Tunnel water-rich high-pressure lining defect detection method

Abstract

The invention provides a tunnel water-rich high-pressure lining defect detection method which comprises the following steps: performing data fusion on multi-cycle tunnel contour point cloud data acquired by a laser radar by using a relative positioning algorithm to obtain three-dimensional contour information of a detected tunnel, and processing the three-dimensional contour information by using a tunnel modeling algorithm to obtain a tunnel water-rich high-pressure lining defect detection result. The method comprises the steps of obtaining a plurality of model conditions, constructing a tunnel contour model of a detected tunnel, carrying out water pressure resistance detection on each model position in the tunnel contour model to obtain a pressure resistance value corresponding to each model position, positioning a tunnel defect position with the pressure resistance value lower than an average pressure resistance value of a same model area in the tunnel contour model, and carrying out water pressure resistance detection on each model position in the tunnel contour model. The actual position coordinates of the tunnel defect position are recognized and displayed, defect detection can be conducted in the tunnel building process, and it is guaranteed that the built tunnel can meet the long-term use requirement.

Description

Technical Field

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

[0002] A water-rich and high-pressure lining of a tunnel is a lining structure designed for the high water pressure environment that may be encountered in the construction of underground tunnels. Its purpose is to effectively resist the pressure generated by water source penetration or groundwater pressure, ensuring the safety and long-term stability of the tunnel. The water-rich and high-pressure lining of a tunnel is of great significance in areas with complex hydrogeological conditions, abundant groundwater, or high water pressure, especially in areas with poor hydrogeological conditions.

[0003] During tunnel construction, especially when crossing water-rich layers, areas with abundant groundwater, or areas with a high groundwater level, relatively high water pressure may be faced. Under these conditions, the lining structure often cannot withstand the impact of water pressure and is prone to leakage or structural damage. Therefore, a method for detecting structural defects during the construction of a tunnel is needed.

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

[0005] A method for detecting defects in a water-rich and high-pressure lining of a tunnel according to the present invention can detect defects during the construction of a tunnel to ensure that the completed tunnel can meet the requirements of long-term use.

[0006] The present invention provides a method for detecting defects in a water-rich and high-pressure lining of a tunnel, including: Step 1: Using a relative positioning algorithm to fuse multi-period tunnel profile point cloud data obtained by a lidar to obtain three-dimensional profile information of the tunnel to be measured; Step 2: Using a tunnel modeling algorithm to process the three-dimensional profile information to obtain a number of model conditions and construct a tunnel profile model of the tunnel to be measured; Step 3: Performing a water pressure resistance test on each model position in the tunnel profile model to obtain a compressive value corresponding to each model position; Step 4: Locating the tunnel defect positions in the tunnel profile model where the compressive value is lower than the average compressive value of the same model area, identifying the actual position coordinates of the tunnel defect positions and displaying them.

[0007] In an implementable manner, The Step 1 includes: Step 11: Control the lidar to perform periodic measurements on the tunnel to be measured, obtain a number of periodic tunnel profile point cloud data of the tunnel to be measured, and use the relative positioning algorithm to align the data of each periodic profile point cloud respectively to obtain the tunnel symmetry axis corresponding to each periodic profile point cloud data; Step 12: Connect the tunnel symmetry axes to obtain the virtual central axis of the tunnel to be measured. Input each periodic tunnel profile point cloud data into the axis region corresponding to the virtual central axis, and fuse the several point cloud data corresponding to the same central axis point to obtain the fused data corresponding to each central axis point; Step 13: Determine the real-time tunnel length of the tunnel to be measured according to the virtual axis center. Combine the fused data corresponding to adjacent central axis points in the virtual central axis to obtain several basic combined points and several corresponding basic combined data of the tunnel to be measured; Step 14: Iteratively combine the basic combined data corresponding to adjacent basic combined points, construct the appearance structure of the tunnel to be measured according to the generated iterative combination information, input the generated iterative combined data into the appearance structure, and generate the three-dimensional profile information of the tunnel to be measured.

[0008] In an implementable manner, Step 2 includes: Step 21: Use the tunnel modeling algorithm to perform partial segmentation processing on the three-dimensional profile information to obtain the composition profile information corresponding to each tunnel component of the tunnel to be measured, and use standard geometry to perform geometric matching on each composition profile information respectively to obtain the cross-section composition characteristics corresponding to each component; Step 22: Use the tunnel modeling algorithm to perform profile enhancement processing on the three-dimensional profile information to obtain the edge profile and inner profile corresponding to each tunnel component of the tunnel to be measured. Combine the cross-section composition characteristics, edge profile and inner profile corresponding to the same tunnel component to obtain several model conditions; Step 23: Build a three-dimensional model framework of the tunnel to be measured based on the three-dimensional profile information, and use each model condition to render each tunnel component in the three-dimensional model framework to obtain the tunnel profile model of the tunnel to be measured.

[0009] In an implementable manner, It further includes: Identify several load-bearing points included in the tunnel profile model, mark the several load-bearing angles corresponding to each load-bearing point on the tunnel profile model respectively, generate a real-time load-bearing report of the tunnel to be measured and display it.

[0010] In an implementable manner, Step 3 includes: Step 31: Obtain the environmental data of the tunnel to be measured, construct several environmental characteristics faced by the tunnel to be measured, perform water pressure analysis on each of the faced environmental characteristics to obtain several water pressure samples, and respectively combine different numbers of the water pressure samples to generate several detection water pressure distribution information of the tunnel to be measured; Step 32: Respectively use each of the detection water pressure distribution information to perform anti-water pressure detection on the tunnel contour model, obtain several detection values corresponding to each model position, and construct a pressure-applied - pressure-resistant linear graph corresponding to each model position based on the pressure-applied value of the model position for each of the detection water pressure distribution information; Step 33: Use a 1D convolutional neural network to perform trend analysis on each of the pressure-applied - pressure-resistant linear graphs, estimate the tunnel collapse water pressure value corresponding to each model position, and derive the pressure-resistant value corresponding to the tunnel patch water pressure value using the corresponding pressure-applied - pressure-resistant linear graph to obtain the pressure-resistant value corresponding to each model position.

[0011] In an implementable manner, It further includes: When detecting collapse occurs to the tunnel contour model during the anti-water pressure detection process, locate the collapse position in the tunnel contour model; Regard the collapse position as a key defect position, generate a corresponding key defect warning and transmit it to a designated terminal for display.

[0012] In an implementable manner, Step 4 includes: Step 41: Respectively take each model position as the center and regard the corresponding nine-square grid as the same model area, and respectively calculate the average pressure-resistant value corresponding to each same model area; Step 42: Respectively mark the numerical difference between each model position and the corresponding average pressure-resistant value in the model position corresponding to the tunnel contour model, and screen out the tunnel defect positions with negative numerical differences; Step 43: Respectively trace each tunnel defect position in the point cloud data, and deduce and display the actual position coordinates corresponding to each tunnel defect position according to the tracing result.

[0013] In an implementable manner, It further includes: Construct tunnel deformation information of the tunnel to be measured according to each actual position coordinate and the corresponding data difference and display it.

[0014] In an implementable manner, Further included are: Analyze the structural stability of the tunnel under test according to the compressive strength values corresponding to each of the said model positions; 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 reminder information is generated and displayed.

[0015] The achievable beneficial effects of the above technical solution are as follows: The lidar is used to collect the point cloud data of the tunnel under test, and then the relative positioning algorithm is used to fuse these point cloud data to obtain the three-dimensional contour information of the tunnel under test. Further, the tunnel modeling algorithm is used to construct the tunnel contour model of the tunnel under test. By performing a water pressure resistance test on the tunnel contour model, the compressive strength values of each tunnel position in the tunnel under test are determined, and then the tunnel defect positions with insufficient compressive capacity are 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 immediately, avoiding a large amount of manpower and material resources consumed in later rework, and effectively shortening the construction duration of the tunnel under test.

[0016] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification and the drawings.

[0017] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0018] The 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 to the present invention. In the drawings: Figure 1 is a schematic working flow diagram of a method for detecting defects in a water-rich and high-pressure lining of a tunnel in an embodiment of the present invention; Figure 2 is a schematic working flow diagram of step 1 of a method for detecting defects in a water-rich and high-pressure lining of a tunnel in an embodiment of the present invention. Detailed Embodiments

[0019] The following describes the preferred embodiments of the present invention with reference to the 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.

[0020] Embodiment 1 This embodiment provides a method for detecting defects in a water-rich and high-pressure lining of a tunnel, as Figure 1 shown, including: Step 1: Use the relative positioning algorithm to fuse the multi-period tunnel contour point cloud data obtained by the lidar to obtain the three-dimensional contour information of the tunnel under test; Step 2: Use the tunnel modeling algorithm to process the three-dimensional contour information to obtain several model conditions, and construct the tunnel contour model of the tunnel under test; Step 3: Perform a water pressure resistance test on each model position in the tunnel contour model to obtain the compressive resistance value corresponding to each model position; Step 4: Locate the tunnel defect positions in the tunnel contour model where the compressive resistance value is lower than the average compressive resistance value of the same model area, identify the actual position coordinates of the tunnel defect positions and display them.

[0021] In this example, the measurement period of the lidar is 24 hours / time; In this example, the model condition represents the most basic condition for constructing the model; In this example, the water pressure resistance test represents the process of analyzing the water pressure resistance ability of the tunnel under test in the tunnel contour model; In this example, each model position corresponds to a compressive resistance value and a corresponding same model area; In this example, the same model area represents a nine-square grid range centered on a model position.

[0022] The working principle and beneficial effects of the above technical solution: The point cloud data of the tunnel under test is collected by the lidar, and then these point cloud data are fused using the relative positioning algorithm to obtain the three-dimensional contour information of the tunnel under test. Further, the tunnel modeling algorithm is used to construct the tunnel contour model of the tunnel under test. The water pressure resistance test is carried out on the tunnel contour model to determine the compressive resistance value of each tunnel position in the tunnel under test, and then the tunnel defect positions with insufficient compressive resistance ability are 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 immediately, avoiding a large amount of manpower and material resources consumed in the later stage for rework, effectively shortening the construction duration of the tunnel under test.

[0023] Embodiment 2 Based on Embodiment 1, the method for detecting tunnel water-rich high-pressure lining defects is as follows Figure 2 As shown, Step 1 includes: Step 11: Control the lidar to perform periodic measurements on the tunnel under test to obtain several period tunnel contour point cloud data of the tunnel under test, and use the relative positioning algorithm to perform data alignment on each period contour point cloud data to obtain the tunnel symmetry axis corresponding to each period contour point cloud data; Step 12: Connect the symmetry axes of the tunnels to obtain the virtual central axis of the tunnel under test. Input the point cloud data of each periodic tunnel profile into the corresponding axis region of the virtual central axis, and fuse the several point cloud data corresponding to the same central axis point to obtain the fused data corresponding to each central axis point; Step 13: Determine the real-time tunnel length of the tunnel under test according to the virtual axis center. Combine the fused data corresponding to adjacent central axis points in the virtual central axis to obtain several basic combined points and several corresponding basic combined data of the tunnel under test; Step 14: Iteratively combine the basic combined data corresponding to adjacent basic combined points, construct the appearance structure of the tunnel under test according to the generated iterative combination information, input the generated iterative combined data into the appearance structure, and generate the three-dimensional contour information of the tunnel under test.

[0024] In this example, each time the lidar performs a measurement, it obtains a point cloud data of a periodic tunnel profile; In this example, the tunnel symmetry axis indicates that the tunnel under test is folded along this symmetry axis; In this example, the virtual central axis represents the result of connecting the symmetry axes of tunnels in different periods; In this example, the axis region represents the symmetry axis region related to the point cloud data of one period; In this example, the basic combined point represents the region corresponding to the combination of the fused data of adjacent periods, and the basic combined data represents the data result generated after this combination; In this example, the iterative combination means that the basic combined points with adjacent relationships are combined multiple times until the overall combination result of the tunnel under test is obtained.

[0025] The working principle and beneficial effects of the above technical solution: In order to timely detect the defects of the tunnel, the lidar performs periodic measurements on the tunnel under test, uses the relative positioning algorithm to analyze the tunnel symmetry axis of the obtained periodic profile point cloud data, and then connects the tunnel symmetry axes to generate a virtual central 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 central axis point in the virtual central axis. Then, the fused data on adjacent central axis points in the virtual central axis are combined, and the combined data are further combined until the overall data of the tunnel under test are obtained, and the three-dimensional contour information of the tunnel under test is generated. In this way, the point cloud data collected in different periods can be fused, avoiding the contingency of single point cloud data and improving the accuracy of defect detection.

[0026] Embodiment 3 Based on Embodiment 1, for the method for detecting defects in a water-rich high-pressure lining of a tunnel, Step 2 includes: Step 21: Use the tunnel modeling algorithm to perform partial segmentation processing on the three-dimensional contour information to obtain the constituent contour information corresponding to each tunnel constituent part of the tunnel to be measured. Use standard geometries to perform geometric matching on each piece of constituent contour information to obtain the cross-section constituent features corresponding to each constituent part. Step 22: Use the tunnel modeling algorithm to perform contour enhancement processing on the three-dimensional contour information to obtain the edge contour and inner contour corresponding to each tunnel constituent part of the tunnel to be measured. Combine the cross-section constituent features, edge contour, and inner contour corresponding to the same tunnel constituent part to obtain a number of model conditions. Step 23: Based on the three-dimensional contour information, construct a three-dimensional model framework of the tunnel to be measured. Use each model condition to render each tunnel constituent part in the three-dimensional model framework to obtain the tunnel contour model of the tunnel to be measured.

[0027] In this example, the partial segmentation processing means dividing the tunnel to be measured into: the ground part, the tunnel wall part, and the tunnel top part; In this example, geometric matching means the process of fitting the constituent contour with regular geometries; In this example, the edge contour refers to the contour presented by the edge of the tunnel, and the inner contour refers to the contour presented by the buildings inside the tunnel.

[0028] The working principle and beneficial effects of the above technical solution: First, perform segmentation processing on the three-dimensional contour information to determine the cross-section constituent features of different parts of the tunnel to be measured. Then, perform contour enhancement on the three-dimensional contour information to distinguish the edge contour and inner contour of the tunnel to be measured. Furthermore, use the three obtained features to establish model conditions, and further convert the three-dimensional contour information into a three-dimensional model framework, and use the model conditions to render it to obtain the tunnel contour model of the tunnel to be measured. In this way, every detail of the tunnel to be measured can be analyzed, making the obtained model consistent with the actual situation of the tunnel to be measured, and improving the effectiveness of defect detection.

[0029] Embodiment 4 Based on Embodiment 3, the method for detecting defects in a water-rich high-pressure lining of a tunnel further includes: Identify a number of load-bearing points included in the tunnel contour model, and mark the corresponding load-bearing angles of each load-bearing point in the tunnel contour model respectively to generate and display a real-time load-bearing report of the tunnel to be measured.

[0030] Working principle and beneficial effects of the above technical solution: To facilitate the supervision of the construction process by relevant personnel, the real-time bearing capacity information of the tunnel under test is analyzed and displayed by identifying the bearing points in the tunnel contour model, providing convenience for relevant personnel.

[0031] Example 5 Based on Example 1, for the method for detecting defects in a water-rich high-pressure lining of a tunnel, step 3 includes: Step 31: Obtain the environmental data of the tunnel under test, construct several environmental characteristics faced by the tunnel under test, perform water pressure analysis on each of the environmental characteristics faced to obtain several water pressure samples, and combine different numbers of the water pressure samples respectively to generate several detection water pressure distribution information of the tunnel under test; Step 32: Use each of the detection water pressure distribution information to perform a water pressure resistance test on the tunnel contour model, obtain several detection values corresponding to each model position, and construct a pressure - resistance linear graph corresponding to each model position based on the pressure application values of the model positions for each of the detection water pressure distribution information; 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 model position, and deduce the pressure resistance value corresponding to the tunnel patch water pressure value using the corresponding pressure - resistance linear graph to obtain the pressure resistance value corresponding to each model position.

[0032] In this example, the environmental characteristics faced represent the characteristics presented by the external environment that the tunnel under test may face in its environment. 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 are not necessarily the same. In this example, the 1D convolutional neural network represents a network used to extract the local features of the pressure - resistance linear graph and then capture its development trend. In this example, the pressure resistance value represents the maximum water pressure value that a model position can withstand.

[0033] Working principle and beneficial effects of the above technical solution: Determine the environmental characteristics faced by the tunnel to be measured based on the environmental data of the environment where the tunnel to be measured is located, so as to construct corresponding water pressure samples. In order to avoid the situation where the tunnel to be measured cannot withstand complex pressure when multiple environmental characteristics appear at one time, combine water pressure samples with different quantities (two or more), construct several kinds of detected water pressure distribution information of the tunnel to be measured, and then perform anti-water pressure detection on the tunnel contour, construct a pressure-applying and pressure-resistant linear graph for each model position, and further analyze its development trend through a convolutional neural network to determine the pressure-resistant value of each model position. In this way, various water pressure conditions in the environment where the tunnel to be measured is located can be detected and simulated, the anti-water pressure situation of the tunnel to be measured in a complex environment is determined, comprehensive analysis is realized, and damage to the tunnel to be measured caused by accidental extreme environments is avoided.

[0034] Example 6 Based on Example 5, the method for detecting defects in a water-rich and high-pressure lining of a tunnel further includes: When performing the anti-water pressure detection, locate the collapse position in the tunnel contour model when the tunnel contour model collapses during the detection; Regard the collapse position as a key defect position, and generate a corresponding key defect warning and transmit it to a specified terminal for display.

[0035] In this example, the specified terminal refers to a terminal used by relevant personnel and having a display function, generally including: on-site screens, mobile phones, and remote screens, etc.

[0036] Working principle and beneficial effects of the above technical solution: If the three-dimensional contour model collapses during the anti-water pressure detection, it indicates that there are verified defects in the tunnel to be measured. At this time, a timely reminder is given, and relevant personnel can take timely remedial measures according to the on-site situation to avoid affecting the quality of the tunnel after completion.

[0037] Example 7 Based on Example 1, in the method for detecting defects in a water-rich and high-pressure lining of a tunnel, step 4 includes: Step 41: Take each corresponding nine-square grid as a same-model area with each model position as the center, and calculate the average pressure-resistant value corresponding to each same-model area respectively; Step 42: Mark the numerical difference between each model position and the corresponding average pressure-resistant value in the corresponding model position of the tunnel contour model, and screen out the tunnel defect positions with negative numerical differences; Step 43: Trace each tunnel defect position in the point cloud data respectively, and deduce the actual position coordinates corresponding to each tunnel defect position according to the tracing result and display them.

[0038] The working principle and beneficial effects of the above technical solution: By comparing the position of a model with the average compressive value of its same-model area, the tunnel defect position of the tunnel to be measured is determined, and then it is traced in the point cloud data to determine the event defect position in the tunnel to be measured. Finally, its coordinates are extracted and displayed. In this way, accurate positioning can be achieved, providing technical reference for relevant personnel.

[0039] Example 8 Based on Example 7, the method for detecting tunnel water-rich high-pressure lining defects further includes: Construct the tunnel deformation information of the tunnel to be measured according to each actual position coordinate and the corresponding data difference and display it.

[0040] The working principle and beneficial effects of the above technical solution: Analyze the deformation information of the tunnel to be measured and provide accurate data for relevant personnel.

[0041] Example 9 Based on Example 1, the method for detecting tunnel water-rich high-pressure lining defects further includes: Analyze the structural stability of the tunnel to be measured according to the compressive value corresponding to each model position; When the structural stability is lower than the standard stability, it is determined that the structure of the tunnel to be measured is abnormal, and a corresponding reminder message is generated and displayed.

[0042] In this example, the standard stability represents the standard value uploaded in advance by relevant personnel before construction. Generally speaking, the standard stability is not lower than 95%.

[0043] The working principle and beneficial effects of the above technical solution: When the stability of the tunnel to be measured is too low, a reminder is given in time to avoid unnecessary losses caused by the collapse of the tunnel in the later stage.

[0044] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A method for detecting defects in a water-rich and high-pressure lining of a tunnel, characterized in that Including: Step 1: Use the relative positioning algorithm to fuse the multi-period tunnel contour point cloud data obtained by the lidar to obtain the three-dimensional contour information of the tunnel to be measured; Step 2: Use the tunnel modeling algorithm to process the three-dimensional contour information to obtain several model conditions, and construct the tunnel contour model of the tunnel to be measured; Step 3: Perform a water pressure resistance test on each model position in the tunnel contour model to obtain the compressive resistance value corresponding to each model position; Step 4: Locate the tunnel defect positions in the tunnel contour model where the compressive resistance value is lower than the average compressive resistance value of the same model area, identify the actual position coordinates of the tunnel defect positions and display them.

2. The method for detecting defects in a water-rich high-pressure lining of a tunnel according to claim 1, wherein The said Step 1 includes: Step 11: Control the lidar to perform periodic measurements on the tunnel to be measured to obtain several period tunnel contour point cloud data of the tunnel to be measured, and use the relative positioning algorithm to align the data of each period contour point cloud respectively to obtain the tunnel symmetry axis corresponding to each period contour point cloud data; Step 12: Connect the tunnel symmetry axes to obtain the virtual central axis of the tunnel to be measured, input each period tunnel contour point cloud data into the axis area corresponding to the virtual central axis respectively, and fuse the several point cloud data corresponding to the same central axis point to obtain the fused data corresponding to each central axis point; Step 13: Determine the real-time tunnel length of the tunnel to be measured according to the virtual axis center, and combine the fused data corresponding to the adjacent central axis points in the virtual central axis to obtain several basic combined points and several corresponding basic combined data of the tunnel to be measured; Step 14: Iteratively combine the basic combined data corresponding to the adjacent basic combined points, construct the appearance structure of the tunnel to be measured according to the generated iterative combination information, input the generated iterative combined data into the appearance structure, and generate the three-dimensional contour information of the tunnel to be measured.

3. The method for detecting defects in a water-rich high-pressure lining of a tunnel according to claim 1, wherein, The said Step 2 includes: Step 21: Use the tunnel modeling algorithm to perform partial segmentation processing on the three-dimensional contour information to obtain the composition contour information corresponding to each tunnel component of the tunnel to be measured, and use standard geometry to perform geometric matching on each composition contour information respectively to obtain the cross-section composition characteristics corresponding to each component; Step 22: Use the tunnel modeling algorithm to perform contour enhancement processing on the three-dimensional contour information to obtain the edge contour and inner contour corresponding to each tunnel component of the tunnel to be measured, and combine the cross-section composition characteristics, edge contour and inner contour corresponding to the same tunnel component to obtain several model conditions; Step 23: Based on the three-dimensional contour information, construct the three-dimensional model framework of the tunnel to be measured, and use each model condition to render each tunnel component in the three-dimensional model framework respectively to obtain the tunnel contour model of the tunnel to be measured.

4. The tunnel water-rich high-pressure lining defect detection method according to claim 3, characterized in that, Also included: Identify several load-bearing points included in the tunnel contour model, respectively mark several load-bearing angles corresponding to each load-bearing point in the tunnel contour model, generate a real-time load-bearing report of the tunnel under test and display it.

5. The tunnel water-rich high-pressure lining defect detection method according to claim 1, characterized in that The step 3 includes: Step 31: Obtain the environmental data of the tunnel under test, construct several environmental characteristics faced by the tunnel under test, respectively perform water pressure analysis on each of the faced environmental characteristics to obtain several water pressure samples, respectively combine different numbers of the water pressure samples to generate several detection water pressure distribution information of the tunnel under test; Step 32: Respectively use each detection water pressure distribution information to perform a water pressure resistance test on the tunnel contour model, obtain several detection values corresponding to each model position, and construct a pressure-applied - pressure-resistant linear graph corresponding to each model position based on the pressure-applied value of the model position for each detection water pressure distribution information; Step 33: Use a 1D convolutional neural network to respectively perform trend analysis on each pressure-applied - pressure-resistant linear graph, estimate the tunnel collapse water pressure value corresponding to each model position, use the corresponding pressure-applied - pressure-resistant linear graph to deduce the pressure-resistant value corresponding to the tunnel patch water pressure value, and obtain the pressure-resistant value corresponding to each model position.

6. The method for detecting defects in a water-rich and high-pressure lining of a tunnel according to claim 5, wherein It further includes: When a detection collapse occurs in the tunnel contour model during the water pressure resistance test, locate the collapse position in the tunnel contour model; Regard the collapse position as a key defect position, generate a corresponding key defect warning and transmit it to a designated terminal for display.

7. The method for detecting defects of a water-rich high-pressure lining in a tunnel according to claim 1, characterized in that, The step 4 includes: Step 41: Respectively regard the corresponding nine-square grid with each model position as the center as the same model area, and respectively calculate the average pressure-resistant value corresponding to each same model area; Step 42: Respectively mark the numerical difference between each model position and the corresponding average pressure-resistant value in the model position corresponding to the tunnel contour model, and screen out the tunnel defect positions with negative numerical differences; Step 43: Respectively trace each tunnel defect position in the point cloud data, and deduce the actual position coordinates corresponding to each tunnel defect position according to the tracing result and display them.

8. The method for detecting defects in a water-rich high-pressure lining of a tunnel according to claim 7, characterized in that, It further includes: Construct tunnel deformation information of the tunnel under test based on each actual position coordinate and the corresponding data difference and display it.

9. The tunnel water-rich high-pressure lining defect detection method according to claim 1, wherein It further includes: Analyze the structural stability of the tunnel under test according to the pressure-resistant value corresponding to each model position; When the structural stability is lower than the standard stability, determine that the structure of the tunnel under test is abnormal, generate a corresponding reminder message and display it.

Images