Tunnel surrounding rock multi-mode intelligent fine grading method and system

Abstract

The invention belongs to the field of tunnel engineering, and particularly discloses a tunnel surrounding rock multi-mode intelligent fine grading method and system, and the method comprises the steps: 1, constructing a sample library which comprises parameters while drilling of a tunnel face, a digital image and a corresponding tunnel face surrounding rock grade; 2, constructing a while-drilling parameter refined grading characteristic system; 3, constructing a surrounding rock intelligent grading model based on multi-modal data fusion; 4, dividing the rock mass in front of the tunnel face into a plurality of three-dimensional space unit bodies according to the tunnel contour and blast hole distribution characteristics; and 5, based on the surrounding rock intelligent grading model, finely and intelligently judging the grade of the tunnel face surrounding rock. According to the method, the intelligent surrounding rock grading model based on the multi-modal data fusion theory is constructed, the refined intelligent judgment of the tunnel face surrounding rock grade is realized, the precision and robustness of the refined intelligent judgment of the surrounding rock grade of the model are improved, the surrounding rock grading level in the construction stage is improved, more comprehensive reference is provided for a subsequent construction scheme, and the construction efficiency is improved. And tunnel intelligent construction is guided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent tunnel construction, and in particular to a multi-modal intelligent fine grading method and system for tunnel surrounding rock. Background Art

[0002] In tunnel construction, accurate identification of surrounding rock grade is of great significance to construction safety and progress. Traditional surrounding rock classification mainly relies on manual experience and on-site surveys, which are highly subjective and inaccurate, and are difficult to adapt to the refined construction needs under complex geological conditions. With the development of tunnel excavation technology, a large number of face drilling parameters and digital images can be obtained in real time. Through deep learning, machine learning and other artificial intelligence technologies, intelligent identification of surrounding rock grade can avoid human errors and more efficiently process and analyze complex construction environment data.

[0003] At the same time, the surrounding rock structure is complex and changeable, with significant local differences. The identification of the surrounding rock level should meet refined standards in order to formulate more accurate construction measures and reduce construction risks. Therefore, a single modality and overall classification are often not enough to fully reflect the true situation of the rock mass in front of the face. The multi-modal intelligent and refined classification of surrounding rock combines the drilling parameters and the face image information, comprehensively considers the characteristics of each modal data, and achieves a more comprehensive and accurate identification of the surrounding rock level. At the same time, it effectively avoids the roughness of the overall identification and can identify changes in the local surrounding rock level. Therefore, the multi-modal intelligent and refined classification of tunnel surrounding rock can effectively improve the intelligence level and safety of tunnel construction, assist in scientific decision-making during the construction process, and reduce engineering risks. 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 multimodal intelligent fine grading of tunnel surrounding rock, which can realize multimodal intelligent fine grading of tunnel surrounding rock 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 tunnel surrounding rock multi-modal intelligent fine classification method and system, comprising the following steps:

[0006] S1. Constructing a sample library, which includes original drilling parameters, digital images and corresponding surrounding rock grades of the tunnel face;

[0007] S2. Constructing a refined classification feature system for drilling parameters;

[0008] S3, constructing a surrounding rock intelligent classification model based on multimodal data fusion;

[0009] S4. Divide the rock mass in front of the tunnel face into several three-dimensional space units according to the tunnel contour and blasthole distribution characteristics;

[0010] S5. Based on the intelligent surrounding rock classification model, the surrounding rock grade of the tunnel face is intelligently identified.

[0011] Preferably, the drilling parameters of the face in the sample library in step S1 include feed speed, impact pressure, thrust pressure and rotation pressure automatically collected by the intelligent drilling trolley, the digital image of the face is collected by the onboard industrial camera of the trolley, and the surrounding rock grade of the face is determined by a standard method, including grade II, grade III, grade IV and grade V.

[0012] Preferably, in step S2, a refined classification feature system of drilling parameters is constructed, which specifically includes the following:

[0013] S21. Based on the four original drilling parameters, five rock drillability indices including equivalent propulsion force, equivalent impact force, difficulty in drilling index, E index and equivalent feed rate are calculated;

[0014] S22. Taking the tunnel face excavation cycle as the unit, six statistical characteristics of four original drilling parameters and five rock drillability indices are counted, including the mean, first quartile, second quartile, third quartile, standard deviation and coefficient of variation;

[0015] S23. Taking the tunnel face excavation cycle as a unit, a 9×2×3 three-dimensional feature vector of the while-drilling parameters is generated according to the original while-drilling parameters, rock drillability index, and statistical feature type.

[0016] Preferably, the step S21 specifically includes: 5 rock drillability indicators and propulsion force F f 、Impact force F h and the rotation torque M r The calculation formula is:

[0017] Γ ff =F f / (M r / D)

[0018] Γ fh =F h / (M r / D)

[0019] Γ v =V p / (V r D)

[0020] Γ hard =Γ ff Γ fh / Γ v

[0021]

[0022] Where:ff is the equivalent propulsive force; F f is the thrust, in N; D is the drill diameter, in mm; M r is the rotational torque, in N·m; Γ fh is the equivalent impact force; F h is the impact force, in N; Γ v is the equivalent feed rate; V p is the feed rate, in m / min; V r is the drilling speed of the drilling tool, in r / min; Γ hard is the difficulty to drill indicator; E is the E indicator; D f is the diameter of the rear end of the piston, in mm; P f is the propulsion pressure, in Pa; D hB is the diameter of the rear end of the piston, in mm; m h is the mass of the piston, in kg; P h is the impact pressure, unit is Pa; S h is the impact stroke, in mm; t h is the time of impacting the fiber tail, in seconds; P r is the rotation pressure, unit: Pa; q r is the motor displacement, in ml / r; i r is the reduction ratio.

[0023] Preferably, the step S22 specifically includes: the quartiles are obtained by sorting the data from small to large and then dividing the sorted data into four equal parts, wherein the first quartile (Q1) corresponds to the value at the 25% position, the second quartile (Q2) is the median, corresponding to the value at the 50% position, and the third quartile (Q3) corresponds to the value at the 75% position, and the mean, standard deviation, and coefficient of variation are calculated as follows:

[0024]

[0025]

[0026] 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.

[0027] Preferably, step S23 specifically includes: combining the original drilling parameters and rock drillability indexes, totaling 9 features, with the first quartile and the second quartile to form a first two-dimensional feature vector, then combining them with the third quartile and the standard deviation to form a second two-dimensional feature vector, and finally combining them with the mean and the coefficient of variation to form a third two-dimensional feature vector, and then stacking these three two-dimensional feature vectors vertically on a two-dimensional plane to construct a 9×2×3 three-dimensional feature vector of the drilling parameters.

[0028] Preferably, the step S3 of constructing a surrounding rock intelligent classification model based on multimodal data fusion specifically includes the following steps:

[0029] S31, extracting features through a dual convolutional neural network and obtaining the classification probability of each modality;

[0030] S32. Establish a weight adaptive adjustment mechanism for the face digital image modality and the drilling parameter modality to achieve automatic training of the multi-modal model.

[0031] Preferably, the step S31 specifically includes: using a dual convolutional neural network algorithm, taking the digital image of the face and the three-dimensional feature vector of the drilling parameters as input, each modal network is provided with a convolution layer and a pooling layer, performing a linear transformation in the fully connected layer, and using the Softmax function to calculate the classification probability of the four surrounding rock levels of each modality.

[0032] Preferably, the step S32 specifically includes: establishing a weight adaptive adjustment mechanism of the face digital image modality and the drilling parameter modality through a cross entropy loss function, that is, a mapping relationship between the graded probabilities of different modalities and the cross entropy function:

[0033]

[0034] Where: L is the loss rate; y i is the actual label; p i is the model prediction probability; K is the total number of label categories; i is the index variable, from 1 to K; weight c is the weight of the c-mode; L c is the loss rate of the c-mode.

[0035] Based on the weight of each mode, the weighted classification probabilities of the four surrounding rock levels are calculated respectively. The weighted classification probabilities of the same surrounding rock level under two modes are added together to obtain the classification probabilities of the four surrounding rock levels of the tunnel surrounding rock multimodal intelligent classification model. The total loss rate of the tunnel surrounding rock multimodal intelligent classification model is calculated using the cross entropy loss function, and the loss rate is allocated according to the weight of each mode, and back propagation is performed to update the model parameters.

[0036] Preferably, in step S4, dividing the rock mass in front of the tunnel face into a plurality of three-dimensional space units according to the tunnel profile and blasthole distribution characteristics specifically includes the following steps:

[0037] S41. In the two-dimensional transverse direction of the tunnel face, along the width and height of the tunnel, the tunnel face is divided into 18 transverse blocks according to the tunnel contour and blasthole distribution;

[0038] S42. The face area is further segmented along the tunnel excavation direction to eventually form a number of three-dimensional space units.

[0039] Preferably, the step S41 specifically includes: taking the center line of the tunnel and the bottom of the pit as the reference, first drawing the horizontal line and the vertical line, and then offsetting them by 2 to 4 m in the up and down and left and right directions respectively, and setting the maximum size of a single block to 2 to 4 m, until the outline boundary of the tunnel is covered; finally, the entire tunnel outline is divided into 18 blocks, numbered from K-1 to K-18, with an area of ​​3m 2 Up to 8m 2 between.

[0040] Preferably, step S42 specifically includes: setting the spacing of the longitudinal segments to 0.4 m, dividing the face in the transverse width and height directions, combining the longitudinal partitions, and finally extending the two-dimensional partitions along the depth in front of the face to form a plurality of three-dimensional space units.

[0041] Preferably, the refined intelligent identification of the surrounding rock level of the tunnel face based on the surrounding rock intelligent grading model in step S5 includes constructing a three-dimensional feature vector of the drilling parameters of each unit body, splitting the digital image of the tunnel face according to the same horizontal blocking method, and inputting the three-dimensional feature vector of the drilling parameters of each unit body and the corresponding horizontally blocked digital image of the tunnel face into the tunnel surrounding rock multimodal intelligent grading model to obtain the surrounding rock level of any unit body, thereby realizing refined intelligent identification of the surrounding rock level of the tunnel face.

[0042] In addition, to achieve the above purpose, the present invention also provides the following technical solution: a tunnel surrounding rock multi-modal intelligent fine classification system, the system includes the following modules:

[0043] Sample library construction module: constructs a sample library, which includes the drilling parameters, digital images and corresponding surrounding rock levels of the tunnel face;

[0044] Feature construction module: constructs a refined classification feature system for drilling parameters;

[0045] Surrounding rock intelligent classification model construction module: construct a surrounding rock intelligent classification model with multi-modal data fusion;

[0046] Rock mass division module in front of the tunnel face: according to the tunnel contour and blasthole distribution characteristics, the rock mass in front of the tunnel face is divided into several three-dimensional space units;

[0047] Intelligent and refined identification module of surrounding rock grade at the tunnel face: Based on the intelligent surrounding rock classification model, it can intelligently and refinedly identify the surrounding rock grade at the tunnel face.

[0048] The beneficial effects of the present invention are as follows: the present invention performs multimodal fusion of the drilling parameters of the tunnel face collected during tunnel excavation with digital images and divides the rock mass in front of the tunnel face, thereby realizing multimodal intelligent and fine grading of the tunnel surrounding rock, improving the comprehensiveness and accuracy of surrounding rock grade identification, avoiding the roughness of overall identification and the subjectivity of human identification, which is conducive to formulating more accurate construction plans, reducing construction risks, and facilitating intelligent tunnel construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a schematic diagram of a process flow of a multi-modal intelligent fine classification method for tunnel surrounding rock in Example 1;

[0050] Figure 2 This is a schematic diagram of a digital image of a tunnel face collected by an airborne industrial camera in Example 1;

[0051] Figure 3 A schematic diagram of constructing a three-dimensional feature vector of drilling parameters in Example 1;

[0052] Figure 4 A schematic diagram of constructing a surrounding rock intelligent classification model by multimodal data fusion in Example 1;

[0053] Figure 5 This is a schematic diagram of the horizontal division and numbering of the tunnel face in Example 1;

[0054] Figure 6 This is an example diagram of the surrounding rock intelligent fine classification results in Example 1;

[0055] Figure 7 This is a schematic diagram of the module of the tunnel surrounding rock multi-modal intelligent fine classification system;

[0056] In the figure, 110 is a sample library construction module; 120 is a feature construction module; 130 is a surrounding rock intelligent classification model construction module; 140 is a rock mass classification module in front of the tunnel face; 150 is a tunnel face surrounding rock grade intelligent and refined identification module. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0058] Example 1

[0059] In tunnel construction, accurate identification of surrounding rock grade is of great significance to construction safety and progress. Traditional surrounding rock classification mainly relies on manual experience and on-site surveys, which are highly subjective and inaccurate, and are difficult to adapt to the refined construction needs under complex geological conditions.

[0060] To this end, the inventors have proposed a multi-modal intelligent fine classification method and system for tunnel surrounding rock through long-term research and practice. Based on the multi-modal fusion of the face drilling parameters and digital images collected during tunnel excavation and the division of the rock mass in front of the face, the multi-modal intelligent fine classification of tunnel surrounding rock is realized. This method aims to provide a fast and accurate multi-modal intelligent fine classification method for surrounding rock, improve the accuracy and refinement level of surrounding rock classification, assist in scientific decision-making during construction, and reduce engineering risks.

[0061] See also Figure 1 This embodiment provides a technical solution: a multi-modal intelligent fine classification method for tunnel surrounding rock, which includes the following steps:

[0062] Step S1: Construct a sample library, which includes the original drilling parameters, digital images and corresponding surrounding rock levels of the face. The original drilling parameters of the sample library include 4 items such as feed speed, impact pressure, thrust pressure and rotary pressure, which are automatically collected by the intelligent drilling rig. Every time 0.02m is drilled, the intelligent drilling rig automatically collects a set of drilling parameters, and the digital image of the face is collected by the rig's airborne industrial camera. An example of the data of a certain blasthole of a face recorded by the intelligent drilling rig is shown in Table 1, and an example of the digital image of the face collected by the airborne industrial camera is shown in Table 2. Figure 2 shown.

[0063] Table 1 Example of data of a certain blasthole on a certain face recorded by the intelligent rock drilling rig

[0064]

[0065] The surrounding rock grade of the tunnel face in the sample library is obtained by standard classification according to the "Railway Tunnel Design Code TB 10003-2016". The surrounding rock grade can be divided into grades I to VI. The common surrounding rock grade in actual projects is grades II to V.

[0066] Step S2: Construct a refined classification feature system for while-drilling parameters.

[0067] 1) Based on the four original drilling parameters, five rock drillability indices including equivalent propulsion force, equivalent impact force, difficulty in drilling index, E index, and equivalent feed rate are calculated. f 、Impact force F h and the rotation torque M r The calculation formula is:

[0068] Γ ff =F f / (M r / D) Formula (1)

[0069] Γ fh =F h / (M r / D) Formula (2)

[0070] Γ v =V p / (V r D) Formula (3)

[0071] Γ hard =Γ ff Γ fh / Γ v Formula (4)

[0072]

[0073] Where: ff is the equivalent propulsive force; F f is the thrust, in N; D is the drill diameter, in mm; M r is the rotational torque, in N·m; Γ fh is the equivalent impact force; F h is the impact force, in N; Γ v is the equivalent feed rate; V p is the feed rate, in m / min; V r is the drilling speed of the drilling tool, in r / min; Γ hard is the difficulty to drill indicator; E is the E indicator; D f is the diameter of the rear end of the piston, in mm; P f is the propulsion pressure, in Pa; D hB is the diameter of the rear end of the piston, in mm; m h is the mass of the piston, in kg; P h is the impact pressure, unit is Pa; S h is the impact stroke, in mm; t h is the time of impacting the fiber tail, in seconds; P ris the rotation pressure, unit: Pa; q r is the motor displacement, in ml / r; i r is the reduction ratio.

[0074] 2) Taking the tunnel face excavation cycle as the unit, six statistical characteristics of four original drilling parameters and five rock drillability indicators were counted, including the mean, first quartile, second quartile, third quartile, standard deviation and coefficient of variation.

[0075] Quartiles are obtained by sorting the data from small to large and then dividing the sorted data into four equal parts, where the first quartile (Q1) corresponds to the value at the 25% position, the second quartile (Q2) is the median, corresponding to the value at the 50% position, and the third quartile (Q3) corresponds to the value at the 75% position. The mean, standard deviation, and coefficient of variation are calculated as follows:

[0076]

[0077] 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.

[0078] 3) Taking the tunnel face excavation cycle as a unit, a 9×2×3 three-dimensional feature vector of the drilling parameters is generated according to the original drilling parameters, rock drillability index, and statistical feature type.

[0079] like Figure 3 As shown in the figure, f1~f9 are the original drilling parameters and rock drillability indicators, totaling 9 features, Q1, Q2, Q3, Std, Mean, and CV are the first quartile, second quartile, first third quartile, standard deviation, mean, and coefficient of variation. The original drilling parameters and rock drillability indicators, totaling 9 features, are first combined with the first quartile and the second quartile to form the first two-dimensional feature vector (M Q1,Q2 ), and then combined with the third quartile and standard deviation to form the second two-dimensional feature vector (M Q3,Std ), and finally combined with the mean and coefficient of variation to form the third two-dimensional feature vector (M Mean,CV ), and then stack these three two-dimensional feature vectors vertically on the two-dimensional plane to construct a 9×2×3 three-dimensional feature vector of the drilling parameters.

[0080] Step S3: Constructing a surrounding rock intelligent classification model based on multimodal data fusion.

[0081] 1) Extract features through dual convolutional neural networks and obtain the classification probability of each modality;

[0082] like Figure 4 As shown in the figure, a dual convolutional neural network algorithm is adopted, and the digital image of the face and the three-dimensional feature vector of the drilling parameters are taken as input. The network of each mode is set with a convolution layer and a pooling layer. Linear transformation is performed in the fully connected layer, and the Softmax function is used to calculate the classification probability of the four surrounding rock levels of each mode.

[0083] 2) Establish a weight adaptive adjustment mechanism for the digital image modality of the face and the drilling parameter modality to achieve automatic training of the multimodal model.

[0084] like Figure 4 As shown in the figure, after calculating the classification probabilities of the two modes, the weight adaptive adjustment mechanism of the face digital image mode and the drilling parameter mode is established through the cross entropy loss function, that is, the mapping relationship between the classification probabilities of different modes and the cross entropy function:

[0085]

[0086] Where: L is the loss rate; y i is the actual label; p i is the model prediction probability; K is the total number of label categories; i is the index variable, from 1 to K; weight c is the weight of the c-mode; L c is the loss rate of the c-mode.

[0087] Based on the weight of each mode, the weighted classification probabilities of the four surrounding rock levels are calculated respectively. The weighted classification probabilities of the same surrounding rock level under two modes are added together to obtain the classification probabilities of the four surrounding rock levels of the tunnel surrounding rock multimodal intelligent classification model. The total loss rate of the tunnel surrounding rock multimodal intelligent classification model is calculated using the cross entropy loss function, and the loss rate is allocated according to the weight of each mode, and back propagation is performed to update the model parameters.

[0088] Step S4: According to the tunnel contour and blasthole distribution characteristics, the rock mass in front of the tunnel face is divided into a number of three-dimensional space units.

[0089] 1) In the two-dimensional transverse direction of the tunnel face, along the width and height of the tunnel, the tunnel face is divided into 18 transverse blocks according to the tunnel contour and blasthole distribution;

[0090] like Figure 5As shown in the figure, the center line of the tunnel and the bottom of the pit are used as the reference. The horizontal and vertical lines are drawn first, and then offset by 2 to 4 meters in the up and down and left and right directions respectively. The maximum size of a single block is set to 2 to 4 meters until the outline boundary of the tunnel is covered. Finally, the entire tunnel outline is divided into 18 blocks, numbered from K-1 to K-18, with an area of ​​3m 2 Up to 8m 2 between.

[0091] 2) The face area is further segmented along the tunneling direction to form several three-dimensional space units. The spacing of the longitudinal segments is set to 0.4m. By dividing the face in the width and height directions, combined with the longitudinal partitions, these two-dimensional partitions are finally extended along the depth in front of the face to form several three-dimensional space units.

[0092] Step S5: Based on the surrounding rock intelligent classification model, fine-grained intelligent identification of the tunnel face surrounding rock level. Fine-grained intelligent identification of the tunnel face surrounding rock level based on the surrounding rock intelligent classification model includes: constructing a three-dimensional feature vector of the drilling parameters of each unit body, splitting the tunnel face digital image in the same horizontal block manner, inputting the three-dimensional feature vector of the drilling parameters of each unit body and the corresponding horizontal block tunnel face digital image into the tunnel surrounding rock multimodal intelligent classification model, obtaining the surrounding rock level of any unit body, and realizing fine-grained intelligent identification of the tunnel face surrounding rock level. Examples of fine-grained identification results of surrounding rock are shown in FIG. Figure 6 shown.

[0093] Example 2

[0094] Based on the same inventive concept as the above method embodiment, the present application embodiment also provides a tunnel surrounding rock multi-modal intelligent fine classification system, which can realize the functions provided by the above method embodiment, such as Figure 7 As shown, the system modules include the following:

[0095] Sample library building module 110: building a sample library, the sample library including original drilling parameters, digital images and corresponding surrounding rock grades of the tunnel face;

[0096] Feature construction module 120: constructing a refined classification feature system of while-drilling parameters;

[0097] Surrounding rock intelligent classification model construction module 130: constructing a surrounding rock intelligent classification model based on multi-modal data fusion;

[0098] The rock mass division module 140 in front of the tunnel face is used to divide the rock mass in front of the tunnel face into a plurality of three-dimensional space units according to the tunnel contour and the blasthole distribution characteristics;

[0099] Intelligent and refined identification module 150 for the surrounding rock grade of the tunnel face: Based on the intelligent surrounding rock classification model, the surrounding rock grade of the tunnel face is intelligently and refinedly identified.

[0100] The present invention realizes multimodal intelligent grading of tunnel surrounding rock based on the drilling parameters and digital images of the tunnel face automatically collected by the intelligent drilling rig and the airborne industrial camera. After the intelligent drilling rig and the airborne industrial camera collect the drilling parameters and digital images of the tunnel face, the method can call the intelligent grading model of surrounding rock fusion with multimodal data to realize multimodal intelligent grading of surrounding rock without the participation of geological personnel. Compared with the traditional manual surrounding rock grading method, it avoids the subjectivity of manual identification of surrounding rock level, reduces the error of manual identification, improves the accuracy of surrounding rock level identification, and improves the refinement level of surrounding rock level identification. This method contributes to scientific decision-making during the construction process and promotes the intelligent construction of tunnels.

[0101] 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 protection scope of the present invention.

Claims

1. A multi-modal intelligent fine classification method for tunnel surrounding rock, characterized in that: The following steps are involved: S1. Constructing a sample library, which includes original drilling parameters, digital images and corresponding surrounding rock grades of the tunnel face; S2. Constructing a refined classification feature system for drilling parameters; S3, constructing a surrounding rock intelligent classification model based on multimodal data fusion; S4. Divide the rock mass in front of the tunnel face into several three-dimensional space units according to the tunnel contour and blasthole distribution characteristics; S5. Based on the intelligent surrounding rock classification model, the surrounding rock grade of the tunnel face is intelligently identified.

2. The multi-modal intelligent fine classification method for tunnel surrounding rock according to claim 1 is characterized by: The original drilling parameters of the face in the sample library in step S1 include feed speed, impact pressure, thrust pressure and rotary pressure automatically collected by the intelligent rock drilling trolley; the digital image of the face is collected by the onboard industrial camera of the trolley; the surrounding rock grade of the face is determined by a standard method, including grade II, grade III, grade IV and grade V.

3. The tunnel surrounding rock multi-modal intelligent fine classification method according to claim 1 is characterized by: The step S2 constructs a refined classification feature system for drilling parameters, which specifically includes the following: S21. Based on the four original drilling parameters, five rock drillability indices including equivalent propulsion force, equivalent impact force, difficult-to-drill index, E index, and equivalent feed rate are calculated; S22. Taking the tunnel face excavation cycle as a unit, six statistical characteristics of four original drilling parameters and five rock drillability indices are counted, including the mean, first quartile, second quartile, third quartile, standard deviation and coefficient of variation; S23. Taking the tunnel face excavation cycle as a unit, a 9×2×3 three-dimensional feature vector of the while-drilling parameters is generated according to the original while-drilling parameters, rock drillability indexes, and statistical characteristics.

4. The multi-modal intelligent fine classification method for tunnel surrounding rock according to claim 3 is characterized by: In step S21, the five rock drillability indicators and the thrust F f 、Impact force F h and the rotation torque M r The calculation formula is: Γ ff =F f / (M r / D) Γ fh =F h / (M r / D) Γ v =V p / (V r D) C hard =C ff C fh / C v In step S22, the quartiles are obtained by sorting the data from small to large and then dividing the sorted data into four equal parts, wherein the first quartile (Q1) corresponds to the value at the 25% position, the second quartile (Q2) is the median, corresponding to the value at the 50% position, and the third quartile (Q3) corresponds to the value at the 75% position. The mean, standard deviation, and coefficient of variation are calculated as follows: In step S23, the original drilling parameters and rock drillability indexes, totaling 9 features, are first combined with the first quartile and the second quartile to form the first two-dimensional feature vector, then combined with the third quartile and the standard deviation to form the second two-dimensional feature vector, and finally combined with the mean and the coefficient of variation to form the third two-dimensional feature vector. These three two-dimensional feature vectors are then stacked vertically on a two-dimensional plane to construct a 9×2×3 three-dimensional feature vector of drilling parameters.

5. The tunnel surrounding rock multi-modal intelligent fine classification method according to claim 1 is characterized by: The step S3 constructs a surrounding rock intelligent classification model based on multimodal data fusion, which specifically includes the following: S31, extracting features through a dual convolutional neural network and obtaining the classification probability of each modality; The dual convolutional neural network algorithm is used, with the digital image of the face and the three-dimensional feature vector of the drilling parameters as input. The network of each mode is set with a convolution layer and a pooling layer, and a linear transformation is performed in the fully connected layer. The Softmax function is used to calculate the classification probability of the four surrounding rock levels of each mode. S32, establishing a weight adaptive adjustment mechanism for the face digital image modality and the drilling parameter modality to achieve automatic training of the multi-modal model; Through the cross entropy loss function, the weight adaptive adjustment mechanism of the tunnel face digital image mode and the drilling parameter mode is established, that is, the mapping relationship between the classification probability of different modes and the cross entropy function: Based on the weight of each mode, the weighted classification probabilities of the four surrounding rock levels are calculated respectively. The weighted classification probabilities of the same surrounding rock level under two modes are added together to obtain the classification probabilities of the four surrounding rock levels of the tunnel surrounding rock multimodal intelligent classification model. The total loss rate of the tunnel surrounding rock multimodal intelligent classification model is calculated using the cross entropy loss function, and the loss rate is allocated according to the weight of each mode, and back propagation is performed to update the model parameters.

6. The multi-modal intelligent fine classification method for tunnel surrounding rock according to claim 1 is characterized by: In step S4, the rock mass in front of the tunnel face is divided into a plurality of three-dimensional space units according to the tunnel profile and the blasthole distribution characteristics, which specifically includes the following steps: S41. In the two-dimensional transverse direction of the tunnel face, along the width and height of the tunnel, the tunnel face is divided into 18 transverse blocks according to the tunnel contour and blasthole distribution; S42. The face area is further segmented along the tunnel excavation direction to eventually form a number of three-dimensional space units.

7. The multi-modal intelligent fine classification method for tunnel surrounding rock according to claim 6 is characterized by: The step S41 specifically includes: taking the center line of the tunnel and the bottom of the pit as the reference, first drawing the horizontal line and the vertical line, and then offsetting them by 2 to 4 meters in the up and down and left and right directions respectively, and setting the maximum size of a single block to 2 to 4 meters, until the outline boundary of the tunnel is covered; finally, dividing the entire tunnel outline into 18 blocks, numbered from K-1 to K-18, with an area of ​​3m 2 Up to 8m 2 between.

8. The tunnel surrounding rock multi-modal intelligent fine classification method according to claim 6 is characterized by: The step S42 specifically includes: setting the spacing of the longitudinal segments to 0.4 m, dividing the tunnel face in the transverse width and height directions, combining the longitudinal partitions, and finally extending these two-dimensional partitions along the depth in front of the tunnel face to form a plurality of three-dimensional space units.

9. The tunnel surrounding rock multi-modal intelligent fine classification method according to claim 1 is characterized by: In step S5, the surrounding rock grade of the tunnel face is refined and intelligently identified based on the surrounding rock intelligent classification model, specifically including: constructing a three-dimensional feature vector of the drilling parameters of each unit body, splitting the digital image of the tunnel face according to the same horizontal block method, inputting the three-dimensional feature vector of the drilling parameters of each unit body and the corresponding horizontally divided digital image of the tunnel face into the tunnel surrounding rock multimodal intelligent classification model, obtaining the surrounding rock grade of any unit body, and realizing refined intelligent identification of the surrounding rock grade of the tunnel face.

10. A system according to the tunnel surrounding rock multi-modal intelligent fine classification method according to any one of claims 1 to 9, characterized in that: Includes the following modules: Sample library building module (110): building a sample library, the sample library including drilling parameters, digital images and corresponding surrounding rock grades of the tunnel face; Feature construction module (120): constructing a refined classification feature system of drilling parameters; Surrounding rock intelligent classification model construction module (130): constructing a surrounding rock intelligent classification model based on multi-modal data fusion; The rock mass division module (140) in front of the tunnel face is used to divide the rock mass in front of the tunnel face into a plurality of three-dimensional space units according to the tunnel profile and the blasthole distribution characteristics; Intelligent and refined identification module for the surrounding rock grade of the tunnel face (150): Based on the surrounding rock intelligent classification model, the surrounding rock grade of the tunnel face is intelligently and refinedly identified.

Images