Deformation monitoring and early warning method and system for existing tunnel

Abstract

The invention relates to the field of tunnel early warning, in particular to a deformation monitoring and early warning method and system for an existing tunnel, and the method comprises the steps: extracting historical monitoring image sequences of a plurality of image monitoring point positions of a reference tunnel, analyzing the historical monitoring image sequences, and obtaining a target time point when the reference tunnel deforms; then, characteristics of load proportion, temperature and humidity, surrounding rock water content, vibration amplitude and vibration frequency of a tunnel lining in a period of time before deformation are extracted in combination with monitoring data of various geological structure categories of a reference tunnel, so that deformation characteristic template data are constructed, wherein the characteristics exist in the load proportion, the temperature and humidity, the surrounding rock water content, the vibration amplitude and the vibration frequency of the tunnel lining in a period of time before deformation; when deformation monitoring is carried out on the existing tunnel, deformation characteristic data of the load proportion, the temperature and humidity, the surrounding rock water content, the vibration amplitude and the vibration frequency in the existing tunnel are extracted, and similarity comparison is carried out on the deformation characteristic data and deformation characteristic template data to judge whether a deformation risk exists or not.

Description

Technical Field

[0001] The present invention relates to the field of tunnel warning, and specifically to a method and system for deformation monitoring and warning of existing tunnels. Background Art

[0002] During the construction process and the period of being put into use of a tunnel, it is necessary to conduct deformation monitoring and warning on the tunnel. The tunnel deformation warning technology can monitor the deformation of the tunnel structure in real time, and can issue an alarm in time once abnormal changes are found. This helps to take measures in advance to avoid or reduce personal injuries and property losses caused by disasters such as tunnel collapses and crack expansions.

[0003] In the prior art, the deformation monitoring of existing tunnels mainly relies on rangefinders to measure the inner wall of the tunnel, or uses contact monitoring equipment to monitor the tunnel, so as to detect the subtle deformations on the inner wall for warning. However, only detecting the surface of the tunnel lining cannot obtain the stress data of the surrounding rock and its changing trend. Therefore, it is impossible to predict the changes of the lining in advance according to the stress changes, and thus it is impossible to reinforce the lining in advance to avoid large deformations of the lining. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method and system for deformation monitoring and warning of existing tunnels to solve the above technical problems.

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

[0006] A method for deformation monitoring and warning of existing tunnels according to the present invention includes the steps of:

[0007] Obtaining a historical monitoring image sequence of multiple image monitoring points of a reference tunnel, a historical monitoring data sequence of multiple mechanical monitoring positions, and geological structure information of multiple mechanical monitoring positions, wherein the historical monitoring image sequence includes monitoring images at multiple historical time points, and the historical monitoring data sequence includes the load ratio, temperature and humidity, water content of the surrounding rock, vibration amplitude, and vibration frequency of the lining at multiple historical time points;

[0008] Determining the target positions where lining deformation exists and the target time points when lining deformation occurs in the existing tunnel based on the historical monitoring image sequence;

[0009] Classifying multiple mechanical monitoring positions based on the geological structure information to obtain geological structure categories; and constructing deformation feature template data based on the target monitoring data of the mechanical monitoring positions of each geological structure category, wherein the target monitoring data includes monitoring data at multiple historical time points of the target time point and a target time period before the target time point;

[0010] Obtain the monitoring data sequences and geological structure categories at multiple time points within a target time period before the current time point for the target location of the existing tunnel, and extract deformation feature data from the monitoring data sequences;

[0011] Determine the target deformation feature template data for the target location based on the geological structure category, compare the similarity between the deformation feature data and the target deformation feature template data, and perform deformation warning on the existing tunnel based on the comparison result.

[0012] In an embodiment of the present application, determining the target location with lining deformation and the target time point of lining deformation in the existing tunnel based on the historical monitoring image sequence includes:

[0013] Divide the historical monitoring images at any two adjacent time points in the historical monitoring image sequence into the same control group;

[0014] Use the previous frame image in the control group as the reference image and the latter frame image as the comparison image;

[0015] Perform preprocessing on the reference image and the comparison image respectively to obtain a first preprocessed image and a second preprocessed image, where the preprocessing methods include grayscale conversion and high-pass filtering;

[0016] Adjust the brightness of the first preprocessed image and the second preprocessed image to obtain a first image and a second image with consistent brightness; and extract the gap candidate regions with gray values less than a preset threshold from the first image and the second image;

[0017] Extract the contour features of the gap candidate regions; perform morphological processing on the contour features of the gap candidate regions to obtain the closed contour features of the gap candidate regions; calculate the size and roundness of the closed contour features, and use the contour features that meet the preset size range and roundness range as the top arch gap contours;

[0018] Draw the closed contour features of the first image and the second image onto a blank image respectively to obtain a first contour image and a second contour image;

[0019] Extract the centroids of the top arch gap contours and other closed contour features, and register the first contour image and the second contour image based on the centroid of the top arch gap contour;

[0020] Use the closed contour features with the closest centroid distance in the first contour image and the second contour image as the comparison contours, and calculate the coincidence rate ρ of each group of comparison contours. The mathematical expression of the coincidence rate ρ is:

[0021]

[0022] Wherein, A ol is the area of the overlapping part of the reference contour, and A max is the area of the contour with a larger area in the reference contour;

[0023] Restore the reference contour with the coincidence rate ρ less than the preset threshold to the reference image to obtain the deformation position; and take the time point of the reference image as the target time point.

[0024] In an embodiment of the present application, performing brightness adjustment on the first preprocessed image and the second preprocessed image to obtain a first image and a second image with consistent brightness, including:

[0025] Normalize the gray values of all pixel points in the first preprocessed image and the second preprocessed image to obtain a first normalized image and a second normalized image respectively;

[0026] Reassign the first normalized image and the second normalized image using the same gray range to obtain a first image and a second image with consistent brightness.

[0027] In an embodiment of the present application, constructing deformation feature template data based on the target monitoring data of the mechanical monitoring positions of each geological structure category, including:

[0028] Calculate the variance of each monitoring parameter at multiple historical time points in the target monitoring data;

[0029] When there is a target monitoring parameter in the target monitoring data with a variance greater than the preset corresponding variance threshold, extract the outlier of the target monitoring parameter, calculate the average value of other monitoring parameters at multiple historical time points, and construct a feature vector based on the outlier of the target monitoring parameter, the average value of other monitoring parameters at multiple historical time points, and the first parameter flag bit, where the value of the first parameter flag bit indicates that the feature vector is a mutation feature;

[0030] When there is no monitoring parameter in the target monitoring data with a variance greater than the preset variance threshold, calculate the average value of each monitoring parameter at multiple historical time points, and construct a feature vector based on the average value of each monitoring parameter at multiple historical time points and the second flag bit, where the second parameter flag bit indicates that the feature vector is a persistence feature;

[0031] Perform density clustering on all feature vectors to obtain multiple feature clusters;

[0032] Take the feature clusters with the number of feature vectors greater than the preset number threshold as target feature clusters, and calculate the average value of each monitoring parameter in the target feature clusters to obtain deformation feature template data.

[0033] In an embodiment of the present application, extracting deformation feature data from the monitoring data sequence includes:

[0034] Calculating the variances of multiple monitoring parameters in the monitoring data sequence at multiple time points;

[0035] When there are target monitoring parameters in the monitoring data sequence whose variances are greater than the preset corresponding variance thresholds, extracting the outliers of the target monitoring parameters, calculating the average values of other monitoring parameters at multiple historical time points, and constructing a feature vector based on the outliers of the target monitoring parameters, the average values of other monitoring parameters at multiple historical time points, and the first parameter flag bit, and using the feature vector as the deformation feature data;

[0036] When there are no monitoring parameters in the target monitoring data whose variances are greater than the preset variance threshold, calculating the average values of each monitoring parameter at multiple historical time points, and constructing deformation feature data based on the average values of each monitoring parameter at multiple historical time points and the second flag bit.

[0037] In an embodiment of the present application, extracting the outliers of the target monitoring parameters, calculating the average values of other monitoring parameters at multiple historical time points, and constructing a feature vector based on the outliers of the target monitoring parameters, the average values of other monitoring parameters at multiple historical time points, and the first parameter flag bit includes:

[0038] Calculating the average value of the target monitoring parameter at multiple historical time points; calculating the deviation rate of each value of the target monitoring parameter from the average value; taking the values with deviation rates greater than the set deviation ratio as outliers, clustering all the outliers to obtain multiple outlier clusters; calculating the average value of each outlier cluster to obtain the outliers of the target monitoring parameter;

[0039] Combining each outlier of the target monitoring parameter with the average values of other monitoring parameters at multiple historical time points and the first flag bit respectively to obtain one or more feature vectors.

[0040] In an embodiment of the present application, determining the target deformation feature template data of the target location based on the geological structure category, and comparing the similarity between the deformation feature data and the target deformation feature template data includes:

[0041] Determining the target deformation feature template data with the same geological structure category and the same flag bit as the target location;

[0042] Calculating the deviation rate D of each monitoring parameter between the deformation feature data and the target deformation feature template data, where the deviation rate D i The mathematical expression of is:

[0043]

[0044] Wherein, x i is the value of the i-th monitoring parameter in the deformation feature data, and x' i is the value of the i-th monitoring parameter in the target deformation feature template data, and x max is the maximum value of x i and x'; i When the deviation rate D at each position is less than the preset deviation rate threshold, it is determined that the deformation feature data is similar to the target deformation feature template data; otherwise, it is determined that the deformation feature data is not similar to the target deformation feature template data.

[0045] In an embodiment of the present application, based on the comparison result, deformation warning is performed on the existing tunnel, including: i When the comparison result is similar, the monitoring data sequence is marked as having a deformation risk and a warning message is generated, and the warning message is sent to the target object; when the comparison result is dissimilar, the monitoring data sequence is marked as having no deformation risk.

[0046] In an embodiment of the present application, the target position is a position where strain is likely to occur and is pre-marked.

[0047]

[0048]

[0049]

[0050] The present application also provides a deformation monitoring and warning system for an existing tunnel, including:

[0051] A sample acquisition module, configured to acquire a historical monitoring image sequence of multiple image monitoring points of a reference tunnel, a historical monitoring data sequence of multiple mechanical monitoring positions, and geological structure information of multiple mechanical monitoring positions, wherein the historical monitoring image sequence includes monitoring images at multiple historical time points, and the historical monitoring data sequence includes the load ratio of the lining, temperature and humidity, water content of the surrounding rock, vibration amplitude, and vibration frequency at multiple historical time points;

[0052] A deformation event screening module, configured to determine a target position where lining deformation exists and a target time point when lining deformation occurs in the existing tunnel based on the historical monitoring image sequence;

[0053] A template feature extraction module, configured to classify multiple mechanical monitoring positions based on the geological structure information to obtain geological structure categories; and construct deformation feature template data based on the target monitoring data of the mechanical monitoring positions of each geological structure category, wherein the target monitoring data includes monitoring data at multiple historical time points of the target time point and a target time period before the target time point;

[0053] A feature extraction module, configured to obtain a monitoring data sequence and a geological structure category at multiple time points within a target duration before the target position of an existing tunnel at the current time point, and extract deformation feature data from the monitoring data sequence;

[0054] A comparison and early warning module, configured to determine target deformation feature template data of the target position based on the geological structure category, compare the similarity between the deformation feature data and the target deformation feature template data, and perform deformation early warning on the existing tunnel based on the comparison result.

[0055] The beneficial effects of the present invention are as follows: A deformation monitoring and early warning method and system for an existing tunnel according to the present invention extract a historical monitoring image sequence of multiple image monitoring points of a reference tunnel, analyze the historical monitoring image sequence, and obtain the target time point when the reference tunnel deforms. Then, in combination with the monitoring data of multiple geological structure categories of the reference tunnel, the characteristics of the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency of the tunnel lining are extracted within a period of time before the deformation occurs, so as to construct deformation feature template data. When monitoring the deformation of an existing tunnel, the deformation feature data of the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency in the existing tunnel are extracted, and the deformation feature data and the deformation feature template data are compared for similarity to determine whether there is a deformation risk. The present application comprehensively analyzes various factors affecting the deformation of the tunnel lining, thereby providing an early warning method different from the lining surface detection. Combining with the existing lining surface detection technology, it can comprehensively monitor and early warn the deformation of the tunnel. Description of the Drawings

[0056] The present invention will be further described below with reference to the drawings and embodiments:

[0057] Figure 1 It is a cross-sectional structure diagram of an existing tunnel shown in an embodiment of the present application;

[0058] Figure 2 It is an application scenario diagram of the deformation monitoring and early warning method for an existing tunnel shown in an embodiment of the present application;

[0059] Figure 3 It is a flowchart of the deformation monitoring and early warning method for an existing tunnel shown in an embodiment of the present application;

[0060] Figure 4 It is a schematic diagram of the deformation determination process based on machine vision in an embodiment of the present application;

[0061] Figure 5 It is a structure diagram of a deformation monitoring and early warning system for an existing tunnel shown in an embodiment of the present application. Detailed Embodiments

[0062] The following describes the implementation manners of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention.

[0063] Figure 1 is a cross-sectional structure diagram of an existing tunnel shown in an embodiment of this application. As Figure 1 shown, the existing tunnel includes an initial support formed in the initial construction stage, and a segment 110 formed by strengthening the structure outside the initial support. The initial support and the segment 110 form a complete lining structure. The outside of the lining structure is surrounding rock, and contact pressure will be generated at the position where the surrounding rock contacts the lining. The contact pressure is not constant. Affected by temperature and humidity, groundwater activities, vibrations caused by the driving of vehicles in the tunnel, etc., the contact pressure will change, and when the change is large, it is easy to cause deformation of the lining.

[0064] Figure 2 is an application scenario diagram of a deformation monitoring and early warning method for an existing tunnel shown in an embodiment of this application. As Figure 2 shown, in this application, a pressure sensor 210 is arranged between the surrounding rock and the lining, and a temperature and humidity sensor 220, a vibration sensor 230, etc. are arranged in the internal structure of the surrounding rock. The above sensors are connected to the host through wires for analysis.

[0065] In addition, a camera 240 is arranged in the tunnel. The camera 240 sends the collected images of the tunnel vault and the gap images to the host for visual analysis. Combining the internal structure parameter analysis and the visual analysis of the surface structure, comprehensive deformation monitoring of the tunnel can be carried out. In this application, the visual analysis can adopt other existing visual analysis technologies, or can also adopt the visual analysis solution in this application below.

[0066] Figure 3 is a flowchart of a deformation monitoring and early warning method for an existing tunnel shown in an embodiment of this application. As Figure 3 shown: A deformation monitoring and early warning method for an existing tunnel in this embodiment may include steps S310 to S350:

[0067] S310, acquiring a historical monitoring image sequence of multiple image monitoring points of a reference tunnel, a historical monitoring data sequence of multiple mechanical monitoring positions, and geological structure information of multiple mechanical monitoring positions, wherein the historical monitoring image sequence includes monitoring images at multiple historical time points, and the historical monitoring data sequence includes load ratio, temperature and humidity, surrounding rock moisture content, vibration amplitude, and vibration frequency of the lining at multiple historical time points;

[0068] In the present application, it is easy to understand that the historical monitoring data sequence is regularly collected and constructed by sensors pre-buried in the tunnel structure, and the historical monitoring image sequence is regularly collected and acquired by fixed cameras set up in the tunnel.

[0069] The geological structure data is obtained from the survey data during the construction of the tunnel, such as bedding, joints, faults, folds and other structures. Different geological structures will have different effects and influences on the lining, so this application analyzes them separately based on the geological structures.

[0070] In addition, the reference tunnel in the present application may be the historical data of one tunnel or the historical data of multiple tunnels of the same category, and no limitation is made here.

[0071] S320, determining a target location where lining deformation exists in the existing tunnel and a target time point at which lining deformation occurs based on the historical monitoring image sequence; the target location is a pre-marked location where strain is prone to occur, such as a gap, a crown, etc.

[0072] Figure 4 FIG. 1 is a flow chart of deformation determination based on machine vision in an embodiment of the present application. Figure 4 As shown, in this application, machine vision technology is used to determine the historical monitoring images with deformation, and then determine the time point when the tunnel lining deformation occurs, including:

[0073] S321, dividing the historical monitoring images of any two adjacent time points in the historical monitoring image sequence into the same control group; and pairing and grouping the historical monitoring images of adjacent time points for subsequent comparative analysis.

[0074] S322, using the previous frame image in the control group as a reference image and the next frame image as a control image;

[0075] S323, preprocessing the reference image and the control image respectively to obtain a first preprocessed image and a second preprocessed image, wherein the preprocessing method includes grayscale conversion and high-pass filtering;

[0076] The image was preprocessed using grayscale conversion and high-pass filtering to highlight edge information and reduce unnecessary details. This improved the performance of subsequent processing steps, making important features such as cracks more visible.

[0077] S324. Adjust the brightness of the first preprocessed image and the second preprocessed image to obtain a first image and a second image with consistent brightness; and extract candidate gap regions with gray values less than a preset threshold from the first image and the second image;

[0078] Adjust the brightness of the two images to be consistent, and filter out regions that may represent gaps based on gray values. This ensures that images taken at different time points are compared under the same conditions, improving the accuracy of crack detection. Specifically, the process of brightness adjustment includes:

[0079] S3241. Normalize the gray values of all pixel points in the first preprocessed image and the second preprocessed image to obtain a first normalized image and a second normalized image respectively;

[0080] The mathematical expression of the normalized image is:

[0081]

[0082] In the formula, Normalized(i,j) represents the value of the pixel point (i,j) in the normalized image, gray(i,j) is the gray value of the pixel point (i,j) in the preprocessed image, gray min is the minimum gray value in the preprocessed image, gray max is the maximum gray value in the preprocessed image.

[0083] S3242. Reassign values to the first normalized image and the second normalized image using the same gray value range to obtain a first image and a second image with consistent brightness.

[0084] In this application, the value range of the first normalized image and the second normalized image is extended to 0 - 255. Therefore, the gray values of the first image and the second image are obtained in the following way.

[0085]

[0086] The images processed through the above process have consistent brightness, which is convenient for accurately representing different regions, such as gaps, with different gray features when extracting gray features later.

[0087] In the image, since the gap appears in the form of a shadow, the gray value is small. This application sets a gray threshold to filter out the gap region.

[0088] S325. Extract the contour features of the candidate gap region; perform morphological processing on the contour features of the candidate gap region to obtain the closed contour features of the candidate gap region; calculate the size and roundness of the closed contour features, and use the contour features that meet the preset size range and roundness range as the top arch gap contours.

[0089] After obtaining the candidate gap regions with lower gray values, to avoid the influence of patterns on the wall, some wall tiles or floor cracks. This application performs screening on the candidate gap regions based on contour features.

[0090] First, use the canny operator to extract the contour features of the candidate gap region, and then perform erosion and dilation on the contour features to form complete and closed contour features. Then extract the geometric information of the closed contour, such as size and roundness, to extract the contours of the top arch gaps and wall gaps that meet the preset size range and roundness.

[0091] As Figure 2 shown, at the lining connection, there will be connected top arch gaps and wall gaps, and these gaps change significantly during the deformation of the lining. Therefore, use the contours of these gaps as the reference parameters for whether the lining has deformed.

[0092] S326. Draw the closed contour features of the first image and the closed contour features of the second image into a blank image respectively to obtain a first contour image and a second contour image.

[0093] Draw the processed closed contour features onto a blank image to generate a first contour image and a second contour image that only contain contour information. This simplifies the image content, and subsequent processes can focus on the comparison of cracks and other key features.

[0094] S327. Extract the centroids of the top arch gap contours and other closed contour features, and register the first contour image and the second contour image based on the centroid of the top arch gap contour.

[0095] There are often multiple top arch gap contours in an image. Therefore, by extracting the centroids of multiple top arch gap contours, the first contour image and the second contour image can be accurately registered.

[0096] S328. Use the closed contour features with the closest centroid distance in the first contour image and the second contour image as the comparison contours, and calculate the coincidence rate ρ of each group of comparison contours. The mathematical expression of the coincidence rate ρ is:

[0097]

[0098] where A ol is the area of the overlapping part of the comparison contour, Amax is the area of the contour with a larger area in the control contour;

[0099] After registration, the centroids of each contour are used for combination, and the gap contour with the closest distance is used as the contour of the gap at the same position but different times. Then, calculate the area and coincidence rate of the overlapping part of the two contours, and judge whether the gap has changed significantly through the coincidence rate.

[0100] S329, restore the control contour with a coincidence rate ρ less than the preset threshold to the control image to obtain the deformation position; and use the time point of the control image as the target time point.

[0101] If the coincidence rate ρ is less than the preset threshold, it means that the two cannot be accurately overlapped, indicating that the gap has changed significantly. At this time, it can be determined that the lining corresponding to the gap has deformed. At this time, restore the control contour to the control image to obtain the deformation position. Use the shooting time point of the control image as the target time point when the deformation occurs.

[0102] S330, classify multiple mechanical monitoring positions based on the geological structure information to obtain geological structure categories; and construct deformation feature template data based on the target monitoring data of the mechanical monitoring positions of each geological structure category, where the target monitoring data includes the monitoring data of multiple historical time points at the target time point and the target duration before the target time point;

[0103] After the above machine vision analysis, the target time point when the deformation occurs is obtained, and the monitoring data can be analyzed based on the target time point to obtain the characteristics of the monitoring data when the lining deforms and for a period of time before the lining deforms.

[0104] In this embodiment, the deformation of the lining may be formed under long-term and stable comprehensive conditions. For example, a long-term high-temperature and high-humidity environment causes the load of the lining to be at a relatively high level for a long time. It may also be caused by suddenly changing monitoring parameters in a short period. For example, a sudden heavy rain causes a high water content in the surrounding rock, which in turn causes an increase in the groundwater water pressure and a change in the properties of the surrounding rock, and then causes the deformation of the lining.

[0105] In view of this, in this application, not only the target time point but also the monitoring data for a period of time before the target time point are analyzed. Specifically, it includes:

[0106] S331, calculate the variance of each monitoring parameter at multiple historical time points in the target monitoring data;

[0107] The variance can reflect the volatility of data. If the variance is large, it indicates that within a period between the target time points, the values of the monitoring parameters have changed drastically. In this case, it is speculated that the deformation is caused by the monitoring parameters with drastic changes. If the variance is small, it indicates that the deformation of the lining is not caused by the drastic changes in the values of the monitoring parameters, but by the fact that the values of multiple monitoring parameters have been within a stable range for a long time.

[0108] S332. When there is a target monitoring parameter with a variance greater than the preset corresponding variance threshold in the target monitoring data, extract the abnormal values of the target monitoring parameter, calculate the average values of other monitoring parameters at multiple historical time points, and construct a feature vector based on the abnormal values of the target monitoring parameter, the average values of other monitoring parameters at multiple historical time points, and the first parameter flag bit. Among them, the value of the first parameter flag bit indicates that the feature vector is a mutation feature.

[0109] If there is a target monitoring parameter with a variance greater than the preset corresponding variance threshold in the target monitoring data, then regard this piece of data as the data whose deformation is caused by mutation abnormal values, and thus construct a feature vector, and the feature vector contains the first flag bit.

[0110] The feature vector can be: (x1, x2, x3, x4, x5, x6, m), where x1 is the load ratio, x2 is the temperature, x3 is the humidity, x4 is the water content of the surrounding rock, x5 is the vibration amplitude, x6 is the vibration frequency, and m is the flag bit.

[0111] For the target monitoring data of the mutation type, the present application constructs a feature vector in the following manner, including:

[0112] S3321. Calculate the average value of the target monitoring parameter at multiple historical time points; and calculate the deviation rate of each value of the target monitoring parameter from the average value; regard the values with a deviation rate greater than the set deviation ratio as abnormal values, cluster all abnormal values, and obtain multiple abnormal value clusters; calculate the average value of each abnormal value cluster to obtain the abnormal value of the target monitoring parameter.

[0113] In this embodiment, the deviation rate is used to screen abnormal values. The abnormal values may be clustered in one interval or may be clustered in multiple intervals. It may be necessary to cluster all abnormal values to obtain the aggregation characteristics of the abnormal values.

[0114] The number of clusters obtained by clustering may be one or multiple, so the typical abnormal values obtained may also be one or multiple.

[0115] S3322. Combine each abnormal value of the target monitoring parameter with the average values of other monitoring parameters at multiple historical time points and the first flag bit respectively to obtain one or more feature vectors.

[0116] If there are multiple typical outliers, then a feature vector can be constructed based on the average values of such outliers and other monitoring parameters at multiple historical time points and the first flag bit.

[0117] S333. When there is no monitoring parameter in the target monitoring data with a variance greater than a preset variance threshold, calculate the average value of each monitoring parameter at multiple historical time points, and construct a feature vector based on the average value of each monitoring parameter at multiple historical time points and the second flag bit, where the second parameter flag bit indicates that the feature vector is a persistent feature;

[0118] If the lining deformation is not caused by mutation, then take the average value of the monitoring parameters during this period as its eigenvalue to construct a feature vector.

[0119] S334. Perform density clustering on all feature vectors to obtain multiple feature clusters;

[0120] In this application, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to perform density clustering, so as to obtain clusters of multiple feature vectors.

[0121] S335. Take the feature clusters with the number of feature vectors greater than a preset number threshold as target feature clusters, and calculate the average value of each monitoring parameter in the target feature clusters to obtain deformation feature template data.

[0122] If the amount of data in the cluster is large, it means that a large number of feature vectors are concentrated in one cluster, and the feature vectors in this cluster can reflect the feature template corresponding to a kind of lining deformation. Therefore, calculate the average value of the values of each monitoring parameter in the cluster as the typical value of the deformation feature template data.

[0123] S340. Obtain the monitoring data sequence and geological structure category of the target position of the existing tunnel at multiple time points within a target time period before the current time point, and extract deformation feature data from the monitoring data sequence;

[0124] The existing tunnel is the target tunnel that needs to be monitored for deformation in this application. The monitoring data sequence at multiple time points within a target time period before the current time point is collected through the sensors described above, and then feature extraction is performed, including:

[0125] S341. Calculate the variances of multiple monitoring parameters in the monitoring data sequence at multiple time points;

[0126] S342. When there is a target monitoring parameter with a variance greater than the corresponding preset variance threshold in the monitoring data sequence, extract the outlier of the target monitoring parameter, calculate the average value of other monitoring parameters at multiple historical time points, and construct a feature vector based on the outlier of the target monitoring parameter, the average value of other monitoring parameters at multiple historical time points, and the first parameter flag bit, and use the feature vector as the deformation feature data;

[0127] S343. When there is no monitoring parameter with a variance greater than the preset variance threshold in the target monitoring data, calculate the average value of each monitoring parameter at multiple historical time points, and construct deformation feature data based on the average value of each monitoring parameter at multiple historical time points and the second flag bit.

[0128] S350. Determine the target deformation feature template data of the target location based on the geological structure category, compare the similarity between the deformation feature data and the target deformation feature template data, and perform deformation warning on the existing tunnel based on the comparison result.

[0129] Finally, use the pre-constructed target deformation feature template data for comparison to determine whether there is a lining risk currently, specifically including:

[0130] S351. Determine the target deformation feature template data with the same geological structure category and the same flag bit as the target location;

[0131] S352. Calculate the deviation rate D of each monitoring parameter in the deformation feature data and the target deformation feature template data, where the deviation rate D i The mathematical expression of is:

[0132]

[0133] In the formula, x i is the value of the i-th monitoring parameter in the deformation feature data, x' i is the value of the i-th monitoring parameter in the target deformation feature template data, x max is x i and x' i The maximum value of;

[0134] S353. When the deviation rate D at each position i is less than the preset deviation rate threshold, it is determined that the deformation feature data is similar to the target deformation feature template data; otherwise, it is determined that the deformation feature data is not similar to the target deformation feature template data.

[0135] In this embodiment, the deviation rate is used to evaluate the similarity between the two. When the comparison result is similar, the monitored data sequence is marked as having a deformation risk and a warning message is generated, and the warning message is sent to the target object; when the comparison result is dissimilar, the monitored data sequence is marked as having no deformation risk.

[0136] A deformation monitoring and warning method for an existing tunnel according to the present invention extracts the historical monitoring image sequence of multiple image monitoring points of a reference tunnel, analyzes the historical monitoring image sequence, and obtains the target time point when the reference tunnel deforms. Then, in combination with the monitoring data of multiple geological structure categories of the reference tunnel, the characteristics of the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency of the tunnel lining are extracted within a period of time before the deformation occurs. Thus, the deformation characteristic template data is constructed. When monitoring the deformation of the existing tunnel, the deformation characteristic data of the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency in the existing tunnel is extracted, and the deformation characteristic data is compared with the deformation characteristic template data to determine whether there is a deformation risk. This application comprehensively analyzes various factors affecting the deformation of the tunnel lining, thereby providing a warning method different from the lining surface detection. Combining with the existing lining surface detection technology, it can comprehensively monitor and warn the deformation of the tunnel.

[0137] As Figure 5 shown, this application also provides a deformation monitoring and warning system for an existing tunnel, including:

[0138] A sample acquisition module for acquiring the historical monitoring image sequence of multiple image monitoring points of a reference tunnel, the historical monitoring data sequence of multiple mechanical monitoring positions, and the geological structure information of multiple mechanical monitoring positions, wherein the historical monitoring image sequence includes monitoring images at multiple historical time points, and the historical monitoring data sequence includes the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency of the tunnel lining at multiple historical time points;

[0139] A deformation event screening module for determining the target position where the lining of the existing tunnel deforms and the target time point when the lining deforms based on the historical monitoring image sequence;

[0140] A template feature extraction module for classifying multiple mechanical monitoring positions based on the geological structure information to obtain geological structure categories; and constructing deformation characteristic template data based on the target monitoring data of the mechanical monitoring positions of each geological structure category, wherein the target monitoring data includes the monitoring data at the target time point and multiple historical time points within the target duration before the target time point;

[0141] A feature extraction module, configured to obtain a monitoring data sequence and a geological structure category at multiple time points within a target duration before the current time point of the target location of an existing tunnel, and extract deformation feature data from the monitoring data sequence;

[0142] A comparison and early warning module, configured to determine target deformation feature template data of the target location based on the geological structure category, compare the similarity between the deformation feature data and the target deformation feature template data, and perform deformation early warning on the existing tunnel based on the comparison result.

[0143] A deformation monitoring and early warning system for an existing tunnel according to the present invention extracts a historical monitoring image sequence of multiple image monitoring points of a reference tunnel, analyzes the historical monitoring image sequence, and obtains a target time point when the reference tunnel deforms. Then, in combination with the monitoring data of various geological structure categories of the reference tunnel, the characteristics of the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency of the tunnel lining are extracted within a period of time before the deformation occurs, so as to construct deformation feature template data. When monitoring the deformation of an existing tunnel, the deformation feature data of the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency in the existing tunnel are extracted, and the similarity between the deformation feature data and the deformation feature template data is compared to determine whether there is a deformation risk. This application comprehensively analyzes various factors affecting the deformation of the tunnel lining, thereby providing an early warning method different from the lining surface detection, and in combination with the existing lining surface detection technology, can perform all-round deformation monitoring and early warning on the tunnel deformation.

[0144] The above embodiments are only preferred embodiments cited to fully illustrate the present application, and the protection scope of the present application is not limited thereto. Equivalent substitutions or transformations made by those skilled in the art on the basis of the present application are all within the protection scope of the present application.

Claims

1. A deformation monitoring and early warning method for existing tunnels, characterized in that, Including the steps: Obtain the historical monitoring image sequence of multiple image monitoring points of the reference tunnel, the historical monitoring data sequence of multiple mechanical monitoring positions, and the geological structure information of multiple mechanical monitoring positions. Among them, the historical monitoring image sequence includes monitoring images at multiple historical time points, and the historical monitoring data sequence includes the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency of the lining at multiple historical time points; Based on the historical monitoring image sequence, determine the target position where the lining deformation exists in the existing tunnel and the target time point when the lining deformation occurs; Classify multiple mechanical monitoring positions based on the geological structure information to obtain geological structure categories; and construct deformation feature template data based on the target monitoring data of the mechanical monitoring positions of each geological structure category. Among them, the target monitoring data includes the monitoring data at the target time point and multiple historical time points within the target time period before the target time point; Obtain the monitoring data sequence and geological structure category of the target position in the existing tunnel at multiple time points within the target time period before the current time point, and extract deformation feature data from the monitoring data sequence; Based on the geological structure category, determine the target deformation feature template data of the target position, compare the deformation feature data with the target deformation feature template data for similarity, and issue a deformation warning for the existing tunnel based on the comparison result.

2. The deformation monitoring and early warning method for an existing tunnel according to claim 1, characterized in that, Based on the historical monitoring image sequence, determining the target position where the lining deformation exists in the existing tunnel and the target time point when the lining deformation occurs includes: Divide the historical monitoring images of any two adjacent time points in the historical monitoring image sequence into the same control group; Take the previous frame image in the control group as the reference image and the latter frame image as the comparison image; Perform preprocessing on the reference image and the comparison image respectively to obtain the first preprocessed image and the second preprocessed image. Among them, the preprocessing method includes grayscale conversion and high-pass filtering; Adjust the brightness of the first preprocessed image and the second preprocessed image to obtain the first image and the second image with consistent brightness; and extract the crack candidate areas with gray values less than the preset threshold from the first image and the second image; Extract the contour features of the crack candidate areas; perform morphological processing on the contour features of the crack candidate areas to obtain the closed contour features of the crack candidate areas; calculate the size and roundness of the closed contour features, and use the contour features that meet the preset size range and roundness range as the crown crack contours; Draw the closed contour features of the first image and the closed contour features of the second image into a blank image respectively to obtain the first contour image and the second contour image; Extract the centroids of the crown crack contours and other closed contour features, and register the first contour image and the second contour image based on the centroid of the crown crack contour; Take the closed contour features with the closest centroid distance in the first contour image and the second contour image as the comparison contours, and calculate the coincidence rate ρ of each group of comparison contours. The mathematical expression of the coincidence rate ρ is: where A ol is the area of the overlapping part of the control profile, and A max is the area of the profile with a larger area in the control profile; Restore the control contour with a coincidence rate ρ less than the preset threshold to the control image to obtain the deformation position; and use the time point of the control image as the target time point.

3. The deformation monitoring and early warning method for an existing tunnel according to claim 1, characterized in that, Perform brightness adjustment on the first preprocessed image and the second preprocessed image to obtain a first image and a second image with consistent brightness, including: Normalize the gray values of all pixel points in the first preprocessed image and the second preprocessed image to obtain a first normalized image and a second normalized image respectively; Reassign values to the first normalized image and the second normalized image using the same gray range to obtain a first image and a second image with consistent brightness.

4. A deformation monitoring and early warning method for existing tunnels according to claim 1, characterized in that, Construct deformation feature template data based on the target monitoring data of the mechanical monitoring positions of each geological structure category, including: Calculate the variance of each monitoring parameter at multiple historical time points in the target monitoring data; When there is a target monitoring parameter with a variance greater than the preset corresponding variance threshold in the target monitoring data, extract the outlier of the target monitoring parameter, calculate the average value of other monitoring parameters at multiple historical time points, and construct a feature vector based on the outlier of the target monitoring parameter, the average value of other monitoring parameters at multiple historical time points, and the first parameter flag bit, where the value of the first parameter flag bit indicates that the feature vector is a mutation feature; When there is no monitoring parameter with a variance greater than the preset variance threshold in the target monitoring data, calculate the average value of each monitoring parameter at multiple historical time points, and construct a feature vector based on the average value of each monitoring parameter at multiple historical time points and the second flag bit, where the second parameter flag bit indicates that the feature vector is a persistent feature; Perform density clustering on all feature vectors to obtain multiple feature clusters; Use the feature cluster with the number of feature vectors greater than the preset number threshold as the target feature cluster, and calculate the average value of each monitoring parameter in the target feature cluster to obtain the deformation feature template data.

5. A deformation monitoring and early warning method for an existing tunnel according to claim 1, characterized in that, Extract deformation feature data from the monitoring data sequence, including: Calculate the variance of multiple monitoring parameters in the monitoring data sequence at multiple time points; When there is a target monitoring parameter with a variance greater than the preset corresponding variance threshold in the monitoring data sequence, extract the outlier of the target monitoring parameter, calculate the average value of other monitoring parameters at multiple historical time points, and construct a feature vector based on the outlier of the target monitoring parameter, the average value of other monitoring parameters at multiple historical time points, and the first parameter flag bit, and use the feature vector as the deformation feature data; When there is no monitoring parameter with a variance greater than the preset variance threshold in the target monitoring data, calculate the average value of each monitoring parameter at multiple historical time points, and construct deformation feature data based on the average value of each monitoring parameter at multiple historical time points and the second flag bit.

6. A deformation monitoring and early warning method for an existing tunnel according to claim 4 or 5, characterized in that, Extract the outlier of the target monitoring parameter, calculate the average value of other monitoring parameters at multiple historical time points, and construct a feature vector based on the outlier of the target monitoring parameter, the average value of other monitoring parameters at multiple historical time points, and the first parameter flag bit, including: Calculate the average value of the target monitoring parameter at multiple historical time points; calculate the deviation rate of each value of the target monitoring parameter from the average value; use the values with deviation rates greater than the set deviation ratio as outliers, cluster all the outliers to obtain multiple outlier clusters; calculate the average value of each outlier cluster to obtain the outliers of the target monitoring parameter; Combine each type of outlier of the target monitoring parameter with the average value of other monitoring parameters at multiple historical time points and the first flag bit respectively to obtain one or more feature vectors.

7. A deformation monitoring and early warning method for existing tunnels according to claim 1, characterized in that, Based on the geological structure category, determine the target deformation feature template data of the target location, and compare the similarity between the deformation feature data and the target deformation feature template data, including: Determine the target deformation feature template data with the same geological structure category and the same flag bit as the target location; Calculate the deviation rate D of each monitoring parameter between the deformation feature data and the target deformation feature template data, where the deviation rate D i has the following mathematical expression: where x i is the value of the i-th monitoring parameter in the deformation feature data, and x' i is the value of the i-th monitoring parameter in the target deformation feature template data, and x max is the i maximum value of x i and x'; The deviation rate D at each position i When it is less than the preset deviation rate threshold, it is determined that the deformation feature data is similar to the target deformation feature template data; otherwise, it is determined that the deformation feature data is not similar to the target deformation feature template data.

8. A deformation monitoring and early warning method for existing tunnels according to claim 1, characterized in that Based on the comparison result, conduct deformation warning for the existing tunnel, including: When the comparison result is similar, mark the monitoring data sequence as having deformation risk and generate a warning message, and send the warning message to the target object; when the comparison result is dissimilar, mark the monitoring data sequence as having no deformation risk.

9. A deformation monitoring and early warning method for an existing tunnel according to claim 1, characterized in that, The target location is a pre-marked location where strain is likely to occur.

10. A deformation monitoring and early warning system for existing tunnels, characterized in that, Including: A sample acquisition module, configured to acquire the historical monitoring image sequence of multiple image monitoring points of the reference tunnel, the historical monitoring data sequence of multiple mechanical monitoring positions, and the geological structure information of multiple mechanical monitoring positions, wherein the historical monitoring image sequence includes monitoring images at multiple historical time points, and the historical monitoring data sequence includes the load ratio, temperature and humidity, water content of surrounding rock, vibration amplitude, and vibration frequency of the lining at multiple historical time points; A deformation event screening module, configured to determine the target location with lining deformation and the target time point of lining deformation in the existing tunnel based on the historical monitoring image sequence; A template feature extraction module, configured to classify multiple mechanical monitoring positions based on the geological structure information to obtain geological structure categories; and construct deformation feature template data based on the target monitoring data of the mechanical monitoring positions of each geological structure category, wherein the target monitoring data includes the monitoring data at the target time point and multiple historical time points within the target duration before the target time point; A feature extraction module, configured to acquire the monitoring data sequence and the geological structure category of the target location of the existing tunnel at multiple time points within the target duration before the current time point, and extract deformation feature data from the monitoring data sequence; A comparison and warning module, configured to determine the target deformation feature template data of the target location based on the geological structure category, compare the similarity between the deformation feature data and the target deformation feature template data, and conduct deformation warning for the existing tunnel based on the comparison result.

Images