A Method and System for Dimensional Inspection of Bridge Steel Tower Components Based on 3D Laser Scanning

Abstract

This invention discloses a method and system for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning. The method includes obtaining overall point cloud data of the target steel tower component using a three-dimensional laser scanner; obtaining effective point cloud data of the target steel tower component based on the overall point cloud data; clustering the effective point cloud data using the DBSCAN algorithm to obtain all unit point cloud data of the target steel tower component; processing the steel pipe point cloud data using the RANSAC algorithm to obtain the steel pipe diameter; processing the ribbed steel plate point cloud data using a normal vector-based segmentation method, the DBSCAN algorithm, a voxel sampling algorithm, and the RANSAC algorithm to obtain the rib spacing; processing the segment point cloud data using the RANSAC algorithm to obtain the length and width of the side panel, and then rotating the segment point cloud data for slicing and two-dimensional planar projection to obtain the overall dimensions of the segment. This invention enables non-contact measurement of the dimensions of bridge steel tower components, effectively solving the problem of low efficiency in traditional manual measurement.

Description

Technical Field

[0001] This invention belongs to the field of information technology and building safety management technology, and more specifically, relates to a method and system for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning. Background Technology

[0002] During the construction of bridge steel towers, due to limitations in site, transportation, and hoisting, small components are often welded into segments before being transported to the construction site for assembly. Before assembly, the dimensions and quality of each component and segment need to be inspected. Traditional inspection methods often involve workers using tools such as rulers and measuring tapes to check the dimensions and quality of components and segments. This method is inefficient, prone to subjective errors by workers, and makes it impossible to accurately and efficiently control the dimensional quality at each stage of processing. Summary of the Invention

[0003] To address the aforementioned deficiencies or improvement needs of existing technologies, this invention provides a method and system for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning. By combining three-dimensional laser scanning technology, RANSAC algorithm, direct-pass filtering algorithm, DBSCAN algorithm, Rodriguez formula, and least squares method, this invention achieves a high-precision, automated, and robust non-contact detection process for the dimensions of bridge steel tower components. This not only improves the accuracy and efficiency of measurements but also enhances the reliability and flexibility of data processing. It provides strong technical support for quality control, structural health monitoring, maintenance, and repair of bridge engineering projects, while simultaneously reducing costs and improving the economic benefits of the project.

[0004] To achieve the above objectives, one aspect of the present invention provides a method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning, comprising the following steps:

[0005] S1: Use a 3D laser scanner to scan a specific area containing the target steel tower components to obtain overall point cloud data containing the target steel tower components;

[0006] S2: The background noise in the overall point cloud data is processed by a direct-pass filtering algorithm to obtain the effective point cloud data of the target steel tower component;

[0007] S3: The DBSCAN algorithm is used to cluster the effective point cloud data to obtain all unit point cloud data of the target steel tower component; the all unit point cloud data of the target steel tower component includes steel pipe point cloud data, ribbed steel plate point cloud data and segment point cloud data.

[0008] S4: The RANSAC algorithm is used to fit the steel pipe axis and remove noise from the steel pipe point cloud data to obtain the steel pipe outer wall point cloud data; the steel pipe diameter is obtained based on the steel pipe outer wall point cloud data.

[0009] S5: The point cloud data of the ribbed steel plate is processed by the normal vector-based segmentation method and the DBSCAN algorithm to obtain the point cloud data of the instantiated horizontal plate unit and the vertical plate unit; the point cloud data of the instantiated horizontal plate unit and the vertical plate unit are processed by the voxel sampling algorithm and the RANSAC algorithm to obtain the rib spacing.

[0010] S6: The RANSAC algorithm is used to extract the segment point cloud data by multi-plane fitting of the segment to obtain the segment side panel point cloud data; the cross product of the normal vector of the side panel and the Z-axis is used as the front direction of the segment, and the original segment is rotated so that the front direction is parallel to the Y-axis to obtain the rotated segment point cloud data.

[0011] S7: Obtain the length and width of the segment side panel based on the point cloud data of the segment side panel; obtain the overall size of the segment based on the point cloud data of the rotated segment;

[0012] S8: Obtain the target value of the overall segment size of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the amount of machining deformation of the target steel tower component;

[0013] S9: Obtain the error value of the overall segment size based on the overall segment size in step S7 and the target value of the overall segment size in step S8; compare the error value with the precision value required for manufacturing, and mark and prompt the segment size that does not meet the manufacturing precision requirements.

[0014] Further, step S2 involves using a pass-through filtering algorithm to process the background noise in the overall point cloud data containing the target steel tower component, thereby obtaining effective point cloud data of the target steel tower component; this includes:

[0015] Construct a bounding box larger than the target steel tower component, and restrict the target steel tower component to a certain range using the three dimensions of x, y, and z.

[0016] A point cloud pass-through filtering algorithm is used to remove noise data outside the bounding box, while retaining the target steel tower components and some surrounding noise.

[0017] Further, step S4 involves using the RANSAC algorithm to fit the steel pipe axis and remove noise from the steel pipe point cloud data in all element point cloud data of the target steel tower component, thereby obtaining the steel pipe outer wall point cloud data; this includes:

[0018] S411: Divide the steel pipe point cloud data into a sample point set and a test point set;

[0019] S412: The RANSAC algorithm is used to fit the steel pipe axis to the sample point set data to obtain the steel pipe fitted axis equation;

[0020] S413: Calculate the distance between each point in the test point set data and the fitted axis of the steel pipe according to the steel pipe axis equation, set a distance threshold, remove noise points on the inner wall of the steel pipe according to the distance threshold, and obtain the point cloud data of the outer wall of the steel pipe;

[0021] Further, the step S4 of obtaining the steel pipe diameter based on the point cloud data of the outer wall of the steel pipe includes:

[0022] S421: Rotate the steel pipe axis to be parallel to the z-axis; calculate the rotation matrix of the steel pipe axis using the Rodrigues formula;

[0023] S422: Use the rotation matrix to transform the coordinates of each point in the point cloud data of the outer wall of the steel pipe from the coordinate system before rotation to the coordinate system after rotation;

[0024] S423: Project the rotated steel pipe axis onto the xoy plane to obtain two-dimensional circle data;

[0025] S424: Use the least squares method to perform circle fitting on the two-dimensional circle data to obtain the center coordinates and radius of the best-fit circle, and then obtain the diameter of the steel pipe.

[0026] Further, step S5 involves processing the point cloud data of the ribbed steel plate using a normal vector-based segmentation method and the DBSCAN algorithm to obtain point cloud data of instantiated transverse and longitudinal plate units; including:

[0027] The point cloud data of the horizontal and vertical plates are distinguished and extracted from the point cloud data of the ribbed steel plate by a normal vector-based segmentation method.

[0028] The DBSCAN algorithm is used to instantiate and segment the point cloud data of the horizontal and vertical plates to obtain the point cloud data of the instantiated horizontal and vertical plate units.

[0029] Step S5 involves using a voxel sampling algorithm and the RANSAC algorithm to perform planar fitting on the point cloud data of the instantiated horizontal and vertical plate units to obtain the rib spacing; this includes:

[0030] A voxel sampling algorithm is used to process the plate elements to obtain uniformly distributed plate elements. The center coordinates of each plate element are calculated, and the RANSAC algorithm is used to perform plane fitting to obtain the common normal vector of the plate elements. The distance between the center coordinates of each horizontal plate and the vertical plate along the common normal vector is used as the rib spacing.

[0031] Further, in step S6, the RANSAC algorithm is used to perform multi-plane fitting extraction on the segment point cloud data to obtain segment side panel data; including:

[0032] S611: Use the RANSAC algorithm to perform multi-plane fitting on the segment point cloud data. The RANSAC algorithm first fits the plane containing the most point cloud data. For each fitted plane, the point cloud data of that plane is stored in a list, and the fitted plane data is deleted from the remaining segment point cloud data.

[0033] S612: Repeat step S61 to continue plane fitting until the number of planes in the list reaches the preset threshold, then exit the fitting process to obtain the key plane plates (such as side plates, bottom plates, etc.) of each segment.

[0034] S613: Select the side panels from the key planar panels of each segment.

[0035] Further, step S7 involves obtaining the length and width of the segment side panel based on the point cloud data of the segment side panel; including:

[0036] S711: Use a statistical filtering algorithm to remove noise point clouds near the edge of the rectangular plate in the segment side panel point cloud data, rotate the side panel until the reference plane normal vector is parallel to the Z-axis and project it to obtain two-dimensional side panel data;

[0037] S712: Calculate the length and width of the side panel based on the two-dimensional side panel data;

[0038] Step S712 calculates the length and width of the side panel based on the two-dimensional side panel data; including:

[0039] An edge extraction algorithm is used to identify edge points in the two-dimensional side panel data; the RANSAC algorithm is used to fit the edge points with straight lines to obtain the edge line equations; the intersection points of the fitted edge lines are calculated based on the edge line equations to determine the diagonal points of the rectangular plate; the distance from the intersection points to the edge of the rectangular plate is calculated using a distance formula to obtain the length and width of the side panel.

[0040] Further, the step S7 of obtaining the overall size of the segment based on the rotated segment point cloud data includes:

[0041] S721: Slice the rotated segment point cloud data along the Y-axis, take partial slices from the front and rear segments, and use a normal vector segmentation algorithm and a pass-through filtering algorithm to extract the key structural point cloud data for segment slice size detection. Then, project the key structural point cloud data onto the xoz plane to obtain segment two-dimensional point cloud data.

[0042] S722: The RANSAC algorithm is used to fit the two-dimensional point cloud data of the segment to obtain the equation of each line and calculate the coordinates of the intersection of the line equations. For data that needs to fit circular features, the least squares method is used to estimate the coordinates of the center of the circle. Finally, the distance formula is used to calculate the distance between the key intersections to obtain the overall size of the segment.

[0043] Further, step S8, which involves obtaining the target value of the overall segmental dimension of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the machining deformation of the target steel tower component, includes:

[0044] S81: Based on the processing drawings of the target steel tower component, establish an accurate geometric model of the target steel tower component, and use finite element analysis software to mesh the geometric model to construct the finite element model of the target steel tower component;

[0045] S82: Determine the boundary constraint conditions of the target steel tower component in the finite element model based on the placement state of the target steel tower component at the processing site;

[0046] S83: Based on the temperature difference between the ambient temperature recorded during on-site scanning and the processing temperature, calculate the impact of temperature change on material properties, and apply the corresponding temperature load in the finite element model; apply the self-weight of the steel tower component in the finite element model;

[0047] S84: Run the finite element analysis software to calculate the deformation of the target steel tower component under the effects of temperature and self-weight.

[0048] S85: Add the deformation amount to the dimensions on the target steel tower component's machining drawings to obtain the target value of the overall segmental dimensions of the target steel tower component considering the deformation.

[0049] A second aspect of the present invention provides a bridge steel tower component size detection system based on three-dimensional laser scanning, for implementing the bridge steel tower component size detection method based on three-dimensional laser scanning, comprising:

[0050] The first main module is used to scan a specific area containing the target steel tower components using a 3D laser scanner to obtain overall point cloud data containing the target steel tower components;

[0051] The second main module is used to process the background noise in the overall point cloud data using a pass-through filtering algorithm to obtain the effective point cloud data of the target steel tower component.

[0052] The third main module is used to perform clustering processing on the effective point cloud data using the DBSCAN algorithm to obtain all unit point cloud data of the target steel tower component; the all unit point cloud data of the target steel tower component includes steel pipe point cloud data, ribbed steel plate point cloud data and segment point cloud data.

[0053] The fourth main module is used to perform steel pipe axis fitting and noise removal on the steel pipe point cloud data using the RANSAC algorithm to obtain steel pipe outer wall point cloud data; and to obtain the steel pipe diameter based on the steel pipe outer wall point cloud data.

[0054] The fifth main module is used to process the point cloud data of the ribbed steel plate using a normal vector-based segmentation method and the DBSCAN algorithm to obtain the point cloud data of the instantiated horizontal and vertical plate units; and to process the point cloud data of the instantiated horizontal and vertical plate units using a voxel sampling algorithm and the RANSAC algorithm to obtain the rib spacing.

[0055] The sixth main module is used to extract segment point cloud data by multi-plane fitting of the segment using the RANSAC algorithm, and obtain segment side panel point cloud data; the cross product of the normal vector of the side panel and the Z-axis is used as the front direction of the segment, and the original segment is rotated so that the front direction is parallel to the Y-axis to obtain the rotated segment point cloud data.

[0056] The seventh main module is used to obtain the length and width of the segment side panel based on the point cloud data of the segment side panel; and to obtain the overall size of the segment based on the point cloud data of the rotated segment.

[0057] The eighth main module is used to obtain the target value of the overall segment size of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the amount of machining deformation of the target steel tower component;

[0058] The ninth main module is used to obtain the error value of the overall size of the segment based on the overall size of the segment and the target value of the overall size of the segment; and to mark and prompt the segment size that does not meet the manufacturing accuracy requirements by comparing the error value with the accuracy value required by the manufacturing requirements.

[0059] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0060] (1) The present invention provides a method and system for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning. By comprehensively applying high-precision three-dimensional laser scanning technology and combining powerful data processing algorithms, such as RANSAC, direct-pass filtering, and DBSCAN, the present invention achieves accurate non-contact measurement of the dimensions of bridge steel tower components. Specifically, by fitting the steel pipe axis and removing noise using the RANSAC algorithm, more accurate point cloud data of the outer wall of the steel pipe can be obtained, thereby improving the accuracy of diameter measurement. The introduction of the RANSAC algorithm significantly improves the robustness to noise and outliers, ensuring reliable geometric feature fitting even under complex or imperfect data conditions. Direct-pass filtering effectively removes background noise, and the DBSCAN algorithm accurately separates the target components, laying a solid foundation for subsequent dimension analysis. By calculating the rotation matrix using the Rodrigues formula, the scheme can rotate the steel pipe axis. The process involves rotating the data to be parallel to the reference axis and then using the least squares method to fit the projected two-dimensional circular data, thereby accurately calculating the diameter of the steel pipe. The voxelization sampling algorithm and the RANSAC algorithm further optimize the processing of the ribbed steel plate point cloud data, ensuring accurate measurement of the rib spacing. The RANSAC algorithm effectively extracts accurate multi-faceted information from complex segment point cloud data, particularly for the identification of side panels. By calculating the cross product of the side panel normal vector and the axis, the frontal orientation of the segment can be clearly determined, which helps standardize the measurement process and ensures that all dimensional measurements are performed within the correct reference frame. Rotating the original segment to have its frontal orientation parallel to the axis simplifies subsequent dimensional measurement work. This invention provides comprehensive dimensional information for the design verification, manufacturing, installation, and maintenance of bridge steel tower components, thereby ensuring that the manufacturing and installation quality of the components meets design and safety standards.

[0061] (2) The present invention provides a method and system for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning. By establishing a finite element model of the target steel tower component, the deformation analysis of the target steel tower component under the action of temperature difference and self-weight is performed. The corresponding deformation amount is added to the dimensions on the processing drawings of the target steel tower component to obtain the target value of the overall segment dimension of the target steel tower component. The measured value of the overall segment dimension minus the target value of the overall segment dimension is used as the error value of the overall segment dimension given by the detection. This is more accurate and reasonable than the traditional approach of not considering the deformation of the component under load and simply using the dimensions on the processing drawings as the target value, thus improving the practical guiding value of the detection results.

[0062] (3) The present invention provides a method and system for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning. By automating the data processing and analysis process, manual operation is reduced, work efficiency and the consistency of measurement results are improved, while the possibility of human error is reduced. The precise alignment of point cloud data obtained from different angles is ensured by fine registration technology and multi-site scanning strategy, which improves the accuracy of the overall data. The method of the present invention can handle bridge steel tower components of various shapes and types, and can provide comprehensive quality control and structural health monitoring means for all stages of bridge engineering, from design verification to construction monitoring, and then to maintenance and repair. Attached Figure Description

[0063] Figure 1 This is a schematic diagram of the internal logic of a method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning, according to an embodiment of the present invention.

[0064] Figure 2 This is the noise removal result of the inner wall of the steel pipe in an embodiment of the present invention;

[0065] Figure 3 This is the result of ribbed steel plate segmentation in an embodiment of the present invention;

[0066] Figure 4 This is the instantiation and segmentation result of the horizontal and vertical plates in an embodiment of the present invention;

[0067] Figure 5 This is a segment dimension measurement diagram of an embodiment of the present invention;

[0068] Figure 6 This is the side panel edge detection result of an embodiment of the present invention;

[0069] Figure 7 This is a segmental two-dimensional projection result of an embodiment of the present invention;

[0070] Figure 8 This is a schematic diagram of a bridge steel tower component size detection system based on three-dimensional laser scanning according to an embodiment of the present invention;

[0071] Figure 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention;

[0072] Figure 10 This is a flowchart illustrating a method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning, according to an embodiment of the present invention.

[0073] It should be noted that:

[0074] DBSCAN is short for Density-Based Spatial Clustering of Applications with Noise, representing a density-based spatial clustering algorithm.

[0075] RANSAC is short for RANdom Sampling Consensus, which stands for Random Sampling Consensus Algorithm. Detailed Implementation

[0076] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0077] like Figure 1 As shown, one aspect of the present invention provides a method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning, used for automated non-contact detection of the unit dimensions of bridge steel tower components, comprising the following steps:

[0078] S1: Use a 3D laser scanner to scan a specific area containing the target steel tower components to obtain overall point cloud data containing the target steel tower components;

[0079] S2: The overall point cloud data of the target steel tower component is processed using a direct-pass filtering algorithm to obtain the effective point cloud data of the target steel tower component;

[0080] S3: The DBSCAN algorithm is used to cluster the effective point cloud data of the target steel tower component to obtain all unit point cloud data of the target steel tower component; the all unit point cloud data of the target steel tower component includes steel pipe point cloud data, ribbed steel plate point cloud data and segment point cloud data;

[0081] S4: The RANSAC algorithm is used to fit the steel pipe axis and remove noise from the steel pipe point cloud data to obtain the steel pipe outer wall point cloud data; the steel pipe diameter is obtained based on the steel pipe outer wall point cloud data.

[0082] S5: The point cloud data of the ribbed steel plate is processed by the normal vector-based segmentation method and the DBSCAN algorithm to obtain the point cloud data of the instantiated horizontal plate unit and the vertical plate unit; the point cloud data of the instantiated horizontal plate unit and the vertical plate unit are processed by the voxel sampling algorithm and the RANSAC algorithm to obtain the rib spacing.

[0083] S6: The RANSAC algorithm is used to extract the segment point cloud data by multi-plane fitting of the segment to obtain the segment side panel point cloud data; the cross product of the normal vector of the side panel and the Z-axis is used as the front direction of the segment, and the original segment is rotated so that the front direction is parallel to the Y-axis to obtain the rotated segment point cloud data.

[0084] S7: Obtain the length and width of the segment side panel based on the point cloud data of the segment side panel; obtain the overall size of the segment based on the point cloud data of the rotated segment;

[0085] S8: Obtain the target value of the overall segment size of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the amount of machining deformation of the target steel tower component;

[0086] S9: Obtain the error value of the overall segment size based on the overall segment size in step S7 and the target value of the overall segment size in step S8; compare the error value with the precision value required for manufacturing, and mark and prompt the segment size that does not meet the manufacturing precision requirements.

[0087] Further, step S1 involves using a 3D laser scanner to scan a specific area containing the target steel tower component to obtain overall point cloud data containing the target steel tower component. This includes: setting up different stations around the target steel tower component, placing at least 3 common target spheres between adjacent stations, and completing the scanning of point cloud data around the target steel tower component; registering the point cloud data obtained from each station to ensure strong correspondence between the target spheres of adjacent stations, guaranteeing that the positional deviation is within 1mm, and completing the fine registration of the point cloud to obtain overall point cloud data containing the target steel tower component.

[0088] Furthermore, the overall point cloud data containing the target steel tower component obtained in step S1 contains a large amount of background noise data, which needs to be largely removed. Step S2 involves using a direct-pass filtering algorithm to process the background noise in the overall point cloud data containing the target steel tower component to obtain valid point cloud data of the target steel tower component. This includes: preprocessing the overall point cloud data of the target steel tower component using a point cloud direct-pass filtering algorithm. The basic idea of ​​the point cloud direct-pass filtering algorithm is to restrict the point cloud data to a certain range in the x, y, and z dimensions. This method can effectively remove most of the background noise data in the overall point cloud data of the target steel tower component, obtaining valid point cloud data of the target steel tower component. In specific implementation, a bounding box slightly larger than the target steel tower component is constructed (restricting the target steel tower component to a certain range through the x, y, and z dimensions), and noise data outside the bounding box is removed, retaining the target steel tower component and a small amount of surrounding noise.

[0089] Furthermore, after the pass-through filtering in step S2 removes most of the background noise data, a small amount of noise data still exists around the target steel tower component; step S3, which involves using the DBSCAN algorithm to cluster the effective point cloud data to obtain all unit point cloud data of the target steel tower component, includes: using the DBSCAN algorithm to spatially cluster the target steel tower component point cloud data and the noise point cloud data in the effective point cloud data of the target steel tower component according to the point cloud density, to obtain all unit point cloud data of the target steel tower component; the all unit point cloud data of the target steel tower component includes steel pipe point cloud data. The data includes ribbed steel plate point cloud data and segment point cloud data. The DBSCAN algorithm identifies core points by detecting whether the number of points within a neighborhood distance ε of a data point reaches the minimum value MinPts. Core points and their neighborhood points form clusters, while points that do not meet the core point condition may be marked as noise. This algorithm does not require a preset number of clusters, effectively identifies clusters with complex shapes, and resists noise interference. In a specific implementation of this invention, the neighborhood distance ε is set to 2, and the minimum number of points is set to 1000. The target component and noise data are divided into different classes to obtain the target component data.

[0090] Further, in step S4, the RANSAC algorithm is used to perform steel pipe axis fitting and noise removal on the steel pipe point cloud data in all element point cloud data of the target steel tower component to obtain the steel pipe outer wall point cloud data; including:

[0091] S411: Divide the steel pipe point cloud data into a sample point set and a test point set;

[0092] S412: The RANSAC algorithm is used to fit the steel pipe axis to the sample point set data to obtain the steel pipe fitted axis equation;

[0093] S413: Calculate the distance between each point in the test point set data and the fitted axis of the steel pipe according to the steel pipe axis equation, set a distance threshold, remove noise points on the inner wall of the steel pipe according to the distance threshold, and obtain the point cloud data of the outer wall of the steel pipe;

[0094] In step S4, the RANSAC algorithm randomly samples a portion of the steel pipe point cloud data as a sample point set. This point set typically contains two points, sufficient to define a straight line. Based on this sample point set, the parameters of the axis fitting model are estimated. The model parameters will be the equation of the straight line, usually expressed as a two-point equation or parametric equation. Then, the remaining point set in the steel pipe point cloud data is used to verify whether the obtained axis fitting model is optimal. Specifically, for each point, its distance to the fitted axis is calculated and compared with a preset distance threshold. Points with distances less than the threshold are considered inliers, meaning they fit the model. The above sampling, parameter estimation, and verification are repeated. The verification process involves multiple iterations; each iteration may generate a new axis fitting model; the model with the most supported interior points is selected as the optimal model; this model is considered to be the most representative of the steel pipe axis, i.e., the optimal axis fitting model is obtained; in the specific implementation of this invention, the RANSAC algorithm is used for axis fitting, the minimum distance from the point to the cylindrical surface is set to sigma = 0.02, the number of randomly sampled points is n = 5, and the maximum number of iterations is iterations = 1000, to obtain the axis equation; a distance threshold is set, the distance from all points in the steel pipe to the axis is calculated, the points on the inner wall of the steel pipe are removed, and the point cloud data of the outer wall of the steel pipe is obtained.

[0095] Furthermore, if Let B be the coordinates of a point on the fitted axis of the steel pipe, where B is the direction vector of the line and y is the coordinates of the point. Then, the equation of the fitted axis of the steel pipe in step S4 is:

[0096]

[0097] If a point has coordinates A(x1, y1, z1) in the test point set of the steel pipe point cloud data, then the formula for calculating the distance d from point A to the axis is:

[0098]

[0099] Further, in step S4, the diameter of the steel pipe is obtained based on the point cloud data of the outer wall of the steel pipe, including:

[0100] S421: Rotate the steel pipe axis to be parallel to the z-axis; calculate the rotation matrix of the steel pipe axis using the Rodrigues formula;

[0101] S422: Use the rotation matrix to transform the coordinates of each point in the point cloud data of the outer wall of the steel pipe from the coordinate system before rotation to the coordinate system after rotation;

[0102] S423: Project the rotated steel pipe axis onto the xoy plane, ignoring the Z coordinate, to obtain two-dimensional circle data;

[0103] S424: Use the least squares method to perform circle fitting on the two-dimensional circle data to obtain the center coordinates and radius of the best-fit circle, and then obtain the diameter of the steel pipe.

[0104] In step S421, if the axis normal vector Z-axis vector The rotation matrix R of the steel pipe axis is calculated by the following formula:

[0105]

[0106] θ = arccos(cosθ) (5)

[0107]

[0108] R = I + sinθK + (1 - cosθ)K 2 (7)

[0109] Where I is the identity matrix;

[0110] In step S422, if the coordinates of a point in the point cloud data of the outer wall of the steel pipe before rotation are M0(x0,y0,z0), then the coordinates after rotation, M2(x2,y2,z2), are calculated using the following formula:

[0111] M2 = RM0 (8);

[0112] In step S423, the least squares method is used to fit the circle, and the diameter of the circle is the diameter of the steel pipe. As shown in Table 1, the intelligent detection value, target value and absolute error of the steel pipe diameter in the embodiment of the present invention are shown.

[0113] Table 1

[0114]

[0115] Further, step S5 involves processing the point cloud data of the ribbed steel plate using a normal vector-based segmentation method and the DBSCAN algorithm to obtain point cloud data of instantiated transverse and longitudinal plate units; including:

[0116] The point cloud data of the ribbed steel plate is distinguished and extracted from the point cloud data of the horizontal plate and the vertical plate by a normal vector-based segmentation method; the point cloud data of the horizontal plate and the vertical plate are instantiated and segmented by the DBSCAN algorithm to obtain the point cloud data of the instantiated horizontal plate unit and the vertical plate unit.

[0117] In a specific implementation of this invention, the ribbed steel plate includes a transverse plate, a longitudinal plate, and the steel plate itself. The reference normal vectors of these three components are mutually perpendicular. A method based on the normal vectors (i.e., according to the direction of the normal vectors) is used to segment the transverse plate, longitudinal plate, and the steel plate itself from the point cloud data of the ribbed steel plate. Figure 3 As shown;

[0118] The normal vector is calculated using a principal component analysis (PCA) method, and the process is as follows:

[0119] First, for each point, find its nearest neighbor set P = {p1, p2, p3, ..., p...} k};

[0120] Next, calculate the covariance matrix C of the point set P;

[0121] Then, calculate the eigenvalues ​​and eigenvectors of the covariance matrix C;

[0122] Finally, sort the feature vectors in descending order of their corresponding feature values, and select the largest feature vector as the normal vector of that point.

[0123] In a specific implementation of this invention, when using the DBSCAN algorithm to instantiate and segment the point cloud data of the horizontal and vertical plates, the neighbor number is set to 2000, and the point cloud data of the instantiated horizontal and vertical plate units are obtained respectively, as follows: Figure 4 As shown.

[0124] Further, step S5 involves using a voxel sampling algorithm and the RANSAC algorithm to perform planar fitting on the point cloud data of the instantiated horizontal and vertical plate units to obtain the rib spacing; including:

[0125] The plate elements are processed using a voxel sampling algorithm to obtain uniformly distributed plate elements; the center coordinates of each plate element are calculated, and the common normal vector of the plate elements is obtained by performing plane fitting using the RANSAC algorithm. The distance between the center coordinates of each horizontal plate and the vertical plate along the common normal vector is taken as the rib spacing.

[0126] In a specific implementation of this invention, voxel sampling is performed on each plate, and the voxel_size is set to 0.005 to obtain uniformly distributed plate elements. The center coordinates of each plate element are calculated, i.e., the average values ​​of x, y, and z are calculated respectively. The RANSAC algorithm is used to fit the plane of each plate, and the minimum distance from the point to the plane is set to sigma = 0.012, the number of randomly sampled points is n = 5, and the maximum number of iterations is iterations = 1000 to obtain the normal vector of each plate. The average values ​​of the normal vectors of the horizontal and vertical plates are calculated respectively as the reference normal vectors of the horizontal and vertical plates. Finally, the distance of the center coordinates of each plate in the horizontal and vertical plates along the reference normal vector is calculated as the rib spacing. As shown in Table 2, the intelligent detection value, target value, and absolute error of the rib spacing of the ribbed steel plate in the embodiment of this invention are shown.

[0127] Table 2

[0128]

[0129] Further, in step S6, the RANSAC algorithm is used to perform multi-plane fitting extraction on the segment point cloud data to obtain segment side panel data; including:

[0130] S611: Use the RANSAC algorithm to perform multi-plane fitting on the segment point cloud data. The RANSAC algorithm first fits the plane containing the most point cloud data. For each fitted plane, the point cloud data of that plane is stored in a list, and the fitted plane data is deleted from the remaining segment point cloud data.

[0131] S612: Repeat step S61 to continue plane fitting until the number of planes in the list reaches the preset threshold, then exit the fitting process to obtain the key plane plates (such as side plates, bottom plates, etc.) of each segment.

[0132] S613: Select the side panels from the key planar panels of each segment;

[0133] Furthermore, in a specific embodiment of the present invention, step S6 includes first marking the dimensions to be inspected for the entire segment, such as... Figure 5 As shown, the RANSAC algorithm is used to perform multi-plane fitting on the segment point cloud data. The minimum distance from a point to a plane is set to sigma = 0.012, the number of randomly sampled points is n = 5, and the maximum number of iterations is 1000. During the RANSAC plane fitting process, planes that can fit more point clouds are selected first. After fitting a plane, the point cloud data of the current plane is stored in a list, and the currently fitted plane data is deleted from the segment for plane fitting again. When the number of planes in the list reaches a certain threshold, the fitting is terminated, and the key plane plates of each segment are obtained. The side panels are then selected from the obtained key plane plates.

[0134] Further, step S7 involves obtaining the length and width of the segment side panel based on the point cloud data of the segment side panel; including:

[0135] S711: Use a statistical filtering algorithm to remove noise point clouds near the edge of the rectangular plate in the segment side panel point cloud data, rotate the side panel until the reference plane normal vector is parallel to the Z-axis and project it to obtain two-dimensional side panel data;

[0136] S712: Calculate the length and width of the side panel based on the two-dimensional side panel data.

[0137] Furthermore, in a specific embodiment of the present invention, step S711 includes: setting the statistical filtering neighborhood parameter k = 100 to complete the noise reduction of the side panel; rotating the side panel until the reference plane normal vector is parallel to the axis and projecting it to obtain two-dimensional side panel data.

[0138] Further, step S712 calculates the length and width of the side panel based on the two-dimensional side panel data; including:

[0139] An edge extraction algorithm is used to identify edge points in the two-dimensional side panel data; the RANSAC algorithm is used to fit the edge points with straight lines to obtain the edge line equations; the intersection points of the fitted edge lines are calculated based on the edge line equations to determine the diagonal points of the rectangular plate; the distance from the intersection points to the edge of the rectangular plate is calculated using a distance formula to obtain the length and width of the side panel.

[0140] In a specific embodiment of the present invention, in step S712, since the side panel is rectangular, an edge extraction algorithm is used to extract the edges of the side panel. For a point p in the two-dimensional data... i Construct p i The vector set Q(n1,n2,n3...n) of its neighborhood points i ), randomly select any vector n from set Q. i Use it as a reference vector; iterate through the remaining vectors in set Q, and if the current vector is rotated clockwise to n... i If the angle is smaller, the current rotation angle is saved to the clockwise angle set R1; otherwise, if the counterclockwise rotation angle is smaller, it is saved to the counterclockwise angle set R2. The maximum angle in R1 is α, and the maximum angle in R2 is β. Let S = α + β; if s is close to 180°, then the current point p is considered to be... i Points near the edge line are considered; if s is close to 90°, then the current point p is considered to be... i Points near the corners; edge detection results for the rectangular plate are as follows: Figure 6 As shown, the obtained edge points are fitted with straight lines to obtain four straight line equations, the coordinates of the intersection points are obtained, and then the length and width of the rectangular plate are calculated according to the distance formula.

[0141] Further, the step S7 of obtaining the overall size of the segment based on the rotated segment point cloud data includes:

[0142] S721: Slice the rotated segment along the Y-axis, extract the point cloud data of key components for size detection of the segment slice from the point cloud data of the rotated segment, and project the point cloud data of key components onto the xoz plane to obtain two-dimensional point cloud data of the segment.

[0143] S722: The RANSAC algorithm is used to fit the two-dimensional point cloud data of the segment to obtain the equation of each line and calculate the coordinates of the intersection points of each line equation. These intersection points are the intersection points between lines and represent the key size features of the segment. For data that needs to fit circular features, the least squares method is used to estimate the coordinates of the circle center. Finally, the distance formula is used to calculate the distance between the key intersection points. These distances represent the overall size of the segment.

[0144] Further, in a specific embodiment of the present invention, in step S721, the thickness of each slice is set to 0.02m, a normal vector-based segmentation algorithm is used to obtain key components for segmental linear fitting, a pass-through filtering algorithm is used to obtain key components for segmental circular fitting, and the point cloud is projected onto the xoz plane, and each point is labeled, such as... Figure 7 As shown; for Figure 5 For dimension L1, the length and width of the rectangular plate containing L1 can be determined by measuring its dimensions. For dimensions L2, L3, L4, L5, H1, B1, and B2, the coordinates of key points can be calculated. L2 is the distance between points p6 and p9, and L3 is the distance between points p3 and p9. 10 The distances are: L4 is the distance between points p5 and p8 minus the radius of the steel pipe; L5 is the distance between points p4 and p8 minus the radius; B1 is the distance between points p3 and p6; B2 is the distance between points p9 and p... 10 The distance, H1 is the distance between points p1 and p3 plus the height of the side panel.

[0145] Further, in a specific embodiment of the present invention, in step S722, the RANSAC algorithm is used for line fitting. The minimum distance from a point to a line is set to sigma = 0.005, the number of randomly sampled points is n = 3, and the maximum number of iterations is 1000. The obtained point cloud data of each line are saved in a list and the line segments are marked. Then, each line segment is iteratively fitted 20 times. In each iteration, 80% of the points are randomly sampled. After obtaining the equation of each line, it is classified according to the characteristics of the line equation and the intersection points are calculated. Finally, the least squares method is used to fit the center of the two-dimensional circle to obtain the center coordinates. The distance between each intersection point is calculated to obtain the overall size of the segment.

[0146] Further, step S8, which involves obtaining the target value of the overall segmental dimension of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the machining deformation of the target steel tower component, includes:

[0147] S81: Based on the processing drawings of the target steel tower component, establish an accurate geometric model of the target steel tower component, and use finite element analysis software to mesh the geometric model to construct the finite element model of the target steel tower component;

[0148] S82: Determine the boundary constraint conditions of the target steel tower component in the finite element model based on the placement state of the target steel tower component at the processing site;

[0149] S83: Based on the temperature difference between the ambient temperature recorded during on-site scanning and the processing temperature, calculate the impact of temperature change on material properties, and apply the corresponding temperature load in the finite element model; apply the self-weight of the steel tower component in the finite element model;

[0150] S84: Run the finite element analysis software to calculate the deformation of the target steel tower component under the effects of temperature and self-weight.

[0151] S85: Add the deformation amount to the dimensions on the target steel tower component's machining drawings to obtain the target value of the overall segmental dimensions of the target steel tower component considering the deformation.

[0152] Further, step S9, which involves obtaining the error value of the overall segment size based on the overall segment size and the target value of the overall segment size, includes: subtracting the target value of the overall segment size in S8 from the measured value of the overall segment size in S7 to obtain the error value of the overall segment size given by the detection; and finally, comparing the error value with the manufacturing accuracy requirement, marking and prompting the segment size that does not meet the manufacturing accuracy requirement.

[0153] In an embodiment of the present invention, the intelligent detection value, target value, and absolute error of the overall segment size are shown in Table 3.

[0154] Table 3

[0155] Testing items Measured average value / mm Target value / mm Absolute error / mm <![CDATA[L1]]> 10794.0 10801.3 7.3 <![CDATA[L2-L3]]> 5.9 0 5.9 <![CDATA[L4-L5]]> 6.4 0 6.4 <![CDATA[B1]]> 13329.7 13330.7 1.0 <![CDATA[B2]]> 16130.6 16133.9 3.3 <![CDATA[H1]]> 5993.5 5998.9 5.4

[0156] As can be seen from the above, the method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning provided by the present invention can complete the intelligent detection of the unit dimensions of bridge steel tower components. It can use a computer to calculate the diameter of the steel pipe unit, the rib spacing of the ribbed steel plate, and the overall dimensions of the segment. The method described in the present invention is practical and effective.

[0157] like Figure 8 As shown, a second aspect of the present invention provides a bridge steel tower component size detection system based on three-dimensional laser scanning, used to implement the above-mentioned detection method, including a first main module, a second main module, a third main module, a fourth main module, a fifth main module, a sixth main module, a seventh main module, an eighth main module, and a ninth main module; wherein,

[0158] The first main module is used to scan a specific area containing the target steel tower components using a 3D laser scanner to obtain overall point cloud data containing the target steel tower components;

[0159] The second main module is used to process the background noise in the overall point cloud data using a pass-through filtering algorithm to obtain the effective point cloud data of the target steel tower component.

[0160] The third main module is used to perform clustering processing on the effective point cloud data using the DBSCAN algorithm to obtain all unit point cloud data of the target steel tower component; the all unit point cloud data of the target steel tower component includes steel pipe point cloud data, ribbed steel plate point cloud data and segment point cloud data.

[0161] The fourth main module is used to perform steel pipe axis fitting and noise removal on the steel pipe point cloud data using the RANSAC algorithm to obtain steel pipe outer wall point cloud data; and to obtain the steel pipe diameter based on the steel pipe outer wall point cloud data.

[0162] The fifth main module is used to process the point cloud data of the ribbed steel plate using a normal vector-based segmentation method and the DBSCAN algorithm to obtain the point cloud data of the instantiated horizontal and vertical plate units; and to process the point cloud data of the instantiated horizontal and vertical plate units using a voxel sampling algorithm and the RANSAC algorithm to obtain the rib spacing.

[0163] The sixth main module is used to extract segment point cloud data by multi-plane fitting of the segment using the RANSAC algorithm, and obtain segment side panel point cloud data; the cross product of the normal vector of the side panel and the Z-axis is used as the front direction of the segment, and the original segment is rotated so that the front direction is parallel to the Y-axis to obtain the rotated segment point cloud data.

[0164] The seventh main module is used to obtain the length and width of the segment side panel based on the point cloud data of the segment side panel; and to obtain the overall size of the segment based on the point cloud data of the rotated segment.

[0165] The eighth main module is used to obtain the target value of the overall segment size of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the amount of machining deformation of the target steel tower component;

[0166] The ninth main module is used to obtain the error value of the overall size of the segment based on the overall size of the segment and the target value of the overall size of the segment; and to mark and prompt the segment size that does not meet the manufacturing accuracy requirements by comparing the error value with the accuracy value required by the manufacturing requirements.

[0167] It should be noted that the bridge steel tower component size detection system based on three-dimensional laser scanning provided in this embodiment can be a computer program (including program code) running on a computer device. For example, the bridge steel tower component size detection system based on three-dimensional laser scanning is an application software. The bridge steel tower component size detection system based on three-dimensional laser scanning can be used to execute the corresponding steps in the above-described method provided in the embodiments of this application.

[0168] In some feasible implementations, the bridge steel tower component size detection system based on three-dimensional laser scanning provided in this embodiment can be implemented in a combination of hardware and software. As an example, the bridge steel tower component size detection system based on three-dimensional laser scanning provided in this application embodiment can be a processor in the form of a hardware decoding processor, which is programmed to execute the bridge steel tower component size detection method based on three-dimensional laser scanning provided in this application embodiment. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0169] In some feasible implementations, the bridge steel tower component size detection system based on three-dimensional laser scanning provided in this embodiment can be implemented in software. It can be software in the form of programs and plug-ins, and includes a series of modules to realize the bridge steel tower component size detection method based on three-dimensional laser scanning provided in this embodiment of the invention.

[0170] The bridge steel tower component size detection system provided in this embodiment combines three-dimensional laser scanning technology, RANSAC algorithm, direct-pass filtering algorithm, DBSCAN algorithm, Rodriguez formula, and least squares method, among other advanced technologies, to achieve a high-precision, automated, and robust non-contact detection process for bridge steel tower component dimensions. This not only improves the accuracy and efficiency of measurements but also enhances data reliability and processing flexibility, providing strong technical support for quality control, structural health monitoring, maintenance, and repair of bridge engineering projects. Simultaneously, it reduces costs and improves the economic benefits of engineering projects.

[0171] A third aspect of the present invention also provides an electronic device, Figure 9 This is a schematic diagram of the electronic device in this embodiment, as shown below. Figure 9As shown, the electronic device 1000 in this embodiment may include: a processor 1001, a network interface 1004, and a memory 1005. Furthermore, the electronic device 1000 may also include: a user interface 1003, and at least one communication bus 1002. The communication bus 1002 is used to implement communication between these components. The user interface 1003 may include a display screen and a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1004 may be a high-speed RAM or non-volatile memory, such as at least one disk storage device. The memory 1005 may optionally be at least one storage device located remotely from the processor 1001. Figure 9 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a device control application.

[0172] like Figure 9 In the illustrated electronic device 1000, the network interface 1004 provides network communication functionality; the user interface 1003 is primarily used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 to achieve:

[0173] A 3D laser scanner was used to scan a specific area containing the target steel tower components to obtain overall point cloud data containing the target steel tower components;

[0174] A pass-through filtering algorithm is used to process the background noise in the overall point cloud data to obtain the effective point cloud data of the target steel tower component.

[0175] The DBSCAN algorithm is used to cluster the effective point cloud data to obtain all unit point cloud data of the target steel tower component; the all unit point cloud data of the target steel tower component includes steel pipe point cloud data, ribbed steel plate point cloud data and segment point cloud data.

[0176] The RANSAC algorithm is used to fit the steel pipe axis and remove noise from the steel pipe point cloud data to obtain the steel pipe outer wall point cloud data; the steel pipe diameter is obtained based on the steel pipe outer wall point cloud data.

[0177] The point cloud data of the ribbed steel plate is processed by a normal vector-based segmentation method and the DBSCAN algorithm to obtain point cloud data of instantiated horizontal and vertical plate units; the point cloud data of the instantiated horizontal and vertical plate units are processed by a voxel sampling algorithm and the RANSAC algorithm to obtain the rib spacing.

[0178] The RANSAC algorithm is used to extract the segment point cloud data by multi-plane fitting, and the segment side panel point cloud data is obtained. The cross product of the normal vector of the side panel and the Z-axis is taken as the front direction of the segment. The original segment is rotated so that the front direction is parallel to the Y-axis to obtain the rotated segment point cloud data.

[0179] The length and width of the segment side panel are obtained based on the point cloud data of the segment side panel; the overall size of the segment is obtained based on the point cloud data of the rotated segment.

[0180] The target values ​​of the overall segmental dimensions of the target steel tower component are obtained based on the dimensions of the target steel tower component's machining drawings and the amount of machining deformation of the target steel tower component.

[0181] The error value of the overall size of the segment is obtained based on the overall size of the segment and the target value of the overall size of the segment; the error value is compared with the accuracy value required by the manufacturing requirements, and the segment size that does not meet the manufacturing accuracy requirements is marked and indicated.

[0182] It should be understood that in some feasible implementations, the processor 1001 described above may be a central processing unit (CPU), which may also be other general-purpose processors, DSPs, ASICs, FPGAs, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.

[0183] In specific implementation, the aforementioned electronic device 1000 can perform the above-described actions through its built-in functional modules. Figure 10 The implementation methods provided for each step are detailed in the above-mentioned implementation methods and will not be repeated here.

[0184] The electronic device provided in this embodiment combines multiple advanced technologies such as three-dimensional laser scanning technology, RANSAC algorithm, direct-pass filtering algorithm, DBSCAN algorithm, Rodriguez formula, and least squares method to achieve a high-precision, automated, and robust non-contact inspection process for the dimensions of bridge steel tower components. This not only improves the accuracy and efficiency of measurement but also enhances the reliability of data and the flexibility of processing. It provides strong technical support for the quality control, structural health monitoring, maintenance, and repair of bridge engineering projects, while reducing costs and improving the economic benefits of the project.

[0185] This application also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement... Figure 10 The methods provided in each step are detailed in the implementation methods provided in the above steps, and will not be repeated here.

[0186] The computer-readable storage medium provided in this embodiment combines various advanced technologies such as three-dimensional laser scanning technology, RANSAC algorithm, direct-pass filtering algorithm, DBSCAN algorithm, Rodriguez formula, and least squares method to realize a high-precision, automated, and robust non-contact inspection process for the dimensions of bridge steel tower components. This not only improves the accuracy and efficiency of measurement but also enhances the reliability of data and the flexibility of processing. It provides strong technical support for the quality control, structural health monitoring, maintenance, and repair of bridge engineering, while reducing costs and improving the economic benefits of the project.

[0187] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0188] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning, characterized in that, Includes the following steps: S1: Use a 3D laser scanner to scan a specific area containing the target steel tower components to obtain overall point cloud data containing the target steel tower components; S2: The background noise in the overall point cloud data is processed by a direct-pass filtering algorithm to obtain the effective point cloud data of the target steel tower component; S3: The DBSCAN algorithm is used to cluster the effective point cloud data to obtain all unit point cloud data of the target steel tower component; the all unit point cloud data of the target steel tower component includes steel pipe point cloud data, ribbed steel plate point cloud data and segment point cloud data. S4: The RANSAC algorithm is used to fit the steel pipe axis and remove noise from the steel pipe point cloud data to obtain the steel pipe outer wall point cloud data; the steel pipe diameter is obtained based on the steel pipe outer wall point cloud data. S5: The point cloud data of the ribbed steel plate is processed by the normal vector-based segmentation method and the DBSCAN algorithm to obtain the point cloud data of the instantiated horizontal plate unit and the vertical plate unit; the point cloud data of the instantiated horizontal plate unit and the vertical plate unit are processed by the voxel sampling algorithm and the RANSAC algorithm to obtain the rib spacing. S6: The RANSAC algorithm is used to extract the segment point cloud data by multi-plane fitting of the segment to obtain the segment side panel point cloud data; the cross product of the normal vector of the side panel and the Z-axis is used as the front direction of the segment, and the original segment is rotated so that the front direction is parallel to the Y-axis to obtain the rotated segment point cloud data. S7: Obtain the length and width of the segment side panel based on the point cloud data of the segment side panel; obtain the overall size of the segment based on the point cloud data of the rotated segment; S8: Obtain the target value of the overall segment size of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the amount of machining deformation of the target steel tower component; S9: Obtain the error value of the overall size of the segment based on the overall size of the segment and the target value of the overall size of the segment; compare the error value with the precision value required by the manufacturing requirements, and mark and prompt the segment size that does not meet the manufacturing precision requirements.

2. The method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning according to claim 1, characterized in that: Step S2 involves using a pass-through filtering algorithm to process the background noise in the overall point cloud data containing the target steel tower component, thereby obtaining effective point cloud data of the target steel tower component; this includes: Construct a bounding box larger than the target steel tower component, and restrict the target steel tower component to a certain range using the three dimensions of x, y, and z. A point cloud pass-through filtering algorithm is used to remove noise data outside the bounding box, while retaining the target steel tower components and some surrounding noise.

3. The method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning according to claim 1, characterized in that: Step S4, which involves using the RANSAC algorithm to fit the steel pipe axis and remove noise from the point cloud data of all element point cloud data of the target steel tower component, to obtain the point cloud data of the outer wall of the steel pipe, includes: S411: Divide the steel pipe point cloud data into a sample point set and a test point set; S412: The RANSAC algorithm is used to fit the steel pipe axis to the sample point set data to obtain the steel pipe fitted axis equation; S413: Calculate the distance between each point in the test point set data and the fitted axis of the steel pipe according to the steel pipe axis equation, set a distance threshold, remove noise points on the inner wall of the steel pipe according to the distance threshold, and obtain the point cloud data of the outer wall of the steel pipe.

4. The method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning according to claim 3, characterized in that: Step S4, which involves obtaining the diameter of the steel pipe based on the point cloud data of the outer wall of the steel pipe, includes: S421: Rotate the steel pipe axis to be parallel to the z-axis; calculate the rotation matrix of the steel pipe axis using the Rodrigues formula; S422: Use the rotation matrix to transform the coordinates of each point in the point cloud data of the outer wall of the steel pipe from the coordinate system before rotation to the coordinate system after rotation; S423: Project the rotated steel pipe axis onto the xoy plane to obtain two-dimensional circle data; S424: Use the least squares method to perform circle fitting on the two-dimensional circle data to obtain the center coordinates and radius of the best-fit circle, and then obtain the diameter of the steel pipe.

5. A method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning according to any one of claims 1-4, characterized in that: Step S5 describes processing the point cloud data of the ribbed steel plate using a normal vector-based segmentation method and the DBSCAN algorithm to obtain point cloud data of instantiated transverse and longitudinal plate units; including: The point cloud data of the horizontal and vertical plates are distinguished and extracted from the point cloud data of the ribbed steel plate by a normal vector-based segmentation method. The DBSCAN algorithm is used to instantiate and segment the point cloud data of the horizontal and vertical plates to obtain the point cloud data of the instantiated horizontal and vertical plate units. Step S5 involves using a voxel sampling algorithm and the RANSAC algorithm to perform planar fitting on the point cloud data of the instantiated horizontal and vertical plate units to obtain the rib spacing; this includes: A voxel sampling algorithm is used to process the plate elements to obtain uniformly distributed plate elements. The center coordinates of each plate element are calculated, and the RANSAC algorithm is used to perform plane fitting to obtain the common normal vector of the plate elements. The distance between the center coordinates of each horizontal plate and the vertical plate along the common normal vector is used as the rib spacing.

6. A method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning according to any one of claims 1-4, characterized in that: Step S6 uses the RANSAC algorithm to perform multi-plane fitting extraction on the segment point cloud data to obtain segment side panel data; including: S611: Use the RANSAC algorithm to perform multi-plane fitting on the segment point cloud data. The RANSAC algorithm first fits the plane containing the most point cloud data. For each fitted plane, the point cloud data of that plane is stored in a list, and the fitted plane data is deleted from the remaining segment point cloud data. S612: Repeat step S61 to continue plane fitting until the number of planes in the list reaches the preset threshold, then exit the fitting process to obtain the key plane plates (such as side plates, bottom plates, etc.) of each segment. S613: Select the side panels from the key planar panels of each segment.

7. A method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning according to any one of claims 1-4, characterized in that: Step S7 involves obtaining the length and width of the segment side panel based on the point cloud data of the segment side panel; including: S711: Use a statistical filtering algorithm to remove noise point clouds near the edge of the rectangular plate in the segment side panel point cloud data, rotate the side panel until the reference plane normal vector is parallel to the Z-axis and project it to obtain two-dimensional side panel data; S712: Calculate the length and width of the side panel based on the two-dimensional side panel data; Step S712 calculates the length and width of the side panel based on the two-dimensional side panel data; including: An edge extraction algorithm is used to identify edge points in the two-dimensional side panel data; the RANSAC algorithm is used to fit the edge points with straight lines to obtain the edge line equations; the intersection points of the fitted edge lines are calculated based on the edge line equations to determine the diagonal points of the rectangular plate; the distance from the intersection points to the edge of the rectangular plate is calculated using a distance formula to obtain the length and width of the side panel.

8. A method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning according to any one of claims 1-4, characterized in that: Step S7, which involves obtaining the overall size of a segment based on the rotated segment point cloud data, includes: S721: Slice the rotated segment point cloud data along the Y-axis, take partial slices from the front and rear segments, and use a normal vector segmentation algorithm and a pass-through filtering algorithm to extract the key structural point cloud data for segment slice size detection. Then, project the key structural point cloud data onto the xoz plane to obtain segment two-dimensional point cloud data. S722: The RANSAC algorithm is used to fit the two-dimensional point cloud data of the segment to obtain the equation of each line and calculate the coordinates of the intersection of the line equations. For data that needs to fit circular features, the least squares method is used to estimate the coordinates of the center of the circle. Finally, the distance formula is used to calculate the distance between the key intersections to obtain the overall size of the segment.

9. A method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning according to any one of claims 1-4, characterized in that: Step S8, which involves obtaining the target value of the overall segmental dimension of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the machining deformation amount of the target steel tower component, includes: S81: Based on the processing drawings of the target steel tower component, establish an accurate geometric model of the target steel tower component, and use finite element analysis software to mesh the geometric model to construct the finite element model of the target steel tower component; S82: Determine the boundary constraint conditions of the target steel tower component in the finite element model based on the placement state of the target steel tower component at the processing site; S83: Based on the temperature difference between the ambient temperature recorded during on-site scanning and the processing temperature, calculate the impact of temperature change on material properties, and apply the corresponding temperature load in the finite element model; apply the self-weight of the steel tower component in the finite element model; S84: Run the finite element analysis software to calculate the deformation of the target steel tower component under the effects of temperature and self-weight. S85: Add the deformation amount to the dimensions on the target steel tower component's machining drawings to obtain the target value of the overall segmental dimensions of the target steel tower component considering the deformation.

10. A bridge steel tower component dimension detection system based on three-dimensional laser scanning, characterized in that, The method for detecting the dimensions of bridge steel tower components based on three-dimensional laser scanning as described in any one of claims 1-9 includes: The first main module is used to scan a specific area containing the target steel tower components using a 3D laser scanner to obtain overall point cloud data containing the target steel tower components; The second main module is used to process the background noise in the overall point cloud data using a pass-through filtering algorithm to obtain the effective point cloud data of the target steel tower component. The third main module is used to perform clustering processing on the effective point cloud data using the DBSCAN algorithm to obtain all unit point cloud data of the target steel tower component; the all unit point cloud data of the target steel tower component includes steel pipe point cloud data, ribbed steel plate point cloud data and segment point cloud data. The fourth main module is used to perform steel pipe axis fitting and noise removal on the steel pipe point cloud data using the RANSAC algorithm to obtain steel pipe outer wall point cloud data; and to obtain the steel pipe diameter based on the steel pipe outer wall point cloud data. The fifth main module is used to process the point cloud data of the ribbed steel plate using a normal vector-based segmentation method and the DBSCAN algorithm to obtain the point cloud data of the instantiated horizontal and vertical plate units; and to process the point cloud data of the instantiated horizontal and vertical plate units using a voxel sampling algorithm and the RANSAC algorithm to obtain the rib spacing. The sixth main module is used to extract segment point cloud data by multi-plane fitting of the segment using the RANSAC algorithm, and obtain segment side panel point cloud data; the cross product of the normal vector of the side panel and the Z-axis is used as the front direction of the segment, and the original segment is rotated so that the front direction is parallel to the Y-axis to obtain the rotated segment point cloud data. The seventh main module is used to obtain the length and width of the segment side panel based on the point cloud data of the segment side panel; and to obtain the overall size of the segment based on the point cloud data of the rotated segment. The eighth main module is used to obtain the target value of the overall segment size of the target steel tower component based on the dimensions of the target steel tower component's machining drawings and the amount of machining deformation of the target steel tower component; The ninth main module is used to obtain the error value of the overall size of the segment based on the overall size of the segment and the target value of the overall size of the segment; and to mark and prompt the segment size that does not meet the manufacturing accuracy requirements by comparing the error value with the accuracy value required by the manufacturing requirements.

Images