Shallow-buried tunnel blasting surface vibration waveform prediction method and system

Abstract

The invention provides a shallow-buried tunnel blasting surface vibration waveform prediction method and system, and relates to the technical field of surface vibration waveform prediction, and the method comprises the steps: collecting geological, blasting and environmental parameters of historical and current blasting, and forming a standardized parameter set through three-stage index storage, abnormal value screening and standardization processing; establishing a mapping relation between blasting parameters and a vibration waveform time domain sequence based on an LSTM neural network, and predicting a current blasting vibration waveform; fusing the geological condition influence factors, the environmental sensitivity influence factors and the predicted waveform features to generate a comprehensive safety assessment index; and according to a matching result of the index and a multi-level safety threshold value, the risk is divided into four levels of safety, low risk, medium risk and high risk, and differential management and control are executed, so that accurate prediction and dynamic regulation and control of the blasting vibration risk are realized. According to the invention, the vibration wave propagation process in the shallow tunnel blasting construction can be accurately simulated, so that the influence of blasting can be better evaluated.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of surface vibration waveform prediction, in particular to a shallow tunnel blasting surface vibration waveform prediction method and system. BACKGROUND

[0002] Shallow tunnel blasting construction is a key link in the fields of urban underground space development, transportation infrastructure construction, etc., and the surface vibration effect generated thereby is directly related to the safety of adjacent buildings, underground pipelines and the normal life of residents. Therefore, accurate prediction, evaluation and control of the surface vibration generated by blasting operations are core technical problems for ensuring engineering safety and reducing environmental and social risks. Traditional vibration evaluation methods rely mainly on empirical formulas or simplified numerical simulation, and are difficult to fully reflect the vibration response characteristics under the coupling action of complex geological conditions, variable blasting parameters and sensitive surrounding environment, so the prediction accuracy and real-time performance need to be improved, and there are obvious deficiencies in fine safety control.

[0003] In the prior art, a blasting operation control system and method based on the Internet of Things, with publication number CN119539506A, integrates Internet of Things sensing and simulation analysis technology to achieve comprehensive evaluation and dynamic regulation of blasting vibration propagation range and environmental risk. However, this scheme focuses on macro regional safety distance calculation and risk scoring based on multiple factors (such as geology and climate), and its vibration prediction does not go deep into the waveform time domain sequence level, lacking fine-grained description of the whole vibration process characteristics; at the same time, its consideration of the impact on the surrounding environment does not establish a direct and dynamic mapping relationship with the blast source parameters, nor does it model the vibration superposition effect of multi-stage millisecond blasting in shallow tunnels, so there is still room for further improvement in terms of vibration waveform prediction accuracy, environmental sensitive factor coupling analysis and real-time grading control.

[0004] The above information disclosed in the background section is only intended to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0005] The present application aims to provide a shallow tunnel blasting surface vibration waveform prediction method and system to solve the problems raised in the background.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solutions: A shallow tunnel blasting surface vibration waveform prediction method, comprising the following specific steps: Step 1: Collect basic parameters and corresponding vibration waveform time-domain sequences from multiple shallow tunnel blasting constructions, as well as basic parameters from the current shallow tunnel blasting. The basic parameters include geological parameters, blasting parameters, and surrounding environmental parameters. A three-level index table is designed based on parameter type to classify and store the basic parameters. An outlier detection algorithm is used to filter valid parameters from the three-level index table, and the valid parameters are standardized to obtain a standardized parameter set. Step 2: Analyze the blasting parameters of each detonation section in the standardized parameter set and their corresponding vibration waveform time domain sequence, establish a mapping relationship between the blasting parameters and the vibration waveform time domain sequence, and determine the predicted vibration waveform time domain sequence corresponding to the current blasting based on the mapping relationship; Step 3: Based on the geological parameters and surrounding environmental parameters in the standardized parameter set, determine the geological condition influencing factors and environmental sensitivity influencing factors, perform a fusion analysis on the geological condition influencing factors, environmental sensitivity influencing factors and the predicted vibration waveform time domain sequence, and generate a comprehensive safety assessment index for quantitatively evaluating the safety of the current blasting; Step 4: Calling the preset multi-level safety risk threshold, matching and analyzing the comprehensive safety assessment index with the multi-level safety risk threshold, and determining the risk level of the current blasting operation based on the matching result; the risk level includes four levels: safe, low risk, medium risk, and high risk; Step 5: Implement differentiated control measures based on the determined risk level: the safety level is implemented according to the original plan and routine monitoring is carried out simultaneously; the low-risk level enables real-time high-frequency vibration monitoring; the medium-risk level proportionally reduces the amount of single-stage explosives and extends the detonation time difference based on the low-risk control; the high-risk level suspends blasting operations and takes enhanced shock-absorbing measures until the risk is reduced.

[0007] Furthermore, the basic parameters of multiple shallow tunnel blasting constructions and the corresponding vibration waveform time domain series, as well as the basic parameters of the current shallow tunnel blasting, are collected. The specific collection method is as follows: Through drilling exploration, geological radar scanning, and on-site rock mechanics tests, the blast source center of the blasting section is taken as the center of the circle with a radius of The geological parameters at multiple sampling points within the range, including rock elastic modulus, rock Poisson's ratio, rock density, joint and fissure density, and soil shear wave velocity, are averaged as the geological parameter value corresponding to the center of the explosion source. Among them, the soil shear wave velocity refers to the speed at which the shear wave propagates in the soil layer, which is used to evaluate the hardness and looseness of the soil layer. The blasting parameters are obtained from the blasting design and the blasting system, including the maximum charge of each blasting section, the blasting sequence, the blasthole depth and the spatial coordinates of the corresponding blasting source center point; Expressed as , Indicates the The detonation time of the explosive at the center of the explosion source, is the index of the detonation segment, , Indicates the number of detonation segments, each of which corresponds to a blast source center point; By analyzing the design drawings and on-site inspection, it is determined that the center of the explosion source of the detonation section is the center of the circle with a radius of The surrounding environmental parameters within the range include building burial depth, building equivalent stiffness, underground pipeline diameter, and underground pipeline burial depth. For each explosion source center point, the building burial depth and building equivalent stiffness of the building closest to the explosion source center point are taken as representative values. The shortest vertical distance from the explosion source center point to each nearby pipeline is calculated, and the underground pipeline diameter and underground pipeline burial depth of the pipeline corresponding to the minimum value of the shortest vertical distance are taken as representative values. If there are multiple pipelines corresponding to the minimum value of the shortest vertical distance, the underground pipeline diameter and underground pipeline burial depth of the pipeline made of the most vibration-sensitive material are taken as representative values. The first-level index of the three-level index table is the parameter categories, namely geological parameters, blasting parameters and surrounding environment parameters; the second-level index is the specific parameter name under each parameter category; the third-level index is the acquisition timestamp and spatial coordinates of each parameter.

[0008] Furthermore, when screening the valid parameters of the three-level index table through the outlier detection algorithm, a dual threshold method based on physical meaning and statistical distribution is adopted: first, the reasonable value range of each parameter is set according to engineering experience, and parameter values ​​outside the reasonable value range are judged as outliers and eliminated; second, for parameters within the reasonable value range, the box plot method is used to judge parameter values ​​less than the lower quartile - 3 times the interquartile range or greater than the upper quartile + 3 times the interquartile range as discrete outliers and eliminate them; The standardization process uses the range standardization method to convert the filtered parameter values ​​into Range: ; in is the original value of the parameter, is the parameter standardized value, 、 are the minimum and maximum values ​​of the parameter to be standardized in the valid parameter set after outlier screening; After the above processing, a standardized parameter set containing standardized values ​​of geological parameters, blasting parameters and surrounding environment parameters is obtained.

[0009] Furthermore, the blasting parameters of each detonation section in the standardized parameter set and their corresponding vibration waveform time domain sequences are analyzed, and a mapping relationship between the blasting parameters and the vibration waveform time domain sequences is established. Based on this mapping relationship, the predicted vibration waveform time domain sequence corresponding to the current blasting is determined. The specific logic is as follows: A machine learning model was constructed based on a long short-term memory network. The standardized parameter set, consisting of blasting parameters and vibration waveform time-domain sequences from historical shallow tunnel blasting operations, was divided into a training set, a validation set, and a test set at a ratio of 70%, 15%, and 15%. The model was trained using the blasting parameters corresponding to each blasting section as input and the corresponding vibration waveform time-domain sequences for each blasting section as output. The model has three LSTM hidden layers with 128, 64, and 32 neurons, respectively. The model is trained using the mean squared error (MSE) as the loss function and the Adam optimizer. The learning rate is set to 0.001, and the first-order moment estimate exponential decay rate is set to 0.9. During iterative training, training is automatically stopped when the validation set loss does not decrease for 10 consecutive rounds to prevent overfitting. After the training is completed, the blasting parameters corresponding to each detonation section of the current blasting operation are input into the model, and the model outputs the waveform time domain sequence corresponding to each detonation section; the waveform time domain sequences of all detonation sections are superimposed according to the detonation timing to form a complete predicted vibration waveform time domain sequence.

[0010] Furthermore, based on the geological parameters and surrounding environmental parameters in the standardized parameter set, geological condition influencing factors and environmental sensitivity influencing factors are determined; The formula for calculating the geological condition influencing factor is as follows: ; Where, For the The geological conditions affecting the center of the explosion source are: The first parameter in the standardized The density of joints and fissures at the center of each explosion source, is the wave impedance influencing factor, where The first parameter in the standardized The rock density at the center of the explosion source is The first parameter in the standardized The shear wave velocity of the soil layer at the center of the explosion source is The first parameter in the standardized The elastic modulus of the rock mass at the center of the explosion source is is the maximum value of the rock mass elastic modulus in the standardized parameter set, The first parameter in the standardized The Poisson's ratio of the rock mass at the center of the explosion source is 、 、 and is the preset weight, 、 、 and are all non-negative numbers and satisfy ; For each detonation section , extract the surrounding environmental parameters corresponding to the explosion source center point from the standardized parameter set, including building depth, building equivalent stiffness, underground pipeline diameter, and underground pipeline depth; based on the above parameters, calculate the building reflection correction coefficient and underground pipeline attenuation correction coefficient to determine the environmental sensitivity influencing factor. The calculation formula is as follows: ; Where, For the The building reflection correction coefficient at the center of the explosion source is: For the The attenuation correction coefficient of underground pipelines at the center of each explosion source is: For the The environmental sensitivity influencing factor of the explosion source center, The first parameter in the standardized The equivalent stiffness of the building at the center of the explosion source is is the maximum value of the equivalent stiffness of the building in the standardized parameter set; The first parameter in the standardized The diameter of the underground pipeline at the center of the explosion source, is the maximum value of underground pipeline diameter in the standardized parameter set; The first parameter in the standardized The depth of underground pipelines at the center of each explosion source; A fusion analysis of geological condition influencing factors, environmental sensitivity influencing factors, and predicted vibration waveform time domain series is performed to generate a comprehensive safety assessment index for quantitatively evaluating the safety of the current blasting. The formula is as follows: ; Where, is the comprehensive safety assessment index, Indicates the number of detonation sections, Predict the peak particle vibration velocity of the vibration waveform time domain sequence for the i-th detonation segment; Predict the dominant frequency of the vibration waveform time domain sequence for the i-th detonation segment.

[0011] Further, a preset multi-level safety risk threshold is called, the comprehensive safety evaluation index is matched and analyzed with the multi-level safety risk threshold, and the risk level of the current blasting operation is determined according to the matching result, and the specific logic thereof is as follows: If , it is determined that the risk level of the current blasting operation is “safe”; If , it is determined that the risk level of the current blasting operation is “low risk”; If , it is determined that the risk level of the current blasting operation is “medium risk”; If , it is determined that the risk level of the current blasting operation is “high risk”; In the formula, , , , respectively represent the preset upper limit of the safety threshold, the upper limit of the low risk threshold, the upper limit of the medium risk threshold and the lower limit of the high risk threshold, and satisfy .

[0012] Further, the specific execution process of step 5 is as follows: According to the determined risk level of the current blasting operation, corresponding hierarchical regulation and real-time feedback operation is performed: if the risk level is low risk, real-time high-frequency vibration monitoring sensors are arranged in the area where the predicted peak particle vibration speed is greater than 0.5 cm / s and the sensitive structure within 50 m from the center of the explosion source during blasting, the sampling frequency is not less than 1000 Hz, and the dynamic feedback monitoring data is fed back to the management platform; if the risk level is medium risk, on the basis of low risk monitoring, the single segment explosive quantity is reduced to 70% of the original design value, and the initiation time difference is extended to 1.5 times of the original design; if the risk level is high risk, the blasting operation is immediately suspended, and the reinforcement damping measures are taken, and the risk level is reevaluated until it is reduced to medium risk and below; at the same time, the regulation measures and execution results under each risk level are recorded to the database for optimizing the early warning model and threshold setting.

[0013] The present application also provides a shallow tunnel blasting ground surface vibration waveform prediction system, which is used for executing the shallow tunnel blasting ground surface vibration waveform prediction method, and comprises: The data acquisition and preprocessing module is used for collecting basic parameters of multiple shallow-buried tunnel blasting constructions and corresponding vibration waveform time domain sequences, and basic parameters of the current shallow-buried tunnel blasting; the basic parameters include geological parameters, blasting parameters and surrounding environment parameters, the basic parameters are classified and stored based on a three-level index table of parameter types, effective parameters in the three-level index table are screened through an abnormal value detection algorithm, and the effective parameters are standardized to obtain a standardized parameter set; The mapping relationship determination module is used for analyzing blasting parameters of each detonation section in the standardized parameter set and corresponding vibration waveform time domain sequences, establishing a mapping relationship between the blasting parameters and the vibration waveform time domain sequences, and determining a predicted vibration waveform time domain sequence corresponding to the current blasting based on the mapping relationship; The safety index fusion calculation module is used for determining a geological condition influence factor and an environmental sensitivity influence factor according to the geological parameters and the surrounding environment parameters in the standardized parameter set, and performing fusion analysis on the geological condition influence factor, the environmental sensitivity influence factor and the predicted vibration waveform time domain sequence to generate a comprehensive safety evaluation index for quantitatively evaluating safety of the current blasting; The risk grading module is used for calling preset multi-level safety risk thresholds, performing matching analysis on the comprehensive safety evaluation index and the multi-level safety risk thresholds, and determining a risk level of the current blasting operation according to a matching result; the risk level includes four levels of safety, low risk, medium risk and high risk. The graded control measure execution module is used for executing differential control measures according to the determined risk level: a safety level is implemented according to an original scheme and synchronous conventional monitoring is performed; real-time high-frequency vibration monitoring is enabled for a low risk level; a single-segment detonating charge is reduced in proportion and a detonation time difference is prolonged for a medium risk level on the basis of low risk control; blasting operation is suspended for a high risk level, and intensive shock absorption measures are taken, and the blasting operation is implemented after the risk is reduced.

[0014] Compared with the prior art, the present application has the following advantages: The present application realizes high-precision prediction of the time-domain sequence of the blasting ground vibration waveform of a shallow tunnel by constructing a deep learning model that fuses geological conditions, environmental sensitivity and predicted vibration waveform characteristics, and significantly improves the accuracy and reliability of vibration evaluation. The comprehensive safety evaluation index with multi-factor coupling can quantitatively reflect the complex risk conditions of blasting operations, and combined with multi-level thresholds, the risk is finely graded. The systematic grading control mechanism dynamically adjusts the monitoring strategy and blasting parameters according to the real-time risk assessment results, intensifies the monitoring of key areas in low-risk situations, automatically optimizes the charge and detonation timing in medium-risk situations, and decisively interrupts the operation and initiates intensive measures in high-risk situations, effectively avoiding the drawbacks of response lag and extensive control of traditional methods. The present application organically combines data-driven prediction, multi-source factor fusion and intelligent decision response, greatly improving the safety, controllability and environmental friendliness of shallow tunnel blasting operations, and providing comprehensive technical support for blasting construction in complex urban environments. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 It is the overall method flowchart of the present application; Figure 2 It is the overall system module schematic diagram of the present application; Figure 3 It is the parallel coordinate image of joint fissure density and geological condition influence factor; Figure 4 It is the parallel coordinate image of wave impedance influence factor and geological condition influence factor; Figure 5 It is the 3D strip image of joint fissure density and geological condition influence factor. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical scheme and advantages of the present application clearer and more apparent, the present application will be further described in detail below with specific examples.

[0017] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be understood as the usual meaning understood by those skilled in the art to which the present application belongs. The "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connected" or "connected" and similar words are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to represent relative positional relationship, when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0018] Embodiment: Please refer to Figure 1 The present application provides a technical solution: A shallow tunnel blasting ground surface vibration waveform prediction method, the specific steps include: Step 1: Collect the basic parameters of multiple shallow tunnel blasting construction and the corresponding vibration waveform time domain sequence, and the basic parameters of the current shallow tunnel blasting; The basic parameters include geological parameters, blasting parameters and surrounding environment parameters, the basic parameters are classified and stored based on the three-level index table of parameter type, the effective parameters in the three-level index table are screened by the outlier detection algorithm, and the effective parameters are standardized to obtain the standardized parameter set; In this embodiment, the basic parameters of multiple shallow tunnel blasting construction and the corresponding vibration waveform time domain sequence, and the basic parameters of the current shallow tunnel blasting are collected, and the specific collection method is as follows: Through borehole exploration, geological radar scanning and field rock mass mechanics test method, the geological parameters of multiple sampling points within the radius of the blast source center point of the initiation section are obtained, including rock mass elastic modulus, rock mass Poisson's ratio, rock mass density, joint fissure density and soil shear wave velocity, and the average value is taken as the geological parameter value of the corresponding blast source center point; wherein the soil shear wave velocity refers to the speed of shear wave propagation in the soil layer, which is used to evaluate the hardness and looseness of the soil layer; The blasting parameters are obtained from the blasting design scheme and the initiation system, including the single-section maximum charge of each initiation section, the segmented initiation timing, the borehole depth and the corresponding blast source center point spatial coordinates; wherein the segmented initiation timing is expressed as , represents the initiation time of the explosive of the th blast source center point, is the index of the initiation section, , represents the number of initiation sections, and each initiation section corresponds to a blast source center point; Through analysis of design drawings and field detection, the surrounding environment parameters within the radius of the blast source center point of the initiation section are determined, including building depth, building equivalent stiffness, underground pipeline diameter and underground pipeline depth; wherein for each blast source center point, the building depth and building equivalent stiffness of the nearest building to the blast source center point are taken as the representative values; calculate the shortest vertical distance from the blast source center point to each pipeline, take the underground pipeline diameter and underground pipeline depth of the pipeline corresponding to the minimum value of the shortest vertical distance as the representative values; if there are multiple pipelines corresponding to the minimum value of the shortest vertical distance, take the underground pipeline diameter and underground pipeline depth of the pipeline with the most sensitive material to vibration as the representative values; The first index of the three-level index table is a parameter category, which is a geological parameter, a blasting parameter and a surrounding environment parameter, the second index is a specific parameter name under each parameter category, and the third index is a parameter collection timestamp and a spatial coordinate.

[0019] When screening effective parameters of the three-level index table through an outlier detection algorithm, a dual threshold method based on physical meaning and statistical distribution is adopted: first, a reasonable value range of each parameter is set according to engineering experience, and parameter values exceeding the reasonable value range are determined as outliers and removed; second, for parameters within the reasonable value range, a box plot method is adopted, and parameter values less than the lower quartile minus 3 times the interquartile range or greater than the upper quartile plus 3 times the interquartile range are determined as discrete outliers and removed. The standardization processing adopts a range standardization method, and the screened parameter values are converted to interval: ; wherein is a parameter original value, is a parameter standardized value, , are the minimum value and the maximum value of the current parameter to be standardized in the effective parameter set after the outlier screening, respectively. After the above processing, a standardized parameter set containing the standardized values of the geological parameters, the blasting parameters and the surrounding environment parameters is obtained.

[0020] Step 1 is the data basis and preprocessing core of the overall scheme, and its significance lies in that a high-quality, multi-dimensional, time-space associated standardized parameter set is constructed through systematic data collection, structured storage and standardization processing. This step adopts a three-level index table to store geological, blasting and environmental parameters, ensuring the ordered management and rapid retrieval of massive heterogeneous data; in combination with a dual outlier detection algorithm based on physical meaning and statistical distribution, invalid data caused by human errors, device noises and other factors are effectively removed, improving the reliability and consistency of the data set; further through range standardization processing, the differences in dimensions and numerical ranges of different parameters are eliminated, providing standardized and balanced input data for subsequent machine learning models, and fundamentally guaranteeing the accuracy and stability of the vibration prediction model training and evaluation.

[0021] Compared with the prior art, the advantages of this step mainly lie in three aspects: first, in the data collection layer, the principle of sampling within a spatial range with the center point of the explosion source as the center is clearly defined, and the geological parameters are averaged and the environmental parameters are taken as the nearest or most sensitive representative values, thereby enhancing the spatial representativeness and engineering pertinence of the parameters and avoiding the problem of random selection and lack of spatial correlation of environmental parameters in the traditional method; second, in the data management layer, a three-level index structure and a double abnormal value detection mechanism are innovatively used to realize systematic and standardized management of multi-source heterogeneous data and solve the defects of scattered data storage and insufficient quality control in the prior art; third, in the data processing layer, a strict standardized process is used to provide a directly calculable high-quality input for subsequent deep learning-based waveform prediction, thereby overcoming the disadvantages of limited model prediction accuracy caused by non-uniform data format and much noise in the traditional method.

[0022] Step 2: Analyze the blasting parameters of each initiation section in the standardized parameter set and the corresponding vibration waveform time domain sequence, establish a mapping relationship between the blasting parameters and the vibration waveform time domain sequence, and determine the predicted vibration waveform time domain sequence corresponding to the current blasting based on the mapping relationship; In this embodiment, the blasting parameters of each initiation section in the standardized parameter set and the corresponding vibration waveform time domain sequence are analyzed, a mapping relationship between the blasting parameters and the vibration waveform time domain sequence is established, and the predicted vibration waveform time domain sequence corresponding to the current blasting is determined based on the mapping relationship. The specific logic is as follows: Based on the long short-term memory network, a machine learning model is constructed, and the blasting parameters and vibration waveform time domain sequence of the historical shallow tunnel blasting construction in the standardized parameter set are divided into a training set, a validation set and a test set in the proportions of 70%, 15% and 15% respectively; the blasting parameters corresponding to each initiation section are used as the input of the model, and the vibration waveform time domain sequence of each initiation section is used as the output of the model for model training. The model has 3 layers of LSTM hidden layers, and the number of neurons is 128, 64 and 32 respectively. The mean square error (MSE) is used as the loss function for model training, and the Adam optimizer is used, wherein the learning rate is set to 0.001, the first moment estimation exponential decay rate is set to 0.9, and the training is automatically stopped when the validation set loss does not decrease for 10 consecutive rounds to prevent overfitting. After training is completed, the blasting parameters corresponding to each initiation section of the current blasting operation are input into the model, and the model outputs the waveform time domain sequence corresponding to each initiation section; the waveform time domain sequences of all initiation sections are superimposed according to the initiation sequence to form a complete predicted vibration waveform time domain sequence.

[0023] Step 2, the core prediction engine of the overall solution, is significant in achieving precise digital simulation of the blasting vibration process by establishing a nonlinear mapping relationship between blasting parameters and the time-domain sequence of vibration waveforms. Based on a standardized parameter set, this step utilizes a long-short-term memory network to capture the temporal dependencies between blasting parameters and vibration waveforms. This allows for accurate prediction of the time-domain sequence of vibration waveforms generated by each detonation stage and, through time-series superposition, a complete predicted vibration waveform. This process overcomes the limitation of traditional empirical formulas that can only predict peak vibration velocity, providing waveform data containing complete vibration characteristics such as amplitude, frequency, and duration, providing an unprecedented data foundation for subsequent safety assessments.

[0024] Compared with the existing technology, the advantages of this step are mainly reflected in three aspects: First, in terms of prediction dimension, the existing technology is mostly limited to predicting a single indicator of vibration intensity or safety distance, while the present invention directly predicts the complete vibration waveform time domain sequence, which can obtain key features such as the main frequency and vibration duration, and achieves a qualitative leap from "intensity prediction" to "waveform reconstruction"; second, in terms of algorithm advancement, the use of deep learning methods rather than traditional empirical formulas or statistical regression can better handle the complex timing relationships and nonlinear characteristics of multi-segment micro-difference blasting, significantly improving the prediction accuracy; third, in terms of practicality, by superimposing each waveform according to the detonation sequence, the vibration superposition effect in the actual blasting is truly simulated, overcoming the oversimplification problem of simplifying multi-segment blasting into a single sound source in the existing technology, and providing technical support for accurately evaluating the cumulative impact of blasting vibration on the surrounding environment.

[0025] Step 3: Based on the geological parameters and surrounding environmental parameters in the standardized parameter set, determine the geological condition influencing factors and environmental sensitivity influencing factors, perform a fusion analysis on the geological condition influencing factors, environmental sensitivity influencing factors and the predicted vibration waveform time domain sequence, and generate a comprehensive safety assessment index for quantitatively evaluating the safety of the current blasting; In this embodiment, the geological condition influencing factor and the environmental sensitivity influencing factor are determined based on the geological parameters and surrounding environment parameters in the standardized parameter set; The formula for calculating the geological condition influencing factor is as follows: ; Where, For the The geological conditions affecting the center of the explosion source are: The first parameter in the standardized The density of joints and fissures at the center of each explosion source, is the wave impedance influencing factor, where The first parameter in the standardized The rock density at the center of the explosion source is The first parameter in the standardized The shear wave velocity of the soil layer at the center of the explosion source is The first parameter in the standardized The elastic modulus of the rock mass at the center of the explosion source is is the maximum value of the rock mass elastic modulus in the standardized parameter set, The first parameter in the standardized The Poisson's ratio of the rock mass at the center of the explosion source is 、 、 and is the preset weight, , , , .

[0026] The weight coefficient is set according to The practical reason is that the density of joints and fissures is the most critical factor in controlling the integrity of the rock mass and the energy attenuation of the blasting vibration wave. A large number of cracks will significantly enhance the scattering and absorption effects of the wave, so it is given the highest weight. Wave impedance directly determines the propagation efficiency and energy dissipation of stress waves in geotechnical media, and is the core physical index affecting vibration intensity. Therefore, the weight Secondly; elastic modulus reflects the stiffness of the rock mass and has an important influence on the vibration frequency characteristics, but its sensitivity is lower than that of wave impedance, so the weight is Ranked third; Poisson's ratio mainly characterizes the lateral deformation capacity of the rock mass. Its influence on vibration propagation is relatively indirect and weak, so it is given the lowest weight. This weight distribution strategy ensures that the geological condition influencing factors can most effectively capture the geological characteristics that play a dominant role in the blasting vibration of shallow tunnels.

[0027] In the above formula, the dependent variable is the geological condition influencing factor, specifically reflecting the The combined impact of geological conditions at the center of each blast source on the propagation of blasting vibration waves represents a quantitative integration of key geological characteristics such as rock integrity and mechanical properties. Its core meaning is to characterize the combined effect of geological conditions on vibration wave amplitude, frequency, and attenuation through a single indicator. The technical effect lies in converting multi-dimensional geological parameters into quantitative factors that can be directly linked to blasting parameters.

[0028] The correlation between the independent variables and the dependent variables is due to the direct influence of each parameter on the propagation of blasting vibration waves: joint crack density Determines the degree of rock fragmentation, directly affecting the reflection, refraction and energy attenuation of vibration waves; wave impedance influencing factor Reflects the rock mass's ability to transmit vibration waves, and determines the wave velocity and energy transfer efficiency; elastic modulus ratio Reflects the difference in rock mass stiffness and affects the attenuation rate of vibration waves; The brittleness of the rock mass affects the degree of waveform distortion of the vibration wave. These independent variables are the core parameters that control the propagation characteristics of the vibration wave in geological conditions, and therefore are closely related to the dependent variables that characterize the comprehensive influence. There are inherent connections, and their combined effect determines the ultimate impact of geological conditions on vibration propagation.

[0029] and joint crack density Negatively correlated, that is, the denser the rock joints, the weaker the comprehensive beneficial effect of geological conditions on vibration propagation (such as stable energy transfer); and the wave impedance influence factor , elastic modulus ratio 、 They are all positively correlated, that is, the greater the wave impedance, the higher the rock elastic modulus, and the smaller the Poisson's ratio, the stronger the comprehensive favorable influence of geological conditions on vibration propagation, and the better the energy transfer and waveform stability of the vibration wave.

[0030] The formal rationality of this formula is reflected in three aspects: first, it integrates geological parameters of different dimensions, such as joint and fissure density, wave impedance, elastic modulus, and Poisson's ratio, into a single influencing factor in the form of weighted summation of sub-items, which not only retains the independent effect of each parameter on vibration propagation, but also reflects the difference in their influence degree through weight distribution, which conforms to the actual characteristics of the comprehensive effect of multiple factors in geological conditions; second, it adopts the weighted summation of joint and fissure density to calculate the influence of different factors on the joint and fissure density. The Poisson's ratio is expressed in the form of The inverse correlation between parameters and geological conditions is naturally realized in the form of: the denser the joints and the larger the Poisson's ratio, the weaker the favorable effect on vibration propagation, which is consistent with the effect of rock mass characteristics on vibration waves in engineering practice; thirdly, the elastic modulus adopts relative value , and the wave impedance is directly taken in product form, which ensures the dimensionless integration of parameters after standardization, avoids calculation conflicts between different physical dimensions, and makes the formula output have stable quantitative meaning, laying a reliable foundation for the follow-up.

[0031] Table 1: Statistics of factors affecting geological conditions

[0032] See also Figures 3-5The physical relationship and variation trend between the geological condition influencing factor and each input parameter are verified through different dimensional visual analysis, and the rationality of the formula is proved. Moreover, it can be seen from the 15 groups of data in Table 1 that there is a significant correlation between the geological condition influencing factor and each parameter: when the joint fissure density is low, the geological condition influencing factor is generally high, reflecting the positive effect of rock mass integrity on geological conditions; the increase of the wave impedance influencing factor and the elastic modulus will also lead to the rise of the geological condition influencing factor, which embodies the important influence of rock mass mechanical properties on overall geological conditions. The Poisson's ratio presents an inverse correlation, that is, the smaller the Poisson's ratio, the larger the geological condition influencing factor, which is consistent with the influence law of rock mass brittleness on vibration propagation.

[0033] Overall, the variation trend of the geological condition influencing factor is consistent with the comprehensive action of multiple parameters, verifying the rationality of the constructed formula. When the rock mass integrity is good and the mechanical properties are excellent (such as low joint density and high elastic modulus), the geological condition influencing factor is at a high level, and vice versa, which is consistent with the actual influence of geological conditions on vibration propagation in shallow tunnel blasting, indicating that the formula can effectively integrate key geological parameters and provide reliable quantitative basis for subsequent comprehensive safety evaluation index calculation.

[0034] For each initiation segment The surrounding environment parameters of the blast source center point are extracted from the standardized parameter set, including building depth, building equivalent stiffness, underground pipeline diameter, and underground pipeline depth; the building reflection correction coefficient and the underground pipeline attenuation correction coefficient are calculated based on the above parameters, so as to determine the environmental sensitivity influencing factor, and the calculation formula is as follows: ; In the formula, is the building reflection correction coefficient at the th blast source center point, is the underground pipeline attenuation correction coefficient at the th blast source center point, is the environmental sensitivity influencing factor of the th blast source center point, is the building equivalent stiffness at the th blast source center point in the standardized parameter set, is the maximum building equivalent stiffness in the standardized parameter set; is the underground pipeline diameter at the th blast source center point in the standardized parameter set, is the maximum underground pipeline diameter in the standardized parameter set; is the underground pipeline depth at the th blast source center point in the standardized parameter set. and is a preset proportion coefficient, , .

[0035] In the above formula, the building reflection correction coefficient and the underground pipeline attenuation correction coefficient have clear physical meanings and rationality: For the building reflection correction coefficient , the construction of the calculation formula reflects the influence of the equivalent stiffness of the building on the reflection ability. By standardizing the stiffness at the center point of the i th explosion source through the proportion relationship , the relative intensity contribution to the reflection can be truly reflected. At the same time, the exponential decay term takes into account the influence of the underground pipeline depth, and the deeper the depth, the weaker the reflection ability, so the exponential decay form can more reasonably characterize this physical phenomenon.

[0036] Secondly, for the underground pipeline attenuation correction coefficient , the calculation formula emphasizes the influence of the diameter of the underground pipeline on the degree of signal attenuation. Through the standardization , the relative pipeline size contribution to the attenuation is reflected. At the same time, part considers the influence of the underground pipeline depth, and the deeper the depth, the more significant the attenuation effect, combined with the characteristics of the exponential function, which helps to accurately describe the attenuation process of the pipeline to the explosion source signal. Therefore, the construction of the two formulas is reasonable and conforms to the engineering practice, which helps to realize the effective quantization and analysis of the environmental factors.

[0037] Finally, for the environmental sensitivity influence factor , its value is used to comprehensively reflect the sensitivity of the environment around the blasting point to the vibration response, and the larger the value, the higher the environmental sensitivity at the center point of the explosion source, and the greater the risk of environmental impact caused by blasting vibration. This factor couples the building reflection effect and the underground pipeline attenuation effect through mathematical form, realizes the unified quantization of different types of environmental sensitivity, and provides a key environmental impact parameter for subsequent safety evaluation. In the calculation formula , the independent variable is related to the equivalent stiffness and depth of the building, and the greater the stiffness and the shallower the depth, the more significant the reflection effect; the independent variable is related to the diameter and depth of the pipeline, and the larger the diameter and the shallower the depth, the weaker the vibration attenuation ability. The difference between and plus 1 is used, which not only embodies the antagonistic relationship between the building reflection enhancement vibration effect and the pipeline attenuation weakening vibration effect, but also ensures that the result value is positive and has a clear physical meaning: when the reflection effect is dominant, when the attenuation effect is dominant.

[0038] For the first formula of the above formula group, the dependent variable is the building reflection correction coefficient, which specifically reflects the quantitative correction degree of the strength of the reflection of the building on the blasting vibration wave. Its meaning is to quantify the comprehensive influence of the building on the reflection of the vibration wave by integrating the equivalent stiffness of the building and the buried depth parameter; the technical effect is to introduce the correction basis of the reflection of the building for the initial waveform, so that the waveform is more in line with the real state disturbed by the reflection of the building in actual propagation.

[0039] The equivalent stiffness of the building directly determines its ability to reflect the vibration wave, and the greater the stiffness, the stronger the reflection, so it is related to ; the buried depth affects the reflection efficiency of the building on the ground surface vibration wave, and the greater the buried depth, the weaker the reflection effect, so it is related through the exponential term. Therefore, is positively correlated with the equivalent stiffness of the building , and is negatively correlated with the buried depth .

[0040] For the second formula of the above formula group, the dependent variable is the underground pipeline attenuation correction coefficient, which reflects the quantitative correction degree of the strength of the energy attenuation effect of the underground pipeline on the vibration wave, and its meaning is to integrate the pipeline diameter and the buried depth parameter to quantify the attenuation effect of the pipeline on the vibration wave; the technical effect is to reflect the absorption and blocking effect of the underground pipeline on the vibration energy by correcting the initial waveform, and to improve the environmental adaptability of the waveform prediction.

[0041] For , the diameter of the underground pipeline determines its shielding and attenuation ability to the vibration wave, and the greater the diameter, the more significant the attenuation, and the buried depth affects the action range of the pipeline on the ground surface vibration, and the greater the buried depth, the weaker the attenuation effect, so both are related to , and together reflect the attenuation effect of the pipeline through the correction term. Therefore, is negatively correlated with the diameter of the underground pipeline , and is positively correlated with the buried depth of the underground pipeline .

[0042] The geological condition influence factor, the environmental sensitivity influence factor and the predicted vibration waveform time domain sequence are fused and analyzed to generate a comprehensive safety evaluation index for quantitatively evaluating the safety of the current blasting, and the formula based thereon is as follows: ; In the formula, is the comprehensive safety evaluation index, the number of initiation segments, the peak particle vibration velocity of the time-domain sequence of the vibration waveform predicted for the i th initiation segment; the dominant frequency of the time-domain sequence of the vibration waveform predicted for the i th initiation segment; wherein, and obtained by performing spectral analysis on the time-domain sequence of the vibration waveform of each initiation segment predicted in step 2.

[0043] the dependent variable is a dimensionless comprehensive quantitative index for comprehensively reflecting the overall safety risk level of the current blasting operation. The greater the value, the higher the potential risk of the blasting operation to the surrounding environment and structures. The index realizes multi-dimensional comprehensive evaluation of blasting safety by integrating geological conditions, environmental sensitivity and vibration waveform characteristics, and provides a scientific and objective quantitative basis for risk classification, overcoming the limitations of single-index evaluation.

[0044] the independent variables include a geological condition influence factor , an environmental sensitivity influence factor , a peak particle vibration velocity and a dominant frequency . and respectively reflect the amplification or attenuation effect of the geological conditions and the surrounding environment of the blasting point on vibration propagation; reflects the vibration intensity, and the square form highlights the impact of high-intensity vibration; reflects the vibration frequency characteristics, and different frequencies of vibration have different impacts on structures. These independent variables are coupled through multiplication and summation, and together determine the potential risk level of blasting vibration.

[0045] In the formula, is positively correlated with , , : the real reason is that when the geological conditions are worse, the environment is more sensitive, or the vibration velocity is greater, will increase; is positively correlated with , but the growth is relatively flat, indicating that high-frequency vibration, although with higher risk, has a more moderate impact than vibration intensity. In addition, the use of logarithmic and square root functions not only compresses the dynamic range of the data, avoiding the dominance of extreme values, but also maintains the positive correlation of each influence factor, making the final index more practical in engineering.

[0046] Step 3, as the risk quantification core of the overall scheme, has the significance of realizing the fine and quantitative evaluation of the blasting vibration risk by constructing the geological condition influence factor and the environmental sensitivity influence factor. This step, based on the standardized parameters, comprehensively considers the key geological factors such as the rock mass integrity (joint fissure density), wave impedance characteristics (rock density and shear wave velocity), rock mass stiffness (elastic modulus), and deformation characteristics (Poisson's ratio), as well as the environmental sensitive factors such as the reflection effect of buildings and the attenuation characteristics of underground pipelines, and through the mathematical modeling of multi-factor coupling, converts the complex geological and environmental conditions into quantifiable influence factors. Further, the geological conditions, environmental sensitivity, and predicted vibration waveform characteristics are analyzed to generate a comprehensive safety evaluation index that can fully reflect the risk level of the blasting operation, providing a scientific and objective quantitative basis for risk classification.

[0047] Compared with the prior art, the advantages of this step mainly lie in three aspects: first, in the evaluation dimension, the prior art mostly uses a single risk scoring method, while the present application innovatively proposes a dual evaluation mechanism of geological condition influence factor and environmental sensitivity influence factor, which respectively fine evaluates from the two dimensions of medium propagation characteristics and carrier sensitivity, realizing the multi-dimensional deepening of risk evaluation; second, in the factor construction, the prior art usually uses a simple linear weighting method, while the present application more accurately reflects the propagation law of vibration waves in the actual medium and the interaction mechanism with the environmental structure by establishing a physical model containing exponential decay, logarithmic transformation and other nonlinear relationships; third, in the index fusion method, the prior art mostly stays at the simple data level integration, while the present application uses a method combining logarithmic compression and square root transformation, which highlights the influence of high-intensity vibration and balances the numerical differences between different dimension parameters, making the final comprehensive safety evaluation index more engineering interpretable and practical.

[0048] Step 4: calling the preset multi-level safety risk threshold, matching and analyzing the comprehensive safety evaluation index with the multi-level safety risk threshold, and determining the risk level of the current blasting operation according to the matching result; the risk level includes four levels of safety, low risk, medium risk, and high risk; In this embodiment, the preset multi-level safety risk threshold is called, the comprehensive safety evaluation index is matched and analyzed with the multi-level safety risk threshold, and the risk level of the current blasting operation is determined according to the matching result, which is based on the following specific logic: If , it is determined that the risk level of the current blasting operation is "safe"; If , it is determined that the risk level of the current blasting operation is "low risk"; If , it is determined that the risk level of the current blasting operation is "medium risk"; like , then the risk level of the current blasting operation is determined to be "high risk"; Where, 、 、 、 Represent the preset safety threshold upper limit, low risk threshold upper limit, medium risk threshold upper limit and high risk threshold lower limit respectively, and meet .

[0049] The multi-level safety risk thresholds are determined as follows: Based on a historical blasting case database, the distribution characteristics of the comprehensive safety assessment index Z value and the corresponding relationship between the actual vibration effects are statistically analyzed, and the threshold intervals are divided based on expert experience. Cluster analysis is used to identify the natural distribution boundaries of the Z value, and the risk level is divided into four typical intervals: safe, low risk, medium risk, and high risk. Machine learning algorithms are used to optimize the threshold boundaries to ensure that each threshold meets a strict numerical increment relationship and matches the actual risk level of the project. Once the threshold is determined, it is subject to field testing, verification, and feedback adjustment to ultimately form a multi-level safety risk threshold system suitable for specific project conditions.

[0050] Step 4: Comprehensive evaluation index With preset multi-level thresholds 、 、 、 By matching the continuous quantitative risk values ​​into four distinct levels of "safe, low risk, medium risk, and high risk," this method provides a direct basis for the precise implementation of differentiated control measures. Compared to the simple "safe / dangerous" dichotomy or the crude judgment based on a single empirical threshold in existing technologies, this method achieves a more refined differentiation of risk levels through a multi-level threshold system optimized based on historical data, significantly improving the targeted and operational nature of risk management.

[0051] Step 5: Implement differentiated control measures based on the determined risk level: For safety levels, implement the original plan and synchronize routine monitoring; for low-risk levels, enable real-time high-frequency vibration monitoring; for medium-risk levels, proportionally reduce the amount of single-stage explosives and extend the detonation time difference based on the low-risk control measures; for high-risk levels, suspend blasting operations and implement enhanced vibration reduction measures until the risk is reduced; In this embodiment, the specific execution process of step 5 is as follows: According to the determined risk level of the current blasting operation, corresponding hierarchical regulation and real-time feedback operation is performed: if the risk level is low risk, real-time high-frequency vibration monitoring sensors are arranged in the area where the predicted peak particle vibration velocity is greater than 0.5 cm / s and the sensitive structure within 50 m range from the center of the explosion source during blasting, the sampling frequency is not less than 1000 Hz, and the dynamic feedback monitoring data is fed back to the management platform; if the risk level is medium risk, on the basis of low risk monitoring, the single segment explosive quantity is reduced to 70% of the original design value, and the initiation time difference is extended to 1.5 times of the original design; if the risk level is high risk, the blasting operation is immediately suspended, and the intensification damping measures are taken, and the risk level is reevaluated until it is reduced to medium risk and below; at the same time, the regulation measures and execution results under each risk level are recorded to the database for optimizing the early warning model and threshold setting.

[0052] Step 5 converts the risk assessment results into specific pipe operation, realizing closed-loop management from prediction and early warning to precise execution. Differentiated measures are set for different risk levels: focus on monitoring high-frequency vibration area when the risk is low; quantitatively adjust the blasting parameters when the risk is medium: reduce the explosive quantity to 70%, and extend the time difference to 1.5 times; immediately stop work and take strengthening measures when the risk is high. Compared with the vague expressions such as "strengthen monitoring" or "adjust parameters" in the prior art, the present scheme gives clear quantitative execution standards and operation process, ensuring that the control measures can be implemented and verified. At the same time, through the whole process data recording, feedback is provided for model optimization, forming a virtuous cycle of continuous improvement.

[0053] Please refer to Figure 2 , a shallow tunnel blasting ground vibration waveform prediction system, comprising: a data acquisition and preprocessing module for collecting basic parameters of multiple shallow tunnel blasting constructions and corresponding vibration waveform time domain sequences, and basic parameters of the current shallow tunnel blasting; the basic parameters include geological parameters, blasting parameters and surrounding environment parameters, the basic parameters are classified and stored based on a three-level index table designed according to the parameter types, the effective parameters in the three-level index table are screened through an outlier detection algorithm, and the effective parameters are standardized to obtain a standardized parameter set; a mapping relationship determination module for analyzing the blasting parameters of each initiation section in the standardized parameter set and the corresponding vibration waveform time domain sequences, establishing a mapping relationship between the blasting parameters and the vibration waveform time domain sequences, and determining the corresponding predicted vibration waveform time domain sequence of the current blasting based on the mapping relationship; a safety index fusion calculation module for determining a geological condition influence factor and an environmental sensitivity influence factor according to the geological parameters and the surrounding environment parameters in the standardized parameter set, and performing fusion analysis on the geological condition influence factor, the environmental sensitivity influence factor and the predicted vibration waveform time domain sequence to generate a comprehensive safety evaluation index for quantitatively evaluating the safety of the current blasting. The risk grading module is configured to call preset multi-level safety risk thresholds, match and analyze the comprehensive safety evaluation index with the multi-level safety risk thresholds, and determine the risk level of the current blasting operation according to the matching result; the risk level includes four levels of safety, low risk, medium risk and high risk. The grading control measure execution module is configured to execute differential control measures according to the determined risk level: the safety level is implemented according to the original scheme and synchronized with the conventional monitoring; the real-time high-frequency vibration monitoring is enabled for the low risk level; the single-segment detonating charge is reduced in proportion and the detonation time difference is extended for the medium risk level on the basis of the low risk control; the blasting operation is suspended for the high risk level, and the enhanced shock absorption measures are taken until the risk is reduced.

[0054] The above formulas are dimensionless values calculated, the formulas are obtained by software simulation of a large number of collected data to obtain a formula of the nearest real situation, and the preset parameters in the formulas are set by a person skilled in the art according to the actual situation.

[0055] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized in the form of a computer program product wholly or partially. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0056] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0057] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for predicting a ground surface vibration waveform of a blast in a shallow tunnel, characterized by, The specific steps include: Step 1: Collect the basic parameters of multiple shallow tunnel blasting construction and the corresponding vibration waveform time domain sequence, as well as the basic parameters of the current shallow tunnel blasting; the basic parameters include geological parameters, blasting parameters and surrounding environment parameters, the basic parameters are classified and stored based on the three-level index table of parameter types, the effective parameters in the three-level index table are screened through an outlier detection algorithm, and the effective parameters are standardized to obtain a standardized parameter set; Step 2: Analyze the blasting parameters of each initiation section in the standardized parameter set and the corresponding vibration waveform time domain sequence, establish the mapping relationship between the blasting parameters and the vibration waveform time domain sequence, and determine the predicted vibration waveform time domain sequence corresponding to the current blasting based on the mapping relationship; Step 3: Determine the geological condition influence factor and the environmental sensitivity influence factor according to the geological parameters and the surrounding environment parameters in the standardized parameter set, and perform fusion analysis on the geological condition influence factor, the environmental sensitivity influence factor and the predicted vibration waveform time domain sequence to generate a comprehensive safety evaluation index for quantitatively evaluating the safety of the current blasting; Step 4: Call the preset multi-level safety risk threshold, match and analyze the comprehensive safety evaluation index with the multi-level safety risk threshold, and determine the risk level of the current blasting operation according to the matching result; the risk level includes four levels of safety, low risk, medium risk and high risk; Step 5: According to the determined risk level, differential control measures are executed: the safety level is implemented according to the original scheme and synchronous conventional monitoring; the low risk level enables real-time high-frequency vibration monitoring; the medium risk level reduces the single section initiation explosive quantity by a certain proportion and prolongs the initiation time difference on the basis of low risk control; the high risk level suspends the blasting operation and takes strengthening damping measures, and implements after the risk is reduced.

2. The method of claim 1, wherein the method is characterized by: The basic parameters of multiple shallow tunnel blasting construction and the corresponding vibration waveform time domain sequence, as well as the basic parameters of the current shallow tunnel blasting, are collected, and the specific collection methods are as follows: The geological parameters at multiple sampling points within a radius of the center point of the blasting source of the initiation section are obtained by borehole exploration, geological radar scanning and field rock mass mechanical test, including rock mass elastic modulus, rock mass Poisson's ratio, rock mass density, joint fissure density and soil layer shear wave velocity, and the average value is taken as the geological parameter value of the corresponding blasting source center point. The soil layer shear wave velocity refers to the speed of shear wave propagation in the soil layer and is used for evaluating the hardness and looseness of the soil layer. The blasting parameters are obtained from a blasting design scheme and an initiation system, including single-segment maximum charge quantity of each initiation segment, segmented initiation timing, blast hole depth, and corresponding center point spatial coordinates of the blast source; wherein the segmented initiation timing represents , the initiation time of the first center point of the explosive, is the index of the initiation segment, , represents the number of initiation segments, and each initiation segment corresponds to a center point of the blast source; By analyzing the design drawings and on-site detection, the peripheral environment parameters within a radius of 30 m around the center point of the detonation source of the initiation section are determined, including the building depth, building equivalent stiffness, underground pipeline diameter, and underground pipeline depth. The building depth and building equivalent stiffness of the building closest to the center point of the detonation source are taken as representative values for each center point of the detonation source. The shortest vertical distance from the center point of the detonation source to each pipeline is calculated, and the underground pipeline diameter and underground pipeline depth of the pipeline corresponding to the minimum value of the shortest vertical distance are taken as representative values. If there are multiple pipelines corresponding to the minimum value of the shortest vertical distance, the underground pipeline diameter and underground pipeline depth of the pipeline with the most sensitive material to vibration are taken as representative values. The first index of the three-level index table is the parameter category, which includes geological parameters, blasting parameters and surrounding environment parameters, the second index is the specific parameter name under each parameter category, and the third index is the time stamp and spatial coordinates of each parameter.

3. The method of claim 2, wherein the method is characterized by: When screening the effective parameters of the three-level index table through the outlier detection algorithm, a dual threshold method based on physical meaning and statistical distribution is adopted: first, the reasonable value range of each parameter is set according to engineering experience, and the parameter values exceeding the reasonable value range are determined as outliers and removed; Secondly, for the parameters within the reasonable value range, the box plot method is used to determine the discrete type of outliers and remove them, which are less than the lower quartile minus 3 times the interquartile range or greater than the upper quartile plus 3 times the interquartile range; The standardization processing adopts a range standardization method, and converts the parameter values screened according to the following formula to Interval: ； wherein is a parameter raw value, is a parameter normalized value, , are the minimum and maximum values of the current parameter to be normalized in the effective parameter set after the outlier screening, respectively. After the above processing, the standardized parameter set containing the standardized values of the geological parameters, the blasting parameters and the surrounding environment parameters is obtained.

4. The method of claim 3, wherein the method is characterized by: The blasting parameters of each initiation section in the standardized parameter set and the corresponding vibration waveform time domain sequence are analyzed, the mapping relationship between the blasting parameters and the vibration waveform time domain sequence is established, and the predicted vibration waveform time domain sequence corresponding to the current blasting is determined based on the mapping relationship, and the specific logic is as follows: A machine learning model is constructed based on a long short-term memory network. The blasting parameters and vibration waveform time domain sequences of the standardized parameter set of historical shallow tunnel blasting construction are divided into a training set, a validation set and a test set according to the proportions of 70%, 15% and 15%. The blasting parameters corresponding to each initiation section are used as the input of the model, and the vibration waveform time domain sequences corresponding to each initiation section are used as the output of the model for model training. The model has three LSTM hidden layers, with neuron numbers of 128, 64 and 32 respectively. The mean square error (MSE) is used as the loss function for model training, and the Adam optimizer is used, with a learning rate of 0.001, a first moment estimate exponential decay rate of 0.9, and automatic stopping of training when the validation set loss does not decrease for 10 consecutive rounds to prevent overfitting. After training, the blasting parameters corresponding to each initiation section of the current blasting operation are input into the model, and the model outputs the waveform time domain sequence corresponding to each initiation section. The waveform time domain sequences of all initiation sections are superimposed according to the initiation timing to form a complete predicted vibration waveform time domain sequence.

5. The method of claim 1, wherein the method is characterized by: According to the geological parameters and surrounding environmental parameters in the standardized parameter set, the geological condition influence factor and the environmental sensitivity influence factor are determined. The formula for calculating the geological condition influence factor is as follows: ； In the formula, is the geological condition influence factor of the nth explosion source center point, is the normalized parameter set, is the joint fissure density at the nth explosion source center point in the normalized parameter set, is the wave impedance influence factor, wherein is the rock density at the nth explosion source center point in the normalized parameter set, is the soil shear wave velocity at the nth explosion source center point in the normalized parameter set, is the rock elastic modulus at the nth explosion source center point in the normalized parameter set, is the maximum value of the rock elastic modulus in the normalized parameter set, is the rock Poisson's ratio at the nth explosion source center point in the normalized parameter set, , , and are preset weights, , , and are all non-negative numbers and satisfy ;​​​​​ For each initiation section The surrounding environment parameters corresponding to the explosion source center point are extracted from the standardized parameter set, including building burial depth, building equivalent stiffness, underground pipeline diameter, and underground pipeline burial depth; the building reflection correction coefficient and the underground pipeline attenuation correction coefficient are calculated based on the above parameters, so as to determine the environmental sensitivity influence factor, and the calculation formula is as follows: ； Where, For the The building reflection correction coefficient at the center of the explosion source is: For the The attenuation correction coefficient of underground pipelines at the center of each explosion source is: For the The environmental sensitivity influencing factor of the explosion source center, The first parameter in the standardized The equivalent stiffness of the building at the center of the explosion source is is the maximum value of the equivalent stiffness of the building in the standardized parameter set; The first parameter in the standardized The diameter of the underground pipeline at the center of the explosion source, is the maximum value of underground pipeline diameter in the standardized parameter set; The first parameter in the standardized The depth of underground pipelines at the center of each explosion source; The geological condition influence factor, the environmental sensitivity influence factor and the predicted vibration waveform time domain sequence are fused and analyzed to generate a comprehensive safety evaluation index for quantitative evaluation of the safety of the current blasting operation. The formula is as follows: ； wherein is a comprehensive safety evaluation index, denotes the number of initiation segments, is an index of the initiation segment, is the peak particle vibration velocity of the predicted vibration waveform time series of the i-th initiation segment; is the dominant frequency of the predicted vibration waveform time series of the i-th initiation segment.

6. The method of claim 5, wherein the method is characterized by: The preset multi-level safety risk threshold is called, and the comprehensive safety evaluation index is matched and analyzed with the multi-level safety risk threshold. According to the matching result, the risk level of the current blasting operation is determined. The specific logic is as follows: If then the risk level of the current blasting operation is determined as "safe"; If then the risk level of the current blasting operation is determined as "low risk"; If then the risk level of the current blasting operation is determined as "medium risk"; If then the risk level of the current blasting operation is determined as "high risk"; In the formula, , , , respectively represent the preset upper limit of the safety threshold, the upper limit of the low-risk threshold, the upper limit of the medium-risk threshold, and the lower limit of the high-risk threshold, and satisfy .

7. The method of claim 1, wherein the method is characterized by: The specific execution process of step 5 is as follows: According to the determined risk level of the current blasting operation, corresponding hierarchical regulation and real-time feedback operations are performed: if the risk level is low, real-time high-frequency vibration monitoring sensors are arranged in the area where the predicted peak particle vibration velocity is greater than 0.5 cm / s and within 50 m of the blast source center point during blasting, with a sampling frequency not less than 1000 Hz, and dynamic feedback of monitoring data to the management platform; if the risk level is medium, the single-section initiation explosive quantity is reduced to 70% of the original design value and the initiation time difference is extended to 1.5 times of the original design based on the low-risk monitoring; if the risk level is high, the blasting operation is immediately suspended, and intensive shock absorption measures are taken, and the risk level is re-evaluated until it is reduced to medium risk or below; at the same time, the regulation measures and execution results under each risk level are recorded in the database for optimization of the early warning model and threshold setting.

8. A system for predicting ground vibration waveform of a blast in a shallow tunnel, characterized by: The shallow tunnel blasting ground vibration waveform prediction system is used to perform the shallow tunnel blasting ground vibration waveform prediction method of any one of claims 1-7, comprising: The data acquisition and preprocessing module is used for collecting basic parameters and corresponding vibration waveform time domain sequences of multiple shallow tunnel blasting constructions and basic parameters of the current shallow tunnel blasting; the basic parameters include geological parameters, blasting parameters and surrounding environment parameters, the basic parameters are classified and stored based on a three-level index table according to parameter types, effective parameters in the three-level index table are screened through an abnormal value detection algorithm, and the effective parameters are standardized to obtain a standardized parameter set; The mapping relationship determination module is used for analyzing blasting parameters of each detonation section in the standardized parameter set and corresponding vibration waveform time domain sequences, establishing a mapping relationship between the blasting parameters and the vibration waveform time domain sequences, and determining a predicted vibration waveform time domain sequence corresponding to the current blasting based on the mapping relationship; The safety index fusion calculation module is used for determining a geological condition influence factor and an environmental sensitivity influence factor according to the geological parameters and the surrounding environment parameters in the standardized parameter set, and performing fusion analysis on the geological condition influence factor, the environmental sensitivity influence factor and the predicted vibration waveform time domain sequence to generate a comprehensive safety evaluation index for quantitatively evaluating safety of the current blasting; The risk grading module is used for calling preset multi-level safety risk thresholds, matching and analyzing the comprehensive safety evaluation index and the multi-level safety risk thresholds, and determining a risk level of the current blasting operation according to a matching result; the risk level includes four levels of safety, low risk, medium risk and high risk; The graded control measure execution module is used for executing differential control measures according to the determined risk level: the safety level is implemented according to an original scheme and synchronous conventional monitoring; the low risk level enables real-time high-frequency vibration monitoring; the medium risk level reduces single-section detonating explosive quantity and prolongs detonation time difference according to a proportion on the basis of low risk control; and the high risk level suspends blasting operation and takes enhanced shock absorption measures, and implements the measures after the risk is reduced.

Images