A deep rock mass mechanical parameter inversion method based on multi-source survey information

Abstract

The present application relates to a kind of deep rock mass mechanical parameter inversion methods based on multi-source survey information, comprising the following steps: obtaining rock mechanics parameter, rock mass structure parameter and rock mass engineering parameter;Based on the Hoek-Brown criterion, according to the rock mechanics parameter, rock mass structure parameter and rock mass engineering parameter, the rock mass mechanical parameter is calculated;Rock mechanics parameter, rock mass structure parameter and rock mass engineering parameter are used as input information, and the corresponding rock mass mechanical parameter is used as output information, to construct sample database, utilize the sample database training deep learning neural network model, obtain deep rock mass mechanical parameter inversion model;Deep rock mass engineering mechanics parameter is obtained by using the deep rock mass mechanical parameter inversion model inversion.Deep rock mass mechanical parameter inversion method of the present application can quickly and accurately obtain rock mass mechanical parameter, and has strong practicability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel engineering, and particularly relates to a deep rock mass mechanical parameter inversion method based on multi-source survey information. BACKGROUND

[0002] China has become the country with the largest scale of highway tunnel construction, the fastest construction efficiency, the largest number of operation and the most complex structure form in the world, and has achieved a milestone development in tunnel structure design, lining disease monitoring and maintenance key technologies.

[0003] With the proposal and application of the new Austrian tunneling method, the tunnel engineering construction technology in China has been greatly developed, and the tunnel construction scale is also getting larger and larger, and a large amount of on-site monitoring data generated thereby provides researchers with another idea of determining rock mass parameters, that is, an inversion analysis method.

[0004] However, the problems of “limited data dispersion”, “complex failure mechanism” and “fuzzy influencing factors” faced by rock mechanics seriously affect the development of numerical analysis methods. Deep rock mass is a geological body that has been in a high ground stress environment for a long time, and its past history will continue to affect the behavior of the rock mass now and in the future. Accurate acquisition of in-situ engineering mechanical parameters of deep rock mass has important guiding significance for the subsequent construction of the tunnel site. At present, the method for accurately acquiring the in-situ engineering mechanical parameters of deep rock mass is not mature enough. How to quickly and accurately obtain the in-situ mechanical parameters of deep rock mass so as to more accurately guide the subsequent excavation and support construction of the tunnel has become a problem to be solved at present. SUMMARY

[0005] In order to at least partially solve the problem that the in-situ mechanical parameters of deep rock mass are difficult to accurately acquire, the present application provides a deep rock mass mechanical parameter inversion method based on multi-source survey information, which can be expected to realize efficient and accurate acquisition of the mechanical parameters of deep rock mass.

[0006] The deep rock mass mechanical parameter inversion method based on multi-source survey information provided by the present application comprises the following steps:

[0007] S1, rock mechanical parameters are acquired, wherein the rock mechanical parameters comprise rock uniaxial compressive strength, rock cohesion and rock internal friction angle;

[0008] S2, rock mass structure parameters are acquired, wherein the rock mass structure parameters comprise rock mass integrity coefficient;

[0009] S3, rock mass engineering parameters are acquired, wherein the rock mass engineering parameters comprise tunnel buried depth, blasting disturbance coefficient and groundwater influence correction coefficient;

[0010] S4, a calculation model of Hoek-Brown criterion is adopted to calculate corresponding rock mass mechanical parameters according to the rock mechanical parameters, rock mass structure parameters and rock mass engineering parameters, the rock mass mechanical parameters including rock mass uniaxial compressive strength, rock mass elastic modulus, rock mass cohesion and rock mass internal friction angle;

[0011] S5, a sample database is constructed with the rock mechanical parameters, rock mass structure parameters and rock mass engineering parameters as input information and the corresponding rock mass mechanical parameters as output information, and a deep learning neural network model is established, the model is trained by using the sample database to obtain a deep rock mass mechanical parameter inversion model;

[0012] S6, the deep rock mass mechanical parameters are obtained by using the deep rock mass mechanical parameter inversion model.

[0013] Preferably, in step S4, the rock mass elastic modulus E, the rock mass cohesion C, the rock mass internal friction angle φ and the rock mass uniaxial compressive strength σ c are calculated by the following calculation model:

[0014]

[0015]

[0016] In the above formulae, D is a blasting disturbance coefficient, σ UCS is a rock uniaxial compressive strength, K4 is a groundwater influence correction coefficient, K v is a rock mass integrity coefficient, γ is a rock mass specific gravity; H is a tunnel depth; m i is a rock mechanical parameter; SCF is a strength correction coefficient, SCF = 22.25K v -10K4-74.725; p is a calculation intermediate variable, p = SCF + 0.27σ UCS ; and GSI is a geomechanical strength index.

[0017] Preferably, the rock mechanical parameter m i is calculated by the following formula:

[0018]

[0019] In the formula, σ UCS is a rock uniaxial compressive strength, c1 is a rock cohesion, σ is a confining pressure, and θ is a rock internal friction angle; when f(σ, m i ) takes a minimum value, the obtained m i is the rock mechanical parameter.

[0020] Preferably, the geomechanical strength index GSI is quantitatively calculated by the following formula:

[0021] GSI = 0.089 (100 + 3σ UCS + 250K V - 100K4 + 0.5θ - 4c1) + 10.375

[0022] In the formula: σ UCS is the uniaxial compressive strength of rock, c1 is the rock cohesion, θ is the internal friction angle of rock, K V is the rock mass integrity coefficient, and K4 is the groundwater influence correction coefficient.

[0023] Preferably, in step S1, the rock mechanical parameters are obtained based on measurement while drilling for hard rock, and the rock mechanical parameters are obtained by dynamic compression and shear test for soft rock.

[0024] Preferably, when the rock mechanical parameters are obtained based on measurement while drilling, the borehole is divided into units along the drilling direction, and the rock mechanical parameters of the corresponding unit are obtained based on the measurement while drilling parameters of 0.5 m in the range every 20 cm of drilling, and the process is repeated to obtain the rock mechanical parameter data at different drilling depths.

[0025] Preferably, in step S2, the borehole image is obtained based on borehole television, and the rock mass structure surface parameters including structure surface crack density are obtained by extracting and analyzing the image, and the rock mass integrity coefficient is calculated based on the structure surface crack density;

[0026] Preferably, in step S2, the borehole image is obtained based on borehole television, and the rock mass structure surface parameters including structure surface crack density are obtained by extracting and analyzing the image, and the rock mass integrity coefficient is calculated based on the structure surface crack density;

[0027] Preferably, in step S5, the deep learning neural network model adopts a fully connected layer neural network model, which is composed of three fully connected layers, each of which uses a ReLU activation function, and a skip connection is included in the network.

[0028] The model input features at least include the uniaxial compressive strength of rock, the rock cohesion, the internal friction angle of rock, the rock mass integrity coefficient, the tunnel depth, the blasting disturbance coefficient and the groundwater influence correction coefficient, the number of model output parameters is four, which are the rock mass uniaxial compressive strength, the rock mass elastic modulus, the rock mass internal friction angle and the rock mass cohesion, and the loss function is composed of four parameters, and the coefficients are 0.2, 0.2, 0.5 and 0.1.

[0029] Preferably, the method further comprises a verification step of the accuracy of the deep rock mass mechanical parameter inversion model.

[0030] For a specific work point, actual displacement monitoring is carried out, three-direction displacement deformation data of the vault, the spandrel and the side wall are recorded, and actual monitoring displacement curves are obtained; a large number of three-dimensional numerical calculations are utilized to record displacements of corresponding monitoring points under different rock mass parameters, and numerical calculation displacement curves are obtained;

[0031] The rock mass mechanical parameters corresponding to the numerical calculation displacement curve closest to the actual monitoring displacement curve are obtained by searching the numerical calculation displacement curve through the bee colony algorithm; and the parameters are compared with the calculation parameters of the deep rock mass mechanical parameter inversion model based on the step S5, if the parameters are incorrect, the displacement curve inversion parameters are added to the sample database, and the inversion model is trained again.

[0032] Compared with the related prior art, the beneficial effects of the present application are at least embodied in:

[0033] All the parameters required by the inversion method of the present application can be measured on site, all the data come from the site, the sample of the structural plane and the rock parameters is more and more accurate, and a large number of indoor tests are not required.

[0034] In addition, in some embodiments, the deformation measured on site is used as a reference value for accuracy checking, and has very high accuracy under the support of a large amount of data on site, solving the problem that deep in-situ engineering mechanical parameters are difficult to accurately obtain. It has an important guiding role for the later construction of the tunnel. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 The figure is a deep rock mass mechanical parameter inversion method of the embodiment of the present application;

[0036] Figure 2 The figure is a drilling hole unit division diagram of the embodiment of the present application;

[0037] Figure 3 The figure is an example data diagram of the rock mechanical parameters calculated and obtained in the embodiment of the present application;

[0038] Figure 4 The figure is an inversion parameter diagram of the deep rock mass mechanical parameter inversion model of the embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0040] Reference Figure 1As shown, the deep rock mass mechanical parameter inversion method based on multi-source survey information of one embodiment comprises the following steps:

[0041] S1, obtaining rock mechanical parameters, the rock mechanical parameters comprising rock uniaxial compressive strength, rock cohesion and rock internal friction angle;

[0042] S2, obtaining rock mass structure parameters, the rock mass structure parameters comprising rock mass integrity coefficient;

[0043] S3, obtaining rock mass engineering parameters, the rock mass engineering parameters comprising tunnel depth, blasting disturbance coefficient and groundwater influence correction coefficient;

[0044] S4, using the calculation model of Hoek-Brown criterion, calculating corresponding rock mass mechanical parameters according to the rock mechanical parameters, rock mass structure parameters and rock mass engineering parameters, the rock mass mechanical parameters comprising rock mass uniaxial compressive strength, rock mass elastic modulus, rock mass cohesion and rock mass internal friction angle;

[0045] S5, taking the rock mechanical parameters, rock mass structure parameters and rock mass engineering parameters as input information, and corresponding rock mass mechanical parameters as output information, constructing a sample database, and establishing a deep learning neural network model, training the model by using the sample database to obtain a deep rock mass mechanical parameter inversion model;

[0046] S6, using the deep rock mass mechanical parameter inversion model to obtain deep rock mass mechanical parameters.

[0047] It can be understood that, based on the deep rock mass mechanical parameter inversion method based on multi-source survey information provided in the embodiment, the deep rock mass mechanical parameters can be effectively inverted more accurately and efficiently based on in-situ mechanical parameters and three-dimensional rock mass structure and other multi-source data.

[0048] In some embodiments, in step S4, the rock mass elastic modulus E, rock mass cohesion C, rock mass internal friction angle φ and rock mass uniaxial compressive strength σ c are calculated by the following calculation model:

[0049]

[0050] In the above formulas, D is the blasting disturbance coefficient, σ UCS is the rock uniaxial compressive strength, K4 is the groundwater influence correction coefficient, K v is the rock mass integrity coefficient, γ is the rock mass specific gravity; H is the tunnel depth; m i is the rock mechanical parameter; SCF is the strength correction coefficient, SCF = 22.25K v -10K4-74.725; p is a calculation intermediate variable, p = SCF + 0.27σ UCS; GSI is a geological strength index.

[0051] It can be understood that the calculation model of the improved Hoek-Brown criterion is used in the embodiment, and the calculation of the rock mass mechanical parameters is more accurate and reasonable, and the mechanical parameters of the deep rock mass can be more accurately reflected.

[0052] In some embodiments, the rock mechanics parameter m i in the Hoek-Brown criterion

[0053]

[0054] In the formula: σ UCS is the uniaxial compressive strength of the rock, c1 is the rock cohesion, σ is the confining pressure, and θ is the internal friction angle of the rock. When f(σ, m i ) takes the minimum value, the obtained m i is the rock mechanics parameter.

[0055] It can be understood that the rock mechanics parameter m i in the Hoek-Brown criterion is a parameter for describing the hardness of the intact rock, which reflects the softness and hardness of the intact rock. In the traditional application, it is used as an empirical parameter, and the corresponding value can be obtained according to the value table of the “Non-coal open-pit mine slope engineering technical specification” (GB 51016-2014). However, the value obtained by the empirical formula based on the value table inevitably has the problem of insufficient accuracy. In the embodiment, the value of the rock mechanics parameter m i can be calculated and determined based on the field test data, and the accuracy is higher.

[0056] In some embodiments, the geological strength index GSI is quantitatively calculated by the following formula:

[0057] GSI = 0.089 (100 + 3σ UCS + 250K V - 100K4 + 0.5θ - 4c1) + 10.375

[0058] In the formula: σ UCS is the uniaxial compressive strength of the rock, c1 is the rock cohesion, θ is the internal friction angle of the rock, K V is the rock integrity coefficient, and K4 is the groundwater influence correction coefficient.

[0059] In some embodiments, in step S1, for hard rock, the rock mechanical parameters can be obtained based on measurement while drilling; for soft rock, the rock mechanical parameters can be obtained through dynamic compression and shear test. In this embodiment, different test methods are adopted to obtain rock mechanical parameters for different types of rock mass properties, so that the obtained rock mechanical parameters are more accurate and reasonable. It can be understood that the measurement while drilling technology uses various parameters monitored and recorded in real time during drilling, including drilling speed, torque, thrust, etc. These data can be obtained through sensors installed on the drill bit or drill pipe. By analyzing these drilling parameters, the structural characteristics and mechanical properties of the rock mass can be identified. Specifically, in this embodiment, the rock mechanical parameters can be obtained by analyzing the pressure, torque, rotational speed and vibration parameters of the drill pipe during drilling. Similarly, obtaining rock mechanical parameters through dynamic compression and shear test is a way that can be adopted by those skilled in the art, and is not limited thereto, and will not be described here.

[0060] As a preferred embodiment, referring to Figure 2 As shown, when obtaining the rock mechanical parameters based on measurement while drilling, the drilling hole is divided into units along the drilling direction. For each drilling of 20 cm, the rock mechanical parameters of the corresponding unit are obtained based on the inversion calculation of the drilling test parameters within the range of 0.5 m, and the calculation is repeated to obtain the rock mechanical parameter data at different drilling depths. More specifically, to obtain more effective sample data within a reasonable range, when the drilling hole is divided into units, the unit size of the drilling calculation model can be set to 1 m x 1 m x 0.7 m, and the step size is 0.2 m. Thus, 100 units can be obtained at a drilling depth of 20 m. Figure 3 Exemplary rock mechanical parameters obtained through drilling test calculation are listed.

[0061] It is worth noting that based on the scheme of this embodiment, the rock mechanical parameters, i.e., uniaxial compressive strength of rock, cohesion (cohesion) and internal friction angle, can be obtained based on the drilling test parameters of the drilling hole on site. In this embodiment, the target rock is directly tested in its real state, which is more true and reliable than laboratory testing after sampling. The obtained data are rock mechanical parameters varying with drilling depth, which are more representative and diverse, and meet the state in the real scene.

[0062] In some embodiments, in step S2, the borehole television is used to obtain the borehole rock mass image, and the rock mass structure surface parameters including the structure surface crack density are obtained by extraction analysis on the image, and the rock mass integrity coefficient is calculated based on the structure surface crack density. It should be noted that the rock mass structure surface parameters can be determined based on the borehole television combined with the stereology theory; specifically, the 360° image in the borehole can be obtained based on the borehole television technology, and the rock mass structure surface parameters can be determined by using the structure surface automatic identification method based on the stereology theory and deep learning image processing. The rock mass structure surface parameters that can be identified include the rock mass structure crack average tendency, average inclination, crack number, rock mass structure crack density and rock mass integrity coefficient, and the specific principle process is not described here. Of course, the rock mass integrity coefficient can also be determined by using other determination methods in the present embodiment.

[0063] Further, based on the unit division of the drill hole, more structure surface parameter data can be obtained, that is, every 20 cm of drilling, extraction analysis is performed once based on the digital image of 0.5 m in the range to obtain a rock mass integrity coefficient, so as to realize strict correspondence between the rock mass integrity coefficient and the rock mechanics parameters.

[0064] In some embodiments, the blasting disturbance coefficient D can be selected to have different values according to different blasting modes actually used in tunnel excavation, and the specific values can be referred to Table 1:

[0065] Table 1

[0066] Excavation method TMB Controlled blasting Manual, mechanical Low mass blasting Hard rock 0 0.1 0.2 0.8 Soft rock 0 0.2 0.5 1

[0067] In some embodiments, the groundwater influence correction coefficient K4 can be valued according to the development degree of the slope groundwater and the rock mass integrity coefficient K V , and the value range of K4 is 0-1. The better the rock mass integrity, the worse the groundwater development, and the smaller the value of K4. The specific value of K4 can be referred to Table 2:

[0068] Table 2

[0069]

[0070]

[0071] In some embodiments, in step S5, the deep learning neural network model adopts a full connection layer neural network model, which is composed of 3 full connection layers, a ReLU activation function is used after each full connection layer, and a skip connection is included in the network; the model input features (input information) at least include the rock uniaxial compressive strength, the rock cohesion, the rock internal friction angle, the rock mass integrity coefficient K V, tunnel depth, blasting disturbance coefficient and groundwater influence correction coefficient, the number of model output parameters is 4, which are: rock uniaxial compressive strength, rock elastic modulus, rock internal friction angle and rock cohesion, and the loss function is composed of 4 parameters, and the coefficients are 0.2, 0.2, 0.5 and 0.1.

[0072] Referring to Figure 4 In some embodiments, the input information of the inversion model mainly includes rock parameters, engineering parameters and rock mass structure parameters, wherein the rock parameters include rock uniaxial strength (rock uniaxial compressive strength), rock cohesion and rock internal friction angle; the rock mass structure parameters include rock mass integrity coefficient K V , the engineering parameters include tunnel depth, blasting strength (blasting disturbance coefficient) and groundwater state (groundwater influence correction coefficient), and the output information of the inversion model includes rock mass parameters, specifically: rock uniaxial compressive strength, rock elastic modulus, rock internal friction angle and rock cohesion.

[0073] In some embodiments, the method further comprises a verification step of the accuracy of the deep rock mass mechanical parameter inversion model:

[0074] For a specific work site, actual displacement monitoring is performed, three-dimensional displacement deformation data of the arch crown, arch shoulder and side wall are recorded, actual monitoring displacement curves are obtained, a large number of three-dimensional numerical calculations (for example, a large number of three-dimensional numerical calculations are carried out by using 3DEC program) are performed, displacement deformations of corresponding monitoring points under different rock mass parameters are recorded, and numerical calculation displacement curves are obtained.

[0075] The numerical calculation displacement curve closest to the actual monitoring displacement curve is searched by using the bee colony algorithm, corresponding rock mass mechanical parameters are obtained, and the parameters are compared with the calculation parameters of the deep rock mass mechanical parameter inversion model obtained based on step S5; if not correct, the displacement curve inversion parameters are added to the sample database, and the inversion model is trained again to further improve the inversion accuracy and effectiveness of the inversion model; otherwise, if correct, it is further proved that the inversion model can accurately and effectively invert the real deep rock mass mechanical parameters.

[0076] In the description of the embodiments of the application, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0077] Reference throughout this application to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "in another embodiment" or "in further embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment, but can refer to one or more, but not all, of the embodiments, unless otherwise specifically set forth. The terms "including," "comprising," "having," and their variants are meant to be equivalent in that they all mean to include but not to be limited to, unless otherwise specifically indicated.

[0078] While embodiments of the application have been shown and described, it is to be understood that the application is not limited to the details of the embodiments described, since the scope of the application is defined with respect to the appended claims.

Claims

1. A method for inverting deep rock mass mechanical parameters based on multi-source exploration information, characterized in that, Includes the following steps: S1. Obtain rock mechanical parameters, including uniaxial compressive strength, cohesion, and internal friction angle of rock. S2. Obtain rock mass structural parameters, including the rock mass integrity coefficient; S3. Obtain rock mass engineering parameters, including tunnel depth, blasting disturbance coefficient and groundwater influence correction coefficient; S4. Using the Hawke-Brown criterion calculation model, calculate the corresponding rock mass mechanical parameters based on the rock mechanics parameters, rock mass structural parameters, and rock mass engineering parameters. The rock mass mechanical parameters include the uniaxial compressive strength of the rock mass, the elastic modulus of the rock mass, the cohesion of the rock mass, and the internal friction angle of the rock mass. S5. Using rock mechanics parameters, rock mass structure parameters, and rock mass engineering parameters as input information, and the corresponding rock mechanics parameters as output information, construct a sample database, establish a deep learning neural network model, train the model using the sample database, and obtain a deep rock mass mechanics parameter inversion model. S6. The deep rock mass mechanical parameters are obtained by inverting the deep rock mass mechanical parameters using the aforementioned deep rock mass mechanical parameter inversion model; In step S4, the rock mass elastic modulus E and rock mass cohesion are calculated using the following calculation model. Friction angle within the rock mass and the uniaxial compressive strength of the rock mass ; ， ， ， ， In the above formulas, D is the blasting disturbance coefficient. K is the uniaxial compressive strength of the rock, K4 is the correction factor for the influence of groundwater, and K v The rock mass integrity coefficient. H represents the rock mass density; H represents the tunnel depth. These are rock mechanical parameters; This is the strength correction factor. ; To calculate intermediate variables, ; Geomechanical strength index; Rock mechanical parameters The calculation is performed using the following formula: In the formula: For the uniaxial compressive strength of rock, For rock cohesion, For confining pressure, Let be the internal friction angle of the rock, when When the minimum value is taken, the result is These are rock mechanics parameters.

2. The method for inverting deep rock mass mechanical parameters based on multi-source exploration information according to claim 1, characterized in that, Geomechanical strength index Quantification is performed using the following formula: In the formula: For the uniaxial compressive strength of rock, 1 represents rock cohesion. K is the internal friction angle of the rock. V The rock mass integrity coefficient. This is the correction factor for the impact of groundwater.

3. The method for inverting deep rock mass mechanical parameters based on multi-source exploration information according to claim 1, characterized in that: In step S1, for hard rock, the rock mechanical parameters are obtained based on measurements while drilling; for soft rock, the rock mechanical parameters are obtained through dynamic compression-shear testing.

4. The method for inverting deep rock mass mechanical parameters based on multi-source exploration information according to claim 3, characterized in that: When obtaining the rock mechanical parameters based on measurements while drilling, the borehole is divided into units along the drilling direction. Every 20cm of drilling, the rock mechanical parameters of the corresponding unit are obtained based on the measurements while drilling within that range of 0.5m. This process is repeated to obtain rock mechanical parameter data at different borehole depths.

5. The method for inverting deep rock mass mechanical parameters based on multi-source exploration information according to claim 4, characterized in that: In step S2, the rock mass image inside the borehole is acquired based on borehole television, and the image is extracted and analyzed to obtain rock mass structural parameters including structural surface fracture density. The rock mass integrity coefficient is calculated based on the structural surface fracture density. Specifically, for every 20cm of drilling, an extraction and analysis is performed based on a 0.5m digital image within that range to obtain a rock mass integrity coefficient, so as to achieve a strict correspondence between the rock mass integrity coefficient and the rock mechanical parameters.

6. The method for inverting deep rock mass mechanical parameters based on multi-source exploration information according to claim 1, characterized in that: In step S5, the deep learning neural network model adopts a fully connected layer neural network model, which consists of 3 fully connected layers. Each fully connected layer is followed by a ReLU activation function, and the network contains a skip connection. The model input features include at least the uniaxial compressive strength of rock, rock cohesion, rock internal friction angle, rock mass integrity coefficient, tunnel burial depth, blasting disturbance coefficient, and groundwater influence correction coefficient. The model output parameters are four: uniaxial compressive strength of rock mass, rock mass elastic modulus, rock internal friction angle, and rock mass cohesion. The loss function is composed of these four parameters, with coefficients of 0.2, 0.2, 0.5, and 0.1, respectively.

7. The method for inverting deep rock mass mechanical parameters based on multi-source exploration information according to claim 1, characterized in that: It also includes a verification step for the accuracy of the deep rock mass mechanical parameter inversion model: For specific work sites, actual displacement monitoring is carried out to record the three-dimensional displacement deformation data of the arch crown, arch shoulder and sidewalls, and to obtain the actual monitored displacement curve; By using a large number of three-dimensional numerical calculations, the displacement and deformation of the corresponding monitoring points under different rock mass parameters are recorded to obtain numerically calculated displacement curves. The bee colony algorithm is used to search for the numerically calculated displacement curve that is closest to the actual monitored displacement curve to obtain the corresponding rock mass mechanics parameters. These parameters are then compared with the calculated parameters of the inversion model based on the deep rock mass mechanics parameters obtained in step S5. If they are incorrect, the displacement curve inversion parameters are added to the sample database and the inversion model is trained again.

Images