Intelligent Analysis Method and System for Tunnel Surrounding Rock Mechanical Parameters Based on Drilling Parameters

Abstract

This invention belongs to the field of intelligent tunnel construction technology and discloses a method and system for intelligent analysis of tunnel surrounding rock mechanical parameters based on drilling parameters. The method includes the following steps: constructing a sample database and feature system for intelligent analysis of tunnel surrounding rock mechanical parameters based on drilling parameters; constructing a sub-level intelligent grading model of tunnel surrounding rock based on drilling parameters using a transfer learning algorithm; and analyzing the elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the surrounding rock based on the grading probability vector output by the sub-level intelligent grading model and the feature values ​​of the surrounding rock mechanical parameters of each sub-level. This invention achieves intelligent analysis of tunnel surrounding rock mechanical parameters by combining the grading probability vector output by the sub-level intelligent grading model of tunnel surrounding rock based on drilling parameters with the feature values ​​of the mechanical parameters of each sub-level. This improves the efficiency of obtaining tunnel surrounding rock mechanical parameters, reduces tunnel construction costs, enhances construction efficiency and safety, and provides guidance for intelligent tunnel construction.

Description

Technical Field

[0001] This invention relates to the field of intelligent tunnel construction technology, specifically to an intelligent analysis method and system for tunnel surrounding rock mechanical parameters based on drilling parameters. Background Technology

[0002] With the accelerating aging of the population and the increasing prominence of labor shortages, the transformation of tunnel engineering towards less-staffed and unmanned construction models has become a key direction for the industry's development. Meanwhile, as tunnel engineering continues to expand into deeper and more complex geological areas, obtaining the surrounding rock mechanical parameters provides a scientific and reliable reference for the formulation of subsequent construction plans, playing a crucial role in ensuring safe and efficient tunnel construction.

[0003] Traditional methods for obtaining tunnel surrounding rock mechanical parameters, such as on-site sampling followed by laboratory testing or field testing, are costly and time-consuming, making them insufficient for the needs of intelligent construction. With the development of tunnel boring technology, a large number of tunnel face parameters are acquired in real time. Through artificial intelligence technologies such as machine learning, these parameters can be rapidly and intelligently analyzed, providing a scientific and reliable reference for subsequent construction planning. This effectively ensures the safety of intelligent tunnel construction and reduces project costs. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides an intelligent analysis method and system for tunnel surrounding rock mechanical parameters based on drilling parameters, which can realize intelligent analysis of tunnel surrounding rock mechanical parameters and solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent analysis method for tunnel surrounding rock mechanical parameters based on drilling parameters, comprising the following steps:

[0006] S1. Construct a sample database of intelligent analysis of tunnel surrounding rock mechanical parameters based on drilling parameters;

[0007] S2. Construct an intelligent analytical feature system for the mechanical parameters of the surrounding rock of the tunnel based on drilling parameters;

[0008] S3. Employ transfer learning algorithms to construct a sub-level intelligent classification model for tunnel surrounding rock based on drilling parameters;

[0009] S4. Based on the classification probability vector and the characteristic values ​​of the surrounding rock mechanical parameters of each sub-level output by the intelligent classification model of tunnel surrounding rock sub-level, the elastic modulus, Poisson's ratio, cohesion and internal friction angle of the surrounding rock are obtained analytically.

[0010] Preferably, in step S1, the sample database includes four raw drilling parameters automatically collected by the intelligent rock drilling rig: rotational pressure, feed rate, impact pressure, and propulsion pressure; the surrounding rock grade of the face includes Grade II, Grade III1, Grade III2, Grade IV1, Grade IV2, Grade V1, and Grade V2.

[0011] Preferably, the intelligent analytical feature system for tunnel surrounding rock mechanical parameters based on drilling parameters in step S2 specifically includes the following:

[0012] S21. Based on four original drilling parameters, calculate five rock drillability indices: equivalent feed rate, equivalent thrust, difficulty drilling index, E index, and equivalent impact force; calculate four energy indices: propulsion specific energy, impact specific energy, rotational specific energy, and mechanical specific energy.

[0013] S22. Taking the excavation cycle at the working face as a unit, statistically analyze 6 statistical characteristics of 4 original drilling parameters, 5 rock drillability indices, and 4 energy indices, specifically including standard deviation, first quartile, second quartile, third quartile, coefficient of variation, and mean; construct a 78-characteristic system for drilling parameters.

[0014] Preferably, in step S21, the calculation formulas for the five rock drillability indicators and four energy indicators are as follows:

[0015]

[0016]

[0017] Where: δ ff It is the equivalent propulsive force; D is the drill bit diameter; P is the equivalent thrust. r It is the rotational pressure; q r It refers to the motor displacement; i r It is the reduction ratio; P f It is the driving force; D f It is the diameter of the rear end of the piston; δ fh It is the equivalent striking power; D ca D cb These are the diameters of the piston in the hydraulic cylinder after impact and the front end, respectively; m h For piston mass; t h It is the impact time of the fiber tail; P h It is to exert pressure; δ v It is the equivalent feed rate; V r It is the drill bit rotation speed; V d It is the feed rate; δ hard It's a difficult indicator to penetrate; E is the E indicator; Ψ h It is the impact energy; S h It is the impact trajectory; Ψ r It is the specific energy of rotation; Ψt It is the propulsion specific energy; Ψ m It is mechanical specific energy.

[0018] Preferably, in step S22, the data points of the 5 rock drillability indicators and 4 energy indicators are arranged in ascending order, and then the data are divided into four equal intervals to determine the values ​​at the three dividing points. Among them, the first quartile Q1 is located at the 25th percentile after the data is sorted, the second quartile Q2 is the median, located at the 50th percentile, and the third quartile Q3 corresponds to the 75th percentile. The mean reflects the central tendency of the data, the standard deviation measures the degree of dispersion, and the coefficient of variation is the ratio of the standard deviation to the mean, which is used to compare the dispersion of data of different dimensions.

[0019] Preferably, in step S3, a transfer learning algorithm is used to construct a sub-level intelligent classification model of tunnel surrounding rock based on drilling parameters, specifically including the following:

[0020] S31. Training a sub-level intelligent classification source model for tunnel surrounding rock based on source domain drilling parameters: After normalizing the sample database, it is divided into two datasets: a source domain and a target domain. The 78 features of the drilling parameters in the source domain dataset are horizontally concatenated into a 1×78 input feature vector as input. A convolutional neural network (CNN) is used for feature extraction and classification. The network structure includes convolutional layers, pooling layers, and fully connected layers. The fully connected layers use the Softmax activation function, and the cross-entropy loss function and Adam adaptive learning rate optimization are used to calculate the loss and optimize the model's weights and bias parameters to complete the source model training.

[0021] S32. Training a sub-level intelligent hierarchical transfer learning model for tunnel surrounding rock based on target domain drilling parameters: Load the source model trained on the source domain dataset, then freeze the parameters of the convolutional layers and the fully connected layers except for the last two layers, so that the weights and biases of these layers remain unchanged during the transfer learning process and are not updated; horizontally concatenate the 78 features of the target domain dataset into a 1×78 input feature vector and use it as the target data input, then fine-tune based on the target data, and retrain the fully connected layers of the model using the Adam optimizer to adjust the parameters of the fully connected layers;

[0022] Through the above steps, the source model adapts to the target domain data, obtaining a tunnel surrounding rock sub-level intelligent grading transfer learning model, thus completing the construction of a tunnel surrounding rock sub-level intelligent grading model based on drilling parameters.

[0023] Preferably, in step S4, based on the classification probability vector output by the intelligent classification model of tunnel surrounding rock sub-levels and the characteristic values ​​of the surrounding rock mechanical parameters of each sub-level, the elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the surrounding rock are analytically obtained, specifically including the following:

[0024] S41. Calculate the characteristic values ​​of the mechanical parameters of the surrounding rock elastic modulus, Poisson's ratio, cohesion, and internal friction angle for each sub-level.

[0025] S42. Based on the output of the intelligent classification model of tunnel surrounding rock sub-levels, analyze the classification probability vector and the characteristic values ​​of the surrounding rock mechanical parameters of each sub-level.

[0026] Preferably, in step S41: according to the "Railway Tunnel Design Code TB 10003-2016", the average of the upper and lower limits of the surrounding rock mechanical parameters of each sub-level is taken as its characteristic value; the characteristic values ​​of the elastic modulus corresponding to the surrounding rock levels of the tunnel face from level II to level V2 are 25, 15.35, 8.35, 4.9, 2.55, 1.65, and 1.15 GPa, respectively; the characteristic values ​​of the Poisson's ratio corresponding to levels II to V2 are 0.225, 0.255, 0.28, 0.305, 0.33, 0.37, and 0.42, respectively; the characteristic values ​​of the internal friction angle corresponding to levels II to V2 are 55, 47, 41.5, 37, 31, 24.5, and 21°, respectively; and the characteristic values ​​of the cohesion corresponding to levels II to V2 are 1.8, 1.3, 0.9, 0.6, 0.35, 0.16, and 0.085 MPa, respectively.

[0027] Preferably, in step S42, the elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the surrounding rock are calculated based on the classification probability vector of the surrounding rock sub-level and the characteristic values ​​of each surrounding rock mechanical parameter. The calculation formula is as follows:

[0028]

[0029] In the formula: y E y ν y C , These are the analytical results for the elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the tunnel surrounding rock; E i ν i C i , These are the eigenvalues ​​of subtype i; P i It is the probability of sub-level type i output by the intelligent classification model of tunnel surrounding rock sub-level.

[0030] On the other hand, to achieve the above objectives, the present invention also provides the following technical solution: an intelligent analysis system for tunnel surrounding rock mechanical parameters based on drilling parameters, comprising the following modules:

[0031] Sample database construction module: Constructs a sample database, which includes drilling parameters of the face and the corresponding sub-levels of the surrounding rock at the face;

[0032] Feature system construction module: Calculates rock drillability index, energy index, and statistical characteristics, and constructs a 78-feature system for drilling parameters;

[0033] Tunnel Surrounding Rock Sub-level Intelligent Grading Model Construction Module: Employs transfer learning algorithm to construct a tunnel surrounding rock sub-level intelligent grading model based on drilling parameters;

[0034] Tunnel surrounding rock mechanical parameter analysis module: Based on the probability vector of surrounding rock sub-level classification and the characteristic values ​​of surrounding rock mechanical parameters of each sub-level, the surrounding rock mechanical parameters are obtained by analysis.

[0035] The beneficial effects of this invention are as follows: Based on the drilling parameters collected during tunnel construction, this invention achieves rapid and real-time intelligent analysis of the surrounding rock mechanical parameters through artificial intelligence technologies such as transfer learning. This provides a scientific and reliable reference for the formulation of subsequent construction plans, effectively ensuring the safety of intelligent tunnel construction, reducing engineering costs, and contributing to intelligent tunnel construction. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the intelligent analysis method for tunnel surrounding rock mechanical parameters based on drilling parameters in an embodiment of the present invention;

[0037] Figure 2 This is a schematic diagram of the process for constructing the drilling parameter feature system in an embodiment of the present invention;

[0038] Figure 3 This is a schematic diagram illustrating the process of constructing a tunnel surrounding rock sub-classification model based on drilling parameters and analyzing the surrounding rock mechanical parameters in an embodiment of the present invention.

[0039] Figure 4 This is a schematic diagram of the intelligent analysis system module for tunnel surrounding rock mechanical parameters based on drilling parameters in an embodiment of the present invention;

[0040] In the diagram, 110 is the sample database construction module; 120 is the feature system construction module; 130 is the tunnel surrounding rock sub-level intelligent classification model construction module; and 140 is the tunnel surrounding rock mechanical parameter analysis module. Detailed Implementation

[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0042] Example 1

[0043] In tunnel construction, the mechanical parameters of the surrounding rock reflect its physical and mechanical properties and are an important basis for subsequent construction planning. Traditional methods for obtaining these parameters, such as on-site sampling followed by laboratory testing or conducting field tests, are costly and time-consuming, and are no longer sufficient to meet the needs of intelligent construction.

[0044] To address this, through long-term research and practice, the inventors proposed a method for rapid and intelligent analysis of tunnel surrounding rock mechanical parameters based on drilling face parameters collected during tunnel excavation, using a transfer learning algorithm. This method aims to provide a fast and automated approach for analyzing tunnel surrounding rock mechanical parameters, improving the efficiency of parameter acquisition, reducing tunnel construction costs, and enhancing the level of intelligent tunnel construction.

[0045] Please see Figure 1 This invention provides a technical solution: an intelligent analysis method and system for tunnel surrounding rock mechanical parameters based on drilling parameters, comprising the following steps:

[0046] Step S1: Construct a sample database of intelligent analysis of tunnel surrounding rock mechanical parameters based on drilling parameters.

[0047] The sample database includes four drilling parameters automatically collected by the intelligent rock drilling rig: rotational pressure, feed rate, impact pressure, and propulsion pressure. The surrounding rock grade of the working face is determined by standard methods, including Grade II, Grade III1, Grade III2, Grade IV1, Grade IV2, Grade V1, and Grade V2. An example of data for a certain borehole at a certain working face recorded by the intelligent rock drilling rig is shown in Table 1.

[0048] Table 1. Example of data from a specific borehole on a certain working face recorded by an intelligent rock drilling rig.

[0049]

[0050]

[0051] The rock mass level of the tunnel face in the sample library is obtained by standard classification according to the "Railway Tunnel Design Code TB10003-2016". The rock mass level can be divided into I to VI. The common rock mass level in actual engineering is II to V. For II to V, the rock mass level is further subdivided according to the code, and the rock mass sub-level is III1 to V2.

[0052] Step S2: Construct an intelligent analytical feature system for tunnel surrounding rock mechanical parameters based on drilling parameters.

[0053] S21, such as Figure 2As shown, based on four original drilling parameters, five rock drillability indices are calculated: equivalent feed rate, equivalent thrust, difficulty-to-drill index, E index, and equivalent impact force. Four energy indices are also calculated: propulsion specific energy, impact specific energy, rotational specific energy, and mechanical specific energy. The calculation formulas are as follows:

[0054]

[0055] Where: δ ff It is the equivalent propulsive force, in N; D is the drill bit diameter, in mm; P r It is the rotational pressure, in Pa; q r This refers to the motor displacement, measured in ml / r; i r It is the reduction ratio; P f It is the propulsion pressure, measured in bar; D f It is the diameter of the rear end of the propellant piston, in mm; δ fh It is the equivalent striking force, measured in N; D ca D cb These are the diameters of the piston in the hydraulic cylinder after impact and the front end, respectively, in mm; m h For piston mass; t h It is the impact time of the fiber tail, measured in seconds; P h It is the impact pressure, measured in bar; δ v It is the equivalent feed rate; V r V is the drill bit rotation speed, measured in r / min; d It is the feed rate, in m / min; δ hard It's a difficult indicator to penetrate; E is the E indicator; Ψ h It is the impact energy, measured in Pa; S h It is the impact stroke, in mm; Ψ r It is the specific energy of rotation, in Pa; Ψ t It is the specific energy of propulsion, in Pa; Ψ m It is mechanical specific energy, measured in Pa.

[0056] S22, such as Figure 2 As shown, taking the excavation cycle at the face as a unit, six statistical characteristics of four original drilling parameters, five rock drillability indices, and four energy indices were statistically analyzed. Specifically, these characteristics include six items: standard deviation, first quartile, second quartile, third quartile, coefficient of variation, and mean. A 78-characteristic system for drilling parameters was constructed.

[0057] The data points for 5 rock drillability indicators and 4 energy indicators were arranged in ascending order. Then, the data were divided into four equal intervals to determine the values ​​at three dividing points. The first quartile, Q1, is located at the 25th percentile after the data is sorted; the second quartile, Q2, which is the median, is located at the 50th percentile; and the third quartile, Q3, is located at the 75th percentile. The mean reflects the central tendency of the data, the standard deviation measures the degree of dispersion, and the coefficient of variation is the ratio of the standard deviation to the mean, used to compare the dispersion of data with different dimensions.

[0058] Step S3: Use transfer learning algorithm to construct a sub-level intelligent classification model of tunnel surrounding rock based on drilling parameters.

[0059] S31. Training a sub-level intelligent hierarchical source model for tunnel surrounding rock based on source domain drilling parameters;

[0060] like Figure 3 As shown, the sample database is normalized and then divided into source and target domain datasets proportionally. The 78 features of the source domain dataset are horizontally concatenated into a 1×78 input feature vector, which is then used for feature extraction and classification using a Convolutional Neural Network (CNN). The network structure includes convolutional layers, pooling layers, and fully connected layers. The fully connected layers use the Softmax activation function, and the cross-entropy loss function and Adam adaptive learning rate optimization are employed to calculate the loss and optimize the model's weights and biases to complete model training.

[0061] S32. Training a sub-level intelligent hierarchical transfer learning model for tunnel surrounding rock based on target domain drilling parameters;

[0062] like Figure 3 As shown, the source model trained on the source domain data is loaded, and then the parameters of the convolutional layers and the fully connected layers (except for the last two layers) are frozen. This ensures that the weights and biases of these layers remain unchanged during the transfer learning process and are not updated. The 78 features of the drilling parameters of the target dataset are horizontally concatenated into a 1×78 input feature vector, which is then used as the input to the target data. Fine-tuning is then performed based on the target data, and the fully connected layers of the model are retrained using the Adam optimizer to adjust the parameters of the fully connected layers. Through these steps, the source model adapts to the target domain data, resulting in a tunnel surrounding rock sub-level intelligent grading transfer learning model; thus, the construction of a tunnel surrounding rock sub-level intelligent grading model based on drilling parameters is completed.

[0063] Step S4: Based on the classification probability vector and the characteristic values ​​of the surrounding rock mechanical parameters of each sub-level output by the intelligent classification model of tunnel surrounding rock sub-level, the elastic modulus, Poisson's ratio, cohesion and internal friction angle of the surrounding rock are obtained analytically.

[0064] S41, such as Figure 3As shown, the characteristic values ​​of mechanical parameters such as elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the surrounding rock for each sub-level are calculated; based on the "Railway Tunnel Design Code TB" According to the "10003-2016", the average of the upper and lower limits of the surrounding rock mechanical parameters of each sub-level is used as its characteristic value. The characteristic values ​​of elastic modulus corresponding to Level II to Level V2 are 25, 15.35, 8.35, 4.9, 2.55, 1.65, and 1.15 GPa, respectively; the characteristic values ​​of Poisson's ratio corresponding to Level II to Level V2 are 0.225, 0.255, 0.28, 0.305, 0.33, 0.37, and 0.42, respectively; the characteristic values ​​of internal friction angle corresponding to Level II to Level V2 are 55, 47, 41.5, 37, 31, 24.5, and 21°, respectively; and the characteristic values ​​of cohesion corresponding to Level II to Level V2 are 1.8, 1.3, 0.9, 0.6, 0.35, 0.16, and 0.085 MPa, respectively.

[0065] S42, such as Figure 3 As shown, the elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the surrounding rock are calculated based on the classification probability vector of the surrounding rock sub-level and the characteristic values ​​of each surrounding rock mechanical parameter. The calculation formula is as follows:

[0066]

[0067] In the formula: y E y ν y C , These are the analytical results for the elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the tunnel surrounding rock, respectively. E y C , The units are GPa, MPa, and ° respectively; E i ν i C i , These are the eigenvalues ​​of subtype i, E i C i , The units are GPa, MPa, and ° respectively; P i It is the probability of sub-level type i output by the intelligent classification model of tunnel surrounding rock sub-level.

[0068] Table 2 shows examples of intelligent analysis results for typical tunnel surrounding rock mechanical parameters.

[0069] Table 2 Examples of Intelligent Analysis Results of Typical Tunnel Surrounding Rock Mechanical Parameters

[0070]

[0071] Based on the same inventive concept as the above-described method embodiments, this application also provides an intelligent analysis system for tunnel surrounding rock mechanical parameters based on drilling parameters. This system can achieve the functions provided by the above-described method embodiments, such as... Figure 4 As shown, the system includes the following modules:

[0072] Sample database construction module 110: Constructs a sample database, which includes drilling parameters of the face and the corresponding sub-levels of the surrounding rock at the face;

[0073] Feature system construction module 120: Calculate drillability, energy index, and statistical characteristics, and construct a feature system of 78 drilling parameters;

[0074] Module 130 for constructing intelligent sub-class classification model of tunnel surrounding rock: Using transfer learning algorithm, construct intelligent sub-class classification model of tunnel surrounding rock based on drilling parameters;

[0075] Tunnel surrounding rock mechanical parameter analysis module 140: Based on the probability vector of surrounding rock sub-level classification and the characteristic values ​​of surrounding rock mechanical parameters of each sub-level, the surrounding rock mechanical parameters are obtained by analysis.

[0076] This invention is based on the drilling parameters collected by an intelligent rock drilling rig during tunnel construction. Through artificial intelligence technologies such as transfer learning, it achieves rapid and real-time intelligent analysis of the surrounding rock mechanical parameters. This method can complete the dynamic analysis of surrounding rock parameters during drilling, which greatly improves efficiency and reduces costs compared with traditional testing methods. It provides a scientific and reliable reference for the formulation of subsequent construction plans, effectively ensures the safety of intelligent tunnel construction, and contributes to intelligent tunnel construction.

[0077] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0078] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0079] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0080] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0081] The terms "first" and "second" used in the embodiments are merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permitted. 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 those illustrated or described herein.

[0082] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent analysis of tunnel surrounding rock mechanical parameters based on drilling parameters, characterized in that, Includes the following steps: S1. Construct a sample database of intelligent analysis of tunnel surrounding rock mechanical parameters based on drilling parameters; S2. Construct an intelligent analytical feature system for the mechanical parameters of the surrounding rock of the tunnel based on drilling parameters; S3. Employing transfer learning algorithms, a sub-level intelligent classification model for tunnel surrounding rock based on drilling parameters is constructed; specifically, it includes the following: S31. Training a sub-level intelligent classification source model for tunnel surrounding rock based on source domain drilling parameters: After normalizing the sample database, it is divided into two datasets: a source domain and a target domain. The 78 features of the drilling parameters in the source domain dataset are horizontally concatenated into a 1×78 input feature vector as input. A convolutional neural network (CNN) is used for feature extraction and classification. The network structure includes convolutional layers, pooling layers, and fully connected layers. The fully connected layers use the Softmax activation function, and the cross-entropy loss function and Adam adaptive learning rate optimization are used to calculate the loss and optimize the model's weights and bias parameters to complete the source model training. S32. Training a sub-level intelligent hierarchical transfer learning model for tunnel surrounding rock based on target domain drilling parameters: Load the source model trained on the source domain dataset, then freeze the parameters of the convolutional layers and the fully connected layers except for the last two layers, so that the weights and biases of these layers remain unchanged during the transfer learning process and are not updated; horizontally concatenate the 78 features of the target domain dataset into a 1×78 input feature vector and use it as the target data input, then fine-tune based on the target data, and retrain the fully connected layers of the model using the Adam optimizer to adjust the parameters of the fully connected layers; Through steps S31-S32, the source model adapts to the target domain data, obtaining a tunnel surrounding rock sub-level intelligent grading transfer learning model, thus completing the construction of a tunnel surrounding rock sub-level intelligent grading model based on drilling parameters. S4. Based on the classification probability vector output by the intelligent classification model of tunnel surrounding rock sub-levels and the characteristic values ​​of surrounding rock mechanical parameters of each sub-level, the elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the surrounding rock are analytically obtained; specifically including the following: S41. Calculate the characteristic values ​​of the mechanical parameters of the surrounding rock elastic modulus, Poisson's ratio, cohesion, and internal friction angle for each sub-level. S42. Based on the output of the intelligent classification model of tunnel surrounding rock sub-levels, analyze the classification probability vector and the characteristic values ​​of the surrounding rock mechanical parameters of each sub-level. The elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the surrounding rock are calculated based on the classification probability vector of the surrounding rock sub-level and the characteristic values ​​of each surrounding rock mechanical parameter. The calculation formula is as follows: ； ； ； ； In the formula: y E 、y ν 、y C 、y φ These are the analytical results for the elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the tunnel surrounding rock. E i 、 ν i 、C i φ i They are sub-types i eigenvalues; P i It is the sub-level type output by the intelligent classification model of tunnel surrounding rock sub-level. i The probability of.

2. The intelligent analysis method for tunnel surrounding rock mechanical parameters based on drilling parameters according to claim 1, characterized in that: In step S1, the sample database includes four raw drilling parameters automatically collected by the intelligent rock drilling rig: rotational pressure, feed rate, impact pressure, and propulsion pressure; the surrounding rock grades at the working face include Grade II, Grade III1, Grade III2, Grade IV1, Grade IV2, Grade V1, and Grade V2.

3. The intelligent analysis method for tunnel surrounding rock mechanical parameters based on drilling parameters according to claim 1, characterized in that: Step S2 involves constructing an intelligent analytical feature system for the mechanical parameters of the tunnel surrounding rock based on drilling parameters, specifically including the following: S21. Based on four original drilling parameters, calculate five rock drillability indices: equivalent feed rate, equivalent thrust, difficulty drilling index, E index, and equivalent impact force; calculate four energy indices: propulsion specific energy, impact specific energy, rotational specific energy, and mechanical specific energy. S22. Taking the excavation cycle at the working face as a unit, statistically analyze 6 statistical characteristics of 4 original drilling parameters, 5 rock drillability indices, and 4 energy indices, specifically including standard deviation, first quartile, second quartile, third quartile, coefficient of variation, and mean; construct a 78-characteristic system for drilling parameters.

4. The intelligent analysis method for tunnel surrounding rock mechanical parameters based on drilling parameters according to claim 3, characterized in that: In step S21, the calculation formulas for the five rock drillability indices and four energy indices are as follows: ； ； ； ； ； ； ； ； ； In the formula: It is an equivalent propulsive force; D It is the drill bit diameter; It is the rotational pressure; It refers to the motor displacement; It is the reduction ratio; It is the pressure to push forward; It is the diameter of the rear end of the piston; It is the equivalent striking power; , These are the diameters of the front end of the cylinder piston after it strikes the hydraulic cylinder. For piston mass; It is the impact time of the fiber tail; It is to exert pressure; It is the equivalent feed rate; It is the drill bit rotation speed; It is the feed rate; These are indicators that are difficult to penetrate; E yes E index; It's about hitting the target more effectively; It is an impact journey; It is the specific energy of rotation; It is to promote specific energy; It is mechanical specific energy.

5. The intelligent analysis method for tunnel surrounding rock mechanical parameters based on drilling parameters according to claim 3, characterized in that: In step S22, the data points of the five rock drillability indicators and four energy indicators are arranged in ascending order. Then, the data are divided into four equal-length intervals, thereby determining the values ​​at three dividing points; where the first quartile is... Q1 Located at the 25th percentile after data sorting, the second quartile. Q2 That is, the median, located at the 50th percentile; the third quartile. Q3 This corresponds to the 75th position; the mean reflects the central tendency of the data, the standard deviation measures the degree of dispersion, and the coefficient of variation is the ratio of the standard deviation to the mean, used to compare the dispersion of data of different dimensions.

6. The intelligent analysis method for tunnel surrounding rock mechanical parameters based on drilling parameters according to claim 1, characterized in that: In step S41: the average value of the upper and lower limits of the surrounding rock mechanical parameters of each sub-level is used as its characteristic value; The characteristic values ​​of elastic modulus for grades II to V2 of the working face surrounding rock are 25, 15.35, 8.35, 4.9, 2.55, 1.65, and 1.15 GPa, respectively; the characteristic values ​​of Poisson's ratio for grades II to V2 are 0.225, 0.255, 0.28, 0.305, 0.33, 0.37, and 0.42, respectively; the characteristic values ​​of internal friction angle for grades II to V2 are 55, 47, 41.5, 37, 31, 24.5, and 21 °, respectively; and the characteristic values ​​of cohesion for grades II to V2 are 1.8, 1.3, 0.9, 0.6, 0.35, 0.16, and 0.085 MPa, respectively.

7. A system for intelligent analysis of tunnel surrounding rock mechanical parameters based on drilling parameters according to any one of claims 1-6, characterized in that: Includes the following modules: Sample database construction module (110): Constructs a sample database, which includes the drilling parameters of the face and the corresponding sub-levels of the surrounding rock at the face; Feature system construction module (120): Calculate rock drillability index, energy index, and statistical characteristics, and construct the 78 feature system of drilling parameters; Tunnel Surrounding Rock Sub-level Intelligent Grading Model Construction Module (130): Using the transfer learning algorithm, a tunnel surrounding rock sub-level intelligent grading model based on drilling parameters is constructed; Tunnel surrounding rock mechanical parameter analysis module (140): Based on the probability vector of surrounding rock sub-level classification and the characteristic values ​​of surrounding rock mechanical parameters of each sub-level, the surrounding rock mechanical parameters are obtained by analysis.

Images