A method for detecting defects in tunnel water-rich high-pressure lining

Abstract

The present invention provides a method for detecting defects in water-rich and high-pressure linings of tunnels, comprising: using a relative positioning algorithm to fuse multi-cycle tunnel contour point cloud data acquired by a laser radar to obtain three-dimensional contour information of the tunnel under test; using a tunnel modeling algorithm to process the three-dimensional contour information to obtain a plurality of model conditions, constructing a tunnel contour model of the tunnel under test; performing water pressure resistance testing on each model position in the tunnel contour model to obtain a pressure resistance value corresponding to each model position; locating tunnel defect positions in the tunnel contour model whose pressure resistance values ​​are lower than the average pressure resistance value of the same model area; identifying and displaying the actual position coordinates of the tunnel defect positions; and performing defect detection during the construction of the tunnel to ensure that the constructed tunnel can meet the needs of long-term use.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel defect detection, and in particular to a method for detecting defects in a water-rich high-pressure lining of a tunnel. Background Art

[0002] Tunnel water-rich high-pressure lining is a lining structure designed for the high water pressure environments encountered during underground tunnel construction. Its purpose is to effectively resist the pressure generated by water infiltration or groundwater pressure, ensuring the safety and long-term stability of the tunnel. Tunnel water-rich high-pressure lining is of great significance in areas with complex hydrogeological conditions, abundant groundwater, or high water pressure, especially in areas with poor hydrogeological conditions.

[0003] Tunnel construction, especially when traversing aquifers, areas with abundant groundwater, or areas with high groundwater levels, can be subject to significant water pressure. Under these conditions, the lining structure often cannot withstand the impact of water pressure, resulting in leakage or structural damage. Therefore, a method for detecting structural defects during tunnel construction is needed.

[0004] Therefore, the present invention provides a method for detecting defects in a tunnel's water-rich high-pressure lining. Summary of the Invention

[0005] The present invention provides a method for detecting defects in a water-rich high-pressure tunnel lining, which can perform defect detection during the construction of a tunnel to ensure that the constructed tunnel can meet the requirements of long-term use.

[0006] The present invention provides a method for detecting defects in a tunnel water-rich high-pressure lining, comprising:

[0007] Step 1: Use the relative positioning algorithm to fuse the multi-cycle tunnel contour point cloud data acquired by the lidar to obtain the 3D contour information of the measured tunnel;

[0008] Step 2: Processing the three-dimensional contour information using a tunnel modeling algorithm to obtain a number of model conditions and constructing a tunnel contour model of the tunnel under test;

[0009] Step 3: Performing water pressure resistance testing on each model position in the tunnel contour model to obtain a pressure resistance value corresponding to each model position;

[0010] Step 4: Locate the tunnel defect position whose compressive strength value is lower than the average compressive strength value of the same model area in the tunnel contour model, identify the actual position coordinates of the tunnel defect position and display them.

[0011] In one practicable manner,

[0012] The step 1 comprises:

[0013] Step 11: Controlling the laser radar to perform periodic measurement on the measured tunnel to obtain a plurality of periodic tunnel contour point cloud data of the measured tunnel, and using the relative positioning algorithm to align each of the periodic contour point cloud data to obtain the tunnel symmetry axis corresponding to each of the periodic contour point cloud data;

[0014] Step 12: Connect the tunnel symmetry axes to obtain a virtual central axis of the measured tunnel, input each periodic tunnel contour point cloud data into the axis area corresponding to the virtual central axis, fuse multiple point cloud data corresponding to the same central axis point, and obtain fused data corresponding to each central axis point;

[0015] Step 13: determining the real-time tunnel length of the tunnel under test based on the virtual axis center, combining the fused data corresponding to adjacent central axis points in the virtual central axis to obtain a plurality of basic combination points and a plurality of corresponding basic combination data of the tunnel under test;

[0016] Step 14: Iteratively combine the basic combination data corresponding to adjacent basic combination points, construct the appearance structure of the measured tunnel based on the generated iterative combination information, input the generated iterative combination data into the appearance structure, and generate three-dimensional contour information of the measured tunnel.

[0017] In one practicable manner,

[0018] The step 2 comprises:

[0019] Step 21: using the tunnel modeling algorithm to perform partial segmentation processing on the three-dimensional contour information to obtain component contour information corresponding to each tunnel component of the measured tunnel, and using standard geometry to perform geometric matching on each component contour information to obtain cross-sectional composition features corresponding to each component;

[0020] Step 22: Performing contour enhancement processing on the three-dimensional contour information using the tunnel modeling algorithm to obtain edge contours and inner contours corresponding to each tunnel component of the measured tunnel, and combining the cross-sectional composition features, edge contours, and inner contours corresponding to the same tunnel component to obtain a plurality of model conditions;

[0021] Step 23: constructing a three-dimensional model framework of the tunnel under test based on the three-dimensional contour information, and rendering each tunnel component in the three-dimensional model framework using each model condition to obtain a tunnel contour model of the tunnel under test.

[0022] In one practicable manner,

[0023] Also includes:

[0024] Identify several anchor points included in the tunnel outline model, mark several load-bearing angles corresponding to each anchor point in the tunnel outline model, generate a real-time load-bearing report of the measured tunnel, and display it.

[0025] In one practicable manner,

[0026] The step 3 comprises:

[0027] Step 31: Acquire environmental data of the tunnel under test, construct several environmental characteristics of the tunnel under test, perform water pressure analysis on each of the environmental characteristics to obtain several water pressure samples, and combine different numbers of the water pressure samples to generate several types of detected water pressure distribution information of the tunnel under test;

[0028] Step 32: Performing water pressure resistance testing on the tunnel contour model using each of the detected water pressure distribution information to obtain a plurality of detection values ​​corresponding to each of the model positions, and constructing a pressure-resistance linear graph corresponding to each of the model positions based on the pressure values ​​of each of the detected water pressure distribution information at the model position;

[0029] Step 33: Use a 1D convolutional neural network to perform trend analysis on each of the pressure-resistance linear graphs, estimate the tunnel collapse water pressure value corresponding to each of the model positions, and use the corresponding pressure-resistance linear graph to derive the resistance value corresponding to the tunnel patch water pressure value to obtain the resistance value corresponding to each of the model positions.

[0030] In one practicable manner,

[0031] Also includes:

[0032] When the tunnel contour model collapses during the water pressure resistance test, locating the collapse position in the tunnel contour model;

[0033] The collapse location is regarded as a key defect location, and a corresponding key defect warning is generated and transmitted to a designated terminal for display.

[0034] In one practicable manner,

[0035] The step 4 comprises:

[0036] Step 41: taking each model position as the center, treating the corresponding nine-square grid as a same-model area, and calculating the average compressive strength value corresponding to each same-model area;

[0037] Step 42: Mark the numerical difference between each model position and the corresponding average compressive strength value in the model position corresponding to the tunnel contour model, and select tunnel defect positions with negative numerical differences;

[0038] Step 43: tracing each of the tunnel defect positions in the point cloud data, deriving the actual position coordinates corresponding to each of the tunnel defect positions based on the tracing results, and displaying them.

[0039] In one practicable manner,

[0040] Also includes:

[0041] Tunnel deformation information of the measured tunnel is constructed and displayed according to each of the actual position coordinates and the corresponding data difference.

[0042] In one practicable manner,

[0043] Also includes:

[0044] Analyzing the structural stability of the tunnel under test according to the compressive strength value corresponding to each position of the model;

[0045] When the structural stability is lower than the standard stability, it is determined that the structure of the tunnel under test is abnormal, and corresponding warning information is generated and displayed.

[0046] The achievable beneficial effects of the above technical solution are: using laser radar to collect point cloud data of the tunnel under test, and then using relative positioning algorithm to fuse these point cloud data to obtain the three-dimensional contour information of the tunnel under test, and further using tunnel modeling algorithm to construct a tunnel contour model of the tunnel under test, and by performing water pressure resistance testing on the tunnel contour model, the compressive strength value of each tunnel position in the tunnel under test is determined, and then the defective position of the tunnel with insufficient compressive strength is located. In this way, the construction process of the tunnel under test can be supervised, and the engineering quality of the tunnel under test can be understood at any time. When quality problems are found, they can be solved in the first time, avoiding the later consumption of a lot of manpower and material resources for rework, and effectively shortening the construction time of the tunnel under test.

[0047] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0048] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 Schematic diagram of the workflow of a method for detecting defects in a water-rich, high-pressure lining of a tunnel according to an embodiment of the present invention;

[0051] Figure 2 This is a schematic diagram of the workflow of step 1 of a method for detecting defects in a tunnel water-rich high-pressure lining according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0053] Example 1

[0054] This embodiment provides a method for detecting defects in a tunnel's water-rich high-pressure lining. Figure 1 As shown, including:

[0055] Step 1: Use the relative positioning algorithm to fuse the multi-cycle tunnel contour point cloud data acquired by the lidar to obtain the 3D contour information of the measured tunnel;

[0056] Step 2: Processing the three-dimensional contour information using a tunnel modeling algorithm to obtain a number of model conditions and constructing a tunnel contour model of the tunnel under test;

[0057] Step 3: Performing water pressure resistance testing on each model position in the tunnel contour model to obtain a pressure resistance value corresponding to each model position;

[0058] Step 4: Locate the tunnel defect position whose compressive strength value is lower than the average compressive strength value of the same model area in the tunnel contour model, identify the actual position coordinates of the tunnel defect position and display them.

[0059] In this example, the lidar measurement cycle is 24 hours / time;

[0060] In this instance, model conditions represent the most basic conditions used to construct the model;

[0061] In this example, water pressure resistance testing refers to the process of analyzing the water pressure resistance of the tested tunnel in the tunnel profile model;

[0062] In this example, each model position corresponds to a compressive strength value and a region with the same model;

[0063] In this example, the same model area represents a nine-square grid range centered on a model position.

[0064] The working principle and beneficial effects of the above technical solution are as follows: the point cloud data of the measured tunnel is collected by laser radar, and then the relative positioning algorithm is used to fuse these point cloud data to obtain the three-dimensional contour information of the measured tunnel. The tunnel modeling algorithm is further used to construct a tunnel contour model of the measured tunnel. The water pressure resistance value of each tunnel position in the measured tunnel is determined by performing water pressure resistance testing on the tunnel contour model, and then the defective position of the tunnel with insufficient pressure resistance is located. In this way, the construction process of the measured tunnel can be supervised, and the engineering quality of the measured tunnel can be understood at any time. When quality problems are found, they can be solved in the first time, avoiding the later consumption of a lot of manpower and material resources for rework, and effectively shortening the construction time of the measured tunnel.

[0065] Example 2

[0066] On the basis of Example 1, the method for detecting defects in a tunnel with rich water and high pressure lining is as follows: Figure 2 As shown, the step 1 includes:

[0067] Step 11: Controlling the laser radar to perform periodic measurement on the measured tunnel to obtain a plurality of periodic tunnel contour point cloud data of the measured tunnel, and using the relative positioning algorithm to align each of the periodic contour point cloud data to obtain the tunnel symmetry axis corresponding to each of the periodic contour point cloud data;

[0068] Step 12: Connect the tunnel symmetry axes to obtain a virtual central axis of the measured tunnel, input each periodic tunnel contour point cloud data into the axis area corresponding to the virtual central axis, fuse multiple point cloud data corresponding to the same central axis point, and obtain fused data corresponding to each central axis point;

[0069] Step 13: determining the real-time tunnel length of the tunnel under test based on the virtual axis center, combining the fused data corresponding to adjacent central axis points in the virtual central axis to obtain a plurality of basic combination points and a plurality of corresponding basic combination data of the tunnel under test;

[0070] Step 14: Iteratively combine the basic combination data corresponding to adjacent basic combination points, construct the appearance structure of the measured tunnel based on the generated iterative combination information, input the generated iterative combination data into the appearance structure, and generate three-dimensional contour information of the measured tunnel.

[0071] In this example, each time the LiDAR performs a measurement, a period of tunnel contour point cloud data is obtained;

[0072] In this example, the tunnel symmetry axis indicates that the tunnel under test is folded along the symmetry axis;

[0073] In this example, the virtual central axis represents the result of connecting the symmetry axes of tunnels with different periods;

[0074] In this example, the axis region represents a symmetry axis region associated with a periodic point cloud data;

[0075] In this example, the basic combination point represents the area corresponding to the combination of the fused data of adjacent cycles, and the basic combination data represents the data result generated after this combination;

[0076] In this example, iterative combination means combining basic combination points having an adjacent relationship multiple times until the overall combination result of the measured tunnel is obtained.

[0077] The working principle and beneficial effects of the above technical solution: In order to detect tunnel defects in a timely manner, the laser radar performs periodic measurements on the measured tunnel, and uses the relative positioning algorithm to analyze the tunnel symmetry axis of the obtained periodic contour point cloud data. The tunnel symmetry axis is then connected to generate a virtual center axis. In this way, the data on the tunnel symmetry axis can be determined first, and then the remaining data can be classified and fused to obtain the fused data corresponding to each center axis point in the virtual center axis. The fused data on adjacent center axis points in the virtual center axis are then combined, and the combined data are further combined again until the overall data of the measured tunnel is obtained, and the three-dimensional contour information of the measured tunnel is generated. In this way, the point cloud data collected at different periods can be fused, avoiding the randomness of single point cloud data and improving the accuracy of defect detection.

[0078] Example 3

[0079] Based on Example 1, the method for detecting defects in a water-rich high-pressure tunnel lining, step 2, includes:

[0080] Step 21: using the tunnel modeling algorithm to perform partial segmentation processing on the three-dimensional contour information to obtain component contour information corresponding to each tunnel component of the measured tunnel, and using standard geometry to perform geometric matching on each component contour information to obtain cross-sectional composition features corresponding to each component;

[0081] Step 22: Performing contour enhancement processing on the three-dimensional contour information using the tunnel modeling algorithm to obtain edge contours and inner contours corresponding to each tunnel component of the measured tunnel, and combining the cross-sectional composition features, edge contours, and inner contours corresponding to the same tunnel component to obtain a plurality of model conditions;

[0082] Step 23: constructing a three-dimensional model framework of the tunnel under test based on the three-dimensional contour information, and rendering each tunnel component in the three-dimensional model framework using each model condition to obtain a tunnel contour model of the tunnel under test.

[0083] In this example, the part segmentation process means dividing the tunnel under test into: a ground part, a tunnel wall part and a tunnel top part;

[0084] In this instance, geometric matching refers to the process of fitting component contours using regular geometry;

[0085] In this example, the edge contour represents the contour presented by the edge of the tunnel, and the inner contour represents the contour presented by the building inside the tunnel.

[0086] The working principle and beneficial effects of the above technical solution are as follows: the three-dimensional contour information is first segmented to determine the cross-sectional composition features of different parts of the measured tunnel, and then the three-dimensional contour information is contour enhanced to distinguish the edge contour and inner contour of the measured tunnel. The three characteristics obtained are then used to establish model conditions, and the three-dimensional contour information is further converted into a three-dimensional model framework, which is rendered using the model conditions to obtain a tunnel contour model of the measured tunnel. In this way, every detail of the measured tunnel can be analyzed, so that the obtained model is consistent with the actual situation of the measured tunnel, thereby improving the effectiveness of defect detection.

[0087] Example 4

[0088] Based on Example 3, the method for detecting defects in a water-rich high-pressure tunnel lining further includes:

[0089] Identify several anchor points included in the tunnel outline model, mark several load-bearing angles corresponding to each anchor point in the tunnel outline model, generate a real-time load-bearing report of the measured tunnel, and display it.

[0090] The working principle and beneficial effects of the above technical solution: In order to facilitate relevant personnel to supervise the construction process, the real-time load-bearing information of the measured tunnel is analyzed and displayed by identifying the bearing points in the tunnel contour model, providing convenience for relevant personnel.

[0091] Example 5

[0092] Based on Example 1, the method for detecting defects in a water-rich high-pressure tunnel lining, step 3, includes:

[0093] Step 31: Acquire environmental data of the tunnel under test, construct several environmental characteristics of the tunnel under test, perform water pressure analysis on each of the environmental characteristics to obtain several water pressure samples, and combine different numbers of the water pressure samples to generate several types of detected water pressure distribution information of the tunnel under test;

[0094] Step 32: Performing water pressure resistance testing on the tunnel contour model using each of the detected water pressure distribution information to obtain a plurality of detection values ​​corresponding to each of the model positions, and constructing a pressure-resistance linear graph corresponding to each of the model positions based on the pressure values ​​of each of the detected water pressure distribution information at the model position;

[0095] Step 33: Use a 1D convolutional neural network to perform trend analysis on each of the pressure-resistance linear graphs, estimate the tunnel collapse water pressure value corresponding to each of the model positions, and use the corresponding pressure-resistance linear graph to derive the resistance value corresponding to the tunnel patch water pressure value to obtain the resistance value corresponding to each of the model positions.

[0096] In this example, the environmental characteristics represent the characteristics of the external environment that the tunnel under test may face in its environment;

[0097] In this example, the detection water pressure distribution information represents the process of performing different water pressure detections on different model positions of the tunnel under test. During the same detection process, the detection water pressures corresponding to different model positions may not be the same.

[0098] In this example, a 1D convolutional neural network is used to extract local features of the stress-resistance linear graph and then capture its development trend.

[0099] In this example, the compressive strength value indicates the maximum water pressure that a model location can withstand.

[0100] The working principle and beneficial effects of the above technical solution are as follows: the environmental characteristics of the tested tunnel are determined based on the environmental data of the environment in which the tested tunnel is located, thereby constructing corresponding water pressure samples. In order to prevent the tested tunnel from being unable to withstand complex pressure conditions when multiple environmental characteristics appear at one time, different numbers (two or more) of water pressure samples are combined to construct several types of detected water pressure distribution information of the tested tunnel, and then the tunnel contour is tested for water pressure resistance. A pressure-resistance linear graph of each model position is constructed, and its development trend is further analyzed through a convolutional neural network to determine the resistance value of each model position. In this way, various water pressure conditions in the environment in which the tested tunnel is located can be tested and simulated, and the water pressure resistance of the tested tunnel in a complex environment can be determined, thereby achieving a comprehensive analysis and avoiding accidental damage to the tested tunnel caused by extreme environments.

[0101] Example 6

[0102] Based on Example 5, the method for detecting defects in a water-rich high-pressure tunnel lining further includes:

[0103] When the tunnel contour model collapses during the water pressure resistance test, locating the collapse position in the tunnel contour model;

[0104] The collapse location is regarded as a key defect location, and a corresponding key defect warning is generated and transmitted to a designated terminal for display.

[0105] In this example, the designated terminal refers to a terminal with display function used by relevant personnel, generally including an on-site screen, a mobile phone, a remote screen, etc.

[0106] The working principle and beneficial effects of the above technical solution are as follows: If the three-dimensional contour model collapses during the water pressure resistance test, it indicates that there are verified defects in the tested tunnel. At this time, a timely reminder will be given, and relevant personnel can take timely remedial measures based on the on-site conditions to avoid affecting the quality of the completed tunnel.

[0107] Example 7

[0108] Based on Example 1, the method for detecting defects in a water-rich high-pressure tunnel lining, step 4, includes:

[0109] Step 41: taking each model position as the center, treating the corresponding nine-square grid as a same-model area, and calculating the average compressive strength value corresponding to each same-model area;

[0110] Step 42: Mark the numerical difference between each model position and the corresponding average compressive strength value in the model position corresponding to the tunnel contour model, and select tunnel defect positions with negative numerical differences;

[0111] Step 43: tracing each of the tunnel defect positions in the point cloud data, deriving the actual position coordinates corresponding to each of the tunnel defect positions based on the tracing results, and displaying them.

[0112] The working principle and beneficial effects of the above technical solution are as follows: by comparing the average compressive strength value of a model position with that of the same model area, the tunnel defect position of the measured tunnel is determined, and then it is traced in the point cloud data to determine the location of the event defect in the measured tunnel. Finally, its coordinates are extracted and displayed. In this way, precise positioning can be achieved, providing a technical reference for relevant personnel.

[0113] Example 8

[0114] Based on implementation 7, the method for detecting defects in a water-rich high-pressure tunnel lining further includes:

[0115] Tunnel deformation information of the measured tunnel is constructed and displayed according to each of the actual position coordinates and the corresponding data difference.

[0116] The working principle and beneficial effects of the above technical solution are: analyzing the deformation information of the measured tunnel and providing accurate data to relevant personnel.

[0117] Example 9

[0118] Based on Example 1, the method for detecting defects in a water-rich high-pressure tunnel lining further includes:

[0119] Analyzing the structural stability of the tunnel under test according to the compressive strength value corresponding to each position of the model;

[0120] When the structural stability is lower than the standard stability, it is determined that the structure of the tunnel under test is abnormal, and corresponding warning information is generated and displayed.

[0121] In this example, the standard stability refers to the standard value uploaded in advance by relevant personnel before construction. Generally speaking, the standard stability is not less than 95%.

[0122] The working principle and beneficial effects of the above technical solution are as follows: when the stability of the tunnel under test is too low, timely reminders are given to avoid unnecessary losses caused by subsequent tunnel collapse.

[0123] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for detecting defects in a tunnel's water-rich high-pressure lining, characterized in that: include: Step 1: Use the relative positioning algorithm to fuse the multi-cycle tunnel contour point cloud data acquired by the lidar to obtain the 3D contour information of the measured tunnel; Step 2: Processing the three-dimensional contour information using a tunnel modeling algorithm to obtain a number of model conditions and constructing a tunnel contour model of the tunnel under test; Step 3: Performing water pressure resistance testing on each model position in the tunnel contour model to obtain a pressure resistance value corresponding to each model position; Step 4: Locate the tunnel defect position whose compressive strength value is lower than the average compressive strength value of the same model area in the tunnel contour model, identify the actual position coordinates of the tunnel defect position and display them; The same model area refers to the nine-square grid range centered on a model position; The step 1 comprises: Step 11: Controlling the laser radar to perform periodic measurement on the measured tunnel to obtain a plurality of periodic tunnel contour point cloud data of the measured tunnel, and using the relative positioning algorithm to align each of the periodic tunnel contour point cloud data to obtain the tunnel symmetry axis corresponding to each of the periodic contour point cloud data; Step 12: Connect the tunnel symmetry axes to obtain a virtual central axis of the measured tunnel, input each periodic tunnel contour point cloud data into the axis area corresponding to the virtual central axis, fuse multiple point cloud data corresponding to the same central axis point, and obtain fused data corresponding to each central axis point; Step 13: determining the real-time tunnel length of the measured tunnel according to the virtual central axis, combining the fused data corresponding to adjacent central axis points in the virtual central axis to obtain a plurality of basic combination points and a plurality of corresponding basic combination data of the measured tunnel; Step 14: iteratively combining the basic combination data corresponding to adjacent basic combination points, constructing the appearance structure of the tunnel under test based on the generated iterative combination information, and inputting the generated iterative combination data into the appearance structure to generate three-dimensional contour information of the tunnel under test; The step 3 comprises: Step 31: Acquire environmental data of the tunnel under test, construct several environmental characteristics of the tunnel under test, perform water pressure analysis on each of the environmental characteristics to obtain several water pressure samples, and combine different numbers of the water pressure samples to generate several types of detected water pressure distribution information of the tunnel under test; Step 32: Performing water pressure resistance testing on the tunnel contour model using each of the detected water pressure distribution information to obtain a plurality of detection values ​​corresponding to each of the model positions, and constructing a pressure-resistance linear graph corresponding to each of the model positions based on the pressure values ​​of each of the detected water pressure distribution information at the model position; Step 33: Use a 1D convolutional neural network to perform trend analysis on each of the pressure-resistance linear graphs, estimate the tunnel collapse water pressure value corresponding to each of the model positions, and use the corresponding pressure-resistance linear graph to derive the resistance value corresponding to the tunnel collapse water pressure value to obtain the resistance value corresponding to each of the model positions.

2. A method for detecting defects in a tunnel water-rich high-pressure lining according to claim 1, characterized in that: The step 2 comprises: Step 21: using the tunnel modeling algorithm to perform partial segmentation processing on the three-dimensional contour information to obtain component contour information corresponding to each tunnel component of the measured tunnel, and using standard geometry to perform geometric matching on each component contour information to obtain cross-sectional composition features corresponding to each component; Step 22: Performing contour enhancement processing on the three-dimensional contour information using the tunnel modeling algorithm to obtain edge contours and inner contours corresponding to each tunnel component of the measured tunnel, and combining the cross-sectional composition features, edge contours, and inner contours corresponding to the same tunnel component to obtain a plurality of model conditions; Step 23: constructing a three-dimensional model framework of the tunnel under test based on the three-dimensional contour information, and rendering each tunnel component in the three-dimensional model framework using each model condition to obtain a tunnel contour model of the tunnel under test.

3. A method for detecting defects in a tunnel water-rich high-pressure lining according to claim 2, characterized in that: Also includes: Identify several anchor points included in the tunnel outline model, mark several load-bearing angles corresponding to each anchor point in the tunnel outline model, generate a real-time load-bearing report of the measured tunnel, and display it.

4. A method for detecting defects in a tunnel water-rich high-pressure lining according to claim 1, characterized in that: Also includes: When the tunnel contour model collapses during the water pressure resistance test, locating the collapse position in the tunnel contour model; The collapse location is regarded as a key defect location, and a corresponding key defect warning is generated and transmitted to a designated terminal for display.

5. A method for detecting defects in a tunnel water-rich high-pressure lining according to claim 1, characterized in that: The step 4 comprises: Step 41: taking each model position as the center, treating the corresponding nine-square grid as a same-model area, and calculating the average compressive strength value corresponding to each same-model area; Step 42: Mark the numerical difference between each model position and the corresponding average compressive strength value in the model position corresponding to the tunnel contour model, and select tunnel defect positions with negative numerical differences; Step 43: tracing each of the tunnel defect positions in the point cloud data, deriving the actual position coordinates corresponding to each of the tunnel defect positions based on the tracing results, and displaying them.

6. A method for detecting defects in a tunnel water-rich high-pressure lining according to claim 5, characterized in that: Also includes: Tunnel deformation information of the measured tunnel is constructed and displayed according to each of the actual position coordinates and the corresponding data difference.

7. A method for detecting defects in a tunnel water-rich high-pressure lining according to claim 1, characterized in that: Also includes: Analyzing the structural stability of the tunnel under test according to the compressive strength value corresponding to each position of the model; When the structural stability is lower than the standard stability, it is determined that the structure of the tunnel under test is abnormal, and corresponding warning information is generated and displayed.

Images