Intelligent planning method and system for self-adaptive pipeline migration and transformation

Abstract

The invention provides a self-adaptive pipeline migration and transformation intelligent planning method and system, and the method comprises the steps: obtaining laser scanning point cloud data and penetration detection data of an existing pipeline above the ground; fusing the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline; based on the multi-source detection data, establishing a data set containing three-dimensional position information and material attributes; for the shielded pipeline part in the existing pipeline, reconstructing space bending information of the shielded pipeline part based on the multi-source detection data; based on the data set and the reconstructed spatial bending information, generating low-dimensional expression data retaining the existing pipeline connection structure by using a dimension reduction calculation model; and based on the low-dimensional expression data and a preset new pipeline constraint condition, generating an avoidance planning scheme of the new pipeline. According to the invention, the precision and efficiency of dense urban area pipeline relocation and transformation planning are improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent planning of urban underground pipelines, and in particular to an adaptive pipeline relocation intelligent planning method and system. Background Art

[0002] As the density of urban underground space development continues to increase, the problem of intersection conflicts between new and existing pipelines is becoming increasingly prominent, especially in densely populated urban areas. Existing pipelines are often blocked by buildings or strata, and traditional detection methods cannot easily obtain complete three-dimensional data. There is an urgent need for an intelligent planning method that can integrate multi-source data, accurately reconstruct the shape of obscured pipelines, and automatically generate avoidance plans.

[0003] Currently, there is a technical solution that uses laser scanning and geological radar layered detection. This solution aligns the two types of data through a temporal registration algorithm, extracts pipeline features based on point cloud density threshold segmentation, and finally uses a three-dimensional path search algorithm to generate an avoidance path.

[0004] This method does not adequately preserve the topological relationship of the pipeline connection structure, and is prone to losing key spatial constraints during dimensionality reduction processing, resulting in the risk of sudden curvature changes or spacing violations in the generated avoidance path. In addition, the computational complexity increases sharply with the increase in the number of pipeline nodes. Summary of the Invention

[0005] The present application provides an adaptive pipeline relocation intelligent planning method and system to solve the problems of low accuracy and poor efficiency in pipeline relocation planning in dense urban areas in the prior art.

[0006] In a first aspect, the present application provides an adaptive pipeline relocation intelligent planning method, comprising: Obtain laser scanning point cloud data and penetration detection data of existing pipelines above the ground; Fusing the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline; Based on the multi-source detection data, establishing a data set including three-dimensional position information and material attributes; For a blocked pipeline portion of the existing pipeline, reconstructing spatial curvature information of the blocked pipeline portion based on the multi-source detection data; Based on the data set and the reconstructed spatial curvature information, a dimensionality reduction calculation model is used to generate low-dimensional expression data that retains the existing pipeline connection structure; Based on the low-dimensional expression data and preset constraints on the new pipeline, an avoidance planning scheme for the new pipeline is generated.

[0007] Optionally, for the obscured pipeline portion of the existing pipeline, reconstructing the spatial curvature information of the obscured pipeline portion based on the multi-source detection data includes: Separating a penetration detection data segment corresponding to the obscured pipeline portion from the multi-source detection data; Based on the trend of adjacent visible pipe segments, a spatial reference axis is constructed; The penetration detection data segment is compared with the spatial reference axis, and the spatial curvature information is reconstructed based on the comparison result to obtain reconstructed spatial curvature information.

[0008] Optionally, reconstructing the space curvature information based on the comparison result to obtain the reconstructed space curvature information includes: Calculating the vertical distance value from each spatial point of the penetration detection data segment to the reference axis according to the comparison result to form a vertical distance value sequence; generating a point offset direction sequence according to the positive and negative signs of each vertical distance value in the vertical distance value sequence; constructing a continuous morphological curve based on the point offset direction sequence; The continuous morphology curve is smoothed, and the smoothed continuous morphology curve is used as the reconstructed space curvature information.

[0009] Optionally, the smoothing of the continuous morphology curve includes: Perform equidistant segmentation on the smoothed continuous morphological curve to generate multiple curve segments; Calculate the change in bending direction of each curve segment endpoint; Check whether the bending direction changes of adjacent curve segment endpoints meet the preset consistency conditions; According to the detection results, the curve segments that meet the consistency condition are connected to form a smoothed continuous morphological curve.

[0010] Optionally, fusing the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline includes: Establishing a spatial position correspondence between the surface coordinate system of the laser scanning point cloud data and the underground coordinate system of the penetration detection data; Identifying, based on the spatial position correspondence, a common coverage area of ​​the laser scanning point cloud data and the penetration detection data describing the same existing pipeline portion; In the common coverage area, mapping the underground depth data in the penetration detection data to the surface coordinate system according to the spatial position correspondence; For non-common coverage areas, retaining original underground depth data in the penetration detection data; The mapped underground depth data in the common coverage area is fused with the original underground depth data in the non-common coverage area to form multi-source detection data.

[0011] Optionally, the step of generating low-dimensional expression data retaining the existing pipeline connection structure using a dimensionality reduction calculation model based on the data set and the reconstructed spatial curvature information includes: Encoding the three-dimensional position information and material attributes in the data set into a first feature vector; encoding the reconstructed space curvature information into a second eigenvector; Combining the first eigenvector and the second eigenvector, and inputting the combined result into a dimensionality reduction calculation model, wherein the dimensionality reduction calculation model imposes a spatial position constraint of the pipeline connection point on the combined result during the dimensionality reduction process; According to the spatial position constraints, low-dimensional expression data is output.

[0012] Optionally, generating an avoidance planning scheme for a new pipeline based on the low-dimensional expression data and preset constraints of the new pipeline includes: Analyzing the spatial position conditions and morphological conditions from the newly-built pipeline constraint conditions; Converting the low-dimensional expression data into an obstacle constraint boundary, and constructing a path feasible domain space for the new pipeline by combining the obstacle constraint boundary and the spatial position condition; Generating a candidate path node sequence for a new pipeline in the path feasible domain space; Selecting a key path node sequence that meets the morphological condition from the candidate path node sequence; The critical path node sequence is converted to the original three-dimensional coordinate system through inverse mapping to generate an avoidance planning scheme.

[0013] In a second aspect, the present application provides an adaptive pipeline relocation intelligent planning system, comprising: An acquisition module is used to obtain laser scanning point cloud data and penetration detection data of existing pipelines above the ground; A fusion module, configured to fuse the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline; An establishment module, configured to establish a data set including three-dimensional position information and material attributes based on the multi-source detection data; a reconstruction module, configured to reconstruct spatial curvature information of a blocked pipeline portion of the existing pipeline based on the multi-source detection data; An input module is used to generate low-dimensional expression data that retains the existing pipeline connection structure using a dimensionality reduction calculation model based on the data set and the reconstructed spatial curvature information; A generation module is used to generate an avoidance planning scheme for the new pipeline based on the low-dimensional expression data and preset new pipeline constraint conditions.

[0014] In a third aspect, the present application provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute an adaptive pipeline relocation intelligent planning method as described in any one of the first aspects.

[0015] In a fourth aspect, the present application provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement an adaptive pipeline relocation intelligent planning method as described in any one of the first aspects.

[0016] In the present application, an adaptive pipeline relocation intelligent planning method is provided, which includes: obtaining laser scanning point cloud data and penetration detection data of existing pipelines above the ground; fusing the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline; establishing a data set containing three-dimensional position information and material properties based on the multi-source detection data; for the obscured pipeline portion of the existing pipeline, reconstructing the spatial curvature information of the obscured pipeline portion based on the multi-source detection data; based on the data set and the reconstructed spatial curvature information, using a dimensionality reduction calculation model to generate low-dimensional expression data that retains the connection structure of the existing pipeline; based on the low-dimensional expression data and preset new pipeline constraint conditions, generating an avoidance planning scheme for the new pipeline.

[0017] The technical solution provided by this application has the following beneficial effects: This application realizes the synchronous collection of surface and underground pipeline data, providing a basis for multi-source data fusion; solves the field of view limitations of a single detection method and improves the integrity of pipeline three-dimensional information; structures the storage of key pipeline features to support subsequent analysis and calculation; fills data blind spots and restores the true three-dimensional shape of hidden pipe sections; compresses data dimensions while maintaining pipeline topological relationships to reduce computational complexity; and automatically outputs compliant paths based on constraints to improve planning efficiency and accuracy.

[0018] Furthermore, the present application also separates the penetration detection data segments of the obscured pipe segments, constructs a spatial reference axis in combination with the direction of the adjacent visible pipe segments, compares the offset distribution of the data segments and the axis, and reconstructs continuous and accurate spatial curvature information.

[0019] In addition, the spatial reference axis of the visible pipe segment is used to guide the reconstruction process of the obscured part, ensuring that the curved shape is naturally connected with the existing pipeline and avoiding path planning deviations caused by data missing.

[0020] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 A flowchart of an adaptive pipeline relocation intelligent planning method provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an adaptive pipeline relocation intelligent planning system provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0024] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0025] Current pipeline relocation planning technologies, based on laser scanning and geological radar layered detection, can achieve data fusion. However, their processing logic, which relies on temporal registration and point cloud density segmentation, has inherent limitations. The topological relationships of pipeline connections are easily destroyed during dimensionality reduction, resulting in discontinuous curvature or spacing violations in the generated avoidance paths. Furthermore, the algorithm complexity increases exponentially with the number of pipeline nodes, making it difficult to meet the real-time planning requirements of large-scale pipeline networks in dense urban areas. These shortcomings stem from the existing methods' inability to maintain pipeline spatial constraints and their suboptimal computational architecture.

[0026] In response to the above problems, this application proposes an adaptive pipeline relocation intelligent planning method, which reconstructs the three-dimensional topology of the pipeline through the deep fusion of multi-source detection data and dimensionality reduction calculation driven by spatial constraints. Specifically, the laser scanning and penetration detection data are first integrated to establish a complete data set containing material properties, and the bending information of the obscured pipe section is reconstructed based on the spatial reference axis; then, the connection structure is preserved through dimensionality reduction to generate low-dimensional expression data, and finally, the avoidance planning scheme is output in combination with the constraint conditions. This method has a breakthrough in embedding the pipeline connection relationship as a spatial constraint into the dimensionality reduction process, which not only solves the problem of path curvature mutation caused by the loss of topological information in the existing technology, but also greatly improves the planning efficiency through low-dimensional space calculation, and realizes high-precision, real-time intelligent planning of complex pipeline networks in dense urban areas.

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0028] Figure 1 A flowchart of an adaptive pipeline relocation intelligent planning method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes: Step 101: Obtain laser scanning point cloud data and penetration detection data of existing pipelines above the ground.

[0029] In step 101, laser scanning point cloud data represents a dense set of three-dimensional coordinates of the surface pipeline acquired by a laser scanner, with each point containing XYZ position information. Penetration detection data represents underground pipeline reflection signal data acquired by equipment such as geological radar, including parameters such as depth and material reflection intensity.

[0030] In the embodiment of the present application, a vehicle-mounted laser scanner is used to scan along the pipeline to obtain a high-density point cloud of the visible part on the ground, and a geological radar vehicle is used simultaneously for underground detection; the laser scanner records the geometric shape of the exposed part of the pipeline, and the geological radar obtains the buried depth and contour data of the underground pipeline through electromagnetic wave reflection; the two types of equipment realize synchronous data collection through a unified time and space reference to ensure the time and space consistency of subsequent fusion.

[0031] For example, during a city road renovation project, a Type A laser scanner was used to scan surface water supply pipelines at fixed intervals to obtain point cloud data. Simultaneously, a Type B geological radar was used to survey the underground area at a set frequency. The laser scanners obtained the 3D coordinates of the pipeline supports, while the geological radar measured the pipeline depth. Both types of data were recorded in a database with a unified timestamp. The scanning interval was determined based on the pipeline diameter, meeting the requirements of the sampling theorem.

[0032] Step 102: Fusing the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline.

[0033] In step 102 , the multi-source detection data represents a complete data set including surface three-dimensional coordinates and underground depth information after fusion.

[0034] In an embodiment of the present application, a conversion relationship between the laser point cloud surface coordinate system and the radar underground coordinate system is established; overlapping areas describing the same pipeline segment in the two types of data are identified; the radar depth data is mapped to the surface coordinate system in the overlapping area; the original radar data is retained for the non-overlapping area; and finally, it is merged into a unified data set containing above-ground and underground information.

[0035] For example, the laser point cloud coordinate system obtained in step 101 is associated with the radar coordinate system through a transformation matrix, with the ground reference point as the common origin; the pipeline vertex buried depth measured by the radar in the overlapping segment in the X direction is converted to the surface Z coordinate; the original radar depth data is retained for the building-blocked segment to form a fused data set.

[0036] Step 103: Based on the multi-source detection data, a data set including three-dimensional position information and material attributes is established.

[0037] In step 103, the three-dimensional position information refers to the specific coordinate data of the existing pipeline in space, including the X, Y, and Z coordinate values ​​of each key point on the pipeline centerline. X and Y represent the planar position of the pipeline on the surface, and Z represents the vertical height or burial depth of the pipeline. This data is extracted through the fusion of laser scanning and penetration detection. Material attributes represent the pipeline material category code divided according to the electromagnetic reflection intensity. The dataset is a structured storage of the existing pipeline feature set, including the three-dimensional coordinate information of the pipeline key points and the corresponding material attribute codes. The material attributes are determined by matching the reflection signal intensity of the penetration detection data with the standard material library and are used for subsequent dimensionality reduction calculations and path planning.

[0038] In an embodiment of the present application, the three-dimensional coordinates of the key points of the pipeline centerline are extracted from the fused data; the material type library is matched according to the radar reflection signal intensity; and the data is structured and stored as a coordinate-material association data set.

[0039] For example, for the water supply pipeline segments in the fused data, the XYZ coordinates of the center points at every set distance are extracted; the material library is matched according to the reflected signal intensity value, and the cast iron pipe segment code is determined to be the set value; finally, a structured table containing coordinates and material codes is generated.

[0040] Step 104: For the obscured pipeline portion in the existing pipeline, reconstruct the spatial curvature information of the obscured pipeline portion based on the multi-source detection data.

[0041] In step 104, obscured pipelines refer to hidden areas of pipelines in densely populated urban areas that cannot be directly detected by laser scanning due to the presence of ground buildings, other pipelines, or obstacles. These areas require supplemental acquisition using penetration detection data (e.g., radar). Spatial curvature information refers to the actual three-dimensional path and curvature of the obscured pipeline, which can be understood as three-dimensional morphological information. This information is obtained through spatial analysis and geometric calculations of the penetration detection data. It accurately describes the actual curvature of the pipeline and provides precise spatial constraints for path planning.

[0042] In an embodiment of the present application, radar data segments of obscured segments are separated from fused data; a reference axis is fitted based on adjacent visible pipe segments; the offset of radar data points relative to the axis is calculated; and a continuous curved shape is generated through curve fitting.

[0043] For example, in the building-blocked section, the average strike angle of adjacent visible pipe sections is taken to construct a reference straight line; the radar data points of the blocked section are vertically projected onto the axis to calculate the offset distance; a cubic polynomial is used to fit the offset distribution to obtain the bending curve equation z=ax³+bx²+cx+d, where the coefficients are determined by the least squares method.

[0044] Step 105: Based on the data set and the reconstructed spatial curvature information, a dimensionality reduction calculation model is used to generate low-dimensional expression data that retains the existing pipeline connection structure.

[0045] In step 105, the existing pipeline connection structure specifically refers to the topological connection relationship between each pipe section in the pipeline system, including the spatial position and connection method of branch points and intersection points; and the structure of the existing pipeline generally refers to the overall three-dimensional form of the pipeline, including physical characteristics such as pipe diameter, direction, and burial depth. The relationship between the two is that the connection structure is the core component of the pipeline structure, which determines the network topology characteristics of the pipeline, while the pipeline structure is the specific spatial expression of the connection structure. Low-dimensional expression data refers to the feature vector compressed by the dimensionality reduction calculation model. This vector retains the key connection structure and spatial topological relationship of the pipeline while reducing the data dimension, making the subsequent path planning calculation more efficient while ensuring the rationality of the avoidance plan.

[0046] In an embodiment of the present application, the three-dimensional coordinates and material are encoded as a first feature vector; the bending information is encoded as a second vector; the combination is input into a dimensionality reduction model, and position constraints are imposed on the coordinates of the connection points during the dimensionality reduction process; and a low-dimensional vector that retains the topological relationship is output.

[0047] For example, the coordinates and material data of the water supply pipeline are encoded as a vector, and the sampling points of the bending curve are encoded as another vector; during the dimensionality reduction calculation, the error of the branch point coordinates is constrained not to exceed the set threshold, and the compressed feature vector is finally output.

[0048] Step 106: Generate an avoidance planning scheme for the new pipeline based on the low-dimensional expression data and preset constraints for the new pipeline.

[0049] In step 106, the new pipeline constraints are engineering specifications that must be met during planning. These include minimum safe spacing from existing pipelines, maximum allowable curvature radius, and material compatibility. These constraints guide the generation and optimization of avoidance paths. The avoidance planning solution represents a three-dimensional pipeline path that satisfies the spacing and curvature constraints.

[0050] In an embodiment of the present application, the spacing and curvature constraints of the newly created pipeline are analyzed; a path node sequence that satisfies the constraints is searched in a low-dimensional space; the selected sequence is inversely mapped into three-dimensional coordinates; and a continuous path is generated through spline interpolation.

[0051] For example, the minimum spacing is set according to the gas pipeline design specifications; node combinations that meet the conditions are screened in the low-dimensional space; after converting the nodes back to three-dimensional coordinates, the final path is generated using a spline curve, where the curve parameters are determined by solving a set of interpolation equations.

[0052] This method achieves accurate reconstruction of pipeline obstruction sections in dense urban areas through multi-source data fusion and spatial constraint preservation technology. The generated avoidance scheme not only meets the requirements of engineering specifications but also maintains the topological rationality of the pipeline network, improving the accuracy and efficiency of pipeline relocation planning in complex environments.

[0053] To address the problem of insufficient accuracy in reconstructing the shape of an obscured pipeline, in some embodiments, step 104: reconstructing spatial curvature information of the obscured pipeline portion of the existing pipeline based on the multi-source detection data includes: Step 201: Separate the penetration detection data segment corresponding to the blocked pipeline portion from the multi-source detection data.

[0054] In step 201, the penetration detection data segment refers to the local detection data corresponding to the area blocked by buildings or strata, which is extracted from the complete penetration data and contains the depth and contour information of the pipeline in the section.

[0055] In an embodiment of the present application, the occlusion range is determined by analyzing the signal interruption area in the multi-source detection data, and the penetration detection data corresponding to the segment is intercepted from the fused data, retaining its depth and reflection intensity characteristics for subsequent reconstruction.

[0056] Step 202: Construct a spatial reference axis based on the trend of adjacent visible pipe segments.

[0057] In step 202, the trend of adjacent visible pipe segments refers to the pipeline extension direction derived from the geometric features of the unobstructed pipeline portion. Specifically, this is achieved by calculating the rate of change of the tangent vector angle and the radius of curvature of the centerlines of adjacent visible pipe segments and fitting the pipeline extension direction prediction model using the least squares method. The spatial reference axis refers to the theoretical centerline constructed by extending the geometric features of the visible pipe segments on both sides of the obstructed area and is used to guide the morphological reconstruction of the obstructed area.

[0058] In an embodiment of the present application, the coordinates of the center points of the visible pipe segments before and after the occlusion area are taken, and their strike angles and curvature change trends are calculated. A reference axis extending to the occlusion area is generated through polynomial fitting, and the axis maintains a natural connection with the visible pipe segment.

[0059] Step 203: Compare the penetration detection data segment with the spatial reference axis, and reconstruct the spatial curvature information based on the comparison result to obtain reconstructed spatial curvature information.

[0060] In step 203, the reconstruction process of the spatial curvature information is to restore the true three-dimensional shape of the obscured pipe section by comparing the actual detection data with the offset distribution of the theoretical axis.

[0061] In an embodiment of the present application, each point of the penetration detection data segment is projected vertically onto the reference axis, the distance offset and direction of each projection point are calculated, and a curve fitting algorithm is used based on the offset mode to generate a continuous and smooth pipeline bending shape to ensure a smooth transition with adjacent pipe sections.

[0062] Here's a specific example: In a road reconstruction project in City A, a section of an underground water supply pipeline was obscured by the foundation of Building B. First, a geological radar data segment corresponding to this obscured section was extracted from the fused multi-source detection data. This segment contained depth information for eight detection points, spaced 0.5 meters apart along the pipeline. Based on the centerline coordinates of the visible pipeline segments on both sides of the obscured area, the average azimuth angle of 32 degrees and the inclination angle of 5 degrees for the first 5 meters of the pipeline were taken to construct the spatial reference axis equation z = tan5° x + 1.85, where the x-axis is determined by an azimuth angle of 32 degrees. The three-dimensional coordinates of the eight detection points were compared with the reference axis, and the perpendicular distance from each point to the axis was calculated: d_i = |0.087x_i - z_i + 1.85| / √(0.087² + 1), where x_i and z_i are the coordinates of the detection points. This yielded a distance sequence of 0.12 m, 0.15 m, 0.18 m, 0.22 m, 0.25 m, 0.23 m, 0.20 m, and 0.17 m. Based on this distance sequence, the least squares method was used to fit a cubic curve, z = 1.85 + 0.002x³ - 0.015x² + 0.032x. The coefficients were determined by solving the normal equation system Σx_i^6·a + Σx_i^5·b + Σx_i^4·c = Σx_i^3·d_i, ensuring a fitting error of less than 0.04 m.

[0063] In an embodiment of the present application, high-precision reconstruction of the curved shape of the obscured pipeline is achieved through collaborative analysis of the penetration data fragments and the reference axis. This not only overcomes the field of view limitations of a single data source, but also ensures the natural connection between the reconstruction results and the existing pipeline, providing a reliable spatial constraint basis for subsequent avoidance planning.

[0064] In order to further improve the reconstruction accuracy of the curved shape of the obscured pipeline, in some embodiments, step 203: reconstructing the spatial curvature information based on the comparison result to obtain the reconstructed spatial curvature information includes: Step 301: Calculate the vertical distance value from each spatial point of the penetration detection data segment to the reference axis according to the comparison result to form a vertical distance value sequence.

[0065] In step 301, the vertical distance value sequence refers to a numerical sequence formed by arranging the vertical distances from each spatial point in the penetration detection data to the reference axis in the order of detection, reflecting the degree of deviation between the actual direction of the pipeline and the theoretical axis.

[0066] In an embodiment of the present application, by calculating the vertical distance from each detection point in the penetration detection data segment to the reference axis, the detection points are arranged in spatial order to form a distance change sequence, which is used to analyze the amplitude change characteristics of pipeline bending.

[0067] Step 302: Generate a point offset direction sequence according to the positive and negative signs of each vertical distance value in the vertical distance value sequence.

[0068] In step 302, the point offset direction sequence refers to the pipeline offset direction record determined according to the positive and negative signs of the vertical distance values, where a positive value indicates a deviation to one side of the axis, and a negative value indicates a deviation to the other side.

[0069] In an embodiment of the present application, a sign judgment is performed on each value in the vertical distance value sequence to generate a sequence consisting of positive and negative signs, which reflects the left and right deviation trend of the pipeline relative to the reference axis and provides directional guidance for subsequent curve construction.

[0070] Step 303: Constructing a continuous morphology curve based on the point offset direction sequence.

[0071] In step 303 , the continuous shape curve refers to a smooth three-dimensional curve constructed based on the offset direction sequence and the distance value, and describes the actual bending shape of the obscured pipe segment.

[0072] In the embodiment of the present application, the curve direction is determined according to the offset direction sequence, and combined with the amplitude change of the vertical distance value sequence, a curve fitting method is used to generate a continuous curve that naturally connects with adjacent pipe sections to ensure the physical rationality of the pipeline morphology.

[0073] Step 304: Smoothing the continuous morphology curve, and using the smoothed continuous morphology curve as reconstructed space curvature information.

[0074] In the embodiment of the present application, the positions of the curve control points are adjusted by a mathematical smoothing algorithm so that the curvature changes evenly and transitions, and finally smooth and continuous spatial curvature information that meets engineering requirements is output.

[0075] Here's a specific example: In the underground pipeline renovation project in City A, for a 600 mm diameter water supply pipeline segment obscured by Building C, the authors first determined the vertical distances of eight detection points (0.12 m, 0.15 m, 0.18 m, 0.22 m, 0.25 m, 0.23 m, 0.20 m, and 0.17 m) to be positive. This generated an offset direction sequence consisting of eight "right" values, indicating that the pipeline was positioned to the right of the reference axis. Based on this sequence, a cubic polynomial fit was used to construct the initial morphological curve. The curve coefficients were determined by solving the equation system Σx_i^6·a+Σx_i^5·b+Σx_i^4·c=Σx_i^3·d_i, where x_i represents the horizontal position of the i-th detection point and d_i represents the corresponding vertical distance. The resulting curve equation is z=1.85+0.002x³-0.015x²+0.032x. When smoothing the curve, the moving average method is used to take the average of the coordinates of three adjacent points. The adjusted curvature change rate of the curve is controlled within 0.15 per meter. Finally, the smoothed spatial curvature information is output for subsequent planning. The smoothness of the curve is verified by calculating the curvature difference between adjacent segments to ensure that it does not exceed the project's allowable change rate standard of 0.05 per meter.

[0076] In the embodiment of the present application, through the collaborative analysis of the vertical distance sequence and the offset direction sequence, combined with curve fitting and smoothing optimization, a high-fidelity reconstruction of the curved shape of the obscured pipeline is achieved, which not only ensures the natural connection with the adjacent pipe sections, but also meets the accuracy requirements of engineering applications, providing a reliable spatial data foundation for subsequent pipeline relocation planning.

[0077] To further improve the smoothness and continuity of the pipeline bending shape, in some embodiments, step 304: smoothing the continuous shape curve includes: Step 401: performing equidistant segmentation on the smoothed continuous morphological curve to generate a plurality of curve segments.

[0078] In step 401, curve segmentation refers to dividing a continuous morphological curve into several segments of fixed length, each segment including a starting point and an ending point.

[0079] In the embodiment of the present application, the entire curve is divided into several sections according to the set segment length to ensure that the length of each section is consistent, which facilitates subsequent unified processing and analysis.

[0080] Step 402: Calculate the bending direction change of each curve segment endpoint.

[0081] In step 402, the bending direction variation refers to the angle difference between the tangent lines at the two end points of the curve segment, reflecting the degree of bending of the curve segment.

[0082] In an embodiment of the present application, the tangent directions at the starting point and the end point of each curve segment are calculated, and the angle difference between the two is obtained as the bending characteristic quantity of the segment, which is used to evaluate the severity of the curve change.

[0083] Step 403: Detect whether the bending direction changes of adjacent curve segment endpoints meet a preset consistency condition.

[0084] In step 403, the consistency condition means that the difference in the amount of change in the bending direction of adjacent curve segments does not exceed a set threshold, ensuring a natural transition of the curve.

[0085] In the embodiment of the present application, the differences in the changes in the bending directions of adjacent segments are compared to determine whether the smooth transition requirement is met, and a curve segment combination that meets the standard is screened out.

[0086] Step 404: According to the detection result, the curve segments that meet the consistency condition are connected to form a smoothed continuous morphological curve.

[0087] In step 404 , the smoothed continuous morphology curve refers to the final optimized curve formed by connecting the curve segments that meet the requirements.

[0088] In the embodiment of the present application, endpoint matching and connection are performed on adjacent curve segments that meet the consistency condition, and local adjustments are made at the connection points when necessary to generate an overall smooth pipeline bending shape.

[0089] Here's a specific example: In the underground pipe network renovation project in Urban District A, a smoothing optimization process was performed on the curved curve of the reconstructed water supply pipeline: z = 1.85 + 0.002x³ - 0.015x² + 0.032x. The curve was first divided horizontally at equal intervals of 0.6 meters, resulting in five segments with x-coordinates of 0, 0.6, 1.2, 1.8, and 2.4 meters. The change in curvature at the endpoints of each segment was calculated. By taking the first-order derivative of the curve, tanθ = dz / dx = 0.006x² - 0.03x + 0.032, the angle value of each endpoint, θ_i = arctan(0.006x_i² - 0.03x_i + 0.032), was obtained. The angle difference between adjacent segments, Δθ = θ_{i+1} - θ_i, was calculated, resulting in a series of changes of 3.0, 2.7, 2.2, and 1.8 degrees. The consistency condition is set as the difference between adjacent Δθ values ​​not exceeding 1.2 degrees. After testing, all segments meet the requirements. The segments that meet the conditions are connected by matching the endpoint coordinates. The connection is connected using cubic spline interpolation to ensure curvature continuity. The interpolation parameters are determined by solving the equation system S''(x_i)=S''(x_{i+1}), and finally a smoothed continuous curve is formed. The curvature radius R is calculated using the formula R=[1+(dz / dx)²]^(3 / 2) / |d²z / dx²|, where dz / dx represents the first-order derivative of the curve and d²z / dx² represents the second-order derivative.

[0090] In the embodiment of the present application, the connection method of curve segmentation processing and consistency detection is used to effectively eliminate local mutation points in the morphological curve, ensure the natural transition of pipeline bending changes, maintain the accuracy of the original data, and improve the overall smoothness of the curve, providing a more reliable geometric basis for pipeline relocation.

[0091] To further improve the accuracy and integrity of multi-source data fusion, in some embodiments, step 102: fusing the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline includes: Step 501: Establishing a spatial position correspondence between the surface coordinate system of the laser scanning point cloud data and the underground coordinate system of the penetration detection data.

[0092] In step 501, the surface coordinate system of the laser scanning point cloud data is a coordinate system directly established when a laser scanner is used to perform a three-dimensional scan of the pipeline above the ground. The coordinate system takes the scanner position as the origin and is constructed by measuring the XYZ coordinates of the laser reflection point. The underground coordinate system of the penetration detection data is a coordinate system established when underground data is collected by penetration detection equipment such as geological radar. The coordinate system takes the detection starting point as the reference, and the depth direction extends downward perpendicular to the ground. The depth here specifically refers to the vertical distance value of the underground pipeline from the ground described in the penetration detection data, that is, the pipeline buried depth data. The spatial position correspondence refers to the conversion rules between the surface coordinate system and the underground coordinate system, including the alignment of the coordinate origin and the axial correspondence.

[0093] In an embodiment of the present application, a conversion relationship between two coordinate systems is established by selecting a ground reference point as a common origin, wherein the Z axis of the surface coordinate system is upward and the Z axis of the underground coordinate system is downward, and the two are connected by the height difference.

[0094] Step 502: Based on the spatial position correspondence, identify the common coverage area of ​​the laser scanning point cloud data and the penetration detection data describing the same existing pipeline location.

[0095] In step 502, the common coverage area refers to the pipeline section that can be detected by both laser scanning and penetration detection, which means that both types of data have valid detection results in this area.

[0096] In the embodiment of the present application, by comparing the spatial distribution ranges of the two types of data, segments containing valid detection data in both are found, and these segments are the common coverage areas.

[0097] Step 503: Within the common coverage area, the underground depth data in the penetration detection data is mapped to the surface coordinate system according to the spatial position correspondence.

[0098] In step 503, the underground depth information in the penetration detection data refers to the buried depth data of underground pipelines obtained by penetration detection equipment such as geological radar. This information is calculated from the reflection time difference after the electromagnetic wave emitted by the equipment encounters the pipeline. The specific value is the round-trip time of the electromagnetic wave multiplied by half of the wave speed in the medium. The relationship between underground depth information and the underground coordinate system: underground depth information is the core parameter in the underground coordinate system. The system takes the detection starting point as the origin and extends vertically downward in the depth direction. The depth information represents the vertical coordinate value of the pipeline in the coordinate system. The two are the relationship between data and the carrier frame. The mapping process of underground depth data refers to the process of converting the underground depth value obtained by penetration detection into the surface coordinate system.

[0099] In an embodiment of the present application, within the common coverage area, the underground depth value obtained by penetration detection is converted into a height value in the surface coordinate system according to the established coordinate conversion relationship, thereby achieving unified expression of data.

[0100] Step 504: For non-common coverage areas, retain the original underground depth data in the penetration detection data.

[0101] In step 504, the original underground depth data refers to the unconverted depth information obtained by penetration detection in the non-co-coverage area.

[0102] In the embodiment of the present application, for areas that can only be detected by penetration detection, the original depth measurement results are retained to ensure data integrity.

[0103] Step 505: Fusing the mapped underground depth data in the common coverage area with the original underground depth data in the non-common coverage area to form multi-source detection data.

[0104] In step 505, the data fusion process refers to the process of integrating the converted common coverage area data and the original non-common coverage area data into a unified data set.

[0105] In the embodiment of the present application, the coordinate-transformed common coverage area data and the original non-common coverage area data are merged according to spatial positions to form a complete multi-source detection data set.

[0106] Here's a specific example: In the underground pipeline renovation project for a main road in City A, a C-type laser scanner was used to obtain point cloud data of the ground water supply pipeline supports at a 0.2-meter interval. A D-type geological radar was also used to detect the underground pipelines at a density of 5 points per meter. A ground reference point at the road's starting point was selected as the coordinate origin, and a conversion relationship between the upward Z-axis of the surface coordinate system and the downward Z-axis of the underground coordinate system was established. Coordinate unification was achieved using the formula Z_surface = -Z_underground + 2.15, where 2.15 meters represents the measured elevation difference between the ground and the radar detection starting point. In the 18-23-meter X-axis section, the laser scan revealed the center coordinates of the surface manhole as 20.5 meters (X) and 4.2 meters (Y). This corresponds to a radar-detected buried depth of 1.92 meters for the pipeline vertex. This conversion yielded a surface coordinate of Z = -1.92 + 2.15 = 0.23 meters. In the 25-30-meter X-axis section, which was obscured by buildings, the original radar depth data of 1.85-2.03 meters was retained. The final multi-source detection data includes: the coordinates of the common coverage area are X=20.5 meters, Y=4.2 meters, Z=0.23 meters, and the depth value of the non-coverage area is 1.85-2.03 meters. The coordinate conversion accuracy is checked through ground control points, and the error is controlled within 0.015 meters.

[0107] In the embodiment of the present application, by establishing a precise coordinate transformation relationship, seamless fusion of above-ground and underground data is achieved, which not only retains the original characteristics of various types of data, but also ensures the accurate expression of the data in a unified coordinate system, providing a complete and reliable data foundation for subsequent three-dimensional reconstruction of pipelines.

[0108] In order to further improve the efficiency of pipeline data processing and maintain the topological relationship of the pipeline network, in some embodiments, step 105: generating low-dimensional expression data that retains the existing pipeline connection structure using a dimensionality reduction calculation model based on the dataset and the reconstructed spatial curvature information, includes: Step 601: Encode the three-dimensional position information and material attributes in the data set into a first feature vector.

[0109] In step 601 , the first feature vector refers to a numerical sequence converted from the three-dimensional coordinates and material attributes of the pipeline, and is used to characterize the basic spatial and material characteristics of the pipeline.

[0110] In an embodiment of the present application, the three-dimensional coordinate values ​​and corresponding material codes of the key points of the pipeline are extracted from the data set and arranged in a fixed order to form a numerical vector to ensure that the basic characteristics of each pipeline segment are fully expressed.

[0111] Step 602: Encode the reconstructed space curvature information into a second eigenvector.

[0112] In step 602, the second feature vector is a numerical sequence converted from the reconstructed spatial curvature information, and is used to describe the curvature morphological characteristics of the pipeline.

[0113] In the embodiment of the present application, the reconstructed bending curve is sampled at equal intervals, and the spatial position parameters of each sampling point are recorded and arranged in sequence to form a numerical sequence describing the bending characteristics of the pipeline.

[0114] Step 603: Combine the first eigenvector and the second eigenvector, and input the combined result into a dimensionality reduction calculation model. The dimensionality reduction calculation model imposes spatial position constraints of pipeline connection points on the combined result during the dimensionality reduction process.

[0115] In step 603, the spatial position constraint refers to the relative position relationship of the pipeline connection points that is forcibly maintained during the dimensionality reduction process to ensure that the topological structure is not destroyed.

[0116] In an embodiment of the present application, the coordinate variation range of pipeline intersection points and branch points is restricted during dimensionality reduction calculations, requiring these key points to maintain an unchanged relative position relationship before and after dimensionality reduction.

[0117] Step 604: Output low-dimensional expression data according to the spatial position constraint.

[0118] In an embodiment of the present application, through constrained dimensionality reduction calculation, a feature vector with reduced output dimension but containing the pipeline spatial structure and connection relationship is used for subsequent efficient processing.

[0119] Here's a specific example: In the underground water supply network renovation project in urban area A, given an established dataset containing coordinates and material attributes and a reconstructed curvature curve z = 1.82 + 0.0018x³ - 0.014x² + 0.03x, the 3D coordinates and material codes of key pipeline nodes were first selected to form the first eigenvector, with cast iron coded as 0.84 and steel pipe coded as 0.91. Fifteen points were sampled at 0.5-meter intervals on the reconstructed curvature curve, and the spatial position parameters of each point were arranged to form the second eigenvector. The two vectors were combined and fed into a dimensionality reduction model. During the calculation, the coordinates of the two branch points were constrained to not vary by more than 0.04 meters. This constraint was achieved by optimizing the objective function minΣ||WX-Y||² + λΣ||C_j(X)-D_j||², where W represents the projection matrix, X represents the input data, Y represents the output data, C_j(X) represents the jth constraint, D_j is the constraint target value, and λ is set to 0.5 to balance reconstruction error and constraint satisfaction. The final output is a 6-dimensional feature vector. After verification, the branch point position error is 0.035 meters, and the bending feature is intact. The weights of each dimension of the feature vector after dimensionality reduction are determined by solving the eigenvalue problem (W^TW+λC^TC)v=γv, where v represents the eigenvector and γ represents the eigenvalue.

[0120] In the embodiment of the present application, efficient compression processing of pipeline data is achieved through the method of feature vector combination and constrained dimensionality reduction, which not only greatly reduces the data dimension but also fully preserves the spatial connection relationship of the pipeline, providing a streamlined and accurate data basis for subsequent avoidance planning.

[0121] To further improve the rationality and feasibility of the new pipeline avoidance planning, in some embodiments, step 106: generating the new pipeline avoidance planning scheme based on the low-dimensional expression data and the preset new pipeline constraint conditions, includes: Step 701: parse the spatial position conditions and morphological conditions from the newly created pipeline constraint conditions.

[0122] In step 701, the spatial position condition refers to the minimum safe distance required between the new pipeline and the existing pipeline. The morphological condition refers to the maximum curvature limit allowed for the new pipeline.

[0123] In the embodiment of the present application, the minimum spacing standards between new pipelines and various existing pipelines, as well as the curvature radius limits determined according to the pipeline material and purpose, are extracted from engineering specifications as basic constraints for planning.

[0124] Step 702: Convert the low-dimensional expression data into an obstacle constraint boundary, and construct a path feasible domain space for the new pipeline by combining the obstacle constraint boundary and the spatial position condition.

[0125] In step 702, the obstacle constraint boundary is the conversion of existing pipeline features expressed in low-dimensional data into the spatial boundaries that the new pipeline must avoid. The path feasible region is the three-dimensional spatial range within which the new pipeline is allowed to be laid out, after deducting the avoidance boundaries and safety distances of existing pipelines. This space ensures that the new pipeline meets safety spacing requirements from existing facilities and complies with engineering design layout specifications.

[0126] In an embodiment of the present application, the spatial influence range of the existing pipeline is restored based on the low-dimensional feature vector, and combined with the safety distance requirements, a prohibited area that the new pipeline cannot enter is delineated to form a clear avoidance boundary.

[0127] Step 703: Generate a candidate path node sequence for a new pipeline in the path feasible domain space.

[0128] In step 703, the candidate path node sequence refers to a set of key control points of several possible paths initially generated in the feasible domain space. Each sequence represents a potential pipeline route plan, including the spatial coordinates of path turning points and feature points.

[0129] In an embodiment of the present application, within the space remaining after deducting the obstacle constraint boundary, the area where the pipeline can be arranged is determined according to engineering design requirements and serves as the basic space for path search.

[0130] Step 704: Filter the key path node sequence that meets the morphological condition from the candidate path node sequence.

[0131] In step 704, the critical path node sequence refers to the optimal path control point sequence that meets the morphological constraints (such as curvature, slope, etc.) selected from the candidate solutions. This sequence can not only meet the avoidance requirements but also ensure the engineering rationality of the pipeline direction.

[0132] In an embodiment of the present application, multiple possible paths are generated in the feasible domain space according to certain rules, and the coordinates of the key turning points of each path are recorded to form a set of alternative solutions.

[0133] Step 705: convert the critical path node sequence into the original three-dimensional coordinate system through inverse mapping to generate an avoidance planning scheme.

[0134] In step 705, the original three-dimensional coordinate system is a unified spatial reference established by fusing the surface coordinate system and the underground coordinate system, wherein the surface coordinate system provides the XY plane coordinates of the pipeline above the ground, and the underground coordinate system provides the depth Z value of the pipeline. The two are associated through the coordinate conversion formula X'=X, Y'=Y, Z'=-Z+H (H is the height difference between the ground and the detection reference plane), and finally form a unified three-dimensional coordinate system containing complete above-ground and underground information.

[0135] In an embodiment of the present application, the selected optimal path node sequence is converted back to the original coordinate system, and a continuous and smooth three-dimensional pipeline path is generated through curve fitting to form an implementable engineering solution.

[0136] Here's a specific example: In the construction of a new underground gas pipeline in Urban Area A, an avoidance plan was generated based on the 6-dimensional low-dimensional feature vector of the existing water supply pipeline. First, the constraints were analyzed according to the gas design specifications, determining a minimum safe distance of 0.5 meters from the water supply pipeline and a maximum allowable curvature radius of 2 meters. The low-dimensional feature vector was converted to an obstacle boundary in three-dimensional space using a transformation matrix. The boundary range was calculated using the formula R = √(x² + y² + z²) + 0.5, where R represents the safety boundary radius and x, y, and z are the coordinate offsets after the low-dimensional vector conversion. After deducting the obstacle boundary, a feasible layout area for the new pipeline was constructed, which fell within the range of 18-25 meters in the X direction, 3-5 meters in the Y direction, and -1.8 to -1.2 meters in the Z direction. Within the feasible domain, a grid search method was used to generate three candidate paths, each containing seven key nodes with a node spacing of 1.2 meters. By calculating the curvature radius of each path (R = [1 + (dz / dx)²]^(3 / 2) / |d²z / dx²|), we identify an optimal path node sequence with a curvature radius greater than 2.1 meters. This sequence is then transformed back to the original coordinate system using inverse mapping, and the final avoidance path is generated using cubic spline interpolation. The interpolation parameters are determined by solving the equation system S''(x_i)=S''(x_{i+1}), where S represents a piecewise cubic polynomial and x_i represents the node coordinates.

[0137] In the embodiment of the present application, by converting low-dimensional data into spatial constraints and optimizing path selection within the feasible domain, safe avoidance of new pipelines and existing pipelines is achieved, which not only meets the requirements of engineering specifications but also ensures the rationality of pipeline layout and construction feasibility.

[0138] Figure 2 This is a structural diagram of an adaptive pipeline relocation intelligent planning system provided in an embodiment of the present application, such as Figure 2 As shown, the system includes: The acquisition module 21 is used to acquire laser scanning point cloud data and penetration detection data of existing pipelines above the ground.

[0139] The fusion module 22 is used to fuse the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline.

[0140] The establishing module 23 is configured to establish a data set including three-dimensional position information and material attributes based on the multi-source detection data.

[0141] The reconstruction module 24 is configured to reconstruct spatial curvature information of the obscured pipeline portion in the existing pipeline based on the multi-source detection data.

[0142] The input module 25 is configured to generate low-dimensional expression data that retains the existing pipeline connection structure based on the data set and the reconstructed spatial curvature information using a dimensionality reduction calculation model.

[0143] The generating module 26 is configured to generate an avoidance planning scheme for the new pipeline based on the low-dimensional expression data and preset constraints of the new pipeline.

[0144] Figure 2 The adaptive pipeline relocation intelligent planning system can execute Figure 1 The implementation principles and technical effects of the adaptive pipeline relocation intelligent planning method described in the illustrated embodiment are not further elaborated. The specific manner in which each module and unit performs operations in the adaptive pipeline relocation intelligent planning system in the above embodiment has been described in detail in the relevant embodiment of the method and will not be further elaborated here.

[0145] In one possible design, Figure 2 An adaptive pipeline relocation intelligent planning system of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0146] The processing component 32 is used to perform the above Figure 1 The embodiment provides an adaptive pipeline relocation intelligent planning method.

[0147] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0148] The storage component 31 is configured to store various types of data to support operations on the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0149] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0150] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0151] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0152] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0153] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 An adaptive pipeline relocation intelligent planning method according to the illustrated embodiment.

[0154] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0155] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0156] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0157] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An adaptive pipeline relocation intelligent planning method, characterized in that: include: Obtain laser scanning point cloud data and penetration detection data of existing pipelines above the ground; Fusing the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline; Based on the multi-source detection data, establishing a data set including three-dimensional position information and material attributes; For a blocked pipeline portion of the existing pipeline, reconstructing spatial curvature information of the blocked pipeline portion based on the multi-source detection data; Based on the data set and the reconstructed spatial curvature information, a dimensionality reduction calculation model is used to generate low-dimensional expression data that retains the existing pipeline connection structure; Based on the low-dimensional expression data and preset constraints on the new pipeline, an avoidance planning scheme for the new pipeline is generated.

2. The method according to claim 1, characterized in that The reconstructing, for the obscured pipeline portion of the existing pipeline based on the multi-source detection data, spatial curvature information of the obscured pipeline portion includes: Separating a penetration detection data segment corresponding to the obscured pipeline portion from the multi-source detection data; Based on the trend of adjacent visible pipe segments, a spatial reference axis is constructed; The penetration detection data segment is compared with the spatial reference axis, and the spatial curvature information is reconstructed based on the comparison result to obtain reconstructed spatial curvature information.

3. The method according to claim 2, characterized in that The reconstructing the space curvature information based on the comparison result to obtain the reconstructed space curvature information includes: Calculating the vertical distance value from each spatial point of the penetration detection data segment to the reference axis according to the comparison result to form a vertical distance value sequence; generating a point offset direction sequence according to the positive and negative signs of each vertical distance value in the vertical distance value sequence; constructing a continuous morphological curve based on the point offset direction sequence; The continuous morphology curve is smoothed, and the smoothed continuous morphology curve is used as the reconstructed space curvature information.

4. The method according to claim 3, characterized in that The smoothing of the continuous morphological curve comprises: Perform equidistant segmentation on the smoothed continuous morphological curve to generate multiple curve segments; Calculate the change in bending direction of each curve segment endpoint; Check whether the bending direction changes of adjacent curve segment endpoints meet the preset consistency conditions; According to the detection results, the curve segments that meet the consistency condition are connected to form a smoothed continuous morphological curve.

5. The method according to claim 1, wherein The fusing of the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline includes: Establishing a spatial position correspondence between the surface coordinate system of the laser scanning point cloud data and the underground coordinate system of the penetration detection data; Identifying, based on the spatial position correspondence, a common coverage area of ​​the laser scanning point cloud data and the penetration detection data describing the same existing pipeline portion; In the common coverage area, mapping the underground depth data in the penetration detection data to the surface coordinate system according to the spatial position correspondence; For non-common coverage areas, retaining original underground depth data in the penetration detection data; The mapped underground depth data in the common coverage area is fused with the original underground depth data in the non-common coverage area to form multi-source detection data.

6. The method according to claim 1, characterized in that The method of generating low-dimensional expression data retaining the existing pipeline connection structure based on the data set and the reconstructed spatial curvature information using a dimensionality reduction calculation model includes: Encoding the three-dimensional position information and material attributes in the data set into a first feature vector; encoding the reconstructed space curvature information into a second eigenvector; Combining the first eigenvector and the second eigenvector, and inputting the combined result into a dimensionality reduction calculation model, wherein the dimensionality reduction calculation model imposes a spatial position constraint of the pipeline connection point on the combined result during the dimensionality reduction process; According to the spatial position constraints, low-dimensional expression data is output.

7. The method according to claim 1, characterized in that The generating of an avoidance planning scheme for a new pipeline based on the low-dimensional expression data and preset constraints on the new pipeline includes: Analyzing the spatial position conditions and morphological conditions from the newly-built pipeline constraint conditions; Converting the low-dimensional expression data into an obstacle constraint boundary, and constructing a path feasible domain space for the new pipeline by combining the obstacle constraint boundary and the spatial position condition; Generating a candidate path node sequence for a new pipeline in the path feasible domain space; Selecting a key path node sequence that meets the morphological condition from the candidate path node sequence; The critical path node sequence is converted to the original three-dimensional coordinate system through inverse mapping to generate an avoidance planning scheme.

8. An adaptive pipeline relocation intelligent planning system, characterized by: include: An acquisition module is used to obtain laser scanning point cloud data and penetration detection data of existing pipelines above the ground; A fusion module, configured to fuse the laser scanning point cloud data and the penetration detection data to form multi-source detection data of the existing pipeline; An establishment module, configured to establish a data set including three-dimensional position information and material attributes based on the multi-source detection data; a reconstruction module, configured to reconstruct spatial curvature information of a blocked pipeline portion of the existing pipeline based on the multi-source detection data; An input module is used to generate low-dimensional expression data that retains the existing pipeline connection structure using a dimensionality reduction calculation model based on the data set and the reconstructed spatial curvature information; A generation module is used to generate an avoidance planning scheme for the new pipeline based on the low-dimensional expression data and preset new pipeline constraint conditions.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an adaptive pipeline relocation intelligent planning method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, an adaptive pipeline relocation intelligent planning method according to any one of claims 1 to 7 is implemented.

Images