A method for extracting design parameters of outdoor industrial pipelines, terminal equipment and medium
By constructing a real-world cloud data model and using image recognition technology, the design parameters of outdoor pipelines in industrial plants can be extracted quickly and accurately, solving the problem that existing tools cannot efficiently obtain these parameters. This provides accurate facility status information and design parameters, supporting the transformation and upgrading of industrial plants.
Patent Information
- Application Number
- CN202311015584.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-11
- Publication Date
- 2025-10-31
- Estimated Expiration
- 2043-08-11
AI Technical Summary
Existing surveying tools cannot quickly and accurately obtain the design parameters of large-area outdoor industrial pipelines in industrial plants, resulting in high renovation and upgrading costs and extended construction periods.
By constructing a real-world point cloud data model based on outdoor oblique photographic images of the factory area, image recognition and aerial triangulation are performed to extract the boundary range and feature matching points of industrial pipelines. Combined with point cloud data fitting, the design parameters of the pipelines are obtained.
It enables the rapid and accurate extraction of spatial location and geometric feature information of outdoor industrial pipelines, providing basic data for the maintenance and renovation of industrial plants, and reducing labor costs and construction time.
Smart Images

Figure CN117197690B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of industrial building surveying, and in particular to a method for extracting design parameters of outdoor industrial pipelines, terminal equipment, and medium. Background Technology
[0002] For industrial plants with complex production processes, the layout of sites, buildings, and various facilities is compact, and road and rail transit routes are intricate. As the number of newly built plants gradually decreases, the upgrading and renovation of existing plants will increase. Maintaining and reusing existing industrial pipelines will effectively save on renovation costs and accelerate the renovation process.
[0003] For industrial plants that have been in operation for many years, outdoor industrial pipelines often undergo route changes and localized replacements of pipe diameters. Accurately obtaining the actual condition of outdoor industrial pipelines, including pipe diameter, center coordinates, and bend angles, is crucial for the smooth implementation of the renovation design when conducting overall renovation planning. Common surveying tools, such as total stations, theodolites, and laser rangefinders, cannot complete the surveying of large-area industrial plants in a short time. Labor costs are high, and subsequent on-site surveys by various personnel are still necessary. Therefore, rapidly and accurately surveying the outdoor landscape of the plant area and extracting design parameters related to pipelines is a pressing technical problem that needs to be solved. Summary of the Invention
[0004] To address the aforementioned problems, this invention proposes a method for extracting design parameters for outdoor industrial pipelines, as well as a terminal device and a medium.
[0005] The specific plan is as follows:
[0006] A method for extracting design parameters for outdoor industrial pipelines includes the following steps:
[0007] S1: Construct a real-world cloud data model of the factory area based on outdoor oblique photographic images of the factory area;
[0008] S2: Perform image recognition on industrial pipes in outdoor oblique photography images, and obtain the boundary range of industrial pipes based on the images of the recognized industrial pipes;
[0009] S3: Perform aerial triangulation on the image of the identified industrial pipeline to obtain the feature matching points in each image. Compare the feature matching points in each image with the boundary range of the industrial pipeline, extract the feature matching points within the boundary range, and map them into the real-world point cloud data model of the factory area. Set the corresponding data points in the real-world point cloud data model as data points belonging to the industrial pipeline.
[0010] S4: Based on all data points belonging to the industrial pipeline, obtain the point cloud data of the industrial pipeline;
[0011] S5: Fitting industrial pipelines based on point cloud data;
[0012] S6: Extract the design parameters from the industrial pipeline based on the fitting results.
[0013] Furthermore, in the capture of outdoor oblique photographic images, aerial photography is used to plan the shooting route and flight altitude, with outdoor pipelines as the main subject.
[0014] Furthermore, the construction process of the real-world point-of-view cloud data model in step S1 includes the following steps:
[0015] S101: Perform aerial triangulation and overall adjustment calculations on outdoor oblique photographic images to obtain feature matching points for outdoor real-world reconstruction of the factory area;
[0016] S102: Generating a triangular network based on feature matching points;
[0017] S103: After mapping the color values corresponding to each feature matching point in the outdoor oblique photographic image to each corner point in the triangular network, extract each corner point of the mapped triangular network to generate a real-world point cloud data model.
[0018] Furthermore, step S102 also includes smoothing and encrypting the triangular network so that the side length of the encrypted triangular network is less than a preset side length threshold.
[0019] Furthermore, step S4 specifically includes: isolating all data points belonging to the industrial pipeline from the actual point cloud data model of the plant area, and removing data points that do not belong to the industrial pipeline within the height and horizontal plane range to obtain the point cloud data of the industrial pipeline.
[0020] Furthermore, the fitting of industrial pipelines includes fitting of straight pipe sections, and the fitting process includes the following steps:
[0021] (1) Select multiple points that are evenly distributed along the straight pipe axis as initial seed points;
[0022] (2) Randomly select three seed points from all initial seed points, calculate the cross product of the normal vectors between every two seed points in the three selected seed points, and obtain three axis normal vectors; determine whether the angle between the three axis normal vectors is less than the preset angle threshold. If it is, add the three axis normal vectors together and use the sum as the initial axis direction of the straight pipe; otherwise, return to (1) to reselect initial seed points.
[0023] (3) Project the normals of the three seed points onto the zero plane with the initial axis direction as the normal, and use the projected coordinates of the three seed points to fit a plane circle, and use the center of the fitted circle as the initial end face center of the straight tube.
[0024] (4) Calculate the planar projection distance from the center of the initial end face to each of the three seed points, and determine whether the mean square error of the three planar projection distances is within the allowable error range. If so, take the average of the three planar projection distances as the initial radius of the straight pipe; otherwise, return to (1) to reselect the initial seed point.
[0025] (5) Based on the RANSAC algorithm, take slices along the extension direction of the two ends of the axis with a preset initial step size, and fit the slices into a planar circle. Determine whether the center of the fitted circle is in the direction of the initial axis of the straight pipe and the fitted radius is consistent with the initial radius of the straight pipe. If so, extend the fitting range of the straight pipe to the slice position; otherwise, reduce the step size and re-acquire the slice until the step size is less than the preset step size threshold, and determine the center coordinates and end face radius of the final two ends of the straight pipe.
[0026] Furthermore, the fitting of industrial pipelines includes fitting of straight pipe sections with varying diameters, which is performed in the following two cases;
[0027] (1) For a reducing straight pipe connecting two straight pipes:
[0028] The straight line connecting the centers of the opposite end faces of the two straight pipes is taken as the axis of the variable pipe, and the coordinates of the centers of the opposite end faces are taken as the coordinates of the center of the end face of the variable pipe. The diameters of both ends of the variable pipe are set to be consistent with the diameters of the opposite end faces of the two straight pipes.
[0029] (2) For a reducing straight pipe with only one end connected to a straight pipe:
[0030] The endpoints, radius, and axis of the through-hole straight pipe are used as the initial parameters for the end section of the variable-diameter straight pipe connected to the through-hole straight pipe. Based on the RANSAC algorithm, slices are taken along the direction of the axis extending from the through-hole straight pipe segment with a certain step size. Planar circular fitting is performed on the slices. If the center of the fitted circle is in the axis direction, the variable-diameter straight pipe is extended to the position of this slice, and the center position and diameter value of the slice are recorded. Otherwise, the step size is reduced and the slices are re-acquired until the step size is less than the preset step size threshold, at which point the terminal face of the variable-diameter straight pipe is determined.
[0031] Furthermore, the fitting of industrial pipelines includes fitting of bends, and the fitting process includes the following steps:
[0032] (1) Calculate the spatial angle θ between the two ends of the bend and divide the spatial angle θ into n parts. Calculate the distance l from the center of one end face to the line of intersection of the two ends.
[0033] (2) Take the axis of one end face, offset it with θ / n as the normal direction offset and lθ / n as the center offset, and perform planar circular fitting on the offset plane slice;
[0034] For bends of the through-diameter type, determine if the fitted diameter matches the diameter of the bend's end face. If so, extend the fitted range of the bend to the slice position; otherwise, adjust the normal direction offset and the center offset, and then re-obtain the slice for fitting.
[0035] For bends of varying diameter, determine whether the fitted diameter is between the two diameters on both ends of the bend. If so, extend the fitted range of the bend to the slice position; otherwise, adjust the normal direction offset and the center offset, and then re-obtain the slice for fitting.
[0036] An outdoor industrial pipeline design parameter extraction terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method described above in the embodiments of the present invention.
[0037] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described above in the embodiments of the present invention.
[0038] The present invention adopts the above technical solution, which can quickly capture and accurately restore the actual situation of the factory's outdoor environment, extract the spatial positioning and geometric feature information of outdoor pipelines, and provide basic data for the regular maintenance and upgrading of outdoor pipeline networks in industrial plants. Attached Figure Description
[0039] Figure 1 The diagram shown is a flowchart of Embodiment 1 of the present invention. Detailed Implementation
[0040] To further illustrate the various embodiments, the present invention provides accompanying drawings. These drawings are part of the disclosure of the present invention, primarily used to illustrate the embodiments, and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementations and the advantages of the present invention.
[0041] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments.
[0042] Example 1:
[0043] This invention provides a method for extracting design parameters for outdoor industrial pipelines, such as... Figure 1 As shown, the method includes the following steps:
[0044] S1: Construct a real-world cloud data model of the factory area based on outdoor oblique photographic images of the factory area.
[0045] In this embodiment, outdoor oblique photogrammetry is conducted using aerial photography, with the outdoor pipeline network as the primary subject. The flight path and altitude are planned accordingly, with a forward overlap rate of no less than 80% and a lateral overlap rate of no less than 75%. While ensuring the safety of the flight equipment, the flight altitude should not exceed the average altitude of the outdoor pipeline network by more than 150 meters. A stable RTK connection is maintained throughout the flight, and ground control points can be acquired if necessary. After the photography is completed, the outdoor oblique photogrammetry images are preprocessed, deleting images that do not meet quality requirements, such as those with improper exposure or excessive fog coverage.
[0046] The construction process of the real-world point cloud data model in this embodiment includes the following steps:
[0047] S101: Perform aerial triangulation and overall adjustment calculations on outdoor oblique photographic images to obtain feature matching points for outdoor real-world reconstruction of the factory area;
[0048] S102: Generating a triangular network based on feature matching points;
[0049] S103: After mapping the color values corresponding to each feature matching point in the outdoor oblique photographic image to each corner point in the triangular network, extract each corner point of the mapped triangular network to generate a real-world point cloud data model with true color.
[0050] Furthermore, this embodiment also includes smoothing and encrypting the triangular network according to accuracy requirements, so as to ensure that the side length of the encrypted triangular network is less than a preset side length threshold (such as 1cm).
[0051] S2: Perform image recognition on industrial pipes in outdoor oblique photography images, and obtain the boundary range of industrial pipes based on the recognized images.
[0052] In this embodiment, the image recognition model is constructed using an existing convolutional neural network, and the model is pre-trained before being used for image recognition in step S2.
[0053] During pre-training, the model is trained using outdoor oblique photographic images of a standard industrial plant area. All training images contain segmentation markers for the pixels representing outdoor industrial pipe networks. All pipes can use the same type of segmentation marker, meaning there should be at least two global segmentation marker categories. After training, a subset of oblique photographic images of the outdoor industrial pipes to be extracted is used as a test set to test the recognition accuracy. The ratio of correctly classified pixels to the total number of pixels is calculated. Once the pixel segmentation accuracy on the test set reaches 85% or higher, all images to be recognized can be input into the convolutional neural network to obtain complete pipe recognition results within the plant area. If the segmentation accuracy on the test set does not reach 85%, new training materials are added to the training set, or image enhancement techniques are used to improve the segmentation accuracy on the test set.
[0054] S3: Perform aerial triangulation on the images of the identified industrial pipelines to obtain feature matching points in each image. Compare the feature matching points in each image with the boundary range of the industrial pipeline, extract the feature matching points within the boundary range, and map them into the real-world point cloud data model of the plant area. Set the data points in the real-world point cloud data model corresponding to the feature matching points within the boundary range as data points belonging to the industrial pipeline.
[0055] If the feature matching points in the image are within the boundary range, then these feature matching points are on the industrial pipeline, and the data points (corner points) in the corresponding triangular network should also belong to the data points on the industrial pipeline.
[0056] S4: Based on all data points belonging to the industrial pipeline, obtain the point cloud data of the industrial pipeline.
[0057] All data points belonging to industrial pipelines are isolated from the complete real-world point cloud data model of the plant area, and further data points that are clearly distinguishable as not belonging to industrial pipelines in terms of height and horizontal plane are removed to obtain the point cloud data of industrial pipelines.
[0058] S5: Fitting industrial pipelines based on point cloud data.
[0059] Fitting of industrial pipelines includes fitting of straight pipe sections with continuous diameter, fitting of straight pipe sections with varying diameter, and fitting of pipe bends.
[0060] (I) Fitting of Straight Pipe Sections with Vacancies
[0061] In fitting industrial pipelines, the first step is to fit all straight pipe sections of various diameters. The fitting process includes the following steps:
[0062] (1) Select multiple points that are evenly distributed along the straight pipe axis as initial seed points.
[0063] The number of initial seed points should be between 4 and 6. Too many initial seed points will not significantly improve the accuracy of the fitting results, and the distance between the initial seed points should not be too large.
[0064] (2) Randomly select three seed points T1, T2, and T3 from all initial seed points. Calculate the cross product of the normal vectors between any two selected seed points to obtain three axis normal vectors, i.e., a 12 =n1×n2、a 13 =n1×n3、a 23 =n² × n³. Determine if the angle between the three axis normal vectors is less than a preset angle threshold (e.g., 5°). If so, add the three axis normal vectors together, i.e., a = a. 12 +a 13 +a 23 The sum is used as the initial axis direction of the straight pipe; otherwise, return to (1) to reselect the initial seed point.
[0065] (3) Project the normals L1, L2, and L3 of the three seed points onto the zero plane with the initial axis direction as the normal. Use the projected coordinates c1, c2, and c3 of the three seed points to fit a plane circle. Use the center of the fitted circle as the center of the initial end face of the straight pipe.
[0066] (4) Calculate the planar projection distance from the center of the initial end face to each of the three seed points, and determine whether the mean square error of the three planar projection distances is within the allowable error range. If so, take the average value of the three planar projection distances as the initial radius of the straight pipe; otherwise, return to (1) to reselect the initial seed point.
[0067] (5) Based on the RANSAC algorithm, take slices along the extension direction of the two ends of the axis with a preset initial step size, and fit the slices into a planar circle. Determine whether the center of the fitted circle is in the direction of the initial axis of the straight pipe and the fitted radius is consistent with the initial radius of the straight pipe. If so, extend the fitting range of the straight pipe to the slice position; otherwise, reduce the step size (e.g., reduce it by half) and re-acquire the slices until the step size is less than the preset step size threshold (e.g., 3 cm), and determine the center coordinates and end face radii of the final two end faces of the straight pipe.
[0068] (II) Fitting of Variable Diameter Straight Pipe Section
[0069] After fitting all the standard diameter straight pipes, the center, radius, and axial direction of the end face of the standard diameter straight pipes are used to fit the variable diameter straight pipe sections. The fitting of variable diameter straight pipe sections includes the following two cases:
[0070] (1) For a reducing straight pipe connecting two straight pipes:
[0071] The straight line connecting the centers of the opposite end faces of the two straight pipes is taken as the axis of the reducing pipe, and the coordinates of the centers of the opposite end faces are taken as the coordinates of the center of the end face of the reducing pipe. The diameters of both ends of the reducing pipe are set to be consistent with the diameters of the opposite end faces of the two straight pipes.
[0072] (2) For a reducing straight pipe with only one end connected to a straight pipe:
[0073] The endpoints, radius, and axis of the through-hole straight pipe are used as the initial parameters for the end section of the variable-diameter straight pipe connected to the through-hole straight pipe. Based on the RANSAC algorithm, slices are taken along the direction of the axis extending from the through-hole straight pipe segment with a certain step size. Planar circular fitting is performed on the slices. If the center of the fitted circle is in the axis direction, the variable-diameter straight pipe is extended to the position of this slice, and the center position and diameter value of the slice are recorded. Otherwise, the step size is reduced and the slices are re-acquired until the step size is less than the preset step size threshold, at which point the terminal face of the variable-diameter straight pipe is determined.
[0074] (III) Fitting of the bend section
[0075] After all straight pipes have been fitted, the center of the end face, the direction of the end face axis, and the end face radius are determined using the straight pipes connected to both ends of the bend. The specific steps are as follows:
[0076] (1) Calculate the spatial angle θ between the two ends of the bend and divide the spatial angle θ into n parts. Calculate the distance l from the center of one end face to the line of intersection of the two ends.
[0077] (2) Take the axis of one end face, offset it with θ / n as the normal direction offset and lθ / n as the center offset, and perform planar circular fitting on the offset plane slice;
[0078] For bends of the through-diameter type, determine if the fitted diameter matches the diameter of the bend's end face. If so, extend the fitted range of the bend to the slice position; otherwise, adjust the normal direction offset and the center offset, and then re-obtain the slice for fitting.
[0079] For bends of varying diameter, determine whether the fitted diameter is between the two diameters on both ends of the bend. If so, extend the fitted range of the bend to the slice position; otherwise, adjust the normal direction offset and the center offset, and then re-obtain the slice for fitting.
[0080] The total number of slices is n. To ensure the fitting accuracy of the bend, θ / n should not exceed 5°.
[0081] S6: Extract the design parameters from the industrial pipeline based on the fitting results.
[0082] The design parameters include the coordinates of the center of each end face, the central axis, the radius, and the bending angle. Based on the fitting results of the straight pipe, the coordinates of the center of each end face and the radius are extracted. The axis direction is determined by connecting the coordinates of the center of each end face. Based on the fitting results of the bent pipe, the coordinates of the center of each end face and the radius are extracted. Cubic Bezier curve fitting is performed using the coordinates of the two end faces and the center of each slice. The fitting result is the axis of the bent pipe segment, and the spatial angle between the two end faces is the bending angle of the bent pipe.
[0083] This invention provides intuitive, complete, and accurate facility status information for plant operation and maintenance. The extracted pipeline design parameters can be used to quickly build pipeline models in 3D design software, providing a reliable reference for the repair, dismantling, and replacement of complex pipeline networks. It has broad application prospects in the field of industrial building surveying. Compared to previous surveying methods, this embodiment can complete the measurement and design parameter extraction of large-area pipeline networks in a shorter working time while ensuring the accuracy of the data results.
[0084] Example 2:
[0085] The present invention also provides an outdoor industrial pipeline design parameter extraction terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the method embodiment described above in Embodiment 1 of the present invention.
[0086] Furthermore, as an executable solution, the outdoor industrial pipeline design parameter extraction terminal device can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The outdoor industrial pipeline design parameter extraction terminal device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above-described composition of the outdoor industrial pipeline design parameter extraction terminal device is merely an example and does not constitute a limitation on the device. It may include more or fewer components, or combine certain components, or use different components. For example, the outdoor industrial pipeline design parameter extraction terminal device may also include input / output devices, network access devices, buses, etc., and this embodiment of the invention does not limit this.
[0087] Furthermore, as an executable solution, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the outdoor industrial pipeline design parameter extraction terminal equipment, connecting all parts of the equipment via various interfaces and lines.
[0088] The memory can be used to store the computer programs and / or modules. The processor, by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory, realizes various functions of the outdoor industrial pipeline design parameter extraction terminal device. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0089] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the embodiments of the present invention.
[0090] If the module / unit integrated in the outdoor industrial pipeline design parameter extraction terminal equipment is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc.
[0091] Although the invention has been specifically shown and described in conjunction with preferred embodiments, those skilled in the art should understand that various changes in form and detail may be made to the invention without departing from the spirit and scope of the invention as defined in the appended claims, all of which shall be within the scope of protection of the invention.
Claims
1. A method for extracting design parameters for outdoor industrial pipelines, characterized in that, Includes the following steps: S1: Construct a real-world cloud data model of the factory area based on outdoor oblique photographic images of the factory area; S2: Perform image recognition on industrial pipes in outdoor oblique photography images, and obtain the boundary range of industrial pipes based on the images of the recognized industrial pipes; S3: Perform aerial triangulation on the image of the identified industrial pipeline to obtain the feature matching points in each image. Compare the feature matching points in each image with the boundary range of the industrial pipeline, extract the feature matching points within the boundary range, and map them into the real-world point cloud data model of the factory area. Set the corresponding data points in the real-world point cloud data model as data points belonging to the industrial pipeline. S4: Based on all data points belonging to the industrial pipeline, obtain the point cloud data of the industrial pipeline; S5: Fitting industrial pipelines based on point cloud data; S6: Extract the design parameters from the industrial pipeline based on the fitting results.
2. The method for extracting design parameters of outdoor industrial pipelines according to claim 1, characterized in that: In the shooting of outdoor oblique photography images, aerial photography is used to plan the shooting route and flight altitude with outdoor pipelines as the main shooting object.
3. The method for extracting design parameters of outdoor industrial pipelines according to claim 1, characterized in that: The construction process of the real-world point cloud data model in step S1 includes the following steps: S101: Perform aerial triangulation and overall adjustment calculations on outdoor oblique photographic images to obtain feature matching points for outdoor real-world reconstruction of the factory area; S102: Generating a triangular network based on feature matching points; S103: After mapping the color values corresponding to each feature matching point in the outdoor oblique photographic image to each corner point in the triangular network, extract each corner point of the mapped triangular network to generate a real-world point cloud data model.
4. The method for extracting design parameters of outdoor industrial pipelines according to claim 1, characterized in that: Step S102 also includes smoothing and encrypting the triangular network so that the side length of the encrypted triangular network is less than a preset side length threshold.
5. The method for extracting design parameters of outdoor industrial pipelines according to claim 1, characterized in that: Step S4 specifically includes: isolating all data points belonging to the industrial pipeline from the actual point cloud data model of the plant area, and removing data points that do not belong to the industrial pipeline within the height and horizontal plane range to obtain the point cloud data of the industrial pipeline.
6. The method for extracting design parameters of outdoor industrial pipelines according to claim 1, characterized in that: The fitting of industrial pipelines includes the fitting of straight pipe sections. The fitting process includes the following steps: (1) Select multiple points that are evenly distributed along the straight pipe axis as initial seed points; (2) Randomly select three seed points from all initial seed points, calculate the cross product of the normal vectors between every two seed points in the three selected seed points, and obtain three axis normal vectors; determine whether the angle between the three axis normal vectors is less than the preset angle threshold. If it is, add the three axis normal vectors together and use the sum as the initial axis direction of the straight pipe; otherwise, return to (1) to reselect initial seed points. (3) Project the normals of the three seed points onto the zero plane with the initial axis direction as the normal, and use the projected coordinates of the three seed points to fit a plane circle, and use the center of the fitted circle as the initial end face center of the straight tube. (4) Calculate the planar projection distance from the center of the initial end face to each of the three seed points, and determine whether the mean square error of the three planar projection distances is within the allowable error range. If so, take the average of the three planar projection distances as the initial radius of the straight pipe; otherwise, return to (1) to reselect the initial seed point. (5) Based on the RANSAC algorithm, take slices along the extension direction of the two ends of the axis with a preset initial step size, and fit the slices into a planar circle. Determine whether the center of the fitted circle is in the direction of the initial axis of the straight pipe and the fitted radius is consistent with the initial radius of the straight pipe. If so, extend the fitting range of the straight pipe to the slice position; otherwise, reduce the step size and re-acquire the slice until the step size is less than the preset step size threshold, and determine the center coordinates and end face radius of the final two ends of the straight pipe.
7. The method for extracting design parameters of outdoor industrial pipelines according to claim 1, characterized in that: Fitting of industrial pipelines includes fitting of straight pipe sections with varying diameters, which is performed in the following two cases; (1) For a reducing straight pipe connecting two straight pipes: The straight line connecting the centers of the opposite end faces of the two straight pipes is taken as the axis of the variable pipe, and the coordinates of the centers of the opposite end faces are taken as the coordinates of the center of the end face of the variable pipe. The diameters of both ends of the variable pipe are set to be consistent with the diameters of the opposite end faces of the two straight pipes. (2) For a reducing straight pipe with only one end connected to a straight pipe: The endpoints, radius, and axis of the through-hole straight pipe are used as the initial parameters for the end section of the variable-diameter straight pipe connected to the through-hole straight pipe. Based on the RANSAC algorithm, slices are taken along the direction of the axis extending from the through-hole straight pipe segment with a certain step size. Planar circular fitting is performed on the slices. If the center of the fitted circle is in the axis direction, the variable-diameter straight pipe is extended to the position of this slice, and the center position and diameter value of the slice are recorded. Otherwise, the step size is reduced and the slices are re-acquired until the step size is less than the preset step size threshold, at which point the terminal face of the variable-diameter straight pipe is determined.
8. The method for extracting design parameters of outdoor industrial pipelines according to claim 1, characterized in that: Fitting industrial pipelines includes fitting bends, and the fitting process includes the following steps: (1) Calculate the spatial angle θ between the two ends of the bend and divide the spatial angle θ into n parts. Calculate the distance l from the center of one end face to the line of intersection of the two ends. (2) Take the axis of one end face, offset it with θ / n as the normal direction offset and lθ / n as the center offset, and perform planar circular fitting on the offset plane slice; For bends of the through-diameter type, determine if the fitted diameter matches the diameter of the bend's end face. If so, extend the fitted range of the bend to the slice position; otherwise, adjust the normal direction offset and the center offset, and then re-obtain the slice for fitting. For bends of varying diameter, determine whether the fitted diameter is between the two diameters on both ends of the bend. If so, extend the fitted range of the bend to the slice position; otherwise, adjust the normal direction offset and the center offset, and then re-obtain the slice for fitting.
9. A terminal device for extracting design parameters of outdoor industrial pipelines, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any one of claims 1 to 8.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 8.
Citation Information
Patent Citations
Pipeline inner surface detection method and device based on three-dimensional point cloud
CN112581457A
Three-dimensional point cloud-based aero-engine pipeline full-range gap measurement method and application
CN114419012A