A method and system for rapid 3D modeling of pipeline network in steam turbine room of thermal power plant

Abstract

The present invention discloses a method and system for rapid 3D modeling of a turbine room pipe network in a thermal power plant, belonging to the technical field of digital modeling of thermal power plants. The method and system specifically include: using laser scanning technology and a total station to obtain pipe network point cloud data and position coordinate data; using a filtering algorithm to remove noise, and a point cloud registration algorithm to splice and fuse the point cloud data to form a pipe network point cloud model, and aligning it with the geographic coordinate system through a coordinate transformation algorithm; using a regional growing algorithm to extract pipe network features, combining the design drawing attribute data with a template matching algorithm to mark and classify, and establish the pipe network topological structure relationship; using 3D modeling software to perform 3D visual modeling of the pipe network; and finally performing verification and correction to obtain a final rapid 3D model of the turbine room pipe network. The present invention improves modeling efficiency and accuracy.

Description

Technical Field

[0001] The invention belongs to the technical field of digital modeling of thermal power plants, and in particular relates to a method and system for rapid three-dimensional modeling of a pipe network in a steam engine room of a thermal power plant. Background Art

[0002] The piping network within a thermal power plant's turbine room is complex, encompassing numerous pipelines, including steam, condensate, and water lines. Therefore, an accurate 3D model of this piping network is crucial for equipment management, fault diagnosis, and renovation planning. Traditional 3D modeling methods often require significant manpower, material resources, and time, and the modeling process is complex and prone to errors. For example, the surveying and mapping of the pipeline network may be inaccurate, resulting in deviations from the actual model. During the model construction phase, component parameter settings and connection relationships may be inefficient, impacting both modeling speed and quality.

[0003] For example, Chinese patent application publication number CN119089614A discloses a method, apparatus, device, and medium for automated three-dimensional urban pipe network GIS modeling. The method includes: obtaining pipeline data for the urban pipe network, preprocessing the pipeline data to obtain raw pipeline information data; identifying a pipe point table and a pipeline table within the raw pipeline information data, wherein the pipe point table includes key fields for several pipe points, and the pipeline table includes key fields for several pipelines; generating a modeling configuration file based on the key fields for the several pipe points and several pipelines; generating a modeling time configuration, and based on the modeling time configuration, importing the modeling configuration file into a preset modeling program to automatically model the urban pipe network, thereby obtaining a three-dimensional pipe network GIS model. This technical solution seamlessly integrates with different modeling software platforms and offers advantages such as high modeling efficiency, low labor costs, and low operating costs due to rapid data updates.

[0004] For example, the Chinese patent with authorization announcement number CN115795768B discloses a three-dimensional modeling and data update method and system for pipeline networks that takes into account physical form, including: obtaining the scope of the underground pipeline construction project area, exporting the regional pipeline status data as a working base map, and assisting in the planning and design of pipeline projects; integrating and establishing quality inspection rules to review the pipeline project planning and design scheme; configuring quality inspection rule items based on the completion measurement data of the pipeline project, and generating a quality inspection report; judging the update status of the completion measurement data that has passed the quality inspection, and inserting the elements with the update status of deletion and attribute update into the historical database for data backup; using a range-level incremental update method to realize the update and storage of two-dimensional data; adopting an automated parameter modeling method that takes into account physical form to complete the construction of the underground pipeline three-dimensional model for the two-dimensional data stored in the database; establishing an urban underground comprehensive pipeline network information system to realize pipeline database management, application and sharing.

[0005] The above existing technologies all have the following problems: they are limited by the functions and flexibility of the preset modeling programs, resulting in poor scope of application and flexibility, and are more suitable for large-scale and relatively fixed pipeline systems such as urban pipeline networks; the data source and preprocessing complexity are high, and the modeling efficiency and degree of automation are low. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention proposes a method and system for rapid three-dimensional modeling of the steam turbine room pipeline network in a thermal power plant, which uses laser scanning technology and a total station to obtain pipeline network point cloud data and position coordinate data; adopts a filtering algorithm to remove noise, and a point cloud registration algorithm to splice and fuse the point cloud data to form a pipeline network point cloud model, and aligns it with the geographic coordinate system through a coordinate transformation algorithm; uses a regional growing algorithm to extract pipeline network features, and uses a template matching algorithm to annotate and classify in combination with the design drawing attribute data to establish the pipeline network topological structure relationship; uses three-dimensional modeling software to perform three-dimensional visual modeling of the pipeline network; finally, performs verification and correction to obtain the final rapid three-dimensional model of the steam turbine room pipeline network; the present invention improves modeling efficiency and accuracy.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for rapid 3D modeling of a pipe network in a steam turbine room of a thermal power plant, comprising:

[0009] Step S1: Use laser scanning technology to perform a full-scale scan of the pipe network in the turbine room to obtain pipe network point cloud data, and use a total station to measure the core parts to obtain position coordinate data;

[0010] Step S2: Preprocess the collected pipe network point cloud data, and use a point cloud registration algorithm to stitch and fuse the point cloud data obtained from multiple scans to form a turbine room pipe network point cloud model. Combined with the position coordinate data, a coordinate transformation algorithm is used to align the turbine room pipe network point cloud model with the actual geographic coordinate system.

[0011] Step S3: Based on the geometric shape of the pipeline and the distribution characteristics of the point cloud data, a region growing algorithm is used to automatically extract pipeline network features from the aligned turbine room pipeline network point cloud model. Combined with the attribute data in the design drawings, a template matching algorithm is used to annotate and classify the extracted pipeline network features, and a topological structure relationship of the pipeline network is established. The pipeline network features include pipeline centerline, pipe diameter information, pipe fitting type, and the position and posture of the pipe fittings in space.

[0012] Step S4: Based on the extracted pipe network features and topological structure, three-dimensional visual modeling of the pipe network is performed using three-dimensional modeling software;

[0013] Step S5: Compare and verify the constructed three-dimensional pipe network model, and modify and improve the three-dimensional model according to the verification result to obtain the final rapid three-dimensional pipe network model of the thermal power plant steam turbine room.

[0014] Specifically, the specific steps of step S2 include:

[0015] S2.1: Obtaining pipe network point cloud data And p i =(x i ,y i ,z i ),i∈[1,n], and use The collected pipe network point cloud data is preprocessed to obtain the preprocessed pipe network point cloud data P′={p1′,...,p′ n}, and p i ′=(x i ′,y i ′,z i ′), where p n represents the nth pipe network point cloud data point, p′ n represents the nth pre-processed pipe network point cloud data point, x i 、y i 、z i Represents the x, y, and z coordinate values ​​of the i-th pipe network point cloud data point, x i ′、y i ′、z i ′ respectively represent the x, y, and z coordinate values ​​of the i-th preprocessed pipe network point cloud data point, G(x j -x i ,y j -y i ,z j -z i ) represents the three-dimensional Gaussian weight function, G(x j -x i ,y j -y i ) represents the two-dimensional Gaussian weight function, N(i) represents the pipe network point cloud data point p i The set of points within the surrounding filter window;

[0016] S2.2: Preprocess the pipe network point cloud data P′={p1′,...,p′ n Each point p in i ′, with p i ′ is the center to determine a 3×3 neighborhood, and the point feature histogram is used to calculate p i ′The geometric relationship of the points in the neighborhood, get point p i ′’s feature descriptor.

[0017] Specifically, the specific steps of step S2 also include:

[0018] S2.3: Obtaining pipe network point cloud data and use Calculate two point clouds and The similarity measure between all feature points in , where d(p b,j ,p c,l ) represents the Euclidean distance, p b,j Representing point clouds The feature points in c,l Representing point clouds The feature points in b,jr Represents the feature point p b,j The coordinate value in the r dimension, p c,lr Represents the feature point p c,l The coordinate value in the r dimension, r represents the dimension, and r = 1, 2, 3 corresponds to the x, y, z coordinates;

[0019] S2.4: Based on the similarity measurement results, preliminary feature point pairs are obtained, m preliminary feature point pairs are randomly selected, and a rigid body transformation model is calculated based on the m preliminary feature point pairs in combination with feature descriptors.

[0020] Specifically, the specific steps of step S2 also include:

[0021] S2.5: Calculate the transformation error of the remaining feature point pairs according to the rigid body transformation model, and compare the transformation error with a preset error threshold. If the error is less than the error threshold, the feature point is considered an inlier point to form an inlier point set.

[0022] S2.6: Through iterative repetition, find the set of point pairs with the largest number of inliers as the final feature point pairs, and preliminarily align the point clouds based on the final feature point pairs.

[0023] Specifically, the specific steps of step S2 also include:

[0024] S2.7: Select control points from the position coordinate data in step S1. For each control point, substitute its coordinates into the formula The error equation is obtained, where They represent the x-coordinate value, y-coordinate value, and z-coordinate value in the actual geographic coordinate system, respectively; k represents the scale parameter. Represents the rotation parameters on the x, y, and z coordinates, Δx i ′、Δy i ′、Δz i ′ represents the translation parameters in x, y, and z coordinates respectively;

[0025] S2.8: Combine the error equations of all control points into a matrix form to obtain the error equation matrix, and use the least squares method to solve the error equation matrix to obtain the estimated values ​​of the seven parameters;

[0026] S2.9: Substitute the calculated seven parameters into the formula in S2.7 again, and perform coordinate transformation on all points in the preliminarily aligned pipe network point cloud model so that they are aligned with the actual geographic coordinate system, thereby obtaining the aligned turbine room pipe network point cloud model.

[0027] Specifically, the specific steps of step S3 include:

[0028] S3.1: Obtain the aligned point cloud model of the turbine room pipe network, analyze the distribution characteristics of the point cloud data, and select the starting point and branch point of the pipeline as seed points based on the geometric shape of the pipeline.

[0029] S3.2: Set the normal vector angle threshold based on the characteristics of the point cloud data and the geometric accuracy requirements of the pipe network;

[0030] S3.3: Starting from the seed point in S3.1, traverse the point cloud data in the aligned turbine room pipe network point cloud model according to the normal vector angle threshold set in S3.2. For each seed point, check the angle between the normal vector of its adjacent points and the normal vector of the seed point.

[0031] Specifically, the specific steps of step S3 also include:

[0032] S3.4: If the angle between the normal vector of the adjacent point and the normal vector of the seed point is less than the normal vector angle threshold, the adjacent point is included in the same area as the seed point, and the adjacent points of the newly included point are continuously checked until no new adjacent point has a normal vector with an angle less than the normal vector angle threshold, and the pipe network characteristic data is obtained;

[0033] S3.5: Based on the attribute data in the design drawings, construct 3D template models of different pipe fittings. Use a shape-based matching method to match the extracted pipe network feature data with the 3D template models of the pipe fittings. If the match is successful, annotate the attribute information in the 3D template model of the pipe fittings onto the corresponding pipe network features.

[0034] S3.6: Establish the topological structure of the pipeline network based on the marked pipeline network features and the connection relationships between them.

[0035] A rapid 3D modeling system for a pipe network in a steam turbine room of a thermal power plant, comprising: a data acquisition module, a data processing module, a feature extraction and annotation module, a 3D modeling module, and a verification and correction module;

[0036] The data acquisition module is used to collect pipe network data in the turbine room;

[0037] The data processing module is used to perform denoising, splicing and fusion on the collected data to form a point cloud model of the turbine room pipe network and align it with the actual geographic coordinate system;

[0038] The feature extraction and annotation module is used to extract pipe network features from the pipe network point cloud model, perform annotation and classification, and establish the topological structure relationship of the pipe network;

[0039] The three-dimensional modeling module is used to perform three-dimensional visual modeling of the pipe network using three-dimensional modeling software to generate an intuitive and interactive three-dimensional pipe network model;

[0040] The verification and correction module is used to compare and verify the constructed three-dimensional pipe network model with the actual on-site conditions, and to correct and improve the three-dimensional model based on the verification results.

[0041] Specifically, the data processing module includes: a filtering and denoising unit, a point cloud registration unit, and a coordinate transformation unit;

[0042] The filtering and denoising unit is used to perform denoising processing on the collected pipe network point cloud data using a filtering algorithm;

[0043] The point cloud registration unit is used to stitch and fuse the point cloud data obtained by multiple scans using a point cloud registration algorithm, and to form a point cloud model of the turbine room pipe network by finding the feature correspondence between different scan data;

[0044] The coordinate transformation unit is used to align the turbine room pipe network point cloud model with the actual geographic coordinate system using a coordinate transformation algorithm, so that the turbine room pipe network point cloud model accurately matches the actual situation in terms of spatial position.

[0045] Specifically, the verification and correction module includes: a comparison and verification unit and a correction and improvement unit;

[0046] The comparison and verification unit is used to compare the three-dimensional pipe network model with the actual situation on site to check the accuracy and completeness of the model;

[0047] The correction and improvement unit is used to correct and improve the three-dimensional model according to the comparison and verification results.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. The present invention proposes a rapid three-dimensional modeling system for the steam turbine room pipe network of a thermal power plant, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.

[0050] 2. This paper proposes a method for rapid 3D modeling of the turbine room piping network in a thermal power plant. Through laser scanning technology and precise measurement using a total station, the 3D point cloud data and position coordinate data of the turbine room piping network can be quickly and comprehensively acquired, thereby ensuring the accuracy and completeness of the data. Preprocessing and point cloud registration algorithms can be used to efficiently generate a point cloud model of the turbine room piping network and align it with the actual geographic coordinate system.

[0051] 3. The present invention proposes a method for rapid three-dimensional modeling of the steam turbine room pipe network in a thermal power plant. Utilizing a region growing algorithm and a template matching algorithm, the method can automatically extract, label, and classify pipe network features, thereby rapidly establishing the topological structure of the pipe network. This not only improves modeling efficiency but also ensures the precision and accuracy of the model. Ultimately, a complete three-dimensional model of the steam turbine room pipe network in a thermal power plant is obtained through visual modeling and comparison verification using three-dimensional modeling software. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a schematic diagram of a method for rapid three-dimensional modeling of a pipe network in a steam turbine room of a thermal power plant according to the present invention;

[0053] Figure 2 This is a principle flow chart of a method for rapid three-dimensional modeling of a pipe network in a thermal power plant turbine room according to the present invention;

[0054] Figure 3 This is an architecture diagram of a rapid three-dimensional modeling system for a thermal power plant steam turbine room pipe network according to the present invention. DETAILED DESCRIPTION

[0055] Example 1

[0056] See also Figure 1 and Figure 2 The present invention provides an embodiment of a method for rapid three-dimensional modeling of a pipe network in a steam turbine room of a thermal power plant, comprising the following steps:

[0057] Step S1: Use laser scanning technology to perform a full-scale scan of the pipe network in the turbine room to obtain pipe network point cloud data, and use a total station to measure the core parts to obtain position coordinate data;

[0058] It should be noted that when using laser scanning technology to perform a comprehensive scan of the pipeline network within the turbine room, the resulting network point cloud data is composed of multiple sets of point cloud data. Due to the turbine room's spatial layout and the complex structure of the pipeline network, it is difficult to fully capture the point cloud information of all pipelines in a single scan. To obtain complete pipeline network data, scanning is usually performed from multiple scanning stations, with each scanning station obtaining a set of point cloud data covering the portion of the pipeline network visible from that station's perspective. Subsequent data processing, such as constructing a complete 3D model of the pipeline network, requires splicing and fusing these multiple sets of point cloud data. This is because each set of point cloud data only represents a portion of the pipeline network. Only by combining them can a complete point cloud model of the entire turbine room pipeline network be obtained.

[0059] Furthermore, the specific steps of step S1 include:

[0060] (1) Equipment preparation and parameter setting

[0061] Laser scanning equipment preparation: Select a laser scanner based on the size, complexity, and modeling accuracy requirements of the turbine room pipe network. For example, if the turbine room pipe network is small and densely packed, a laser scanner with millimeter-level accuracy and high resolution is required.

[0062] Total station preparation: calibrate the total station to ensure its measurement accuracy, including checking the horizontality and verticality of the total station, and setting the measurement unit and angle unit;

[0063] (2) Scan planning

[0064] Plan the laser scanning path and sites based on the turbine room layout and pipe network distribution. Generally speaking, ensure that the scanning sites can cover the entire pipe network system to avoid blind spots. Use wrap-around scanning, layered scanning, and other methods. For complex pipe network intersections and high-altitude pipelines, pay special attention to the scanning angle and site location to obtain complete point cloud data.

[0065] (3) Laser scanning operation

[0066] Place the laser scanner at the planned site and start the scanning program. During the scanning process, the spatial coordinates and reflection intensity of each scanning point are recorded. The laser scanner emits a laser beam and receives reflected light. It calculates the distance from the scanning point to the scanner based on the laser's flight time or phase difference. Combined with the scanner's own spatial position and angle information, it determines the three-dimensional coordinates of the scanning point, thereby obtaining the pipe network point cloud data.

[0067] (4) Total station core part measurement

[0068] After completing the laser scan, use a total station to measure the core parts of the pipe network, where the core parts include key nodes such as pipe connection points, valve installation locations, and pipe branches; place the total station in a suitable position, aim at the target point, measure its horizontal angle, vertical angle, and slope distance, and use trigonometric functions to calculate the three-dimensional coordinates of the target point. For example, for a target point, let the horizontal angle measured by the total station be α, the vertical angle be β, the slope distance be s, and the station coordinates of the total station be (X0, Y0, Z0). The coordinate calculation formula of the target point is: Among them, sin(·) represents the sine function, and cos(·) represents the cosine function;

[0069] Record the location coordinate data of each core measurement point. These location coordinate data will be combined with the pipe network point cloud data for subsequent data processing and model construction;

[0070] (5) Data recording and organization

[0071] The pipe network point cloud data obtained by laser scanning and the position coordinate data measured by the total station are sorted out. The data can be stored on a local hard disk or cloud server. The pipe network point cloud data can be saved in LAS and PLY data formats, and the position coordinate data can be saved in table form to ensure the integrity and accuracy of the data. At the same time, relevant information such as the time, location, equipment number, etc. of data collection can be recorded to facilitate subsequent data tracing and processing.

[0072] Step S2: Preprocess the collected pipe network point cloud data, and use a point cloud registration algorithm to stitch and fuse the point cloud data obtained from multiple scans to form a turbine room pipe network point cloud model. Combined with the position coordinate data, a coordinate transformation algorithm is used to align the turbine room pipe network point cloud model with the actual geographic coordinate system.

[0073] Step S3: Based on the geometric shape of the pipeline and the distribution characteristics of the point cloud data, a region growing algorithm is used to automatically extract pipeline network features from the aligned turbine room pipeline network point cloud model. Combined with the attribute data in the design drawings, a template matching algorithm is used to annotate and classify the extracted pipeline network features, and a topological structure relationship of the pipeline network is established. The pipeline network features include pipeline centerline, pipe diameter information, pipe fitting type, and the position and posture of the pipe fittings in space.

[0074] Step S4: Based on the extracted pipe network features and topological structure, three-dimensional visual modeling of the pipe network is performed using three-dimensional modeling software;

[0075] Furthermore, the specific steps of step S4 include:

[0076] (1) In the 3D modeling software, use its data import function to import the converted pipe network feature data, including the pipe centerline coordinates, pipe diameter information, pipe type and position posture, and topological structure data into the workspace;

[0077] (2) Based on the imported pipeline centerline coordinates and pipe diameter information, the basic geometric shape creation tools are used in the software to generate a pipeline model. For each section of pipeline, a cylinder is created with the centerline as the axis and the pipe diameter as the diameter;

[0078] (3) According to actual needs, the pipeline model is processed in detail, such as adding texture to the pipeline surface and setting the transparency of the pipeline;

[0079] (4) For different types of pipe fittings, such as elbows, tees, and valves, if there are models that meet the requirements in the software's built-in model library, they can be directly called; if not, you need to create your own according to the geometric shape and size of the pipe fitting; you can also import pipe fitting models from external model libraries, such as online 3D model resource websites or the company's internal standard pipe fitting model library;

[0080] (5) According to the imported pipe fitting position and posture information, the pipe fitting is accurately placed in the three-dimensional space, and the connection point of the pipe fitting is aligned with the corresponding pipe end point to ensure that the connection between the pipe fitting and the pipe conforms to the topological structure relationship. At the same time, in the software, the position and posture of the pipe fitting can be adjusted using the move, rotate and scale tools;

[0081] (6) In the software, using its associated tools or scripting functions, the connection relationship between the pipeline and pipe fitting models is constructed based on the imported topological structure data.

[0082] Step S5: Compare and verify the constructed three-dimensional pipe network model, and modify and improve the three-dimensional model according to the verification result to obtain the final rapid three-dimensional pipe network model of the thermal power plant steam turbine room.

[0083] Furthermore, the specific steps of step S5 include:

[0084] (1) Compare and verify the constructed 3D model with the actual pipe network through field measurement to check the accuracy of the model, including whether the direction, location, and size of the pipes are consistent with the actual situation;

[0085] (2) Based on the comparison and verification results, the 3D model is corrected and improved. If connection errors are found, such as incorrect alignment of pipe fittings and pipelines, wrong connection sequence, etc., they are corrected in a timely manner;

[0086] (3) After correction and improvement, the final rapid three-dimensional model of the steam turbine room pipe network of the thermal power plant is obtained, and the model is finally inspected and tested to ensure its stability and usability.

[0087] For example, in a thermal power plant turbine room pipe network modeling project, first, appropriate laser scanners and total stations are selected to comprehensively scan the pipe network within the turbine room and measure key locations. The laser scanner's scanning accuracy is set to 0.5mm and its resolution is 1mm to ensure that detailed and accurate point cloud data can be obtained. At the same time, the total station accurately measures important locations such as pipeline connection points, with a measurement error within ±0.1mm.

[0088] The collected data was then imported into data processing software and denoised using a Gaussian filter algorithm. The standard deviation of the filter was set to 0.3 mm, effectively removing noise points. A curvature-based simplification method was used to streamline the data, reducing the number of point clouds by 70% while retaining the key features of the pipeline network. The total station data was calibrated and fused with the point cloud data to form a complete data set.

[0089] Secondly, a region growing algorithm was used to extract pipeline centerlines. The growth threshold was set to 0.05m based on the actual pipeline conditions. This allowed accurate identification of the centerlines of each pipeline. Measurements and calculations were performed on point cloud cross-sections to obtain the exact dimensions and wall thickness of each pipeline segment with a diameter ranging from 0.2m to 1m. A shape analysis algorithm was used to identify and extract parameters for valves, elbows, tees, and other pipe fittings. Over 50 different types of pipe fittings were identified, and their precise installation locations and connection directions were determined.

[0090] In addition, a pipeline model was created in professional 3D modeling software based on the extracted center lines and parameters. A pipe fitting model was constructed using the software's built-in pipe fitting library and accurately connected to the pipeline model. The model was given metal material properties and the color was adjusted to silver-gray, with a glossiness of 0.6 and a reflectivity of 0.4 to give the model a good visual effect.

[0091] Finally, the constructed three-dimensional model was compared and verified. By comparing the dimensions of 10 key parts through on-site measurement and verification with the model, the error was controlled within ±2mm, ensuring the accuracy and reliability of the model.

[0092] The specific steps of step S2 include:

[0093] S2.1: Obtaining pipe network point cloud data And p i =(x i ,y i ,z i ),i∈[1,n], and use The collected pipe network point cloud data is preprocessed to obtain the preprocessed pipe network point cloud data P′={p1′,...,p′ n}, and p i ′=(xi ′,y i ′,z i ′), where p n represents the nth pipe network point cloud data point, p′ n represents the nth pre-processed pipe network point cloud data point, x i 、y i 、z i Represents the x, y, and z coordinate values ​​of the i-th pipe network point cloud data point, x i ′、y i ′、z i ′ respectively represent the x, y, and z coordinate values ​​of the i-th preprocessed pipe network point cloud data point, G(x j -x i ,y j -y i ,z j -z i ) represents the three-dimensional Gaussian weight function, G(x j -x i ,y j -y i ) represents the two-dimensional Gaussian weight function, N(i) represents the pipe network point cloud data point p i The set of points within the surrounding filter window;

[0094] It is important to understand that when laser scanning technology is used to perform a full-scale scan of the pipe network in the turbine room, the pipe network point cloud data obtained is a holistic point cloud, which contains a large number of points. These points are a set of three-dimensional coordinate points obtained by sampling the pipe network surface in space using laser scanning equipment. Feature points are representative points extracted from this holistic point cloud.

[0095] It is also important to understand that in the process of point cloud registration, two or more point clouds are involved. For example, suppose the pipeline network of the steam engine room is scanned twice, and point cloud b and point cloud c are obtained. In order to align point cloud b and point cloud c, it is necessary to find corresponding points between them. This process requires calculating the similarity measure between each feature point in point cloud b and all feature points in point cloud c.

[0096] S2.2: Preprocess the pipe network point cloud data P′={p1′,...,p′ n Each point p in i ′, with p i ′ is the center to determine a 3×3 neighborhood, and the point feature histogram is used to calculate p i ′The geometric relationship of the points in the neighborhood, get point p i ′’s feature descriptor;

[0097] S2.3: Obtaining pipe network point cloud data and use Calculate two point clouds and The similarity measure between all feature points in , where d(p b,j ,p c,l ) represents the Euclidean distance, p b,j Representing point clouds The feature points in c,l Representing point clouds The feature points in b,jr Represents the feature point p b,j The coordinate value in the r dimension, p c,lr Represents the feature point p c,l The coordinate value in the r dimension, r represents the dimension, and r = 1, 2, 3 corresponds to the x, y, z coordinates;

[0098] S2.4: Based on the similarity measurement results, preliminary feature point pairs are obtained, m preliminary feature point pairs are randomly selected, and a rigid body transformation model is calculated based on the m preliminary feature point pairs and combined with feature descriptors;

[0099] Furthermore, the specific steps of S2.4 include:

[0100] (1) Obtain the feature descriptor of each feature point and filter out preliminary feature point pairs according to S2.2;

[0101] (2) Randomly select m feature point pairs from the screened preliminary feature point pairs as input for subsequent calculations;

[0102] (3) Using the selected m preliminary feature point pairs and combining them with feature descriptors, the parameters of the rigid body transformation model are calculated. The rigid body transformation formula is A′=R×A+t, where R represents the rotation matrix, t represents the translation vector, A represents the original coordinates, and A′ represents the transformed coordinates.

[0103] (4) Obtaining the optimal rotation matrix R and translation vector t by solving the least squares problem, wherein the least squares problem is a prior art in this field and is not an inventive solution of the present application, and is not described in detail here;

[0104] (5) Use the remaining feature point pairs to verify the accuracy of the calculated rigid body transformation model, and optimize and adjust the model based on the verification results.

[0105] S2.5: Calculate the transformation error of the remaining feature point pairs according to the rigid body transformation model, and compare the transformation error with a preset error threshold. If the error is less than the error threshold, the feature point is considered an inlier point to form an inlier point set.

[0106] S2.6: Through iterative repetition, find the point pair with the largest number of inliers as the final feature point pair, and preliminarily align the point cloud based on the final feature point pair;

[0107] It should be understood that a feature point pair is a pair of features from two different point clouds (e.g. point clouds and ), in the feature matching process of point cloud registration, the goal is to find the point cloud Each feature point in the point cloud The corresponding points in the image are each a pair of corresponding points. When using the random sampling consistency method for feature point matching, the inliers refer to feature point pairs that conform to a certain assumed rigid body transformation model. This rigid body transformation model includes rotation and translation, which describes the possible spatial position relationship between the two point clouds. At the same time, in actual point cloud data, due to the regularity and continuity of the geometric shape of the pipeline network, the corresponding parts of the same object, such as a pipeline, in the point clouds obtained by different scans should follow similar rigid body transformation laws. For example, the position relationship of a pipeline in two scans is described by an overall rotation and translation. Therefore, when a reasonable rigid body transformation model is calculated by randomly selecting several feature point pairs, there will be multiple other feature point pairs that conform to this transformation model, such as those with errors less than the threshold. These point pairs represent the point cloud. and The truly corresponding parts in the image are the inliers. They constitute the inliers set. Through multiple iterations of random sampling consistency method, the set of point pairs with the largest number of inliers is selected as the final feature point pair. This is to find the matching point pair that can most accurately describe the transformation relationship between the two point clouds, thereby achieving more accurate point cloud registration.

[0108] S2.7: Select control points from the position coordinate data in step S1. For each control point, substitute its coordinates into the formula The error equation is obtained, where They represent the x-coordinate value, y-coordinate value, and z-coordinate value in the actual geographic coordinate system, respectively; k represents the scale parameter. Represents the rotation parameters on the x, y, and z coordinates, Δx i ′、Δy i ′、Δz i ′ represents the translation parameters in x, y, and z coordinates respectively;

[0109] S2.8: Combine the error equations for all control points into a matrix form to obtain an error equation matrix, and use the least squares method to solve the error equation matrix to obtain estimated values ​​of the seven parameters. The least squares method solution formula is prior art in this field and does not constitute the inventive solution of this application, so it is not repeated here.

[0110] S2.9: Substitute the calculated seven parameters into the formula in S2.7 again, and perform coordinate transformation on all points in the preliminarily aligned pipe network point cloud model so that they are aligned with the actual geographic coordinate system, thereby obtaining the aligned turbine room pipe network point cloud model.

[0111] The specific steps of step S3 include:

[0112] S3.1: Obtain the aligned point cloud model of the turbine room pipe network, analyze the distribution characteristics of the point cloud data, and select the starting point and branch point of the pipeline as seed points based on the geometric shape of the pipeline.

[0113] S3.2: Set the normal vector angle threshold based on the characteristics of the point cloud data and the geometric accuracy requirements of the pipe network;

[0114] S3.3: Starting from the seed point in S3.1, traverse the point cloud data in the aligned turbine room pipe network point cloud model according to the normal vector angle threshold set in S3.2. For each seed point, check the angle between the normal vector of its adjacent points and the normal vector of the seed point;

[0115] S3.4: If the angle between the normal vector of the adjacent point and the normal vector of the seed point is less than the normal vector angle threshold, the adjacent point is included in the same area as the seed point, and the adjacent points of the newly included point are continuously checked until no new adjacent point has a normal vector with an angle less than the normal vector angle threshold, and the pipe network characteristic data is obtained;

[0116] S3.5: Based on the attribute data in the design drawings, construct three-dimensional template models of different pipe fittings, and use a shape feature-based matching method to match the extracted pipe network feature data with the three-dimensional template model of the pipe fitting. If the match is successful, the attribute information in the three-dimensional template model of the pipe fitting is annotated with the corresponding pipe network feature. The shape feature-based matching method is the prior art content in this field and does not constitute the inventive solution of this application, and is not described in detail here.

[0117] S3.6: Establish the topological structure of the pipeline network based on the marked pipeline network features and the connection relationships between them.

[0118] Example 2

[0119] See also Figure 3 Another embodiment provided by the present invention is a rapid three-dimensional modeling system for a steam turbine room pipe network in a thermal power plant, comprising:

[0120] Data acquisition module, data processing module, feature extraction and annotation module, 3D modeling module, verification and correction module;

[0121] Data acquisition module, used to collect pipe network data in the turbine room;

[0122] The data processing module is used to remove noise, stitch and fuse the collected data to form a point cloud model of the turbine room pipe network and align it with the actual geographic coordinate system;

[0123] The feature extraction and annotation module is used to extract pipe network features from the pipe network point cloud model, perform annotation and classification, and establish the topological structure relationship of the pipe network;

[0124] 3D modeling module, used to perform 3D visualization modeling of the pipe network using 3D modeling software, generating an intuitive and interactive 3D pipe network model;

[0125] The verification and correction module is used to compare and verify the constructed three-dimensional pipe network model with the actual on-site conditions, and to correct and improve the three-dimensional model based on the verification results.

[0126] The data acquisition module includes: laser scanning unit and total station measurement unit;

[0127] The laser scanning unit is used to perform a full-scale scan of the pipe network in the turbine room using laser scanning technology to obtain pipe network point cloud data, which can reflect the approximate geometric shape and spatial location information of the pipe network;

[0128] The total station measurement unit is used to measure the core parts of the pipeline network and obtain position coordinate data. The position coordinate data is used to supplement the local accuracy problems that may exist in laser scanning and provide key control point information for subsequent data registration and coordinate system alignment. The core parts of the pipeline network include but are not limited to key connection points, valves, and branch starting points.

[0129] The data processing module includes: filtering and denoising unit, point cloud registration unit, and coordinate transformation unit;

[0130] The filtering and denoising unit is used to denoise the collected pipe network point cloud data using a filtering algorithm to remove noise points caused by environmental interference, such as light reflection and equipment vibration, to improve the purity and quality of the data, so as to more accurately extract pipe network features and build models in the future;

[0131] The point cloud registration unit is used to stitch and fuse the point cloud data obtained from multiple scans using a point cloud registration algorithm. By finding the feature correspondence between different scan data, it integrates them into a complete point cloud model of the turbine room pipe network, ensuring data integrity and continuity, and avoiding model loss or incoherence caused by scanning range limitations.

[0132] The coordinate transformation unit is used to align the pipe network point cloud model with the actual geographic coordinate system using the coordinate transformation algorithm, so that the model accurately matches the actual situation in spatial position, ensuring the accuracy of the pipe network model in geographic space.

[0133] The feature extraction and annotation module includes: feature extraction unit, annotation and classification unit, and topology structure establishment unit;

[0134] The feature extraction unit is used to automatically extract pipeline network features from the pipeline network point cloud model using a region growing algorithm based on the geometric shape of the pipeline and the distribution characteristics of the point cloud data.

[0135] The labeling and classification unit is used to combine the attribute data in the design drawings and use the template matching algorithm to label and classify the extracted pipe network features;

[0136] Among them, the main method is to set appropriate growth criteria to identify point cloud areas with similar characteristics as different pipeline network elements such as pipes and fittings, thereby extracting key geometric features such as pipeline centerline and pipe diameter information, and providing accurate shape parameters for three-dimensional modeling.

[0137] The topology structure establishment unit is used to establish the topology structure relationship of the pipeline network based on the extracted pipeline network features and annotation information.

[0138] Among them, the main thing is to compare the extracted pipe network features with the standard pipe fittings shape, size and other information in the design drawings, determine the specific type of each pipe fitting through template matching, such as elbows, tees, and valves, and assign corresponding attribute labels. At the same time, establish the topological structure relationship of the pipe network, clarify the connection sequence and logical relationship between each pipe network element, so that the model not only has geometric shape information, but also has complete engineering attribute information.

[0139] The verification and correction module includes: a comparison and verification unit and a correction and improvement unit;

[0140] Comparison and verification unit, used to compare the three-dimensional model of the pipeline network with the actual on-site conditions to check the accuracy and completeness of the model;

[0141] The main method is to measure the dimensions, positions and other information of some key parts on site, compare and analyze them with the corresponding data in the three-dimensional model, and check whether there are deviations or errors in the model. At the same time, engineers with actual operation and maintenance experience are invited to review the integrity and rationality of the model, and evaluate whether the model accurately reflects the actual situation of the steam turbine room pipeline network from an actual engineering perspective, and find out the differences and potential problems between the model and reality.

[0142] The correction and improvement unit is used to correct and improve the three-dimensional model according to the results of comparison and verification, to ensure the accuracy and practicality of the model, to improve the accuracy and reliability of the model, and to meet actual application needs.

[0143] Among them, for dimensional deviations, the parameters of the corresponding pipes and fittings in the model are adjusted; for topological structure errors, the connection relationship between the pipeline network elements is reorganized and modified; for missing or unclear parts in the model, feedback is given to the data acquisition module or feature extraction and annotation module to supplement data collection or re-extract features. After multiple iterative verification and corrections, the final accurate and complete rapid three-dimensional model of the thermal power plant steam turbine room pipeline network is obtained.

[0144] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific embodiments. The above-mentioned specific embodiments are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention. These are all protected by the present invention.

Claims

1. A method for rapid three-dimensional modeling of a pipe network in a thermal power plant turbine room, characterized in that: include: Step S1: Use laser scanning technology to perform a full-scale scan of the pipe network in the turbine room to obtain pipe network point cloud data, and use a total station to measure the core parts to obtain position coordinate data; Step S2: Preprocess the collected pipe network point cloud data, and use a point cloud registration algorithm to stitch and fuse the point cloud data obtained from multiple scans to form a turbine room pipe network point cloud model. Combined with the position coordinate data, a coordinate transformation algorithm is used to align the turbine room pipe network point cloud model with the actual geographic coordinate system. Step S3: Based on the geometric shape of the pipeline and the distribution characteristics of the point cloud data, a region growing algorithm is used to automatically extract pipeline network features from the aligned turbine room pipeline network point cloud model. Combined with the attribute data in the design drawings, a template matching algorithm is used to annotate and classify the extracted pipeline network features, and a topological structure relationship of the pipeline network is established. The pipeline network features include pipeline centerline, pipe diameter information, pipe fitting type, and the position and posture of the pipe fittings in space. Step S4: Based on the extracted pipe network features and topological structure, three-dimensional visual modeling of the pipe network is performed using three-dimensional modeling software; Step S5: Compare and verify the constructed pipe network 3D model, and modify and improve the 3D model based on the verification results to obtain the final rapid 3D model of the pipe network of the thermal power plant turbine room; The specific steps of step S2 include: S2.1: Obtaining pipe network point cloud data ,and and use Preprocess the collected pipe network point cloud data to obtain preprocessed pipe network point cloud data ,and ,in, Represents the nth pipe network point cloud data point, represents the nth pre-processed pipe network point cloud data point, 、 、 Respectively represent the x, y, and z coordinate values ​​of the i-th pipe network point cloud data point, 、 、 Respectively represent the x, y, and z coordinate values ​​of the i-th preprocessed pipe network point cloud data point, represents the three-dimensional Gaussian weight function, represents a two-dimensional Gaussian weight function, Represents a pipe network point cloud data point The set of points within the surrounding filter window; S2.2: Preprocessed pipe network point cloud data Each point in ,by Determine a 3×3 neighborhood for the center and use the point feature histogram to calculate The geometric relationship of points in the neighborhood, get the point Feature descriptor of S2.3: Obtaining pipe network point cloud data and ,use Calculate two point clouds and The similarity measure between all feature points in , where represents the Euclidean distance, Representing point clouds The feature points in Representing point clouds The feature points in Representing feature points The coordinate value in the r dimension, Representing feature points The coordinate value in the r dimension, r represents the dimension, and Corresponding to x, y, z coordinates; S2.4: Based on the similarity measurement results, preliminary feature point pairs are obtained, m preliminary feature point pairs are randomly selected, and a rigid body transformation model is calculated based on the m preliminary feature point pairs and combined with feature descriptors; S2.5: Calculate the transformation error of the remaining feature point pairs according to the rigid body transformation model, and compare the transformation error with a preset error threshold. If the error is less than the error threshold, the feature point is considered an inlier point to form an inlier point set. S2.6: Through iterative repetition, find the point pair with the largest number of inliers as the final feature point pair, and preliminarily align the point cloud based on the final feature point pair; S2.7: Select control points from the position coordinate data in step S1. For each control point, substitute its coordinates into the formula The error equation is obtained, where 、 、 They represent the x-coordinate value, y-coordinate value, and z-coordinate value in the actual geographic coordinate system, respectively; k represents the scale parameter. 、 、 Represents the rotation parameters on the x, y, and z coordinates respectively, 、 、 Represent the translation parameters in x, y, and z coordinates respectively; S2.8: Combine the error equations of all control points into a matrix form to obtain the error equation matrix, and use the least squares method to solve the error equation matrix to obtain the estimated values ​​of the seven parameters; S2.9: Substitute the calculated seven parameters into the formula in S2.7 again, and perform coordinate transformation on all points in the preliminarily aligned pipe network point cloud model so that they are aligned with the actual geographic coordinate system, thereby obtaining the aligned turbine room pipe network point cloud model.

2. A method for rapid three-dimensional modeling of a pipe network in a thermal power plant turbine room according to claim 1, characterized in that: The specific steps of step S3 include: S3.1: Obtain the aligned point cloud model of the turbine room pipe network, analyze the distribution characteristics of the point cloud data, and select the starting point and branch point of the pipeline as seed points based on the geometric shape of the pipeline. S3.2: Set the normal vector angle threshold based on the characteristics of the point cloud data and the geometric accuracy requirements of the pipe network; S3.3: Starting from the seed point in S3.1, traverse the point cloud data in the aligned turbine room pipe network point cloud model according to the normal vector angle threshold set in S3.

2. For each seed point, check the angle between the normal vector of its adjacent points and the normal vector of the seed point.

3. A method for rapid three-dimensional modeling of a pipe network in a thermal power plant turbine room according to claim 2, characterized in that: The specific steps of step S3 also include: S3.4: If the angle between the normal vector of the adjacent point and the normal vector of the seed point is less than the normal vector angle threshold, the adjacent point is included in the same area as the seed point, and the adjacent points of the newly included point are continuously checked until no new adjacent point has a normal vector with an angle less than the normal vector angle threshold, and the pipe network characteristic data is obtained; S3.5: Based on the attribute data in the design drawings, construct 3D template models of different pipe fittings. Use a shape-based matching method to match the extracted pipe network feature data with the 3D template models of the pipe fittings. If the match is successful, annotate the attribute information in the 3D template model of the pipe fittings onto the corresponding pipe network features. S3.6: Establish the topological structure of the pipeline network based on the marked pipeline network features and the connection relationships between them.

4. A rapid 3D modeling system for a thermal power plant turbine room pipe network, which is used to implement a rapid 3D modeling method for a thermal power plant turbine room pipe network according to any one of claims 1 to 3, characterized in that: include: Data acquisition module, data processing module, feature extraction and annotation module, 3D modeling module, verification and correction module; The data acquisition module is used to collect pipe network data in the turbine room; The data processing module is used to perform denoising, splicing and fusion on the collected data to form a point cloud model of the turbine room pipe network and align it with the actual geographic coordinate system; The feature extraction and annotation module is used to extract pipe network features from the pipe network point cloud model, perform annotation and classification, and establish the topological structure relationship of the pipe network; The three-dimensional modeling module is used to perform three-dimensional visual modeling of the pipe network using three-dimensional modeling software to generate an intuitive and interactive three-dimensional pipe network model; The verification and correction module is used to compare and verify the constructed three-dimensional pipe network model with the actual on-site conditions, and to correct and improve the three-dimensional model based on the verification results.

5. A rapid three-dimensional modeling system for a thermal power plant turbine room pipe network according to claim 4, characterized in that: The data processing module includes: a filtering and denoising unit, a point cloud registration unit, and a coordinate transformation unit; The filtering and denoising unit is used to perform denoising processing on the collected pipe network point cloud data using a filtering algorithm; The point cloud registration unit is used to stitch and fuse the point cloud data obtained by multiple scans using a point cloud registration algorithm, and to form a point cloud model of the turbine room pipe network by finding the feature correspondence between different scan data; The coordinate transformation unit is used to align the turbine room pipe network point cloud model with the actual geographic coordinate system using a coordinate transformation algorithm, so that the turbine room pipe network point cloud model accurately matches the actual situation in terms of spatial position.

6. A rapid three-dimensional modeling system for a thermal power plant turbine room pipe network according to claim 5, characterized in that: The verification and correction module includes: a comparison and verification unit and a correction and improvement unit; The comparison and verification unit is used to compare the three-dimensional pipe network model with the actual situation on site to check the accuracy and completeness of the model; The correction and improvement unit is used to correct and improve the three-dimensional model according to the comparison and verification results.

Images