complete surrounding rock are calculated according to the overall structure of the deep engineering complete surrounding rock, including: When the tunnel of the deep engineering with complete surrounding rock is a circular tunnel, the tunnel size is determined as the radius of the tunnel; when the tunnel of the deep engineering with complete surrounding rock is not a circular tunnel, the tunnel size is determined as the effective radius of the tunnel; Using the formula Calculate the height-to-span ratio d, where H and D are the height and span of the developed portion of the intact surrounding rock of the deep project, respectively.

5. The method for predicting the failure depth of complete surrounding rock spalling in deep engineering according to claim 1 is characterized in that: The formula for calculating the maximum concentrated stress in the tunnel spalling area of ​​the complete surrounding rock of the deep engineering project based on the original rock stress and the height-to-span ratio is: s max =(aσ2-σ3)ln(d)+(σ1+σ2+σ3); Among them, σ max is the maximum concentrated stress in the tunnel wall area, d is the height-to-span ratio, σ1, σ2, σ3 are the maximum principal stress, intermediate principal stress and minimum principal stress in the original rock stress respectively, and a is the coefficient.

6. A device for predicting the failure depth of complete surrounding rock spalling in deep engineering, characterized in that: The device for predicting the failure depth of complete surrounding rock spalling in deep engineering uses the method for predicting the failure depth of complete surrounding rock spalling in deep engineering as described in any one of claims 1 to 5, and the device for predicting the failure depth of complete surrounding rock spalling in deep engineering comprises: The original rock stress acquisition module is used to obtain the original rock stress at the potential location of spalling in the intact surrounding rock of deep engineering projects; The first calculation module is used to calculate the crack splitting failure mode evaluation index and the rock true triaxial crack initiation stress according to the original rock stress; the crack splitting failure mode evaluation index is an evaluation index of the crack splitting failure mode related to the splitting failure mode of the complete surrounding rock of the deep engineering under the three-dimensional stress state; The second calculation module is used to calculate the tunnel size and height-span ratio of the complete surrounding rock of the deep engineering according to the overall structure of the complete surrounding rock of the deep engineering; A third calculation module is used to calculate the maximum concentrated stress in the tunnel spalling area of ​​the complete surrounding rock of the deep engineering according to the original rock stress and the height-to-span ratio; The prediction module is used to input the original rock stress, crack splitting failure mode evaluation index, rock true triaxial crack initiation stress, tunnel size and height-span ratio into the spalling failure depth prediction model to obtain the spalling failure depth of the complete surrounding rock of the deep engineering; the spalling failure depth prediction model is obtained by training the random forest model.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting the depth of complete surrounding rock fragmentation failure in deep engineering as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the depth of complete surrounding rock spalling failure in deep engineering as described in any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting the depth of complete surrounding rock spalling failure in deep engineering as described in any one of claims 1 to 5 is implemented.

Images