A method for non-excavation repair of pipelines by combining a robot with ultraviolet light curing

Abstract

The present invention relates to a method for non-excavation repair of pipelines by combining with a robot using ultraviolet light curing, comprising the following steps: S1: Use a detection robot to enter the pipeline and collect point cloud, high-definition image, and thermal imaging data; S2: Construct a three-dimensional grid model to completely restore the internal geometric shape and defect distribution state of the pipeline, and label the defect areas in the model; S3: According to the type and location of the defect areas, obtain repair task strategies, including the division of repair segments and ultraviolet light curing parameters; S4: Input the repair task strategies into the three-dimensional grid model for virtual repair simulation, and obtain the final repair plan after optimizing the parameters; S5: Based on the final repair plan, perform repair based on a repair robot, and detect the repair status in real time through a camera. The present invention effectively improves the accuracy and efficiency of non-excavation repair of pipelines.

Description

Technical Field

[0001] The present invention relates to the field of trenchless pipeline repair, and particularly to a method for trenchless repair of pipeline ultraviolet light curing combined with a robot. Background Art

[0002] With the acceleration of the urbanization process, as an important part of urban infrastructure, the maintenance and repair of underground pipe networks have become increasingly important. However, traditional pipeline repair methods usually require large-scale excavation, with a long construction period, high costs, and are prone to having negative impacts on traffic, the environment, and surrounding facilities. Therefore, trenchless pipeline repair technologies have been widely applied in recent years. Among them, the ultraviolet light curing repair technology (UV-CIPP, Ultraviolet Cured-in-Place Pipe) has become one of the mainstream technologies in the trenchless repair field due to its high efficiency, environmental friendliness, and low interference characteristics.

[0003] Ultraviolet light curing repair uses special resin materials and is irradiated by ultraviolet light carried by a robot, enabling the materials to quickly cure inside the pipeline, forming a new lining structure to restore or enhance the pipeline strength. This method avoids cumbersome excavation and replacement processes, greatly reducing the impact of construction on the environment. However, the internal defects of pipelines are complex and diverse, such as cracks, corrosion, perforation, and blockages, etc. They are widely distributed and have large characteristic differences. Therefore, traditional repair methods still face many challenges in accurately repairing the target area, optimizing the repair efficiency, and ensuring the repair quality. Summary of the Invention

[0004] In order to solve the above problems, the purpose of the present invention is to provide a method for trenchless repair of pipeline ultraviolet light curing combined with a robot, effectively improving the accuracy and efficiency of trenchless pipeline repair.

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

[0006] A method for trenchless repair of pipeline ultraviolet light curing combined with a robot, comprising the following steps:

[0007] S1: Use a detection robot to enter the pipeline, perform three-dimensional laser scanning, panoramic shooting, and thermal imaging monitoring on it, and collect point cloud, high-definition image, and thermal imaging data;

[0008] S2: Based on the collected point cloud, high-definition image, and thermal imaging, construct a three-dimensional grid model to completely restore the internal geometric shape and defect distribution state of the pipeline, and label the defect areas in the model;

[0009] S3: According to the type and location of the defect area, obtain a repair task strategy, including the division of repair segments and ultraviolet light curing parameters;

[0010] S4: Input the repair task strategy into the three-dimensional grid model for virtual repair simulation, and obtain the final repair plan after optimizing the parameters;

[0011] S5: Based on the final repair plan, perform the repair using a repair robot, and detect the repair status in real time through a camera.

[0012] Further, the specific content of S1 is:

[0013] The inspection robot moves uniformly along the inner wall of the pipeline and performs real-time positioning:

[0014] ;

[0015] Among them, is the position of the robot at time t; is the position of the robot at time t - 1; is the displacement between two points; is the rotation matrix provided by the attitude sensor;

[0016] The laser scanner collects the point cloud on the surface of the pipeline at a data density of S points per second, and the laser ranging of the i-th point L i is converted into the point (x i , y i , z i ) ;

[0017] ;

[0018] Among them, Z is the step length of the robot moving along the axis of the pipeline, θ i is the relative rotation angle, and finally a complete three-dimensional point cloud file P(x, y, z) is generated;

[0019] The panoramic camera takes a picture every step of Δd, and the image data forms an unfoldable panoramic inner wall map through a stitching algorithm. The relative position is determined by the following formula:

[0020] ;

[0021] Among them, is the i-th picture;

[0022] The thermal imaging sensor scans the infrared temperature data on the inner wall of the pipeline and records the temperature distribution matrix T.

[0023] Further, the specific content of S2 is:

[0024] Preprocess the obtained point cloud, high-definition image, and thermal imaging data;

[0025] Based on the preprocessed point cloud data, a three-dimensional grid model of the pipeline surface is constructed using the triangular mesh reconstruction method;

[0026] Identify the defect area and extract features through point cloud analysis, high-definition image edge detection, and thermal imaging temperature difference analysis; Based on the extracted features, judge the risk level;

[0027] Map the defect texture and temperature difference data to the surface of the three-dimensional grid model, and label the defect location and category on the surface of the three-dimensional grid model;

[0028] Establish a pipeline axis reference to unify the coordinates of the point cloud, high-definition image, and thermal imaging map.

[0029] Furthermore, the preprocessing is specifically as follows:

[0030] The point cloud data uses statistical filtering to remove isolated noise points:

[0031] ;

[0032] Among them, D(p i ) is the density reference value of point p i , k is the standard deviation ratio; P filtered is the point cloud set retained after statistical filtering; mean(D) is the mean value of all density reference values D(p i ); is the standard deviation of all density reference values D(p i );

[0033] Use the ICP algorithm to register the segmented point cloud to obtain the complete three-dimensional information of the pipeline:

[0034] ;

[0035] Among them, T is the registration transformation matrix, R is the rotation matrix, is the offset vector, p i and q i are the corresponding points in the two point cloud sets;

[0036] Use the feature point matching algorithm to splice the original single-frame images for the high-definition image data, enhance the contrast, filter out the noise, fuse the high-definition image data into the three-dimensional grid model, and generate a three-dimensional grid model with surface texture through texture mapping corresponding to each point of the point cloud;

[0037] According to the thermal imaging data, extract the temperature distribution matrix and match the surface information of the point cloud through interpolation.

[0038] Further, through point cloud analysis, high-definition image edge detection, and thermal imaging temperature difference analysis, identify the defect area and extract features; based on the extracted features, judge the risk level, specifically as follows:

[0039] Utilize the geometric mutation on the point cloud surface and the texture edge detection of the image to identify the crack area and obtain the crack length L crack and the crack depth D crack :

[0040] Utilize the matching of the curvature depression of the point cloud data and the high-temperature area of the thermal imaging to identify corrosion and obtain the corrosion depth D corrosion and the corrosion area A;

[0041] Superimpose the abnormal thermal imaging temperature difference onto the point cloud surface, calculate the area and the central position corresponding to the high-temperature area, and map the thermal distribution onto the surface of the three-dimensional grid model;

[0042] According to the obtained abnormal features, calculate the risk score P through a weighted model:

[0043] ;

[0044] where w1, w2, w3, w4, w5 are defect risk contribution coefficients obtained through machine learning training; L crack is the crack length; D crack is the crack depth, and ΔT represents the temperature difference.

[0045] Further, the utilization of the geometric mutation on the point cloud surface and the texture edge detection of the image to identify the crack area and obtain the crack length L crack and the crack depth D crack , specifically as follows:

[0046] Locate the crack by combining the geometric mutation characteristics of the point cloud and the edge information of the cloud surface texture, and calculate the principal curvature of the point cloud:

[0047] K = k1 + k2;

[0048] where k1 and k2 are the two principal curvatures of the local surface of the point cloud, and K represents the degree of local surface mutation;

[0049] If the curvature K > K threshold , mark it as a possible crack area, where K threshold is a preset threshold;

[0050] Calculate the change gradient ΔN of the normal vector N in the point neighborhood:

[0051] ;

[0052] where Na and N b are the normal vectors of adjacent points; if ΔN > ΔN threshold , it is marked as a geometric mutation point, where ΔN threshold is a preset threshold;

[0053] Use the Canny operator to detect the crack edge and obtain the binary crack edge image E(x, y); obtain the skeleton S(x, y) through the thinning method;

[0054] Overlay the high-definition image edge onto the point cloud and match the point cloud and the image through coordinate registration:

[0055] ;

[0056] where, are the three-dimensional coordinates of the point cloud; (u, v) are the image texture coordinates; I(u, v) is the pixel value corresponding to the image texture coordinates (u, v); is the inverse mapping function from the image texture coordinates to the three-dimensional coordinates of the point cloud;

[0057] Accumulate the distances along the crack edge skeleton points to obtain the crack length L crack ; calculate the difference between the crack bottom point and the fitted smooth surface to obtain the crack depth D crack .

[0058] Furthermore, the corrosion is identified by matching the curvature depression of the point cloud data with the high-temperature area of the thermal imaging, and the corrosion depth D corrosion and the corrosion area A are obtained as follows:

[0059] Identify the corrosion by matching the curvature depression of the point cloud data with the high-temperature area of the thermal imaging, fit a smooth surface through the least squares method, and calculate the local surface height deviation of the point cloud:

[0060] ;

[0061] where, z actual is the height of the actual point of the point cloud; z smooth is the height value of the fitted smooth surface; if D corrosion > D threshold , it is defined as the corrosion depression, D threshold is a preset threshold;

[0062] Extract the high-temperature area from the thermal imaging temperature difference matrix, match the high-temperature area with the point cloud depression area, identify the corrosion depression points, and the local surface height deviation of the point cloud corresponding to the corrosion depression points is the corrosion depth D corrosion of the corrosion depression points, and calculate the corrosion area A.

[0063] Further, the S3 is specifically as follows:

[0064] Automatically divide the repair segments according to the type, distribution, and location characteristics of the defects, and determine whether overall repair or local repair is required;

[0065] According to the length L crack 、depth D crack of the crack and the position, calculate the distribution density ρ crack ; If , it is divided into the overall repair segment, where is the preset threshold of the distribution density; If ρ crack <ρ threshold , it is divided into the local repair segment;

[0066] According to the corrosion area A and the corrosion depth D corrosion , calculate the corrosion ratio , where is the pipeline area; If , it is divided into the overall repair segment, where is the preset threshold of the corrosion ratio, if , it is divided into the local repair segment;

[0067] For the local repair segment, calculate the starting position and length of the repair segment;

[0068] For the crack, the repair segment length L segment is:

[0069] ;

[0070] Among them, is the buffer repair length at both ends of the crack;

[0071] For the corrosion, the repair segment length L segment is: ;

[0072] Formulate the curing parameters according to the defect characteristics, including the light power, irradiation time, and curing speed;

[0073] The light power P UV is proportional to the crack depth D crack :

[0074] ;

[0075] Among them, g1 is the influence coefficient of the crack depth on the light power, and g2 is the base power;

[0076] If , the power needs to be increased:

[0077] ;

[0078] The optical power is proportional to the corrosion depth D corrosion and the corrosion area A:

[0079] ;

[0080] where k3 and k4 are influence coefficients;

[0081] The irradiation time T UV is determined by the repair section length L segment and the curing speed v cure :

[0082] ;

[0083] Adjust the curing speed according to the defect depth and distribution density:

[0084] ;

[0085] where is the basic curing speed, is the influence coefficient of crack density on the curing speed; is the influence coefficient of corrosion depth on the curing speed;

[0086] According to the risk score P and the defect location, prioritize the repair of high-risk sections.

[0087] Furthermore, the specific steps of S4 are as follows:

[0088] Input the repair task strategy generated by AI into the digital twin environment;

[0089] Simulate the repair process in the three-dimensional grid model and evaluate the repair effect;

[0090] According to the simulation results, combined with the target repair effect and the constraints of consumables / energy consumption, further optimize the repair parameters and output the final optimized repair plan: obtain the optimal repair section division, light curing parameters, and repair priority.

[0091] Furthermore, the specific steps of S5 are as follows:

[0092] According to the optimized repair plan, control the repair robot to complete the repair tasks of cracks, corrosion, or blockages, including ultraviolet light curing repair and resin filling operations;

[0093] Through the high-definition camera and depth sensor carried by the repair robot, collect the execution status of the repair task in real time;

[0094] According to the detection results during the repair process, the repair parameters are dynamically adjusted to ensure the best repair effect.

[0095] The present invention has the following beneficial effects:

[0096] 1. The present invention uses laser scanning, high-definition images, and thermal imaging to achieve a comprehensive perception of the inside of the pipeline, constructs a digital twin model, completely restores the three-dimensional geometric structure and defect distribution inside the pipeline, organically combines the data of point clouds, high-definition images, and thermal imaging, improves the accuracy of defect location and quantification, conducts risk assessment based on defect characteristics, and realizes an intuitive presentation through 3D visualization;

[0097] 2. According to the defect type (crack / corrosion / clogging) and distribution state, the present invention intelligently plans the local repair or overall repair section, avoids blind repair, improves the repair efficiency, and dynamically adjusts the ultraviolet light power, curing time, and speed according to the defect characteristics (depth, area, etc.) to ensure the maximization of the curing effect and strength of the material;

[0098] 3. Before actual repair, the present invention simulates the ultraviolet light curing process, optimizes the repair parameters relying on physical models and simulation algorithms, can automatically divide the repair section according to defect characteristics and formulate targeted ultraviolet light curing repair parameters, and at the same time optimize the dosage of repair materials and the repair sequence, so as to achieve efficient and precise pipeline repair. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0100] The following further describes the present invention in detail with reference to the drawings and specific embodiments:

[0101] Reference Figure 1 , in this embodiment, a method for non-excavation repair of pipeline ultraviolet light curing in combination with a robot is provided, including the following steps:

[0102] S1: Use a detection robot to enter the pipeline, conduct three-dimensional laser scanning, panoramic shooting, and thermal imaging monitoring on it, and collect point cloud, high-definition image, and thermal imaging data;

[0103] S2: Based on the collected point cloud, high-definition image, and thermal imaging, construct a three-dimensional grid model, completely restore the internal geometric shape and defect distribution state of the pipeline, and label the defect areas in the model (such as high-risk points, crack distribution areas);

[0104] S3: According to the type and location of the defect area, obtain the repair task strategy, including the division of the repair section (overall repair or local repair) and the ultraviolet light curing parameters (light power, irradiation time);

[0105] S4: Input the repair task strategy into the three-dimensional grid model for virtual repair simulation, and obtain the final repair plan after optimizing the parameters;

[0106] S5: Based on the final repair plan, perform the repair using a repair robot, and detect the repair status in real time through a camera.

[0107] In this embodiment, S1 is specifically:

[0108] The inspection robot moves uniformly along the inner wall of the pipeline and performs real-time positioning:

[0109] ;

[0110] Among them, is the position of the robot at time t; is the position of the robot at time t-1; is the displacement between two points; is the rotation matrix provided by the attitude sensor;

[0111] The laser scanner collects the point cloud on the surface of the pipeline at a data density of S points per second, and the laser ranging of the i-th point L i is converted into the point (x i , y i , z i ) ;

[0112] ;

[0113] Among them, Z is the step length of the robot moving along the axis of the pipeline, θ i is the relative rotation angle, and finally a complete three-dimensional point cloud file P(x,y,z) is generated;

[0114] The panoramic camera takes a picture every step of Δd, and the image data forms an unfoldable panoramic inner wall map through a stitching algorithm. The relative position is determined by the following formula:

[0115] ;

[0116] Among them, is the i-th picture;

[0117] The thermal imaging sensor scans the infrared temperature data on the inner wall of the pipeline and records the temperature distribution matrix T.

[0118] In this embodiment, S2 is specifically:

[0119] Preprocess the acquired point cloud, high-definition image, and thermal imaging data;

[0120] Based on the preprocessed point cloud data, use the triangular mesh reconstruction method (such as Delaunay triangulation) to construct a three-dimensional mesh model of the pipeline surface;

[0121] Identify the defect area and extract features through point cloud analysis, high-definition image edge detection, and thermal imaging temperature difference analysis; based on the extracted features, judge the risk level;

[0122] Map the defect textures (cracks, corrosion, etc.) and temperature difference data to the surface of the three-dimensional mesh model, and label the defect positions and categories on the surface of the three-dimensional mesh model:

[0123] Establish a pipeline axis reference to unify the coordinates of the point cloud, high-definition image, and thermal imaging.

[0124] In this embodiment, the preprocessing is as follows:

[0125] Use statistical filtering to remove isolated noise points from the point cloud data:

[0126] ;

[0127] Among them, D(p i ) is the density reference value of point p i , k is the standard deviation ratio; P filtered is the set of point clouds retained after statistical filtering; mean(D) is the mean value of all density reference values D(p i ); is the standard deviation of all density reference values D(p i );

[0128] Use the ICP algorithm to register the segmented point clouds to obtain the complete three-dimensional information of the pipeline:

[0129] ;

[0130] Among them, T is the registration transformation matrix, R is the rotation matrix, is the offset vector, p i and q i are the corresponding points in the two point cloud sets;

[0131] Use the feature point matching algorithm (such as SIFT) to splice the original single-frame images for the high-definition image data, enhance the contrast, filter out the noise, fuse the high-definition image data into the three-dimensional mesh model, and generate a three-dimensional mesh model with surface texture through texture mapping corresponding to each point of the point cloud;

[0132] Extract the temperature distribution matrix according to the thermal imaging data, and match the surface information of the point cloud through interpolation.

[0133] In this embodiment, through point cloud analysis, high-definition image edge detection, and thermal imaging temperature difference analysis, the defect area is identified and features are extracted; based on the extracted features, the risk level is judged, specifically as follows:

[0134] Utilize the geometric mutation on the point cloud surface and the texture edge detection of the image to identify the crack area and obtain the crack length L crack and the crack depth D crack :

[0135] Utilize the curvature depression of the point cloud data and the matching of the high-temperature area in the thermal imaging to identify corrosion and obtain the corrosion depth D corrosion and the corrosion area A;

[0136] Superimpose the abnormal thermal imaging temperature difference on the point cloud surface, calculate the area and the center position corresponding to the high-temperature area, and map the heat distribution to the surface of the three-dimensional grid model;

[0137] According to the obtained abnormal features, calculate the risk score P through the weighted model:

[0138] ;

[0139] where w1, w2, w3, w4, w5 are defect risk contribution coefficients obtained through machine learning training; L crack is the crack length; D crack is the crack depth, and ΔT represents the temperature difference.

[0140] In this embodiment, utilize the geometric mutation on the point cloud surface and the texture edge detection of the image to identify the crack area and obtain the crack length L crack and the crack depth D crack , specifically as follows:

[0141] Locate the crack by combining the geometric mutation characteristics of the point cloud and the edge information of the cloud surface texture, and calculate the principal curvature of the point cloud:

[0142] K = k1 + k2;

[0143] where k1 and k2 are the two principal curvatures of the local surface of the point cloud, and K represents the degree of local surface mutation;

[0144] If the curvature K > K threshold , mark it as a possible crack area, where K threshold is a preset threshold;

[0145] Calculate the change gradient ΔN of the normal vector N in the point neighborhood:

[0146] ;

[0147] where N a and N b are the normal vectors of adjacent points; if ΔN > ΔN threshold , it is marked as a geometric mutation point, where ΔN threshold is a preset threshold;

[0148] Use the Canny operator to detect the crack edge to obtain the binary crack edge image E(x, y); obtain the skeleton S(x, y) through the thinning method;

[0149] Overlay the high-definition image edge onto the point cloud and match the point cloud and the image through coordinate registration:

[0150] ;

[0151] where, is the three-dimensional coordinate of the point cloud; (u, v) is the image texture coordinate; I(u, v) is the pixel value corresponding to the image texture coordinate (u, v); is the inverse mapping function from the image texture coordinate to the three-dimensional coordinate of the point cloud;

[0152] Accumulate the distances along the skeleton points of the crack edge to obtain the crack length L crack ; calculate the difference between the bottom point of the crack and the fitted smooth surface to obtain the crack depth D crack .

[0153] In this embodiment, the corrosion is identified by matching the curvature depression of the point cloud data with the high-temperature region of the thermal imaging, and the corrosion depth D corrosion and the corrosion area A are obtained as follows:

[0154] Identify the corrosion by matching the curvature depression of the point cloud data with the high-temperature region of the thermal imaging, fit a smooth surface by the least square method, and calculate the local surface height deviation of the point cloud:

[0155] ;

[0156] where, z actual is the height of the actual point of the point cloud; z smooth is the height value of the fitted smooth surface; if D corrosion > D threshold , it is defined as a corrosion depression, D threshold is a preset threshold;

[0157] Extract the high-temperature region from the thermal imaging temperature difference matrix, match the high-temperature region with the point cloud depression region, identify the corrosion depression points, and the local surface height deviation of the point cloud corresponding to the corrosion depression points is the corrosion depth D of the corrosion depression points. corrosion , and calculate the corrosion area A.

[0158] In this embodiment, S3 is specifically as follows:

[0159] Automatically divide the repair segments according to the type, distribution, and location characteristics of the defects, and determine whether overall repair or local repair is required;

[0160] According to the length L of the crack crack , depth D crack and the position, calculate the distribution density ρ crack ; if , it is divided into the overall repair segment, where is the preset threshold of the distribution density; if ρ crack <ρ threshold , it is divided into the local repair segment;

[0161] According to the corrosion area A and the corrosion depth D corrosion , calculate the corrosion ratio , where is the pipeline area; if , then it is divided into the overall repair segment, where is the preset threshold of the corrosion ratio, if , then it is divided into the local repair segment;

[0162] For the local repair segment, calculate the starting position and length of the repair segment;

[0163] For the crack, the repair segment length L segment is:

[0164] ;

[0165] where is the buffer repair length at both ends of the crack;

[0166] For the corrosion, the repair segment length L segment is: ;

[0167] Formulate the curing parameters according to the defect characteristics, including the light power, irradiation time, and curing speed;

[0168] The light power P UV is proportional to the crack depth D crack :

[0169] ;

[0170] Among them, g1 is the influence coefficient of crack depth on optical power, and g2 is the base power;

[0171] If , the power needs to be increased:

[0172] ;

[0173] The optical power is proportional to the corrosion depth D corrosion and the corrosion area A:

[0174] ;

[0175] Among them, k3 and k4 are influence coefficients;

[0176] The irradiation time T UV is determined by the length L of the repair section segment and the curing speed v cure :

[0177] ;

[0178] Adjust the curing speed according to the defect depth and distribution density:

[0179] ;

[0180] Among them, is the base curing speed, is the influence coefficient of crack density on the curing speed; is the influence coefficient of corrosion depth on the curing speed;

[0181] Prioritize the repair of high-risk sections according to the risk score P and the defect location.

[0182] In this embodiment, S4 is specifically as follows:

[0183] Input the repair task strategy (repair section division, UV curing parameters, etc.) generated by AI into the digital twin environment;

[0184] Simulate the repair process in the three-dimensional grid model and evaluate the repair effect (such as crack filling degree, corrosion coverage rate, curing time, etc.);

[0185] According to the simulation results, combined with the target repair effect and the constraints of consumables / energy consumption, further optimize the repair parameters and output the final optimized repair plan: Obtain the optimal repair section division, light curing parameters, and repair priority.

[0186] In this embodiment, S5 is specifically as follows:

[0187] According to the optimized repair plan, control the repair robot to complete the repair tasks for cracks, corrosion, or blockages, including ultraviolet curing repair and resin filling operations;

[0188] Through the high-definition camera, depth sensor, etc. carried by the repair robot, collect the execution status of the repair task in real time (such as whether the crack is completely filled, the curing quality of the material, the coverage rate of the repair area, etc.);

[0189] According to the detection results during the repair process, dynamically adjust the repair parameters to ensure the best repair effect.

[0190] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0191] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0192] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the specified functions in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0193] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide means for implementing the specified functions in one Figure 1 one flow or multiple flows and / or blocksFigure 1 Steps of the functions specified in one or more boxes.

[0194] As described above, it is only the preferred embodiment of the present invention, and it is not a limitation to the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes. However, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for non-excavation repair of pipelines by UV curing combined with a robot, characterized in that: The following steps are involved: S1: Use the inspection robot to enter the pipeline, perform 3D laser scanning, panoramic photography and thermal imaging monitoring, and collect point cloud, high-definition image and thermal imaging data; S2: Based on the collected point cloud, high-definition images, and thermal images, a three-dimensional mesh model is constructed to completely restore the internal geometry and defect distribution of the pipeline, and the defect areas in the model are marked; S3: According to the defect area type and location, the repair task strategy is obtained, including the division of repair sections and UV curing parameters; S4: Input the repair task strategy into the three-dimensional grid model to perform virtual repair simulation, and obtain the final repair plan after optimizing the parameters; S5: Based on the final repair plan, the repair robot performs repairs and the camera detects the repair status in real time; The S3 is specifically as follows: Automatically divide the repair sections according to the defect type, distribution and location characteristics to determine whether overall repair or partial repair is required; According to the length of the crack L crack , depth D crack And the position calculation distribution density ρ crack ;like , divided into overall repair sections, where The preset threshold of distribution density; if ρ crack <ρ threshold , divided into local repair segments; According to the corrosion area A and corrosion depth D corrosion , calculate the corrosion ratio ,in is the pipe area; if , it is divided into the overall repair section, in which, Preset threshold for corrosion ratio, if , it is divided into local repair segments; For a local repair segment, calculate the starting position and length of the repair segment; For cracks, repair section length L segment for: ； in, The buffer repair length at both ends of the crack; For corrosion, repair section length L segment for: ; Formulate curing parameters according to defect characteristics, including light power, irradiation time and curing speed; Optical power P UV and crack depth D crack Proportional to: ； Among them, g1 is the influence coefficient of crack depth on optical power, and g2 is the basic power; like , need to increase power: ； Optical power and corrosion depth D corrosion Proportional to the corrosion area A: ； Among them, k3 and k4 influence coefficients; Irradiation time T UV By repairing the segment length L segment and curing speed v cure Decide: ； Adjust the curing speed according to the defect depth and distribution density: ； in, For the basic curing speed, is the influence coefficient of crack density on solidification speed; is the influence coefficient of corrosion depth on solidification speed; Based on the risk score P and defect location, high-risk segments are repaired first.

2. The method for performing UV-curing trenchless repair of pipelines in combination with a robot according to claim 1, characterized in that: The S1 is specifically: The detection robot moves at a constant speed along the inner wall of the pipeline and performs real-time positioning: ； in, is the robot position at time t; For time The robot position; is the displacement between two points; The rotation matrix provided for the attitude sensor; The laser scanner collects point clouds on the pipeline surface at a data density of S points per second, and the laser ranges the i-th point L i Convert to point cloud midpoint (x i , y i , z i ) ; ； Where Z is the step length of the robot moving along the pipeline axis, θ i is the relative rotation angle, and finally a complete three-dimensional point cloud file P (x, y, z) is generated; The panoramic camera takes a picture once per step Δd, and the image data is stitched together to form an expandable panoramic inner wall map. The relative position is determined by the following formula: ； in, is the i-th picture; The thermal imaging sensor scans the infrared temperature data of the inner wall of the pipeline and records the temperature distribution matrix T.

3. The method for performing UV-curing trenchless repair of pipelines in combination with a robot according to claim 2, characterized in that: The S2 is specifically: Pre-process the acquired point cloud, high-definition image, and thermal imaging data; Based on the preprocessed point cloud data, a three-dimensional mesh model of the pipeline surface is constructed using a triangular mesh reconstruction method; Identify defect areas and extract features through point cloud analysis, HD image edge detection, and thermal imaging temperature difference analysis; Based on the extracted features, determine the risk level; Mapping defect texture and temperature difference data to the surface of the 3D mesh model, and marking the defect position and category on the surface of the 3D mesh model; Establish pipeline axis reference and unify coordinates of point clouds, high-definition images and thermal images.

4. The method for performing UV-curing trenchless repair of pipelines in combination with a robot according to claim 3 is characterized in that: The preprocessing is specifically as follows: Point cloud data uses statistical filtering to remove isolated noise points: ； in, D(p i ) For point p i The density reference value, k is the standard deviation ratio; P filtered is the point cloud set retained after statistical filtering; mean(D) is the density reference value D(p i )’s mean; is the density reference value D(p i )’s standard deviation; Use the ICP algorithm to register the segmented point clouds and obtain complete three-dimensional information of the pipeline: ; Among them, T is the registration transformation matrix, R is the rotation matrix, is the offset vector, p i and q i Concentrate corresponding points on two point clouds; The high-definition image data is stitched together using a feature point matching algorithm to enhance contrast, filter out noise, fuse the high-definition image data into a three-dimensional mesh model, and generate a three-dimensional mesh model with surface texture through texture mapping corresponding to each point in the point cloud; Based on the thermal imaging data, the temperature distribution matrix is ​​extracted and the surface information of the point cloud is matched by interpolation.

5. The method for performing UV-curing trenchless repair of pipelines in combination with a robot according to claim 3 is characterized in that: The point cloud analysis, high-definition image edge detection, and thermal imaging temperature difference analysis are used to identify defect areas and extract features; based on the extracted features, the risk level is determined as follows: Using the geometric mutation of the point cloud surface and the texture edge detection of the image, the crack area is identified and the crack length L is obtained. crack and crack depth D crack : Corrosion is identified by matching the curvature depression of point cloud data with the high temperature area of ​​thermal imaging, and the corrosion depth is obtained. D corrosion and corrosion area A; The thermal imaging temperature difference is superimposed on the point cloud surface, the area and center position of the high temperature area are calculated, and the heat distribution is mapped to the surface of the three-dimensional grid model; According to the acquired abnormal features, the risk score P is calculated by the weighted model: ； Among them, w1, w2, w3, w4, w5 are defect risk contribution coefficients obtained through machine learning training; L crack is the crack length; D crack is the crack depth, and ΔT represents the temperature difference.

6. The method for performing UV-curing trenchless repair of pipelines in combination with a robot according to claim 5, characterized in that: The method uses the geometric mutation of the point cloud surface and the texture edge detection of the image to identify the crack area and obtain the crack length L crack and crack depth D crack , as follows: By combining the geometric mutation characteristics of the point cloud and the edge information of the cloud surface texture, the cracks are located and the principal curvature of the point cloud is calculated: K=k1+k2; Among them, k1 and k2 are the two principal curvatures of the local surface of the point cloud, and K represents the degree of mutation of the local surface; If the curvature K>K threshold , marked as possible crack areas, where K threshold is the preset threshold; Calculate the change gradient ΔN of the normal vector N in the point neighborhood: ； Among them, N a and N b is the normal vector of the adjacent point; if ΔN>ΔN threshold , marked as the geometric mutation point, where ΔN threshold is the preset threshold; The Canny operator is used to detect the crack edge and obtain the crack edge binary image E(x,y); the skeleton S(x,y) is obtained by thinning method; Overlay the edge of the HD image onto the point cloud and match the point cloud and image by coordinate registration: ； in, is the three-dimensional coordinate of the point cloud; (u, v) is the image texture coordinate; I(u, v) is the pixel value corresponding to the image texture coordinate (u, v); It is the inverse mapping function from image texture coordinates to point cloud three-dimensional coordinates; Accumulate the distance along the skeleton points of the crack edge to obtain the crack length L crack ; Calculate the difference between the bottom point of the crack and the fitted smooth surface to obtain the crack depth D crack .

7. The method for performing UV-curing trenchless repair of pipelines in combination with a robot according to claim 5, characterized in that: The method uses the curvature concave of the point cloud data to match the high temperature area of ​​the thermal imaging to identify corrosion and obtain the corrosion depth D corrosion And the corrosion area A, as follows: Corrosion is identified by matching the curvature concavity of the point cloud data with the high temperature area of ​​the thermal imaging, the smooth surface is fitted by the least squares method, and the local surface height deviation of the point cloud is calculated: ； Among them, z actual is the height of the actual point in the point cloud; z smooth is the height value of the fitted smooth surface; if , defined as the corrosion pit, D threshold is the preset threshold; The high temperature area is extracted from the thermal imaging temperature difference matrix, and the high temperature area is matched with the concave area of ​​the point cloud to identify the corrosion concave point. The local surface height deviation of the point cloud corresponding to the corrosion concave point is the corrosion depth D of the corrosion concave point. corrosion , and calculate the corrosion area A.

8. The method for performing UV-curing trenchless repair of pipelines in combination with a robot according to claim 1, characterized in that: The S4 is specifically as follows: Input the AI-generated repair task strategy into the digital twin environment; Simulate the repair process in a 3D mesh model and evaluate the repair effect; According to the simulation results, combined with the target repair effect and the constraints of consumables / energy consumption, the repair parameters are further optimized and the final optimized repair plan is output: the optimal repair segment division, light curing parameters and repair priority are obtained.

9. The method for performing UV-curing trenchless repair of pipelines in combination with a robot according to claim 1, characterized in that: The S5 is specifically as follows: According to the optimized repair plan, control the repair robot to complete the repair tasks of cracks, corrosion, or blockage, including UV curing repair and resin filling operations; The repair robot's built-in high-definition camera and depth sensor can be used to collect the execution status of the repair task in real time; According to the detection results during the repair process, the repair parameters are dynamically adjusted to ensure the best repair effect.

Images