A tunnel blasting vibration velocity prediction method and system integrating multi-factor intelligent optimization

Abstract

The present invention belongs to the technical field of intelligent tunnel engineering, and discloses a tunnel blasting vibration velocity prediction method and system integrating multi-factor intelligent optimization. The method collects blasting parameters and historical vibration monitoring data; constructs a data set containing multi-factor features, initializes the hyperparameters of XGBoost and uses the SSA algorithm to iteratively optimize the XGBoost hyperparameters, inputs the training set data to train the optimized SSA-XGBoost model, uses the test set to verify the model performance and compares the prediction performance of the traditional model; dynamically adjusts the single-section charge parameter in real time according to the predicted value, combines the safety threshold to generate a risk warning, and realizes the closed-loop optimization of the blasting design. The present invention combines the safety threshold and the SSA-XGBoost model to generate a real-time risk warning, and realizes the closed-loop optimization of the blasting design by dynamically adjusting the blasting parameters, which improves the construction efficiency while ensuring the construction safety.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent tunnel engineering, and in particular relates to a tunnel blasting vibration velocity prediction method and system integrating multi-factor intelligent optimization. Background Art

[0002] In the field of tunnel engineering, blasting vibration velocity control is the core link to ensure construction safety, structural stability of surrounding buildings, and quality of life of surrounding residents. Among them, effective prediction of vibration velocity peak is of utmost importance. In the past, the prediction methods used mainly relied on the traditional empirical formula-Sadovsky formula or a single machine learning model, which easily caused problems such as poor parameter generalization and inability to reflect the influence of multi-factor coupling. In addition, there are predictions through numerical simulation calculations. This method is highly complex and time-consuming, and it is difficult to adapt to the needs of actual engineering. Recently, machine learning technology has been gradually applied to the engineering field, such as BP neural network, support vector machine, etc., but its prediction accuracy is often limited by the single model structure and insufficient parameter optimization, especially the lack of dynamic correlation analysis under multi-factor coupling, and the failure to fully utilize intelligent algorithms to optimize model performance, resulting in overfitting or underfitting.

[0003] The XGBoost algorithm, with its integrated advantage of gradient boosting decision trees, shows excellent prediction efficiency and accuracy in nonlinear data modeling. However, the performance of the model depends largely on the setting of hyperparameters. Traditional hyperparameter optimization methods are difficult to find the global optimal solution. The Sparrow Search Algorithm (SSA), as a new type of swarm intelligence optimization algorithm, simulates the foraging behavior of biological groups to build a heuristic search strategy. It has powerful global search capabilities and fast convergence characteristics, and can effectively optimize the hyperparameters of the XGBoost model. This fusion strategy not only significantly reduces the deviation of artificial parameter adjustment, but also provides high-precision intelligent decision support for blasting vibration control. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the disclosed embodiment of the present invention provides a tunnel blasting vibration velocity prediction method and system integrating multi-factor intelligent optimization, and specifically relates to an XGBoost tunnel blasting vibration velocity peak intelligent prediction method and system based on SSA optimization.

[0005] The technical solution is as follows: A tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization comprises the following steps:

[0006] S1, collect blasting parameters and historical vibration monitoring data. Blasting parameters include maximum single-stage charge, blasting center distance, drilling depth and rock compressive strength;

[0007] S2. Normalize the data and construct a dataset containing multi-factor features, which includes a training set, a validation set, and a test set. The ratio of the training set, validation set, and test set is 8:1:1;

[0008] S3. Initialize the XGBoost hyperparameters and use the SSA algorithm to iteratively optimize the XGBoost hyperparameters to complete the construction of the SSA-XGBoost model;

[0009] S4. Input the training set data to train the optimized SSA-XGBoost model, use the test set to verify the model performance and compare the prediction performance of the traditional model;

[0010] S5. Dynamically adjust the single-section charge parameter in real time according to the predicted value, generate a risk warning in combination with the safety threshold, and realize the closed-loop optimization of the blasting design.

[0011] In step S1, collect blasting parameters and historical vibration monitoring data, including: in multi-source data collection, for blasting vibration monitoring, use a blasting vibration meter to simultaneously measure three components perpendicular to each other of the particle vibration, and perform vector synthesis on the vibration velocity components in three directions to obtain the total vibration velocity , which is used as the output variable for model training. The calculation formula is:

[0012] ;

[0013] In the formula, is the maximum radial component of the vibration velocity, is the maximum tangential component of the vibration velocity, is the maximum vertical component of the vibration velocity.

[0014] In step S3, initialize the XGBoost hyperparameters, including:

[0015] The objective function of XGBoost consists of a loss function and a regularization term. The formula is:

[0016] ;

[0017] In the formula, is the objective function of XGBoost, is the loss function of the model bias, is the actual value, is the predicted value, is the total number of samples in the dataset, is the regularization term of the th tree, is the total number of trees,

[0018] Introduce Elastic Net regularization, which combines L1 and L2 regularization, then we have:

[0019] ;

[0020] In the formula, is the parameter to control the tree structure, is the number of leaf nodes, is the weight of the first leaf node, is the weight of the second leaf node, is the set composed of the scores of the leaf nodes of each tree, is the L1 norm, is the L2 norm;

[0021] L1 regularization automatically selects the blast center distance and maximum charge characteristics in the blast parameters, and L2 regularization prevents the model from overfitting;

[0022] ;

[0023] In the formula, is the objective function value at the th step, is the sum of the predicted values of the first trees, is the predicted value of the regression tree.

[0024] Furthermore, use the SSA algorithm to iteratively optimize the XGBoost hyperparameters, including:

[0025] Define the parameters for optimizing the XGBoost model, including the number of iterations n_estimators, the maximum depth max_depth, and the learning rate learning_rate;

[0026] Set the parameters of the sparrow search algorithm, including the number of sparrows and the maximum number of iterations, and define the fitness function;

[0027] Simulate the foraging process and update the positions of the discoverers, followers, and vigilant ones;

[0028] The calculation formula for updating the position of the discoverer is:

[0029] ;

[0030] In the formula, is the position information of the th sparrow in the th dimension, is the exponential function, is the number of iterations; is a random value, ; is the maximum number of iterations, is the warning value, ; is a random number that follows a standard normal distribution, is a dimensional matrix with a value of 1; is the safety threshold, ;

[0031] When it means that the discoverer is searching in a safe position;

[0032] When it means that the discoverer has been discovered by the predator and needs to fly to other safe positions to search.

[0033] Furthermore, the calculation formula for updating the position of the follower is:

[0034] ;

[0035] In the formula, is the exponential function, is the global worst position, is the number of sparrows, is the current best position where the discoverer is located; is a dimensional vector, and the value of each element is randomly -1 or 1;

[0036] When it represents that the foraging situation of the th follower is not ideal and the position needs to be updated;

[0037] When the follower can move to the best position.

[0038] Furthermore, the calculation formula for updating the position of the vigilant is:

[0039] ;

[0040] In the formula, is the current best position, is a random number that follows a standard normal distribution; is a random number, ; is the fitness value of the current sparrow individual, and are the current global best and worst fitness values respectively, is the minimum constant used to avoid a zero denominator.

[0041] In step S4, for the SSA-XGBoost model, the root mean square error RMSE, mean absolute error MAE, and coefficient of determination R 2 are used for evaluation.

[0042] In step S5, the safety threshold is determined by introducing geological feature variables and combining with Sadovsky's empirical formula to determine the safety threshold of blasting vibration velocity. The safety threshold formula is as follows:

[0043] ;

[0044] In the formula, is the vibration velocity safety threshold, is the coefficient determined according to geological conditions and blasting experience, is the maximum charge per delay, is the distance from the blast center, is the weight coefficient of geological features, is the normalization function of the fracture density geological feature;

[0045] ;

[0046] In the formula, is the normalization function based on rock hardness, is the normalization function based on fracture density.

[0047] In step S5, the closed-loop optimization of blasting design is realized, including: predicting the vibration velocity of the future construction section through the trained SSA-XGBoost model to optimize the blasting parameters, and simultaneously monitoring and evaluating the blasting effect.

[0048] Another object of the present invention is to provide a tunnel blasting vibration velocity prediction system integrating multi-factor intelligent optimization. This system implements the tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization. This system includes:

[0049] A multi-source data acquisition module for collecting blasting parameters and historical vibration monitoring data. The blasting parameters include the maximum charge per delay, the distance from the blast center, the drilling depth, and the rock compressive strength;

[0050] A data preprocessing module for normalizing the data and constructing a dataset containing multi-factor features. This dataset includes a training set, a validation set, and a test set. Among them, the ratios of the training set, the validation set, and the test set are 8:1:1;

[0051] An SSA-XGBoost model building module for iteratively optimizing the XGBoost hyperparameters using the SSA algorithm to complete the construction of the SSA-XGBoost model;

[0052] The model training and validation module is used to input the training set data to train the optimized SSA-XGBoost model, verify the model performance using the test set and compare the prediction performance of traditional models;

[0053] The engineering application module is used to dynamically adjust the single-section charge parameter in real time according to the predicted value, generate a risk warning in combination with the safety threshold, and realize the closed-loop optimization of the blasting design.

[0054] Combining all the above technical solutions, the beneficial effects of the present invention are as follows: The present invention combines the global optimization ability of the sparrow search algorithm (SSA) and the powerful prediction ability of XGBoost through the SSA-XGBoost model, effectively captures the complex relationships between data. In the test set, the R² value of the SSA-XGBoost model reaches 0.973, showing a significant improvement compared with traditional BP neural network (R² = 0.819) and BP-PSO (R² = 0.926). It proves that it can effectively improve the prediction accuracy of blasting vibration velocity.

[0055] The SSA-XGBoost model in the present invention shows good robustness under different data volumes and data distributions. Even when the data volume is small or the data distribution is uneven, it can still maintain a high prediction accuracy, while traditional models often show large errors. For example, in the test set, the MAE of SSA-XGBoost is 2.419, much lower than 5.112 of traditional BP and 2.503 of BP-PSO.

[0056] The present invention forms a new safety threshold formula by improving the Sadovsky empirical formula, and makes it applicable to the vibration velocity safety control under different geological conditions by introducing the geological feature vector. Combining the safety threshold and the SSA-XGBoost model to generate real-time risk warnings, and realizing the closed-loop optimization of the blasting design by dynamically adjusting the blasting parameters, which improves the construction efficiency while ensuring the construction safety.

[0057] The present invention effectively improves the construction safety and efficiency. Using SSA-XGBoost can achieve high-precision prediction of blasting vibration velocity, dynamically adjust parameters such as single-section charge, reduce the risk of vibration velocity exceeding the limit, reduce the impact on surrounding buildings and residents, and save potential compensation costs; compared with traditional numerical simulations, the working efficiency of this system is significantly improved, the blasting design cycle can be shortened and the labor cost can be reduced; the commercial value is applicable to blasting scenarios such as tunnel engineering and mine exploitation, and there is a clear market demand. Combining intelligent warning and closed-loop optimization can develop related hardware integration systems with high added value.

[0058] In existing research, SSA-XGBoost has been tried in many fields such as mechanics and medicine. However, in the prediction of tunnel blasting vibration velocity, for the first time, it combines multi-source data (geology, charge amount, distance from the blast center, etc.) with a dynamic closed-loop optimization mechanism to solve the problem that the traditional Sadovsky formula cannot quantify the coupling effect of multiple factors. The "prediction-monitoring-feedback" closed-loop mechanism of the present invention realizes the leap from static prediction to dynamic control, filling the technical gap in engineering practice.

[0059] The Sadovsky formula relies on empirical coefficients and cannot reflect the influence of multi-factor coupling (such as geological conditions, charge amount, distance from the blast center, etc.). The present invention considers multi-factor fusion to solve the problem of poor parameter generalization. Traditional models (such as BP neural network) are prone to overfitting when data is scarce (the MAE of the test set reaches 5.112). Through data normalization and SSA optimization, the present invention enables this model to maintain high accuracy (R²>0.97) even in small samples or unbalanced data.

[0060] Although SSA-XGBoost has been applied in other fields, its application in the field of tunnel blasting vibration velocity prediction is less and the effect is poor. Through specialized hyperparameter optimization (such as introducing features such as distance from the blast center and rock strength), the present invention verifies its feasibility and is significantly superior to traditional models (the RMSE of the test set drops from 4.276 to 3.362). Brief Description of the Drawings

[0061] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments in line with the present disclosure and used together with the specification to explain the principles of the present disclosure;

[0062] Figure 1 is a schematic diagram of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization provided by an embodiment of the present invention;

[0063] Figure 2 is a flowchart of the tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization provided by an embodiment of the present invention;

[0064] Figure 3 is a density map in the training set of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization provided by an embodiment of the present invention;

[0065] Figure 4 is a result map of the training set of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization provided by an embodiment of the present invention;

[0066] Figure 5It is the density map of the test set of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization provided by the embodiments of the present invention;

[0067] Figure 6 It is the result map of the test set of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization provided by the embodiments of the present invention;

[0068] Figure 7 It is the density map of the test set of the BP model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention;

[0069] Figure 8 It is the density map of the test set of the BP-PSO model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention;

[0070] Figure 9 It is the density map of the test set of the XGBoost model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention;

[0071] Figure 10 It is the density result map of the training set of the BP model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention;

[0072] Figure 11 It is the density result map of the training set of the BP-PSO model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention;

[0073] Figure 12 It is the density result map of the training set of the XGBoost model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention;

[0074] Figure 13 It is the schematic diagram of the tunnel blasting vibration velocity prediction system integrating multi-factor intelligent optimization provided by the embodiments of the present invention;

[0075] In the figure: 1. Multi-source data acquisition module; 2. Data preprocessing module; 3. SSA-XGBoost model building module; 4. Model training and verification module; 5. Engineering application module. Detailed implementation manners

[0076] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings. Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0077] The innovation of the present invention lies in: the present invention integrates the Sparrow Search Algorithm (SSA) into the XGBoost model, and uses its global search ability to optimize the hyperparameters of XGBoost (such as the number of iterations, learning rate, etc.), thereby improving the prediction accuracy; through multi-source data collection (blasting parameters, geological conditions, vibration monitoring data) and normalization processing, a highly generalized dataset is constructed to solve the problem of poor parameter generalization under the influence of multi-factor coupling. The SSA-XGBoost model still maintains a low error (MAE is only 2.419) in small samples or unbalanced data, and its robustness is better than that of traditional models; geological feature variables are introduced and combined with Sadovsky's empirical formula to improve the safety threshold, and the prediction results are combined with the safety threshold to generate risk warnings in real time, dynamically adjust parameters such as the charge amount per single section, and feedback the monitoring data to iteratively optimize the model, forming a closed-loop control of blasting design - prediction - monitoring - feedback, paying attention to construction safety while improving construction efficiency.

[0078] Example 1, as Figure 1 shown, the principle of the tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization provided by the embodiment of the present invention.

[0079] Specifically, as Figure 2 shown, the tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization provided by the embodiment of the present invention includes the following steps:

[0080] S1, Collect blasting parameters and historical vibration monitoring data. The blasting parameters include the maximum charge amount per single section, the distance from the blast center, the drilling depth, and the rock compressive strength;

[0081] S2, Perform normalization processing on the data to construct a dataset containing multi-factor features. This dataset includes a training set, a validation set, and a test set. Among them, the ratios of the training set, the validation set, and the test set are 8:1:1;

[0082] S3, Initialize the XGBoost hyperparameters, and use the SSA algorithm to iteratively optimize the XGBoost hyperparameters to complete the construction of the SSA-XGBoost model;

[0083] S4, Input the training set data to train the optimized SSA-XGBoost model, and use the test set to verify the model performance and compare the prediction performance of traditional models;

[0084] such as traditional BP neural network, BP-PSO model, and unoptimized XGBoost), evaluate prediction errors (MAE, RMSE, etc.) and the coefficient of determination (R 2 );

[0085] S5. Dynamically adjust the single-section charge parameter in real time according to the predicted value, generate a risk warning in combination with the safety threshold, and realize the closed-loop optimization of the blasting design.

[0086] In step S1, collect blasting parameters and historical vibration monitoring data, including: in multi-source data collection, conduct blasting vibration monitoring. Use a TC-4850 blasting vibration meter to simultaneously measure three components perpendicular to each other of the particle vibration, and perform vector synthesis on the vibration velocity components in three directions to obtain the total vibration velocity , which is used as the output variable for model training. The calculation formula is:

[0087] ;

[0088] In the formula, is the maximum radial component of the vibration velocity, is the maximum tangential component of the vibration velocity, is the maximum vertical component of the vibration velocity.

[0089] Exemplarily, in step S2, perform data normalization processing to standardize the data of the training set and the test set to 0-1, eliminating the influence caused by different magnitudes and dimensions of each variable. The division of the data set is in the ratio of training set: validation set: test set = 8:1:1;

[0090] Exemplarily, in step S3, initialize the XGBoost hyperparameters, including:

[0091] The basic principle of the XGBoost hyperparameters is that its objective function consists of a loss function and a regularization term, and its algorithm can be implemented according to the following formula:

[0092] ;

[0093] In the formula, is the objective function of XGBoost, is the loss function of the model deviation, is the actual value, is the predicted value, is the total number of samples in the data set, is the th tree's regularization term, is the total number of trees, is the base function;

[0094] Introduce Elastic Net regularization, combining L1 and L2 regularization:

[0095] ;

[0096] In the formula, is the parameter to control the tree structure, is the number of leaf nodes, is the weight of the first leaf node, is the weight of the second leaf node, is the set composed of the scores of the leaf nodes of each tree, is the L1 norm, is the L2 norm;

[0097] L1 regularization can automatically screen out key features in the blasting parameters (such as the distance from the blast center, the maximum charge, etc.), and L2 regularization can effectively prevent the model from overfitting.

[0098] ;

[0099] In the formula, is the objective function value at the th step, is the sum of the predicted values of the first trees, is the predicted value of the regression tree.

[0100] Exemplarily, in step S3, the SSA algorithm is used to iteratively optimize the XGBoost hyperparameters, including:

[0101] Define the parameters for optimizing the XGBoost model, such as the number of iterations (n_estimators), the maximum depth (max_depth), the learning rate (learning_rate), etc.;

[0102] Set the parameters of the sparrow search algorithm, including the number of sparrows, the maximum number of iterations, and define the fitness function;

[0103] Simulate the foraging process and update the positions of the discoverers, followers, and vigilant ones;

[0104] The calculation formula for updating the position of the discoverer is:

[0105] ;

[0106] In the formula, is the position information of the th sparrow in the th dimension, is the exponential function, is the number of iterations; is a random value, ; is the maximum number of iterations, is the warning value, ; is a random number that follows a standard normal distribution, is a -dimensional matrix with a value of 1; is the safety threshold, ;

[0107] When , it means that the discoverer is searching in a safe position;

[0108] When , it means that the discoverer has been discovered by the predator and needs to fly to other safe positions to search.

[0109] The calculation formula for updating the position of the follower is:

[0110] ;

[0111] In the formula, is the exponential function, is the global worst position, is the number of sparrows, is the current best position where the discoverer is located; is -dimensional vector, and the value of each element is randomly -1 or 1;

[0112] When , it represents that the foraging situation of the th follower is not ideal and the position needs to be updated;

[0113] When , the follower can move to the best position.

[0114] The calculation formula for updating the position of the vigilant is:

[0115] ;

[0116] In the formula, is the current best position, is a random number that follows a standard normal distribution; is a random number, ; is the fitness value of the current sparrow individual, and are the current global best and worst fitness values respectively, is the minimum constant used to avoid a zero denominator.

[0117] Exemplarily, for the model evaluation in step S4, the calculation formulas for root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) are as follows:

[0118] ;

[0119] ;

[0120] ;

[0121] In the formula: is the predicted value; is the true value; is the average value of the true values.

[0122] The specific performance indicators of the prediction model evaluated by these three indicators are shown in Table 1 below. The SSA-XGBoost model shows higher R² values and lower MAE and RMSE values on both the training set and the test set, proving its effectiveness in predicting blasting vibration velocity.

[0123] Table 1 Performance indicators corresponding to different models

[0124]

[0125] Among them, Figure 3 is the density map of the training set of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) that integrates multi-factor intelligent optimization provided by the embodiments of the present invention; Figure 4 is the result map of the training set of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) that integrates multi-factor intelligent optimization provided by the embodiments of the present invention;

[0126] Figure 5 is the density map of the test set of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) that integrates multi-factor intelligent optimization provided by the embodiments of the present invention; Figure 6 is the result map of the test set of the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) that integrates multi-factor intelligent optimization provided by the embodiments of the present invention; Figure 7 is the density map of the test set of the BP model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) that integrates multi-factor intelligent optimization of the present invention; Figure 8 is the density map of the test set of the BP-PSO model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) that integrates multi-factor intelligent optimization of the present invention; Figure 9 is the density map of the test set of the XGBoost model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) that integrates multi-factor intelligent optimization of the present invention; Figure 10The density result diagram of the training set of the BP model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention; Figure 11 The density result diagram of the training set of the BP-PSO model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention; Figure 12 The density result diagram of the training set of the XGBoost model for comparison with the tunnel blasting vibration velocity prediction method (SSA-XGBoost model) integrating multi-factor intelligent optimization of the present invention;

[0127] Exemplarily, in step S5, the safety threshold is determined by introducing geological feature variables and combining with the Sadovsky empirical formula to determine the safety threshold of the blasting vibration velocity. The safety threshold formula is as follows:

[0128] ;

[0129] In the formula, is the vibration velocity safety threshold, is the coefficient determined according to geological conditions and blasting experience, is the maximum charge per delay, is the distance from the blast center, is the weight coefficient of geological features, is the normalization function of geological features such as fracture density (such as fracture density, etc.);

[0130] ;

[0131] In the formula, is the normalization function based on rock hardness, is the normalization function based on fracture density, and either one can be selected for actual calculation.

[0132] Exemplarily, the blasting closed-loop optimization in step S5 is to predict the vibration velocity of the future construction section through the trained model to optimize the blasting parameters, and at the same time monitor and evaluate the blasting effect, and feedback the evaluation result to the design stage to provide a basis for the next section of blasting design, so as to realize the real-time optimization and improvement of tunnel blasting construction.

[0133] Table 2 Vibration velocity safety threshold of some surrounding buildings

[0134]

[0135] Table 3 K, value of different lithologies in the blast area

[0136]

[0137] Example 2, as Figure 13As shown in the figure, the tunnel blasting vibration velocity prediction system integrating multi-factor intelligent optimization provided by the embodiment of the present invention includes:

[0138] A multi-source data acquisition module 1 for collecting blasting parameters (maximum charge per delay, distance from the blast center, drilling depth, and rock compressive strength) and historical vibration monitoring data;

[0139] A data preprocessing module 2 for normalizing the data, constructing a data set containing multi-factor features, and dividing it into a training set, a validation set, and a test set;

[0140] An SSA-XGBoost model building module 3 for initializing the XGBoost hyperparameters and iteratively optimizing the XGBoost hyperparameters using the SSA algorithm;

[0141] A model training and validation module 4 for inputting the training set data to train the optimized SSA-XGBoost model, using the test set to verify the model performance and compare it with the prediction performance of traditional models (such as: traditional BP neural network, BP-PSO model, and unoptimized XGBoost), and evaluating the prediction errors (MAE, RMSE, etc.) and the coefficient of determination (R 2 )

[0142] An engineering application module 5 for dynamically adjusting parameters such as the charge per delay in real time according to the predicted value, generating a risk warning in combination with a safety threshold (such as: the limit value of the improved Sadovsky formula), and realizing the closed-loop optimization of the blasting design.

[0143] As mentioned above, it is only a relatively optimal specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any modification, equivalent replacement, and improvement made by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention as long as they are made within the spirit and principle of the present invention.

Claims

1. A method for predicting the vibration velocity of tunnel blasting integrating multi-factor intelligent optimization, characterized in that The method includes the following steps: S1. Collect blasting parameters and historical vibration monitoring data. The blasting parameters include the maximum charge per delay, the distance from the blast center, the drilling depth, and the rock compressive strength; S2. Perform normalization processing on the data to construct a dataset containing multi-factor features. The dataset includes a training set, a validation set, and a test set. Among them, the ratio of the training set, the validation set, and the test set is 8:1:1; S3. Initialize the XGBoost hyperparameters, and use the SSA algorithm to iteratively optimize the XGBoost hyperparameters to complete the construction of the SSA-XGBoost model; S4. Input the training set data to train the optimized SSA-XGBoost model, use the test set to verify the model performance and compare the prediction performance of the traditional model; S5. Dynamically adjust the charge per delay parameter in real time according to the predicted value, generate a risk warning in combination with the safety threshold, and achieve the closed-loop optimization of the blasting design; In step S3, initialize the XGBoost hyperparameters, including: The objective function of XGBoost consists of a loss function and a regularization term. The formula is: ； In the formula, is the objective function of XGBoost, is the loss function of the model deviation, is the actual value, is the predicted value, is the total number of samples in the data set, For the The regularization term of the tree, is the total number of trees, is the basis function; Introduce the Elastic Net regularization, combine L1 and L2 regularization, then there is: ； In the formula, is the parameter for controlling the tree structure, is the number of leaf nodes, is the weight of the first leaf node, is the weight of the second leaf node, is the set composed of the scores of the leaf nodes of each tree, is the L1 norm, is the L2 norm; L1 regularization automatically selects the features of the distance from the blast center and the maximum charge in the blasting parameters, and L2 regularization prevents the model from overfitting; ； In the formula, is the objective function value of the th step, is the sum of the predicted values of the previous trees, is the predicted value of the regression tree; Use the SSA algorithm to iteratively optimize the XGBoost hyperparameters, including: Define the parameters for optimizing the XGBoost model, including the number of iterations n_estimators, the maximum depth max_depth, and the learning rate learning_rate; Set the parameters of the sparrow search algorithm, including the number of sparrows and the maximum number of iterations, and define the fitness function; Simulate the foraging process and update the positions of the discoverers, followers, and vigilant ones; The calculation formula for updating the position of the discoverer is: ； In the formula, is the position information of the th sparrow in the th dimension, is the exponential function, is the number of iterations; is a random value, ; is the maximum number of iterations, is the warning value, ; is a random number obeying the standard normal distribution, is a -dimensional matrix with a value of 1; is the safety threshold, ; When it indicates that the discoverer is in a safe position for searching; When it means that the discoverer has been detected by the predator and needs to fly to other safe locations for searching.

2. The method for predicting the vibration velocity of tunnel blasting integrating multi-factor intelligent optimization according to claim 1, wherein In step S1, blasting parameters and historical vibration monitoring data are collected, including: in multi-source data acquisition for blasting vibration monitoring, a blasting vibration meter is used to simultaneously measure three components of the particle vibration perpendicular to each other, and the vibration velocity components in the three directions are vectorially synthesized to obtain the total vibration velocity , which is used as the output variable for model training. The calculation formula is as follows: ； wherein, is the maximum radial component of the vibration velocity, is the maximum tangential component of the vibration velocity, is the maximum vertical component of the vibration velocity.

3. The tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization according to claim 1, wherein, The calculation formula for updating the position of the follower is: ； In the formula, is an exponential function, is the globally worst position, is the number of sparrows, is the current best position of the discoverer; is a vector of dimension , and the value of each element is randomly -1 or 1.

4. The tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization according to claim 1, characterized in that The calculation formula for updating the position of the vigilant one is: ； wherein, is the current best position, is a random number obeying the standard normal distribution; is a random number, ; is the fitness value of the current sparrow individual, and are the current global best and worst fitness values respectively, is the minimum constant.

5. The tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization according to claim 1, characterized in that In step S4, for the SSA-XGBoost model, the root mean square error RMSE, mean absolute error MAE, and coefficient of determination R 2 are used for evaluation.

6. The tunnel blasting vibration velocity prediction method integrating multi-factor intelligent optimization according to claim 1, characterized in that In step S5, the safety threshold is determined by introducing geological feature variables and combining with the Sadovsky empirical formula. The safety threshold formula is as follows: ； In the formula, is the vibration velocity safety threshold, is the coefficient determined according to geological conditions and blasting experience, is the maximum charge per delay, is the distance from the blast center, is the weight coefficient of geological characteristics, is the normalization function of the fracture density geological characteristic; ； wherein, is a normalization function based on rock hardness, is a normalization function based on fracture density.

7. The method for predicting the vibration velocity of tunnel blasting by integrating multi-factor intelligent optimization according to claim 1, characterized in that, In step S5, achieve the closed-loop optimization of the blasting design, including: predicting the vibration velocity of the future construction section through the trained SSA-XGBoost model to optimize the blasting parameters, and at the same time monitoring and evaluating the blasting effect.

8. A tunnel blasting vibration velocity prediction system integrating multi-factor intelligent optimization, characterized in that, The system implements the tunnel blasting vibration velocity prediction method for integrated multi-factor intelligent optimization as described in any one of claims 1-7. The system includes: A multi-source data acquisition module (1) for collecting blasting parameters and historical vibration monitoring data. The blasting parameters include the maximum charge per delay, the distance from the blast center, the drilling depth, and the rock compressive strength; A data preprocessing module (2) for performing normalization processing on the data to construct a dataset containing multi-factor features. The dataset includes a training set, a validation set, and a test set. Among them, the ratio of the training set, the validation set, and the test set is 8:1:1; An SSA-XGBoost model construction module (3) for using the SSA algorithm to iteratively optimize the XGBoost hyperparameters to complete the construction of the SSA-XGBoost model; The model training and validation module (4) is used to input the training set data to train the optimized SSA-XGBoost model, verify the model performance using the test set and compare the prediction performance of the traditional model; The engineering application module (5) is used to dynamically adjust the single-section charge amount parameter in real time according to the predicted value, generate a risk warning in combination with the safety threshold, and realize the closed-loop optimization of the blasting design.

Images