Tunnel surrounding rock ground stress value intelligent analysis method and system based on while-drilling parameters

Abstract

The invention belongs to the technical field of tunnel intelligent construction, and discloses a tunnel surrounding rock ground stress value intelligent analysis method and system based on while-drilling parameters, and the method comprises the following steps: carrying out a tunnel surrounding rock mechanical parameter test, and obtaining the rock uniaxial saturated compressive strength, the rock Poisson's ratio and the elastic modulus; establishing a tunnel surrounding rock crustal stress intelligent analysis sample database based on the while-drilling parameters, and constructing a tunnel initial crustal stress state intelligent classification model based on the while-drilling parameters; based on a classification probability vector output by the classification model, calculating a rock strength-stress ratio, and further analyzing a first principal stress of the tunnel surrounding rock; according to the mechanical specific energy and wave velocity response rule of the surrounding rock three-dimensional stress state, the mapping relation between the mechanical specific energy and the wave velocity is established, and the second principal stress and the third principal stress of the tunnel surrounding rock are analyzed in combination with the acoustic elasticity theory. According to the method, intelligent analysis of the tunnel crustal stress is realized, the timeliness of tunnel crustal stress analysis and the safety and economy of construction are improved, and guidance is provided for intelligent tunnel construction.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent tunnel construction, and in particular to a method and system for intelligently analyzing ground stress values ​​of tunnel surrounding rocks based on drilling parameters. Background Art

[0002] With an aging population and a growing labor shortage, promoting unmanned or even unmanned tunnel construction in areas with complex geological conditions, high and extremely high geostress, has become a key industry development priority. Furthermore, as tunnel construction expands to greater depths, the geostress of the surrounding rock directly impacts tunnel face stability, severely impacting the safety and efficiency of tunnel construction.

[0003] Traditional geostress testing methods are costly and time-consuming, making them inadequate for intelligent construction. With the advancement of tunneling technology, a large number of face parameters are acquired in real time while drilling. Through artificial intelligence technologies such as machine learning, intelligent geostress analysis can be performed quickly and automatically. This provides data support for support design and a reference for rockburst risk assessment, effectively ensuring the safety of intelligent tunnel construction and reducing project costs. Summary of the Invention

[0004] In order to solve the problems existing in the prior art, the present invention provides a method and system for intelligent analysis of tunnel surrounding rock stress values ​​based on drilling parameters, which can realize intelligent analysis of tunnel ground stress and solve the problems mentioned in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for intelligently analyzing the ground stress value of the tunnel surrounding rock based on drilling parameters, comprising the following steps:

[0006] S1. Conduct mechanical parameter tests on tunnel surrounding rock to obtain the rock's uniaxial saturated compressive strength, Poisson's ratio, and elastic modulus;

[0007] S2. Conduct field data collection, establish a sample database for intelligent analysis of tunnel surrounding rock in-situ stress based on drilling parameters, and construct an intelligent classification model for the initial in-situ stress state of the tunnel based on drilling parameters;

[0008] S3. Based on the classification probability vector output by the intelligent classification model of the tunnel's initial geostress state, the rock strength stress ratio is calculated, and then the first principal stress of the tunnel surrounding rock is analyzed;

[0009] S4. Based on the mechanical specific energy and wave velocity response law of the three-dimensional stress state of the surrounding rock, a mapping relationship between mechanical specific energy and wave velocity is established. Combined with the acoustic elasticity theory, the second and third principal stresses of the tunnel surrounding rock are analyzed.

[0010] Preferably, in step S2, field data collection is carried out to establish a sample database of tunnel surrounding rock in-situ stress intelligent analysis based on drilling parameters, and an intelligent classification model of tunnel initial in-situ stress state based on drilling parameters is constructed, which specifically includes the following:

[0011] S21. The sample database includes four drilling parameters automatically collected by the intelligent drilling rig and the initial ground stress state of the surrounding rock at the tunnel face determined by the geological sketch of the tunnel face;

[0012] S22. Taking the tunnel face excavation cycle as a unit, six statistical features of the four while-drilling parameters are calculated, specifically including the mean, first quartile, second quartile, third quartile, standard deviation, and coefficient of variation; and a one-dimensional feature vector of the while-drilling parameters is constructed;

[0013] S23. An integrated learning algorithm is used to construct an intelligent classification model for the initial ground stress state of the tunnel based on drilling parameters.

[0014] Preferably, in step S21, the four drilling parameters automatically collected by the drilling rig include feed rate, impact pressure, thrust pressure, and rotary pressure; the initial ground stress state of the surrounding rock determined by the geological sketch of the face includes general ground stress, high ground stress, and extremely high ground stress.

[0015] Preferably, in step S22, the quartiles are obtained by arranging the data in ascending order and then dividing the ordered data set into four equal intervals, and finally determining the values ​​corresponding to the three split points; wherein the first quartile Q1 corresponds to the value at the 25th percentile position, the second quartile Q2 is the median, corresponding to the value at the 50th percentile position, and the third quartile Q3 corresponds to the value at the 75th percentile position; the mean, standard deviation, and coefficient of variation are calculated as follows:

[0016]

[0017] Where: u c is the mean of the data points; c i is a single data point; n c is the total number of data points; σ c is the standard deviation of the data points; c v,c is the coefficient of variation of the data points.

[0018] Preferably, step S23 specifically includes: splitting the data set into a training set and a test set in a ratio of 4:1, using six traditional machine learning methods including support vector machine SVM, nearest neighbor algorithm KNN, random forest RF, extreme tree ET, gradient boosting GB, and bagging method Bag, adopting the Bayesian optimization algorithm, using 1×24 while-drilling parameter feature vector as input parameter, and initial ground stress state as output parameter to construct six initial ground stress state classification base models; adopting the Stacking ensemble learning method, using the output values ​​of the six base models as new features, selecting the linear regression model as the meta-model, and constructing an intelligent classification model of the initial ground stress state of the tunnel based on the while-drilling parameters.

[0019] Preferably, the step S3 specifically includes the following:

[0020] S31. Calculate the rock strength-stress ratio based on the classification probability vector output by the intelligent classification model for the tunnel's initial geostress state: Obtain classification probability vectors for three initial geostress states: general geostress, high geostress, and extremely high geostress based on the intelligent classification model for the tunnel's initial geostress state. Based on the rock strength-stress ratio intervals corresponding to different stress states, set the characteristic values ​​of the general geostress, high geostress, and extremely high geostress samples to 10, 5.5, and 1, respectively. Calculate the rock strength-stress ratio based on the classification probability vector for the initial geostress state and the characteristic value of the rock strength-stress ratio. The calculation formula is:

[0021]

[0022] Where: y n is the predicted value of the rock strength ratio of the sample; x i is the eigenvalue of the i-th subclass; P i is the classification probability of the i-th subclass; n is the number of subclasses;

[0023] S32. Further analyze the first principal stress of the tunnel surrounding rock based on the rock uniaxial saturated compressive strength: The first principal stress of the tunnel surrounding rock is further calculated by combining the rock uniaxial saturated compressive strength obtained from the test with the analyzed rock strength stress. The calculation formula is:

[0024]

[0025] Where: σ1 is the first principal stress; R c is the uniaxial saturated compressive strength of rock; y n is the predicted value of the rock strength ratio of the sample.

[0026] Preferably, the step S4 specifically includes the following:

[0027] S41. Establish a mapping relationship between mechanical specific energy and wave velocity based on the response law of mechanical specific energy and wave velocity in the three-dimensional stress state of the surrounding rock: Calculate mechanical specific energy based on four drilling parameters, conduct experiments on the response law of mechanical specific energy, wave velocity, and ground stress in the three-dimensional stress state, and explore the response law of mechanical specific energy and wave velocity in the three-dimensional stress state of the surrounding rock by testing the wave velocity of the rock mass under different stress states. Establish a mapping relationship between mechanical specific energy and wave velocity using a logarithmic function. The formula for calculating mechanical specific energy and the mapping relationship between mechanical specific energy and wave velocity are as follows:

[0028]

[0029] Where: Ω mse is the mechanical specific energy; D is the drill hole diameter; D ha 、D hb Respectively, the diameters of the rear and front ends of the impact cylinder piston; m h is the piston mass; L h is the impact stroke of the impact piston; i r is the reduction ratio of the rotary mechanism; q r is the displacement of the hydraulic motor; V r is the rotation speed; D f P is the rear end diameter of the propulsion mechanism piston; f is the propulsion pressure; P r is the rotation pressure; P h is the striking pressure; V d is the feed rate; V p,2 is the wave velocity test value in the second principal stress direction; V p,3 is the test value of wave velocity in the third principal stress direction;

[0030] S42. Combined with the acoustoelasticity theory, analyze the second and third principal stresses of the tunnel surrounding rock: According to the acoustoelasticity theory, the propagation speed of ultrasonic waves has a good relationship with the stress state of the medium. The mapping relationship between stress, wave velocity of the surrounding rock, and mechanical parameters of the surrounding rock is as follows:

[0031]

[0032] Where: σ i is the i-th principal stress; ρ0 is the density of the surrounding rock; V p,i is the longitudinal wave velocity in the direction of the i-th principal stress; λ and μ are the second-order elastic constants of the surrounding rock; l and m are the third-order elastic constants of the surrounding rock;

[0033] The Poisson's ratio and elastic modulus of the rock mass obtained through the test are used to calculate the second-order elastic constant and the third-order elastic constant based on elastic mechanics. The calculation formula is:

[0034]

[0035] Where: E is the elastic modulus of rock mass; v is the Poisson's ratio of rock mass.

[0036] On the other hand, to achieve the above-mentioned purpose, the present invention further provides the following technical solution: an intelligent analysis system for tunnel surrounding rock stress based on drilling parameters, comprising the following modules:

[0037] Tunnel surrounding rock mechanical parameter testing module: Conduct tunnel surrounding rock mechanical parameter testing to obtain rock uniaxial saturated compressive strength, rock mass Poisson's ratio and elastic modulus;

[0038] Sample database and intelligent classification model construction module for tunnel initial geostress state: Field data collection is carried out to establish a sample database for intelligent analysis of tunnel surrounding rock geostress based on drilling parameters. The sample database includes four drilling parameters and the initial geostress state of the tunnel face surrounding rock. Six statistical features of the four drilling parameters are used to construct a one-dimensional feature vector of the drilling parameters. An integrated learning algorithm is used to build an intelligent classification model for the initial geostress state of the tunnel.

[0039] Intelligent analysis module for the first principal stress of the tunnel surrounding rock: Based on the classification probability vector output by the intelligent classification model of the tunnel initial geostress state, the module calculates the rock strength stress ratio and then analyzes the first principal stress of the tunnel surrounding rock;

[0040] Tunnel surrounding rock second and third principal stress analysis module: Based on the mechanical specific energy and wave velocity response law of the surrounding rock's three-dimensional stress state, a mapping relationship between mechanical specific energy and wave velocity is established. Combined with acoustic elasticity theory, the second and third principal stresses of the tunnel surrounding rock are analyzed.

[0041] On the other hand, to achieve the above-mentioned purpose, the present invention further provides the following technical solution: an electronic device, comprising: a processor; and a storage device for storing one or more programs;

[0042] When the one or more programs are executed by the processor, the processor executes the intelligent analysis method of tunnel surrounding rock stress values ​​based on drilling parameters.

[0043] On the other hand, to achieve the above-mentioned purpose, the present invention also provides the following technical solution: a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent analysis method of tunnel surrounding rock stress values ​​based on drilling parameters.

[0044] The beneficial effects of the present invention are: based on the face drilling parameters collected during tunnel excavation, the present invention realizes rapid and intelligent analysis of tunnel ground stress through machine learning algorithms and acoustic elasticity theory, improves the timeliness of tunnel ground stress acquisition, provides data support for support design and rock burst risk assessment, improves tunnel construction efficiency and safety, reduces construction costs, and facilitates intelligent tunnel construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of the intelligent analysis method for the ground stress value of the tunnel surrounding rock based on the drilling parameters;

[0046] Figure 2 A schematic diagram of the process for constructing an intelligent classification model for the initial geostress state of a tunnel based on drilling parameters and analyzing the first principal stress of the tunnel surrounding rock;

[0047] Figure 3 Schematic diagram of the intelligent analysis system module for tunnel surrounding rock stress values ​​based on drilling parameters;

[0048] Figure 4 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention;

[0049] In the figure, 110 is a tunnel surrounding rock mechanical parameter testing module; 120 is a sample database and intelligent classification model construction module for the initial ground stress state of the tunnel; 130 is an intelligent analysis module for the first principal stress of the tunnel surrounding rock; 140 is an analysis module for the second principal stress and the third principal stress of the tunnel surrounding rock; 210 is a processor; and 220 is a storage device. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0051] In tunnel construction, tunnel geostress is a key factor affecting face stability and construction safety. Traditional testing methods, such as hydraulic fracturing and acoustic emission, are labor-intensive and time-consuming, making them inadequate for the real-time geostress data required for intelligent tunnel construction.

[0052] To this end, through extensive research and practice, the inventors have proposed a method for rapidly and intelligently analyzing tunnel geostresses using machine learning algorithms and acoustic elasticity theory, based on face-on-drilling parameters collected during tunnel excavation. This method aims to provide a fast, automated method for analyzing tunnel geostresses, improving tunnel construction efficiency and safety, reducing tunnel construction costs, and enhancing the level of intelligent tunnel construction.

[0053] See also Figure 1 This embodiment provides a technical solution: a method for intelligently analyzing the ground stress value of the tunnel surrounding rock based on drilling parameters, which includes the following steps:

[0054] Step S1: Conduct mechanical parameter testing of the tunnel surrounding rock to obtain the rock's uniaxial saturated compressive strength, Poisson's ratio, and elastic modulus. The rock's uniaxial saturated compressive strength is obtained through uniaxial compressive strength testing according to Section 2.7 of the "Standard for Testing Methods of Engineering Rock Masses" (GBT 50266-2013). The rock's Poisson's ratio and elastic modulus are obtained through uniaxial compression deformation testing according to Section 6.3 of the "Code for Rock Testing in Water Conservancy and Hydropower Engineering" (SL / T 264-2020).

[0055] Step S2: Conduct field data collection, establish a sample database for intelligent analysis of tunnel surrounding rock in-situ stress based on drilling parameters, and construct an intelligent classification model for the initial in-situ stress state of the tunnel based on drilling parameters.

[0056] S21. The sample database for intelligent analysis of tunnel surrounding rock in-situ stress based on drilling parameters includes four drilling parameters automatically collected by the drilling rig: feed rate, impact pressure, thrust pressure, and rotation pressure. The initial in-situ stress state of the tunnel face surrounding rock is determined by the geological sketch of the tunnel face. The intelligent drilling rig automatically collects a set of drilling parameters every 20 mm of drilling. An example of data recorded by the intelligent drilling rig for a certain blasthole on a certain tunnel face is shown in Table 1.

[0057] Table 1 Example of data of a certain blasthole on a tunnel face recorded by the intelligent drilling rig

[0058]

[0059] The initial geostress state of the surrounding rock mass at the tunnel face in the sample database was obtained through geological sketching of the tunnel face. According to the Railway Tunnel Design Code TB 10003-2016, initial geostress states can be divided into three categories: normal geostress, high geostress, and extremely high geostress. The assessment criteria for initial geostress states are shown in Table 2.

[0060] Table 2 Initial ground stress state assessment benchmark

[0061]

[0062] S22. Taking the tunnel face excavation cycle as the unit, six statistical features of the four drilling parameters are calculated, including the first quartile, mean, second quartile, standard deviation, third quartile, and coefficient of variation; and a one-dimensional feature vector of the drilling parameters is constructed.

[0063] Quartiles are calculated by arranging the data in ascending order and then dividing the ordered data set into four equal intervals. The values ​​corresponding to the three split points are finally determined. The first quartile (Q1) corresponds to the value at the 25th percentile position, the second quartile (Q2) is the median, corresponding to the value at the 50th percentile position, and the third quartile (Q3) corresponds to the value at the 75th percentile position. The formulas for calculating the mean, standard deviation, and coefficient of variation are as follows:

[0064]

[0065] Where: u c is the mean of the data points; c i is a single data point; n c is the total number of data points; σ c is the standard deviation of the data points; c v,c is the coefficient of variation of the data points.

[0066] S23. An integrated learning algorithm is used to construct an intelligent classification model for the initial ground stress state of the tunnel based on drilling parameters.

[0067] like Figure 2 As shown in the figure, the dataset is split into training and test sets with a ratio of 4:1. Six traditional machine learning methods, including support vector machine (SVM), k-nearest neighbor algorithm (KNN), random forest (RF), extreme tree (ET), gradient boosting (GB), and bagging (Bag), are used. The Bayesian optimization algorithm is adopted, and 1×24 while-drilling parameter feature vectors are used as input parameters and the initial ground stress state is used as output parameters to construct six initial ground stress state classification base models. The stacking ensemble learning method is adopted, and the output values ​​of the six base models are used as new features. The linear regression model is selected as the meta-model to construct an intelligent classification model for the initial ground stress state of the tunnel based on the while-drilling parameters.

[0068] Step S3: Based on the classification probability vector output by the intelligent classification model of the tunnel initial geostress state, the rock strength stress ratio is calculated, and then the first principal stress of the tunnel surrounding rock is analyzed.

[0069] S31. Calculate the rock strength stress ratio based on the classification probability vector output by the intelligent classification model of the tunnel's initial geostress state.

[0070] like Figure 2 As shown in the figure, based on the intelligent classification model of the tunnel initial geostress state, the classification probability vectors of three initial geostress states, namely general geostress, high geostress, and extremely high geostress, are obtained. According to the rock strength-stress ratio intervals corresponding to different stress states, the characteristic values ​​of the general geostress, high geostress, and extremely high geostress samples are set to 10, 5.5, and 1, respectively. The rock strength-stress ratio is calculated based on the classification probability vector of the initial geostress state and the characteristic value of the rock strength-stress ratio. The calculation formula is:

[0071]

[0072] Where: y n is the predicted value of the rock strength ratio of the sample; x i is the eigenvalue of the i-th subclass; P i is the classification probability of the i-th subclass; n is the number of subclasses.

[0073] Taking two typical tunnel faces as examples, the calculation results of the rock strength stress ratio at the tunnel faces are shown in Table 3.

[0074] Table 3 Calculation results of rock strength stress ratio of typical faces of two tunnels

[0075] Serial number tunnel mileage Rock strength stress ratio 1 Test Tunnel No. 1 PDK100+6.57 8.13 2 Test Tunnel No. 1 PDK100+9.23 9.42 3 Test Tunnel No. 1 PDK101+2.6 8.45 4 Test Tunnel No. 1 PDK101+6.28 8.57 5 Test Tunnel No. 1 PDK101+9.69 7.47 6 Test Tunnel No. 1 PDK102+3.29 9.26 7 Test Tunnel No. 1 PDK102+6.78 8.37 8 Test Tunnel No. 1 PDK103+0.92 8.44 9 Test Tunnel No. 2 DK1215+118.5 3.16 10 Test Tunnel No. 2 DK1215+121.38 4.29 11 Test Tunnel No. 2 DK1215+123.5 4.33 12 Test Tunnel No. 2 DK1215+124.63 4.59

[0076] S32. Further analyze the first principal stress of the tunnel surrounding rock based on the uniaxial saturated compressive strength of the rock.

[0077] like Figure 2 As shown in the figure, the first principal stress of the tunnel surrounding rock is further calculated by the rock uniaxial saturated compressive strength obtained from the test and the rock strength stress obtained by analysis. The calculation formula is:

[0078]

[0079] Where: σ1 is the first principal stress, unit: MPa; R c is the uniaxial saturated compressive strength of rock, unit: MPa; n is the predicted value of the rock strength ratio of the sample.

[0080] Step S4: Based on the mechanical specific energy and wave velocity response law of the surrounding rock's three-dimensional stress state, a mapping relationship between mechanical specific energy and wave velocity is established, and combined with the acoustic elasticity theory, the second principal stress and the third principal stress of the tunnel surrounding rock are analyzed.

[0081] S41. Based on the mechanical specific energy and wave velocity response law of the surrounding rock's three-dimensional stress state, a mapping relationship between mechanical specific energy and wave velocity was established. The mechanical specific energy was calculated based on four drilling parameters, and experiments on the mechanical specific energy-wave velocity-ground stress response law of the three-dimensional stress state were conducted. By testing the rock mass wave velocity under different stress states, the mechanical specific energy and wave velocity response law of the surrounding rock's three-dimensional stress state were explored. The mapping relationship between mechanical specific energy and wave velocity was established in the form of a logarithmic function. The calculation formula for mechanical specific energy and the mapping relationship between mechanical specific energy and wave velocity are as follows:

[0082]

[0083] Where: Ω mse is the mechanical specific energy, unit is Pa; D is the drilling diameter, unit is mm; D ha 、D hb Respectively, the rear and front diameters of the impact cylinder piston, in mm; m h is the piston mass, unit is kg; L h is the impact stroke of the impact piston, in mm; i r is the reduction ratio of the rotary mechanism; q r is the hydraulic motor displacement, unit: mL3 / r. V r is the rotation speed, unit is r / min; D f P is the rear end diameter of the propulsion mechanism piston, in mm; f is the propulsion pressure, in bar; P r is the rotation pressure, unit bar; P h is the impact pressure, unit bar; V d is the feed rate, in m / min; V p,2 V is the wave velocity test value in the second principal stress direction, in km / s; p,3 It is the wave velocity test value in the third principal stress direction, in km / s.

[0084] S42. Combined with acoustic elasticity theory, analyze the second and third principal stresses of the tunnel surrounding rock;

[0085] According to the acoustoelastic effect, the propagation speed of ultrasonic waves has a good relationship with the stress state of the medium. The mapping relationship between stress and the wave velocity and mechanical parameters of the surrounding rock is as follows:

[0086]

[0087] Where: σ i is the i-th principal stress (i=2,3), unit: MPa; ρ0 is the density of the surrounding rock, unit: kg / m 3 ; V p,i is the longitudinal wave velocity in the direction of the i-th principal stress (i=2,3), unit: m / s; λ and μ are the second-order elastic constants of the surrounding rock; l and m are the third-order elastic constants of the surrounding rock.

[0088] The Poisson's ratio and elastic modulus of the rock mass obtained through the test are used to calculate the second-order elastic constant and the third-order elastic constant based on elastic mechanics. The calculation formula is:

[0089]

[0090]

[0091] Where: λ and μ are the second-order elastic constants of the surrounding rock; l and m are the third-order elastic constants of the surrounding rock; E is the elastic modulus of the rock mass, in GPa; v is the Poisson's ratio of the rock mass.

[0092] Taking two typical tunnel faces as examples, the tunnel ground stress analysis results are shown in Table 4.

[0093] Table 4 Analysis results of ground stress at typical faces of two tunnels

[0094] Serial number tunnel mileage <![CDATA[σ1 / MPa]]> <![CDATA[σ2 / MPa]]> <![CDATA[σ3 / MPa]]> 1 Test Tunnel No. 1 PDK100+6.57 8.55 8.31 7.74 2 Test Tunnel No. 1 PDK100+9.23 11.76 11.40 10.54 3 Test Tunnel No. 1 PDK101+2.6 8.35 8.11 7.60 4 Test Tunnel No. 1 PDK101+6.28 8.58 8.32 7.84 5 Test Tunnel No. 1 PDK101+9.69 7.99 7.71 7.31 6 Test Tunnel No. 1 PDK102+3.29 9.23 8.97 8.32 7 Test Tunnel No. 1 PDK102+6.78 8.12 7.88 7.44 8 Test Tunnel No. 1 PDK103+0.92 8.06 7.82 7.35 9 Test Tunnel No. 2 DK1215+118.5 3.70 3.58 3.42 10 Test Tunnel No. 2 DK1215+121.38 4.12 3.99 3.80 11 Test Tunnel No. 2 DK1215+123.5 4.69 4.51 4.33 12 Test Tunnel No. 2 DK1215+124.63 4.43 4.31 4.06

[0095] Based on the same inventive concept as the above method embodiment, the embodiment of the present application also provides a tunnel surrounding rock stress value intelligent analysis system based on drilling parameters, which can realize the functions provided by the above method embodiment, such as Figure 3 As shown, the system includes the following modules:

[0096] Tunnel surrounding rock mechanical parameter testing module 110: Conduct rock uniaxial saturated compressive strength testing in accordance with the "Standard for Engineering Rock Test Methods" (GBT 50266-2013), and conduct rock Poisson's ratio and elastic modulus testing in accordance with the "Rock Testing Procedures for Water Conservancy and Hydropower Engineering" (SL / T 264-2020);

[0097] Module 120: Constructing a sample database and intelligent classification model for the initial geostress state of a tunnel. This module collects on-site data and establishes a sample database for intelligent analysis of geostress in the surrounding rock of a tunnel based on drilling parameters. The sample database includes four drilling parameters and the initial geostress state of the surrounding rock at the tunnel face. Six statistical features of the four drilling parameters are used to construct a one-dimensional feature vector for the drilling parameters. An integrated learning algorithm is used to construct an intelligent classification model for the initial geostress state of a tunnel.

[0098] Tunnel surrounding rock first principal stress intelligent analysis module 130: Based on the classification probability vector output by the intelligent classification model of the tunnel initial ground stress state, the rock strength stress ratio is calculated to analyze the tunnel surrounding rock first principal stress;

[0099] Tunnel surrounding rock second principal stress and third principal stress analysis module 140: Based on the mechanical specific energy and wave velocity response law of the surrounding rock's three-dimensional stress state, a mapping relationship between mechanical specific energy and wave velocity is established, and combined with the acoustic elasticity theory, the second principal stress and third principal stress of the tunnel surrounding rock are analyzed.

[0100] Based on the same inventive concept as the above method embodiment, the embodiment of the present application further provides an electronic device, such as Figure 4 As shown, the device includes: a processor 210; and a storage 220 for storing one or more programs;

[0101] When the one or more programs are executed by the processor 210, the processor executes the intelligent analysis method of tunnel surrounding rock stress values ​​based on drilling parameters.

[0102] The intelligent analysis method of tunnel surrounding rock stress values ​​based on drilling parameters includes the following:

[0103] Conduct mechanical parameter tests on tunnel surrounding rock to obtain the rock's uniaxial saturated compressive strength, Poisson's ratio, and elastic modulus;

[0104] Conduct field data collection, establish a sample database for intelligent analysis of tunnel surrounding rock in-situ stress based on drilling parameters, and construct an intelligent classification model for the initial in-situ stress state of the tunnel based on drilling parameters;

[0105] Based on the classification probability vector output by the intelligent classification model of the tunnel's initial geostress state, the rock strength stress ratio is calculated, and then the first principal stress of the tunnel surrounding rock is analyzed;

[0106] According to the mechanical specific energy and wave velocity response law of the three-dimensional stress state of the surrounding rock, the mapping relationship between mechanical specific energy and wave velocity is established, and combined with the acoustic elasticity theory, the second principal stress and the third principal stress of the tunnel surrounding rock are analyzed.

[0107] Based on the same inventive concept as the above-mentioned method embodiment, the embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor 210, it implements the intelligent analysis method of the tunnel surrounding rock stress value based on the drilling parameters.

[0108] The intelligent analysis method of tunnel surrounding rock stress values ​​based on drilling parameters includes the following:

[0109] Conduct mechanical parameter tests on tunnel surrounding rock to obtain the rock's uniaxial saturated compressive strength, Poisson's ratio, and elastic modulus;

[0110] Conduct field data collection, establish a sample database for intelligent analysis of tunnel surrounding rock in-situ stress based on drilling parameters, and construct an intelligent classification model for the initial in-situ stress state of the tunnel based on drilling parameters;

[0111] Based on the classification probability vector output by the intelligent classification model of the tunnel's initial geostress state, the rock strength stress ratio is calculated, and then the first principal stress of the tunnel surrounding rock is analyzed;

[0112] According to the mechanical specific energy and wave velocity response law of the three-dimensional stress state of the surrounding rock, the mapping relationship between mechanical specific energy and wave velocity is established, and combined with the acoustic elasticity theory, the second principal stress and the third principal stress of the tunnel surrounding rock are analyzed.

[0113] This method uses machine learning algorithms and other artificial intelligence technologies, along with acoustic elasticity theory, to intelligently analyze tunnel geostresses based on face-to-face drilling parameters automatically collected by intelligent drilling rigs. This method analyzes tunnel geostresses in real time during the drilling process, without the need for geologists. Compared to traditional testing methods such as hydraulic fracturing and acoustic emission, this method significantly reduces labor and material costs and improves the efficiency of geostress analysis. This method can effectively guide tunnel construction decisions and facilitate intelligent tunnel construction, especially under conditions of high or extremely high geostress.

[0114] In the several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0115] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0116] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or partly contributed to the prior art or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk. It should be noted that, in this article, the terms "include", "comprising" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without further constraints, an element defined by the phrase "comprises a..." does not preclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0117] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0118] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0119] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0120] The references to "first" and "second" in the embodiments merely distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the specific order or precedence of "first" and "second" can be interchanged where appropriate. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0121] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent analysis method for tunnel surrounding rock stress values ​​based on drilling parameters is characterized by: The following steps are involved: S1. Conduct mechanical parameter tests on tunnel surrounding rock to obtain the rock's uniaxial saturated compressive strength, Poisson's ratio, and elastic modulus; S2. Conduct field data collection, establish a sample database for intelligent analysis of tunnel surrounding rock in-situ stress based on drilling parameters, and construct an intelligent classification model for the initial in-situ stress state of the tunnel based on drilling parameters; S3. Based on the classification probability vector output by the intelligent classification model of the tunnel's initial geostress state, the rock strength stress ratio is calculated, and then the first principal stress of the tunnel surrounding rock is analyzed; S4. Based on the mechanical specific energy and wave velocity response law of the three-dimensional stress state of the surrounding rock, a mapping relationship between mechanical specific energy and wave velocity is established. Combined with the acoustic elasticity theory, the second and third principal stresses of the tunnel surrounding rock are analyzed.

2. The intelligent analysis method for tunnel surrounding rock stress values ​​based on drilling parameters according to claim 1 is characterized by: In step S2, field data collection is carried out to establish a sample database of tunnel surrounding rock in-situ stress intelligent analysis based on while-drilling parameters, and to construct an intelligent classification model of tunnel initial in-situ stress state based on while-drilling parameters, which specifically includes the following: S21. The sample database includes four drilling parameters automatically collected by the intelligent drilling rig and the initial ground stress state of the surrounding rock at the tunnel face determined by the geological sketch of the tunnel face; S22. Taking the tunnel face excavation cycle as a unit, six statistical features of the four while-drilling parameters are calculated, specifically including the mean, first quartile, second quartile, third quartile, standard deviation, and coefficient of variation; and a one-dimensional feature vector of the while-drilling parameters is constructed; S23. An integrated learning algorithm is used to construct an intelligent classification model for the initial ground stress state of the tunnel based on drilling parameters.

3. The intelligent analysis method for tunnel surrounding rock stress values ​​based on drilling parameters according to claim 2 is characterized by: In step S21, the four drilling parameters automatically collected by the drilling rig include feed rate, impact pressure, thrust pressure, and rotary pressure; the initial ground stress state of the surrounding rock determined by the geological sketch of the tunnel face includes normal ground stress, high ground stress, and extremely high ground stress.

4. The intelligent analysis method for tunnel surrounding rock stress values ​​based on drilling parameters according to claim 2 is characterized by: In step S22, the quartiles are obtained by arranging the data in ascending order and then dividing the ordered data set into four equal intervals, and finally determining the values ​​corresponding to the three split points; the first quartile Q1 corresponds to the value at the 25th percentile position, the second quartile Q2 is the median, corresponding to the value at the 50th percentile position, and the third quartile Q3 corresponds to the value at the 75th percentile position; the mean, standard deviation, and coefficient of variation are calculated as follows: Where: u c is the mean of the data points; c i is a single data point; n c is the total number of data points; σ c is the standard deviation of the data points; σ v,c is the coefficient of variation of the data points.

5. The intelligent analysis method of tunnel surrounding rock stress values ​​based on drilling parameters according to claim 2 is characterized by: The step S23 specifically includes: splitting the data set into a training set and a test set in a ratio of 4:1, applying six traditional machine learning methods including support vector machine (SVM), nearest neighbor algorithm (KNN), random forest (RF), extreme tree (ET), gradient boosting (GB), and bagging (Bag), adopting a Bayesian optimization algorithm, using a 1×24 while-drilling parameter feature vector as an input parameter and the initial ground stress state as an output parameter to construct six initial ground stress state classification base models; adopting a stacking ensemble learning method, using the output values ​​of the six base models as new features, selecting a linear regression model as a meta-model, and constructing an intelligent classification model for the initial ground stress state of the tunnel based on the while-drilling parameters.

6. The intelligent analysis method of tunnel surrounding rock stress values ​​based on drilling parameters according to claim 1 is characterized by: The step S3 specifically includes the following: S31. Calculate the rock strength-stress ratio based on the classification probability vector output by the intelligent classification model for the tunnel's initial geostress state: Obtain classification probability vectors for three initial geostress states: general geostress, high geostress, and extremely high geostress based on the intelligent classification model for the tunnel's initial geostress state. Based on the rock strength-stress ratio intervals corresponding to different stress states, set the characteristic values ​​of the general geostress, high geostress, and extremely high geostress samples to 10, 5.5, and 1, respectively. Calculate the rock strength-stress ratio based on the classification probability vector for the initial geostress state and the characteristic value of the rock strength-stress ratio. The calculation formula is: Where: y n is the predicted value of the rock strength ratio of the sample; x i is the eigenvalue of the i-th subclass; P i is the classification probability of the i-th subclass; n is the number of subclasses; S32. Further analyze the first principal stress of the tunnel surrounding rock based on the rock uniaxial saturated compressive strength: The first principal stress of the tunnel surrounding rock is further calculated by combining the rock uniaxial saturated compressive strength obtained from the test with the analyzed rock strength stress. The calculation formula is: Where: σ1 is the first principal stress; R c is the uniaxial saturated compressive strength of rock; y n is the predicted value of the rock strength ratio of the sample.

7. The intelligent analysis method of tunnel surrounding rock stress values ​​based on drilling parameters according to claim 1 is characterized by: The step S4 specifically includes the following: S41. Establish a mapping relationship between mechanical specific energy and wave velocity based on the response law of mechanical specific energy and wave velocity in the three-dimensional stress state of the surrounding rock: Calculate mechanical specific energy based on four drilling parameters, conduct experiments on the response law of mechanical specific energy, wave velocity, and ground stress in the three-dimensional stress state, and explore the response law of mechanical specific energy and wave velocity in the three-dimensional stress state of the surrounding rock by testing the wave velocity of the rock mass under different stress states. Establish a mapping relationship between mechanical specific energy and wave velocity using a logarithmic function. The formula for calculating mechanical specific energy and the mapping relationship between mechanical specific energy and wave velocity are as follows: Where: Ω mse is the mechanical specific energy; D is the drill hole diameter; D ha 、D hb Respectively, the diameters of the rear and front ends of the impact cylinder piston; m h is the piston mass; L h is the impact stroke of the impact piston; i r is the reduction ratio of the rotary mechanism; q r is the displacement of the hydraulic motor; V r is the rotation speed; D f P is the rear end diameter of the propulsion mechanism piston; f is the propulsion pressure; P r is the rotation pressure; P h is the striking pressure; V d is the feed rate; V p,2 is the wave velocity test value in the second principal stress direction; V p,3 is the test value of wave velocity in the third principal stress direction; S42. Combined with the acoustoelasticity theory, analyze the second and third principal stresses of the tunnel surrounding rock: According to the acoustoelasticity theory, the propagation speed of ultrasonic waves has a good relationship with the stress state of the medium. The mapping relationship between stress, wave velocity of the surrounding rock, and mechanical parameters of the surrounding rock is as follows: Where: σ i is the i-th principal stress; ρ0 is the density of the surrounding rock; V p,i is the longitudinal wave velocity in the direction of the i-th principal stress; λ and μ are the second-order elastic constants of the surrounding rock; l and m are the third-order elastic constants of the surrounding rock; The Poisson's ratio and elastic modulus of the rock mass obtained through the test are used to calculate the second-order elastic constant and the third-order elastic constant based on elastic mechanics. The calculation formula is: Where: E is the elastic modulus of rock mass; v is the Poisson's ratio of rock mass.

8. A system for intelligent analysis of tunnel surrounding rock stress values ​​based on drilling parameters according to any one of claims 1 to 7, characterized in that: Includes the following modules: Tunnel surrounding rock mechanical parameter test module (110): conduct tunnel surrounding rock mechanical parameter test to obtain rock uniaxial saturated compressive strength, rock mass Poisson's ratio and elastic modulus; Sample database and intelligent classification model construction module for initial geostress of tunnels (120): Conduct field data collection and establish a sample database for intelligent analysis of geostress of tunnel surrounding rocks based on drilling parameters. The sample database includes four drilling parameters and initial geostress of surrounding rocks at the tunnel face. Six statistical features of the four drilling parameters are used to construct a one-dimensional feature vector of the drilling parameters. An integrated learning algorithm is used to construct an intelligent classification model for initial geostress of tunnels. Tunnel surrounding rock first principal stress intelligent analysis module (130): based on the classification probability vector output by the tunnel initial ground stress state intelligent classification model, calculates the rock strength stress ratio and then analyzes the tunnel surrounding rock first principal stress; The second principal stress and third principal stress analysis module (140) of the tunnel surrounding rock is to establish a mapping relationship between the mechanical specific energy and the wave velocity according to the mechanical specific energy and the wave velocity response law of the three-dimensional stress state of the surrounding rock, and to analyze the second principal stress and the third principal stress of the tunnel surrounding rock in combination with the acoustic elasticity theory.

9. An electronic device, characterized in that: The electronic device includes: a processor (210); and a storage (220) for storing one or more programs; When the one or more programs are executed by the processor (210), the processor is enabled to execute the intelligent analysis method for tunnel surrounding rock stress values ​​based on drilling parameters as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by the processor (210), the method for intelligently analyzing the ground stress value of the tunnel surrounding rock based on drilling parameters as described in any one of claims 1 to 7 is implemented.

Images