Railway box girder full-section data monitoring method and system based on three-dimensional scanner

Abstract

The invention discloses a railway box girder full-section data monitoring method and system based on a three-dimensional scanner, and particularly relates to the technical field of data monitoring, and the method comprises the steps: collecting the data of the full section of a railway box girder through the three-dimensional scanner, scanning each part of the box girder for multiple times, and determining the data collection process of the full section of the railway box girder. Collected railway box girder full-section data are processed, point cloud data are spliced through an aerial triangulation calculation process based on dense point cloud data, key point circle center position accurate estimation and key plane fitting and optimization, and an operator uploads the spliced data and special mark point coordinates to an intelligent measurement integrated platform system. The point cloud information and the contour information of the prefabricated box girder are collected, the acceptance assessment model of the prefabricated box girder is constructed, the possible significant deviation between the box girder model and the design standard is quantified, and the railway box girder full-section acceptance efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and more specifically, to a method and system for monitoring the full-section data of a railway box girder based on a three-dimensional scanner. Background Art

[0002] For many years, the dimensions of railway prefabricated box girders have been measured manually with conventional equipment and instruments such as steel tape measures, levels, vernier calipers, and spirit levels, which have low measurement accuracy, low measurement efficiency, and high labor consumption. With the development of intelligent measurement and scanning technology, based on the need to measure the appearance dimensions of box girders, the traditional railway box girder appearance dimension acceptance method has problems such as low work efficiency and difficulty in avoiding human errors.

[0003] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for monitoring the full-section data of a railway box girder based on a three-dimensional scanner to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The railway box girder full section data monitoring method based on a three-dimensional scanner specifically includes the following steps: S1: Collect data of the entire section of the railway box girder through a 3D scanner, and determine the data collection process of the entire section of the railway box girder by scanning each part of the box girder multiple times; S2: Process the collected full-section data of the railway box girder, and splice the point cloud data through the aerial triangulation calculation process based on dense point cloud data, accurate estimation of the center position of key points, and key plane fitting and optimization; S3: The operator uploads the splicing data and the coordinates of the special marking points to the intelligent measurement integrated platform system. The system will automatically measure the current model, automatically generate acceptance data and export the complete acceptance form; S4: Collect the point cloud information and contour information of the prefabricated box girder, build the acceptance evaluation model of the prefabricated box girder, and quantify the significant deviation between the box girder model and the design standard.

[0006] In a preferred embodiment, the data collection process includes beam end data collection, bottom web side data collection, beam interior data collection and top plate data collection, wherein: In the data collection of the beam end, special marking points are set at the bottom bevel of the beam, the top of the beam and the center line of the support using standard parts, which are used as coordinate positioning points after later splicing. After setting the special marking points and the positioning marking balls for splicing, a non-contact 3D laser scanner is used to collect data at the middle of the beam end. In the data collection of the bottom web plate side, special marking points are set at the span line and the beam end using standard parts, which are used as coordinate positioning points after later splicing. After the marking points are set, a non-contact 3D laser scanner is used to collect web plate data at a position 6m away from the beam end on the beam side, and a non-contact 3D laser scanner is used to collect bottom plate data at the middle position of the beam side. In the data collection in the beam room, two positions close to the beam end and where the positioning marker ball placed at the beam end can be observed are selected as data collection points. At the same time, the non-contact 3D laser scanner is adjusted to ensure that there is no overexposure, and then the non-contact 3D laser scanner is used for data collection; In the top plate data collection, two positions on both sides close to the beam end and where the positioning marker balls placed on the beam end can be observed are selected as data collection points. After the two data collection points are determined, a non-contact 3D laser scanner is used for data collection.

[0007] In a preferred embodiment, the aerial triangulation calculation process based on dense point cloud data includes: Redefine the absolute position coordinate system, organically combine it with the current aerial triangulation calculation method, and redesign the calculation process to minimize or eliminate the errors caused by aerial triangulation calculation. This includes fitting the maximum plane at the beam end and obtaining the plane equation, obtaining the angle between the plane normal vector and the normal vector of the absolute coordinate system, constructing a three-dimensional rotation matrix, transposing the point cloud data, and determining the center point of the point cloud model.

[0008] In a preferred embodiment, accurate estimation of the center position of key points and fitting and optimization of key planes include: The fitting circle model is used to accurately estimate the center position of the circle, and the least square method is used to calculate the optimal center position of the circle. The parameters of the plane model are optimized by minimizing the distance from the point to the plane to obtain the best plane fitting effect.

[0009] In a preferred embodiment, the operator uploads the splicing data and the coordinates of the special marking points to the intelligent measurement integrated platform system, including: The intelligent measurement integrated platform system adopts advanced model optimization technology to reduce the model size and improve the reasoning speed. It uses distributed learning methods to divide the model into multiple parts to reduce the transmission burden. It uses parallel computing technology to give full play to the performance of multi-core processors and GPUs to improve the system computing speed. By building a distributed system, tasks are distributed to multiple computing nodes. Adopt incremental data transmission method, only transmit the changed data, realize block processing of LAS files, only load and process the part of data currently needed, improve file processing efficiency, use distributed file system or database and introduce index technology to speed up the retrieval and query operations of large data such as LAS files.

[0010] In a preferred embodiment, the point cloud information of the prefabricated box girder includes: The point cloud information of the prefabricated box girder is represented by the point cloud matching error anomaly coefficient; The logic for obtaining the point cloud matching error anomaly coefficient is as follows: different point cloud data sets in the same coordinate system are obtained, and the different point cloud data sets in the same coordinate system are marked as: , where n=1, 2, 3, ..., N, N is a positive integer, and n is the number of the point cloud data set of different parts of the prefabricated box girder scanned by the 3D scanner. , k=1, 2, 3, ..., K, K is a positive integer, and k is the number of point cloud data in different point cloud data sets; Based on the ICP algorithm used to match two different point cloud data, the error between the point cloud data in different point cloud data sets is calculated by Euclidean distance, and the point cloud error threshold is set to obtain the point cloud data with a value greater than the point cloud error threshold in the error between the point cloud data in different point cloud data sets. The number of point cloud data with a value greater than the point cloud error threshold is obtained, and the number of point cloud data with a value greater than the point cloud error threshold is marked as: , where m is the number of different point cloud data sets, m=1, 2, 3, ..., M, M is a positive integer, M=N-1; The total number of point cloud data deleted during the point cloud data stitching process is obtained, and the total number of point cloud data deleted during the point cloud data stitching process is marked as: ,in, ; Calculate the point cloud matching error anomaly coefficient, the calculation formula is: ;in, is the point cloud matching error anomaly coefficient, is the number of point cloud data in different point cloud datasets.

[0011] In a preferred embodiment, the profile information of the prefabricated box girder includes: The profile information of precast box beams is expressed by section profile deviation coefficient and spacing deviation coefficient; The logic for obtaining the cross-sectional profile deviation coefficient is as follows: after the prefabricated box girder point cloud data is spliced, a three-dimensional point cloud model of the prefabricated box girder is obtained, point cloud data of different cross sections of the three-dimensional point cloud model of the prefabricated box girder are obtained, curve fitting is performed on the point cloud data of different cross sections, and two-dimensional cross-sectional curves of different cross sections are generated, and the two-dimensional cross-sectional curves of different cross sections are marked as: , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the selected different sections; Set the 2D section standard curves of different sections and mark them as: ; Calculate the distance deviation of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve by Euclidean distance, and mark the distance deviation of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve as: , where j=1, 2, 3, ..., J, J is a positive integer, and j is the number of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve; Calculate the total deviation of different sections using the formula: ;in, is the total deviation of the i-th section of the precast box girder.

[0012] Calculate the mean and standard deviation of the total deviation of different sections of precast box girders, and mark the mean and standard deviation of the total deviation of different sections of precast box girders as: and ;in, , ; Calculate the cross-sectional profile deviation coefficient using the following formula: ;in, is the cross-sectional profile deviation coefficient; The logic for obtaining the spacing deviation coefficient is as follows: after the prefabricated box girder point cloud data is spliced, the position of the special marking point in the prefabricated box girder three-dimensional point cloud model is obtained, and the position coordinates of the special marking point in the prefabricated box girder three-dimensional point cloud model are marked as: ,in, , q=1, 2, 3, ..., Q, Q is a positive integer, q is the number of the special marking point; Get the position coordinates of the preset special marking point and mark the position coordinates of the preset special marking point as: ,in, ; Calculate the spacing deviation coefficient using the following formula: ;in, is the spacing deviation coefficient.

[0013] In a preferred embodiment, constructing an acceptance evaluation model for prefabricated box girders includes: Through comprehensive analysis of the point cloud information and contour information of the prefabricated box girder, the point cloud matching error anomaly coefficient, the section contour deviation coefficient and the spacing deviation coefficient are weighted and calculated to construct the acceptance evaluation model of the prefabricated box girder and generate the acceptance evaluation coefficient. The calculation formula is: ;in, is the acceptance evaluation coefficient, , , They are the proportional coefficients of the point cloud matching error anomaly coefficient, the section profile deviation coefficient, and the spacing deviation coefficient. , , They are both greater than 0; Set the acceptance evaluation coefficient threshold, and compare the acceptance evaluation coefficient with the acceptance evaluation coefficient threshold. If the acceptance evaluation coefficient is greater than the acceptance evaluation coefficient threshold, a warning signal is generated, indicating that the prefabricated box girders currently being produced have large errors. If the acceptance evaluation coefficient is less than the acceptance evaluation coefficient threshold, no warning signal is generated, indicating that the prefabricated box girders currently being produced have high accuracy.

[0014] In a preferred embodiment, a railway box girder full-section data monitoring system based on a three-dimensional scanner includes a data acquisition module, a model splicing module, a data uploading module, and an acceptance evaluation module; The data acquisition module is used to scan the railway box girder multiple times through a 3D scanner to capture the point cloud data of the entire section; The model stitching module is used to restore the three-dimensional coordinates of the point cloud through the dense point cloud data from multiple perspectives using aerial triangulation, extract the key geometric points in the point cloud, use the algorithm to accurately determine the center position of these points, fit the plane part in the scanning area, and optimize the stitching error between the point cloud data; Data upload module, used to upload the complete point cloud data and special marking point information on the box girder to the intelligent measurement integration platform; The acceptance evaluation module is used to obtain the point cloud information and contour information of the prefabricated box girder from the point cloud model, calculate the deviation between the box girder model and the design standard, generate the acceptance evaluation coefficient, and provide a scientific basis for quality control.

[0015] Technical effects and advantages of the present invention: In the intelligent acceptance of the external dimensions of prefabricated box girders, the present invention uses a laser scanner to scan various surfaces of the box girder to obtain high-precision three-dimensional data, introduces a dense point cloud inverse modeling method, a point cloud aerial triangulation algorithm, and an improved RANSAC plane fitting algorithm, etc., to achieve accurate measurement of the cross-section of the railway box girder, and by collecting point cloud information and contour information of the prefabricated box girder, quantifies the significant deviation that may exist between the box girder model and the design standard. The present invention achieves fast, accurate, and non-contact measurement of the entire cross-section of the railway box girder, improves the automation and intelligence level of the measurement, and helps to improve the efficiency of the acceptance of the entire cross-section of the railway box girder. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 It is a schematic flow chart of a method for monitoring full-section data of a railway box girder based on a three-dimensional scanner according to the present invention; Figure 2 It is a schematic structural diagram of a railway box girder full-section data monitoring system based on a three-dimensional scanner according to the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1 Figure 1 A schematic flow chart of a method for monitoring full-section data of a railway box girder based on a three-dimensional scanner is provided, which specifically includes the following steps: S1: Collect data of the entire section of the railway box girder through a 3D scanner, and determine the data collection process of the entire section of the railway box girder by scanning each part of the box girder multiple times; S2: Process the collected full-section data of the railway box girder, and splice the point cloud data through the aerial triangulation calculation process based on dense point cloud data, accurate estimation of the center position of key points, and key plane fitting and optimization; S3: The operator uploads the splicing data and the coordinates of the special marking points to the intelligent measurement integrated platform system. The system will automatically measure the current model, automatically generate acceptance data and export the complete acceptance form; S4: Collect the point cloud information and contour information of the prefabricated box girder, build the acceptance evaluation model of the prefabricated box girder, and quantify the significant deviation between the box girder model and the design standard.

[0019] In step 1, in the intelligent acceptance of the outer dimensions of the prefabricated box girder, a laser scanner is used to scan each surface of the box girder to obtain high-precision three-dimensional data. In order to ensure the accuracy of the data, a multi-site scanning method is used to scan each part of the box girder multiple times to improve the integrity and accuracy of the data; The automation program can control the laser scanner to collect data and automatically process and analyze the collected data. The automation program includes the following functions: Data collection: The automation program can set the scanning parameters and paths, control the laser scanner to collect data, and during the collection process, the automation program can also monitor the integrity and accuracy of the data in real time to ensure the reliability of the data; Data processing: Automated programs can pre-process and analyze the collected data. For example, removing noise, smoothing data, calculating the dimensions of the box beam, etc. Through the processing of automated programs, the time and error of manual processing can be greatly reduced; Intelligent judgment: The automated program can use machine learning algorithms to make intelligent judgments on the processed data. Through training and learning of large amounts of data, the automated program can learn the qualified standards for the box girder dimensions and automatically determine whether the box girder dimensions meet the requirements.

[0020] Repeated measurement function: Since there may be some changes in the production process of prefabricated box girders, the data acquisition system needs to be able to be reused for multiple measurements and comparisons. The repeated measurement function can record the parameters and results of each measurement and generate a measurement report. By comparing the measurement results of different times, the changing trend of the box girder dimensions can be discovered, and corresponding measures can be taken for quality control.

[0021] For the rapid data collection of the entire section of a railway box girder, the scope of the collection is to comprehensively cover every detail of the box girder, that is, the outer shape, inner box, bottom surface and top surface can all be measured without blind spots. By disassembling and analyzing each step of the manual measurement process, and according to different measurement parameter requirements, the data collection process is reasonably divided into 4 parts, namely, beam end data collection, bottom web side data collection, beam interior data collection and top plate data collection, among which: In the data collection of the beam end, special marking points are set at the bottom bevel of the beam, the top of the beam and the center line of the support using standard parts, which are used as coordinate positioning points after later splicing. After setting the special marking points and the positioning marking balls for splicing, a non-contact 3D laser scanner is used to collect data at the middle of the beam end. In the data collection of the bottom web plate side, special marking points are set at the span line and the beam end using standard parts, which are used as coordinate positioning points after later splicing. After the marking points are set, a non-contact 3D laser scanner is used to collect web plate data at a position 6m away from the beam end on the beam side, and a non-contact 3D laser scanner is used to collect bottom plate data at the middle position of the beam side. In the data collection in the beam room, two positions close to the beam end and where the positioning marker ball placed at the beam end can be observed are selected as data collection points. At the same time, the non-contact 3D laser scanner is adjusted to ensure that there is no overexposure, and then the non-contact 3D laser scanner is used for data collection; In the top plate data collection, two positions on both sides close to the beam end where the positioning marker ball placed on the beam end can be observed are selected as data collection points. After the two data collection points are determined, a non-contact 3D laser scanner is used for data collection. The entire cross-section of the railway box girder is scanned by a non-contact 3D laser scanner, and the full cross-section data of the box girder is covered without blind spots through multiple scans. After completing the above data collection, the collected data is remotely sent back to the operator's computer via the Internet. The collected data is then spliced ​​and some special marking points are extracted for subsequent processing. The spliced ​​data is a more accurate 3D reconstructed model.

[0022] In the full-section data collection of railway box girders, the support center line and span line are marked on the side of the box girder, and the marking targets are fixed around the box girder to ensure the accuracy of the scanning data and the high precision of the subsequent splicing.

[0023] It should be noted that the support centerline and span line are the key reference lines in the box girder geometry, providing a clear reference for subsequent data calibration and splicing, and as the basis of the coordinate system, ensuring that the scanned point cloud data can be accurately mapped to a unified spatial coordinate; Marker targets are usually used as reference points for stitching data collected from multiple sites, ensuring that data from different scanning sites can be seamlessly stitched into a complete three-dimensional model through the target's location information. The target's position in space is clear and easy to identify, and it is the core input of the stitching algorithm. In addition, data collected from different sites may have deviations in the coordinate system. Targets can be used to unify these data into a global coordinate system.

[0024] In order to adapt to the full scanning of the outer plane of the box girder and reduce errors, one measuring station is selected for scanning at each beam end to collect the plane point cloud of the box girder end; stations are set up at 6m away from the beam end on both sides of the box girder to collect the side point cloud of the web and wing plate of the box girder end; 2 stations are set up at the bottom of the box girder to collect the point cloud of the bottom plate; 2 stations are set up inside the box girder to collect the point cloud of the box girder; 2 stations are set up on the top plate to collect the point cloud of the top plate. The splicing between the measuring stations is done by using target balls, and 3 target balls are placed on the diagonal of the box girder so that each Each station can observe at least 3 stationary target balls.

[0025] Point cloud acquisition and positioning technology for box girders with random spatial positions and uneven edges and corners. Using the characteristics of instrument recognition of object color, black and white targets are used to mark the position information into the point cloud. In order to reduce the workload of preliminary preparation, the principle of setting fewer targets is followed. In accordance with the principle of not setting targets unless necessary, 4 targets are set at each corner point of the bottom of the beam to solve the problem of no points at right angles caused by the rounded corners of the bottom surface of the box girder. The center lines of the horizontal and vertical supports of the box girder are marked with targets to solve the problem that the support holes cannot be scanned from the bottom.

[0026] The data measured by the scanner is copied to the computer and then imported into the SCENE platform software. The sphere placed at the scanning site is identified and used as the base point to stitch the collected images, so that the images scanned at each site are stitched to form a complete box girder model. In order to further improve the precision of cluster stitching, the targets with stitching errors greater than the preset value are processed, and the base points with incorrect identification are processed by manual deletion and re-stitching to reduce the error. After the stitching is completed, in the 3D view, the manipulator is used to move, rotate and scale the image in a simple way, crop the redundant images and delete the invisible points to reduce the point cloud volume and improve the smoothness of operation, and then create the project point cloud and export it. Using the recognition function of the software, the black and white targets marked on the box girder can be marked, and the coordinates of 22 marking points can be obtained. Finally, the exported project point cloud and the coordinates of the marking points are input into the box girder 3D measurement system platform, and the data is processed by the platform to finally output the original record report of the box girder appearance inspection.

[0027] In step 2, the collected data is further processed and analyzed to determine whether the dimensions of the prefabricated box beam meet the requirements, including the following functions: Data cleaning: remove noise and outliers from collected data to ensure the accuracy of data analysis; Data transformation: transform and process the collected data to better reflect the dimensions of the prefabricated box beam. For example, the data can be smoothed and filtered. Feature extraction: Extract feature information related to the shape and size of the prefabricated box girder from the processed data. For example, the length, width, height, curvature and other features of the box girder can be extracted; Model construction: The extracted feature information is used to construct a model to predict whether the dimensions of the prefabricated box girder meet the requirements. Various machine learning algorithms can be used for model construction, such as support vector machines, neural networks, decision trees, etc.

[0028] The stitching of point cloud data mainly involves preprocessing the original point cloud data obtained from the 3D scanning device to improve the data quality and stitching accuracy. The preprocessing includes the following steps: Data denoising: Since the scanning process may be affected by various factors, such as equipment errors, ambient lighting, etc., there may be noise points in the acquired point cloud data. Through data denoising, these noise points can be removed to improve data quality. Data smoothing: Smoothing the point cloud data to reduce sharp parts and abrupt points in the data, making the data smoother and more continuous. Data simplification: Since the amount of point cloud data may be very large, direct stitching may consume a lot of computing resources and time. Therefore, it is necessary to simplify the point cloud data to reduce the amount of data and improve the stitching efficiency.

[0029] Determine the stitching benchmark stage: Select a stable, high-precision point cloud as the benchmark for stitching. You can choose the point cloud where the public target is located as the benchmark, or you can choose other point clouds with good stability as the benchmark. The principle of selecting the benchmark is to ensure the accuracy and stability of the stitching.

[0030] Choosing appropriate registration methods and feature extraction and matching algorithms can improve the accuracy and efficiency of stitching. Common registration methods include ICP algorithm, NDT algorithm, transformation estimation method, etc. Among them, ICP algorithm is one of the most commonly used point cloud registration algorithms. It can quickly converge to the optimal solution and is suitable for large-scale point cloud processing.

[0031] In the registration process, it is necessary to estimate the rigid body transformation of the two point clouds, that is, to find a transformation matrix so that the two point clouds can correspond to each other. Rigid body transformation estimation can be solved by algorithms such as the least squares method. The two point clouds can be spliced ​​by the estimated rigid body transformation matrix.

[0032] After the stitching is completed, the stitching results need to be evaluated and corrected. The quality evaluation mainly checks the accuracy of the stitching results, including whether there are obvious deviations and discontinuities. If problems are found, corrections need to be made. The correction method can be based on manual operation or automatic repair.

[0033] The calculation scheme of point cloud data includes data preprocessing, key point extraction, feature description, point cloud registration, 3D reconstruction and data visualization, among which: Data preprocessing: mainly involves cleaning and filtering the acquired point cloud data to eliminate noise and irrelevant data. This step usually includes data filtering and data reduction. Data filtering can use methods such as smoothing filtering and median filtering to eliminate noise and outliers. Data reduction can use methods such as Euclidean distance and normal distance to reduce the amount of data and improve calculation efficiency; Key point extraction: To extract key points from point cloud data, methods similar to SIFT and SURF in 2D image processing can be used. These methods can extract local features from point clouds, such as curvature, normal direction, surface material, etc. In addition, there are some algorithms specifically for point cloud data, such as ISS3D, Harris3D, etc., which can extract key points from point clouds.

[0034] Feature description: For the extracted key points, feature description is required. Commonly used feature description algorithms include PFH, FPFH, etc. These algorithms can calculate the distribution of points around the key points, thereby obtaining the feature description of the key points.

[0035] Point cloud registration: Point cloud registration is the process of aligning multiple point cloud data. Common point cloud registration algorithms include ICP (Iterative Closest Point) and its improved algorithms, NDT (Normal Distribution Transform) and its improved algorithms. These algorithms can find the best transformation matrix between two point clouds so that the corresponding points between them reach the minimum error.

[0036] 3D reconstruction: 3D reconstruction is the process of generating a 3D model based on point cloud data. Commonly used 3D reconstruction algorithms include point cloud triangulation and voxel meshing. These algorithms can convert point cloud data into a 3D model for subsequent analysis and processing.

[0037] Data visualization: Data visualization is the process of visualizing the processed point cloud data. Common visualization methods include point cloud direct drawing, voxel grid visualization, etc. These methods can convert the processed point cloud data into images or models for observation and analysis.

[0038] According to the point cloud data obtained by the non-contact 3D laser scanner, the coordinate values ​​of the point cloud data are all relative position coordinates relative to the scanner. When performing aerial triangulation calculation, the absolute position coordinate system needs to be redefined. According to the existing aerial triangulation calculation methods, the calculation process is redesigned to minimize or eliminate the errors caused by aerial triangulation calculation. The calculation process can be roughly divided into four parts, namely fitting the maximum plane of the beam end and obtaining the plane equation, obtaining the angle between the plane normal vector and the normal vector of the absolute coordinate system, constructing a 3D rotation matrix, transposing the point cloud data, and determining the center point of the point cloud model, including: Select the target point at the bottom of the beam, the target point on the support line and the 200 nearest points around it, and use the RANSAC plane segmentation method to find the maximum plane equation based on the target point at the bottom of the beam, the target point on the support line and the 200 nearest points around it; Obtain the maximum plane and the normal vector of the absolute coordinate system, construct a three-dimensional rotation matrix, and calculate the plane angle; Determine the initial center point of the model, then build a reference coordinate system based on the coordinate system where the initial center point is located, and finally transpose the entire point cloud data to the reference coordinate system.

[0039] Through the above steps, the point cloud model is accurately converted to the absolute position coordinate system, and the coordinate zero point is the midpoint of the line connecting the two beam bottom bevel marking points at the beam end. Then, according to the measurement requirements, the point cluster at the required position is selected at a fixed point, and the measurement average value is obtained more accurately.

[0040] Specifically, in the point cloud processing stage: point cloud filtering, point cloud registration, and point cloud segmentation are used to perform preliminary processing on point cloud data. Point cloud filtering can remove noise and invalid points to improve data quality; point cloud registration can align multiple point cloud data to obtain more comprehensive and accurate information; point cloud segmentation can divide point clouds into different objects or parts for subsequent processing and analysis; Feature extraction stage: extract key points from point cloud data and describe their features. The extracted features include edges, corner points, normal vectors, etc. These features will be used to reconstruct and calculate geometric information. Accurate estimation of the center position: To achieve high-precision reproduction and calculation, it is necessary to estimate the center position of the key points. The fitting circle model is used to accurately estimate the center position. The fitting circle model uses the least squares method to calculate the best center position. Plane fitting and optimization stage: For situations where key planes need to be fitted, the least squares method, RANSAC and other optimization algorithms are used to fit the plane model, and the parameters of the plane model are optimized by minimizing the distance from the point to the plane to obtain the best plane fitting effect. Data processing and algorithm optimization stage: In order to improve processing efficiency and accuracy, innovative data processing methods and algorithm optimization strategies are adopted. GPU is used to accelerate computing and perform incremental processing on large-scale data; deep learning and other methods are used to extract features and perform model fitting.

[0041] Example 2 Example 1: The prefabricated box girder is scanned by using a three-dimensional scanner to obtain point cloud data of the prefabricated box girder, and the point cloud data of the prefabricated box girder is spliced ​​to generate a model of the prefabricated box girder. Example 2: The model of the prefabricated box girder is automatically measured, and data is collected in the process of generating the model of the prefabricated box girder to determine the acceptance result of the prefabricated box girder.

[0042] In step 3, after the data is spliced, the operator uploads the spliced ​​data and the coordinates of the special marking points to the intelligent measurement integrated platform system. The system will automatically measure the current model, automatically generate acceptance data and export the complete acceptance form. At the same time, the system supports historical data query management and operator account management, and provides convenient and effective interfaces and tools for accessing data information. In order to meet the requirements of scientific organization and storage of data, efficient acquisition and maintenance of data, the intelligent measurement integrated platform system includes: Model optimization and compression: Use advanced model optimization techniques, such as pruning, quantization, and distillation, to reduce the size of the model and increase the speed of inference. Use distributed learning methods to split the model into multiple parts, and train and deploy them in a distributed manner to reduce the transmission burden. Use parallel computing technology to give full play to the performance of multi-core processors and GPUs to increase the computing speed of the system. Build a distributed system and distribute tasks to multiple computing nodes to improve the overall performance of the system. Incremental data transmission and processing: Adopt incremental data transmission method, only transmit the changed data to reduce the transmission volume. Implement block processing of LAS files, only load and process the part of data currently needed, and improve file processing efficiency. Use efficient data storage engine, such as distributed file system or database, to improve data reading and storage speed. Introduce index technology to speed up the retrieval and query operations of large data such as LAS files. User interface optimization: Design a user-friendly user interface, provide intuitive data display and operation interface, and facilitate users to understand and control measurement data in real time. You can use charts, animations, reports, etc. to visualize complex data information. Use intuitive and concise user interaction design to reduce user operation steps. Use visualization technology to present complex measurement results in a graphical way, making it easier for users to understand. Introduce automated processes to reduce user manual operations and improve the automation level of the system.

[0043] Through incremental data transmission and processing innovations, the system only transmits changed data, reducing the amount of transmission and improving data transmission efficiency. Automated process and intelligent recommendation innovations introduce automated processes and intelligent recommendation mechanisms to reduce user manual operations and improve the intelligence of the system. Model optimization and compression technology innovations use advanced model optimization technology to reduce model size and increase inference speed, solving the problem of slow transmission of overly large models, improving system performance and reducing the demand for computing resources.

[0044] In step 4, in the process of processing the point cloud data of the prefabricated box girder, the ICP algorithm is used to match different point clouds. To ensure the matching of different point cloud data, the abnormal point cloud data greater than the set distance threshold is deleted to determine the point cloud information of the prefabricated box girder. After the point cloud data is spliced, the contour information of the prefabricated box girder is determined according to the model of the prefabricated box girder. The point cloud information of the prefabricated box girder is represented by the point cloud matching error anomaly coefficient, and the contour information of the prefabricated box girder is represented by the cross-sectional profile deviation coefficient and the spacing deviation coefficient.

[0045] The logic for obtaining the point cloud matching error anomaly coefficient is as follows: different point cloud data sets in the same coordinate system are obtained, and the different point cloud data sets in the same coordinate system are marked as: , where n=1, 2, 3, ..., N, N is a positive integer, and n is the number of the point cloud data set of different parts of the prefabricated box girder scanned by the 3D scanner. , k=1, 2, 3, ..., K, K is a positive integer, and k is the number of point cloud data in different point cloud data sets; Based on the ICP algorithm used to match two different point cloud data, the error between the point cloud data in different point cloud data sets is calculated by Euclidean distance, and the point cloud error threshold is set to obtain the point cloud data with a value greater than the point cloud error threshold in the error between the point cloud data in different point cloud data sets. The number of point cloud data with a value greater than the point cloud error threshold is obtained, and the number of point cloud data with a value greater than the point cloud error threshold is marked as: , where m is the number of different point cloud data sets, m=1, 2, 3, ..., M, M is a positive integer, M=N-1; The total number of point cloud data deleted during the point cloud data stitching process is obtained, and the total number of point cloud data deleted during the point cloud data stitching process is marked as: ,in, ; It should be noted that first a reference point cloud is selected (usually the first point cloud collected), and then matched with the second point cloud. After the matching is completed, the second point cloud is matched with the third point cloud, and so on. Once all point clouds are aligned through iterative optimization and registration, they are fused together to form a complete 3D model. During the matching process, if the errors of some points are large (for example, exceeding the preset threshold), these points may be considered as matching error points and may be deleted or eliminated. The point cloud error threshold is set by professional staff and will not be elaborated here.

[0046] Calculate the point cloud matching error anomaly coefficient, the calculation formula is: ;in, is the point cloud matching error anomaly coefficient, is the number of point cloud data in different point cloud datasets.

[0047] It can be seen from the formula that the larger the point cloud matching error anomaly coefficient is, the larger the proportion of point cloud data with abnormal points or large errors is in the process of point cloud data splicing, which means that the quality of splicing may be poor, more point cloud data is deleted, and there may be large errors in the production process of prefabricated box girders.

[0048] Among them, the acceptance of prefabricated box girders requires accurate measurement data to ensure that they meet the design and quality standards. When using a 3D scanner to obtain point cloud data, the point cloud data of multiple scanning positions need to be spliced ​​together to form a complete 3D model. If there is a large point cloud matching error in the splicing process, the spliced ​​box girder model may have problems such as misalignment, distortion or other geometric inconsistencies. The point cloud matching error anomaly coefficient can help evaluate the quality and measurement accuracy of the splicing process. If the coefficient is too large, it means that the splicing error is large, which may cause the generated model to fail to accurately reflect the actual size and shape of the prefabricated box girder, thereby affecting the acceptance result; There may be error points or abnormal points in the point cloud data due to different scanning angles, scanning equipment or scanning environments. Abnormal points refer to points that do not match the actual structure and are usually identified and deleted during the splicing process. If the point cloud matching error abnormality coefficient is high, it means that the proportion of abnormal points is large, which may indicate quality control problems in the production process, such as irregular surface or defects of the box beam. By monitoring this coefficient, these potential problems can be effectively discovered and the production process can be further improved or corrected. The 3D model of prefabricated box girders is the basis for subsequent structural analysis, load-bearing capacity assessment and practical application. If a large number of errors or abnormal points appear during the splicing process, the accuracy and reliability of the model will be affected, which will in turn affect the structural safety analysis. The point cloud matching error anomaly coefficient can quantify the splicing error and help determine whether it is necessary to further optimize the splicing process or clean the data, thereby ensuring the accuracy of the 3D model and ultimately ensuring that the quality of the box girder meets the standards.

[0049] The logic for obtaining the cross-sectional profile deviation coefficient is as follows: after the prefabricated box girder point cloud data is spliced, a three-dimensional point cloud model of the prefabricated box girder is obtained, point cloud data of different cross sections of the three-dimensional point cloud model of the prefabricated box girder are obtained, curve fitting is performed on the point cloud data of different cross sections, and two-dimensional cross-sectional curves of different cross sections are generated, and the two-dimensional cross-sectional curves of different cross sections are marked as: , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the selected different sections; It should be noted that in order to extract the cross-section of the box girder, a set of point cloud data is cut out at a predetermined cross-sectional position, and the point cloud data is extracted on a specified plane by "intercepting" the three-dimensional point cloud data, which means finding the intersection of the plane and the point cloud data through mathematical methods (such as normal vector calculation) to obtain the point cloud data on the plane, including selecting a plane to intersect the point cloud, obtaining the points on the plane, determining the direction of the cross-section based on the calculation of the normal vector, and extracting the point cloud parallel to the direction. Methods for curve fitting of point cloud data of different cross-sections include least squares fitting and spline interpolation, etc. Different types of curve models are selected to fit the data according to actual conditions, such as circular, elliptical or polynomial curves, etc., which will not be elaborated here.

[0050] Set the 2D section standard curves of different sections and mark them as: ; Calculate the distance deviation of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve by Euclidean distance, and mark the distance deviation of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve as: , where j=1, 2, 3, ..., J, J is a positive integer, and j is the number of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve; It should be noted that the two-dimensional section curves of different sections are the actual sections obtained by fitting the point cloud data. This section curve is fitted by the point cloud of a certain section in the scanning data, and represents the actual shape of the box girder at this section. The two-dimensional section standard curves of different sections are pre-defined ideal section shapes, which are usually derived based on design requirements or standard specifications. The measurement points refer to specific points with spatial coordinates extracted from the point cloud data. By comparing the measurement points of the two-dimensional section standard curve and the two-dimensional section curve, the deviation of the section can be quantified.

[0051] Calculate the total deviation of different sections using the formula: ;in, is the total deviation of the i-th section of the precast box girder.

[0052] Calculate the mean and standard deviation of the total deviation of different sections of precast box girders, and mark the mean and standard deviation of the total deviation of different sections of precast box girders as: and ;in, , ; Calculate the cross-sectional profile deviation coefficient using the following formula: ;in, is the cross-sectional profile deviation coefficient.

[0053] It can be seen from the formula that the larger the cross-sectional profile deviation coefficient is, the different deviation amplitudes of different cross-sections of the prefabricated box girder exist, indicating that there may be large errors in the production process of the prefabricated box girder.

[0054] Specifically, if the cross-sectional profile deviation coefficient is large, it may mean that there are large geometric errors in the production process, especially in the production process of prefabricated box girders. This error may be caused by factors such as mold deviation, material unevenness, temperature change, etc., which leads to changes in the shape of the box girder; The cross-sectional profile deviation coefficient may also be affected by the quality of the point cloud data. If the point cloud data has a large error during the splicing process, or the scanning accuracy is not high, it may lead to a large error in the cross-sectional fitting, which in turn leads to a large deviation coefficient; It may be necessary to strengthen monitoring and adjustments in the production process to ensure that the geometry of the box beam better meets the design requirements. To do this, it may be necessary to adjust the mold, improve the production process, or use more precise technology in the measurement and data processing stage.

[0055] The logic for obtaining the spacing deviation coefficient is as follows: after the prefabricated box girder point cloud data is spliced, the position of the special marking point in the prefabricated box girder three-dimensional point cloud model is obtained, and the position coordinates of the special marking point in the prefabricated box girder three-dimensional point cloud model are marked as: ,in, , q=1, 2, 3, ..., Q, Q is a positive integer, q is the number of the special marking point; Get the position coordinates of the preset special marking point and mark the position coordinates of the preset special marking point as: ,in, ; It should be noted that special markers are markers with known positions placed on the surface of the box girder or at key locations, such as black and white targets, reflective balls or other types of positioning markers. When performing 3D scanning, special markers can help accurately determine the spatial position and posture of point cloud data. When data from multiple scanning sites need to be spliced, markers can help align different point cloud data to ensure that the overall model after splicing is accurate.

[0056] Calculate the spacing deviation coefficient using the following formula: ;in, is the spacing deviation coefficient.

[0057] It can be seen from the formula that the larger the spacing deviation coefficient is, the larger the spacing deviation between the special marking points in the prefabricated box girder model is, indicating that there may be large errors in the production process of the prefabricated box girder.

[0058] It should be noted that there is a significant difference in the distance between the actual position of the marking point and the designed position, indicating that there may be a positioning deviation in the setting of the marking point, or errors caused by equipment accuracy or environmental interference during the measurement process, reflecting that the actual size of the prefabricated box girder deviates from the design requirements. If the spacing deviation coefficient continues to increase in multiple measurements, it means that there may be cumulative deviations in the production process of the prefabricated box girder, and the production process or equipment may need to be inspected and adjusted.

[0059] Through comprehensive analysis of the point cloud information and contour information of the prefabricated box girder, the point cloud matching error anomaly coefficient, the section contour deviation coefficient and the spacing deviation coefficient are weighted and calculated to construct the acceptance evaluation model of the prefabricated box girder and generate the acceptance evaluation coefficient. The calculation formula is: ;in, is the acceptance evaluation coefficient, , , They are the proportional coefficients of the point cloud matching error anomaly coefficient, the section profile deviation coefficient, and the spacing deviation coefficient. , , Both are greater than 0.

[0060] It can be seen from the formula that the larger the proportional coefficient of the point cloud matching error anomaly coefficient, the cross-sectional profile deviation coefficient, and the spacing deviation coefficient, the larger the acceptance evaluation coefficient. This indicates that the model of the prefabricated box girder determined by a 3D scanner indicates that there may be significant deviations between the box girder model and the design standard, which affects the evaluation of the box girder quality.

[0061] Set the acceptance evaluation coefficient threshold, and compare the acceptance evaluation coefficient with the acceptance evaluation coefficient threshold. If the acceptance evaluation coefficient is greater than the acceptance evaluation coefficient threshold, a warning signal is generated, indicating that the prefabricated box girders currently being produced have large errors. If the acceptance evaluation coefficient is less than the acceptance evaluation coefficient threshold, no warning signal is generated, indicating that the prefabricated box girders currently being produced have high accuracy.

[0062] In the intelligent acceptance of the external dimensions of prefabricated box girders, the present invention uses a laser scanner to scan various surfaces of the box girder to obtain high-precision three-dimensional data, introduces a dense point cloud inverse modeling method, a point cloud aerial triangulation algorithm, and an improved RANSAC plane fitting algorithm, etc., to achieve accurate measurement of the cross-section of the railway box girder, and by collecting point cloud information and contour information of the prefabricated box girder, quantifies the significant deviation that may exist between the box girder model and the design standard. The present invention achieves fast, accurate, and non-contact measurement of the entire cross-section of the railway box girder, improves the automation and intelligence level of the measurement, and helps to improve the efficiency of the acceptance of the entire cross-section of the railway box girder.

[0063] Example 3 Figure 2The present invention provides a schematic structural diagram of a railway box girder full-section data monitoring system based on a three-dimensional scanner, which specifically includes a data acquisition module, a model splicing module, a data upload module, and an acceptance evaluation module; The data acquisition module is used to scan the railway box girder multiple times through a 3D scanner to capture the point cloud data of the entire section; The model stitching module is used to restore the three-dimensional coordinates of the point cloud through the dense point cloud data from multiple perspectives using aerial triangulation, extract the key geometric points in the point cloud, use the algorithm to accurately determine the center position of these points, fit the plane part in the scanning area, and optimize the stitching error between the point cloud data; Data upload module, used to upload the complete point cloud data and special marking point information on the box girder to the intelligent measurement integration platform; The acceptance evaluation module is used to obtain the point cloud information and contour information of the prefabricated box girder from the point cloud model, calculate the deviation between the box girder model and the design standard, generate the acceptance evaluation coefficient, and provide a scientific basis for quality control.

[0064] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0065] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0066] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0067] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0068] Those skilled in the art can 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.

[0069] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0070] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0071] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A railway box girder full-section data monitoring method based on a three-dimensional scanner, characterized in that: The specific steps include: S1: Collect data of the entire section of the railway box girder through a 3D scanner, and determine the data collection process of the entire section of the railway box girder by scanning each part of the box girder multiple times; S2: Process the collected full-section data of the railway box girder, and splice the point cloud data through the aerial triangulation calculation process based on dense point cloud data, accurate estimation of the center position of key points, and key plane fitting and optimization; S3: The operator uploads the splicing data and the coordinates of the special marking points to the intelligent measurement integrated platform system. The system will automatically measure the current model, automatically generate acceptance data and export the complete acceptance form; S4: Collect the point cloud information and contour information of the prefabricated box girder, build the acceptance evaluation model of the prefabricated box girder, and quantify the significant deviation between the box girder model and the design standard.

2. The method for monitoring the full cross-section data of a railway box girder based on a three-dimensional scanner according to claim 1 is characterized in that: The data collection process for determining the full section of a railway box girder includes: The data collection process is divided into beam end data collection, bottom web side data collection, beam interior data collection and top plate data collection, among which: In the data collection of the beam end, special marking points are set at the bottom bevel of the beam, the top of the beam and the center line of the support using standard parts, which are used as coordinate positioning points after later splicing. After setting the special marking points and the positioning marking balls for splicing, a non-contact 3D laser scanner is used to collect data at the middle of the beam end. In the data collection of the bottom web plate side, special marking points are set at the span line and the beam end using standard parts, which are used as coordinate positioning points after later splicing. After the marking points are set, a non-contact 3D laser scanner is used to collect web plate data at a position 6m away from the beam end on the beam side, and a non-contact 3D laser scanner is used to collect bottom plate data at the middle position of the beam side. In the data collection in the beam room, two positions close to the beam end and where the positioning marker ball placed at the beam end can be observed are selected as data collection points. At the same time, the non-contact 3D laser scanner is adjusted to ensure that there is no overexposure, and then the non-contact 3D laser scanner is used for data collection; In the top plate data collection, two positions on both sides close to the beam end and where the positioning marker balls placed on the beam end can be observed are selected as data collection points. After the two data collection points are determined, a non-contact 3D laser scanner is used for data collection.

3. The method for monitoring the full cross-section data of a railway box girder based on a three-dimensional scanner according to claim 2 is characterized in that: The aerotriangulation process based on dense point cloud data includes: Redefine the absolute position coordinate system, organically combine it with the current aerial triangulation calculation method, and redesign the calculation process to minimize or eliminate the errors caused by aerial triangulation calculation. This includes fitting the maximum plane at the beam end and obtaining the plane equation, obtaining the angle between the plane normal vector and the normal vector of the absolute coordinate system, constructing a three-dimensional rotation matrix, transposing the point cloud data, and determining the center point of the point cloud model.

4. The method for monitoring the full cross-section data of a railway box girder based on a three-dimensional scanner according to claim 3 is characterized in that: Accurate estimation of key point center position and key plane fitting and optimization, including: The fitting circle model is used to accurately estimate the center position of the circle, and the least square method is used to calculate the optimal center position of the circle. The parameters of the plane model are optimized by minimizing the distance from the point to the plane to obtain the best plane fitting effect.

5. The method for monitoring the full cross-section data of a railway box girder based on a three-dimensional scanner according to claim 4 is characterized in that: The operator uploads the stitching data and the coordinates of special marking points to the intelligent measurement integrated platform system, including: The intelligent measurement integrated platform system adopts advanced model optimization technology to reduce the model size and improve the reasoning speed. It uses distributed learning methods to divide the model into multiple parts to reduce the transmission burden. It uses parallel computing technology to give full play to the performance of multi-core processors and GPUs to improve the system computing speed. By building a distributed system, tasks are distributed to multiple computing nodes. Adopt incremental data transmission method, only transmit the changed data, realize block processing of LAS files, only load and process the part of data currently needed, improve file processing efficiency, use distributed file system or database and introduce index technology to speed up the retrieval and query operations of large data such as LAS files.

6. The method for monitoring the full cross-section data of a railway box girder based on a three-dimensional scanner according to claim 5, characterized in that: Point cloud information of precast box beam, including: The point cloud information of the prefabricated box girder is represented by the point cloud matching error anomaly coefficient; The logic for obtaining the point cloud matching error anomaly coefficient is as follows: different point cloud data sets in the same coordinate system are obtained, and the different point cloud data sets in the same coordinate system are marked as: , where n=1, 2, 3, ..., N, N is a positive integer, and n is the number of the point cloud data set of different parts of the prefabricated box girder scanned by the 3D scanner. , k=1, 2, 3, ..., K, K is a positive integer, and k is the number of point cloud data in different point cloud data sets; Based on the ICP algorithm used to match two different point cloud data, the error between the point cloud data in different point cloud data sets is calculated by Euclidean distance, and the point cloud error threshold is set to obtain the point cloud data with a value greater than the point cloud error threshold in the error between the point cloud data in different point cloud data sets. The number of point cloud data with a value greater than the point cloud error threshold is obtained, and the number of point cloud data with a value greater than the point cloud error threshold is marked as: , where m is the number of different point cloud data sets, m=1, 2, 3, ..., M, M is a positive integer, M=N-1; The total number of point cloud data deleted during the point cloud data stitching process is obtained, and the total number of point cloud data deleted during the point cloud data stitching process is marked as: ,in, ; Calculate the point cloud matching error anomaly coefficient, the calculation formula is: ;in, is the point cloud matching error anomaly coefficient, is the number of point cloud data in different point cloud datasets.

7. The method for monitoring the full cross-section data of a railway box girder based on a three-dimensional scanner according to claim 6, characterized in that: Profile information of precast box beams, including: The profile information of precast box beams is expressed by section profile deviation coefficient and spacing deviation coefficient; The logic for obtaining the cross-sectional profile deviation coefficient is as follows: after the prefabricated box girder point cloud data is spliced, a three-dimensional point cloud model of the prefabricated box girder is obtained, point cloud data of different cross sections of the three-dimensional point cloud model of the prefabricated box girder are obtained, curve fitting is performed on the point cloud data of different cross sections, and two-dimensional cross-sectional curves of different cross sections are generated, and the two-dimensional cross-sectional curves of different cross sections are marked as: , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the selected different sections; Set the 2D section standard curves of different sections and mark them as: ; Calculate the distance deviation of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve by Euclidean distance, and mark the distance deviation of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve as: , where j=1, 2, 3, ..., J, J is a positive integer, and j is the number of each measuring point between the two-dimensional section curve of different sections and the two-dimensional section standard curve; Calculate the total deviation of different sections using the formula: ;in, is the total deviation of the i-th section of the precast box girder. Calculate the mean and standard deviation of the total deviation of different sections of precast box girders, and mark the mean and standard deviation of the total deviation of different sections of precast box girders as: and ;in, , ; Calculate the cross-sectional profile deviation coefficient using the following formula: ;in, is the cross-sectional profile deviation coefficient; The logic for obtaining the spacing deviation coefficient is as follows: after the prefabricated box girder point cloud data is spliced, the position of the special marking point in the prefabricated box girder three-dimensional point cloud model is obtained, and the position coordinates of the special marking point in the prefabricated box girder three-dimensional point cloud model are marked as: ,in, , q=1, 2, 3, ..., Q, Q is a positive integer, q is the number of the special marking point; Get the position coordinates of the preset special marking point and mark the position coordinates of the preset special marking point as: ,in, ; Calculate the spacing deviation coefficient using the following formula: ;in, is the spacing deviation coefficient.

8. The method for monitoring the full cross-section data of a railway box girder based on a three-dimensional scanner according to claim 7, characterized in that: Construct an acceptance evaluation model for precast box girders, including: Through comprehensive analysis of the point cloud information and contour information of the prefabricated box girder, the point cloud matching error anomaly coefficient, the section contour deviation coefficient and the spacing deviation coefficient are weighted and calculated to construct the acceptance evaluation model of the prefabricated box girder and generate the acceptance evaluation coefficient. The calculation formula is: ;in, is the acceptance evaluation coefficient, , , They are the proportional coefficients of the point cloud matching error anomaly coefficient, the section profile deviation coefficient, and the spacing deviation coefficient. , , They are both greater than 0; Set the acceptance evaluation coefficient threshold, and compare the acceptance evaluation coefficient with the acceptance evaluation coefficient threshold. If the acceptance evaluation coefficient is greater than the acceptance evaluation coefficient threshold, a warning signal is generated, indicating that the prefabricated box girders currently being produced have large errors. If the acceptance evaluation coefficient is less than the acceptance evaluation coefficient threshold, no warning signal is generated, indicating that the prefabricated box girders currently being produced have high accuracy.

9. A railway box girder full-section data monitoring system based on a three-dimensional scanner, used to implement the railway box girder full-section data monitoring method based on a three-dimensional scanner as claimed in any one of claims 1 to 8, characterized in that: It includes data collection module, model splicing module, data upload module and acceptance evaluation module; The data acquisition module is used to scan the railway box girder multiple times through a 3D scanner to capture the point cloud data of the entire section; The model stitching module is used to restore the three-dimensional coordinates of the point cloud through the dense point cloud data from multiple perspectives using aerial triangulation, extract the key geometric points in the point cloud, use the algorithm to accurately determine the center position of these points, fit the plane part in the scanning area, and optimize the stitching error between the point cloud data; Data upload module, used to upload the complete point cloud data and special marking point information on the box girder to the intelligent measurement integration platform; The acceptance evaluation module is used to obtain the point cloud information and contour information of the prefabricated box girder from the point cloud model, calculate the deviation between the box girder model and the design standard, generate the acceptance evaluation coefficient, and provide a scientific basis for quality control.

Images