A three-dimensional laser point cloud detection method and system for the wide and thick strip of lining in the water-filled area of ​​a tunnel

Abstract

The present invention provides a method and system for detecting the wide and thick strips of the lining in the water-contributing area of ​​a tunnel. The method comprises detecting the wide and thick strips of the lining in the water-contributing area of ​​the tunnel by a rolling ball method, collecting laser point cloud data of the wide and thick strips of the lining in the water-contributing area of ​​the tunnel by three-dimensional laser scanning of the tunnel point cloud; establishing a high-fidelity tunnel twin model; simulating the tunnel deformation by finite element method, constructing a finite element simulation tunnel deformation analysis model, and outputting the true value of the tunnel deformation of the tunnel twin model; building a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; performing simulated three-dimensional laser scanning on the tunnel twin model in a virtual environment to obtain large sample detection data; assisting in training a deformation detection neural network model based on the large sample detection data; performing tunnel point cloud registration by the neural network model; obtaining a tunnel cross-section point cloud by fitting the tunnel centerline, and performing tunnel deformation analysis; and significantly improving the accuracy of tunnel deformation analysis processing.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional laser point cloud detection of wide and thick strips of lining in a tunnel water-filled area and laser detection of tunnel engineering safety technology; more specifically, the present invention relates to a three-dimensional laser point cloud detection method and system for wide and thick strips of lining in a tunnel water-filled area. Background Art

[0002] Tunnel engineering safety technology is very critical. Due to the slow deformation of tunnels and the difficulty in obtaining effective experimental detection data, the research on tunnel deformation detection technology is limited. How to detect the wide and thick strips of the lining in the tunnel water-contributing area and collect data on the wide and thick strips of the lining in the tunnel water-contributing area, how to simulate tunnel deformation, simulate tunnel deformation and analyze the true value of tunnel deformation, how to build a virtual simulation platform for tunnel simulation scanning and simulate three-dimensional laser scanning in a virtual environment to obtain large sample detection data, how to more efficiently optimize the training of neural network models and perform tunnel point cloud alignment and tunnel deformation analysis, etc., remain to be solved. Therefore, it is necessary to propose a three-dimensional laser point cloud detection system and method for the wide and thick strips of the lining in the tunnel water-contributing area to at least partially solve the problems existing in the existing technology. Summary of the Invention

[0003] A series of simplified concepts are introduced in the summary of the invention, which will be further explained in detail in the specific implementation method. The summary of the invention does not mean to attempt to limit the key features and necessary technical features of the technical solution for protection, nor does it mean to attempt to determine the scope of protection of the technical solution for protection.

[0004] To at least partially solve the above problems, the present invention provides a three-dimensional laser point cloud detection method for the wide and thick strip of the lining in the water-filled area of ​​a tunnel, comprising:

[0005] S10: Use the rolling ball method to detect the lining width and thickness of the tunnel water supply area, and use 3D laser scanning of the tunnel point cloud to collect laser point cloud data of the lining width and thickness of the tunnel water supply area; and establish a high-fidelity tunnel twin model;

[0006] S20, simulating tunnel deformation through finite element analysis, building a finite element simulation tunnel deformation analysis model, and outputting the true value of tunnel deformation of the tunnel twin model;

[0007] S30: Build a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; simulate three-dimensional laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data;

[0008] S40, based on large sample detection data, assists in training a deformation detection neural network model; performs tunnel point cloud registration through the neural network model; obtains tunnel cross-section point cloud by fitting the tunnel centerline, and performs tunnel deformation analysis.

[0009] Preferably, S10 includes:

[0010] S101 uses the rolling ball method to detect the width and thickness of the lining in the water-bearing area of ​​the tunnel. Using strain and humidity sensing optical fibers, it estimates the damaged defect area and obtains humidity information in the defect area.

[0011] S102, while the spherical body rolls left and right and up and down around the tunnel water supply area, the tunnel point cloud is scanned by three-dimensional laser to collect laser point cloud data of the lining width and thickness zone of the tunnel water supply area;

[0012] S103: Establish a high-fidelity tunnel twin model based on the damaged defect area, humidity information of the defect area, and laser point cloud data of the lining width and thickness of the tunnel water supply area.

[0013] Preferably, S20 includes:

[0014] S201, establishing finite element simulation metadata of sampling nodes of the lining width and thickness zone in the water-bearing area, wherein the finite element simulation metadata includes the geological structure of the rock layer and soil, the moisture content of the rock layer and soil, the thickness of the rock layer and soil, and the deformation of the tunnel;

[0015] S202, based on the single metadata tunnel deformation analysis information, intelligently allocating the proportions of the geological structure influence weight, the rock layer soil moisture content influence weight, and the rock layer soil thickness influence weight that affect the tunnel deformation;

[0016] S203, constructing a finite element simulation tunnel deformation analysis model; outputting the tunnel deformation true value of the tunnel twin model based on the finite element simulation tunnel deformation analysis model.

[0017] Preferably, S30 includes:

[0018] S301: Building a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data;

[0019] S302, simulate three-dimensional laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data.

[0020] Preferably, S40 includes:

[0021] S401, assisting in training a deformation detection neural network model based on large sample detection data; the deformation detection neural network model includes a Geotransformer neural network model;

[0022] S402, performing tunnel point cloud registration using a neural network model; obtaining a tunnel cross-section point cloud by fitting the tunnel centerline, and performing tunnel deformation analysis;

[0023] S403, determining the tunnel deformation position in the tunnel cross-section point cloud and inferring the tunnel deformation evolution trend;

[0024] The tunnel deformation analysis is performed by fitting the tunnel centerline to obtain the tunnel cross-section point cloud, which includes the following steps: inputting the collected tunnel cross-section data; selecting a small number of points to construct and solve the error equation; distinguishing between in-point and out-point based on the threshold; determining whether the number of in-points meets 90%; if not, eliminating the out-points and integrating the in-points; outputting the in-points that meet the conditions, and performing tunnel cross-section analysis based on the in-points.

[0025] The present invention provides a three-dimensional laser point cloud detection system for the wide and thick strip of the lining in the water-filled area of ​​a tunnel, comprising:

[0026] The tunnel water conservancy area lining twin model subsystem uses the rolling ball method to detect the width and thickness of the tunnel water conservancy area lining. It also uses 3D laser scanning of the tunnel point cloud to collect laser point cloud data of the width and thickness of the tunnel water conservancy area lining. This allows for the establishment of a high-fidelity tunnel twin model.

[0027] The finite element simulation tunnel deformation subsystem simulates tunnel deformation through finite element analysis, builds a finite element simulation tunnel deformation analysis model, and outputs the true value of tunnel deformation of the tunnel twin model;

[0028] The tunnel simulation scanning virtual simulation subsystem builds a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; simulates 3D laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data;

[0029] The tunnel point cloud registration and deformation analysis subsystem assists in training the deformation detection neural network model based on large sample detection data; performs tunnel point cloud registration through the neural network model; obtains the tunnel cross-section point cloud by fitting the tunnel centerline, and performs tunnel deformation analysis.

[0030] Preferably, the tunnel water conferring area lining twin model subsystem includes:

[0031] The rolling ball method tunnel defect detection module uses the rolling ball method to detect the width and thickness of the lining in the tunnel water supply area. Through the strain and humidity sensing optical fiber, it estimates the damaged defect area and obtains humidity information in the defect area.

[0032] The 3D laser scanning tunnel point cloud module collects laser point cloud data of the wide and thick strips of the tunnel water supply area through 3D laser scanning of the tunnel point cloud as the sphere rolls left and right and up and down around the tunnel water supply area.

[0033] The high-fidelity tunnel twin model architecture module establishes a high-fidelity tunnel twin model based on the damaged defect area, humidity information of the defect area, and laser point cloud data of the lining width and thickness of the tunnel water supply area.

[0034] Preferably, the finite element simulation tunnel deformation subsystem includes:

[0035] The finite element simulation module for the lining of the water-bearing area establishes finite element simulation metadata for sampling nodes of the lining width and thickness in the water-bearing area. The finite element simulation metadata includes the geological structure of the rock layer and soil, the moisture content of the rock layer and soil, the thickness of the rock layer and soil, and the deformation of the tunnel.

[0036] The intelligent tunnel deformation weight allocation module intelligently allocates the weights of geological structure, rock layer soil moisture content, and rock layer soil thickness that affect tunnel deformation based on the single metadata tunnel deformation analysis information.

[0037] The tunnel deformation analysis model module is used to construct a finite element simulation tunnel deformation analysis model; based on the finite element simulation tunnel deformation analysis model, the true value of the tunnel deformation of the tunnel twin model is output.

[0038] Preferably, the tunnel simulation scanning virtual simulation subsystem includes:

[0039] Tunnel scanning simulation platform: Based on the tunnel twin model and laser scanning feature data, a tunnel simulation scanning virtual simulation platform is built;

[0040] The simulated 3D laser scanning module performs simulated 3D laser scanning on the tunnel twin model in a virtual environment to obtain large sample detection data.

[0041] Preferably, the tunnel point cloud registration deformation analysis subsystem includes:

[0042] The detection data network model training module assists in training the deformation detection neural network model based on large sample detection data; the deformation detection neural network model includes the Geotransformer neural network model;

[0043] The tunnel point cloud registration module uses a neural network model to perform tunnel point cloud registration; it obtains tunnel cross-section point clouds by fitting the tunnel centerline and performs tunnel deformation analysis;

[0044] Tunnel deformation determination and inference module determines the tunnel deformation position in the tunnel cross-section point cloud and infers the tunnel deformation evolution trend;

[0045] The tunnel deformation analysis is performed by fitting the tunnel centerline to obtain the tunnel cross-section point cloud, which includes the following steps: inputting the collected tunnel cross-section data; selecting a small number of points to construct and solve the error equation; distinguishing between in-point and out-point based on the threshold; determining whether the number of in-points meets 90%; if not, eliminating the out-points and integrating the in-points; outputting the in-points that meet the conditions, and performing tunnel cross-section analysis based on the in-points.

[0046] Compared with the prior art, the present invention has at least the following beneficial effects:

[0047] The present invention provides a method and system for detecting the width and thickness of the lining of the water-contributing area of ​​a tunnel. The method detects the width and thickness of the lining of the water-contributing area of ​​the tunnel by a rolling ball method, collects the laser point cloud data of the width and thickness of the lining of the water-contributing area of ​​the tunnel by three-dimensional laser scanning of the tunnel point cloud; establishes a high-fidelity tunnel twin model; simulates the deformation of the tunnel by finite element method, constructs a finite element simulation tunnel deformation analysis model, and outputs the true value of the tunnel deformation of the tunnel twin model; builds a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; simulates the three-dimensional laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data; assists in training the deformation detection neural network model based on the large sample detection data; performs tunnel point cloud registration through the neural network model; obtains the tunnel cross-section point cloud by fitting the tunnel central axis, and performs tunnel deformation analysis; uses a digital twin method for tunnel deformation detection research to establish a high-fidelity tunnel twin model; simulates the deformation of the tunnel by finite element method, and outputs the true value of the tunnel deformation of the tunnel twin model The system can output the deformation true value of the tunnel twin model; build a virtual simulation platform to realize 3D laser scanning of the tunnel model in a virtual environment to obtain large sample detection data and assist in training deformation detection methods; deformation detection uses Geotransformer neural network to realize tunnel point cloud registration, and obtains tunnel cross-section point cloud by fitting the tunnel centerline to realize tunnel deformation analysis; it improves the safety of tunnel engineering and can solve the problem that tunnel deformation is slow and difficult to obtain effective experimental detection data; it can detect the lining width and thickness of the tunnel water supply area and collect data on the lining width and thickness of the tunnel water supply area; it can simulate tunnel deformation more accurately; it can simulate tunnel deformation and analyze the true value of tunnel deformation; it can build a tunnel simulation scanning virtual simulation platform, and simulate 3D laser scanning in a virtual environment to obtain large sample detection data; it can more efficiently optimize the training of neural network models and perform tunnel point cloud registration, significantly improving the accuracy of tunnel deformation analysis and processing; it has important technical significance and significant effects.

[0048] The present invention describes a three-dimensional laser point cloud detection method and system for the wide and thick strip of the lining in the water-bearing area of ​​a tunnel. Other advantages, objectives and features of the present invention will be partially reflected in the following description and will also be understood by technicians in this field through research and practice of the present invention. 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 This is a diagram showing an embodiment of a three-dimensional laser point cloud detection method for wide and thick strips of lining in a tunnel water-filled area according to the present invention.

[0051] Figure 2This is a diagram of an embodiment of a three-dimensional laser point cloud detection system for wide and thick strips of lining in a tunnel water-filled area according to the present invention.

[0052] Figure 3 This is another embodiment of the three-dimensional laser point cloud detection system for the wide and thick strip of the lining in the water-filled area of ​​a tunnel described in the present invention. DETAILED DESCRIPTION

[0053] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments so that those skilled in the art can implement the invention with reference to the description. As shown in the drawings, the present invention provides a three-dimensional laser point cloud detection method for the wide and thick strip of the lining in the water-filled area of ​​a tunnel, comprising:

[0054] S10: Use the rolling ball method to detect the lining width and thickness of the tunnel water supply area, and use 3D laser scanning of the tunnel point cloud to collect laser point cloud data of the lining width and thickness of the tunnel water supply area; and establish a high-fidelity tunnel twin model;

[0055] S20, simulating tunnel deformation through finite element analysis, building a finite element simulation tunnel deformation analysis model, and outputting the true value of tunnel deformation of the tunnel twin model;

[0056] S30: Build a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; simulate three-dimensional laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data;

[0057] S40, based on large sample detection data, assists in training a deformation detection neural network model; performs tunnel point cloud registration through the neural network model; obtains tunnel cross-section point cloud by fitting the tunnel centerline, and performs tunnel deformation analysis.

[0058] The principle and effect of the above technical solution are: a three-dimensional laser point cloud detection method for the wide and thick strips of the lining in the water-contributing area of ​​a tunnel, comprising: detecting the wide and thick strips of the lining in the water-contributing area of ​​the tunnel by the rolling ball method, collecting laser point cloud data of the wide and thick strips of the lining in the water-contributing area of ​​the tunnel by three-dimensional laser scanning of the tunnel point cloud; establishing a high-fidelity tunnel twin model; simulating the deformation of the tunnel by finite element simulation, constructing a finite element simulation tunnel deformation analysis model, and outputting the true value of the tunnel deformation of the tunnel twin model; building a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; performing simulated three-dimensional laser scanning on the tunnel twin model in a virtual environment to obtain large sample detection data; assisting in training a deformation detection neural network model based on the large sample detection data; performing tunnel point cloud registration through the neural network model; obtaining the tunnel cross-section point cloud by fitting the tunnel central axis, and performing tunnel deformation analysis; using the digital twin method for tunnel deformation detection research to establish a high-fidelity tunnel twin model; simulating the tunnel by finite element simulation deformation, and output the true deformation value of the tunnel twin model; build a virtual simulation platform to realize three-dimensional laser scanning of the tunnel model in a virtual environment to obtain large sample detection data and assist in training deformation detection methods; deformation detection uses Geotransformer neural network to realize tunnel point cloud registration, and obtains tunnel section point cloud by fitting the tunnel centerline to realize tunnel deformation analysis; it improves the safety of tunnel engineering and can solve the problem that tunnel deformation is slow and difficult to obtain effective experimental detection data; it can detect the lining width and thickness of the tunnel water-bearing area and collect data on the lining width and thickness of the tunnel water-bearing area; it can simulate tunnel deformation more accurately; it can simulate tunnel deformation and analyze the true value of tunnel deformation; it can build a tunnel simulation scanning virtual simulation platform, and simulate three-dimensional laser scanning in a virtual environment to obtain large sample detection data; it can more efficiently optimize the training of neural network models and perform tunnel point cloud registration, significantly improving the accuracy of tunnel deformation analysis and processing; it has important technical significance and significant effects.

[0059] In one embodiment, S10 includes:

[0060] S101 uses the rolling ball method to detect the width and thickness of the lining in the water-bearing area of ​​the tunnel. Using strain and humidity sensing optical fibers, it estimates the damaged defect area and obtains humidity information in the defect area.

[0061] S102, while the spherical body rolls left and right and up and down around the tunnel water supply area, the tunnel point cloud is scanned by three-dimensional laser to collect laser point cloud data of the lining width and thickness zone of the tunnel water supply area;

[0062] S103: Establish a high-fidelity tunnel twin model based on the damaged defect area, humidity information of the defect area, and laser point cloud data of the lining width and thickness of the tunnel water supply area.

[0063] The principle and effect of the above technical solution are as follows: Figure 3As shown, the wide and thick strips of the lining in the water-contributing area of ​​the tunnel are detected by the rolling ball method, and the damaged defect area is estimated and the humidity information of the defect area is obtained by the strain and humidity sensing optical fiber; during the rolling of the sphere around the water-contributing area of ​​the tunnel, the laser point cloud data of the wide and thick strips of the lining in the water-contributing area of ​​the tunnel are collected by three-dimensional laser scanning of the tunnel point cloud; a high-fidelity tunnel twin model is established based on the damaged defect area, the humidity information of the defect area and the laser point cloud data of the wide and thick strips of the lining in the water-contributing area of ​​the tunnel; the wide and thick strips of the lining in the water-contributing area of ​​the tunnel are detected by the rolling ball method, and the strain optical fiber detection information and the humidity and humidity sensing detection information are obtained; based on the strain optical fiber detection information and the humidity and humidity sensing detection information, the damaged defect area is estimated and the humidity information of the defect area is obtained. The method includes: setting a sphere with a radius of hr, and setting a strain and humidity sensing optical fiber on the surface of the sphere; the sphere rolls around the water-contributing area of ​​the tunnel, and the sphere The area contacted by the spherical body is the estimated damaged defect area, and the space not contacted by the spherical body is the effective protection space; the strain and humidity sensing optical fiber includes a grating optical fiber ribbon 1011 on the surface of the spherical body, a humidity-sensitive material 1012 on the surface of the spherical body, and an optical fiber humidity signal detection module 1013; the grating optical fiber ribbon on the surface of the spherical body detects the area contacted by the spherical body according to the optical fiber strain, and obtains the optical fiber strain signal of the spherical body contact; humidity causes the humidity-sensitive material on the surface of the spherical body to change, and a change signal is formed according to the change of the humidity-sensitive material on the surface of the spherical body, and the change signal of the humidity-sensitive material contacted by the spherical body is obtained; the optical fiber humidity signal detection module detects the optical fiber strain signal of the spherical body contact and the change signal of the humidity-sensitive material contacted by the spherical body, obtains strain optical fiber detection information and humidity and humidity-sensitive detection information, and estimates the damaged defect area according to the strain optical fiber detection information and the humidity and humidity-sensitive detection information, and obtains the humidity information of the defect area.

[0064] In one embodiment, S20 includes:

[0065] S201, establishing finite element simulation metadata of sampling nodes of the lining width and thickness zone in the water-bearing area, wherein the finite element simulation metadata includes the geological structure of the rock layer and soil, the moisture content of the rock layer and soil, the thickness of the rock layer and soil, and the deformation of the tunnel;

[0066] S202, based on the single metadata tunnel deformation analysis information, intelligently allocating the proportions of the geological structure influence weight, the rock layer soil moisture content influence weight, and the rock layer soil thickness influence weight that affect the tunnel deformation;

[0067] S203, constructing a finite element simulation tunnel deformation analysis model; outputting the tunnel deformation true value of the tunnel twin model based on the finite element simulation tunnel deformation analysis model.

[0068] The principle and effect of the above technical solution are as follows: establishing finite element simulation metadata of sampling nodes of wide and thick strips of lining in water-bearing area, the finite element simulation metadata includes rock soil geological structure, rock soil moisture content, rock soil thickness and tunnel deformation; intelligently allocating the proportions among geological structure influence weight, rock soil moisture content influence weight and rock soil thickness influence weight that affect tunnel deformation according to single metadata tunnel deformation analysis information; constructing a finite element simulation tunnel deformation analysis model; outputting the tunnel deformation true value of the tunnel twin model according to the finite element simulation tunnel deformation analysis model; establishing finite element simulation metadata of sampling nodes of wide and thick strips of lining in water-bearing area according to single metadata tunnel deformation analysis information, the finite element simulation metadata includes rock soil geological structure, rock soil moisture content, rock soil thickness and tunnel deformation; establishing metadata simulation analysis relationship among rock soil geological structure, rock soil moisture content, rock soil thickness and tunnel deformation according to finite element simulation metadata; metadata simulation analysis relationship includes: mainly obtaining rock type data, soil type data and rock soil ratio data in obtaining rock soil geological structure; The rock type is analyzed based on its rock strength, the soil type is analyzed based on its water absorption and softness, and the rock-soil ratio is analyzed based on the statistical average of the rock and soil contents. The lower the rock strength, the higher the soil water absorption and softness, and the lower the rock-soil ratio, the greater the impact of the geological structure on the tunnel deformation, which is set as the geological structure influence weight of the tunnel deformation. When the rock soil moisture content increases, the pressure on the wide and thick strips of the lining in the water-bearing area increases, and the plastic deformation of the tunnel section increases, which is set as the rock soil moisture content influence weight of the tunnel deformation. The thicker the rock soil, the greater the pressure on the tunnel, the greater the pressure on the wide and thick strips of the lining in the water-bearing area, and the greater the impact on the tunnel deformation, which is set as the rock soil thickness influence weight of the tunnel deformation. Tunnel deformation is simulated and analyzed according to single metadata to obtain single metadata tunnel deformation analysis information. Based on the single metadata tunnel deformation analysis information, influence weights are allocated in proportion to the tunnel deformation size. The proportions of the geological structure influence weight, rock soil moisture content influence weight, and rock soil thickness influence weight that affect the tunnel deformation are intelligently allocated to construct a finite element simulation tunnel deformation analysis model.

[0069] In one embodiment, S30 includes:

[0070] S301: Building a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data;

[0071] S302, simulate three-dimensional laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data.

[0072] The principle and effect of the above technical solution are as follows: based on the tunnel twin model and laser scanning feature data, a tunnel simulation scanning virtual simulation platform is built; the tunnel twin model is simulated with three-dimensional laser scanning in a virtual environment to obtain large sample detection data; based on the tunnel twin model and laser scanning feature data, a tunnel simulation scanning virtual simulation platform is built, including: through the physical three-dimensional laser scanning device in the tunnel, the scanning data of the lining width and thickness of multiple sections of the water-bearing area in the tunnel are collected; the physical three-dimensional laser scanning device is set on the initial tunnel center axis; a strain temperature-sensitive optical fiber fitting the initial tunnel center axis is set on the initial tunnel center axis to verify that the scanning baseline of the physical three-dimensional laser scanning device is consistent with the initial tunnel center axis; through the physical three-dimensional laser scanning device, the data of the lining width and thickness of multiple sections of the water-bearing area in the tunnel are collected; a one-to-one correspondence between the physical three-dimensional laser scanning and the simulated three-dimensional laser scanning data of the lining width and thickness of the water-bearing area is established, and a tunnel simulation scanning virtual simulation platform is built.

[0073] In one embodiment, S40 includes:

[0074] S401, assisting in training a deformation detection neural network model based on large sample detection data; the deformation detection neural network model includes a Geotransformer neural network model;

[0075] S402, performing tunnel point cloud registration using a neural network model; obtaining a tunnel cross-section point cloud by fitting the tunnel centerline, and performing tunnel deformation analysis;

[0076] S403, determining the tunnel deformation position in the tunnel cross-section point cloud and inferring the tunnel deformation evolution trend;

[0077] like Figure 1 As shown in the figure, the tunnel cross-section point cloud is obtained by fitting the tunnel central axis, and the tunnel deformation analysis includes: inputting the collected tunnel cross-section data; selecting a small number of points to construct the error equation and solving it; distinguishing the in-points and out-points according to the threshold value; determining whether the number of in-points meets 90%; if the number of in-points does not meet 90%, eliminating the out-points and integrating the in-points; outputting the in-points that meet the conditions, and performing tunnel cross-section analysis based on the in-points.

[0078] The principle and effect of the above technical solution are as follows: based on large sample detection data, auxiliary training of deformation detection neural network model; deformation detection neural network model includes Geotransformer neural network model; tunnel point cloud registration is performed through neural network model; tunnel cross-section point cloud is obtained by fitting the tunnel central axis, and tunnel deformation analysis is performed; tunnel deformation position in tunnel cross-section point cloud is determined, and tunnel deformation evolution trend is inferred; tunnel cross-section point cloud is obtained by fitting the tunnel central axis, and tunnel deformation analysis includes: inputting collected tunnel cross-section data; selecting a small number of points to construct error equation and solving it; distinguishing between in-points and out-points according to threshold value; determining whether the number of in-points meets 90%; if the number of in-points does not meet 90%, the out-points are eliminated and the in-points are integrated; outputting in-points that meet the conditions, and performing tunnel cross-section analysis based on the in-points;

[0079] Determining the tunnel deformation position in the tunnel cross-section point cloud and inferring the tunnel deformation evolution trend includes: obtaining multi-dimensional simulated tunnel deformation position index data through simulated three-dimensional laser scanning; comparing and verifying the multi-dimensional simulated tunnel deformation position index data with the scanning data of the lining width and thickness strips of multiple sections of the water-bearing area in the tunnel, and verifying the accuracy of the simulated three-dimensional laser scanning; when the verification error of the simulated three-dimensional laser scanning accuracy is lower than the set verification error, fitting the tunnel centerline through the multi-dimensional simulated tunnel deformation position index data to obtain the tunnel cross-section point cloud, perform tunnel deformation analysis, determine the tunnel deformation position in the tunnel cross-section point cloud, and infer the tunnel deformation evolution trend.

[0080] like Figure 2 As shown, the present invention provides a three-dimensional laser point cloud detection system for the wide and thick strip of the lining in the water-filled area of ​​a tunnel, comprising:

[0081] The tunnel water conservancy area lining twin model subsystem uses the rolling ball method to detect the width and thickness of the tunnel water conservancy area lining. It also uses 3D laser scanning of the tunnel point cloud to collect laser point cloud data of the width and thickness of the tunnel water conservancy area lining. This allows for the establishment of a high-fidelity tunnel twin model.

[0082] The finite element simulation tunnel deformation subsystem simulates tunnel deformation through finite element analysis, builds a finite element simulation tunnel deformation analysis model, and outputs the true value of tunnel deformation of the tunnel twin model;

[0083] The tunnel simulation scanning virtual simulation subsystem builds a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; simulates 3D laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data;

[0084] The tunnel point cloud registration and deformation analysis subsystem assists in training the deformation detection neural network model based on large sample detection data; performs tunnel point cloud registration through the neural network model; obtains the tunnel cross-section point cloud by fitting the tunnel centerline, and performs tunnel deformation analysis.

[0085] The principle and effect of the above technical solution are as follows: the present invention provides a three-dimensional laser point cloud detection system for the wide and thick strips of the lining in the water-contributing area of ​​a tunnel, comprising: a tunnel water-contributing area lining twin model subsystem, which detects the wide and thick strips of the lining in the water-contributing area of ​​the tunnel by the rolling ball method, collects the laser point cloud data of the wide and thick strips of the lining in the water-contributing area of ​​the tunnel by three-dimensional laser scanning of the tunnel point cloud; establishes a high-fidelity tunnel twin model; a finite element simulation tunnel deformation subsystem, which simulates the tunnel deformation by finite element, constructs a finite element simulation tunnel deformation analysis model, and outputs the true value of the tunnel deformation of the tunnel twin model; a tunnel simulation scanning virtual simulation subsystem, which builds a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; simulates three-dimensional laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data; a tunnel point cloud registration deformation analysis subsystem, which assists in training the deformation detection neural network model based on the large sample detection data; performs tunnel point cloud registration by the neural network model; obtains the tunnel section point cloud by fitting the tunnel centerline, and performs tunnel deformation analysis; tunnel deformation detection research The digital twin method studied in this paper is used to establish a high-fidelity tunnel twin model; the deformation of the tunnel is simulated by finite element analysis to output the deformation true value of the tunnel twin model; a virtual simulation platform is built to realize 3D laser scanning of the tunnel model in a virtual environment to obtain large sample detection data to assist in training the deformation detection method; the deformation detection uses the Geotransformer neural network to realize tunnel point cloud registration, and the tunnel cross-section point cloud is obtained by fitting the tunnel centerline to realize tunnel deformation analysis; it improves the safety of tunnel engineering and can solve the problem of slow tunnel deformation and difficulty in obtaining effective experimental detection data; it can detect the width and thickness of the lining in the tunnel water-bearing area and collect data on the width and thickness of the lining in the tunnel water-bearing area; it can more accurately simulate the deformation of the tunnel; it can simulate tunnel deformation and analyze the true value of tunnel deformation; it can build a tunnel simulation scanning virtual simulation platform and simulate 3D laser scanning in a virtual environment to obtain large sample detection data; it can more efficiently optimize the training of neural network models and perform tunnel point cloud registration, significantly improving the accuracy of tunnel deformation analysis and processing; it has important technical significance and significant effects.

[0086] In one embodiment, the tunnel water conferring area lining twin model subsystem includes:

[0087] The rolling ball method tunnel defect detection module uses the rolling ball method to detect the width and thickness of the lining in the tunnel water supply area. Through the strain and humidity sensing optical fiber, it estimates the damaged defect area and obtains humidity information in the defect area.

[0088] The 3D laser scanning tunnel point cloud module collects laser point cloud data of the wide and thick strips of the tunnel water supply area through 3D laser scanning of the tunnel point cloud as the sphere rolls left and right and up and down around the tunnel water supply area.

[0089] The high-fidelity tunnel twin model architecture module establishes a high-fidelity tunnel twin model based on the damaged defect area, humidity information of the defect area, and laser point cloud data of the lining width and thickness of the tunnel water supply area.

[0090] The principle and effect of the above technical solution are as follows: Figure 3 As shown, the tunnel water supply area lining twin model subsystem includes: a rolling ball method tunnel defect detection module, which detects the wide and thick strips of the tunnel water supply area lining by the rolling ball method, and estimates the damaged defect area and obtains the humidity information of the defect area through the strain and humidity sensing optical fiber; a three-dimensional laser scanning tunnel point cloud module, in which the sphere rolls left and right and up and down around the tunnel water supply area, the three-dimensional laser scanning tunnel point cloud is used to collect the laser point cloud data of the wide and thick strips of the tunnel water supply area lining; a high-fidelity tunnel twin model architecture module, which establishes a high-fidelity tunnel twin model based on the damaged defect area, the humidity information of the defect area and the laser point cloud data of the wide and thick strips of the tunnel water supply area lining; the rolling ball method is used to detect the wide and thick strips of the tunnel water supply area lining, and the strain optical fiber detection information and the humidity and humidity sensing detection information are obtained. According to the strain optical fiber detection information and the humidity and humidity sensing detection information, the damaged defect area is estimated and the humidity information of the defect area is obtained. The module includes: setting a sphere with a radius of hr, and setting a A strain and humidity sensing optical fiber is provided; the sphere rolls left and right and up and down around the water supply area of ​​the tunnel; the area touched by the sphere is the estimated damaged defect area, and the space not touched by the sphere is the effective protection space; the strain and humidity sensing optical fiber includes a grating optical fiber ribbon 1011 on the surface of the sphere, a humidity-sensitive material 1012 on the surface of the sphere, and an optical fiber humidity signal detection module 1013; the grating optical fiber ribbon on the surface of the sphere detects the area touched by the sphere according to the optical fiber strain, and obtains the optical fiber strain signal of the sphere contacting the sphere; humidity causes the humidity-sensitive material on the surface of the sphere to change, and a change signal is formed according to the change of the humidity-sensitive material on the surface of the sphere, and the change signal of the humidity-sensitive material contacted by the sphere is obtained; the optical fiber humidity signal detection module detects the optical fiber strain signal of the sphere contacting the sphere and the change signal of the humidity-sensitive material contacted by the sphere, obtains strain optical fiber detection information and humidity and humidity-sensitive detection information, and estimates the damaged defect area according to the strain optical fiber detection information and the humidity and humidity-sensitive detection information, and obtains humidity information of the defect area.

[0091] In one embodiment, the finite element simulation tunnel deformation subsystem includes:

[0092] The finite element simulation module for the lining of the water-bearing area establishes finite element simulation metadata for sampling nodes of the lining width and thickness in the water-bearing area. The finite element simulation metadata includes the geological structure of the rock layer and soil, the moisture content of the rock layer and soil, the thickness of the rock layer and soil, and the deformation of the tunnel.

[0093] The intelligent tunnel deformation weight allocation module intelligently allocates the weights of geological structure, rock layer soil moisture content, and rock layer soil thickness that affect tunnel deformation based on the single metadata tunnel deformation analysis information.

[0094] The tunnel deformation analysis model module is used to construct a finite element simulation tunnel deformation analysis model; based on the finite element simulation tunnel deformation analysis model, the true value of the tunnel deformation of the tunnel twin model is output.

[0095] The principle and effect of the above technical solution are as follows: the finite element simulation tunnel deformation subsystem includes: a finite element simulation module for the lining of the water-bearing area, which establishes the finite element simulation metadata of the sampling nodes of the lining width and thickness of the water-bearing area, and the finite element simulation metadata includes the geological structure of the rock layer and soil, the moisture content of the rock layer and soil, the thickness of the rock layer and soil, and the tunnel deformation; a tunnel deformation weight intelligent allocation module, which intelligently allocates the proportion of the geological structure influence weight, the rock layer and soil moisture content influence weight, and the rock layer and soil thickness influence weight that affect the tunnel deformation based on the single metadata tunnel deformation analysis information; a tunnel deformation analysis model module, which constructs a finite element simulation tunnel deformation analysis model; and outputs the tunnel deformation true value of the tunnel twin model based on the finite element simulation tunnel deformation analysis model.

[0096] According to the single metadata tunnel deformation analysis information, the finite element simulation metadata of the lining width and thickness sampling nodes in the water-bearing area is established. The finite element simulation metadata includes the rock soil geological structure, rock soil moisture content, rock soil thickness and tunnel deformation; according to the finite element simulation metadata, the metadata simulation analysis relationship between the rock soil geological structure, rock soil moisture content, rock soil thickness and tunnel deformation is established; the metadata simulation analysis relationship includes: obtaining the rock type data, soil type data and rock soil ratio data in the rock soil geological structure; the rock type is analyzed according to the rock firmness, the soil type is analyzed according to the water absorption and softness, and the rock soil ratio is analyzed according to the statistical average content between rock and soil; the lower the rock firmness, the higher the soil water absorption and softness, and the lower the rock soil ratio, the higher the geological structure. The greater the influence of the tunnel deformation, the geological structure influence weight is set as the tunnel deformation; when the water content of the rock soil increases, the pressure on the wide and thick belt of the lining in the water-bearing area increases, and the plastic deformation of the tunnel section increases, which is set as the rock soil moisture content influence weight of the tunnel deformation; the thicker the rock soil, the greater the pressure on the tunnel, the greater the pressure on the wide and thick belt of the lining in the water-bearing area, and the greater the influence of the tunnel deformation, which is set as the rock soil thickness influence weight of the tunnel deformation; the tunnel deformation is simulated and analyzed according to the single metadata to obtain the single metadata tunnel deformation analysis information; according to the single metadata tunnel deformation analysis information, the influence weight is allocated according to the proportion of the tunnel deformation size, and the proportions among the geological structure influence weight, rock soil moisture content influence weight, and rock soil thickness influence weight that affect the tunnel deformation are intelligently allocated to construct a finite element simulation tunnel deformation analysis model.

[0097] In one embodiment, the tunnel simulation scanning virtual simulation subsystem includes:

[0098] Tunnel scanning simulation platform: Based on the tunnel twin model and laser scanning feature data, a tunnel simulation scanning virtual simulation platform is built;

[0099] The simulated 3D laser scanning module performs simulated 3D laser scanning on the tunnel twin model in a virtual environment to obtain large sample detection data.

[0100] The principle and effect of the above technical solution are as follows: a tunnel simulation scanning virtual simulation subsystem, including: a tunnel scanning simulation platform, which builds a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; a simulated three-dimensional laser scanning module, which simulates three-dimensional laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data; based on the tunnel twin model and laser scanning feature data, a tunnel simulation scanning virtual simulation platform is built, including: using a physical three-dimensional laser scanning device in the tunnel to collect scanning data of the lining width and thickness of multiple sections of the water-bearing area in the tunnel; the physical three-dimensional laser scanning device is set on the initial tunnel center axis; a strain temperature-sensitive optical fiber that fits the initial tunnel center axis is set on the initial tunnel center axis to verify that the scanning baseline of the physical three-dimensional laser scanning device is consistent with the initial tunnel center axis; through the physical three-dimensional laser scanning device, data of the lining width and thickness of multiple sections of the water-bearing area in the tunnel are collected; a one-to-one correspondence between the physical three-dimensional laser scanning and the simulated three-dimensional laser scanning data of the lining width and thickness of the water-bearing area is established, and a tunnel simulation scanning virtual simulation platform is built.

[0101] In one embodiment, the tunnel point cloud registration and deformation analysis subsystem includes:

[0102] The detection data network model training module assists in training the deformation detection neural network model based on large sample detection data; the deformation detection neural network model includes the Geotransformer neural network model;

[0103] The tunnel point cloud registration module uses a neural network model to perform tunnel point cloud registration; it obtains tunnel cross-section point clouds by fitting the tunnel centerline and performs tunnel deformation analysis;

[0104] Tunnel deformation determination and inference module determines the tunnel deformation position in the tunnel cross-section point cloud and infers the tunnel deformation evolution trend;

[0105] like Figure 1 As shown in the figure, the tunnel cross-section point cloud is obtained by fitting the tunnel central axis, and the tunnel deformation analysis includes: inputting the collected tunnel cross-section data; selecting a small number of points to construct the error equation and solving it; distinguishing the in-points and out-points according to the threshold value; determining whether the number of in-points meets 90%; if the number of in-points does not meet 90%, eliminating the out-points and integrating the in-points; outputting the in-points that meet the conditions, and performing tunnel cross-section analysis based on the in-points.

[0106] The principle and effect of the above technical solution are as follows: the tunnel point cloud registration deformation analysis subsystem includes: a detection data network model training module, which assists in training the deformation detection neural network model based on large sample detection data; the deformation detection neural network model includes a Geotransformer neural network model; a tunnel point cloud registration module, which performs tunnel point cloud registration through a neural network model; obtains tunnel cross-section point clouds by fitting the tunnel central axis, and performs tunnel deformation analysis; a tunnel deformation judgment and inference module, which determines the tunnel deformation position in the tunnel cross-section point cloud and infers the tunnel deformation evolution trend; obtains tunnel cross-section point clouds by fitting the tunnel central axis, and performs tunnel deformation analysis, including: inputting collected tunnel cross-section data; selecting a small number of points to construct an error equation and solving it; dividing the points inside and outside the local area according to the threshold; determining whether the number of points inside the local area meets 90%; if the number of points inside the local area does not meet 90%, the outside points are eliminated and the points inside the local area are integrated; outputting the points inside the local area that meet the conditions, and performing tunnel cross-section analysis based on the points inside the local area;

[0107] Determining the tunnel deformation position in the tunnel cross-section point cloud and inferring the tunnel deformation evolution trend includes: obtaining multi-dimensional simulated tunnel deformation position index data through simulated three-dimensional laser scanning; comparing and verifying the multi-dimensional simulated tunnel deformation position index data with the scanning data of the lining width and thickness strips of multiple sections of the water-bearing area in the tunnel, and verifying the accuracy of the simulated three-dimensional laser scanning; when the verification error of the simulated three-dimensional laser scanning accuracy is lower than the set verification error, fitting the tunnel centerline through the multi-dimensional simulated tunnel deformation position index data to obtain the tunnel cross-section point cloud, perform tunnel deformation analysis, determine the tunnel deformation position in the tunnel cross-section point cloud, and infer the tunnel deformation evolution trend.

[0108] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the description and implementation methods. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

Claims

1. A three-dimensional laser point cloud detection method for the wide and thick strip of the lining in the water-filled area of ​​a tunnel, characterized by: include: S10, using the rolling ball method to detect the lining width and thickness of the tunnel water supply area, and using 3D laser scanning of the tunnel point cloud to collect laser point cloud data of the lining width and thickness of the tunnel water supply area; Build a high-fidelity tunnel twin model; S20, simulating tunnel deformation through finite element analysis, building a finite element simulation tunnel deformation analysis model, and outputting the true value of tunnel deformation of the tunnel twin model; S30: Build a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; Conduct simulated 3D laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data; S40, assisting in training a deformation detection neural network model based on large sample detection data; Tunnel point cloud registration through neural network model; The tunnel deformation analysis is performed by fitting the tunnel centerline to obtain the tunnel cross-section point cloud; The S10 includes: S101 uses the rolling ball method to detect the width and thickness of the lining in the water-bearing area of ​​the tunnel. Using strain and humidity sensing optical fibers, it estimates the damaged defect area and obtains humidity information in the defect area. S102, while the spherical body rolls left and right and up and down around the tunnel water supply area, the tunnel point cloud is scanned by three-dimensional laser to collect laser point cloud data of the lining width and thickness zone of the tunnel water supply area; S103: Establish a high-fidelity tunnel twin model based on the damaged defect area, humidity information of the defect area, and laser point cloud data of the lining width and thickness of the tunnel water supply area; The rolling ball method is used to detect the width and thickness of the lining in the water-filled area of ​​the tunnel, and obtain strain fiber detection information and humidity and humidity-sensitive detection information. According to the strain fiber detection information and humidity and humidity-sensitive detection information, the damaged defect area is estimated, and the humidity information of the defect area is obtained. The method includes: setting a sphere with a radius of hr, and setting a strain and humidity-sensitive optical fiber on the surface of the sphere; the sphere rolls left and right and up and down around the water-filled area of ​​the tunnel, and the area touched by the sphere is the estimated damaged defect area, and the space not touched by the sphere is the effective protection space; the strain and humidity-sensitive optical fiber includes a grating optical fiber ribbon on the surface of the sphere, a humidity-sensitive material on the surface of the sphere, and an optical fiber humidity-sensitive material. The invention also provides a humidity signal detection module; the grating optical fiber ribbon on the surface of the spherical body detects the area where the spherical body contacts according to the optical fiber strain, and obtains the optical fiber strain signal of the spherical body contacting; the humidity causes the humidity-sensitive material on the surface of the spherical body to change, and a change signal is formed according to the change of the humidity-sensitive material on the surface of the spherical body, and the change signal of the humidity-sensitive material contacting the spherical body is obtained; the optical fiber humidity signal detection module detects the optical fiber strain signal of the spherical body contacting and the change signal of the humidity-sensitive material contacting the spherical body, and obtains the strain optical fiber detection information and the humidity and humidity-sensitive detection information. According to the strain optical fiber detection information and the humidity and humidity-sensitive detection information, the damaged defective area is estimated and the humidity information of the defective area is obtained.

2. The three-dimensional laser point cloud detection method for the wide and thick strip of the lining in the water-filled area of ​​a tunnel according to claim 1 is characterized in that: The S20 includes: S201, establishing finite element simulation metadata of sampling nodes of the lining width and thickness zone in the water-bearing area, wherein the finite element simulation metadata includes the geological structure of the rock layer and soil, the moisture content of the rock layer and soil, the thickness of the rock layer and soil, and the deformation of the tunnel; S202, based on the single metadata tunnel deformation analysis information, intelligently allocating the proportions of the geological structure influence weight, the rock layer soil moisture content influence weight, and the rock layer soil thickness influence weight that affect the tunnel deformation; S203, constructing a finite element simulation tunnel deformation analysis model; outputting the tunnel deformation true value of the tunnel twin model based on the finite element simulation tunnel deformation analysis model.

3. The method for three-dimensional laser point cloud detection of wide and thick strips of lining in a tunnel water-contributing area according to claim 1 is characterized in that: The S30 includes: S301: Building a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; S302, simulate three-dimensional laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data.

4. The method for three-dimensional laser point cloud detection of wide and thick strips of lining in a tunnel water-contributing area according to claim 1 is characterized in that: S40 includes: S401, assisting in training a deformation detection neural network model based on large sample detection data; the deformation detection neural network model includes a Geotransformer neural network model; S402, performing tunnel point cloud registration using a neural network model; obtaining a tunnel cross-section point cloud by fitting the tunnel centerline, and performing tunnel deformation analysis; S403, determining the tunnel deformation position in the tunnel cross-section point cloud and inferring the tunnel deformation evolution trend; The tunnel deformation analysis is performed by fitting the tunnel centerline to obtain the tunnel cross-section point cloud, which includes the following steps: inputting the collected tunnel cross-section data; selecting a small number of points to construct and solve the error equation; distinguishing between in-points and out-points based on the threshold; determining whether the number of in-points meets 90%; if so, directly integrating the in-points; if not, eliminating the out-points and integrating the in-points; outputting the in-points that meet the conditions, and performing tunnel cross-section analysis based on the in-points.

5. A three-dimensional laser point cloud detection system for the wide and thick strip of lining in the water-filled area of ​​a tunnel, characterized by: include: The tunnel water conservancy area lining twin model subsystem uses the rolling ball method to detect the width and thickness of the tunnel water conservancy area lining. It also uses 3D laser scanning of the tunnel point cloud to collect laser point cloud data of the width and thickness of the tunnel water conservancy area lining. This allows the establishment of a high-fidelity tunnel twin model. The finite element simulation tunnel deformation subsystem simulates tunnel deformation through finite element analysis, builds a finite element simulation tunnel deformation analysis model, and outputs the true value of tunnel deformation of the tunnel twin model; The tunnel simulation scanning virtual simulation subsystem builds a tunnel simulation scanning virtual simulation platform based on the tunnel twin model and laser scanning feature data; simulates 3D laser scanning of the tunnel twin model in a virtual environment to obtain large sample detection data; The tunnel point cloud registration and deformation analysis subsystem assists in training the deformation detection neural network model based on large sample detection data; tunnel point cloud registration is performed through the neural network model; The tunnel deformation analysis is performed by fitting the tunnel centerline to obtain the tunnel cross-section point cloud; The tunnel water supply area lining twin model subsystem includes: The rolling ball method tunnel defect detection module uses the rolling ball method to detect the width and thickness of the lining in the tunnel water supply area. Through the strain and humidity sensing optical fiber, it estimates the damaged defect area and obtains humidity information in the defect area. The 3D laser scanning tunnel point cloud module collects laser point cloud data of the wide and thick strips of the tunnel water supply area through 3D laser scanning of the tunnel point cloud as the sphere rolls left and right and up and down around the tunnel water supply area. A high-fidelity tunnel twin model architecture module builds a high-fidelity tunnel twin model based on damaged defect areas, moisture information in defect areas, and laser point cloud data of the lining width and thickness in the tunnel water-filled area. The rolling ball method is used to detect the width and thickness of the lining in the water-filled area of ​​the tunnel, and obtain strain fiber detection information and humidity and humidity-sensitive detection information. According to the strain fiber detection information and humidity and humidity-sensitive detection information, the damaged defect area is estimated, and the humidity information of the defect area is obtained. The method includes: setting a sphere with a radius of hr, and setting a strain and humidity-sensitive optical fiber on the surface of the sphere; the sphere rolls left and right and up and down around the water-filled area of ​​the tunnel, and the area touched by the sphere is the estimated damaged defect area, and the space not touched by the sphere is the effective protection space; the strain and humidity-sensitive optical fiber includes a grating optical fiber ribbon on the surface of the sphere, a humidity-sensitive material on the surface of the sphere, and an optical fiber humidity-sensitive material. The invention also provides a humidity signal detection module; the grating optical fiber ribbon on the surface of the spherical body detects the area where the spherical body contacts according to the optical fiber strain, and obtains the optical fiber strain signal of the spherical body contacting; the humidity causes the humidity-sensitive material on the surface of the spherical body to change, and a change signal is formed according to the change of the humidity-sensitive material on the surface of the spherical body, and the change signal of the humidity-sensitive material contacting the spherical body is obtained; the optical fiber humidity signal detection module detects the optical fiber strain signal of the spherical body contacting and the change signal of the humidity-sensitive material contacting the spherical body, and obtains the strain optical fiber detection information and the humidity and humidity-sensitive detection information. According to the strain optical fiber detection information and the humidity and humidity-sensitive detection information, the damaged defective area is estimated and the humidity information of the defective area is obtained.

6. The three-dimensional laser point cloud detection system for thick and wide strips of lining in a tunnel water-filled area according to claim 5 is characterized in that: Finite element simulation tunnel deformation subsystem includes: The finite element simulation module for the lining of the water-bearing area establishes finite element simulation metadata for sampling nodes of the lining width and thickness in the water-bearing area. The finite element simulation metadata includes the geological structure of the rock layer and soil, the moisture content of the rock layer and soil, the thickness of the rock layer and soil, and the deformation of the tunnel. The intelligent tunnel deformation weight allocation module intelligently allocates the weights of geological structure, rock layer soil moisture content, and rock layer soil thickness that affect tunnel deformation based on the single metadata tunnel deformation analysis information. The tunnel deformation analysis model module is used to construct a finite element simulation tunnel deformation analysis model; based on the finite element simulation tunnel deformation analysis model, the true value of the tunnel deformation of the tunnel twin model is output.

7. The three-dimensional laser point cloud detection system for thick and wide strips of lining in a tunnel water supply area according to claim 5 is characterized in that: Tunnel simulation scanning virtual simulation subsystem includes: Tunnel scanning simulation platform: Based on the tunnel twin model and laser scanning feature data, a tunnel simulation scanning virtual simulation platform is built; The simulated 3D laser scanning module performs simulated 3D laser scanning on the tunnel twin model in a virtual environment to obtain large sample detection data.

8. The three-dimensional laser point cloud detection system for thick and wide strips of lining in a tunnel water-filled area according to claim 5 is characterized in that: Tunnel point cloud registration deformation analysis subsystem includes: The detection data network model training module assists in training the deformation detection neural network model based on large sample detection data; the deformation detection neural network model includes the Geotransformer neural network model; The tunnel point cloud registration module uses a neural network model to perform tunnel point cloud registration; it obtains tunnel cross-section point clouds by fitting the tunnel centerline and performs tunnel deformation analysis; Tunnel deformation determination and inference module determines the tunnel deformation position in the tunnel cross-section point cloud and infers the tunnel deformation evolution trend; The tunnel deformation analysis is performed by fitting the tunnel centerline to obtain the tunnel cross-section point cloud, which includes the following steps: inputting the collected tunnel cross-section data; selecting a small number of points to construct and solve the error equation; distinguishing between in-points and out-points based on the threshold; determining whether the number of in-points meets 90%; if so, directly integrating the in-points; if not, eliminating the out-points and integrating the in-points; outputting the in-points that meet the conditions, and performing tunnel cross-section analysis based on the in-points.

Images