Tunnel blasting parameter determination method, device, equipment, medium and program product

By iteratively optimizing tunnel blasting parameters and utilizing predictive models and parameter adjustments, the problem of low accuracy in tunnel blasting parameters was solved, thereby improving the safety and efficiency of construction.

CN118981940APending Publication Date: 2024-11-19CHINA RAILWAY 20TH BUREAU GROUP CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410964928.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The design of tunnel blasting parameters mainly relies on engineering experience and empirical formulas, resulting in low accuracy and affecting the safety and efficiency of tunnel construction.

Method used

By acquiring the main structural parameters of the tunnel, the surrounding rock quality parameters, and the blasting parameters, the preset maximum linear over-excavation prediction model for tunnel blasting is used for iterative optimization. The blasting parameters are adjusted until the over-excavation prediction value is less than or equal to the preset threshold, and the final blasting parameters are determined.

Benefits of technology

It reduces the influence of subjective human judgment, improves the accuracy and objectivity of tunnel blasting parameters, and optimizes the construction process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118981940A_ABST
    Figure CN118981940A_ABST
Patent Text Reader

Abstract

The invention discloses a tunnel blasting parameter determination method and device, equipment, a medium and a program product, and relates to the technical field of tunnel blasting, the disclosed tunnel blasting parameter determination method comprises the steps that main structural plane parameters, surrounding rock quality parameters and blasting parameters of a target tunnel are obtained; inputting the main structural plane parameters, the surrounding rock quality parameters and the blasting parameters into a preset tunnel blasting maximum linear overexcavation prediction model to obtain an overexcavation prediction value; if the overexcavation prediction value is larger than a preset threshold value, the blasting parameters are adjusted, and the step of inputting the main structural plane parameters, the surrounding rock quality parameters and the blasting parameters into the preset tunnel blasting maximum linear overexcavation prediction model to obtain the overexcavation prediction value is executed again till the overexcavation prediction value is smaller than or equal to the preset threshold value; and determining the adjusted blasting parameters as target tunnel blasting parameters. The accuracy of the tunnel parameter determination result can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of tunnel blasting, and in particular to a method, device, equipment, medium and program product for determining tunnel blasting parameters. Background Art

[0002] During the tunnel drilling and blasting construction process, due to the complexity of the tunnel surrounding rock conditions and engineering environment, the design of tunnel blasting parameters is mainly based on engineering experience and relevant empirical formulas. However, the blasting parameters determined by this method have low accuracy and qualitativeness, which will affect the safety and efficiency of subsequent tunnel construction. Summary of the invention

[0003] The main purpose of this application is to provide a method, device, equipment, medium and program product for determining tunnel blasting parameters, aiming to solve the technical problem of low accuracy of tunnel blasting parameter determination results in related technologies.

[0004] To achieve the above objectives, the present application proposes a method for determining tunnel blasting parameters, comprising:

[0005] Obtain the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel;

[0006] Inputting the main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain an overbreak prediction value;

[0007] If the overbreak prediction value is greater than the preset threshold, the blasting parameters are adjusted, and the process returns to the step of inputting the main structural surface parameters, the surrounding rock quality parameters, and the blasting parameters into the preset tunnel blasting maximum linear overbreak prediction model to obtain the overbreak prediction value, until the overbreak prediction value is less than or equal to the preset threshold;

[0008] The adjusted blasting parameters are determined as the target tunnel blasting parameters.

[0009] In one embodiment, the main structural surface parameters include a main structural surface position category and a main structural surface inclination category;

[0010] The steps of obtaining the main structural surface parameters of the target tunnel include:

[0011] Obtaining main structural surface image data of the target tunnel;

[0012] Inputting the main structural surface image data into a preset main structural surface inclination classification recognition model to obtain the main structural surface inclination category;

[0013] Input the main structural surface image data into a preset main structural surface information extraction model to obtain the main structural surface height information of the target tunnel;

[0014] Based on the main structural surface height information and preset position classification standards, the main structural surface location category is determined.

[0015] In one embodiment, the main structural surface parameters, surrounding rock quality parameters and blasting parameters are input into a preset tunnel blasting maximum linear overbreak prediction model, and before the step of obtaining the overbreak prediction value, the step further includes:

[0016] Obtaining an initial overbreak prediction model;

[0017] The adaptive particle swarm algorithm CIPSO based on the curve increasing strategy is used to determine the optimal value of the hyperparameters of the initial over-mining prediction model; the hyperparameters include the number of nodes in the first hidden layer, the number of nodes in the second hidden layer, the learning rate, and the number of training iterations of the initial over-mining prediction model;

[0018] Based on the optimal value of the hyperparameter, the initial over-digging prediction model is updated to obtain the optimal over-digging prediction model;

[0019] The optimal over-excavation prediction model is determined as the preset tunnel blasting maximum linear over-excavation prediction model.

[0020] In one embodiment, the step of obtaining the initial overbreak prediction model includes:

[0021] Acquire a blasting construction data set and an original prediction model; the blasting construction data set includes multiple groups of blasting construction data, each of which includes surrounding rock quality parameters, main structural surface location category, main structural surface inclination category, blasting parameters, and maximum linear over-excavation data;

[0022] Perform preprocessing operations on all blasting construction data in the blasting construction data set to obtain a model training sample set; the preprocessing operations include data screening and data normalization;

[0023] The original prediction model is trained based on the model training sample set to obtain the initial over-mining prediction model.

[0024] In one embodiment, the original prediction model includes a two-layer restricted Boltzmann machine RBM neural network and a single-layer error back propagation BP neural network; wherein the number of hidden layer nodes in each layer of the RBM neural network is 20, the learning rate is 0.01, the preset number of training times is 500, and the number of reverse iterations is 3000.

[0025] In one embodiment, the blasting parameters include the charge of peripheral holes, the peripheral hole spacing, the peripheral auxiliary hole spacing, the charge of peripheral auxiliary holes, the thickness of the light explosion layer, the charge of peripheral holes at the structural surface, the charge of outer auxiliary holes at the structural surface, the number of blast holes, the total amount of explosives and the cycle footage; the surrounding rock quality parameters include the integrity coefficient and the saturated uniaxial compressive strength.

[0026] In addition, to achieve the above-mentioned purpose, the present application also proposes a tunnel blasting parameter determination device, the device comprising:

[0027] An acquisition module is used to obtain the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel;

[0028] A prediction module, used to input the main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain an overbreak prediction value;

[0029] An adjustment module, for adjusting blasting parameters if the overbreak prediction value is greater than a preset threshold, and returning to execute the step of inputting the main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain the overbreak prediction value, until the overbreak prediction value is less than or equal to the preset threshold;

[0030] The determination module is used to determine the adjusted blasting parameters as target tunnel blasting parameters.

[0031] In addition, to achieve the above objectives, the present application also proposes a tunnel blasting parameter determination device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the tunnel blasting parameter determination method as described above.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of determining the tunnel blasting parameters as mentioned above are implemented.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the method for determining tunnel blasting parameters as described above are implemented.

[0034] One or more technical solutions proposed in this application have at least the following technical effects:

[0035] The tunnel blasting parameter determination method provided in the present application can obtain the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel; input the main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear over-excavation prediction model to obtain an over-excavation prediction value; if the over-excavation prediction value is greater than a preset threshold, the blasting parameters can be adjusted, and the step of inputting the main structural surface parameters, surrounding rock quality parameters and blasting parameters into the preset tunnel blasting maximum linear over-excavation prediction model to obtain the over-excavation prediction value is returned to execute until the over-excavation prediction value is less than or equal to the preset threshold; at this time, the adjusted blasting parameters can be determined as the target tunnel blasting parameters.

[0036] This application can adjust the blasting parameters according to the output of the model, and then re-predict until the requirements are met. This process can systematically optimize the blasting parameters to achieve the target over-excavation. Compared with the method of calculating and determining tunnel blasting parameters based on engineering experience and empirical formulas in related technologies, it reduces the influence of human subjective judgment, and the tunnel blasting parameters determined in this way are more accurate and objective. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 A schematic diagram of a process flow provided for Embodiment 1 of the method for determining tunnel blasting parameters of the present application;

[0040] Figure 2 It is a schematic diagram of the maximum linear overbreak under a blasting scheme;

[0041] Figure 3 Schematic diagram of extracting main structural surface information using the SPM-YOLOv8-seg model;

[0042] Figure 4 It is a schematic diagram of DBN network structure;

[0043] Figure 5 A brief flow chart of the method for determining tunnel blasting parameters;

[0044] Figure 6 This is a schematic diagram of the module structure of a device for determining tunnel blasting parameters according to an embodiment of the present application;

[0045] Figure 7 Schematic diagram of the device structure of the hardware operating environment involved in the method for determining tunnel blasting parameters in the embodiment of the present application.

[0046] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0049] The main solution of the embodiment of the present application is: obtaining the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel; inputting the main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear over-excavation prediction model to obtain an over-excavation prediction value; if the over-excavation prediction value is greater than a preset threshold, adjusting the blasting parameters, and returning to execute the step of inputting the main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear over-excavation prediction model to obtain an over-excavation prediction value, until the over-excavation prediction value is less than or equal to the preset threshold; determining the adjusted blasting parameters as the target tunnel blasting parameters.

[0050] During the tunnel drilling and blasting construction process, due to the complexity of the tunnel surrounding rock conditions and engineering environment, the design of tunnel blasting parameters is mainly based on engineering experience and relevant empirical formulas. However, the blasting parameters determined by this method have low accuracy and qualitativeness, which will affect the safety and efficiency of subsequent tunnel construction.

[0051] This application provides a solution that can adjust the blasting parameters according to the output of the model and then re-predict until the requirements are met. This process can systematically optimize the blasting parameters to achieve the target over-excavation. Compared with the method of calculating and determining tunnel blasting parameters based on engineering experience and empirical formulas in related technologies, it reduces the influence of human subjective judgment, and the tunnel blasting parameters determined in this way are more accurate and objective.

[0052] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, etc., or an electronic device capable of realizing the above functions, etc. The following takes a tunnel blasting parameter determination device as an example to illustrate this embodiment and the following embodiments.

[0053] Based on this, the present application embodiment provides a method for determining tunnel blasting parameters, referring to Figure 1 , Figure 1 This is a flow chart of Embodiment 1 of the method for determining tunnel blasting parameters of the present application.

[0054] In this embodiment, the method for determining tunnel blasting parameters includes steps S100 to S400:

[0055] Step S100, obtaining the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel.

[0056] Step S200, inputting the main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain an overbreak prediction value.

[0057] Step S300: If the over-excavation prediction value is greater than the preset threshold, the blasting parameters are adjusted, and the process returns to step S200 until the over-excavation prediction value is less than or equal to the preset threshold.

[0058] Step S400: determining the adjusted blasting parameters as target tunnel blasting parameters.

[0059] Specifically, before the tunnel blasting construction, the construction team can collect and determine in advance the main structural surface parameters of the target tunnel to be constructed, the surrounding rock quality parameters, and the blasting parameters, which are detailed parameters that affect the tunnel over-excavation results. In the blasting excavation construction of the tunnel, the surrounding rock conditions are one of the most important factors affecting the smooth surface blasting effect. Generally, hard rock, medium hard rock, and rock with good rock integrity are conducive to smooth surface blasting. In the "Blasting Manual", the main rock mechanical properties that affect blasting are mainly divided into rock deformation properties and rock strength properties. In the entire blasting design, parameters such as hole spacing and charge are related to the strength of the rock. In tunnel engineering, the BQ classification method in the "Engineering Rock Classification Standard" is often used to classify rock mass. The basic quality index of rock mass is determined by the uniaxial saturated compressive strength Rc and the rock mass integrity coefficient Kv. Combined with the geological survey data of related projects, the parameters of uniaxial saturated compressive strength Rc and rock mass integrity coefficient Kv can be selected, as shown in Table 1, which is a table of surrounding rock quality parameters.

[0060] Table 1

[0061]

[0062] In the design of smooth blasting of tunnels, blastholes can be divided into three types according to their positions and functions: slot holes, auxiliary holes, and peripheral holes. The function of slot holes is to crush and throw part of the rock on the face to form a free surface, which provides favorable conditions for the blasting of subsequent blastholes. The function of auxiliary holes is to further expand the volume of slots and create new free surfaces for the blasting of peripheral holes. The function of peripheral holes is to form a smooth contour after blasting. Among all the blastholes, the peripheral holes are the key blastholes that determine the quality of tunnel formation, and the auxiliary holes closest to the peripheral holes are the key blastholes that provide free surfaces for the blasting of the peripheral holes. These auxiliary holes are called outer circle auxiliary holes. Therefore, the parameters related to the peripheral holes and the parameters related to the outer circle auxiliary holes are selected as blasting parameters. In a feasible implementation manner, blasting parameters may include but are not limited to peripheral eye charge, peripheral eye hole distance, peripheral auxiliary eye hole distance, peripheral auxiliary eye charge, light explosion layer thickness, peripheral eye charge at the structural surface, outer ring auxiliary eye charge at the structural surface, number of blast holes, total explosive amount and cycle footage, etc.; surrounding rock quality parameters may include but are not limited to integrity coefficient and saturated uniaxial compressive strength.

[0063] The main structural surface parameters can be used to describe the geometric features of the tunnel. In a feasible implementation, the main structural surface parameters include the main structural surface position category and the main structural surface inclination category. In this implementation, the step of obtaining the main structural surface parameters of the target tunnel can specifically include steps S110 to S140:

[0064] Step S110, obtaining the main structural surface image data of the target tunnel.

[0065] Step S120, inputting the main structural surface image data into a preset main structural surface inclination classification recognition model to obtain the main structural surface inclination category.

[0066] Step S130, inputting the main structural surface image data into a preset main structural surface information extraction model to obtain the main structural surface height information of the target tunnel.

[0067] Step S140, determining the main structural surface position category based on the main structural surface height information and a preset position classification standard.

[0068] Specifically, if Figure 2 As shown, Figure 2 is a schematic diagram of the maximum linear overbreak under a blasting scheme, Figure 2 It can be seen that the tunnel over-excavation is serious after blasting. The maximum linear over-excavation position of all sections appears at the junction of the main structural surface and the contour line, and as the angle with the contour line decreases, the maximum linear over-excavation decreases. According to the quality assessment standard for smooth blasting of railway tunnels; the maximum linear over-excavation allowed for the arch of medium-hard rock and soft rock tunnels is 25cm; at the same time, it is found that when the angle between the blastholes and the main structural surface is large and located at the top of the arch, the maximum linear over-excavation of the tunnel is the largest, such as: Figure 2 (b) and 2(e), the maximum linear over-excavation is 32.4cm and 29.4cm respectively, which are 29.6% and 17.6% higher than the standard value respectively; when the angle between the line between the blastholes and the main structural surface is small, the maximum linear over-excavation of the tunnel is relatively reduced, such as: Figure 2 (c) and 2(d), the maximum linear over-excavation is 25.5cm and 26.1cm, respectively, exceeding the standard value by 2% and 2.4%. Combined with the above analysis, the maximum linear over-excavation of the tunnel occurs at the intersection of the main structural surface and the contour line, and the value is related to the inclination angle and position of the structural surface. Therefore, when analyzing the influence of the main structural surface on the maximum linear over-excavation, only the influence of the inclination angle and position of the main structural surface can be considered.

[0069] In order to obtain more accurate maximum linear over-excavation prediction results, so as to adjust the blasting parameters accordingly. The main structural surface inclination category and the main structural surface position category corresponding to the target tunnel can be determined with the help of a preset main structural surface inclination classification recognition model and a preset main structural surface information extraction model. Before the model is applied, multiple groups of face images of the target tunnel under different conditions (such as different surrounding rock conditions, different lighting conditions, different shooting positions, etc.) can be collected by an image acquisition device, and further processed by image processing technology (image segmentation, image space enhancement, image pixel enhancement, etc.) to obtain the main structural surface image data required for the preset model input.

[0070] Among them, the preset main structural surface inclination classification and recognition model can be a Structural plane-YOLOv8 model (SP-YOLOv8 model). The SP-YOLOv8 model is based on the YOLOv8 model and integrates the feature extraction optimization based on asymmetric convolution blocks and the main structural surface filtering algorithm based on aspect ratio and distance constraints to build a tunnel main structural surface inclination classification and recognition model. In engineering geology, rock mass can be divided into 5 categories according to the structural surface inclination angle, namely, nearly horizontal rock layer (0°~5°), gently inclined rock layer (5°~30°), inclined rock layer (30°~70°), steep rock layer (70°~85°), and vertical rock layer (85°~90°). In view of this, the tunnel main structural surface can be divided into 5 categories according to the above classification, numbered 1, 2, 3, 4, and 5 respectively. The tunnel images of different inclination categories are classified and processed respectively, and used for the training of the SP-YOLOv8 model. After the training is completed, the main structural surface inclination classification and recognition model based on SP-YOLOv8 can be obtained. By inputting the main structural surface image data into the trained SP-YOLOv8 model, the corresponding main structural surface inclination angle recognition result (output number 1, 2, 3, 4 or 5) can be output.

[0071] The preset main structure surface information extraction model may be an SPM-YOLOv8-seg model, and the SPM-YOLOv8-seg model may be used to extract information of the main structure surface of the target tunnel, such as Figure 3 As shown, Figure 3This is a schematic diagram of the main structural surface information extraction using the SPM-YOLOv8-seg model; first, the main structural surface image data (i.e., the tunnel face image data) can be input into the model, the coordinates of the right endpoint of the image are the origin (0,0), the image is partitioned by the SPM-YOLOv8-seg model, the main structural surface is expanded to form a mask area (mask area), the coordinates of the lower right corner of the mask area box are (x1, y1), the main structural surface area is extracted and binarization is used for image processing, and then the skeleton extraction method adopts the Zhang-Suen algorithm, the core of which is to indent the area to be extracted from the edge to the center for multiple iterations to form a trace, and the coordinates of the right endpoint of the trace are (x2, y2); then the pixel height y=y1+y2 of the right endpoint of the main structural surface can be obtained by the image pixel height, and then the actual height Y of the right endpoint of the main structural surface can be obtained according to the ratio of the actual tunnel face height, Among them, h is the pixel height of the face, Y is the actual height of the right endpoint of the main structural face, and H is the actual height of the face. The location category of the main structural face can be determined using the preset preset position classification standard and the actual height Y of the right endpoint (i.e., the main structural face height information). For example, the entire upper step face can be divided into three areas according to height. The area within 100 cm from the arch is determined as the arch area, the area within 200 cm from the bottom of the step can be determined as the middle and lower part of the step, and the rest is determined as the spandrel area. The main structural face height information obtained can be classified according to the above standards to determine the main structural face location category. Among them, each different category can be marked with different numbers to facilitate the input of the preset tunnel blasting maximum linear over-excavation prediction model. For example, the arch area can be recorded as 1, the middle and lower part of the step can be recorded as 2, and the spandrel area can be recorded as 3.

[0072] In a feasible implementation manner, before executing step S200 of the method for determining tunnel blasting parameters, steps A100 to A400 may be further included, which may be used to determine a better preset tunnel blasting maximum linear overbreak prediction model:

[0073] Step A100, obtaining an initial over-excavation prediction model.

[0074] Step A200, based on the curve incremental strategy adaptive particle swarm algorithm CIPSO, determines the optimal value of the hyperparameter of the initial over-mining prediction model.

[0075] Among them, the hyperparameters include the number of nodes in the first hidden layer, the number of nodes in the second hidden layer, the learning rate, and the number of training iterations of the initial hyper-mining prediction model.

[0076] Step A300, based on the optimal value of the hyperparameter, update the initial over-excavation prediction model to obtain the optimal over-excavation prediction model.

[0077] Step A400: determining the optimal over-excavation prediction model as a preset tunnel blasting maximum linear over-excavation prediction model.

[0078] Specifically, an initial over-excavation prediction model can be obtained first, and the initial over-excavation prediction model can be an initial version of the final model for subsequent optimization and adjustment. In a feasible implementation, the above step A100 can specifically include obtaining a blasting construction data set and an original prediction model; wherein the blasting construction data set includes multiple groups of blasting construction data, each blasting construction data includes surrounding rock quality parameters, main structural surface location category, main structural surface inclination category, blasting parameters and maximum linear over-excavation data; pre-processing operations are performed on all blasting construction data in the blasting construction data set to obtain a model training sample set; wherein the pre-processing operations include data screening and data normalization; the original prediction model is trained based on the model training sample set to obtain an initial over-excavation prediction model.

[0079] The original prediction model can be a BP single-layer neural network model or a CNN convolutional neural network model, or in a feasible implementation, the original prediction model can be a DBN neural network model (Deep Belief Networks, deep belief network model) including a two-layer restricted Boltzmann machine RBM neural network and a single-layer error back propagation BP neural network. DBN is a deep neural network model that can be trained both supervised and unsupervised, and can solve high-dimensional nonlinear function problems, such as Figure 4 As shown, Figure 4 Figure 1 is a schematic diagram of the DBN network structure. Figure 4 It can be seen that the DBN neural network is composed of an unsupervised lower layer of several RBMs superimposed and a supervised upper layer composed of a BP neural network. RBM is a Markov random field proposed by Professor Hinton and is an important component of the deep neural network (DBN). RBM is generally a neural network structure consisting of two layers: a hidden layer and an input layer. Its basic principle is to adjust the parameter settings through a large amount of training data so that the distribution probability represented by the RBM under the parameters is as consistent as possible with the training data. Before training the original prediction model (DBN model), the number of hidden layer nodes of each layer of the RBM neural network in the DBN model can be set to 20, the learning rate can be set to 0.01, the preset number of training times can be set to 500, and the number of reverse iterations can be set to 3000, so that the DBN model can effectively learn the characteristics and patterns of the data.

[0080] The blasting construction data set includes multiple groups of blasting construction data, each of which contains surrounding rock quality parameters, main structural surface location category, main structural surface inclination category, blasting parameters, and corresponding maximum linear over-excavation data. During the tunnel construction process, due to the negligence of the staff, incomplete data and wrong records may occur. Therefore, in order to ensure the integrity and correctness of the data, the data with missing records and the data that obviously do not conform to the rules can be eliminated (i.e., data screening). After screening, the data set shown in Table 2 can be obtained.

[0081] Table 2

[0082]

[0083] In Table 2, X1 and X2 represent the integrity coefficient and saturated uniaxial compressive strength of the surrounding rock quality parameters respectively; X3 represents the main structural surface inclination category; X4 represents the main structural surface position category; X5~X14 represent the peripheral eye charge, peripheral eye hole distance, peripheral auxiliary eye hole distance, peripheral auxiliary eye charge, smooth blasting layer thickness, peripheral eye charge at the structural surface, outer circle auxiliary eye charge at the structural surface, number of blastholes, total explosive charge and cycle footage of the blasting parameters respectively; Y1 represents the maximum linear over-excavation data.

[0084] In order to improve the convergence speed and calculation accuracy of the original prediction model, the data can be normalized to unify the dimension and variation range. For example, the "mapminmax" normalization formula in MATLAB can be used for data preprocessing. The normalization formula is: Among them, y is the value of the normalized data; x max is the maximum value of the data before normalization; x min is the minimum value of the data before normalization, and the data range after processing is [0,1]. After the above processing, a model training sample set suitable for the original prediction model training can be obtained as shown in Table 3.

[0085] Table 3

[0086]

[0087]

[0088] Therefore, the original prediction model (DBN model) can be trained using the model training sample set in Table 3 above, and the trained model is the above-mentioned initial over-digging prediction model.

[0089] In actual application, the initial over-digging prediction model based on the DBN model may fail to meet the engineering usage due to the inappropriate setting of the artificial learning rate, number of hidden layer nodes and number of training times. Therefore, the model parameters can be optimized, but if the parameters are adjusted manually until the accuracy meets the requirements, a lot of time will be wasted. In order to make the initial over-digging prediction model meet the prediction accuracy requirements, the adaptive particle swarm algorithm CIPSO based on the curve increasing strategy can be used to determine the optimal value of the hyperparameters of the initial over-digging prediction model. Among them, the hyperparameters include the number of nodes in the first layer of the hidden layer, the number of nodes in the second layer of the hidden layer, the learning rate and the number of training iterations of the initial over-digging prediction model. The CIPSO algorithm is optimized based on the improved second-order oscillation method based on the curve increasing strategy on the basis of the PSO algorithm (particle swarm optimization algorithm). As a swarm intelligence algorithm that simulates bird flight and foraging, the PSO algorithm finds the optimal area in a complex search space through the interaction between particles, but the PSO algorithm is prone to fall into the local optimum, while the CIPSO algorithm is an adaptive particle swarm optimization algorithm, which is more suitable for tasks that dynamically adjust its parameters to enhance the search capability, and is better than the PSO algorithm.

[0090] When searching for the optimal parameters of the initial over-digging prediction model based on CIPSO, the optimization target can be set according to the optimization requirements. When optimizing the model hyperparameters, the optimization target can be determined as the number of nodes in the first hidden layer, the number of nodes in the second hidden layer, the learning rate, and the number of training iterations of the initial over-digging prediction model. Then initialize the particle swarm: define an initial particle swarm, each particle represents a candidate solution for a set of hyperparameters of the initial over-digging prediction model. The position of the particle can be encoded as a set of parameter values ​​(such as the number of nodes in the first hidden layer, the number of nodes in the second hidden layer, the learning rate, and the number of training iterations, etc.). The performance of each particle (i.e., each set of hyperparameter settings) on the initial over-digging prediction model is evaluated by the fitness function. The CIPSO algorithm adjusts the behavior of the particle swarm through a curve increment strategy (such as gradually increasing the speed of the particle, the weight of the fitness function, etc.) to improve the exploration and development capabilities of the parameter space. Through multiple iterations, the particle swarm continuously updates its position and speed to find the optimal hyperparameter settings of the initial over-digging prediction model. After each iteration, the performance of each particle is evaluated according to the fitness function, and the position and speed of the particle are adjusted. The optimization process is stopped when a certain number of iterations is reached, the fitness function converges, or a predetermined performance index is reached. Finally, the optimal value of the optimization target (i.e., the optimal value of the hyperparameter of the initial over-mining prediction model) can be output.

[0091] Thus, the values ​​of the hyperparameters of the initial over-excavation prediction model can be updated to the above-mentioned optimal values ​​to obtain the most optimized over-excavation prediction model. The optimal over-excavation prediction model is the preset tunnel blasting maximum linear over-excavation prediction model for predicting tunnel over-excavation.

[0092] Before the tunnel blasting construction, the main structural surface parameters, surrounding rock quality parameters and blasting parameters related to the target tunnel can be input into the aforementioned preset tunnel blasting maximum linear over-excavation prediction model. The model can determine the corresponding over-excavation prediction value by using these influencing parameters. The over-excavation prediction value output by the model is compared with the preset threshold value to determine whether the over-excavation prediction value exceeds the maximum linear over-excavation allowed (i.e., the preset threshold value). The preset threshold value can be determined according to the tunnel engineering design requirements and specifications, or can also be determined by comprehensively considering factors such as tunnel structure and construction safety. When the over-excavation prediction value is greater than the preset threshold value, the blasting parameters in the blasting design can be adjusted, such as increasing or decreasing the blasting charge, adjusting the hole spacing, etc. The adjusted blasting parameters are combined with the corresponding main structural surface parameters and surrounding rock quality parameters, and are input into the preset tunnel blasting maximum linear over-excavation prediction model again for prediction. This step is repeated until the final over-excavation prediction value is less than or equal to the preset threshold value, indicating that the blasting parameters have been adjusted to a level that meets the requirements. Thus, the blasting parameters obtained by the last adjustment can be determined as the target tunnel blasting parameters required for use in actual tunnel blasting construction.

[0093] It can be understood that the tunnel blasting parameter determination method provided in this embodiment can adjust the blasting parameters according to the output of the model, and then re-predict until the requirements are met. This process can systematically optimize the blasting parameters by iteratively optimizing the blasting parameters to achieve the target overbreak. Compared with the method of calculating and determining the tunnel blasting parameters based on engineering experience and empirical formulas in the related art, the influence of human subjective judgment is reduced, and the tunnel blasting parameters determined in this way are more accurate and objective.

[0094] For example, to help understand the implementation process of the tunnel blasting parameter determination method of this embodiment, please refer to Figure 5 , Figure 5 A simplified flow chart of a method for determining tunnel blasting parameters is provided.

[0095] Specifically, before the tunnel blasting construction, the tunnel face image data (main structural surface image data) can be obtained, and the image data can be input into the SP-YOLOv8 model for processing to obtain the main structural surface inclination category; the image data can be input into the SPM-YOLOv8-seg model for processing to extract the main structural surface information (such as the main structural surface height information, etc.), and the corresponding main structural surface position category can be determined in combination with the preset position classification standard. The main structural surface inclination category, main structural surface position category, surrounding rock quality parameters and an initial set of blasting design parameters (i.e., blasting parameters) are input into the CIPSO-DBN model (i.e., the preset tunnel blasting maximum linear over-excavation prediction model), and a maximum linear over-excavation prediction value can be obtained, which is compared with the expected target (i.e., the preset threshold value). If the difference is large, the blasting design parameters can be adjusted, and then input into the CIPSO-DBN model for prediction until a satisfactory result is obtained (i.e., the over-excavation prediction value is less than or equal to the preset threshold value), and the blasting construction plan is determined according to the final blasting design parameters.

[0096] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for determining blasting parameters of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0097] This application also provides a tunnel blasting parameter determination device, please refer to Figure 6 , the tunnel blasting parameter determination device comprises:

[0098] An acquisition module 10 is used to acquire the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel;

[0099] Prediction module 20, used for inputting main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain an overbreak prediction value;

[0100] The adjustment module 30 is used to adjust the blasting parameters if the overbreak prediction value is greater than a preset threshold value, and return to the step of inputting the main structural surface parameters, the surrounding rock quality parameters and the blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain the overbreak prediction value, until the overbreak prediction value is less than or equal to the preset threshold value;

[0101] The determination module 40 is used to determine the adjusted blasting parameters as target tunnel blasting parameters.

[0102] The tunnel blasting parameter determination device provided by the present application adopts the tunnel blasting parameter determination method in the above embodiment, which can solve the technical problem of low accuracy of tunnel blasting parameters determined in the related art. Compared with the related art, the beneficial effects of the tunnel blasting parameter determination device provided by the present application are the same as the beneficial effects of the tunnel blasting parameter determination method provided by the above embodiment, and other technical features in the tunnel blasting parameter determination device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0103] The present application provides a tunnel blasting parameter determination device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the tunnel blasting parameter determination method in the above-mentioned embodiment 1.

[0104] Reference below Figure 7 , which shows a schematic diagram of the structure of a tunnel blasting parameter determination device suitable for implementing the embodiment of the present application. The tunnel blasting parameter determination device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The tunnel blasting parameter determination device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0105] like Figure 7As shown, the tunnel blasting parameter determination device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the tunnel blasting parameter determination device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the tunnel blasting parameter determination device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a tunnel blasting parameter determination device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0106] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0107] The tunnel blasting parameter determination device provided by the present application adopts the tunnel blasting parameter determination method in the above embodiment, which can solve the technical problem of low accuracy of tunnel blasting parameters determined in the related art. Compared with the related art, the beneficial effects of the tunnel blasting parameter determination device provided by the present application are the same as the beneficial effects of the tunnel blasting parameter determination method provided by the above embodiment, and other technical features in the tunnel blasting parameter determination device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0108] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0109] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0110] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the tunnel blasting parameter determination method in the above-mentioned embodiment.

[0111] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0112] The computer-readable storage medium may be included in the tunnel blasting parameter determination device; or may exist independently without being assembled into the tunnel blasting parameter determination device.

[0113] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the tunnel blasting parameter determination device, the tunnel blasting parameter determination device: obtains the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel; inputs the main structural surface parameters, surrounding rock quality parameters and blasting parameters into a preset tunnel blasting maximum linear over-excavation prediction model to obtain an over-excavation prediction value; if the over-excavation prediction value is greater than a preset threshold, adjusts the blasting parameters, and returns to execute the step of inputting the main structural surface parameters, surrounding rock quality parameters and blasting parameters into the preset tunnel blasting maximum linear over-excavation prediction model to obtain the over-excavation prediction value, until the over-excavation prediction value is less than or equal to the preset threshold; and determines the adjusted blasting parameters as the target tunnel blasting parameters.

[0114] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0115] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0116] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0117] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for determining tunnel blasting parameters, and can solve the technical problem of low accuracy of tunnel blasting parameters determined in the related art. Compared with the related art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the method for determining tunnel blasting parameters provided by the above-mentioned embodiment, and will not be repeated here.

[0118] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned method for determining tunnel blasting parameters when executed by a processor.

[0119] The computer program product provided by the present application can solve the technical problem of low accuracy of tunnel blasting parameters determined in the related art. Compared with the related art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the tunnel blasting parameter determination method provided by the above embodiment, which will not be repeated here.

[0120] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for determining tunnel blasting parameters, characterized in that: The method includes: Obtain the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel; Inputting the main structural surface parameters, the surrounding rock quality parameters and the blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain an overbreak prediction value; If the over-excavation prediction value is greater than a preset threshold, the blasting parameters are adjusted, and the step of inputting the main structural surface parameters, the surrounding rock quality parameters, and the blasting parameters into a preset tunnel blasting maximum linear over-excavation prediction model to obtain an over-excavation prediction value is returned to the step of obtaining an over-excavation prediction value until the over-excavation prediction value is less than or equal to the preset threshold; The adjusted blasting parameters are determined as target tunnel blasting parameters.

2. The method according to claim 1, characterized in that The main structural surface parameters include the main structural surface position category and the main structural surface inclination category; The step of obtaining the main structural surface parameters of the target tunnel comprises: Acquiring main structural surface image data of the target tunnel; Inputting the main structural surface image data into a preset main structural surface inclination classification recognition model to obtain the main structural surface inclination category; Inputting the main structural surface image data into a preset main structural surface information extraction model to obtain the main structural surface height information of the target tunnel; The main structural surface position category is determined based on the main structural surface height information and a preset position classification standard.

3. The method according to claim 2, characterized in that Before the step of inputting the main structural surface parameters, the surrounding rock quality parameters and the blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain an overbreak prediction value, the step further includes: Obtaining an initial overbreak prediction model; Based on the curve increasing strategy adaptive particle swarm algorithm CIPSO, determine the optimal value of the hyperparameter of the initial over-digging prediction model; the hyperparameters include the number of nodes in the first layer of the hidden layer, the number of nodes in the second layer of the hidden layer, the learning rate and the number of training iterations of the initial over-digging prediction model; Based on the optimal value of the hyperparameter, the initial over-digging prediction model is updated to obtain an optimal over-digging prediction model; The optimal over-excavation prediction model is determined as the preset tunnel blasting maximum linear over-excavation prediction model.

4. The method according to claim 3, characterized in that The step of obtaining the initial over-excavation prediction model comprises: Acquire a blasting construction data set and an original prediction model; the blasting construction data set includes multiple groups of blasting construction data, each of which includes surrounding rock quality parameters, main structural surface position category, main structural surface inclination category, blasting parameters and maximum linear over-excavation data; Performing a preprocessing operation on all the blasting construction data in the blasting construction data set to obtain a model training sample set; the preprocessing operation includes data screening and data normalization; The original prediction model is trained based on the model training sample set to obtain the initial over-excavation prediction model.

5. The method according to claim 4, characterized in that The original prediction model includes a two-layer restricted Boltzmann machine RBM neural network and a single-layer error back propagation BP neural network; wherein the number of hidden layer nodes of each layer of the RBM neural network is 20, the learning rate is 0.01, the preset number of training times is 500, and the number of reverse iterations is 3000.

6. The method according to any one of claims 1 to 5, characterized in that The blasting parameters include the charge of peripheral holes, the peripheral hole spacing, the peripheral auxiliary hole spacing, the charge of peripheral auxiliary holes, the thickness of the light blasting layer, the charge of peripheral holes at the structural surface, the charge of outer ring auxiliary holes at the structural surface, the number of blast holes, the total amount of explosives and the cycle footage; the surrounding rock quality parameters include the integrity coefficient and the saturated uniaxial compressive strength.

7. A device for determining tunnel blasting parameters, characterized in that: The device comprises: An acquisition module is used to obtain the main structural surface parameters, surrounding rock quality parameters and blasting parameters of the target tunnel; A prediction module, used for inputting the main structural surface parameters, the surrounding rock quality parameters and the blasting parameters into a preset tunnel blasting maximum linear overbreak prediction model to obtain an overbreak prediction value; an adjustment module, configured to adjust the blasting parameters if the over-excavation prediction value is greater than a preset threshold value, and return to the step of inputting the main structural surface parameters, the surrounding rock quality parameters and the blasting parameters into a preset tunnel blasting maximum linear over-excavation prediction model to obtain an over-excavation prediction value, until the over-excavation prediction value is less than or equal to the preset threshold value; The determination module is used to determine the adjusted blasting parameters as target tunnel blasting parameters.

8. A tunnel blasting parameter determination device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for determining tunnel blasting parameters according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of determining the tunnel blasting parameters according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for determining tunnel blasting parameters according to any one of claims 1 to 6 are implemented.

Citation Information

Cited By

  • Blasting design parameter optimization method and system based on deep learning and deep neural network

    CN119848977A

  • Tunnel smooth blasting design parameter intelligent optimization method based on deep learning and neural network

    CN119848978A