Railway bridge construction progress management method, system and device based on point cloud data

Abstract

The application provides a railway bridge construction progress management method, system and device based on point cloud data. The method comprises the following steps: component division is performed on a railway bridge engineering entity, and the components are mapped to parts of a railway bridge design model; three-dimensional point cloud data is analyzed to perform feature matching and structure recognition, match component primitives, and perform parameter adjustment, and then a railway bridge construction progress model is obtained through three-dimensional reverse modeling in a three-dimensional point cloud space; the railway bridge design model, a railway bridge construction log and the railway bridge construction progress model are compared to check the progress; all component primitives and corresponding engineering quantities are input into a graph neural network based on Graphsage to construct a railway bridge construction progress deduction model, and then progress deduction is performed based on the railway bridge construction progress deduction model. The application can realize automatic and intelligent progress management of railway bridge construction based on collected three-dimensional point cloud data.

Description

Technical Field

[0001] This invention relates to the field of railway bridge construction progress management technology, and in particular to a method, system and device for railway bridge construction progress management based on point cloud data. Background Technology

[0002] Existing railway bridge construction progress management is based on a design model plus manual linking of construction logs. Bridge construction information is obtained through electronic construction logs, and bridge construction progress is displayed through Gantt charts and slope diagrams.

[0003] However, the construction logs are filled out manually and then uploaded to the information system. The authenticity of the data collection is greatly affected by the subjective factors of the people filling out the construction logs. Moreover, the level of intelligence in the overall progress management is not high, making it difficult to accurately reflect the progress of bridge construction. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, system and apparatus for railway bridge construction progress management based on point cloud data, so as to eliminate or improve one or more defects existing in the prior art.

[0005] One aspect of the present invention provides a method for railway bridge construction progress management based on point cloud data, the method comprising the following steps:

[0006] Based on the railway bridge design model, the railway bridge engineering entity is divided into components, and the components are mapped to the parts of the railway bridge design model; wherein, the most basic structure of the component division result is the component element;

[0007] Receive three-dimensional point cloud data of bridge construction progress collected by UAV airborne radar;

[0008] By referring to the railway bridge design model, the three-dimensional point cloud data is analyzed to perform feature matching and structure recognition. The component primitives are matched based on the results of feature matching and structure recognition. The corresponding structural parameters in the three-dimensional point cloud data are extracted based on the results of structure recognition. The matched component primitives are parametrically adjusted based on the structural parameters. Three-dimensional reverse modeling is performed in the three-dimensional point cloud space based on the parametrically adjusted component primitives to obtain the railway bridge construction progress model.

[0009] Obtain the railway bridge construction logs entered by technicians;

[0010] The railway bridge design model, railway bridge construction log, and railway bridge construction progress model were compared to verify the progress.

[0011] The engineering quantity corresponding to each component primitive is obtained, and the influencing factors and key dependencies of railway bridge construction are obtained. All component primitives and their corresponding engineering quantities are input into a graph neural network based on Graphsage to construct a railway bridge construction progress prediction model. Then, the progress is predicted based on the railway bridge construction progress prediction model. The influencing factors include the number of construction personnel, the number of construction machinery, material resources, construction processes and methods, and various weather conditions. The key dependencies are the necessary order of component primitives in the graph neural network based on Graphsage.

[0012] Railway bridge construction progress management is carried out based on the aforementioned railway bridge design model, railway bridge construction progress model, and railway bridge construction progress projection model.

[0013] In some embodiments of the present invention, after the step of comparing the railway bridge design model, the railway bridge construction log and the railway bridge construction progress model to verify the progress, the method further includes: visualizing the railway bridge construction progress model; and drawing a construction progress chart by combining the engineering quantity corresponding to each component element and the railway bridge construction progress model.

[0014] In some embodiments of the present invention, in the railway bridge construction progress simulation model, blank spaces are used to visualize the unfinished parts, and the blank spaces are filled in as the time axis progresses to show the progress.

[0015] In some embodiments of the present invention, the method further includes: comparing the railway bridge construction progress model and the railway bridge construction progress projection model, coloring out parts of the construction progress that are at risk of delay, and issuing warning information.

[0016] In some embodiments of the present invention, the critical dependencies include critical paths from pile foundations and caps to piers and caps, from piers and caps to supports, from supports to pad stones and blocks, and from pad stones and blocks to simply supported beams or continuous box girders.

[0017] In some embodiments of the present invention, the railway bridge design model, railway bridge construction progress model, and railway bridge construction progress deduction model are all BIM-based three-dimensional models; the components in the railway bridge design model, railway bridge construction progress model, and railway bridge construction progress deduction model all conform to EBS coding.

[0018] In some embodiments of the present invention, the parameterization adjustment of the successfully matched component primitives in combination with the structural parameters includes: on the basis of the original railway bridge construction progress model, replacing the structural parameters corresponding to the component primitives of the railway bridge construction progress model with modified structural parameters, thereby realizing the update of the railway bridge construction progress model.

[0019] Another aspect of the present invention provides a railway bridge construction progress management system based on point cloud data, the system comprising:

[0020] A railway bridge design model is used to divide the physical entity of a railway bridge into components and map the components to parts of the railway bridge design model; wherein, the most basic structure of the component division result is the component element;

[0021] A railway bridge construction progress model is used to manage the construction progress of railway bridges. By comparing the railway bridge design model with the three-dimensional point cloud data, feature matching and structural identification are performed. The component primitives are matched based on the results of feature matching and structural identification. Based on the results of structural identification, the corresponding structural parameters in the acquired three-dimensional point cloud data are extracted. The matched component primitives are parametrically adjusted based on the structural parameters. Based on the parametrically adjusted component primitives, three-dimensional reverse modeling is performed in the three-dimensional point cloud space to obtain the railway bridge construction progress model.

[0022] A railway bridge construction progress prediction model is used to predict the construction progress of railway bridges. This model obtains the engineering quantity corresponding to each component element, as well as the influencing factors and key dependencies of railway bridge construction. All component elements and their corresponding engineering quantities are input into a graph neural network based on Graphsage to construct the railway bridge construction progress prediction model. The model then predicts the construction progress based on this model. The influencing factors include various factors such as the number of construction workers, the number of construction machines, material resources, construction techniques, and weather conditions. The key dependencies are the necessary order of component elements in the graph neural network.

[0023] The progress verification module acquires the railway bridge construction logs input by technical personnel and compares the railway bridge design model, the railway bridge construction logs, and the railway bridge construction progress model to verify the progress. Based on the railway bridge design model, the railway bridge construction progress model, and the railway bridge construction progress projection model, the module manages the railway bridge construction progress.

[0024] Another aspect of the present invention provides an apparatus including a processor and a memory, the memory storing computer instructions, the processor executing the computer instructions stored in the memory, and the apparatus performing the steps of the method as described in any of the above embodiments when the computer instructions are executed by the processor.

[0025] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method as described in any of the above embodiments.

[0026] The railway bridge construction progress management method, system, and device based on point cloud data of the present invention can perform intelligent and automated supervision and management of railway bridge construction progress at the component level based on the collected three-dimensional point cloud data, and use graph neural network based on graphsage to establish a railway bridge construction progress prediction model to predict the subsequent construction progress, thereby providing comprehensive progress supervision and management.

[0027] Additional advantages, objects, and features of the invention will be set forth in part in the description which follows, and will also become apparent in part to those skilled in the art upon studying the description, or may be learned by practice of the invention. The objects and other advantages of the invention can be realized and obtained by means of the structures specifically pointed out in the description and drawings.

[0028] Those skilled in the art will understand that the objectives and advantages achievable with the present invention are not limited to those specifically described above, and that the above and other objectives achievable with the present invention will become clearer from the following detailed description. Attached Figure Description

[0029] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, are not intended to limit the scope of the invention. In the drawings:

[0030] Figure 1 This is a schematic diagram of a railway bridge construction progress management method based on point cloud data in one embodiment of the present invention.

[0031] Figure 2 This is a flowchart of reverse modeling based on point cloud data in one embodiment of the present invention.

[0032] Figure 3 This is a flowchart of a 4D-based construction progress management system according to one embodiment of the present invention.

[0033] Figure 4 This is a schematic diagram of a progress prediction method in one embodiment of the present invention.

[0034] Figure 5A Three views are created for the parameterization of component primitives in one embodiment of the present invention.

[0035] Figure 5B A three-dimensional view of the parameterized component elements in one embodiment of the present invention is provided.

[0036] Figure 6 This is a schematic diagram of the EBS encoding of a physical component in one embodiment of the present invention.

[0037] Figure 7 This is a schematic diagram of a point cloud data acquisition method in one embodiment of the present invention.

[0038] Figure 8 This is a schematic diagram of point cloud result annotation in one embodiment of the present invention. Detailed Implementation

[0039] 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 embodiments and accompanying drawings. Here, the illustrative embodiments and descriptions of this invention are used to explain the invention, but are not intended to limit the invention.

[0040] It should also be noted that, in order to avoid obscuring the invention with unnecessary details, only the structures and / or processing steps closely related to the solution according to the invention are shown in the accompanying drawings, while other details that are not closely related to the invention are omitted.

[0041] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, element, step, or component, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0042] It should also be noted that, unless otherwise specified, the term "connection" in this article can refer not only to a direct connection, but also to an indirect connection involving an intermediary.

[0043] In the following description, embodiments of the invention will be illustrated with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar parts, or the same or similar steps.

[0044] To overcome the limitations of existing railway bridge construction progress management methods, this invention provides a railway bridge construction progress management method, system, and device based on point cloud data. This method uses point cloud data collected by UAV airborne radar to reverse model and thus achieve progress supervision and management.

[0045] The purpose of this invention is to provide a component-level bridge construction progress management system based on BIM 3D point cloud data. By integrating bridge component-level classification management with BIM point cloud automatic recognition technology (or 3D point cloud intelligent recognition technology), the system automatically acquires bridge construction progress, accurately reflects project progress, fully leverages the value of the BIM model in the construction phase, and comprehensively tracks construction progress. This is of great significance for achieving intelligent bridge management and control, breaking away from the traditional management method based on design models and manual attachment of construction logs, and providing an automated progress verification and management method.

[0046] Point cloud data is a dataset in a coordinate system. Each point contains rich information, including 3D coordinates, color, classification value, intensity value, and time. Point clouds can be understood as reconstructing the real world using high-precision point cloud data. Large-scale point cloud data acquisition can be achieved using drones, allowing for the reconstruction of 3D models from 2D images. It is also possible to reverse engineer point clouds from 3D models, meaning that 3D point cloud data can be obtained by scanning rows and columns of a 3D model.

[0047] Figure 1 This is a schematic diagram of a railway bridge construction progress management method based on point cloud data in one embodiment of the present invention. The method includes the following steps:

[0048] Step S110: Based on the railway bridge design model, the railway bridge engineering entity is divided into components, and the components are mapped to the parts of the railway bridge design model; wherein, the most basic structure of the component division result is the component element.

[0049] Step S120: Receive three-dimensional point cloud data of bridge construction progress collected by UAV airborne radar.

[0050] In step S120, the UAV's onboard radar scans and identifies components at the railway bridge construction site, for example, Figure 7 This is a schematic diagram of a point cloud data acquisition method in one embodiment of the present invention, where the circled area represents the base of the bridge, and the lines represent the position of the bridge. Figure 8 This is a schematic diagram of point cloud results annotation in one embodiment of the present invention. The original image is in color, but it is processed into a grayscale image here. This means that different colors are used to mark the construction progress of the railway bridge. Components that have not been completed are displayed blankly, while components that have been completed are displayed in color, thereby visually presenting the current construction progress.

[0051] Step S130: Compare the railway bridge design model with the three-dimensional point cloud data to perform feature matching and structure recognition. Match component primitives based on the results of feature matching and structure recognition, and extract the corresponding structural parameters from the three-dimensional point cloud data based on the results of structure recognition. Perform parameterized adjustment on the successfully matched component primitives based on the structural parameters. Perform three-dimensional reverse modeling in the three-dimensional point cloud space based on the parameterized component primitives to obtain the railway bridge construction progress model.

[0052] The parameterization adjustment of the matched component primitives in step S130, which combines the structural parameters, includes: replacing the structural parameters corresponding to the component primitives of the railway bridge construction progress model with the modified structural parameters, thereby updating the railway bridge construction progress model.

[0053] Step S140: Obtain the railway bridge construction log entered by the technicians.

[0054] Step S150: Compare the railway bridge design model, railway bridge construction log, and railway bridge construction progress model to verify the progress.

[0055] Step S150 further includes: visualizing the railway bridge construction progress model; and drawing a construction progress chart by combining the engineering quantity corresponding to each component element and the railway bridge construction progress model.

[0056] Step S160: Obtain the engineering quantity corresponding to each component primitive, and obtain the influencing factors and key dependencies of railway bridge construction. Input all component primitives and their corresponding engineering quantities into a graph neural network based on Graphsage to construct a railway bridge construction progress prediction model. Then, based on the railway bridge construction progress prediction model, perform progress prediction. The influencing factors include the number of construction personnel, the number of construction machinery, material resources, construction processes and methods, and various weather conditions. The key dependencies are the necessary order of component primitives in the graph neural network based on Graphsage.

[0057] Step S160 further includes: visualizing the railway bridge construction progress simulation model, using blank space to visualize the unfinished parts, and filling the blank space to show the progress as the time axis progresses.

[0058] Furthermore, the railway bridge construction progress model and the railway bridge construction progress projection model are compared, and parts with a risk of construction delay are marked with a color warning and a warning message is issued.

[0059] The critical dependencies mentioned in step S160 are critical paths in a graph neural network based on graphsage, that is, the necessary sequential relationships that must exist in the construction process. For example, in one embodiment of the present invention, the critical dependencies include critical paths from pile foundation and pile cap to pier body and pier cap, from pier body and pier cap to support, from support to pad stone and pad block, and from pad stone and pad block to simply supported beam or continuous box girder.

[0060] Step S170: Based on the railway bridge design model, railway bridge construction progress model and railway bridge construction progress simulation model, perform railway bridge construction progress management.

[0061] Step S170 includes real-time monitoring of construction progress based on the railway bridge construction progress model, recording parameter errors between actual construction and design drawings based on the comparison between the railway bridge design model and the railway bridge construction model, predicting subsequent construction progress based on the railway bridge construction progress deduction model, and issuing early warnings when obvious abnormalities occur in the construction progress.

[0062] Figure 2 This is a flowchart of a reverse modeling process based on point cloud data in one embodiment of the present invention. First, point cloud data (2D / 3D) of the bridge construction progress is acquired using the airborne radar of a UAV. The bridge components are then divided according to the engineering entities, which are the targets to be constructed, such as bridges and tunnels. The divided components are mapped to the parts of the engineering entities. The point cloud data is identified, and the parameters are matched with the parameters of the components. Then, parametric component reverse modeling is performed based on the point cloud data to obtain a railway bridge construction progress model. Here, components are the breakdowns of the bridge, such as pier caps, pier bodies, and pier covers. Referring to the railway bridge design model, feature matching and structural identification are performed on the point cloud data scanned by the UAV. According to the component breakdown and combination, the structural parameters of the point cloud data are passed to the model. The parameterized adjustments are made to the successfully matched component primitives, and 3D primitive modeling is reconstructed in the point cloud space, ultimately achieving 3D reverse modeling.

[0063] Figure 3 This is a flowchart of a 4D-based construction progress management system according to one embodiment of the present invention. "4D-based" means that the visualization management of the three-dimensional model includes a time dimension. First, the progress is checked by combining the design model (i.e., the railway bridge design model), construction logs, and a railway bridge construction progress model built based on a 3D point cloud. The railway bridge construction progress model is a BIM model. Then, a railway bridge construction progress projection model is constructed using a graph neural network based on Graphsage to project the bridge construction progress. The progress of the railway bridge construction progress model built based on the 3D point cloud is checked, and the projection determines whether the progress is delayed. If a delay exists, an early warning is issued.

[0064] Figure 4 This is a schematic diagram of a progress prediction method in one embodiment of the present invention. Progress prediction requires obtaining the influencing factors and key dependencies of railway bridge construction. The influencing factors include various factors such as the number of construction workers, the number of construction machines, material resources, construction processes and methods, and weather conditions. The key dependencies are the necessary order of component primitives in a graph neural network based on graphsage. Figure 4The paper shows a key dependency as "pile foundation and abutment → pier body and pier cap → bearing → pad stone and pad block → simply supported beam or continuous box girder". All component primitives and corresponding engineering quantities are input into a graph neural network based on Graphsage. The railway bridge construction progress prediction model is constructed by combining the influencing factors and key dependencies. Then, based on the railway bridge construction progress prediction model, the progress is predicted to determine whether the current construction progress is lagging behind.

[0065] In a specific embodiment of the present invention, the 4D-based construction progress management process is as follows:

[0066] (1) Based on the progress data collection time, the BIM design model + construction log and the BIM model generated by point cloud reverse modeling are cross-checked to provide a visual display for the construction unit to manage the progress.

[0067] (2) The bridge construction progress was simulated using the graph neural network based on Graphsage, and the weight of the progress influencing factors was adjusted in combination with the actual project influencing factors. Then, the BIM model was used for three-dimensional progress simulation.

[0068] (3) The three-dimensional parts in the simulation model are represented by blanks. As the time axis moves, the progress of the three-dimensional parts is shown by filling in the blanks.

[0069] (4) Compare the railway bridge construction progress model generated by the three-dimensional point cloud with the railway bridge construction progress projection, color-code warnings for areas where there is a risk of construction delay, and issue warning information.

[0070] The graph neural network-based progress prediction model used in this invention addresses the issue of varying impact lengths of personnel, machinery, materials, environment, and construction methods on construction procedures. Considering the chain-dependent nature of multiple procedures in bridge construction, the invention designs a logical structure for bridge engineering progress prediction based on the graph neural network algorithm. It refines the core algorithms' neighbor sampling and feature aggregation processes to achieve construction progress prediction based on multiple influencing factors.

[0071] Figure 5A To establish three views for the parameterization of component primitives in one embodiment of the present invention, Figure 5B This invention provides a parameterized 3D model of component primitives in one embodiment. For a railway bridge design model, each component possesses a fixed number and type of parameters. Therefore, in step S130, which analyzes the 3D point cloud data for feature matching and structural identification, and combines the results of feature matching and structural identification to match component primitives, only a certain number of parameters need to be matched.

[0072] Similarly, by identifying structural components based on 3D point cloud data and adjusting the parameters of existing railway bridge design models, a railway bridge construction progress model can be obtained through reverse engineering. In simpler terms...

[0073] This involves breaking down the bridge into individual components, parameterizing each component's primitives, and quickly generating a solid model by inputting its dimensions and parameters.

[0074] In the above embodiments of the invention, the railway bridge design model, the railway bridge construction schedule model, and the railway bridge construction...

[0075] All progress simulation models are BIM-based 3D models, and the components in the railway bridge design model, railway bridge construction progress model, and railway bridge construction progress simulation model all conform to EBS coding. Figure 6 This is an embodiment of the present invention.

[0076] A schematic diagram of the EBS coding of a body component. Figure 6 The first column represents the different components of the engineering entity (such as a bridge); the second column represents the EBS code for different components. Taking the pier body and pier cap component codes as an example, the coding information in front of the pier in the platform EBS is retained, the raw material codes under the pier in the EBS are removed, and the component information of the pier body and pier cap is added to form a unique component code that identifies the pier body and pier cap; the third column is a status record on the code for whether different components have been completed.

[0077] 5. The railway bridge construction progress management method based on point cloud data provided by this invention breaks through the traditional method based on design model +

[0078] The manual construction log management method employs automated identification and reverse modeling based on BIM 3D point cloud data to verify the actual project progress. It digitally displays real-world scene information in a vivid 3D BIM model, achieving a dynamic digital twin representation of the bridge project's progress. Through 4D bridge progress simulation and display, it more intuitively and vividly expresses...

[0079] Bridge construction follows a time-lapse schedule, and by integrating design models, point cloud models, and simulation models, it achieves pre-construction early warning, in-process verification, and comprehensive dynamic automated control of bridge construction progress. Ultimately, it realizes automated and intelligent progress management of railway bridge construction based on collected 3D point cloud data.

[0080] Corresponding to the above method, the present invention also provides a railway bridge construction progress management system based on point cloud data, the system comprising:

[0081] A railway bridge design model is used to divide the physical entity of a railway bridge into components and map the components to parts of the railway bridge design model; wherein, the most basic structure of the component division result is the component element;

[0082] A railway bridge construction progress model is used to manage the construction progress of railway bridges. Based on the railway bridge design model, the 3D point cloud data is analyzed for feature matching and structural identification. The results of feature matching and structural identification are combined to match component primitives, and the corresponding structures are extracted from the acquired 3D point cloud data based on the structural identification results.

[0083] The parameters are combined with the structural parameters to perform parameterized adjustment on the successfully matched component primitives. Based on the parameterized component primitives, three-dimensional reverse modeling is performed in three-dimensional point cloud space to obtain the railway bridge construction progress model.

[0084] A railway bridge construction progress prediction model is used to predict the construction progress of railway bridges. This model obtains the engineering quantity corresponding to each component element, as well as the influencing factors and key dependencies of railway bridge construction. All component elements and their corresponding engineering quantities are input into a graph neural network based on Graphsage to construct the railway bridge construction progress prediction model. The model then predicts the construction progress based on this model. The influencing factors include various factors such as the number of construction workers, the number of construction machines, material resources, construction techniques, and weather conditions. The key dependencies are the necessary order of component elements in the graph neural network.

[0085] The progress verification module acquires the railway bridge construction logs input by technical personnel and compares the railway bridge design model, the railway bridge construction logs, and the railway bridge construction progress model to verify the progress. Based on the railway bridge design model, the railway bridge construction progress model, and the railway bridge construction progress projection model, the module manages the railway bridge construction progress.

[0086] Corresponding to the above method, the present invention also provides an apparatus comprising a computer device including a processor and a memory, the memory storing computer instructions, the processor executing the computer instructions stored in the memory, and the apparatus performing the steps of the method as described above when the computer instructions are executed by the processor.

[0087] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the steps of the method as described above. The computer-readable storage medium may be a tangible storage medium, such as random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, floppy disk, hard disk, removable storage disk, CD-ROM, or any other form of storage medium known in the art.

[0088] Those skilled in the art will understand that the exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention. When implemented in hardware, it can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the desired tasks. The programs or code segments can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave.

[0089] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0090] In this invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or in place of features of other embodiments.

[0091] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. For those skilled in the art, various modifications and variations can be made to the embodiments of the present invention. Any modifications, equivalent substitutions, improvements, etc., 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 railway bridge construction progress management method based on point cloud data, characterized by, The method includes the following steps: Based on the railway bridge design model, the railway bridge engineering entity is divided into components, and the components are mapped to the parts of the railway bridge design model; wherein, the most basic structure of the component division result is the component element; Receive three-dimensional point cloud data of bridge construction progress collected by UAV airborne radar; By referring to the railway bridge design model, the three-dimensional point cloud data is analyzed to perform feature matching and structure recognition. The component primitives are matched based on the results of feature matching and structure recognition. The corresponding structural parameters in the three-dimensional point cloud data are extracted based on the results of structure recognition. The matched component primitives are parametrically adjusted based on the structural parameters. Three-dimensional reverse modeling is performed in the three-dimensional point cloud space based on the parametrically adjusted component primitives to obtain the railway bridge construction progress model. Obtain the railway bridge construction logs entered by technicians; The railway bridge design model, railway bridge construction log, and railway bridge construction progress model were compared to verify the progress. The engineering quantity corresponding to each component primitive is obtained, and the influencing factors and key dependencies of railway bridge construction are obtained. All component primitives and their corresponding engineering quantities are input into a graph neural network based on Graphsage to construct a railway bridge construction progress prediction model. Then, the progress is predicted based on the railway bridge construction progress prediction model. The influencing factors include the number of construction personnel, the number of construction machinery, material resources, construction processes and methods, and various weather conditions. The key dependencies are the necessary order of component primitives in the graph neural network based on Graphsage. Railway bridge construction progress management is carried out based on the aforementioned railway bridge design model, railway bridge construction progress model, and railway bridge construction progress projection model.

2. The method according to claim 1, characterized in that, The step of comparing the railway bridge design model, railway bridge construction log, and railway bridge construction progress model to verify the progress also includes: Visualize the construction progress model of railway bridges; By combining the engineering quantities corresponding to each component element with the railway bridge construction progress model, a construction progress chart is drawn.

3. The method according to claim 2, characterized in that, In the railway bridge construction progress simulation model, blank spaces are used to visualize the unfinished parts. As the timeline progresses, the blank spaces are filled to show the progress.

4. The method according to claim 2, characterized in that, The method also includes: The railway bridge construction progress model and the railway bridge construction progress projection model are compared, and the parts with the risk of construction delay are marked with a color warning and a warning message is issued.

5. The method according to claim 1, characterized in that, The critical dependencies include the critical paths from pile foundations and caps to piers and caps, from piers and caps to supports, from supports to pad stones and blocks, and from pad stones and blocks to simply supported beams or continuous box girders.

6. The method according to claim 1, characterized in that, The railway bridge design model, railway bridge construction progress model, and railway bridge construction progress projection model are all BIM-based three-dimensional models. The components in the railway bridge design model, railway bridge construction progress model, and railway bridge construction progress projection model all conform to EBS coding.

7. The method according to claim 1, characterized in that, The parameter adjustment of the successfully matched component primitives in conjunction with the structural parameters includes: Based on the existing railway bridge construction schedule model, the structural parameters corresponding to the component elements of the railway bridge construction schedule model are replaced with modified structural parameters, thereby realizing the update of the railway bridge construction schedule model.

8. A railway bridge construction progress management system based on point cloud data, the system comprising: A railway bridge design model is used to divide the physical entity of a railway bridge into components and map the components to parts of the railway bridge design model; wherein, the most basic structure of the component division result is the component element; A railway bridge construction progress model is used to manage the construction progress of railway bridges. By comparing the railway bridge design model with the 3D point cloud data of the bridge construction progress, feature matching and structural identification are performed. The component primitives are matched based on the results of feature matching and structural identification. Based on the results of structural identification, the corresponding structural parameters in the acquired 3D point cloud data are extracted. The matched component primitives are parametrically adjusted based on the structural parameters. Based on the parametrically adjusted component primitives, 3D reverse modeling is performed in the 3D point cloud space to obtain the railway bridge construction progress model. A railway bridge construction progress prediction model is used to predict the construction progress of railway bridges. This model obtains the engineering quantity corresponding to each component element, as well as the influencing factors and key dependencies of railway bridge construction. All component elements and their corresponding engineering quantities are input into a graph neural network based on Graphsage to construct the railway bridge construction progress prediction model. The model then predicts the construction progress based on this model. The influencing factors include various factors such as the number of construction workers, the number of construction machines, material resources, construction techniques, and weather conditions. The key dependencies are the necessary order of component elements in the graph neural network. The progress verification module acquires the railway bridge construction logs input by technical personnel and compares the railway bridge design model, the railway bridge construction logs, and the railway bridge construction progress model to verify the progress. Based on the railway bridge design model, the railway bridge construction progress model, and the railway bridge construction progress projection model, the module manages the railway bridge construction progress.

9. An apparatus comprising a processor and a memory, characterized in that, The memory stores computer instructions, and the processor executes the computer instructions stored in the memory. When the computer instructions are executed by the processor, the device implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images