A multi-sensor fusion tunnel smooth blasting monitoring system

Abstract

The present invention discloses a multi-sensor fusion tunnel smooth blasting monitoring system, belonging to the field of artificial intelligence technology. The present invention preprocesses and integrates the monitored data, constructs a tunnel digital model, and applies static loads and dynamic loads; obtains the safety critical values of various parameters in the tunnel digital model to obtain a tunnel critical value digital model, extracts the parameters exceeding the safety critical values, generates a tunnel abnormal parameter digital model, and uses the random forest algorithm to identify the abnormal patterns of smooth blasting; when the abnormal pattern of smooth blasting is related to the inside of the tunnel, reconstructs the tunnel digital model; when the optimization suggestions are related to smooth blasting, uses a support vector machine model combined with expert suggestions to obtain new blasting parameters; constructs a tunnel-smooth blasting association model, identifies association rules, and evaluates the influence degree of blasting parameters on tunnel monitoring parameters; applies particle swarm optimization to search for the best combination of blasting parameters to meet the set optimization objectives.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and specifically to a multi-sensor fusion tunnel smooth blasting monitoring system. Background Art

[0002] During the tunnel construction process, smooth blasting is a commonly used controlled blasting technology. By reasonably controlling the blasting parameters, the purpose of achieving a neat tunnel wall surface and reducing construction damage can be achieved. However, the complexity and uncertainty of smooth blasting often lead to potential safety hazards and quality problems in actual construction. The existing blasting monitoring methods mainly rely on single sensors, making it difficult to obtain comprehensive state information of the tunnel during the blasting process. In particular, it is impossible to identify and correct in a timely manner in case of blasting anomalies, which easily leads to the destruction of the tunnel structure and affects the construction efficiency and safety.

[0003] The existing methods for optimizing blasting parameters are mostly based on empirical formulas, lacking feedback optimization combined with real-time tunnel monitoring data, and unable to perform dynamic optimization for specific construction environments and blasting anomalies. The existing monitoring systems are difficult to achieve early identification of blasting abnormal patterns, unable to adjust blasting parameters in a timely manner, increasing construction risks. In addition, the assessment of the impact of tunnel structure safety after blasting is mostly carried out afterwards, and it is impossible to intervene preventively. The existing technologies are difficult to organically combine the tunnel state and blasting parameters through intelligent algorithms, difficult to achieve efficient blasting parameter optimization, and fail to make full use of artificial intelligence technology to intelligently adjust blasting parameters. Summary of the Invention

[0004] The purpose of the present invention is to provide a multi-sensor fusion tunnel smooth blasting monitoring system to solve the problems raised in the existing technology.

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

[0006] A multi-sensor fusion tunnel smooth blasting monitoring system, comprising:

[0007] Tunnel digital model construction module: including: a data acquisition unit and a tunnel digital model construction unit; wherein, the data acquisition unit obtains the stress, deformation and displacement of the tunnel wall, the vibration acceleration, frequency and duration inside the tunnel, the gas composition and corresponding concentration inside the tunnel, the temperature and humidity changes inside the tunnel, as well as the background noise and changes through multiple sensors; the tunnel digital model construction unit preprocesses and integrates the monitored data, constructs a tunnel digital model using a finite element model, applies static loads and dynamic loads, selects a solver according to the analysis target, and performs static and dynamic analyses;

[0008] Smooth surface blasting abnormal pattern acquisition module: including: critical value determination unit, abnormal parameter extraction unit and smooth surface blasting abnormal pattern recognition unit; wherein the critical value determination unit obtains the safety critical value of each parameter in the tunnel digital model to obtain the tunnel critical value digital model; the abnormal parameter extraction unit compares the tunnel critical value digital model with the tunnel digital model, extracts each parameter exceeding the safety critical value, and generates the tunnel abnormal parameter digital model; the smooth surface blasting abnormal pattern recognition unit extracts features from the tunnel abnormal parameter digital model, selects the random forest algorithm to analyze the features, uses historical data for training, and recognizes the abnormal pattern of smooth surface blasting;

[0009] Digital model and blasting parameter update module: including: internal repair suggestion unit and blasting parameter optimization unit; among them, when the abnormal pattern of smooth surface blasting is related to the interior of the tunnel, the internal repair suggestion unit will send the optimization suggestion to the staff to repair the interior of the tunnel, and rebuild the digital model of the tunnel after the tunnel is repaired; when the optimization suggestion is related to smooth surface blasting, the blasting parameter optimization unit obtains the blasting parameters of this smooth surface blasting, and uses the support vector machine model combined with expert suggestions to obtain new blasting parameters;

[0010] The optimal blasting parameter combination generation module includes: an association model construction unit, an association rule identification unit, an influence degree evaluation unit and an optimal parameter search unit; wherein, the association model construction unit associates the blasting parameters with the tunnel digital model to construct a tunnel-smooth surface blasting association model, the association rule identification unit uses correlation analysis to identify the association rules between each blasting parameter and the tunnel monitoring parameter, and the influence degree evaluation unit quantitatively evaluates the influence of the blasting parameters on the tunnel monitoring parameters through regression analysis; the optimal parameter search unit inputs the safety and efficiency indicators of the blasting operation, applies particle swarm optimization, and searches for the optimal blasting parameter combination based on the results of the tunnel-smooth surface blasting association model to meet the set optimization goals.

[0011] In the tunnel digital model construction module, stress sensors are used to measure the stress distribution of the tunnel wall, displacement sensors are used to monitor the displacement and deformation of the tunnel wall, vibration sensors are used to monitor the vibration acceleration, frequency and duration in the tunnel, gas sensors are used to monitor the gas composition and corresponding concentration in the tunnel, temperature and humidity sensors are used to monitor the temperature and humidity changes in the tunnel, and noise sensors are used to monitor background noise and changes; low-pass filters are applied to remove noise from the data, statistical methods are used to detect and eliminate outliers, data from different sensors are normalized, and all data are synchronized by timestamp.

[0012] In the tunnel digital model construction module, use ANSYS finite element analysis software to create the geometric model of the tunnel, input the geometric parameters of the tunnel to form a three-dimensional model of the tunnel; input the material properties of the tunnel and the physical and mechanical properties of the surrounding soil to define the material attributes; select hexahedron mesh as the mesh type for mesh division; set the contact surface between the tunnel wall and the soil as a fixed boundary to simulate the influence of soil pressure on the tunnel, and set the displacement constraint conditions of the tunnel.

[0013] Apply static loads, including traffic loads, earth pressure, and groundwater pressure inside the tunnel; apply dynamic loads, combine with the influence of the dynamic load of smooth blasting, input the blasting wave propagation model, and set the corresponding instantaneous pressure or vibration load; select a solver according to the analysis objective for static or dynamic analysis, set the solution parameters, monitor the calculation progress and convergence situation, and during the solution process, check the rationality of the calculation results; generate the stress distribution, displacement field, and deformation diagram of the tunnel wall, compare the model output with the on-site sensor monitoring data, and evaluate the sensitivity of the model to changes in different input parameters.

[0014] The selection of the solver mainly depends on the type and objective of the analysis. Static and dynamic problems are involved in tunnel analysis, so the corresponding solver should be selected:

[0015] Static analysis is used to analyze the long-term response of the tunnel under constant loads, such as traffic loads, earth pressure, and groundwater pressure. In this case, a static solver is selected to calculate the displacement, stress, and deformation of the tunnel. The static solver does not consider the influence of time on the results and is suitable for dealing with loads applied gradually or kept constant. Among them, the linear static analysis solver is used for linear stress analysis, assuming a linear relationship between the deformation and load of the material. It is applicable to small deformations and the initial stability analysis of the tunnel. The nonlinear static analysis solver is used to handle cases of material nonlinearity, geometric nonlinearity, and contact nonlinearity. For example, when the tunnel material undergoes plastic deformation under the ultimate stress, a nonlinear solver is required.

[0016] Dynamic analysis is used to simulate the influence of dynamic loads such as smooth blasting. Dynamic analysis considers time and inertial effects and evaluates the influence of blasting wave propagation on the instantaneous pressure and vibration of the tunnel. The transient dynamics solver is suitable for simulating the propagation process of the instantaneous pressure wave generated by smooth blasting, and can capture the vibration response inside the tunnel and the instantaneous deformation and stress changes caused by the blasting wave. The modal analysis solver is used to determine the natural frequencies and vibration modes of the tunnel structure, so as to evaluate the dynamic response of the tunnel under blasting loads. The frequency response solver is used to analyze the vibration response of the tunnel at specific frequencies, especially suitable for studying the frequency-related blasting impact.

[0017] When performing finite element analysis, checking the reasonableness of the calculation results is an important step to ensure the accuracy and credibility of the model. The reasonableness can be checked through the following methods:

[0018] During the analysis process, monitor the convergence of the solution. If the solution does not converge, that is, the solution keeps fluctuating or cannot reach a stable state, it means that the mesh division is too coarse, the boundary conditions are set improperly, or the solution parameters are unreasonable. Therefore, it is necessary to check whether the displacement, stress or other key responses gradually tend to be stable as the number of iterations increases, and adjust the solution parameters, such as the relaxation factor, time step, etc., to ensure convergence.

[0019] Compare the finite element analysis results with the theoretical calculations or code standards, such as the stress or displacement distribution of a linearly elastic material under known loads, to confirm whether the model is reasonable. If the results deviate too much, it may be necessary to recheck the boundary conditions, load settings and material properties.

[0020] Compare the stress distribution, displacement field and deformation diagram obtained from the finite element analysis with the monitoring data of sensors in the tunnel. For example, monitor the consistency of the stress and deformation of the tunnel wall with the model prediction values. If there are large deviations, it is necessary to re-evaluate the material properties or the way of load application.

[0021] Check whether there are unreasonable phenomena such as abnormal stress concentration or sudden displacement mutation in the model, especially near the contact surface and boundary conditions. If the local stress or displacement significantly exceeds the expectation, it is necessary to re-evaluate the reasonableness of the contact conditions, mesh division or boundary constraint conditions.

[0022] Sensitivity analysis is used to evaluate the response of the model to different input parameters to ensure the adaptability of the model to the actual construction environment. The following are the steps of sensitivity analysis:

[0023] Select key input parameters, such as the elastic modulus of the material, the charge density of smooth blasting, the load, etc. According to the actual working conditions and the uncertainty of the material, define the change range of these parameters. For example, gradually adjust parameters such as the elastic modulus and density within the range of ±10%.

[0024] While keeping other parameters unchanged, adjust the key parameters one by one and observe their effects on the output results such as the stress, displacement and deformation of the tunnel. For example, in the blasting wave propagation model, change the propagation speed of the blasting wave or the vibration load and observe the stress distribution or displacement change in the tunnel.

[0025] Calculate the change rate of the model output with respect to the input parameters to quantify the sensitivity of the model to each parameter. The sensitivity indicators used include the relative change rate and the elastic coefficient.

[0026] The changes in each input parameter and the corresponding output changes are plotted into sensitivity curves to visually show which parameters have a greater impact on the model results. For example, if the change in the vibration frequency of the blasting wave has a greater impact on the displacement of the tunnel wall, then this frequency will be a key optimization parameter.

[0027] Establish a blasting wave propagation model, including establishing a physical model and a mathematical model; determine the blasting materials used and their characteristics, and obtain the blasting parameters for this smooth blasting, including the decoupling coefficient, smooth hole spacing, minimum resistance line, hole proximity coefficient, linear charge density, and initiation interval time; among them, select a nonlinear elastic model for establishing the physical model, create a geometric model of the blasting source and the surrounding medium, and the surrounding medium includes the tunnel wall and soil; use the wave equation and the pressure attenuation model when establishing the mathematical model;

[0028] According to the propagation of the pressure wave generated by the explosion, use the wave equation to describe the wave characteristics:

[0029]

[0030] where u is the wave displacement, c is the wave speed, and t is the time;

[0031] Utilize the instantaneous high-pressure pulse generated during the explosion of the explosive, and use the following pressure attenuation model P(t):

[0032]

[0033] where P0 is the initial pressure during the explosion, α is the first empirical constant, n is the second empirical constant, and r is the distance from the explosion center;

[0034] Apply the instantaneous pressure boundary condition at the blasting center to simulate the pressure influence at the moment of explosion, set the contact condition between the tunnel wall and the soil to ensure the interaction during the propagation of the pressure wave; set the grid density at the blasting source to capture the instantaneous pressure change generated by the explosion; select an implicit solver to handle the dynamic load; set the time step and the solution accuracy to capture the dynamic response at the moment of explosion; generate the distribution map and the time history curve of the pressure wave after blasting to obtain the propagation situation of the pressure wave in the tunnel; compare the simulation results with the actual monitoring data to verify the blasting wave propagation model.

[0035] In the smooth blasting abnormal mode acquisition module, according to existing industry standards and research literature, determine the safety critical values of each parameter, organize the determined safety critical values into a digital model, and form a tunnel critical value digital model; compare the real-time monitoring data in the tunnel digital model with the tunnel critical value digital model item by item, identify the parameters that exceed the safety critical values, and record their specific values and change trends; summarize the parameters that exceed the safety critical values to form a tunnel abnormal parameter digital model, and classify them according to the nature of the parameters; analyze the change trends of the abnormal parameters to determine whether it is a single event or a continuous abnormality, use visualization tools to display the spatial distribution of the abnormal parameters in the tunnel, and identify high-risk areas; compare the abnormal parameters with historical data to confirm whether it is a real abnormality.

[0036] In the smooth blasting abnormal mode acquisition module, extract all the parameters that exceed the safety critical values from the tunnel abnormal parameter digital model to form a structured data set, label the extracted abnormal parameters to distinguish the normal state from the abnormal state; use correlation analysis to extract the time series characteristics, change rate characteristics and frequency domain characteristics of the abnormal parameters.

[0037] Divide the extracted features into a training set and a test set, use the training set data to train a random forest model, and after training, through the feature importance evaluation method provided by the random forest, identify the features that have the greatest impact on the smooth blasting abnormal mode; input the test set into the trained random forest model, obtain the prediction results of each sample, identify the abnormal mode of smooth blasting, form an abnormal mode output list, and use accuracy, recall rate and F1-score to evaluate the performance of the model.

[0038] In the digital model and blasting parameter update module, based on the abnormal mode of smooth blasting, combine expert knowledge and historical data to formulate specific repair plans, automatically send the optimization suggestions to the on-site staff through the system, and the staff carry out the repair work inside the tunnel according to the optimization suggestions to ensure that the tunnel structure returns to a safe state; during the repair process, monitor the parameters inside the tunnel through multiple sensors and record the data to evaluate the repair effect.

[0039] Organize and clean the new data collected during the repair process, regenerate the tunnel digital model according to the updated parameters, compare the reconstructed tunnel digital model with the actual monitoring data, and evaluate the impact of different parameter changes on the model results to ensure the robustness of the model.

[0040] In the digital model and blasting parameter update module, when the optimization suggestions are related to smooth blasting, obtain the blasting parameters of the current smooth blasting, and collect data related to historical blasting operations, including: cases of successful and failed blasts, specific blasting parameters used in the cases, and corresponding tunnel monitoring parameters; perform data preprocessing, extract the historical values of each blasting parameter, the changes in tunnel monitoring parameters after blasting, and the environmental conditions of the blasting operation, and divide the training set and the test set;

[0041] Using the grid search method, select the radial basis function as the SVM kernel function, select hyperparameters, use the training set to train the SVM model, and learn the mapping relationship between different blasting parameters and tunnel monitoring parameters; evaluate the model performance on the test set; combine the output of the support vector machine model with expert suggestions for comprehensive analysis to obtain new blasting parameters.

[0042] In the optimal blasting parameter combination generation module, integrate the blasting parameters and the corresponding tunnel monitoring parameters into a dataset to ensure that each set of blasting parameters corresponds to the subsequent monitoring results; calculate the correlation between each blasting parameter and the tunnel monitoring parameters using the Pearson correlation coefficient to generate a correlation matrix and identify positive and negative correlation relationships; apply the association rule learning algorithm Apriori to mine the relationship between the blasting parameters and the tunnel monitoring parameters and identify potential association rules;

[0043] Select a linear regression model for modeling, use the tunnel monitoring parameters as the dependent variable and the blasting parameters as the independent variable, divide the data into a training set and a test set, use the training set to train the regression model, and verify it on the test set to evaluate the fitting degree and prediction ability of the model, and quantitatively evaluate the influence degree of each blasting parameter on the tunnel monitoring parameters through the coefficients of the regression model; the larger the absolute value of the coefficient, the greater the influence of the blasting parameter on the tunnel monitoring parameters.

[0044] In the optimal blasting parameter combination generation module, construct a safety index SI based on the tunnel monitoring parameters and an efficiency index EI based on the blasting parameters. The objective function F is defined as:

[0045] F = w1 * SI + w2 * EI;

[0046] where w1 is the first weight coefficient and w2 is the second weight coefficient;

[0047] Set the number of particles to N. Each particle represents a set of blasting parameter combinations (x1, x2,..., x m ), where m is the number of parameters of the blasting parameters; randomly generate the initial position and velocity of each particle;

[0048] Calculate the fitness value F(x i) Use the defined objective function, where i traverses from 1 to m respectively; save the best position p of each particle i and the global best position g; update the velocity v of the particle using the following formula i and the position x i :

[0049] v i (t + 1) = w * v i (t) + c′1 * r′1 * (p i - x i (t)) + c′2 * r′2 * (g - x i (t));

[0050] x i (t + 1) = x i (t) + v i (t + 1);

[0051] where w is the inertia weight, c′1 is the first acceleration constant, c′2 is the second acceleration constant, r′1 is the first random number, r′2 is the second random number, and the value ranges of r′1 and r′2 are [0, 1], v i (t + 1) represents the velocity at time t + 1, x i (t + 1) represents the position at time t + 1;

[0052] Set the maximum number of iterations and the convergence threshold. When the convergence condition reaches the convergence threshold or the maximum number of iterations is reached, stop the iteration; output the global best position in the particle swarm, which is expressed as the optimal blasting parameter combination; apply the optimal parameters to the actual blasting operation, and monitor various parameters of the tunnel to verify the optimization effect, and further adjust the model parameters and optimization objectives according to the actual results for model iteration.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0054] 1. The present invention combines the correlation model between the tunnel digital model and the blasting parameters, uses artificial intelligence algorithms such as random forest and support vector machine to identify the blasting abnormal patterns, and dynamically optimizes the blasting parameters according to the tunnel monitoring data to achieve real-time adjustment, ensuring the safety and efficiency of construction.

[0055] 2. The present invention extracts the parameters exceeding the safety critical value by comparing the tunnel digital model with the safety critical value to generate an abnormal parameter model, and combines historical data for training and analysis, which can identify the smooth blasting abnormal patterns in advance, timely propose optimization suggestions, and reduce the risk of tunnel structure damage.

[0056] 3. The present invention uses the particle swarm optimization algorithm to automatically search for the optimal combination of blasting parameters based on the results of the tunnel - smooth blasting correlation model, ensuring the best blasting effect while meeting safety and efficiency indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is the system structure diagram of a multi - sensor fusion tunnel smooth blasting monitoring system of the present invention;

[0058] Figure 2 is the schematic diagram of the steps for generating the optimal combination of blasting parameters of a multi - sensor fusion tunnel smooth blasting monitoring system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0060] Embodiment: As Figure 1 - Figure 2 shown, the present invention provides a technical solution.

[0061] According to an embodiment of the present invention, as Figure 1 shown in the system structure diagram of a multi - sensor fusion tunnel smooth blasting monitoring system, a multi - sensor fusion tunnel smooth blasting monitoring system includes:

[0062] Tunnel digital model construction module: includes: a data acquisition unit and a tunnel digital model construction unit; wherein, the data acquisition unit obtains the stress, deformation and displacement of the tunnel wall, the vibration acceleration, frequency and duration in the tunnel, the gas composition and corresponding concentration in the tunnel, the temperature and humidity changes in the tunnel, as well as the background noise and changes through multiple sensors; the tunnel digital model construction unit pre - processes and integrates the monitored data, constructs a tunnel digital model using a finite - element model, applies static loads and dynamic loads, selects a solver according to the analysis target, and performs static and dynamic analyses;

[0063] Smooth surface blasting abnormal pattern acquisition module: including: critical value determination unit, abnormal parameter extraction unit and smooth surface blasting abnormal pattern recognition unit; wherein the critical value determination unit obtains the safety critical value of each parameter in the tunnel digital model to obtain the tunnel critical value digital model; the abnormal parameter extraction unit compares the tunnel critical value digital model with the tunnel digital model, extracts each parameter exceeding the safety critical value, and generates the tunnel abnormal parameter digital model; the smooth surface blasting abnormal pattern recognition unit extracts features from the tunnel abnormal parameter digital model, selects the random forest algorithm to analyze the features, uses historical data for training, and recognizes the abnormal pattern of smooth surface blasting;

[0064] Digital model and blasting parameter update module: including: internal repair suggestion unit and blasting parameter optimization unit; among them, when the abnormal pattern of smooth surface blasting is related to the interior of the tunnel, the internal repair suggestion unit will send the optimization suggestion to the staff to repair the interior of the tunnel, and rebuild the digital model of the tunnel after the tunnel is repaired; when the optimization suggestion is related to smooth surface blasting, the blasting parameter optimization unit obtains the blasting parameters of this smooth surface blasting, and uses the support vector machine model combined with expert suggestions to obtain new blasting parameters;

[0065] The optimal blasting parameter combination generation module includes: an association model construction unit, an association rule identification unit, an influence degree evaluation unit and an optimal parameter search unit; wherein, the association model construction unit associates the blasting parameters with the tunnel digital model to construct a tunnel-smooth surface blasting association model, the association rule identification unit uses correlation analysis to identify the association rules between each blasting parameter and the tunnel monitoring parameter, and the influence degree evaluation unit quantitatively evaluates the influence of the blasting parameters on the tunnel monitoring parameters through regression analysis; the optimal parameter search unit inputs the safety and efficiency indicators of the blasting operation, applies particle swarm optimization, and searches for the optimal blasting parameter combination based on the results of the tunnel-smooth surface blasting association model to meet the set optimization goals.

[0066] In the tunnel digital model construction module, stress sensors are used to measure the stress distribution of the tunnel wall, displacement sensors are used to monitor the displacement and deformation of the tunnel wall, vibration sensors are used to monitor the vibration acceleration, frequency and duration in the tunnel, gas sensors are used to monitor the gas composition and corresponding concentration in the tunnel, temperature and humidity sensors are used to monitor the temperature and humidity changes in the tunnel, and noise sensors are used to monitor background noise and changes; low-pass filters are applied to remove noise from the data, statistical methods are used to detect and eliminate outliers, data from different sensors are normalized, and all data are synchronized by timestamp.

[0067] In the tunnel digital model construction module, use ANSYS finite element analysis software to create the geometric model of the tunnel, input the geometric parameters of the tunnel to form a three-dimensional model of the tunnel; input the material properties of the tunnel and the physical and mechanical properties of the surrounding soil to define the material properties; select hexahedral mesh as the mesh type and conduct mesh division; set the contact surface between the tunnel wall and the soil as a fixed boundary to simulate the influence of soil pressure on the tunnel, and set the displacement constraint conditions of the tunnel.

[0068] Apply static loads, including traffic loads, earth pressure, and groundwater pressure inside the tunnel; apply dynamic loads, combine with the influence of the dynamic loads of smooth blasting, input the blasting wave propagation model, and set the corresponding instantaneous pressure or vibration loads; select a solver according to the analysis target to conduct static or dynamic analysis, set the solution parameters, monitor the calculation progress and convergence situation, and during the solution process, check the rationality of the calculation results; generate the stress distribution, displacement field, and deformation diagram of the tunnel wall, compare the model output with the on-site sensor monitoring data, and evaluate the sensitivity of the model to changes in different input parameters.

[0069] In this embodiment, input the material properties of the tunnel wall, such as the elastic modulus, Poisson's ratio, density, etc. of concrete, and the physical and mechanical properties of the surrounding soil, such as the friction coefficient, cohesion, elastic modulus of the soil, etc., to define the properties of each part of the material in the finite element model. The nonlinear elastic model is used to capture the dynamic response of the material during blasting. Set the contact surface between the tunnel wall and the soil as a fixed boundary to simulate the action of earth pressure. For the boundary of the tunnel structure, apply displacement constraints to prevent unreasonable displacement changes. The static loads include traffic loads, earth pressure, and groundwater pressure inside the tunnel. In terms of dynamic loads, apply the instantaneous pressure or vibration loads generated by combining smooth blasting to simulate the wave effect generated by the explosion.

[0070] Establish a blasting wave propagation model, including establishing a physical model and a mathematical model; determine the blasting materials used and their properties, and obtain the blasting parameters of this smooth blasting, including the decoupling coefficient, smooth hole spacing, minimum resistance line, hole proximity coefficient, linear charge density, and initiation interval time; among them, select the nonlinear elastic model for establishing the physical model, create the geometric models of the blasting source and the surrounding medium, and the surrounding medium includes the tunnel wall and the soil; in this embodiment, use the nonlinear elastic model to create the geometric models of the blasting source and its surrounding medium (tunnel wall and soil). Considering the mechanical properties of different materials, ensure high-precision simulation of the blasting center through mesh division.

[0071] When establishing the mathematical model, use the wave equation and the pressure attenuation model.

[0072] According to the propagation of the pressure wave generated by the explosion, use the wave equation to describe the wave characteristics:

[0073]

[0074] where u is the fluctuating displacement, c is the wave speed, and t is the time;

[0075] Using the instantaneous high-pressure pulse generated by the explosive explosion, the following pressure decay model P(t) is used:

[0076]

[0077] where P0 is the initial pressure at the time of explosion, α is the first empirical constant, n is the second empirical constant, and r is the distance from the explosion center;

[0078] Apply the instantaneous pressure boundary condition at the blasting center to simulate the pressure influence at the moment of explosion, set the contact condition between the tunnel wall and the soil to ensure the interaction during the propagation of the pressure wave; set the grid density at the blasting source to capture the instantaneous pressure change generated by the explosion; select the implicit solver to handle the dynamic load; set the time step and the solution accuracy to capture the dynamic response at the moment of explosion; generate the distribution map and the time history curve of the pressure wave after blasting to obtain the propagation situation of the pressure wave in the tunnel; compare the simulation results with the actual monitoring data to verify the blasting wave propagation model.

[0079] In the smooth blasting abnormal mode acquisition module, according to the existing industry standards and research literature, determine the safety critical value of each parameter, organize the determined safety critical values into a digital model to form a tunnel critical value digital model; compare the real-time monitoring data in the tunnel digital model with the tunnel critical value digital model item by item, identify the parameters that exceed the safety critical value, and record their specific values and change trends; summarize the parameters that exceed the safety critical value to form a tunnel abnormal parameter digital model and classify them according to the nature of the parameters; analyze the change trend of the abnormal parameters to determine whether it is a single event or a continuous abnormality, use a visualization tool to display the spatial distribution of the abnormal parameters in the tunnel, and identify the high-risk areas; compare the abnormal parameters with the historical data to confirm whether it is a real abnormality.

[0080] In this embodiment, the geometric parameters of a certain tunnel are as follows: tunnel diameter: 8 m, tunnel length: 200 m, tunnel wall thickness: 0.5 m, tunnel wall material: concrete, elastic modulus is 30 GPa, Poisson's ratio is 0.2, density is 2400 kg / m 3 ; The blasting parameters are set as follows: initial pressure of the blasting source: 10 MPa, distance from the blasting point to the tunnel wall: 2 m, empirical constant: n = 2.5;

[0081] Through the pressure wave propagation model, the results show that: Maximum stress: The maximum stress at the tunnel wall is 12 MPa. Maximum displacement: The maximum displacement at the tunnel wall is 0.002 m. Pressure wave attenuation: The pressure at a distance of 2 m from the explosion center is 8 MPa, and it attenuates to 3 MPa at 5 m.

[0082] In the smooth blasting abnormal mode acquisition module, all parameters exceeding the safety critical values are extracted from the tunnel abnormal parameter digital model to form a structured data set. The extracted abnormal parameters are labeled to distinguish the normal state from the abnormal state. Using correlation analysis, the time series features, change rate features, and frequency domain features of the abnormal parameters are extracted.

[0083] The extracted features are divided into a training set and a test set. The training set data is used to train a random forest model. After training, through the feature importance evaluation method provided by the random forest, the features most influential on the smooth blasting abnormal mode are identified. The test set is input into the trained random forest model to obtain the prediction results of each sample, identify the abnormal mode of smooth blasting, and form an abnormal mode output list. The performance of the model is evaluated using accuracy, recall, and F1-score. In this embodiment, the extracted features are divided into a training set (70%) and a test set (30%).

[0084] In the digital model and blasting parameter update module, based on the abnormal mode of smooth blasting, combined with expert knowledge and historical data, a specific repair plan is formulated. The optimization suggestions are automatically sent to the on-site staff through the system. The staff carry out the repair work inside the tunnel according to the optimization suggestions to ensure that the tunnel structure is restored to a safe state. During the repair process, the parameters inside the tunnel are monitored by multiple sensors, and the data is recorded to evaluate the repair effect. In this embodiment, based on the abnormal mode of smooth blasting, combined with expert knowledge and historical data, a specific repair plan is formulated. For example, according to the change rates of stress and displacement, it is recommended to adjust the blasting charge amount and increase the support measures. The optimization suggestions are automatically sent to the on-site staff through the system, and the on-site personnel carry out the tunnel repair work according to the suggestions, such as strengthening the tunnel wall and adjusting the blasting parameters.

[0085] The new data collected during the repair process is sorted and cleaned, and a new tunnel digital model is regenerated according to the updated parameters. The reconstructed tunnel digital model is compared with the actual monitoring data to evaluate the impact of different parameter changes on the model results and ensure the robustness of the model.

[0086] In the digital model and blasting parameter update module, when the optimization suggestions are related to smooth blasting, obtain the blasting parameters of the current smooth blasting, collect data related to historical blasting operations, including: successful and failed blasting cases, specific blasting parameters used in the cases, and corresponding tunnel monitoring parameters; perform data preprocessing, extract the historical values of each blasting parameter, the changes in tunnel monitoring parameters after blasting, and the environmental conditions of the blasting operation, and divide the training set and the test set;

[0087] Use the grid search method to select the radial basis function as the SVM kernel function, select hyperparameters, use the training set to train the SVM model, and learn the mapping relationship between different blasting parameters and tunnel monitoring parameters; evaluate the model performance on the test set; combine the output of the support vector machine model with expert suggestions for comprehensive analysis to obtain new blasting parameters.

[0088] In the optimal blasting parameter combination generation module, integrate the blasting parameters and the corresponding tunnel monitoring parameters into a data set to ensure that each set of blasting parameters corresponds to the subsequent monitoring results; use the Pearson correlation coefficient to calculate the correlation between each blasting parameter and the tunnel monitoring parameters, generate a correlation matrix, identify positive and negative correlation relationships. In this embodiment, the correlation coefficient between the linear charge density and the tunnel wall stress is 0.82 (strong positive correlation), and the correlation coefficient between the initiation interval time and the tunnel vibration acceleration is -0.68 (negative correlation); apply the association rule learning algorithm Apriori to mine the relationship between the blasting parameters and the tunnel monitoring parameters and identify potential association rules; through association rule learning, it is found that when the linear charge density is greater than 0.7 kg / m and the smooth hole spacing is less than 0.5 m, the risk of exceeding the limit of the tunnel wall stress increases significantly (confidence level is 85%).

[0089] Select a linear regression model for modeling, use the tunnel monitoring parameters as the dependent variable and the blasting parameters as the independent variable, divide the data into a training set and a test set, use the training set to train the regression model, and verify it on the test set to evaluate the fitting degree and prediction ability of the model. Through the coefficients of the regression model, quantitatively evaluate the influence degree of each blasting parameter on the tunnel monitoring parameters; the larger the absolute value of the coefficient, the greater the influence of the blasting parameter on the tunnel monitoring parameters.

[0090] The SVM model has good performance and can accurately predict the tunnel monitoring parameters after blasting. By combining the output of the SVM model with expert suggestions, the optimal blasting parameter schemes under different parameter combinations were identified. The results of linear regression analysis show that the linear charge density, initiation interval time, and smooth blasting hole spacing have significant effects on the tunnel monitoring parameters. The linear charge density has the greatest positive effect on the tunnel wall stress, and the initiation interval time has a significant negative effect on the vibration acceleration. The results of association rule mining provide multiple potential parameter combination rules. For example, the combination of a higher linear charge density and a smaller smooth blasting hole spacing may increase the risk of exceeding the limit of the tunnel wall stress.

[0091] According to another embodiment of the present invention, as Figure 2 shown in the schematic diagram of the generation steps of the optimal blasting parameter combination of a multi-sensor fusion tunnel smooth blasting monitoring system, in the optimal blasting parameter combination generation module, a safety index SI is constructed based on the tunnel monitoring parameters, and an effectiveness index EI is constructed based on the blasting parameters. The objective function F is defined as:

[0092] F = w1 * SI + w2 * EI.

[0093] Where, w1 is the first weight coefficient, and w2 is the second weight coefficient;

[0094] Set the number of particles to N = 100. Each particle represents a set of blasting parameter combinations (x1, x2,..., x m ), where m is the number of parameters of the blasting parameters; randomly generate the initial position and velocity of each particle;

[0095] Calculate the fitness value F(x i ) for each particle, using the defined objective function, where i traverses from 1 to m respectively; save the best position p i of each particle and the global best position g; update the velocity v i and position x i of the particle using the following formulas

[0096] : i v i (t + 1) = w * v i (t) + c′1 * r′1 * (p i - x i (t)) + c′2 * r′2 * (g - x

[0097] x i (t + 1) = x i (t) + v i (t + 1);

[0098] Among them, w is the inertia weight, set to 0.7, c′x is the first acceleration constant, set to 1.5, c′2 is the second acceleration constant, set to 1.5, r′1 is the first random number, r′2 is the second random number, and the value ranges of r′1 and r′2 are [0, 1], v i (t + 1) represents the velocity at time t + 1, x i (t + 1) represents the position at time t + 1;

[0099] Set the maximum number of iterations to 1000 times and the convergence threshold to 0.001. When the convergence condition reaches the convergence threshold or the maximum number of iterations is reached, stop the iteration; output the global best position in the particle swarm, which is expressed as the optimal blasting parameter combination; apply the optimal parameters to the actual blasting operation and monitor various parameters of the tunnel to verify the optimization effect, and further adjust the model parameters and optimization objectives according to the actual results for model iteration.

[0100] In this embodiment, some blasting parameters are as follows: charge amount: 0.5 - 1.5 kg / m, smooth blasting hole spacing: 0.3 - 0.8 m, minimum burden: 0.8 - 1.5 m, linear charge density: 0.4 - 1.0 kg / m, initiation interval time: 0.001 - 0.005 s. Initial safety index (SI): tunnel wall stress: 11.2 MPa, tunnel displacement: 2.8 mm, vibration acceleration: 30 m / s 2 . Efficiency index (EI): blasting energy efficiency: increased by 15%.

[0101] Parameters before optimization: charge amount: 1.2 kg / m, smooth blasting hole spacing: 0.5 m, minimum burden: 1.2 m, linear charge density: 0.85 kg / m, initiation interval time: 0.003 s.

[0102] Monitoring results are as follows: tunnel wall stress: 11.2 MPa, tunnel displacement: 2.8 mm, vibration acceleration: 30 m / s 2 .

[0103] Parameters after PSO optimization: charge amount: 1.0 kg / m, smooth blasting hole spacing: 0.45 m, minimum burden: 1.0 m, linear charge density: 0.78 kg / m, initiation interval time: 0.0025 s.

[0104] Monitoring results are as follows: tunnel wall stress: 9.8 MPa (decreased by 12.5%), tunnel displacement: 2.1 mm (decreased by 25%), vibration acceleration: 25 m / s 2 (decreased by 16.7%).

[0105] It is obvious to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, in all respects, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A multi-sensor fusion tunnel smooth surface blasting monitoring system, characterized in that: include: Tunnel digital model construction module: including: data acquisition unit and tunnel digital model construction unit; the data acquisition unit uses multiple sensors to obtain the stress, deformation and displacement of the tunnel wall, the vibration acceleration, frequency and duration in the tunnel, the gas composition and corresponding concentration in the tunnel, the temperature and humidity changes in the tunnel, and the background noise and changes; the tunnel digital model construction unit pre-processes and integrates the monitored data, uses the finite element model to build a tunnel digital model, applies static loads and dynamic loads, selects a solver according to the analysis target, and performs static and dynamic analysis; In the tunnel digital model building module, the geometric model of the tunnel is created using ANSYS finite element analysis software, and the geometric parameters of the tunnel are input to form a three-dimensional model of the tunnel; the material properties of the tunnel and the physical and mechanical properties of the surrounding soil are input to define the material properties; the hexahedral grid is selected as the grid type for grid division; the contact surface between the tunnel wall and the soil is set as a fixed boundary to simulate the influence of soil pressure on the tunnel, and the displacement constraint conditions of the tunnel are set; Apply static loads, including traffic loads, soil pressure and groundwater pressure in the tunnel; apply dynamic loads, combine the impact of dynamic loads of smooth blasting, input blasting wave propagation model, and set corresponding instantaneous pressure or vibration loads; select solver according to analysis objectives, perform static or dynamic analysis, set solution parameters, monitor calculation progress and convergence, and check the rationality of calculation results during the solution process; generate stress distribution, displacement field and deformation diagram of tunnel wall, compare model output with field sensor monitoring data, and evaluate the sensitivity of model to changes in different input parameters; Establish a blast wave propagation model, including establishing a physical model and establishing a mathematical model; determine the blasting materials used and their characteristics, and obtain the blasting parameters of this smooth blasting, including the uncoupling coefficient, the smooth eye spacing, the minimum resistance line, the blast hole proximity coefficient, the line charge density and the detonation interval time; wherein, the physical model is established by selecting a nonlinear elastic model, and a geometric model of the blasting source and the surrounding medium is created, and the surrounding medium includes the tunnel wall and the soil; the wave equation and the pressure decay model are used when establishing the mathematical model; Smooth surface blasting abnormal pattern acquisition module: including: critical value determination unit, abnormal parameter extraction unit and smooth surface blasting abnormal pattern recognition unit; wherein the critical value determination unit obtains the safety critical value of each parameter in the tunnel digital model to obtain the tunnel critical value digital model; the abnormal parameter extraction unit compares the tunnel critical value digital model with the tunnel digital model, extracts each parameter exceeding the safety critical value, and generates the tunnel abnormal parameter digital model; the smooth surface blasting abnormal pattern recognition unit extracts features from the tunnel abnormal parameter digital model, selects the random forest algorithm to analyze the features, uses historical data for training, and recognizes the abnormal pattern of smooth surface blasting; Digital model and blasting parameter update module: including: internal repair suggestion unit and blasting parameter optimization unit; among them, when the abnormal pattern of smooth surface blasting is related to the interior of the tunnel, the internal repair suggestion unit will send the optimization suggestion to the staff to repair the interior of the tunnel, and rebuild the digital model of the tunnel after the tunnel is repaired; when the optimization suggestion is related to smooth surface blasting, the blasting parameter optimization unit obtains the blasting parameters of this smooth surface blasting, and uses the support vector machine model combined with expert suggestions to obtain new blasting parameters; In the digital model and blasting parameter update module, when the optimization suggestion is related to smooth surface blasting, the blasting parameters of this smooth surface blasting are obtained, and data related to historical blasting operations are collected, including: cases of successful and failed blasting, specific blasting parameters used in the cases, and corresponding tunnel monitoring parameters; data preprocessing is performed to extract the historical values ​​of each blasting parameter, changes in tunnel monitoring parameters after blasting, and environmental conditions of blasting operations, and divide the training set and test set; Using the grid search method, the radial basis function is selected as the SVM kernel function, the hyperparameters are selected, and the SVM model is trained using the training set to learn the mapping relationship between different blasting parameters and tunnel monitoring parameters; the model performance is evaluated on the test set; the output of the support vector machine model is combined with expert suggestions for comprehensive analysis to obtain new blasting parameters; The optimal blasting parameter combination generation module includes: an association model construction unit, an association rule identification unit, an influence degree evaluation unit and an optimal parameter search unit; wherein, the association model construction unit associates the blasting parameters with the tunnel digital model to construct a tunnel-smooth surface blasting association model, the association rule identification unit uses correlation analysis to identify the association rules between each blasting parameter and the tunnel monitoring parameter, and the influence degree evaluation unit quantitatively evaluates the influence of the blasting parameters on the tunnel monitoring parameters through regression analysis; the optimal parameter search unit inputs the safety and efficiency indicators of the blasting operation, applies particle swarm optimization, and searches for the optimal blasting parameter combination based on the results of the tunnel-smooth surface blasting association model to meet the set optimization goals.

2. The multi-sensor fusion tunnel smooth surface blasting monitoring system according to claim 1 is characterized by: In the tunnel digital model construction module, stress sensors are used to measure the stress distribution of the tunnel wall, displacement sensors are used to monitor the displacement and deformation of the tunnel wall, vibration sensors are used to monitor the vibration acceleration, frequency and duration in the tunnel, gas sensors are used to monitor the gas composition and corresponding concentration in the tunnel, temperature and humidity sensors are used to monitor the temperature and humidity changes in the tunnel, and noise sensors are used to monitor the background noise and changes; A low-pass filter is applied to remove noise from the data, outliers are detected and removed using statistical methods, data from different sensors are normalized, and all data are synchronized by timestamp.

3. The multi-sensor fusion tunnel smooth surface blasting monitoring system according to claim 1 is characterized by: According to the propagation of pressure waves generated by the explosion, the wave equation is used to describe the wave characteristics: Among them, u is the wave displacement, c is the wave speed, and t is the time; Using the instantaneous high-voltage pulse generated by the explosion of explosives, the following pressure decay model P(t) is used: Where P0 is the initial pressure at the time of explosion, α is the first empirical constant, n is the second empirical constant, and r is the distance from the explosion center; Instantaneous pressure boundary conditions are applied at the blasting center to simulate the pressure impact at the moment of explosion, and the contact conditions between the tunnel wall and the soil are set to ensure the interaction during the propagation of the pressure wave. The grid density is set at the blasting source to capture the instantaneous pressure changes caused by the explosion. An implicit solver is selected to process dynamic loads. The time step and solution accuracy are set to capture the dynamic response at the moment of explosion. The distribution diagram and time history curve of the pressure wave after the blasting are generated to obtain the propagation of the pressure wave in the tunnel. The simulation results are compared with the actual monitoring data to verify the blasting wave propagation model.

4. The multi-sensor fusion tunnel smooth surface blasting monitoring system according to claim 1 is characterized by: In the smooth blasting abnormal pattern acquisition module, the safety critical value of each parameter is determined according to existing industry standards and research literature, and the determined safety critical value is organized into a digital model to form a tunnel critical value digital model; the real-time monitoring data in the tunnel digital model is compared with the tunnel critical value digital model item by item, the parameters exceeding the safety critical value are identified, and their specific values ​​and change trends are recorded; Summarize the parameters that exceed the safety critical value to form a digital model of tunnel abnormal parameters, and classify them according to the nature of the parameters; analyze the changing trend of abnormal parameters to determine whether it is a single event or a continuous abnormality, use visualization tools to display the spatial distribution of abnormal parameters in the tunnel, and identify high-risk areas; Compare the abnormal parameters with historical data to confirm whether it is a true abnormality.

5. The multi-sensor fusion tunnel smooth surface blasting monitoring system according to claim 4 is characterized by: In the smooth blasting abnormal pattern acquisition module, all parameters exceeding the safety critical value are extracted from the digital model of tunnel abnormal parameters to form a structured data set. The extracted abnormal parameters are annotated to distinguish between normal and abnormal states. Correlation analysis is used to extract the time series characteristics, change rate characteristics and frequency domain characteristics of the abnormal parameters. The extracted features are divided into training set and test set. The training set data is used to train the random forest model. After the training is completed, the feature importance evaluation method provided by the random forest is used to identify the features that have the greatest impact on the abnormal pattern of smooth surface blasting. The test set is input into the trained random forest model to obtain the prediction result of each sample, identify the abnormal pattern of smooth surface blasting, form an abnormal pattern output list, and use accuracy, recall rate and F1-score to evaluate the performance of the model.

6. The multi-sensor fusion tunnel smooth surface blasting monitoring system according to claim 1 is characterized by: In the digital model and blasting parameter update module, a specific repair plan is formulated based on the abnormal pattern of smooth blasting, combined with expert knowledge and historical data. The optimization suggestions are automatically sent to the on-site staff through the system. The staff carry out the repair work inside the tunnel according to the optimization suggestions to ensure that the tunnel structure is restored to a safe state. During the repair process, multiple sensors are used to monitor the parameters inside the tunnel and record data to evaluate the repair effect; The new data collected during the repair process are sorted and cleaned, and the digital model of the tunnel is regenerated according to the updated parameters. The reconstructed digital model of the tunnel is compared with the actual monitoring data, and the impact of different parameter changes on the model results is evaluated to ensure the robustness of the model.

7. The multi-sensor fusion tunnel smooth surface blasting monitoring system according to claim 1 is characterized by: In the optimal blasting parameter combination generation module, the blasting parameters and the corresponding tunnel monitoring parameters are integrated into a data set to ensure that each set of blasting parameters corresponds to the subsequent monitoring results; The Pearson correlation coefficient is used to calculate the correlation between each blasting parameter and the tunnel monitoring parameter, generate a correlation matrix, and identify positive and negative correlations. The association rule learning algorithm Apriori is used to mine the relationship between blasting parameters and tunnel monitoring parameters and identify potential association rules. A linear regression model was selected for modeling. The tunnel monitoring parameters were used as dependent variables and the blasting parameters were used as independent variables. The data were divided into a training set and a test set. The regression model was trained using the training set and verified on the test set to evaluate the model's fit and prediction ability. The coefficients of the regression model were used to quantitatively evaluate the degree of influence of each blasting parameter on the tunnel monitoring parameters. The larger the absolute value of the coefficient, the greater the influence of the blasting parameter on the tunnel monitoring parameters.

8. The multi-sensor fusion tunnel smooth surface blasting monitoring system according to claim 7 is characterized by: In the optimal blasting parameter combination generation module, the safety index SI is constructed based on the tunnel monitoring parameters, and the efficiency index EI is constructed based on the blasting parameters. The objective function F is defined as: F = w1*SI+w2*EI; Wherein, w1 is the first weight coefficient, w2 is the second weight coefficient; Set the number of particles to N, and each particle represents a set of blasting parameter combinations (x1, x2, ..., x m ), where m is the number of parameters of the explosion parameters; the initial position and velocity of each particle are randomly generated; Calculate the fitness value F(x i ), using the defined objective function, where i traverses from 1 to m respectively; save the best position p of each particle i and the global optimal position g; update the particle's velocity v using the following formula i and position x i : v i (t+1)=w*v i (t)+c′1*r′1*(p i -x i (t))+c′2*r′2*(g-x i (t));x i (t+1)=x i (t)+v i (t+1); Where w is the inertia weight, c′1 is the first acceleration constant, c′2 is the second acceleration constant, r′1 is the first random number, r′2 is the second random number, and the value range of r′1 and r′2 is [0,1], v i (t+1) represents the speed at time t+1, x i (t+1) indicates the position at time t+1; The maximum number of iterations and the convergence threshold are set. When the convergence condition reaches the convergence threshold or the maximum number of iterations is reached, the iteration is stopped. The global optimal position in the particle swarm is output, which is expressed as the optimal blasting parameter combination. The optimal parameters are applied to the actual blasting operation, and the various parameters of the tunnel are monitored to verify the optimization effect. According to the actual results, the model parameters and optimization objectives are further adjusted to perform model iteration.

Images