Intelligent design and optimization method of tunnel blasting parameters in complex strata

Abstract

The present invention discloses an intelligent design and optimization method for tunnel blasting parameters in complex strata, specifically relating to the field of tunnel blasting technology. The method comprises the following steps: obtaining initial full-section blasthole design, detonation network design, and charge design information to construct an initial mathematical representation data set; establishing a three-dimensional tunnel model based on tunnel sampling data, inputting the initial data into a trained blasting simulation model to obtain preliminary simulation results; performing deviation analysis by comparing the simulation results with the expected results to determine whether to activate the blasting parameter optimization mechanism; if activated, performing sensitivity analysis and loop analysis to confirm all sensitive parameters. A genetic algorithm is used to optimize the blasting parameters, replacing the corresponding parameters in the initial data set, ultimately obtaining an optimized mathematical representation data set. The present invention can accurately adjust the blasting parameters, reduce unnecessary waste of blasting materials, and avoid secondary correction work caused by over-blasting or under-blasting.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel blasting, and more particularly to an intelligent design and optimization method for tunnel blasting parameters in complex strata. Background Art

[0002] Under the "dual carbon" strategy, tunnel construction is increasingly demanding mechanization, intelligence, and green practices. Tunnel drilling and blasting excavation is limited by technological advancements and control measures. When tunnels pass through complex strata with developed joints and fissures, fault fracture zones, and high ground stress, blasting often results in significant overexcavation and even landslides.

[0003] Controlled tunnel blasting is a controlled blasting technique that rationally utilizes explosive energy. This method creates a neatly formed tunnel with no noticeable cracking in the rock walls caused by blasting. This method maintains the integrity of the surrounding rock, improving its stability and self-supporting capacity while reducing the amount of over-excavation and under-excavation associated with conventional blasting. Controlled blasting originated in Sweden in the early 20th century. The blasting sequence is first trench blasting, followed by perimeter blasting.

[0004] In the prior art, when designing tunnel blasting, the full-section dimensions of the tunnel and the drilling conditions of the mechanical trolley are first considered. Based on the blasting design principle (first cut the slot hole, then the peripheral hole, and finally the auxiliary hole), a parametric design method for the full-section blasthole of the tunnel is proposed. Then, based on the rock blastability classification method, a differentiated design method for the full-section blasthole design is proposed, and finally the refined design of the full-section blasthole is completed. Secondly, from the theoretical perspectives of rock mass explosive consumption and rock breaking burden volume, a method for calculating the charge amount of a single blasthole is proposed, and automatic statistics of the charge amount of the blasthole is realized. Finally, based on the initiation rule of the full-section blasthole from the inside out, an automated initiation network configuration method for the full-section blasthole is proposed. However, before practical application, it is necessary to explore the suitability of the tunnel to be blasted, and if necessary, seek an optimized parameter design that is more suitable for the tunnel to be blasted. Therefore, the present invention proposes an intelligent design and optimization method for blasting parameters of tunnels in complex strata, in order to help blasters better achieve the established blasting goals. Summary of the Invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The intelligent design and optimization method of tunnel blasting parameters in complex strata includes the following steps:

[0007] Obtaining initial full-section blasthole design, detonation network design, and charge design information, and then organizing them into an initial mathematical representation data set;

[0008] A three-dimensional tunnel model is constructed based on the tunnel sampling information, and the initial mathematical representation data set is substituted into the pre-trained tunnel blasting simulation model for simulation to obtain the initial tunnel blasting simulation results;

[0009] Based on the deviation analysis of the initial tunnel blasting simulation results and the expected tunnel blasting simulation results, it is determined whether to activate the blasting parameter optimization mechanism;

[0010] After the blasting parameter optimization mechanism is activated, a sensitivity analysis is first performed to find the first-step sensitive parameters, and then a cyclic analysis is performed until all sensitive parameters are found and summarized into a sensitive parameter group;

[0011] Based on the sensitive parameter group, a genetic algorithm is used to find the optimized parameter design data, and the optimized parameter design data is used to replace the corresponding initial parameter design data in the initial mathematical representation data set to obtain the optimized mathematical representation data set.

[0012] In a preferred embodiment, deviation analysis refers to:

[0013] The tunnel 3D model is divided into multiple 3D areas. The blasting instantaneous pressure data, displacement data, and crushing area range data of each 3D area are obtained respectively, as well as the blasting instantaneous pressure data, displacement data, and crushing area range data in the expected tunnel blasting simulation results of each area. The corresponding data items are difference calculated, and the results of the difference calculation are processed with absolute values ​​to obtain three types of absolute values ​​corresponding to the blasting instantaneous pressure, displacement, and crushing area range. The three types of absolute values ​​are weighted and summed to obtain a comprehensive deviation value.

[0014] In a preferred embodiment, determining whether to activate the blasting parameter optimization mechanism refers to:

[0015] The maximum value of all comprehensive deviation values ​​is extracted and then compared with the preset activation threshold. If the maximum value of all comprehensive deviation values ​​is greater than the preset activation threshold, an abnormal signal is generated. If the maximum value of all comprehensive deviation values ​​is less than or equal to the preset activation threshold, a normal signal is generated. When an abnormal signal is generated, the blasting parameter optimization mechanism is activated.

[0016] In a preferred embodiment, performing sensitivity analysis refers to:

[0017] Single-factor analysis is used to obtain the degree of influence of each individual parameter factor on the simulation results in the simulation model, and then compared with the preset first gradient sensitivity threshold. All individual parameter factors greater than the preset first gradient sensitivity threshold are retained and used as the first-step sensitive parameters.

[0018] In a preferred embodiment, the cycle analysis is performed using the Sobol method or the Morris method.

[0019] In a preferred embodiment, the judgment logic using the Sobol method or the Morris method is as follows: obtain the total number of first-step sensitive parameters and the acceptance time limit of the loop analysis, then substitute the total number of first-step sensitive parameters and the acceptance time limit of the loop analysis as input variables, use the type of method used in the loop analysis as the output variable, fuzzify the input variables, convert the values ​​of the input variables into fuzzy sets, fuzzify the output variables, convert the output variables into fuzzy sets, formulate fuzzy rules, describe the adaptability of the two methods under different data type combinations, reason with the fuzzified input variables through fuzzy rules, and judge the type of method used in the loop analysis.

[0020] In a preferred embodiment, during the cyclic analysis, all the next-step sensitive parameters are found in each cycle, and an interaction effect threshold corresponding to each step is preset. In each cycle, the parameter corresponding to the maximum value of the interaction effect of the sensitive parameter of the previous step is obtained, and then the parameter corresponding to the maximum value of the interaction effect of the sensitive parameter of the previous step is compared with the interaction effect threshold corresponding to the next step. If the parameter corresponding to the maximum value of the interaction effect of the sensitive parameter of the previous step is greater than the interaction effect threshold corresponding to the next step, the parameter corresponding to the maximum value of the interaction effect is determined as the sensitive parameter of the next step. This cycle is repeated until all sensitive parameters are found and summarized into a sensitive parameter group.

[0021] In a preferred embodiment, when a genetic algorithm is used to find optimized parameter design data, the fitness evaluation formula is used to obtain the inverse of the sum of all comprehensive deviation values ​​as the fitness evaluation value, and the maximum value of all comprehensive deviation values ​​is less than or equal to the preset activation threshold. The parameter data combination finally obtained by the optimal search is the optimized parameter design data.

[0022] Technical effects and advantages of the present invention:

[0023] The intelligent design of the present invention ensures a more accurate blasting process by automatically adjusting and selecting appropriate blasting parameters (such as charge amount, detonation time, etc.), thereby optimizing the intensity and range of blasting and reducing the impact of excessive or insufficient blasting. In tunnel construction, due to complex geological conditions and uncertain factors, blasting operations pose a high safety risk. The intelligent design method uses simulation technology to adjust the blasting design, thereby effectively avoiding accident risks and ensuring the safety of the construction process. Traditional blasting design often relies on manual experience and repeated debugging, resulting in waste of resources and increased time costs. The intelligent design optimization method can accurately adjust the blasting parameters and reduce unnecessary waste of blasting materials (such as explosives, detonating tubes, etc.). At the same time, the intelligent system can also optimize equipment and labor input, avoid secondary correction work caused by excessive or insufficient blasting, further reduce labor and equipment costs, and by improving construction efficiency, the intelligent design can also effectively shorten the construction period and reduce the overall cost of the project.

[0024] Blasting construction will cause environmental problems such as vibration and flying rocks, which may affect the ecological environment. Intelligent design can be controlled through precise blasting parameters. The present invention can adjust parameters such as the amount of explosives to avoid excessive vibration. Through precise design and control, intelligent design optimization of blasting parameters can not only ensure the quality of the project, but also meet the requirements of green construction, reduce interference with the surrounding environment, and improve the acceptability of construction personnel and the environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0026] Figure 1 This is a schematic diagram of the intelligent design and optimization method for blasting parameters of tunnels in complex strata in the present invention. DETAILED DESCRIPTION

[0027] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] Reference Figure 1 The following examples were obtained:

[0029] Example 1: Intelligent design optimization of tunnel blasting parameters in complex strata refers to the precise optimization of various parameters of tunnel blasting design (such as explosive quantity, blasting method, blasting time, etc.) through intelligent technology under complex geological conditions to achieve efficient, safe and economical tunnel construction.

[0030] Challenges of tunneling in complex strata: In tunneling projects in complex strata, geological conditions vary widely. Factors such as groundwater levels, rock types, and fault zones can affect blasting effectiveness. Traditional blasting parameter design relies on engineers' experience, which is prone to errors and inaccuracies, leading to increased construction risks or delays. To overcome these issues, the adoption of intelligent design methods is particularly important.

[0031] Advantages of Intelligent Design: Intelligent design optimization uses in-depth analysis of geological exploration data, combined with artificial intelligence and big data technologies, to accurately calculate the optimal value for each blasting parameter. Machine learning algorithms are trained on historical blasting data to predict and optimize blasting parameters, thus avoiding the empirical errors inherent in traditional design methods. Intelligently optimizing and adjusting parameters reduces construction costs and improves safety.

[0032] Blasting parameters refer to the key parameters that need to be set during the tunnel blasting process, such as explosive type, explosive quantity, blasting time interval, charging depth, blasting method, etc. These parameters are crucial to the blasting effect and the smooth progress of tunnel construction.

[0033] The intelligent design and optimization method of tunnel blasting parameters in complex strata includes the following steps:

[0034] The initial full-section blasthole design, blasting network design, and charge design information are obtained and organized into an initial mathematical representation dataset; this process is the starting point of the entire optimization process. By collecting and organizing tunnel blasting design information (such as blasthole layout, blasting sequence, and charge), and converting it into mathematical data representation, an initial dataset for the optimization process is constructed. This data will be used in subsequent simulations and optimization calculations. This ensures a clear starting point for the optimization process and provides a standardized data format for subsequent calculations.

[0035] Based on the tunnel sampling information, a 3D tunnel model is constructed. The initial mathematical representation dataset is then fed into a pre-trained tunnel blasting simulation model to generate initial tunnel blasting simulation results. Constructing a 3D tunnel model using the tunnel sampling information more realistically simulates the tunnel's actual geological and physical environment. The initial design data is then fed into the trained blasting simulation model to perform a blasting simulation, yielding preliminary blasting results (such as blasting range). These simulation results provide a basis for subsequent analysis and optimization, and are crucial for determining whether the blasting results meet expectations.

[0036] Based on the initial tunnel blasting simulation results and the expected tunnel blasting simulation results, a deviation analysis is performed to determine whether to activate the blasting parameter optimization mechanism. By comparing the simulation results with the expected results, the effectiveness of the current design is evaluated. If there is a large deviation between the two, it indicates that the current blasting parameter design may be suboptimal and requires further optimization. This step determines whether to enter the optimization phase and is key to determining whether to activate the optimization mechanism.

[0037] After the blasting parameter optimization mechanism is activated, a sensitivity analysis is first performed to find the first-step sensitive parameters, and then a cyclic analysis is performed until all sensitive parameters are found and summarized into a sensitive parameter group. The purpose of the sensitivity analysis is to find the parameters that have the greatest impact on the blasting effect. Through the sensitivity analysis of each design parameter, it is gradually determined which parameters have a greater impact on the changes in the tunnel blasting effect, and then a group of sensitive parameters are screened out. These parameters will become the key objects of optimization, helping to narrow the optimization scope, focus on the most influential parameters, and improve optimization efficiency and accuracy. The cyclic analysis is to find other parameters with a large degree of interactive influence involved in the optimization process of the first-step sensitive parameters, and perform joint subsequent optimization to avoid excessive impact on other parameters with a large degree of interactive influence caused by optimizing only the first-step sensitive parameters. Finding all sensitive parameters and summarizing them into a sensitive parameter group can complete the overall optimization at one time.

[0038] Based on the sensitive parameter group, a genetic algorithm is used to find optimized parameter design data. This optimized parameter design data is then added to the initial mathematical representation data set, replacing the corresponding initial parameter design data to obtain the optimized mathematical representation data set. The genetic algorithm is an effective global optimization algorithm that can find the optimal solution among a large number of possible parameter combinations. By optimizing the sensitive parameter group through the genetic algorithm, a new set of blasting parameters can be generated. These optimized parameters are expected to make the blasting effect closer to the expected one. This step optimizes the sensitive parameters through the genetic algorithm to ensure that the blasting design is more in line with actual needs. The optimized parameters will replace the original parameters to form the final optimized design data set, completing the design optimization.

[0039] Deviation analysis means dividing the tunnel 3D model into multiple 3D regions, obtaining the blasting instantaneous pressure data, displacement data, and crushing area range data for each 3D region, as well as the blasting instantaneous pressure data, displacement data, and crushing area range data from the expected tunnel blasting simulation results for each region, performing difference calculations on the corresponding data items, and performing absolute value processing on the difference calculation results to obtain three types of absolute values ​​corresponding to the blasting instantaneous pressure, displacement, and crushing area range. These three types of absolute values ​​are weighted and summed to obtain a comprehensive deviation value. The specific steps are as follows:

[0040] Model division and data collection: First, the tunnel 3D model was divided into multiple 3D regions. Within each region, instantaneous pressure data, displacement data, and crushing area data obtained during the actual blasting process were collected.

[0041] Simulation data acquisition: Through tunnel blasting simulation, the expected instantaneous pressure data, displacement data and crushing area range data of each area are obtained.

[0042] Difference calculation: Compare the actual data with the simulation data and calculate the difference of each data (pressure, displacement, crushing area).

[0043] Absolute value processing: Take the absolute value of the calculated difference to ensure that the deviation value is not affected by the sign.

[0044] Weighted summation: Different weights are assigned according to the importance of different data items, and the three types of absolute values ​​(pressure, displacement, and crushing area) are weighted summed to obtain a comprehensive deviation value.

[0045] Deviation analysis can be used to quantitatively evaluate the difference between tunnel blasting simulation results and expected blasting results, thereby judging the accuracy of the input data of the simulation model. If the deviation is large, it can reveal problems with the design parameters of the simulation model, providing a basis for subsequent design optimization and adjustment. By in-depth analysis of deviations in different areas, we can better understand the abnormal phenomena that may occur during the blasting process, thereby providing a more accurate reference for the actual construction process and avoiding potential safety risks. Deviation analysis can also serve as a feedback mechanism to gradually improve the quality and effectiveness of blasting projects through continuous monitoring and correction.

[0046] Determining whether to activate the blasting parameter optimization mechanism means: extracting the maximum value of all comprehensive deviation values, and then comparing it with the preset activation threshold. If the maximum value of all comprehensive deviation values ​​is greater than the preset activation threshold, an abnormal signal is generated. If the maximum value of all comprehensive deviation values ​​is less than or equal to the preset activation threshold, a normal signal is generated. When an abnormal signal is generated, the blasting parameter optimization mechanism is activated.

[0047] The maximum value of the comprehensive deviation values ​​for each three-dimensional region during the tunnel blasting process (calculated by comparing actual data with simulated data) is extracted. This maximum value reflects the location with the greatest deviation within each region. This maximum deviation value is then compared with a pre-set activation threshold. This threshold is typically determined through experience, experimental data, or design requirements, and represents the maximum tolerance for deviation.

[0048] If the maximum deviation value is greater than the activation threshold, it indicates a significant deviation in the blasting process, potentially affecting blasting effectiveness or safety, and the system generates an abnormal signal. If the maximum deviation value is less than or equal to the activation threshold, the blasting effect is within an acceptable range, and the system generates a normal signal. When an abnormal signal is generated, the blasting parameter optimization mechanism is automatically triggered to make adjustments and optimizations, such as modifying blasting charge quantity, delay control, and blasthole layout, to reduce deviation and improve blasting accuracy and effectiveness.

[0049] This mechanism monitors deviations during the blasting process in real time and automatically determines whether blasting parameters need to be adjusted based on the magnitude of the deviation. This automated feedback and adjustment mechanism promptly identifies problems during the blasting process and initiates optimization measures, avoiding delays caused by human intervention. Excessive deviations may indicate problems in the blasting design or implementation, potentially leading to blasting failure, geological disasters, or structural damage. By activating the optimization mechanism when deviations are excessive, potential safety hazards can be avoided and the safety of the blasting process can be ensured. Adjusting blasting parameters can optimize blasting results, making the blasting process more precise and efficient, avoiding resource waste and multiple blasting attempts, and improving tunnel excavation efficiency. Optimizing blasting parameters avoids unnecessary adjustments and effectively reduces additional costs caused by deviations during the blasting process, such as re-blasting and repair work. Adjusting blasting parameters ensures efficient and stable tunnel excavation, thereby improving the quality of the entire tunnel project and enhancing the controllability of blasting operations in complex geological conditions.

[0050] Performing sensitivity analysis means: using single factor analysis to obtain the degree of influence of each individual parameter factor on the simulation results in the simulation model, and then comparing it with the preset first gradient sensitivity threshold, retaining all individual parameter factors greater than the preset first gradient sensitivity threshold and using them as the first step sensitivity parameters.

[0051] Single factor analysis (also known as "single factor sensitivity analysis") is a common method of sensitivity analysis. It analyzes the impact of changes in one input parameter on the model output while ignoring changes in other input parameters. This helps understand how changes in a single factor affect the results of the system or model. Steps of single factor analysis:

[0052] Define input parameter ranges: Determine the possible range of each input parameter, usually setting the minimum and maximum values ​​of the parameter based on actual data or domain knowledge.

[0053] Varying a single input parameter: Keeping all other parameters fixed, change the value of only one input parameter and observe the changes in the model output. This method helps identify how a single input parameter affects the output.

[0054] Record output changes: Record the output results after each parameter change. The relationship between different input values ​​and output results can be displayed in tables, graphs, etc.

[0055] Calculate sensitivity metrics: For example, you can calculate the first gradient (the ratio of the change in the output to the change in the parameter) to quantify the impact of the input parameter change on the output. A larger gradient indicates that the input parameter has a greater impact on the model results.

[0056] Comparison with a Threshold: Each input parameter's sensitivity is compared against a preset sensitivity threshold (e.g., the first-step sensitivity threshold) to identify those parameters with the greatest impact on the output. These parameters are referred to as "first-step sensitive parameters." By varying each input parameter individually and observing the changes in the output, the importance of each parameter is measured. Sensitivity analysis can help identify which parameters significantly influence simulation results and inform informed decisions or optimizations.

[0057] The Sobol method or the Morris method is used for loop analysis. The Sobol method is a global sensitivity analysis method based on variance decomposition, which is used to evaluate the main effects (the influence of a single parameter) and interaction effects (the impact of the interaction between multiple parameters on the output) of input variables. It quantifies the impact of each parameter on the result by decomposing the output variance into the contributions of each input parameter and their combination. The core idea of ​​the Sobol method is to decompose the variance of the model output (that is, the variability of the output) into the independent contributions of each input variable and their interaction contributions. By calculating the "contribution share" of each input variable, it is possible to determine which variables have the greatest impact on the model results.

[0058] The Sobol method quantifies the impact of each parameter on the output by calculating its sensitivity index (SobolIndex): the main effect Sobol index Si represents the contribution ratio of the input variable xi to the model output variance, while the interaction effect Sobol index Sij represents the contribution ratio of the interactive contribution of xi and xj to the output to the model output variance. xi and xj represent the variables corresponding to index numbers i and j respectively. In the circular analysis, the main effect Sobol index Si is the sensitive parameter of the previous step, such as the second-step sensitive parameter. If the input variable xj in the interaction effect Sobol index Sij corresponding to the maximum value at this time is greater than the interaction effect threshold corresponding to the third step, then the input variable xj is the third-step sensitive parameter.

[0059] The Morris method is a local sensitivity analysis method used to evaluate the relative impact of model input parameters on output. It calculates the contribution of each input variable to the change in model output by "jumping" the value of the input variable, and evaluates sensitivity based on these contributions. The Morris method is particularly suitable for high-dimensional problems and requires less computation than the Sobol method. The Morris method can be a combination of input variables. For example, one of the combinations is a known second-order sensitive parameter xi, and the other is another parameter. The other parameters are ranked according to the final result. If the interaction effect of the first-ranked parameter xj is greater than the interaction effect threshold corresponding to the third order, then the first-ranked parameter xj is the third-order sensitive parameter corresponding to this second-order sensitive parameter. If the interaction effect of the first-ranked parameter xj is less than or equal to the interaction effect threshold corresponding to the third order, then the known second-order sensitive parameter xi does not have a corresponding third-order sensitive parameter.

[0060] A more detailed example: In the standard Morris method, main effects only reflect the impact of a single variable on the output, while interaction effects reveal the joint impact of two variables. To analyze combinations of input variables, the following steps can be taken: Select a combination of input variables: Assume there are multiple variables, a known second-order sensitivity parameter xi, and another variable xj. To assess the joint sensitivity of these two variables, consider creating variable combinations (xi, xj) and then analyzing the impact of these combinations on the output. A common strategy is to assess the sensitivity of a variable combination (xi, xj) by generating values ​​for the combination using the Latin Hypercube (LHS) method or another suitable sampling method. For each variable combination (xi, xj), the interaction effect reflects the impact of the combined change of the two variables on the simulation model output. This can be done by constructing a multivariate regression model for the variable combination (xi, xj) and then using least squares regression to estimate the coefficients of each variable and its interaction term. The coefficient of the interaction term represents the degree of influence of the combined change of the two variables on the model output. The simulation model output is defined as the sum of all combined deviations.

[0061] The judgment logic using the Sobol method or the Morris method is:

[0062] Obtain the total number of first-step sensitive parameters and the acceptance time limit of the loop analysis, then substitute the total number of first-step sensitive parameters and the acceptance time limit of the loop analysis as input variables, use the type of method used in the loop analysis as the output variable, perform fuzzy processing on the input variables, convert the values ​​of the input variables into fuzzy sets, perform fuzzy processing on the output variables, convert the output variables into fuzzy sets, formulate fuzzy rules, describe the adaptability of the two methods under different data type combinations, reason with the fuzzified input variables through fuzzy rules, and determine the type of method used in the loop analysis.

[0063] Input variables: The total number of first-order sensitivity parameters: This is an indicator to measure the degree of influence of the model input variables on the output. Generally, the more the number, the greater the sensitivity of the model input variables to the output.

[0064] Acceptance limit for loop analysis: This refers to the upper limit on the computational or runtime for a sensitivity analysis. A shorter time limit may require the selection of a more computationally efficient method, while a longer time limit may allow the use of a more computationally intensive method. The two input variables will be fuzzified. The purpose of fuzzification is to convert these two variables, which have definite values, into fuzzy sets, thereby addressing uncertainty and ambiguity. For example, the "total number of first-order sensitivity parameters" might be converted into the following fuzzy sets: Low: for example, 0–10; Moderate: for example, 10–50; High: for example, 50 or more. Similarly, the acceptance limit for the loop analysis might be fuzzified to: Short: for example, 0–10 hours; Moderate: for example, 10–50 hours; Long: for example, 50 or more hours.

[0065] Output variable definition and fuzzification: The output variable refers to the method to be selected in the decision process, usually the Sobol method or the Morris method. We also fuzzify this output variable. Possible fuzzy sets include the Sobol method and the Morris method.

[0066] The fuzzification of output variables can be classified as follows: Preferred: This means that a certain method is more suitable under given conditions. Moderate: This means that the difference between the two methods is not significant and can be chosen. Not applicable: This means that a certain method has poor adaptability under given conditions.

[0067] Fuzzy rule formulation: Fuzzy rules are used to describe the degree of compatibility between two methods under different combinations of input variables. These rules are constructed based on experience or expert judgment. For example, the rules can be as follows:

[0068] Rule 1: If the "Number of First-Order Sensitivity Parameters" is "Few" and the "Acceptance Time Limit" is "Short", then the output is "Prefer Morris Method". Rule 2: If the "Number of First-Order Sensitivity Parameters" is "Moderate" and the "Acceptance Time Limit" is "Moderate", then the output is "Moderately choose Sobol Method and Morris Method". Rule 3: If the "Number of First-Order Sensitivity Parameters" is "Many" and the "Acceptance Time Limit" is "Long", then the output is "Prefer Sobol Method".

[0069] Fuzzy reasoning: The fuzzy reasoning process is based on fuzzy rules and fuzzy sets. In this process, the input variables (the number of first-order sensitivity parameters and the acceptance time limit after fuzzification) are reasoned through fuzzy rules to derive the output variables (i.e., the applicable method). The specific steps are as follows:

[0070] Input fuzzification: The actual numerical input is mapped to a fuzzy set through a membership function. For example, if the number of first-order sensitivity parameters is 30, its membership in the "moderate" fuzzy set may be 0.7 and its membership in the "few" set may be 0.3.

[0071] Rule-based reasoning: Fuzzy rules are used for reasoning. Through reasoning, we can obtain the membership degree of each possible output. For example, if the inputs are a "moderate" number of sensitivity parameters and a "short" acceptance time limit, the rule might infer that the output method is "a moderate selection of the Sobol method and the Morris method," with a membership degree of 0.8.

[0072] Defuzzification: Based on the inference results, the fuzzy output is converted into a specific choice. For example, defuzzification methods such as the centroid method can be used to arrive at the final choice.

[0073] Ultimately, the results of fuzzy reasoning can determine the most appropriate loop analysis method (Sobol method or Morris method) for a given input condition. This method not only considers the numerical value of the input variable, but also takes into account uncertainty and fuzziness, making decision-making more flexible and intelligent.

[0074] During a cyclic analysis, all sensitive parameters for the next step are identified in each iteration. A threshold for the interaction effect is preset for each step. During each iteration, the parameter corresponding to the maximum interaction effect of the previous step's sensitive parameters is obtained. The parameter corresponding to this maximum interaction effect is then compared with the interaction effect threshold for the next step. If the parameter corresponding to the maximum interaction effect of the previous step's sensitive parameters is greater than the interaction effect threshold for the next step, the parameter corresponding to this maximum interaction effect is determined as the sensitive parameter for the next step. This cycle continues until all sensitive parameters are found and summarized into a sensitive parameter group. It should be noted that during cyclic analysis, sensitive parameters that have already been screened out should be excluded to avoid cyclic pressure and can be summarized at the end. By gradually analyzing the sensitivity parameters of each step, the most influential and critical parameters at each stage can be more accurately identified. The "sensitive parameters" for each stage are those factors with significant interaction effects in that stage. This approach ensures that the identified parameters are not based solely on the changes in a single factor but rather considers the interactions between multiple parameters, allowing for a more comprehensive assessment of the impact of each parameter. Each iteration compares the results against an "interaction effect threshold" to ensure that the selected sensitive parameters meet certain criteria for significance. The introduction of a threshold helps reduce the influence of redundant factors, retaining only those sensitive parameters that significantly impact system output and preventing the final analysis results from being skewed by excessive interference from irrelevant factors. The phased, iterative analysis allows for more targeted and logical selection of sensitive parameters at each stage. Each round of selection is based on the results of the previous round of analysis. This approach accumulates and gradually filters out unimportant parameters, ensuring more refined and accurate sensitive parameter selection at each step. Ultimately, after multiple rounds of screening and analysis, a set of all sensitive parameters is compiled. This method systematically identifies sensitive parameters across multiple stages or interactions, providing a precise basis for decision-making. It is particularly applicable to complex systems with multiple interacting factors, where step-by-step analysis is required to identify the interactions between these factors and their impact on system behavior. This step-by-step process of screening sensitive parameters has significant practical value in the field of multi-parameter optimization.

[0075] When using a genetic algorithm to find optimized parameter design data, the fitness evaluation formula uses the inverse of the sum of all integrated deviations as the fitness evaluation value. The maximum value of all integrated deviations must be less than or equal to a preset activation threshold. The resulting parameter data combination is then considered the optimized parameter design data. To ensure solution quality, an activation threshold is typically set: the maximum value of all integrated deviations must be less than or equal to the preset activation threshold. This activation threshold ensures that the optimized solution does not exhibit excessive error, thus preventing solutions that deviate excessively from the target. For example, if the maximum deviation exceeds the activation threshold, the solution does not meet the design requirements or quality standards and should not be selected as the winner in the genetic algorithm. Genetic algorithms gradually optimize parameter design data by simulating the process of natural selection. In each generation, the algorithm performs selection, crossover, and mutation operations based on the fitness of individuals, generating a new population. Individuals with higher fitness (i.e., parameter combinations with smaller integrated deviations) are more likely to be selected for the next generation. Through multiple generations of iteration, the resulting parameter combination meets the activation threshold and minimizes the sum of all integrated deviations, resulting in the optimized parameter design data. Through the genetic algorithm's optimization process, parameter design can be effectively adjusted to ensure that the final solution meets the set performance requirements. The fitness evaluation formula uses the inverse of all integrated deviation values ​​and controls the quality of the results through activation thresholds, ensuring that the optimization results are not only optimal in theory but also feasible and meet the requirements in practical applications.

[0076] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0077] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0078] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0079] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0080] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. Intelligent design and optimization method for tunnel blasting parameters in complex strata, characterized by: The following steps are involved: Obtaining initial full-section blasthole design, detonation network design, and charge design information, and then organizing them into an initial mathematical representation data set; A three-dimensional tunnel model is constructed based on the tunnel sampling information, and the initial mathematical representation data set is substituted into the pre-trained tunnel blasting simulation model for simulation to obtain the initial tunnel blasting simulation results; Based on the deviation analysis of the initial tunnel blasting simulation results and the expected tunnel blasting simulation results, it is determined whether to activate the blasting parameter optimization mechanism; After the blasting parameter optimization mechanism is activated, a sensitivity analysis is first performed to find the first-step sensitive parameters, and then a cyclic analysis is performed until all sensitive parameters are found and summarized into a sensitive parameter group; Based on the sensitive parameter group, a genetic algorithm is used to find the optimized parameter design data, and the optimized parameter design data is used to replace the corresponding initial parameter design data in the initial mathematical representation data set to obtain the optimized mathematical representation data set.

2. The intelligent design and optimization method for complex stratum tunnel blasting parameters according to claim 1 is characterized in that: Deviation analysis refers to: The tunnel 3D model is divided into multiple 3D areas. The blasting instantaneous pressure data, displacement data, and crushing area range data of each 3D area are obtained respectively, as well as the blasting instantaneous pressure data, displacement data, and crushing area range data in the expected tunnel blasting simulation results of each area. The corresponding data items are difference calculated, and the results of the difference calculation are processed with absolute values ​​to obtain three types of absolute values ​​corresponding to the blasting instantaneous pressure, displacement, and crushing area range. The three types of absolute values ​​are weighted and summed to obtain a comprehensive deviation value.

3. The intelligent design and optimization method for tunnel blasting parameters in complex strata according to claim 2 is characterized in that: Determining whether to activate the blasting parameter optimization mechanism refers to: The maximum value of all comprehensive deviation values ​​is extracted and then compared with the preset activation threshold. If the maximum value of all comprehensive deviation values ​​is greater than the preset activation threshold, an abnormal signal is generated. If the maximum value of all comprehensive deviation values ​​is less than or equal to the preset activation threshold, a normal signal is generated. When an abnormal signal is generated, the blasting parameter optimization mechanism is activated.

4. The intelligent design and optimization method for complex stratum tunnel blasting parameters according to claim 3 is characterized in that: Conducting a sensitivity analysis means: Single-factor analysis is used to obtain the degree of influence of each individual parameter factor on the simulation results in the simulation model, and then compared with the preset first gradient sensitivity threshold. All individual parameter factors greater than the preset first gradient sensitivity threshold are retained and used as the first-step sensitive parameters.

5. The intelligent design and optimization method for complex stratum tunnel blasting parameters according to claim 4 is characterized in that: The Sobol method or Morris method was used for the circular analysis.

6. The intelligent design and optimization method for complex stratum tunnel blasting parameters according to claim 5 is characterized in that: The judgment logic using the Sobol method or the Morris method is: Obtain the total number of first-step sensitive parameters and the acceptance time limit of the loop analysis, then substitute the total number of first-step sensitive parameters and the acceptance time limit of the loop analysis as input variables, use the type of method used in the loop analysis as the output variable, perform fuzzy processing on the input variables, convert the values ​​of the input variables into fuzzy sets, perform fuzzy processing on the output variables, convert the output variables into fuzzy sets, formulate fuzzy rules, describe the adaptability of the two methods under different data type combinations, reason with the fuzzified input variables through fuzzy rules, and determine the type of method used in the loop analysis.

7. The intelligent design and optimization method for tunnel blasting parameters in complex strata according to claim 6 is characterized in that: During the cyclic analysis, all the next-step sensitive parameters are found in each cycle. The interaction effect threshold corresponding to each step is preset. In each cycle, the parameter corresponding to the maximum interaction effect of the previous-step sensitive parameter is obtained, and then the parameter corresponding to the maximum interaction effect of the previous-step sensitive parameter is compared with the interaction effect threshold corresponding to the next step. If the parameter corresponding to the maximum interaction effect of the previous-step sensitive parameter is greater than the interaction effect threshold corresponding to the next step, the parameter corresponding to the maximum interaction effect is determined as the next-step sensitive parameter. This cycle is repeated until all sensitive parameters are found and summarized into a sensitive parameter group.

8. The intelligent design and optimization method for complex stratum tunnel blasting parameters according to claim 7 is characterized in that: When using a genetic algorithm to find optimized parameter design data, the fitness evaluation formula is used to obtain the inverse of the sum of all comprehensive deviation values ​​as the fitness evaluation value, and the maximum value of all comprehensive deviation values ​​is less than or equal to the preset activation threshold. The parameter data combination finally obtained by the optimal search is the optimized parameter design data.

Images