A layered surrounding rock drill-and-blast method tunnel intelligent optimization charging control method and system and a storage medium thereof

Abstract

The present application relates to the technical field of underground engineering, in particular to a layered surrounding rock drill-and-blast method tunnel intelligent optimization charging control method and system and a storage medium thereof, after obtaining the working face contour line and the bedding plane through image recognition, the blast hole layout is imported, and the distance between each blast hole and the bedding plane and the included angle between the bedding plane and the working face contour line are calculated, the blast holes are classified according to the calculation results, the blast holes are divided into one type of blast holes without charging parameter optimization and two types of blast holes needing charging parameter optimization, and the charging parameters of the two types of blast holes are judged and the adjustment range of the charging parameters is determined. The one type of blast holes is charged with conventional charging parameters, and the two types of blast holes are charged according to their respective optimized charging parameters. The method realizes the improvement of the optimization efficiency and accuracy of the tunnel blasting in the layered surrounding rock, improves the tunnel blasting excavation effect, and achieves the purpose of reducing and saving the tunnel construction cost.

Description

Technical Field

[0001] This invention relates to the field of underground engineering technology, and in particular to an intelligent optimized charge control method, system and storage medium for layered surrounding rock drilling and blasting tunnels. Background Technology

[0002] In layered rock formations, the stress and gas generated by blasting propagate along the fissures of the bedding planes, making over-excavation and under-excavation at the tunnel face highly likely. Over-excavated areas require shotcrete backfilling, while under-excavated areas typically require manual secondary blasting, significantly increasing construction costs and impacting construction progress and worker safety. Currently, existing tunnel blasting design methods do not consider the influence of rock bedding planes on the initiation effect. Therefore, whether using manual or mechanized drilling and blasting, in layered rock formations, reliance on manual experience is still crucial. Optimizing and adjusting charge parameters through repeated on-site test blasts to achieve better blasting results suffers from low efficiency, low adjustment accuracy, and the need for repeated test blasts to adjust parameters should the surrounding rock change. Summary of the Invention

[0003] The purpose of this invention is to address the problems of low construction efficiency and low accuracy in the traditional construction method of optimizing and adjusting charge parameters through repeated on-site test blasts, which is a problem in existing technologies. This invention provides an intelligent optimized charge control method and system for layered surrounding rock drilling and blasting tunnels.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] A method for intelligent optimized charge control in layered surrounding rock drilling and blasting tunnels is described below:

[0006] S1. Obtain the tunnel face contour and bedding plane based on image recognition;

[0007] S2. After obtaining the tunnel face outline and bedding plane, import the borehole layout diagram, determine the position of each borehole, and calculate the distance between each borehole and the bedding plane, as well as the angle between the bedding plane and the tunnel face outline.

[0008] S3. Based on the distance parameters between the borehole and the bedding plane and the angle parameters between the bedding plane and the tunnel face contour line, each borehole is classified. If it is determined that the borehole does not need to be optimized for the charge parameters, it is named as a Class I borehole. If it is determined that the borehole needs to be optimized for the charge parameters, it is named as a Class II borehole and labeled accordingly.

[0009] S4. After judging and classifying each blast hole, the adjustment range of the charge parameters is determined based on the blast hole position of the second type of blast hole, the distance between the second type of blast hole and the bedding plane, and the angle between the bedding plane and the tunnel face outline.

[0010] S5. After judging the charging parameters of the Class II blast holes and determining the adjustment range of the charging parameters, the Class II blast holes are renumbered, and conventional charging parameters are imported. The Class I blast holes are charged using conventional charging parameters, and the marked Class II blast holes are charged according to their respective optimized charging parameters. After blasting, the outline of the tunnel face is obtained through image recognition, and the blasting excavation effect is evaluated. The results are fed back to the processor to correct the charging parameters.

[0011] This invention relates to an intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels. Compared to traditional methods that rely on manual experience to judge and adjust charge parameters, this method first obtains the tunnel face outline and bedding planes through image recognition of the tunnel face. Then, it performs conventional borehole layout based on the site environment, calculates the distance between each borehole and the nearby bedding planes, and calculates the angle between the bedding planes and the tunnel face outline. Based on the calculated values, the boreholes are classified into two categories: Category I boreholes, which are charged with conventional parameters, and Category II boreholes, which require optimized charge parameters. Finally, the method further optimizes the charge parameters by considering the position parameters of Category II boreholes, their distance from the bedding planes, and the tunnel face outline. The adjustment range of the charging parameters for each type II blast hole is determined by the angle parameter between the blast hole and the bedding plane. Then, the blast holes are charged according to the confirmed charging parameters. Through image recognition, calculation of the distance between the blast hole and the bedding plane, and calculation of the angle between the bedding plane and the tunnel face outline, the blast holes are divided into those that need charging optimization (type II blast holes) and those that do not need charging optimization (type I blast holes). The accurate charging range of each type II blast hole is obtained by calculating the adjustment range of the charging parameters. Then, the charging is carried out. This method improves the efficiency and accuracy of tunnel blasting in layered surrounding rock, enhances the tunnel blasting excavation effect, saves tunnel construction costs, speeds up construction progress, and improves operational safety.

[0012] As a preferred embodiment of the present invention, the method further includes translating the calculated and optimized charging parameters into digital signals, transmitting the charging parameters to the control module through a data communication module, wherein the control module is connected to a charging trolley, and the charging trolley charges the Class II blast holes and the Class I blast holes through the control module. This configuration eliminates the need for manual charging, ensuring construction efficiency.

[0013] As a preferred embodiment of the present invention, after both the first type of borehole and the second type of borehole are loaded with explosives, an explosion assessment is performed, and the explosion effect assessment module determines whether the explosion meets the requirements. If it does, the explosive loading optimization is completed; otherwise, it returns to S3 to readjust the explosive loading parameters. This setting improves the accuracy of the explosive loading parameter optimization.

[0014] As a preferred embodiment of the present invention, the process of obtaining the tunnel face contour line and bedding plane based on image recognition in S1 is as follows: acquiring an image of the tunnel face through a camera device, and performing repair and bilateral filtering denoising processing on the tunnel face image to obtain the bedding plane. The calculation principle of the bilateral filtering denoising processing is as follows:

[0015]

[0016]

[0017]

[0018] Where: x, y - the coordinates of the currently convolved pixel;

[0019] k,l - the coordinates of the neighboring pixels;

[0020] f(k,l) - Pixel values ​​of the original tunnel face image;

[0021] d(x,y,k,l) ​​- Spatial distance function of the facet image;

[0022] r(x,y,k,l) ​​- Image pixel value range kernel;

[0023] The product of ω(x,y,k,l)-d(x,y,k,l) ​​and r(x,y,k,l);

[0024] σ r -Gaussian standard deviation of the spatial distance function;

[0025] σ d - Spatial grayscale similarity within the domain;

[0026] This setting allows for better extraction of the structural surface boundaries of the facet image.

[0027] As a preferred embodiment of the present invention, the calculation process of the tunnel face contour line is as follows: by building a pixel difference network edge detection model architecture, then creating edge mappings, and then performing loss calculation and model result analysis on each edge mapping through a robust loss function. This setting can better capture gradient information and is beneficial for edge detection of the tunnel face image.

[0028] As a preferred embodiment of the present invention, the construction process of the pixel difference network edge detection model architecture is as follows: The model structure mainly includes three aspects: backbone structure, side structure, and loss function. The backbone network of the entire backbone structure has four stages, each with four residual blocks. For the side structure, a dilated convolutional module (CDCM) is constructed to enrich multi-scale edge information, followed by a compact spatial filter module (CSAM) to eliminate background noise. Then, a 1×1 convolutional layer is used to further reduce the feature volume to a single-channel mapping, which is then interpolated to the original size. Finally, the sigmoid function is used to create edge mappings. Subsequently, for each generated edge mapping (including the final edge mapping), a robust loss function is applied to the value... For the i-th pixel in the j-th edge mapping, the loss is calculated as follows:

[0029]

[0030]

[0031] In the formula: y i - The probability of a true edge;

[0032] η - the defined threshold;

[0033] Percentage of beta-negative pixel samples;

[0034] The final total loss of the L-model.

[0035] As a preferred embodiment of the present invention, after determining the position of each blast hole in S2, the distance between each blast hole and the nearby bedding plane is calculated using the distance formula between a point and a line. After calculating the distance between each blast hole and the nearby bedding plane, the angle between the tunnel face outline and the bedding plane is calculated using the angle formula between lines.

[0036] As a preferred embodiment of the present invention, the distance between the borehole and the bedding plane of the attachment is calculated as follows: Assuming the equation of the straight line is Ax + By + C = 0, and the coordinates of the point are (x0, y0), the distance d from the point to the straight line is calculated using the following formula, the specific formula is as follows:

[0037]

[0038] As a preferred embodiment of the present invention, the calculation steps for the angle between the bedding plane and the tunnel outline are as follows: Since the angle between the bedding plane and the tunnel outline is an acute angle, it is assumed that the equations of the straight lines are l1: A1x + B1y + C1 = 0; l2: A2x + B2y + C2 = 0, and the formula for the angle is as follows:

[0039]

[0040] As a preferred embodiment of the present invention, the process for determining the charge parameters in S3 is as follows:

[0041] S71. Based on the tunnel face outline and bedding planes, the conditions for optimizing the explosive charge parameters are derived.

[0042] The following are the details:

[0043] S711. First, when the blast hole is located on the tunnel face outline, the next condition judgment is made on whether the charge parameters need to be optimized; otherwise, no optimization is performed.

[0044] Furthermore,

[0045] When the bedding thickness is less than 70cm, the borehole charging parameters at that location need to be optimized; otherwise, no optimization is required.

[0046] or,

[0047] When the distance between the borehole and the nearest bedding plane is less than 50mm, the borehole needs to have its charge parameters optimized.

[0048] S72. Mark the blast holes that need to be optimized as Class II blast holes, and calculate the range of the angle between the bedding plane and the tunnel face outline, as well as the angle value of the bedding plane that has the most unfavorable effect on the light blast.

[0049] S73. Based on the range of the angle between the bedding plane and the tunnel face outline, and the angle value at which the bedding plane has the most unfavorable impact on light blasting, optimization measures for different blast hole locations are formulated.

[0050] As a preferred embodiment of the present invention, the specific steps for calculating the range of the angle between the bedding plane and the tunnel face outline in S72 are as follows: First, the stress of the bedding plane is calculated, and the calculation formula is:

[0051]

[0052]

[0053] Where: σ θ - Normal stress on the bedding plane of the rock mass;

[0054] τ θ - Shear stress on rock bedding planes;

[0055] σ x - Normal stress of the surrounding rock unit on the x-axis;

[0056] σ y - Normal stress of the surrounding rock unit on the y-axis;

[0057] Subsequently, based on the Mohr-Coulomb strength theory and its failure criterion, combined with the domain of θ, calculations were performed to obtain the following formula:

[0058]

[0059] In the formula: Refers to θ min ;

[0060] Refers to θ max ;

[0061] That is, θ min <θ <θ max ;

[0062] The Mohr-Coulomb strength theory and its failure criterion formula are as follows:

[0063]

[0064] -σ y ≥[σ].

[0065] As a preferred embodiment of the present invention, the calculation process for the angle most unfavorable to the light burst effect of the bedding plane in S72 is as follows: by calculating the stress of the bedding plane, the calculation formula is as follows:

[0066]

[0067]

[0068] Where: σ θ - Normal stress on the bedding plane of the rock mass;

[0069] τ θ - Shear stress on rock bedding planes;

[0070] σ x - Normal stress of the surrounding rock unit on the x-axis;

[0071] σ y - Normal stress of the surrounding rock unit on the y-axis;

[0072] Then, based on the Mohr-Coulomb strength theory and its failure criterion, the formula is obtained:

[0073] -σ y ≥[σ];

[0074]

[0075] Since the maximum circumferential stress after the explosive charge in the borehole is approximately half the maximum radial stress, at any point on the line connecting the centers of adjacent peripheral holes, the following holds true:

[0076]

[0077] The following equation is then obtained:

[0078]

[0079] Right now

[0080] As can be seen from the above formula, the larger the value on the right, the easier it is to achieve the ideal light burst effect; conversely, the smaller the value on the right, the more difficult it is to achieve the ideal light burst effect, that is, the greater the adverse effect of the bedding plane.

[0081] Then we can set:

[0082] In the formula: f(θ) - [σ];

[0083]

[0084] From the above equation, we can see that when g(θ) reaches its maximum value, f(θ) reaches its minimum value. Then, by transforming g(θ), we obtain:

[0085]

[0086] If the above formula is taken to its maximum value, then the angle θ1 that is most unfavorable to the light burst effect of the bedding plane is obtained:

[0087]

[0088] Right now:

[0089] In the formula: θ1 - the angle at which the bedding plane has the most unfavorable effect on the light burst.

[0090] As a preferred embodiment of the present invention, the charging parameters of each type II borehole are optimized based on the angle value of the bedding plane that has the most unfavorable effect on the light blast and the range of the angle between the bedding plane and the tunnel face outline.

[0091] As a preferred embodiment of the present invention, in S3, after importing conventional charging parameters, conventional charging parameters are used for the first type of boreholes, while the calculated and optimized values ​​are used for the charging of the marked second type of boreholes. After charging, the second type of boreholes are re-labeled and charging parameters are generated.

[0092] As a preferred embodiment of the present invention, the charging trolley identifies the markings of the second type of blast holes through a control module, and then charges the blast holes according to the charging parameters of the second type of blast holes with different markings after identifying the markings.

[0093] As a preferred embodiment of the present invention, the detailed process of adjusting the charge parameters is as follows: After the charge blasting, an image recognition module is used to obtain the two-dimensional contour line of the tunnel face after the blasting, and compare it with the imported design contour line. The area within the design contour line is marked as the under-excavated part, and the area outside the design contour line is marked as the over-excavated part. The ratio of the sum of the areas of the over-excavated and under-excavated parts to the cross-sectional area of ​​the tunnel is calculated to evaluate the blasting effect. The evaluation result is fed back to the charge parameter optimization module for real-time parameter correction.

[0094] A smart optimized charge control system for layered surrounding rock drill-blast tunnels is characterized by comprising an image recognition module, which is communicatively connected to an optimization condition judgment module, which is communicatively connected to a charge parameter optimization module, the charge parameter optimization module is communicatively connected to a data communication module, the data communication module is communicatively connected to a control module, and the control module is connected to an actuator, as detailed below:

[0095] Image recognition module: used to obtain the tunnel face contour and bedding plane based on image recognition and pixel difference network edge detection model of the tunnel face image;

[0096] Optimization condition judgment module: used to determine whether each borehole needs to have its charge parameters optimized;

[0097] Explosive loading parameter optimization module: used to determine the optimization range of explosive loading parameters;

[0098] Data communication module: used to import loading parameters;

[0099] Control module: used for loading the drug;

[0100] Actuating mechanism: used for loading explosives;

[0101] Blasting effect evaluation module: Used to evaluate the blasting excavation effect. The blasting effect evaluation module communicates with the tunnel face, image recognition module, and charge parameter optimization module.

[0102] This invention relates to an intelligent optimized charging control system for layered rock drilling and blasting tunnels. This system utilizes an image recognition module to accurately identify the tunnel face contour and bedding planes; an optimization condition judgment module to determine the need for charging parameter optimization in real time; a data communication module to import parameters in real time; a control module and actuators to ensure precise control of the charging process; and a blasting effect evaluation module to monitor the blasting effect. Such a system can improve the efficiency, safety, and accuracy of tunnel blasting operations, reduce construction costs, and improve project quality.

[0103] A computer storage medium storing a computer program, which, when executed by a processor, implements the steps of the intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels as described above.

[0104] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0105] 1. This invention relates to an intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels. Compared to the traditional method of judging and adjusting charge parameters based on experience, this scheme first obtains the tunnel face outline and bedding plane through image recognition of the tunnel face. Then, it performs conventional borehole layout according to the site environment, calculates the distance between each borehole and the nearby bedding plane, and calculates the angle between the bedding plane and the tunnel face outline. Based on the calculated values, the boreholes are classified into Class I boreholes that are charged with conventional parameters and Class II boreholes that require optimized charge parameters. Subsequently, the location parameters of Class II boreholes, the distance parameters of Class II boreholes from the bedding plane, and the tunnel face outline are used to further optimize the charge control method. The adjustment range of the charging parameters for each type II blast hole is determined by the angle parameter between the blast hole and the bedding plane. Then, the blast holes are charged according to the confirmed charging parameters. Through image recognition, calculation of the distance between the blast hole and the bedding plane, and calculation of the angle between the bedding plane and the tunnel face outline, the blast holes are divided into those that need charging optimization (type II blast holes) and those that do not need charging optimization (type I blast holes). The accurate charging range of each type II blast hole is obtained by calculating the adjustment range of the charging parameters. Then, the charging is carried out. This method improves the efficiency and accuracy of tunnel blasting in layered surrounding rock, enhances the tunnel blasting excavation effect, saves tunnel construction costs, speeds up construction progress, and improves operational safety. Attached Figure Description

[0106] Figure 1 This is a flowchart of the intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to the present invention;

[0107] Figure 2 This is a schematic diagram of the intelligent optimized charge control method for tunnels using the layered surrounding rock drilling and blasting method of the present invention.

[0108] Figure 3 This is a tunnel face image of the intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to the present invention;

[0109] Figure 4 This is an image of the tunnel face identified by the pixel difference network edge detection model (PiDiNet) using the intelligent optimized charge control method for drilling and blasting tunnels in layered surrounding rock, as described in this invention.

[0110] Figure 5This is a schematic diagram of the bedding plane marking at the tunnel face in the intelligent optimized charging control method for drilling and blasting tunnels in the layered surrounding rock method of the present invention;

[0111] Figure 6 This is a schematic diagram of the parameters calculated by the optimization condition judgment module of the intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels of the present invention;

[0112] Figure 7 This is a schematic diagram of the blasting effect evaluation and optimization feedback process of the intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to the present invention. Detailed Implementation

[0113] The present invention will now be described in detail with reference to the accompanying drawings.

[0114] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0115] Example 1

[0116] like Figure 1-2 The method for intelligent optimized charge control in layered surrounding rock drilling and blasting tunnels is shown below.

[0117] S1. Acquire the tunnel face image video, and repair and remove noise from the tunnel face image to obtain the tunnel face outline and bedding plane;

[0118] S2. Then import the conventional layout of the boreholes. First, determine the location of the boreholes and calculate the distance between the borehole and the nearby bedding plane, as well as the angle between the bedding plane and the tunnel outline. Based on the above data, classify each type of borehole. If it is determined that the borehole does not need to be optimized for the charging parameters, it is named a Class I borehole. If it is determined that the borehole needs to be optimized for the charging parameters, it is named a Class II borehole and labeled.

[0119] S3. After judging and classifying each blast hole, the adjustment range of the charge parameters is determined based on the blast hole position of the second type of blast hole, the distance between the second type of blast hole and the bedding plane, and the angle between the bedding plane and the tunnel face outline.

[0120] S4. After judging the charging parameters of the second type of blast holes and determining the adjustment range of the charging parameters, import the conventional charging parameters. Use the conventional charging parameters to charge the first type of blast holes, and charge the marked second type of blast holes according to their respective optimized charging parameters.

[0121] S5. The optimized charging parameters are translated into recognizable digital signals and transmitted to the control module through the data communication module. The control module then controls the charging trolley to charge each borehole.

[0122] The image restoration steps in S1 described above are as follows:

[0123] First, OpenCV's binarization image inpainting technique is used to repair scratches on the acquired face images. By locking the scratches in the face image, the scratches are identified because their color is whiter than the rest of the rock on the face. Therefore, a threshold is set for the binary image to lock the scratches in the image. Then, the first derivative of the boundary points of the scratches to be repaired is calculated, and the first derivative of the boundary points of the repair points is calculated based on the pixels at the selected repair point boundaries and their pixel gradient values ​​at those points. Finally, pixel-by-pixel repair is performed on the scratch areas of the face images through pixel updates, gradually shrinking the scratch boundary areas to be repaired and gradually repairing them until the overall scratch area is repaired.

[0124] The noise removal process for the image in S1 is as follows: The image is denoised using bilateral filtering, and the calculation is as follows:

[0125]

[0126]

[0127]

[0128] Where: x, y - the coordinates of the currently convolved pixel;

[0129] k,l - the coordinates of the neighboring pixels;

[0130] f(k,l) - Pixel values ​​of the original tunnel face image;

[0131] d(x,y,k,l) ​​- Spatial distance function of the facet image;

[0132] r(x,y,k,l) ​​- Image pixel value range kernel;

[0133] The product of ω(x,y,k,l)-d(x,y,k,l) ​​and r(x,y,k,l);

[0134] σ r -Gaussian standard deviation of the spatial distance function;

[0135] σ d - Spatial grayscale similarity within the domain;

[0136] like Figure 3-5 As shown.

[0137] As mentioned above, after denoising and repairing the image, the joint lines and tunnel contours of the image are identified using a pixel difference network recognition model. The specific steps are as follows:

[0138] The model structure is established, comprising a backbone, sidewalls, and a loss function. The backbone network has four stages, each with four residual blocks. The sidewalls are constructed by building a dilated convolutional module (CDCM) to enrich multi-scale edge information, followed by a compact spatial filter module (CSAM) to eliminate background noise. A 1×1 convolutional layer further reduces the feature volume to a single-channel mapping, which is then interpolated to the original size. Finally, a sigmoid function is used to create edge maps. After edge map creation, a robust loss function is used to calculate the loss function for each generated edge map (including the final edge map). The loss value is calculated as follows:

[0139]

[0140]

[0141] In the formula: - The i-th pixel value in the j-th edge map;

[0142] y i - The probability of a true edge;

[0143] η - the defined threshold;

[0144] Percentage of beta-negative pixel samples;

[0145] L-model final total loss;

[0146] Furthermore, the results of the pixel difference network structure surface recognition model are analyzed, and the analysis process is as follows:

[0147] The deep learning pixel difference network edge detection model (PiDiNet) was selected, with 500 epochs used in its training. The values ​​of the model hyperparameters and Adam optimizer hyperparameters, such as learning rate, decay rate, batch size, beta_1, and beta_2, are shown in Table 1.

[0148] Table 1. Parameter values ​​for the structural surface recognition model

[0149]

[0150] like Figure 6 As shown.

[0151] As mentioned above, after importing the borehole layout diagram, the distance between each borehole and the bedding planes near the borehole, as well as the angle between the bedding planes and the tunnel outline, are calculated as follows:

[0152] Distance between each borehole and the bedding planes near that borehole: The distance between a borehole and a nearby bedding plane is calculated using the formula for the distance between a point and a line. Assuming the equation of the line is Ax + By + C = 0, and the coordinates of the point are (x0, y0), the distance d from the point to the line is calculated using the following formula:

[0153] Angle between bedding planes and tunnel outline: The angle between the bedding planes and tunnel outline is calculated using the formula for angles between straight lines. The angle is the acute angle between the tangent to the tunnel outline and the bedding plane. Assuming the equations of the lines are l1: A1x + B1y + C1 = 0; l2: A2x + B2y + C2 = 0, the angle α between the lines is calculated using the following formula:

[0154]

[0155] The process for determining the charge parameters in S3, as described above, is as follows:

[0156] S21. Based on the tunnel face outline and bedding planes, the conditions for optimizing the explosive charge parameters are as follows:

[0157] S211. First, when the blast hole is located on the tunnel face outline, the next condition judgment is made on whether the charge parameters need to be optimized; otherwise, no optimization is performed.

[0158] Furthermore,

[0159] When the bedding thickness is less than 70cm, the borehole charging parameters at that location need to be optimized; otherwise, no optimization is required.

[0160] or,

[0161] When the distance between the borehole and the nearest bedding plane is less than 50mm, the borehole needs to have its charge parameters optimized.

[0162] S22. Mark the second type of blast holes that need to be optimized, and calculate the range of the angle between the bedding plane and the tunnel face outline, as well as the angle value of the bedding plane that has the most unfavorable effect on the light blast.

[0163] S23. Based on the range of the angle between the bedding plane and the tunnel face outline, and the angle value of the bedding plane that has the most unfavorable effect on the light blasting, optimization measures for different blast hole positions are formulated.

[0164] Furthermore, the specific steps for calculating the range of values ​​for the angle between the bedding plane and the tunnel face outline in S22 are as follows: First, calculate the stress on the bedding plane using the following formula:

[0165]

[0166] Where: σ θ - Normal stress on the bedding plane of the rock mass;

[0167] τ θ - Shear stress on rock bedding planes;

[0168] σ x - Normal stress of the surrounding rock unit on the x-axis;

[0169] σ y - Normal stress of the surrounding rock unit on the y-axis;

[0170] Subsequently, based on the Mohr-Coulomb strength theory and its failure criterion, combined with the domain of θ, calculations were performed to obtain the following formula:

[0171]

[0172] In the formula: Refers to θ min ;

[0173] Refers to θ max ;

[0174] That is, θ min <θ <θ max ;

[0175] The Mohr-Coulomb strength theory and its failure criterion formula are as follows:

[0176]

[0177] -σ y ≥[σ];

[0178] Furthermore, the calculation process for the angle most unfavorable to the light burst effect of the bedding plane in S22 is as follows: by calculating the stress on the bedding plane, the calculation formula is as follows:

[0179]

[0180]

[0181] Where: σ θ - Normal stress on the bedding plane of the rock mass;

[0182] τ θ - Shear stress on rock bedding planes;

[0183] σ x - Normal stress of the surrounding rock unit on the x-axis;

[0184] σ y - Normal stress of the surrounding rock unit on the y-axis;

[0185] Then, based on the Mohr-Coulomb strength theory and its failure criterion, the formula is obtained:

[0186] -σ y ≥[σ];

[0187]

[0188] Since the maximum circumferential stress after the explosive charge in the borehole is approximately half the maximum radial stress, at any point on the line connecting the centers of adjacent peripheral holes, the following holds true:

[0189]

[0190] The following equation is then obtained:

[0191]

[0192] Right now

[0193] As can be seen from the above formula, the larger the value on the right, the easier it is to achieve the ideal light burst effect; conversely, the smaller the value on the right, the more difficult it is to achieve the ideal light burst effect, that is, the greater the adverse effect of the bedding plane.

[0194] Then we can set:

[0195] In the formula: f(θ) - [σ];

[0196]

[0197] From the above equation, we can see that when g(θ) reaches its maximum value, f(θ) reaches its minimum value. Then, by transforming g(θ), we obtain:

[0198]

[0199] If the above formula is taken to its maximum value, then the angle θ1 that is most unfavorable to the light burst effect of the bedding plane is obtained:

[0200]

[0201] Right now:

[0202] In the formula: θ1 - the angle at which the bedding plane has the most unfavorable effect on the light burst;

[0203] The known range of values ​​for the angle between the bedding plane and the tunnel face profile is as follows:

[0204]

[0205] In the formula: Refers to θ min ;

[0206] Refers to θ max ;

[0207] That is, θ min <θ <θ max ;

[0208] In this embodiment, the in-plane friction angle of the layering plane is substituted. θ max =70°, θ min =20°;

[0209] The formula for the angle at which the bedding plane has the most unfavorable effect on light bursts is now known:

[0210] This embodiment substitutes the in-plane friction angle of the layering plane. It is found that θ1 = 60°. Based on geometric relationships, it is explained that when the angle θ1 between the bedding plane and the line connecting the borehole is 60° or 30°, the bedding plane has the most unfavorable effect on the blasting effect. Therefore, the optimization measures for charging at different borehole positions can be derived, as shown in Table 2:

[0211] Table 2 Optimization measures for explosive charges at different locations on the working face

[0212]

[0213] Based on the table above, the boreholes at different locations are classified and marked according to whether or not charge optimization is required. When the angle θ between the bedding plane and the tunnel outline is greater than 70° (i.e., θ is greater than θ), the boreholes are classified accordingly. max In this case, the charge parameters of the boreholes within this range are not optimized, and the linear charge density remains q1; when θ is less than 20° (i.e., θ is less than θ1), the charge parameters of the boreholes within this range are not optimized, and the linear charge density remains q1. min If the angles θ1 and θ2 are the most unfavorable for the light burst, then the linear charge density of the boreholes within this range should be reduced to q2 = q1 - 0.02; if the angles θ1 and θ2 are the most unfavorable for the light burst, then the linear charge density of the boreholes at these locations should be reduced to q3 = q1 - 0.04 and q4 = q1 - 0.04; if 20° < θ < 70°, then θ2 = q1 - 0.02. min <θ <θ max When (excluding θ1), the linear charge density of the boreholes within this range is reduced to q5 = (q2 + q3) / 2. When under-drilling occurs, the constants are kept unchanged according to the table above, such as q2 = q1 + 0.02, q3 = q1 + 0.04, to increase the linear charge density of the boreholes within the under-drilling range;

[0214] In the table: q1-θ>θ max Density of the charged propellant at that time;

[0215] q2-θ<θ min Density of the charged propellant at that time;

[0216] The density of the linear charge when q3-θ1=30°;

[0217] Linear charge density when q4-θ1=60°;

[0218] q5-θ min <θ <θ max Density of the linear charge at that time.

[0219] As mentioned above, in S4, after importing the conventional charge parameters, the conventional charge parameters are used for the first type of boreholes, while the calculated and optimized values ​​are used for the marked second type of boreholes. After the charge is loaded, the second type of boreholes are re-labeled and charge parameters are generated.

[0220] Furthermore, the charging trolley identifies the markings of the second type of blast holes through the control module, and then charges the blast holes according to the charging parameters of the second type of blast holes with different markings after identifying the markings.

[0221] Further, the detailed process of adjusting the charge parameters is as follows: After the blast, an image recognition module is used to acquire the two-dimensional contour line of the tunnel face after the blast. This contour line is compared with the imported design contour line. Areas within the design contour line are marked as under-excavated areas, and areas outside the design contour line are marked as over-excavated areas. The ratio of the sum of the over-excavated and under-excavated areas to the tunnel cross-sectional area is calculated to evaluate the blasting effect. The evaluation results are then fed back to the charge parameter optimization module. For over-excavated areas, according to Table 2, the linear charge density of the blast holes within that area is reduced; for under-excavated areas, the linear charge density of the blast holes within that area is increased to achieve real-time parameter correction. Figure 2 and Figure 7 As shown.

[0222] Example 2:

[0223] A smart optimized charge control system for layered surrounding rock tunnels using the drill-and-blast method includes:

[0224] Image recognition module: used to obtain the tunnel face contour and bedding plane based on image recognition and pixel difference network edge detection model of the tunnel face image;

[0225] Optimization condition judgment module: used to determine whether each borehole needs to have its charge parameters optimized;

[0226] Explosive loading parameter optimization module: used to determine the optimization range of explosive loading parameters;

[0227] Data communication module: used to import loading parameters;

[0228] Control module: used for loading the drug;

[0229] Actuating mechanism: used for loading explosives;

[0230] Blasting effect evaluation module: used for evaluating the effect of blasting excavation.

[0231] Example 3:

[0232] A computer storage medium storing a computer program that, when executed by a processor, implements the steps of a smart optimized charge control method for layered surrounding rock drilling and blasting tunnels as described in Example 1.

[0233] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements 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 optimized charge control in layered surrounding rock drilling and blasting tunnels, characterized in that, The specific method is as follows: S1. Based on image recognition and pixel difference network edge detection model of the working face image, the contour line and layering surface of the working face are obtained; S2. After obtaining the tunnel face outline and bedding plane, import the borehole layout diagram, identify the position of each borehole, and calculate the distance between each borehole and the bedding plane, as well as the angle between the bedding plane and the tunnel face outline. S3. Based on the distance parameters between the borehole and the bedding plane and the angle parameters between the bedding plane and the tunnel face contour line, each borehole is classified. If it is determined that the borehole does not need to be optimized for the charge parameters, it is named as a Class I borehole. If it is determined that the borehole needs to be optimized for the charge parameters, it is named as a Class II borehole and labeled accordingly. S4. After judging and classifying each blast hole, the adjustment range of the charge parameters is determined based on the blast hole position of the second type of blast hole, the distance between the second type of blast hole and the bedding plane, and the angle between the bedding plane and the tunnel face outline. S5. After judging the charging parameters of the Class II blast holes and determining the adjustment range of the charging parameters, the Class II blast holes are renumbered, and conventional charging parameters are imported. The Class I blast holes are charged using conventional charging parameters, and the marked Class II blast holes are charged according to their respective optimized charging parameters. After blasting, the outline of the tunnel face is obtained through image recognition, and the blasting excavation effect is evaluated. The results are fed back to the processor to correct the charging parameters. The process for determining the charge parameters in S3 is as follows: S31. Based on the tunnel face outline and bedding planes, the conditions for optimizing the explosive charge parameters are as follows: S311. First, when the blast hole is located on the tunnel face outline, the next condition judgment is made on whether the charging parameters need to be optimized; otherwise, no optimization is performed. When the bedding thickness is less than 70cm, the charging parameters of the blast hole at that location need to be optimized; otherwise, no optimization is performed. Alternatively, when the distance between the blast hole and the nearest bedding surface is less than 50mm, the charging parameters of the blast hole need to be optimized. S32. Mark the type of blast holes that need to be optimized, and calculate the range of the angle between the bedding plane and the tunnel face outline, as well as the angle value of the bedding plane that has the most unfavorable effect on the light blast. S33. Based on the range of the angle between the bedding plane and the tunnel face outline, and the angle value at which the bedding plane has the most unfavorable impact on the light blasting, optimization measures for different blast hole locations are formulated. The range of values ​​for the angle between the S32 intermediate bedding plane and the tunnel face outline includes: First, calculate the stress on the bedding plane; After the calculations are completed, based on the Mohr-Coulomb strength theory and its failure criterion, combined with the domain of the angle between the bedding plane and the tunnel face profile, the following formula is obtained: In the formula: The minimum angle between the bedding plane and the tunnel face outline is... ; The maximum value of the angle between the bedding plane and the tunnel face outline is... ; Refers to the in-plane friction angle of the bedding plane; It refers to the angle between the bedding plane and the tunnel face outline.

2. The intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to claim 1, characterized in that, The method further includes translating the calculated and optimized charge parameters into digital signals, transmitting the charge parameters to the control module through a data communication module, wherein the control module is connected to a charge loading trolley, and the charge loading trolley loads the second-class blast holes and the first-class blast holes through the control module.

3. The intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to claim 1, characterized in that, The method further includes: after both the first type of blast hole and the second type of blast hole are loaded with explosives, an explosion assessment is performed, and the explosion effect assessment module determines whether the explosion meets the requirements. If it does, the explosive loading optimization is completed; otherwise, the process returns to S3 to readjust the explosive loading parameters.

4. The intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to claim 1, characterized in that, The process of obtaining the tunnel face contour and bedding plane based on image recognition in S1 is as follows: An image of the tunnel face is acquired through a camera device, and the image is repaired and subjected to bilateral filtering denoising to obtain the bedding plane. The calculation principle of the bilateral filtering denoising process is as follows: ; ; ; In the formula: It refers to the coordinates of the currently convolved pixel; Refers to the coordinates of a pixel within a domain; Refers to the pixel values ​​of the original tunnel face image; Refers to the spatial distance function of the palm face image; Refers to the kernel of the image pixel value range; Substitute and The product of; The Gaussian standard deviation of the spatial distance function; It refers to the spatial grayscale similarity within a specific domain.

5. The intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to claim 1, characterized in that, In S5, after importing the conventional charge parameters, the conventional charge parameters are used for Class I boreholes, while the calculated and optimized values ​​are used for the charge on Class II boreholes that are marked. After the charge is loaded, the Class II boreholes are re-labeled and charge parameters are generated.

6. The intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to claim 2, characterized in that, The charging trolley identifies the markings of the Class II boreholes through a control module, and then charges the boreholes according to the charging parameters for each marking.

7. The intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels according to claim 3, characterized in that, The detailed process of adjusting the charge parameters is as follows: After the charge blasting, the image recognition module is used to obtain the two-dimensional outline of the tunnel face after the blasting. This outline is compared with the imported design outline. Areas within the design outline are marked as under-excavated areas, and areas outside the design outline are marked as over-excavated areas. The ratio of the sum of the over-excavated and under-excavated areas to the tunnel cross-sectional area is calculated to evaluate the blasting effect. The evaluation results are then fed back to the charge parameter optimization module for real-time parameter correction.

8. A smart optimized charging control system for layered surrounding rock tunnels using the drill-and-blast method, characterized in that, The system is used to implement the intelligent optimized charge control method for layered surrounding rock drilling and blasting tunnels as described in any one of claims 1-7. The system includes an image recognition module, which is communicatively connected to an optimization condition judgment module. The optimization condition judgment module is communicatively connected to a charge parameter optimization module, which is communicatively connected to a data communication module. The data communication module is communicatively connected to a control module, and the control module is connected to an actuator, as detailed below: Image recognition module: used for image recognition and pixel difference network edge detection based on face images. The detection model identifies and obtains the tunnel face contour and bedding planes; Optimization condition judgment module: used to determine whether each borehole needs to have its charge parameters optimized; Explosive loading parameter optimization module: used to determine the optimization range of explosive loading parameters; Data communication module: used to import loading parameters; Control module: used for loading the drug; Actuating mechanism: used for loading explosives; Blasting effect evaluation module: Used to evaluate the blasting excavation effect. The blasting effect evaluation module communicates with the tunnel face, image recognition module, and charge parameter optimization module.

9. A computer storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the intelligent optimized charging control method for layered surrounding rock drilling and blasting tunnels as described in any one of claims 1-7.

Images