Intelligent sensing and in-situ classification method for surrounding rock in underground engineering during drilling

Abstract

This invention discloses a method for intelligent sensing and in-situ classification of surrounding rock in underground engineering during drilling, relating to the field of underground engineering technology. The method includes: establishing a rock mass mechanical parameter inversion model during drilling to dynamically predict the equivalent compressive strength of the rock mass and generate a strength curve that changes with drilling depth; identifying the location of structural planes based on the abrupt change characteristics of the strength curve, constructing a rock mass structural plane response model during drilling, obtaining structural plane parameters based on the location of the structural planes, and further calculating rock mass quality indicators; after the drilling test is completed, constructing a groundwater state testing model during drilling to obtain groundwater state characterization parameters; and based on the surrounding rock classification method, comprehensively considering the equivalent compressive strength of the rock mass, the width of the structural planes, the spacing between the structural planes, the rock mass quality indicators, and the groundwater state characterization parameters to perform intelligent in-situ classification and evaluation of the surrounding rock in underground engineering during drilling. This invention can realize real-time detection and in-situ classification of the properties of surrounding rock in underground engineering during drilling, improving the accuracy and timeliness of testing.

Description

Technical Field

[0001] This invention relates to the field of underground engineering technology, specifically to a method for intelligent sensing and in-situ classification of surrounding rock during drilling in underground engineering. Background Technology

[0002] As mining depths continue to increase, the issue of rock mass stability in deep underground engineering is becoming increasingly prominent. Rock mass classification, as a key technical step in assessing rock mass stability and guiding support design, directly impacts engineering safety and construction efficiency in terms of accuracy and timeliness. However, currently widely used rock mass classification methods suffer from several technical bottlenecks that urgently need to be addressed.

[0003] First, existing methods lag significantly in obtaining rock mass strength parameters. Traditional methods rely on drilling core samples and then sending them to the laboratory for mechanical testing, which not only takes 2-3 weeks, but also inevitably involves disturbance of the rock cores during sampling and transportation, making it difficult for the test results to accurately reflect the mechanical properties of the in-situ rock mass.

[0004] Secondly, the technology for obtaining structural parameters suffers from insufficient accuracy. Furthermore, obtaining key parameters such as in-situ stress and fracture water pressure typically requires specialized exploration work, making it difficult to provide timely guidance for construction decisions.

[0005] More importantly, existing methods lack collaborative analysis capabilities. Studies have shown that the stability of deep surrounding rock is affected by multiple factors coupled together, such as strength parameters, structural features, and geostress state. Traditional methods struggle to simultaneously test and comprehensively analyze these parameters, leading to significant discrepancies between classification results and engineering realities. Summary of the Invention

[0006] To address the problems existing in the prior art, this invention provides a method for intelligent sensing and in-situ classification of surrounding rock in underground engineering during drilling. This method enables real-time detection and in-situ classification of the properties of surrounding rock in underground engineering, thereby improving the accuracy and timeliness of testing. The technical solution of the present invention is as follows: In a first aspect of the present invention, a method for intelligent sensing and in-situ classification of surrounding rock in underground engineering during drilling is provided, comprising the following steps: A drilling-while-inverting model of rock mass mechanical parameters is established to dynamically predict the equivalent compressive strength of the rock mass and generate a strength curve that varies with drilling depth. Based on the abrupt change characteristics of the strength curve, the location of the structural surface is identified by the abrupt change point detection algorithm, and a drilling response model of the rock mass structural surface is constructed. The width and spacing of the structural surface are obtained based on the location of the structural surface, and the rock mass quality index is further calculated. After the drilling test is completed, the fracture water pressure and maximum principal stress are obtained in situ, and a groundwater state drilling test model is constructed to obtain groundwater state characterization parameters. Based on the surrounding rock classification method, a smart in-situ classification model for surrounding rock is constructed by integrating the equivalent compressive strength of the rock mass, the width of the structural planes, the spacing between the structural planes, the rock mass quality indicators, and the groundwater state characterization parameters, and the rock mass geomechanical classification indicators are obtained. Using rock mass geomechanical classification indicators, intelligent in-situ classification and evaluation of surrounding rock in underground engineering is carried out, and a visualization model of rock mass category information is constructed.

[0007] In some embodiments of the present invention, an intelligent surrounding rock drilling system is used to conduct in-situ drilling-while-drilling detection of the surrounding rock in underground engineering projects, and to acquire four types of drilling parameters in real time: drilling pressure, drilling torque, drilling speed, and drill bit rotation speed. Based on the drilling parameters, the rock mass mechanics parameter inversion model is established as follows:

[0008] in, ECS It is the equivalent compressive strength of the rock mass; V This refers to the drilling speed; N This refers to the drill bit rotation speed; F Drilling pressure; M This refers to the drilling torque. μ The coefficient of friction between the cutting edge and the rock mass; R To analyze the drill bit radius; l The length of each row of cutting edges of the drill bit; R 1 represents the cutting edge radius; γ It is the friction angle; The cutting edge inclination angle; a and b These are the regression fit coefficients.

[0009] In some embodiments of the present invention, the calculation formula of the mutation point detection algorithm is as follows:

[0010] The following formula is used to identify the location of structural surfaces:

[0011] in: x j Equivalent compressive strength of rock mass ECS The j One observation value, e j for x j The mean of the previous micro-segment, e j+1 for x j The mean of the next micro segment, q j for xj The standard deviation of the previous micro-segment, q j+1 for x j The standard deviation of the next micro segment, z As a threshold factor, threshold 1 is Y1= zq j Threshold 2 is Y2= zq j+1 . In some embodiments of the present invention, the constructed rock mass structural surface parameter inversion model is as follows:

[0012] in, L i For the first i Location of each structural surface; S i For the first i Each structural surface originates from; S i+1 For the first i +1 structural surface starting point; D i For the first i Each structural surface termination point; D i+1 For the first i +1 structural surface termination point; The width of the structural surface; w i This represents the distance between the midpoints of adjacent structural surfaces. In some embodiments of the present invention, the calculation formulas for rock mass quality indicators are as follows:

[0013]

[0014]

[0015] in, r i The length of the complete segment between structural surfaces, and the length of the starting segment. r 0= S 1; L This refers to the drilling depth; RQD Rock mass quality indicators; h i This represents the effective length of the complete segment between structural surfaces. In some embodiments of the present invention, after the drilling test is completed, the in-situ drilling equipment equipped with a pore water pressure gauge and a borehole stress gauge is used to conduct fracture water pressure test and maximum principal stress test respectively, and finally obtain the groundwater state characterization parameters.

[0016] In some embodiments of the present invention, the constructed groundwater state drilling test model is as follows: k = P w / σ 1 in, k These are parameters characterizing the state of groundwater. P w This refers to the fissure water pressure. σ 1 represents the maximum principal stress. In some embodiments of the present invention, the constructed intelligent in-situ classification model for surrounding rock during drilling is as follows:

[0017] in, , , , , , A 1 is the equivalent compressive strength of the rock mass. ECS The function, A 2 is the spacing between structural surfaces. w The function, A 3 is the width of the structural surface. d The function, A 4 is the rock mass quality index RQD The function, A 5 is a groundwater state characterization parameter. k The function, RMR These are the geomechanical classification indicators for rock masses.

[0018] In some embodiments of the present invention, the intelligent in-situ classification and evaluation of surrounding rock in underground engineering during drilling is as follows: When the RMR value of the rock mass obtained by drilling tests is in the range of 100-81, the surrounding rock quality is very good and it is classified as Class I surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 80-61, the surrounding rock quality is good and it is classified as Class II surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 60-41, the quality of the surrounding rock is generally average, and it is classified as Class III surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 40-21, the surrounding rock quality is poor and it is classified as Class IV surrounding rock. When the RMR value of the rock mass obtained from drilling tests is less than 20, the quality of the surrounding rock is very poor, and it is classified as Class V surrounding rock.

[0019] In some embodiments of the present invention, a visualization model of rock mass category information is constructed based on the results of intelligent in-situ classification of surrounding rock in underground engineering, specifically including: (1) Number the cross-sections and the boreholes on the cross-sections according to the direction of the tunnel from the outside to the inside; (2) Connect the boundary points of the same type of surrounding rock measured by each borehole in each cross section to obtain the boundary line of different types of surrounding rock; (3) Based on the direction of the tunnel from the outside to the inside, connect the boundary lines of the same type of surrounding rock in all sections in sequence to obtain a visualization model of the rock mass category information of the entire tunnel.

[0020] One or more technical solutions of the present invention have the following beneficial effects: (1) The present invention uses drilling to obtain the equivalent compressive strength of rock mass, the width of structural planes, the spacing of structural planes, the quality index of rock mass and the characterization parameters of groundwater state. The intelligent drilling in-situ classification model of surrounding rock can realize the dynamic fusion of the above parameters, thereby realizing the in-situ classification of surrounding rock in underground engineering. Compared with the traditional indoor rock strength test method to obtain the above parameters, it avoids the operation steps of core sampling, transportation, cutting and grinding, improves the testing efficiency and reduces the cost.

[0021] (2) The present invention uses a mutation detection algorithm to identify the mutation characteristics of the strength curve, which can obtain the compressive strength and structural features of the rock mass in real time during the digital drilling test, avoiding the lag of traditional laboratory tests. Through automated data acquisition and analysis, human measurement errors are reduced and the objectivity of the results is improved.

[0022] (3) The present invention uses the ratio of fissure water pressure to maximum principal stress as a groundwater state characterization parameter, which directly quantifies the interference of water pressure on rock stress state, improves the comprehensiveness and accuracy of classification, and the constructed rock mass category information visualization model can more scientifically predict the risk of rock mass deformation, shear slip or hydraulic fracture, and improve construction safety. Attached Figure Description

[0023] Figure 1 The flowchart shows the intelligent sensing and in-situ classification method for surrounding rock in underground engineering according to the present invention. Figure 2 This is a schematic diagram of in-situ drilling of roadways using intelligent in-situ classification of surrounding rock according to the present invention.

[0024] In the figure: 1. Drilling test system; 2. Class I surrounding rock; 3. Class II surrounding rock; 4. Surrounding rock not yet detected. Detailed Implementation

[0025] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0026] Example 1 In a typical embodiment of the present invention, a method for intelligent sensing and in-situ classification of surrounding rock in underground engineering during drilling is proposed, such as... Figure 1As shown, it includes the following steps: Step 1: Establish a rock mass mechanical parameter inversion model while drilling to dynamically predict the equivalent compressive strength of the rock mass and generate a strength curve that varies with drilling depth. Step 2: Based on the abrupt change characteristics of the strength curve, identify the location of the structural surface using the abrupt change point detection algorithm, construct the rock mass structural surface drilling response model, obtain the structural surface width and structural surface spacing based on the structural surface location, and further calculate the rock mass quality index. Step 3: After the drilling test is completed, the fracture water pressure and maximum principal stress are obtained in situ to construct the groundwater state drilling test model and obtain the groundwater state characterization parameters. Step 4: Based on the surrounding rock classification method, and by integrating the equivalent compressive strength of the rock mass, the width of the structural plane, the spacing of the structural plane, the rock mass quality index, and the groundwater state characterization parameters, construct an intelligent in-situ classification model for surrounding rock while drilling, and obtain the geomechanical classification index of the rock mass. Step 5: Utilize rock mass geomechanical classification indicators to conduct intelligent in-situ classification and evaluation of surrounding rock for underground engineering during drilling.

[0027] The specific steps are as follows: Step 1: Establish a rock mass mechanical parameter inversion model while drilling to dynamically predict the equivalent compressive strength of the rock mass. Through real-time data processing, generate a strength curve that varies with drilling depth.

[0028] Specifically, such as Figure 2 As shown, the intelligent drilling test system 1 was used to conduct in-situ drilling exploration of the surrounding rock in underground engineering. The drilling directions of the surrounding rock were Class I surrounding rock 2, Class II surrounding rock 3, and unexplored surrounding rock 4. During the exploration process, four types of drilling parameters were acquired in real time: drilling pressure, drilling torque, drilling speed, and drill bit rotation speed.

[0029] The established rock mass mechanics parameter inversion model while drilling is as follows:

[0030] in, ECS It is the equivalent compressive strength of the rock mass; V This refers to the drilling speed; N This refers to the drill bit rotation speed; F Drilling pressure; M This refers to the drilling torque. μ The coefficient of friction between the cutting edge and the rock mass; R To analyze the drill bit radius; l The length of each row of cutting edges of the drill bit; R 1 represents the cutting edge radius; γ It is the friction angle; The cutting edge inclination angle; a and b These are the regression fit coefficients.

[0031] The above-mentioned rock mass compressive strength inversion model is obtained by performing mechanical analysis on a double-wing anchor drill bit during drilling. Different drill bit structures experience different forces during drilling. Therefore, different drill bit structures correspond to different rock mass compressive strength inversion models. Since the double-wing anchor drill bit is a commonly used drill bit in drilling tests, the above-mentioned rock mass compressive strength inversion model has a wide range of applications and can be applied to most existing drilling testing systems.

[0032] Based on the drilling parameters, the rock mass mechanics parameters are substituted into the drilling inversion model to obtain the equivalent compressive strength of the rock mass.

[0033] Furthermore, a strength curve is generated based on the equivalent compressive strength of the rock mass and the drilling depth, showing how the strength varies with the drilling depth.

[0034] Step 2: Based on the abrupt change characteristics of the strength curve, identify the location of the structural surface using the abrupt change point detection algorithm, construct the rock mass structural surface drilling response model, obtain the structural surface width and structural surface spacing based on the structural surface location, and further calculate the rock mass quality index.

[0035] Specifically, the structural surface location identification is handled by the device's built-in system. CUSUM The algorithm completes the process automatically, and the specific steps for identifying cracks are as follows: (1) Real-time monitoring of drilling parameters and preprocessing using the sliding window method; (2) Based on the drilling parameters monitored in real time, the basic parameters of the algorithm are set. CUSUM Statistics are used to calculate the mean and standard deviation of observed data. (3) Determine the control limits based on the data distribution; when the statistic exceeds the control limits or shows a specific trend (such as continuous rise / fall and the magnitude of the exceedance increases), the structural surface can be identified and the location, width and spacing parameters of the structural surface can be obtained.

[0036] Specifically, the calculation formula for the mutation point detection algorithm is as follows: using a two-sided... CUSUM The algorithm (mutation detection algorithm) was tested due to the rock mass structure surface. ECS Significantly lower than the mean, the mean drilling curve changes significantly as the drill bit enters and exits the structural surface. CUSUM The specific calculation formula for the algorithm is as follows:

[0037] The following formula is used for structural surface identification:

[0038] in: x j Equivalent compressive strength of rock mass ECS The jOne observation value, e j for x j The mean of the previous micro-segment, e j+1 for x j The mean of the next micro segment, q j for x j The standard deviation of the previous micro-segment, q j+1 for x j The standard deviation of the next micro segment, z As a threshold factor, threshold 1 is Y1= zq j Threshold 2 is Y2= zq j+1 .

[0039] Specifically, taking structural surface width recognition as an example: When drilling within intact surrounding rock ECS The curve should tend to be flat. Upon first contact with the structural surface, ECS Observations x i The mean e of the previous micro-segment i The difference is very small, and at the same time, x j It will be significantly higher than the mean e of the next micro-segment. i+1， lead to ECS The curve shows its first fluctuation anomaly, which is considered to be at this point. x j The drill bit has entered the structural plane, with the starting point of the structural plane being S. i ; Observations when drilling through the structural surface x j It will be significantly higher than the mean e of the previous micro-segment. j ,at the same time, x i It will approximate the mean e of the latter small segment. j+1， lead to ECS The curve shows a second fluctuation anomaly, which is considered to be at this point. x j The drill bit has drilled through the structural surface, and the endpoint of the structural surface is... D i Therefore, the width d of the structural surface i =D i -S i .

[0040] Furthermore, the constructed rock mass structure surface parameter inversion model during drilling is as follows:

[0041] in, L i For the first i Location of each structural surface; S i For the first i Each structural surface originates from; S i+1 For the first i +1 structural surface starting point; D i For the first i Each structural surface termination point; D i+1 For the first i +1 structural surface termination point; The width of the structural surface; w i This refers to the spacing between structural surfaces.

[0042] Based on the length of the intact section between structural planes, the rock mass quality index is calculated using the rock mass quality classification standard. RQD The details are as follows:

[0043]

[0044]

[0045] in r i The length of the complete segment between structural surfaces, and the length of the starting segment. r 0= S 1; L This refers to the drilling depth; RQD Rock mass quality indicators; h i This represents the effective length of the complete segment between structural surfaces.

[0046] Step 3: After the drilling test is completed, the fracture water pressure and maximum principal stress are obtained in situ to construct the groundwater state drilling test model and obtain the groundwater state characterization parameters.

[0047] Specifically, after the drilling test is completed, the pore water pressure gauge and the borehole stress gauge will be installed on the in-situ drilling equipment to conduct fracture water pressure test and maximum principal stress test, respectively.

[0048] The specific steps for pore water pressure testing are as follows: (1) Select 1-2 typical boreholes, insert the pore water pressure gauge into the designated position in the borehole through the drill rod, and fill the surrounding area with permeable sand and gravel; (2) Simple sealing measures should be taken at the entrance of the tunnel to prevent interference from surface water; (3) Monitor and read data through the main unit of the equipment to analyze the pore water pressure.

[0049] The specific steps for testing the maximum principal stress are as follows: (1) Clear the permeable gravel from the hole until the hole wall is flat and clean; (2) The borehole stress gauge is placed into the hole to a predetermined depth by mounting it on the drill rod, ensuring close contact with the surrounding rock; (3) Inject expansion agent or grouting material and fix the stress gauge for fixation test; (4) Monitor the data through the main unit of the equipment and analyze the magnitude of the maximum principal stress.

[0050] The groundwater condition testing model is constructed as follows:

[0051] in, k These are parameters characterizing the state of groundwater. P w This refers to the fissure water pressure. σ 1 represents the maximum principal stress.

[0052] Groundwater state characterization parameters were obtained using a groundwater state testing model based on fracture water pressure and maximum principal stress. k .

[0053] Step 4: Based on the surrounding rock classification method, and by integrating the equivalent compressive strength of the rock mass, the width of the structural plane, the spacing of the structural plane, the rock mass quality index, and the groundwater state characterization parameters, an intelligent in-situ classification model for surrounding rock is constructed to obtain the geomechanical classification index of the rock mass.

[0054] Specifically, the intelligent in-situ classification model for surrounding rock during drilling is as follows:

[0055] in, , , , , , A 1 is a function of the rock mass's equivalent compressive strength (ECS). A 2 is a function of the interplanar spacing w. A 3 is a function of the width d of the structural surface. A 4 is a function of the rock mass quality index RQD. A 5 is a function of the groundwater state characterization parameter k. RMR These are the geomechanical classification indicators for rock masses. The values ​​of each of the above functions can be obtained according to the specifications.

[0056] Step 5: Utilize rock mass geomechanical classification indicators to conduct intelligent in-situ classification and evaluation of surrounding rock for underground engineering during drilling.

[0057] Specifically, the intelligent in-situ classification and evaluation of surrounding rock in underground engineering is as follows: When the RMR value of the rock mass obtained by drilling tests is in the range of 100-81, the surrounding rock quality is very good and it is classified as Class I surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 80-61, the surrounding rock quality is good and it is classified as Class II surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 60-41, the quality of the surrounding rock is generally average, and it is classified as Class III surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 40-21, the surrounding rock quality is poor and it is classified as Class IV surrounding rock. When the RMR value of the rock mass obtained from drilling tests is less than 20, the quality of the surrounding rock is very poor, and it is classified as Class V surrounding rock.

[0058] Specifically, based on the above-mentioned intelligent in-situ classification results of surrounding rock in underground engineering, the method for constructing a visualization model of rock mass category information is as follows: (1) Based on the direction of the roadway from the outside to the inside, the test section numbers are sequentially increased starting from "DB1". Three boreholes are arranged in each section, located on the left side, roof and right side respectively. The borehole numbers are marked in a clockwise direction starting from the left side hole as 1 (left side), 2 (roof) and 3 (right side). For example, the borehole named DB(n, 1) refers to the left side borehole of the "n"th test section of the roadway.

[0059] (2) Connect the boundary points of the same type of surrounding rock measured by each borehole in each cross section to obtain the boundary line of the surrounding rock category; (3) Based on the direction of the tunnel from the outside to the inside, connect the boundary lines of the same type of surrounding rock in all sections in sequence to obtain a visualization model of the rock mass category information of the entire tunnel.

[0060] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for intelligent sensing and in-situ classification of surrounding rock in underground engineering drilling, characterized in that, Includes the following steps: A drilling-while-inverting model of rock mass mechanical parameters is established to dynamically predict the equivalent compressive strength of the rock mass and generate a strength curve that varies with drilling depth. Among them, the intelligent drilling system for surrounding rock is used to conduct in-situ drilling-while-drilling exploration of the surrounding rock in underground engineering, and to obtain four types of drilling parameters in real time: drilling pressure, drilling torque, drilling speed, and drill bit rotation speed. Based on the drilling-while-drilling parameters, a drilling-while-drilling inversion model of rock mass mechanics parameters is established as follows: in, ECS It is the equivalent compressive strength of the rock mass; V This refers to the drilling speed; N This refers to the drill bit rotation speed; F Drilling pressure; M This refers to the drilling torque. μ The coefficient of friction between the cutting edge and the rock mass; R To analyze the drill bit radius; l The length of each row of cutting edges of the drill bit; R 1 represents the cutting edge radius; γ It is the friction angle; The cutting edge inclination angle; a and b These are the regression fit coefficients; Based on the abrupt change characteristics of the strength curve, the location of the structural surface is identified by the abrupt change point detection algorithm, and a drilling-while-drilling inversion model of the rock mass structural surface parameters is constructed. The width and spacing of the structural surface are obtained based on the location of the structural surface, and the rock mass quality index is further calculated. The calculation formula for the mutation point detection algorithm is as follows: The following formula is used to identify the location of structural surfaces: in: x j Equivalent compressive strength of rock mass ECS The j One observation value, e j for x j The mean of the previous micro-segment, e j+1 for x j The mean of the next micro segment, q j for x j The standard deviation of the previous micro-segment, q j+1 for x j The standard deviation of the next micro segment, z As a threshold factor, threshold 1 is Y1= zq j Threshold 2 is Y2= zq j+1 ； After the drilling test is completed, the fracture water pressure and maximum principal stress are obtained in situ, and a groundwater state drilling test model is constructed to obtain groundwater state characterization parameters. The groundwater condition testing model constructed during drilling is as follows: k = P w / σ 1 in, k These are parameters characterizing the state of groundwater. P w This refers to the fissure water pressure. σ 1 represents the maximum principal stress; Based on the surrounding rock classification method, a smart in-situ classification model for surrounding rock is constructed by integrating the equivalent compressive strength of the rock mass, the width of the structural planes, the spacing between the structural planes, the rock mass quality indicators, and the groundwater state characterization parameters, and the rock mass geomechanical classification indicators are obtained. Using rock mass geomechanical classification indicators, intelligent in-situ classification and evaluation of surrounding rock in underground engineering is carried out, and a visualization model of rock mass category information is constructed.

2. The method for intelligent sensing and in-situ classification of surrounding rock in underground engineering as described in claim 1, characterized in that, The constructed rock mass structure surface parameter inversion model during drilling is as follows: in, L i For the first i Location of each structural surface; S i For the first i Each structural surface originates from; S i+1 For the first i +1 structural surface starting point; D i For the first i Each structural surface termination point; D i+1 For the first i +1 structural surface termination point; The width of the structural surface; w i This refers to the spacing between structural surfaces.

3. The method for intelligent sensing and in-situ classification of surrounding rock in underground engineering as described in claim 2, characterized in that, The formula for calculating rock mass quality indicators is as follows: in, r i The length of the complete segment between structural surfaces, and the length of the starting segment. r 0= S 1; L This refers to the drilling depth; RQD Rock mass quality indicators; h i This represents the effective length of the complete segment between structural surfaces.

4. The method for intelligent sensing and in-situ classification of surrounding rock in underground engineering as described in claim 1, characterized in that, After the drilling test is completed, the in-situ drilling equipment equipped with a pore water pressure gauge and a borehole stress gauge is used to conduct fracture water pressure test and maximum principal stress test, respectively.

5. The method for intelligent sensing and in-situ classification of surrounding rock in underground engineering as described in claim 1, characterized in that, The constructed intelligent in-situ classification model for surrounding rock during drilling is as follows: in, , , , , , A 1 is the equivalent compressive strength of the rock mass. ECS The function, A 2 is the spacing between structural surfaces. w The function, A 3 is the width of the structural surface. d The function, A 4 is the rock mass quality index RQD The function, A 5 is a groundwater state characterization parameter. k The function, RMR These are the geomechanical classification indicators for rock masses.

6. The method for intelligent sensing and in-situ classification of surrounding rock in underground engineering as described in claim 5, characterized in that, The following is a smart in-situ classification and evaluation of surrounding rock in underground engineering: When the RMR value of the rock mass obtained by drilling tests is in the range of 100-81, the surrounding rock quality is very good and it is classified as Class I surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 80-61, the surrounding rock quality is good and it is classified as Class II surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 60-41, the quality of the surrounding rock is generally average, and it is classified as Class III surrounding rock. When the RMR value of the rock mass obtained by drilling tests is in the range of 40-21, the surrounding rock quality is poor and it is classified as Class IV surrounding rock. When the RMR value of the rock mass obtained from drilling tests is less than 20, the quality of the surrounding rock is very poor, and it is classified as Class V surrounding rock.

7. The method for intelligent sensing and in-situ classification of surrounding rock in underground engineering as described in claim 5, characterized in that, Based on the results of intelligent in-situ classification of surrounding rock in underground engineering, a visualization model of rock mass category information is constructed, specifically including: (1) Number the cross-sections and the boreholes on the cross-sections according to the direction of the tunnel from the outside to the inside; (2) Connect the boundary points of the same type of surrounding rock measured by each borehole in each cross section to obtain the boundary line of different types of surrounding rock; (3) Based on the direction of the tunnel from the outside to the inside, connect the boundary lines of the same type of surrounding rock in all sections in sequence to obtain a visualization model of the rock mass category information of the entire tunnel.

Images