Tunnel blasting vibration monitoring and early warning integrated system based on lining crack condition

Abstract

This invention relates to the field of tunnel blasting vibration monitoring technology, specifically an integrated system for monitoring and early warning of tunnel blasting vibration based on the condition of lining cracks. The invention extracts blasting vibration characteristic data from triaxial vibration signals at different key points during tunnel blasting, and performs correlation analysis with the vibration characteristic data of corresponding reference points to determine the correlation between blasting vibration and crack response, achieving accurate judgment of the relationship between blasting vibration and lining cracks. When a correlation exists between blasting vibration and crack response, a dynamic safety threshold is determined based on the health status of the lining cracks before tunnel blasting, and this threshold is compared with the vibration characteristic data in real time to trigger a graded early warning. When there is no correlation between blasting vibration and crack response, the change rate of crack characteristic data is analyzed by comparing the lining crack conditions over multiple time periods to predict the risk of autonomous crack propagation and trigger a reinforcement early warning, providing more timely and reliable protection for tunnel construction and operation safety, and effectively preventing the deterioration of lining cracks.

Description

Technical Field

[0001] This invention relates to the field of tunnel blasting vibration monitoring technology, and specifically to an integrated system for monitoring and early warning of tunnel blasting vibration based on the condition of lining cracks. Background Technology

[0002] With the continuous development of tunnel engineering construction, the impact of tunnel blasting operations on the lining structure has received increasing attention. Tunnel lining cracks are one of the important factors affecting the safe operation of tunnels, and blasting vibration may be a key cause of crack formation or expansion. Real-time monitoring of the impact of blasting vibration on lining cracks and timely early warning are of great significance for ensuring the safety of tunnel construction and operation.

[0003] Existing technologies, such as Chinese Patent Publication No. CN108491646A, disclose a method for identifying vibration damage caused by blasting when tunnels pass close to important buildings. This method involves selecting the building to be monitored for blasting vibration testing to obtain peak velocity and dominant vibration frequency. Combined with OMA modal testing, the modal parameters of the building are identified, a finite element model is established and corrected, and components that may be damaged under blasting vibration are investigated. Finally, the on-site cracking results are compared with the numerical calculation results to determine whether the damage is caused by blasting vibration. This method is ingeniously conceived, providing a feasible path for identifying blasting vibration damage to buildings, and is characterized by its simplicity and user-friendliness.

[0004] However, existing technologies have the following problems: 1. Existing technologies identify damage through finite element model correction and dynamic response analysis, but do not consider the influence of the initial health condition of cracks on the vibration response. In tunnel engineering, the health of lining cracks directly determines its vibration resistance. Ignoring this factor will cause the vibration damage assessment results to deviate from reality, reducing the accuracy of the assessment.

[0005] 2. Existing technologies only focus on damage caused by blasting vibrations and do not address the autonomous extension of cracks under non-blasting vibration factors. Tunnel lining cracks may extend due to their own evolution rather than blasting vibrations, making it impossible to accurately determine whether blasting vibrations are the direct cause of crack extension. This results in blind spots in safety management and increases the risk of structural instability. Summary of the Invention

[0006] This invention aims to overcome the shortcomings of existing technologies and provide an integrated system for monitoring and early warning of tunnel blasting vibration based on the condition of tunnel lining cracks. By monitoring blasting vibration signals in real time, the system can accurately determine the correlation between blasting vibration and crack response, dynamically assess the health status of tunnel lining cracks, and trigger graded early warnings in a timely manner, effectively ensuring the safety of tunnel construction and operation.

[0007] The technical solution adopted by the present invention to solve its technical problem is: an integrated system for monitoring and early warning of tunnel blasting vibration based on the condition of lining cracks, including a vibration characteristic monitoring module, a vibration correlation determination module, a crack health diagnosis module, a vibration damage risk assessment module, and a crack autonomous extension analysis module.

[0008] The connections between the modules are as follows: the vibration characteristic monitoring module is connected to the vibration correlation determination module; the crack health diagnosis module is connected to both the vibration correlation determination module and the vibration damage risk assessment module; and the crack autonomous propagation analysis module is connected to the vibration correlation determination module.

[0009] The vibration characteristic monitoring module uses a three-dimensional vibration sensor array deployed at key locations of lining cracks to collect vibration signals at different key points during tunnel blasting in real time, and extracts vibration characteristic data from the vibration signals.

[0010] The vibration correlation determination module performs correlation analysis between the vibration characteristic data of different key points and the vibration characteristic data of reference points deployed around the key locations to determine the correlation between blasting vibration and crack response.

[0011] The crack health diagnosis module acquires the initial condition of the tunnel lining cracks before blasting when there is a correlation between blasting vibration and crack response. It quantifies crack feature data through feature extraction technology and outputs the lining crack health status in combination with the crack health assessment model.

[0012] The vibration damage risk assessment module corrects the tunnel's safe vibration velocity based on the health of the lining cracks to determine the dynamic safety threshold, and compares it with vibration characteristic data in real time to trigger graded early warnings.

[0013] The crack autonomous propagation analysis module analyzes the rate of change of crack characteristic data by comparing the crack conditions of the lining over multiple time periods when there is no correlation between blasting vibration and crack response. Based on the rate of change of crack characteristic data, it predicts the risk of autonomous crack propagation and triggers reinforcement warning.

[0014] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention uses a triaxial vibration sensor array to collect triaxial vibration signals at different key points during tunnel blasting in real time. Through preprocessing and feature extraction of blasting vibration feature data, it provides rich data support for subsequent analysis and evaluation, effectively improving the comprehensiveness and accuracy of blasting vibration monitoring.

[0015] (2) This invention obtains the correlation index between cracks and vibration by combining the peak velocity of the composite vector and the proportion of high-frequency energy at each key point of the lining crack with the ratio calculation of the corresponding reference point, thereby accurately determining the correlation between blasting vibration and crack response, avoiding misjudgment or omission, and realizing accurate judgment of the relationship between blasting vibration and lining crack.

[0016] (3) This invention uses image feature extraction technology and ultrasonic detection technology to obtain surface features and depth information of cracks respectively, and outputs the health status of lining cracks according to the constructed crack health assessment model, which provides a quantitative basis for tunnel safety assessment, increases the dynamic assessment function of lining crack health status, and helps to understand the development trend and severity of cracks in a timely manner.

[0017] (4) The present invention determines the dynamic safety threshold based on the health of the lining cracks and triggers graded early warning by comparing vibration characteristic data in real time; at the same time, by comparing and analyzing the lining crack conditions in multiple time periods, it predicts the risk of autonomous crack extension and triggers reinforcement early warning, thereby achieving effective early warning of the risk of autonomous crack extension, providing more timely and reliable protection for tunnel construction and operation safety, effectively preventing further deterioration of lining cracks and reducing tunnel safety risks. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the system module connections of the present invention.

[0020] Figure 2 This is a schematic diagram of the correlation determination process between blasting vibration and crack response in this invention.

[0021] Figure 3 This is a schematic diagram illustrating the steps involved in setting up the crack health assessment model in this invention. Detailed Implementation

[0022] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention. Furthermore, it should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale.

[0023] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use. Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and apparatus should be considered part of the specification.

[0024] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0025] This invention relates to the field of tunnel blasting vibration monitoring technology, specifically to an integrated system for monitoring and early warning of tunnel blasting vibration based on the condition of lining cracks. The invention extracts blasting vibration characteristic data from triaxial vibration signals at different key points during tunnel blasting, and performs correlation analysis with the vibration characteristic data of corresponding reference points to determine the correlation between blasting vibration and crack response, achieving accurate judgment of the relationship between blasting vibration and lining cracks. When a correlation exists between blasting vibration and crack response, a dynamic safety threshold is determined based on the health status of the lining cracks before tunnel blasting, and this threshold is compared with the vibration characteristic data in real time to trigger a graded early warning. When there is no correlation between blasting vibration and crack response, the change rate of crack characteristic data is analyzed by comparing the lining crack conditions over multiple time periods to predict the risk of autonomous crack propagation and trigger a reinforcement early warning, providing more timely and reliable protection for tunnel construction and operation safety, and effectively preventing the deterioration of lining cracks.

[0026] Please see Figure 1 As shown, the present invention provides an integrated system for monitoring and early warning of tunnel blasting vibration based on the condition of lining cracks, including a vibration characteristic monitoring module, a vibration correlation determination module, a crack health diagnosis module, a vibration damage risk assessment module, and a crack autonomous extension analysis module.

[0027] The connections between the modules are as follows: the vibration characteristic monitoring module is connected to the vibration correlation determination module; the crack health diagnosis module is connected to both the vibration correlation determination module and the vibration damage risk assessment module; and the crack autonomous propagation analysis module is connected to the vibration correlation determination module.

[0028] The vibration characteristic monitoring module uses a three-dimensional vibration sensor array deployed at key locations of lining cracks to collect vibration signals at different key points during tunnel blasting in real time, and extracts vibration characteristic data from the vibration signals.

[0029] It should be noted that the specific contents of the vibration characteristic monitoring module are as follows: triaxial vibration sensors are deployed at different key locations of the tunnel lining cracks and at reference points around the key locations of the cracks to form a triaxial vibration sensor array.

[0030] During tunnel blasting operations, the triaxial vibration sensor array begins to work, collecting triaxial vibration signals at key points in real time.

[0031] The collected triaxial vibration signals were preprocessed, and the triaxial peak velocities and the energy of each frequency component were quantitatively analyzed from the preprocessed vibration signals.

[0032] Key locations of tunnel lining cracks include, but are not limited to: crack tip locations, intersection locations, stress concentration locations, and the location directly behind the widest point on the lining surface. These key locations are selected to ensure that vibration sensors can effectively capture the most sensitive vibration response signals. A high-precision triaxial vibration sensor array is used, with each sensor independently measuring the vibration components in the X, Y, and Z directions.

[0033] The collected triaxial vibration signals are preprocessed by applying digital filters to remove non-blasting-related signal components such as environmental noise and electromagnetic interference. Then, wavelet transform or blind source separation technology is used to separate noise and enhance the signal-to-noise ratio. The processed signals are stored as standardized waveforms for subsequent analysis, ensuring the accuracy and robustness of feature extraction.

[0034] This invention employs a triaxial vibration sensor array to collect triaxial vibration signals at different key points during tunnel blasting in real time. Through preprocessing and feature extraction of blasting vibration characteristic data, it provides rich data support for subsequent analysis and evaluation, effectively improving the comprehensiveness and accuracy of blasting vibration monitoring.

[0035] The vibration correlation determination module performs correlation analysis between the vibration characteristic data of different key points and the vibration characteristic data of reference points deployed around the key locations to determine the correlation between blasting vibration and crack response.

[0036] like Figure 2 As shown, determining the correlation between blasting vibration and crack response specifically includes: performing a composite vector analysis on the triaxial peak velocities of each key point of the lining crack to obtain the composite vector peak velocities.

[0037] The analysis method for the peak velocity of the synthesized vector is as follows: In the formula To synthesize the peak velocity vector, These are the peak vibration velocities in the X, Y, and Z directions, respectively.

[0038] High-frequency energy is selected from the energy of each frequency component at each key point, and the ratio of high-frequency energy to the sum of the energy of each frequency component is taken as the high-frequency energy percentage. In tunnel blasting vibration analysis, high-frequency energy specifically refers to the vibration energy carried by a specific high-frequency band in the vibration signal, which is a key indicator for assessing the potential damage of blasting to the lining structure.

[0039] The correlation analysis of the crack-vibration correlation index at each key point is obtained by performing ratio calculations on the peak velocity and high-frequency energy ratio of the synthesized vector at each key point and the peak velocity and high-frequency energy ratio of the synthesized vector at the corresponding reference point. In this invention, the ratio calculation can be performed by multiplying the ratio of the peak velocity of the synthesized vector at the corresponding reference point by the ratio of the high-frequency energy ratio to the high-frequency energy ratio of the corresponding reference point.

[0040] If the correlation index between cracks and vibration at all key points is less than the set correlation index threshold, it is determined that there is no correlation between blasting vibration and crack response; otherwise, it is determined that there is a correlation between blasting vibration and crack response.

[0041] This invention obtains the correlation index between cracks and vibration by combining the composite vector peak velocity and high-frequency energy ratio of key points of lining cracks with the ratio calculation of corresponding reference points. This accurately determines the correlation between blasting vibration and crack response, avoiding misjudgment or omission, and achieving precise judgment on the relationship between blasting vibration and lining cracks.

[0042] The crack health diagnosis module acquires the initial condition of the tunnel lining cracks before blasting when there is a correlation between blasting vibration and crack response. It quantifies crack feature data through feature extraction technology and outputs the lining crack health status in combination with the crack health assessment model.

[0043] It should be noted that the specific method for quantifying crack feature data through feature extraction technology is as follows: a laser scanner is integrated into a mobile platform, and point cloud data of the tunnel lining surface is continuously scanned by emitting a laser beam. Crack areas in the lining are then identified from the point cloud data. The crack areas in the point cloud appear as local discontinuities or abrupt changes in depth, which can directly reflect the changes in the surface length, direction, and width of the crack.

[0044] Edge detection is performed on the cracked area of ​​the lining to extract the edge contour of the cracked area, and the crack length, crack width and crack direction angle are located from the edge contour.

[0045] Ultrasonic detectors installed on a mobile platform emit ultrasonic waves to different locations in the lining crack area. The crack depth at different locations is calculated by recording the propagation time difference of the reflected waves, and the maximum crack depth is selected.

[0046] In one specific embodiment, the crack length is located as follows: the start and end points of the edge contour are located using pixel coordinates, the pixel distance between the two points is calculated using the Euclidean distance formula, and then the pixel distance is converted into crack length by combining the scale used during image acquisition. For irregular curved cracks, the farthest endpoints at both ends need to be selected.

[0047] The method for locating the crack width is as follows: extract pixels on both sides of the edge contour of the lining crack area, calculate the distance between adjacent pixels, and select the maximum distance as the crack width.

[0048] The crack direction angle positioning method is as follows: the edge contour of the lining crack area is divided into several line segments at equal length intervals. The direction vector of each line segment is determined by the position coordinates of the two ends of the line segment. The direction vector of each line segment is classified by a clustering algorithm. The direction with the highest proportion is taken as the main direction. The angle between the direction vector of the main direction and the tunnel axial vector is taken as the crack direction angle.

[0049] like Figure 3 As shown, the crack health assessment model is set up as follows: S1, collect multiple sets of historical monitoring data corresponding to tunnel lining cracks, where the historical monitoring data includes crack feature data and health scores. Standardize the crack feature data to form a dataset. The standardization process can use the Z-score standardization method to convert each feature data into a standardized value with a mean of 0 and a standard deviation of 1.

[0050] S2. Divide the dataset into training and testing sets according to a set ratio. Use the standardized crack feature data in the training set as input features and the health score as the target variable. Substitute them into the set linear regression equation for training to obtain the regression coefficients and constant terms of the feature data and construct the initial crack health assessment model.

[0051] S3. Predict the health score of the test set using the initial crack health assessment model, adjust and optimize the initial crack health assessment model using accuracy and mean square error, and output the final crack health assessment model.

[0052] In one specific embodiment, the accuracy rate is the ratio of the number of samples in the test set that correctly predicted the health score to the total number of samples in the test set.

[0053] The mean squared error is the difference between the health score predicted by the model and the actual health score in the test set.

[0054] The adjustment and optimization conditions for the initial crack health assessment model are as follows: when the accuracy is less than the set accuracy or the mean square error is greater than the set mean square error, the regression coefficients and constant terms of the feature data in the constructed initial crack health assessment model are adjusted and optimized. Cross-validation can be used to evaluate the accuracy and recall of the initial crack health assessment model under different parameter combinations. When the accuracy is greater than the set accuracy and the mean square error is less than the set mean square error, the final crack health assessment model is output.

[0055] It should be noted that the output method for the lining crack health status is as follows: the crack length, crack width, maximum crack depth, and crack orientation angle in the quantified crack feature data are standardized. The standardized crack feature data is then substituted into the final crack health status assessment model to output a lining crack health status score. The lining crack health status is obtained based on this score. The ratio of the lining crack health status score to the total score is used as the lining crack health status.

[0056] This invention uses image feature extraction technology and ultrasonic detection technology to obtain the surface features and depth information of cracks, and outputs the health status of lining cracks based on the constructed crack health assessment model. This provides a quantitative basis for tunnel safety assessment, adds a dynamic assessment function for the health status of lining cracks, and helps to understand the development trend and severity of cracks in a timely manner.

[0057] The vibration damage risk assessment module corrects the tunnel's safe vibration velocity based on the health of the lining cracks to determine the dynamic safety threshold, and compares it with vibration characteristic data in real time to trigger graded early warnings.

[0058] It should be noted that the specific content of the vibration damage risk assessment module is as follows: Using the energy of each frequency component as a weight, a weighted average analysis is performed on the frequency to output the dominant centroid frequency of the vibration signal. Based on the dominant centroid frequency, the permissible mass vibration velocity of the tunnel at the corresponding frequency is selected. Specifically, the permissible mass vibration velocity of the tunnel at the corresponding dominant centroid frequency is selected from the tunnel blasting safety database based on the calculated dominant centroid frequency.

[0059] A dynamic safety threshold is generated based on a combination of the allowable mass vibration velocity in the tunnel and the health status of the lining cracks. In this invention, the combination operation can be a product operation.

[0060] The comparison results between the peak velocity of the synthesized vector at different key points and the dynamic safety threshold are used to determine the graded early warning.

[0061] The formula for calculating the centroid dominant frequency of the vibration signal can be: In the formula, The core frequency is the main frequency. These are the minimum and maximum values ​​of the frequency component numbers, respectively. For the k-th frequency component, For frequency components The energy below.

[0062] The method for determining the graded early warning is as follows: if the peak velocity of the composite vector at a certain key point is greater than or equal to the dynamic safety threshold, an emergency audible and visual alarm is triggered; if the peak velocity of the composite vector at all key points is less than the dynamic safety threshold, a safety hazard warning is issued.

[0063] The crack autonomous propagation analysis module analyzes the rate of change of crack characteristic data by comparing the crack conditions of the lining over multiple time periods when there is no correlation between blasting vibration and crack response. Based on the rate of change of crack characteristic data, it predicts the risk of autonomous crack propagation and triggers reinforcement warning.

[0064] It should be noted that the method for predicting the risk of autonomous crack propagation is as follows: the edge contour area of ​​the lining crack region is obtained from the lining crack conditions in multiple time periods. A coordinate system is established with time period as the horizontal axis and edge contour area as the vertical axis. Points are plotted on the edge contour area of ​​the lining crack region in the established coordinate system to construct the change curve of crack edge contour area with time period, and the change rate of crack edge contour area is located from it.

[0065] The maximum crack depth and crack orientation angle are extracted from the crack conditions of the lining at multiple time periods. The maximum crack depth and maximum crack orientation angle are then selected. The crack depth ratio is obtained based on the ratio of the maximum crack depth to the lining thickness.

[0066] Substitute the crack edge contour area change rate, crack depth ratio, and maximum crack direction angle into the set crack extension type risk prediction rule to output the crack autonomous extension type risk and trigger the corresponding reinforcement warning.

[0067] In one specific embodiment, the crack extension type risk prediction rule is set as follows: if the maximum value of the crack direction angle is greater than the set longitudinal crack direction angle threshold, then the self-extension type of the lining crack is the longitudinal extension type, and when the crack depth ratio is greater than the set crack depth ratio threshold, then the lining crack is in the longitudinal extension type risk.

[0068] Conversely, the self-extending type of the lining crack is classified as the transverse extension type. When the rate of change of the crack edge contour area is greater than the set threshold for the rate of change of the crack contour area or the crack depth ratio is greater than the set threshold for the crack depth ratio, the lining crack is at risk of transverse extension.

[0069] This invention determines a dynamic safety threshold based on the health status of lining cracks and triggers graded early warnings by comparing vibration characteristic data in real time. At the same time, by comparing and analyzing the lining crack conditions over multiple time periods, it predicts the risk of autonomous crack propagation and triggers reinforcement early warnings, thus achieving effective early warning of the risk of autonomous crack propagation. This provides more timely and reliable protection for tunnel construction and operation safety, effectively prevents further deterioration of lining cracks, and reduces tunnel safety risks.

[0070] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0071] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0072] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0073] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0074] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0075] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions, characterized in that, include: The vibration characteristic monitoring module uses a three-dimensional vibration sensor array deployed at key locations of lining cracks to collect vibration signals at different key points during tunnel blasting in real time and extract vibration characteristic data from the vibration signals. The vibration correlation determination module performs correlation analysis between the vibration characteristic data of different key points and the vibration characteristic data of reference points deployed around the key locations to determine the correlation between blasting vibration and crack response. The crack health diagnosis module obtains the initial condition of the lining cracks before tunnel blasting when there is a correlation between blasting vibration and crack response. It quantifies crack feature data through feature extraction technology and outputs the lining crack health status in combination with the crack health assessment model. The vibration damage risk assessment module corrects the tunnel's safe vibration velocity based on the health of the lining cracks to determine the dynamic safety threshold, and compares it with vibration characteristic data in real time to trigger graded early warnings. The crack autonomous propagation analysis module analyzes the change rate of crack characteristic data by comparing the crack conditions of the lining over multiple time periods when there is no correlation between blasting vibration and crack response. Based on the change rate of crack characteristic data, it predicts the risk of autonomous crack propagation and triggers reinforcement warning. The method for predicting the risk of autonomous crack propagation is as follows: The edge contour area of ​​the lining crack region is obtained from the lining crack conditions in multiple time periods. A coordinate system is established with time period as the horizontal axis and edge contour area as the vertical axis. Points are plotted on the edge contour area of ​​the lining crack region in the established coordinate system to construct the change curve of crack edge contour area with time period, and the change rate of crack edge contour area is located from it. The maximum crack depth and crack orientation angle are extracted from the crack conditions of the lining at multiple time periods. The maximum crack depth and maximum crack orientation angle are then selected. The crack depth ratio is obtained based on the ratio of the maximum crack depth to the lining thickness. Substitute the crack edge contour area change rate, crack depth ratio, and maximum crack direction angle into the set crack extension type risk prediction rule to output the crack autonomous extension type risk and trigger the corresponding reinforcement warning.

2. The integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions as described in claim 1, characterized in that: The specific contents of the vibration characteristic monitoring module are as follows: Three-dimensional vibration sensors are deployed at different key locations of tunnel lining cracks and at reference points around the key locations of the cracks to form a three-dimensional vibration sensor array. During tunnel blasting operations, the triaxial vibration sensor array begins to work, collecting triaxial vibration signals at key points in real time. The collected triaxial vibration signals were preprocessed, and the triaxial peak velocities and the energy of each frequency component were quantitatively analyzed from the preprocessed vibration signals.

3. The integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions as described in claim 2, characterized in that: The determination of the correlation between blasting vibration and crack response specifically includes: The composite vector peak velocity is obtained by performing a composite vector analysis on the triaxial peak velocities at each key point of the lining crack. High-frequency energy is selected from the energy of each frequency component at each key point, and the ratio of high-frequency energy to the sum of the energy of each frequency component is taken as the proportion of high-frequency energy. The correlation analysis of the peak velocity and high-frequency energy ratio of the synthetic vector at each key point with the peak velocity and high-frequency energy ratio of the synthetic vector at the corresponding reference point is performed to obtain the correlation index between cracks and vibration at each key point. If the correlation index between cracks and vibration at all key points is less than the set correlation index threshold, it is determined that there is no correlation between blasting vibration and crack response; otherwise, it is determined that there is a correlation between blasting vibration and crack response.

4. The integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions as described in claim 1, characterized in that: The specific method for quantifying crack feature data using feature extraction technology is as follows: A laser scanner is integrated into a mobile platform to continuously scan and acquire point cloud data of the tunnel lining surface by emitting a laser beam, and the crack areas of the lining are identified from the point cloud data. Edge detection is performed on the cracked area of ​​the lining to extract the edge contour of the cracked area, and the crack length, crack width and crack direction angle are located from the edge contour. Ultrasonic detectors installed on a mobile platform emit ultrasonic waves to different locations in the lining crack area. The crack depth at different locations is calculated by recording the propagation time difference of the reflected waves, and the maximum crack depth is selected.

5. The integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions according to claim 4, characterized in that: The method for locating the crack orientation angle is as follows: The edge contour of the lining crack area is divided into several line segments at equal length intervals. The direction vector of each line segment is determined by the coordinates of the two endpoints of the line segment. A clustering algorithm is used to classify the direction vectors of each line segment. The direction with the highest proportion is taken as the main direction. The angle between the direction vector of the main direction and the tunnel axial vector is taken as the crack direction angle.

6. The integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions as described in claim 4, characterized in that: The crack health assessment model is set up as follows: Multiple sets of historical monitoring data corresponding to tunnel lining cracks were collected. The historical monitoring data included crack feature data and health scores. The crack feature data were standardized to form a dataset. The dataset is divided into training and testing sets according to a set ratio. The standardized crack feature data in the training set is used as the input feature, and the health score is used as the target variable. The data are substituted into the set linear regression equation for training to obtain the regression coefficients and constant terms of the feature data, and to build the initial crack health assessment model. The initial crack health assessment model is used to predict the health score of the test set. The initial crack health assessment model is adjusted and optimized using accuracy and mean squared error, and the final crack health assessment model is output.

7. The integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions as described in claim 6, characterized in that: The method for outputting the health status of the lining cracks is as follows: The crack length, crack width, maximum crack depth, and crack orientation angle in the quantified crack feature data are standardized. The standardized crack feature data are then substituted into the final crack health assessment model to output the lining crack health score. The lining crack health is obtained based on the lining crack health score.

8. The integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions according to claim 2, characterized in that: The specific contents of the vibration damage risk assessment module are as follows: Using the energy of each frequency component as a weight, the frequency is weighted and averaged to output the centroid frequency of the vibration signal. Based on the centroid frequency, the safe allowable mass point vibration velocity at the corresponding frequency is selected. A dynamic safety threshold is generated based on a combination of the tunnel's permissible mass vibration velocity and the health of the lining cracks. The comparison results between the peak velocity of the synthesized vector at different key points and the dynamic safety threshold are used to determine the graded early warning.

9. The integrated system for monitoring and early warning of tunnel blasting vibration based on lining crack conditions according to claim 1, characterized in that: The method for setting the risk prediction rule for crack propagation type is as follows: If the maximum value of the crack direction angle is greater than the set threshold for the longitudinal crack direction angle, then the self-extension type of the lining crack is the longitudinal extension type, and when the crack depth ratio is greater than the set threshold for the crack depth ratio, then the lining crack is at risk of longitudinal extension type. Conversely, the self-extension type of the lining crack is classified as the transverse extension type. When the rate of change of the crack edge contour area is greater than the set threshold for the rate of change of the crack contour area or the crack depth ratio is greater than the set threshold for the crack depth ratio, the lining crack is at risk of transverse extension type.

Images