Intelligent optimization method and system for tunnel smooth blasting blast holes in layered rock mass

Abstract

The invention provides an intelligent optimization method and system for tunnel smooth blasting blast holes in layered rock mass, and belongs to the technical field of tunnel engineering and blasting. The method comprises the steps of collecting stratified rock geological data, evaluating and extracting features, constructing a multi-objective optimization function, solving by an intelligent optimization algorithm, performing construction feedback and dynamic optimization and the like. The method comprises the following steps of: acquiring data by using various geological exploration equipment, performing evaluation processing on the data by using a support vector machine model, constructing an optimization function considering multiple indexes, solving an optimal blast hole parameter combination by combining a genetic algorithm and a particle swarm optimization algorithm, and finally feeding back a blasting effect to dynamically adjust an optimization scheme. According to the intelligent optimization method and system for the smooth blasting blast holes of the tunnel in the layered rock mass, the blasting effect can be improved, over-break and under-break and concrete consumption can be reduced, the construction cost can be reduced, the construction safety and efficiency can be enhanced, and remarkable economic and social benefits can be achieved for layered rock mass tunnel engineering construction.

Description

Technical Field

[0001] The present invention relates to the fields of tunnel engineering and blasting technology, and particularly to an intelligent optimization method and system for smooth blasting holes in tunnels in layered rock masses. Background Art

[0002] In tunnel engineering construction, smooth blasting technology is widely used to control the excavation contour, reduce overbreak and underbreak, and reduce the disturbance damage to the surrounding rock. However, layered rock masses have unique geological characteristics, such as changes in the strike and dip of bedding planes, rock layer thickness, differences in rock mass strength and integrity, etc. These characteristics pose challenges to traditional smooth blasting technology. Existing technologies often rely on experience and analogy methods to design blast hole parameters, and it is difficult to accurately consider the complexity of layered rock masses, resulting in unstable blasting effects, serious overbreak and underbreak phenomena, poor wall surface flatness, frequent local collapses and other problems, significantly increasing the construction cost and affecting the project quality and safety.

[0003] Some current optimization methods mostly target a single blasting effect index, such as overbreak and underbreak volume or wall surface flatness, lacking comprehensive consideration of various factors of blasting effects. This single-objective optimization method cannot balance blasting effects and economic benefits, and it is difficult to meet the comprehensive requirements of modern tunnel engineering for high quality, high efficiency, low cost and high safety.

[0004] Therefore, to address the challenges of smooth blasting in layered rock mass tunnels, it is urgent to develop an intelligent optimization method and system. This system needs to be able to accurately analyze the geological characteristics of layered rock masses, comprehensively consider various factors of blasting effects, and realize the intelligent optimization of blast hole parameters, thereby improving the blasting quality, reducing the construction cost, and ensuring the safety and efficiency of tunnel engineering construction. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent optimization method and system for smooth blasting holes in tunnels in layered rock masses, which can improve the blasting effect, reduce overbreak and underbreak and concrete consumption, reduce the construction cost, enhance the construction safety and efficiency, and have significant economic and social benefits for the construction of layered rock mass tunnel projects.

[0006] To achieve the above purpose, the present invention provides an intelligent optimization method for smooth blasting holes in tunnels in layered rock masses, including the following steps: Step S1: Use a variety of geological exploration equipment to obtain geological data of the tunnel face in the layered rock mass; Step S2: Conduct quality assessment and feature extraction on the obtained geological data, determine the reliability and applicability of the data based on a preset data assessment model, remove abnormal data and noise interference, and extract geological features related to tunnel smooth blasting; Step S3: Construct a multi-objective optimization function according to the evaluated geological data and the extracted geological features; Step S4: Use an intelligent optimization algorithm to solve the constructed multi-objective optimization function and search for the optimal combination of blast hole parameters. Step S5: Apply the obtained optimal blast hole parameters to the actual tunnel smooth blasting construction. Meanwhile, monitor and evaluate the actual blasting effect after blasting, and feedback the evaluation results to the multi-objective optimization function construction link to update the geological data and adjust the weight coefficients, so as to realize the dynamic optimization of the subsequent blast hole optimization scheme.

[0007] Preferably, in step S1, the geological exploration equipment includes a ground penetrating radar, a three-dimensional laser scanner, a sonic detector, and a core drilling equipment. By using a variety of equipment in combination, detailed geological information of the layered rock mass can be obtained from different angles and depths, improving the comprehensiveness and accuracy of the geological data.

[0008] Preferably, in step S1, the geological data includes the strike, dip angle, rock mass integrity parameter, joint development degree, and surrounding rock strength parameter of the bedding plane.

[0009] Preferably, in step S2, the data evaluation model is established based on the support vector machine, and the specific process is as follows: Data preparation: Collect historical geological data and corresponding blasting effect data. Use the geological data as the input feature vector and the blasting effect data as the output label, and standardize the data so that its mean is 0 and the standard deviation is 1. Model training: Divide the processed data into a training set and a test set, and allocate them according to a ratio of 7:3. Use the radial basis function as the kernel function of the support vector machine, and use the training set to train the support vector machine model. Optimize the performance of the model by adjusting the penalty parameter and the kernel function parameter. Model evaluation and optimization: Use the test set to evaluate the trained support vector machine model, calculate the accuracy, recall rate, and F1 value of the model, and adjust and optimize the model parameters according to the evaluation results. New data evaluation and processing: After standardizing the newly obtained geological data, input it into the trained support vector machine model. The model outputs the quality evaluation result of this data, and preprocess the new data according to the evaluation result, and extract the features related to the strike, dip angle, rock mass integrity parameter, joint development degree, and surrounding rock strength parameter of the bedding plane in the geological data.

[0010] Preferably, in step S3, the multi-objective optimization function comprehensively considers the overbreak and underbreak amount after blasting, the residual trace rate of the perimeter holes, the wall surface flatness, and the overconsumption of shotcrete, and introduces a cost weight factor to make the optimization scheme take into account economy. Its mathematical expression is: ; Where represents the multi-objective optimization function, represents the blast hole parameter vector, including blast hole position, spacing, angle and depth, represents the overbreak and underbreak amount, represents the remaining trace rate of the perimeter holes, represents the rock wall flatness, represents the over-consumption of shotcrete, 、 、 、 represents the weight coefficient corresponding to each objective; ; ; ; ; Among them, represents the distance from the excavation contour line to the design contour line of the th measurement point after actual blasting, represents the distance of the corresponding point on the design contour line, represents the number of measurement points, represents the number of remaining traces of the perimeter holes after blasting, represents the total number of perimeter holes, represents the standard deviation of the distance from the actual excavation contour line of the rock wall to the design contour line after blasting, represents the th actual usage amount of shotcrete for a certain section, represents the th theoretical design amount of shotcrete for a certain section, represents the number of sections of shotcrete; The multi-objective optimization function also incorporates the blasting vibration velocity and frequency as constraint conditions into the objective function, and the constraint conditions are as follows: ; ; Among them, represents the maximum blasting vibration velocity, represents the upper limit of the allowable blasting vibration velocity, represents the minimum blasting vibration frequency, represents the lower limit of the allowable blasting vibration frequency.

[0011] Preferably, the determination of the weight coefficient is based on the analytic hierarchy process combined with the expert scoring method and is dynamically adjusted according to the geological characteristics.

[0012] Preferably, in step S4, the intelligent optimization algorithm combines the genetic algorithm and the particle swarm algorithm. By simulating the biological evolution process and swarm intelligence behavior, it explores the optimal solution that meets the constraint conditions in the solution space. The specific implementation steps of the intelligent optimization algorithm are as follows: Step S41: Initialize the population. Randomly generated combinations of blast hole parameters are used as the initial solution, and each solution is encoded. The real number encoding method is adopted, and the blast hole position, spacing, angle, and depth are transformed into real number vectors; Step S42: Calculate the objective function value corresponding to each solution. According to the constructed multi-objective optimization function, substitute the decoded blast hole parameters for calculation to obtain the function values of each blasting effect index and the comprehensive objective function value, which are used as the basis for evaluating the quality of the solution; Step S43: Selection operation. Adopt the tournament selection strategy to select parent individuals from the current population and enter the crossover and mutation operation links; Step S44: Crossover operation. Combine the simulated binary crossover operator of the genetic algorithm and the position update strategy of the particle swarm algorithm to perform crossover combinations on the parent individuals to generate new offspring individuals; Step S45: Mutation operation. Adopt the polynomial mutation operator to perform local search on the offspring individuals, perturb the blast hole parameters, increase the diversity of the solutions, and prevent the algorithm from falling into local optima. By setting the mutation distribution index, control the size of the mutation step; Step S46: Update the population. Combine the parent individuals and the offspring individuals, sort them according to the objective function value to generate a new population, which serves as the basis for the next iteration. At the same time, check the constraint conditions for the solutions in the new population, eliminate the solutions that do not meet the engineering requirements, and adopt a repair strategy to process the out-of-bounds variables to make them meet the constraint conditions; Step S47: Repeat steps S42 to S46 until the preset iteration termination condition is reached, and output the optimal combination of blast hole parameters, the corresponding objective function value, and the values of each blasting effect index.

[0013] Preferably, the termination conditions include: reaching the maximum number of iterations, the convergence accuracy of the objective function value, or the blasting effect meeting the engineering requirements.

[0014] Preferably, in step S4, the constraint conditions include the reasonable range constraint of the blast hole spacing, the allowable deviation constraint of the blast hole angle, and the blasting safety distance constraint; The reasonable range constraint of the blast hole spacing is as follows: ; The allowable deviation constraint of the blast hole angle is as follows: ; The blasting safety distance constraint is as follows: ; ; Among them, represents the actual hole spacing of the th type of blast hole, represents the minimum allowable hole spacing of the th type of blast hole, represents the maximum allowable hole spacing of the th type of blast hole, , represents the cut hole, represents the auxiliary hole, represents the perimeter hole, represents the designed angle of the blast hole, represents the actual angle, represents the allowable deviation, represents the distance between the blasting point and the protected target, represents the safety distance, represents the coefficient related to the geological conditions and blasting type, represents the maximum charge per delay.

[0015] The present invention also provides an intelligent optimization system for smooth blasting holes in a tunnel in a layered rock mass, including: A data acquisition module for obtaining geological data of the tunnel face and the surrounding rock in front of it in a layered rock mass tunnel by using a variety of geological exploration equipment; A data processing module for performing quality evaluation and feature extraction on the obtained geological data, determining the reliability and applicability of the data based on a preset data evaluation model, removing abnormal data and noise interference, and extracting geological features related to smooth blasting in the tunnel; An optimization module for constructing a multi-objective optimization function according to the evaluated geological data and the extracted geological features, and using an intelligent optimization algorithm to solve the constructed multi-objective optimization function to search for the optimal combination of blast hole parameters; A construction feedback module for applying the obtained optimal blast hole parameters to the actual tunnel smooth blasting construction, and at the same time monitoring and evaluating the actual blasting effect after blasting, and feeding back the evaluation results to the multi-objective optimization function construction link to update the geological data and adjust the weight coefficients to achieve dynamic optimization of the subsequent blast hole optimization scheme.

[0016] Therefore, by adopting the above-mentioned intelligent optimization method and system for smooth blasting holes in a tunnel in a layered rock mass, the beneficial technical effects of the present invention are as follows: (1) By using a variety of geological exploration equipment to obtain detailed geological data of the tunnel face of layered rock masses, including the strike, dip angle of bedding planes, rock mass integrity parameters, joint development degree, and surrounding rock strength parameters, etc., and combining with a support vector machine model to conduct quality assessment and feature extraction of the data, it is possible to accurately remove abnormal data and noise interference, extract geological features closely related to smooth blasting, provide a reliable data basis for subsequent optimization calculations, and thus effectively improve the prediction accuracy and reliability of blasting effects.

[0017] (2) The constructed multi-objective optimization function comprehensively considers various factors such as overbreak and underbreak after blasting, remaining trace rate of perimeter holes, wall rock flatness, and overconsumption of shotcrete, etc., and introduces a cost weight factor. At the same time, the blasting vibration velocity and frequency are incorporated as constraint conditions into the optimization process, realizing the comprehensive quantification and integrated optimization of blasting effects. Compared with traditional single-objective optimization methods, this method can take into account the control of construction costs while ensuring blasting effects, making the optimization scheme more economical and practical.

[0018] (3) The intelligent optimization algorithm combining genetic algorithm and particle swarm algorithm, by simulating the biological evolution process and swarm intelligence behavior, efficiently explores the optimal solution that meets the constraint conditions in the solution space. This algorithm can dynamically adjust the optimization direction of blasting parameters according to geological features, avoid falling into local optimal solutions, and improve the optimization efficiency and global search ability. At the same time, the construction feedback link feeds back the actual blasting effect evaluation results into the optimization model for updating geological data and adjusting weight coefficients, realizing the dynamic adjustment of subsequent blasting hole optimization schemes, and further enhancing the adaptability and intelligence of the optimization method to complex layered rock mass geological conditions.

[0019] (4) The intelligent optimization system of the present invention organically integrates links such as data acquisition, processing, optimization, and construction feedback, forming a complete set of solutions for optimizing the smooth blasting holes of tunnels in layered rock masses. This system can effectively reduce overbreak and underbreak phenomena, improve the remaining trace rate of perimeter holes and wall rock flatness, reduce concrete consumption, thereby significantly improving the construction quality and efficiency of tunnel smooth blasting, reducing construction costs, and enhancing construction safety, having significant economic and social benefits for the construction of tunnels in layered rock masses. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of an intelligent optimization method for smooth blasting holes of tunnels in layered rock masses according to the present invention; Figure 2 is a flow chart for constructing a multi-objective optimization function; Figure 3 is a flow chart for determining weight coefficients; Figure 4It is a flowchart for an intelligent optimization algorithm to solve the constructed multi-objective optimization function. Specific Embodiments

[0021] The technical solutions of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] Unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs.

[0023] Embodiment 1 As Figure 1 shown, an intelligent optimization method for smooth blasting holes in a layered rock mass tunnel includes the following steps: Step S1: Use a variety of geological exploration equipment to obtain geological data of the tunnel face of the layered rock mass tunnel; The geological exploration equipment includes a ground penetrating radar, a 3D laser scanner, a sonic detector, and a core drilling equipment.

[0024] Ground penetrating radar: Use IDS SIR-4000, scanning spacing 10 cm × 10 cm, frequency 1 GHz; 3D laser scanner: RIEGL VZ-4000, point cloud density 50 pts / m 2 ; Sonic detector: PUNDIT, test spacing 50 cm, wave velocity range 1000 - 4500 m / s; Core drilling: 75 mm core drill, drill depth 5 m, RQD (rock core integrity) test.

[0025] The geological data includes the strike, dip angle, rock mass integrity parameter, joint development degree, and surrounding rock strength parameter of the bedding plane.

[0026] Step S2: Conduct quality assessment and feature extraction on the obtained geological data, determine the reliability and applicability of the data based on a preset data evaluation model, remove abnormal data and noise interference, and extract geological features related to smooth blasting of the tunnel.

[0027] The data evaluation model is established based on a support vector machine, and the specific process is as follows: Data preparation: Collect historical geological data and corresponding blasting effect data, use the geological data as input feature vectors, and the blasting effect data as output labels, and standardize the data so that its mean is 0 and the standard deviation is 1; Model training: Divide the processed data into a training set and a test set, allocate them according to a ratio of 7:3, use the radial basis function as the kernel function of the support vector machine, train the support vector machine model with the training set, and optimize the performance of the model by adjusting the penalty parameter and the kernel function parameter; Model evaluation and optimization: Use the test set to evaluate the trained support vector machine model, calculate the accuracy, recall, and F1 value of the model, and adjust and optimize the model parameters according to the evaluation results; New data evaluation and processing: After standardizing the newly acquired geological data, input it into the trained support vector machine model. The model outputs the quality evaluation results of the data. According to the evaluation results, preprocess the new data and extract the features related to the strike, dip angle, rock mass integrity parameter, joint development degree, and surrounding rock strength parameter of the bedding plane in the geological data.

[0028] Step S3: According to the evaluated geological data and the extracted geological features, construct a multi-objective optimization function.

[0029] As Figure 2 shown, the multi-objective optimization function comprehensively considers the overbreak and underbreak amount after blasting, the remaining trace rate of the perimeter holes, the wall rock flatness, and the overconsumption of shotcrete, and introduces a cost weight factor. Its mathematical expression is: ; Among them, represents the multi-objective optimization function, represents the vector of blast hole parameters, including the position, spacing, angle, and depth of the blast holes, represents the overbreak and underbreak amount, represents the remaining trace rate of the perimeter holes, represents the wall rock flatness, represents the overconsumption of shotcrete, , , , represent the weight coefficients corresponding to each objective; ; ; ; ; Among them, represents the distance between the excavation contour line and the design contour line at the th measurement point after actual blasting, represents the distance at the corresponding point on the design contour line, represents the number of measurement points, represents the number of remaining traces of the perimeter holes after blasting, represents the total number of perimeter holes, represents the standard deviation of the distance between the actual excavation contour line and the design contour line of the wall rock after blasting, represents the The actual usage of shotcrete for each section, represents the theoretical designed quantity of shotcrete for the section; The multi-objective optimization function also incorporates the blasting vibration velocity as a constraint condition into the objective function, and the constraint condition is as follows: ; where represents the maximum blasting vibration velocity, represents the upper limit of the allowable blasting vibration velocity.

[0030] As Figure 3 shown, the determination of the weight coefficient is based on the analytic hierarchy process combined with the expert scoring method and is dynamically adjusted according to the geological characteristics: 1. Establish a hierarchical structure model: Take the blasting effect index and cost factors as the target layer, and take the overbreak and underbreak quantity, the remaining trace rate of the perimeter holes, the rock wall flatness, the over-consumption of shotcrete, as well as the blasting vibration velocity and frequency as the criterion layer to construct a hierarchical structure model.

[0031] 2. Construct a judgment matrix: Invite experts in the field of tunnel blasting engineering to make pairwise comparisons of the factors in the criterion layer, and assign corresponding values according to their relative importance to construct a judgment matrix. The element of the judgment matrix represents the th factor relative to the th factor importance degree, and its value range is 1-9, where =1 means that the two factors are equally important, =3 means that the th factor is slightly more important than the th factor, =5 means that the th factor is significantly more important than the th factor, =7 means that the th factor is strongly more important than the

[0032] th factor, =9 means that the th factor is extremely more important than the th factor, 3. Calculate the weight vector: Use the eigenvalue method to solve the judgment matrix to obtain the weight vector corresponding to each factor, and conduct a consistency test. The consistency test judges whether the judgment matrix has satisfactory consistency by calculating the consistency index (CI) and the random consistency index (RI). If CI / RI ≤ 0.1, it is considered that the judgment matrix has satisfactory consistency, otherwise the judgment matrix needs to be adjusted.

[0033] 4. Combine the expert scoring method: Collect the scoring results of multiple experts on the importance of each blasting effect index and cost factor, and normalize the scoring results to obtain the expert scoring weights of each factor.

[0034] 5. Dynamically adjust each weight based on the weight vector obtained by the analytic hierarchy process, the weight vector obtained by the expert scoring method, and the features related to the strike, dip angle of bedding planes, rock mass integrity parameters, joint development degree, and surrounding rock strength parameters: Overbreak and underbreak weight coefficient : ; Perimeter hole remaining trace rate weight coefficient : ; Rock wall flatness weight coefficient : ; Shotcrete overconsumption weight coefficient : ; Among them, and respectively represent the weight coefficients obtained by the analytic hierarchy process and the weight coefficients obtained by the expert scoring method. and and and all represent the basic weights of the rock wall flatness obtained by the analytic hierarchy process. and and and all represent the basic weights of the rock wall flatness obtained by the expert scoring method. represents the adjustment coefficient of the bedding plane on the overbreak and underbreak weight. represents the adjustment coefficient of the rock mass integrity parameter and joint development degree on the perimeter hole remaining trace rate weight. represents the adjustment coefficient of the surrounding rock strength parameter on the rock wall flatness weight. represents the adjustment coefficient of the rock mass structural plane spacing on the shotcrete overconsumption weight. represents the dip angle of the bedding plane. represents the maximum dip angle of the bedding plane. represents the rock mass integrity parameter. represents the maximum rock mass integrity parameter. represents the joint development degree. represents the maximum joint development degree. represents the surrounding rock strength parameter. represents the maximum surrounding rock strength parameter, represents the spacing of rock mass structural planes, represents the maximum spacing of rock mass structural planes.

[0035] Step S4: Use an intelligent optimization algorithm to solve the constructed multi-objective optimization function and search for the optimal combination of blast hole parameters.

[0036] As Figure 4 shown, the intelligent optimization algorithm combines the genetic algorithm and the particle swarm algorithm. By simulating the biological evolution process and swarm intelligence behavior, it explores the optimal solution that meets the constraint conditions in the solution space. The specific implementation steps of the intelligent optimization algorithm are as follows: Step S41: Initialize the population, randomly generate a certain number of blast hole parameter combinations as the initial solutions, and encode each solution. Using the real number encoding method, convert the blast hole position, spacing, angle, and depth into real number vectors; Step S42: Calculate the objective function values corresponding to each solution. According to the constructed multi-objective optimization function, substitute the decoded blast hole parameters into the calculation to obtain the function values of each blasting effect index and the comprehensive objective function value, which serve as the basis for evaluating the quality of the solutions; Step S43: Selection operation. Adopt the tournament selection strategy to select the solutions with higher fitness from the current population as the parent individuals and enter the crossover and mutation operation links. The fitness is calculated based on the objective function value. The higher the fitness, the better the solution and the greater the probability of being selected; Step S44: Crossover operation. Combine the simulated binary crossover operator of the genetic algorithm and the position update strategy of the particle swarm algorithm to perform crossover combinations on the parent individuals to generate new offspring individuals; Step S45: Mutation operation. Use the polynomial mutation operator to perform local search on the offspring individuals, perturb the blast hole parameters with a certain mutation probability to increase the diversity of the solutions and prevent the algorithm from falling into a local optimum. By setting the mutation distribution index, control the size of the mutation step; Step S46: Update the population. Combine the parent individuals and the offspring individuals, sort them according to the objective function value, select the solutions with higher fitness to form a new population as the basis for the next iteration. At the same time, check the constraint conditions for the solutions in the new population, eliminate the solutions that do not meet the engineering requirements, and use a repair strategy to process the out-of-bounds variables to make them meet the constraint conditions; Step S47: Repeat steps S42 to S46 until the preset iteration termination condition is reached, and output the optimal combination of blast hole parameters, the corresponding objective function value, and the values of each blasting effect index.

[0037] In step S4, the constraint conditions include the reasonable range constraint of the blasthole spacing, the allowable deviation constraint of the blasthole angle, and the blasting safety distance constraint.

[0038] The reasonable range constraint of the blasthole spacing is as follows: ; The allowable deviation constraint of the blasthole angle is as follows: ; The blasting safety distance constraint is as follows: ; ; Among them, represents the actual blasthole spacing of the th type of blasthole, represents the minimum allowable blasthole spacing of the th type of blasthole, represents the maximum allowable blasthole spacing of the th type of blasthole, , represents the cut hole, represents the auxiliary hole, represents the perimeter hole, represents the designed blasthole angle, represents the actual angle, represents the allowable deviation, represents the distance between the blasting point and the protected target, represents the safety distance, represents the coefficient related to the geological conditions and the blasting type, represents the maximum charge per delay.

[0039] Step S5: Apply the obtained optimal blasthole parameters to the actual tunnel smooth blasting construction. At the same time, monitor and evaluate the actual blasting effect after blasting, and feedback the evaluation results to the multi-objective optimization function construction link to update the geological data and adjust the weight coefficients, so as to realize the dynamic optimization of the subsequent blasthole optimization scheme.

[0040] Embodiment 2 An intelligent optimization system for tunnel smooth blasting blastholes in layered rock masses includes: A data acquisition module for obtaining geological data of the tunnel face and the surrounding rock in front of it in layered rock mass tunnels by using a variety of geological exploration equipment; A data processing module for performing quality assessment and feature extraction on the obtained geological data, determining the reliability and applicability of the data based on a preset data evaluation model, removing abnormal data and noise interference, and extracting geological features related to tunnel smooth blasting; An optimization module, which is used to construct a multi-objective optimization function according to the evaluated geological data and the extracted geological features, and use an intelligent optimization algorithm to solve the constructed multi-objective optimization function to search for the optimal combination of blast hole parameters; A construction feedback module, which is used to apply the obtained optimal blast hole parameters to the actual tunnel smooth blasting construction. At the same time, monitor and evaluate the actual blasting effect after blasting, and feedback the evaluation results to the multi-objective optimization function construction link to update the geological data and adjust the weight coefficients, so as to realize the dynamic optimization of the subsequent blast hole optimization scheme.

[0041] It should be noted that the content not elaborated in detail in the present invention is the prior art and is well known to those skilled in the art.

[0042] Therefore, by adopting the above-mentioned intelligent optimization method and system for blast holes in tunnel smooth blasting in layered rock masses, the present invention can improve the blasting effect, reduce overbreak and underbreak and concrete consumption, reduce construction costs, enhance construction safety and efficiency, and has significant economic and social benefits for the construction of layered rock mass tunnel projects.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent optimization method for smooth blasting holes in tunnels in layered rock masses, characterized in that It includes the following steps: Step S1: Obtain the geological data of the tunnel face of stratified rock mass by using a variety of geological exploration equipment; Step S2: Conduct quality assessment and feature extraction on the obtained geological data, determine the reliability and applicability of the data based on a preset data evaluation model, remove abnormal data and noise interference, and extract geological features related to tunnel smooth blasting; Step S3: Construct a multi-objective optimization function according to the evaluated geological data and the extracted geological features; Step S4: Use an intelligent optimization algorithm to solve the constructed multi-objective optimization function and search for the optimal combination of blast hole parameters; Step S5: Apply the obtained optimal blast hole parameters to the actual tunnel smooth blasting construction. At the same time, monitor and evaluate the actual blasting effect after blasting, and feedback the evaluation results to the multi-objective optimization function construction link to update the geological data and adjust the weight coefficients, so as to realize the dynamic optimization of the subsequent blast hole optimization scheme.

2. The intelligent optimization method for smooth blasting holes in tunnels in layered rock masses according to claim 1, wherein In step S1, the geological exploration equipment includes a geological radar, a three-dimensional laser scanner, a sonic detector, and a core drilling equipment.

3. The intelligent optimization method for smooth blasting holes in tunnels in layered rock masses according to claim 1, wherein, In step S1, the geological data includes the strike, dip angle, rock mass integrity parameter, joint development degree, and surrounding rock strength parameter of the bedding plane.

4. The intelligent optimization method for smooth blasting holes in tunnels in layered rock masses according to claim 1, characterized in that, In step S2, the data evaluation model is established based on a support vector machine, and the specific process is as follows: Collect historical geological data and corresponding blasting effect data, use the geological data as the input feature vector, and the blasting effect data as the output label, and standardize the data so that its mean is 0 and the standard deviation is 1; Divide the processed data into a training set and a test set, allocate them according to a ratio of 7:3, use the radial basis function as the kernel function of the support vector machine, train the support vector machine model with the training set, and optimize the performance of the model by adjusting the penalty parameter and the kernel function parameter; Use the test set to evaluate the trained support vector machine model, calculate the accuracy, recall rate, and F1 value of the model, and adjust and optimize the model parameters according to the evaluation results; After standardizing the newly obtained geological data, input it into the trained support vector machine model. The model outputs the quality evaluation result of the data, and preprocess the new data according to the evaluation result, and extract the features related to the strike, dip angle, rock mass integrity parameter, joint development degree, and surrounding rock strength parameter in the geological data.

5. The intelligent optimization method for smooth blasting holes in tunnels in layered rock masses according to claim 1, characterized in that In step S3, the multi-objective optimization function comprehensively considers the overbreak and underbreak amount, the remaining trace rate of the perimeter holes, the wall surface flatness, and the over-consumption of shotcrete after blasting, and introduces a cost weight factor. Its mathematical expression is: ； Among them, represents the multi-objective optimization function, represents the blast hole parameter vector, including blast hole position, spacing, angle and depth, represents the overbreak and underbreak amount, represents the peripheral hole remaining trace rate, represents the rock wall flatness, represents the over-consumption of shotcrete, , , , represent the weight coefficients corresponding to each objective; ； ； ； ； Among them, represents the distance from the excavation contour line to the design contour line of the th measurement point after actual blasting, represents the distance of the corresponding point on the design contour line, represents the number of measurement points, represents the number of remaining traces of the perimeter holes after blasting, represents the total number of perimeter holes, represents the standard deviation of the distance from the actual excavation contour line of the rock wall to the design contour line after blasting, represents the actual consumption of shotcrete in the th section, represents the theoretical design quantity of shotcrete in the th section, represents the number of sections of shotcrete; The multi-objective optimization function also incorporates the blasting vibration velocity as a constraint condition into the objective function. The constraint condition is as follows: ； Among them, represents the maximum velocity of blasting vibration, represents the upper limit of the allowable velocity of blasting vibration.

6. The intelligent optimization method for smooth blasting holes in tunnels in layered rock masses according to claim 5, characterized in that The determination of the weight coefficient is based on the analytic hierarchy process combined with the expert scoring method and is dynamically adjusted according to the geological features.

7. An intelligent optimization method for smooth blasting holes in tunnels in layered rock masses according to claim 1, characterized in that In step S4, the intelligent optimization algorithm combines the genetic algorithm and the particle swarm algorithm. By simulating the biological evolution process and swarm intelligence behavior, it explores the optimal solution that satisfies the constraint conditions in the solution space. The specific implementation steps of the intelligent optimization algorithm are as follows: Step S41: Initialize the population. Randomly generate combinations of blast hole parameters as the initial solutions, and perform encoding representation for each solution. Adopt the real number encoding method to convert the blast hole position, spacing, angle, and depth into real number vectors. Step S42: Calculate the objective function values corresponding to each solution. According to the constructed multi-objective optimization function, substitute the decoded blast hole parameters into the calculation to obtain the function values of each blasting effect index and the comprehensive objective function value, which serve as the basis for evaluating the quality of the solutions. Step S43: Selection operation. Adopt the tournament selection strategy to select parent individuals from the current population and enter the crossover and mutation operation links. Step S44: Crossover operation. Combine the simulated binary crossover operator of the genetic algorithm and the position update strategy of the particle swarm algorithm to perform crossover combination on the parent individuals to generate new offspring individuals. Step S45: Mutation operation. Adopt the polynomial mutation operator to perform local search on the offspring individuals, perturb the blast hole parameters, increase the diversity of the solutions, prevent the algorithm from falling into local optimum, and control the size of the mutation step by setting the mutation distribution index. Step S46: Update the population. Merge the parent individuals and the offspring individuals, sort them according to the objective function values to generate a new population as the basis for the next iteration. At the same time, check the constraint conditions for the solutions in the new population, eliminate the solutions that do not meet the engineering requirements, and adopt a repair strategy to process the out-of-bounds variables to make them meet the constraint conditions. Step S47: Repeat Step S42 to Step S46 until the preset iteration termination conditions are reached, and output the optimal combination of blast hole parameters, the corresponding objective function values, and the values of each blasting effect index.

8. An intelligent optimization method for smooth blasting holes in tunnels in layered rock masses according to claim 7, characterized in that, The termination conditions include: reaching the maximum number of iterations, the convergence accuracy of the objective function value, or the blasting effect meeting the engineering requirements.

9. The intelligent optimization method for smooth blasting holes in tunnels in layered rock masses according to claim 7, wherein In Step S4, the constraint conditions include the reasonable range constraint of the blast hole spacing, the allowable deviation constraint of the blast hole angle, and the blasting safety distance constraint. The reasonable range constraint of the blast hole spacing is as follows: ； The allowable deviation constraint of the blast hole angle is as follows: ； The blasting safety distance constraint is as follows: ； ； Among them, represents the actual hole spacing of the -type blast holes, represents the minimum allowable hole spacing of the -type blast holes, represents the maximum allowable hole spacing of the -type blast holes, , represents the cut hole, represents the auxiliary hole, represents the perimeter hole, represents the designed hole angle, represents the actual angle, represents the allowable deviation, represents the distance between the blasting point and the protected target, represents the safety distance, represents the coefficient related to the geological conditions and blasting type, represents the maximum charge per delay.

10. An intelligent optimization system for smooth blasting holes in tunnels in layered rock masses, characterized in that, It includes: The data acquisition module is used to obtain the geological data of the tunnel face and the surrounding rock in front of it in the layered rock mass tunnel by using a variety of geological exploration equipment. The data processing module is used to perform quality evaluation and feature extraction on the obtained geological data, determine the reliability and applicability of the data based on the preset data evaluation model, remove abnormal data and noise interference, and extract the geological features related to the smooth blasting of the tunnel. The optimization module is used to construct a multi-objective optimization function according to the evaluated geological data and the extracted geological features, and use an intelligent optimization algorithm to solve the constructed multi-objective optimization function to search for the optimal combination of blast hole parameters. The construction feedback module is used to apply the obtained optimal blast hole parameters to the actual tunnel smooth blasting construction. At the same time, monitor and evaluate the actual blasting effect after blasting, and feedback the evaluation results to the multi-objective optimization function construction link to update the geological data and adjust the weight coefficients to achieve the dynamic optimization of the subsequent blast hole optimization plan.

Images