Tower foot weld seam information extraction method, device and equipment and storage medium

Abstract

The present application is suitable for the field of tower foot welding, and discloses a tower foot weld information extraction method, device, equipment and storage medium, the method comprising: processing the obtained tower foot overhead point cloud data, obtaining the main shoe plate thickness, the secondary shoe plate thickness, the bottom plate size and the vertical weld starting point coordinates of the first quadrant; processing the obtained tower foot side view point cloud data, and combining the main shoe plate thickness, the secondary shoe plate thickness and the bottom plate size to obtain the vertical weld end point coordinates, the horizontal weld end point coordinates, the first horizontal weld starting point coordinates, the second horizontal weld starting point coordinates and the inter-plate angle of the first quadrant; determining the first horizontal weld starting point coordinates, the second horizontal weld starting point coordinates, the vertical weld starting point coordinates and the inter-plate angle of the second quadrant, the third quadrant and the fourth quadrant according to the foregoing information, the method can accurately extract the size information and the weld information of the tower foot through machine vision and point cloud data processing technology.

Description

Technical Field

[0001] This invention relates to the field of tower foot welding, and in particular to a method, apparatus, equipment, and storage medium for extracting tower foot weld information. Background Technology

[0002] With the continuous expansion of power grid construction and the continuous increase in transmitted electricity, transmission line towers, as the most basic infrastructure of power grid construction, have a large demand for tower feet. The existing welding teams of enterprises can no longer meet the current production needs, which puts forward an urgent requirement for the development of automatic and intelligent welding robots for tower foot welding.

[0003] In recent years, advanced manufacturing companies both domestically and internationally have used programming pendant welding robots to weld tower feet, improving processing efficiency to some extent. However, due to differences in tower foot dimensions and non-standardized structures, the teaching and programming time is lengthy, severely impacting welding efficiency. The latest tower foot welding robots in the industry achieve teach-free programming by manually inputting key tower foot parameters and using laser weld seam positioning. However, each manual input of key parameters still takes 3-5 minutes, resulting in insufficient efficiency. Furthermore, due to assembly errors, there is a certain discrepancy between manually input tower foot information and the actual tower foot, leading to a high failure rate in automated welding.

[0004] Therefore, existing technologies still need improvement and development. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for extracting tower foot weld information. It utilizes machine vision and point cloud data processing technology, combined with geometric and spatial calculation methods, to accurately extract the dimensional information and weld information of the tower foot, thus solving the problem of tower foot assembly errors.

[0006] The first aspect of the present invention provides a method for extracting tower foot weld information, comprising: acquiring tower foot top-view point cloud data and tower foot side-view point cloud data; processing the tower foot top-view point cloud data to obtain the thickness of the main boot plate, the thickness of the secondary boot plate, the size of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant; processing the tower foot side-view point cloud data, and combining the thickness of the main boot plate, the thickness of the secondary boot plate, and the size of the base plate to obtain the coordinates of the end point of the vertical weld, the end point of the horizontal weld, the starting point of the first horizontal weld, the starting point of the second horizontal weld, and the inter-plate angle in the first quadrant; and based on the coordinates of the starting point of the vertical weld in the first quadrant and the starting point of the first horizontal weld... The starting point coordinates, the second horizontal weld starting point coordinates, the main shoe plate thickness, the secondary shoe plate thickness, and the base plate dimensions determine the starting point coordinates of the first horizontal weld, the second horizontal weld, the vertical weld, and the inter-plate angle in the second, third, and fourth quadrants. The main shoe plate thickness, the secondary shoe plate thickness, and the base plate dimensions are integrated to form the tower foot dimension information. The starting point coordinates of the first horizontal weld, the second horizontal weld, the vertical weld, the horizontal weld end point, the vertical weld end point, and the inter-plate angle in the first, second, third, and fourth quadrants are also integrated to form the tower foot weld information.

[0007] Preferably, the tower foot is captured by an industrial 3D camera from both top and side views to obtain top-view point cloud data and side-view point cloud data.

[0008] Preferably, the step of processing the tower foot top-view point cloud data to obtain the thickness of the main boot plate, the thickness of the secondary boot plate, the dimensions of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant includes: segmenting the tower foot top-view point cloud data using a planar segmentation algorithm, and extracting the tower foot top-view main body data based on the segmented top-view point cloud data; extracting the first tower foot bottom surface point cloud data from the tower foot top-view main body data, and calculating the base plate side length information based on the first tower foot bottom surface point cloud data; cropping the tower foot top-view main body data according to a preset angle threshold to obtain the first boot plate horizontal plane point cloud data, and calculating the thickness information of the main boot plate, the thickness information of the secondary boot plate, and the coordinates of the starting point of the vertical weld based on the first boot plate horizontal plane point cloud data.

[0009] Preferably, before segmenting the tower foot top-view point cloud data using a planar segmentation algorithm, the method includes: performing noise reduction and filtering processing on the tower foot top-view point cloud data.

[0010] Preferably, the plane segmentation algorithm is the RANSAC algorithm.

[0011] Preferably, the step of obtaining the thickness information of the main shoe plate, the thickness information of the secondary shoe plate, and the coordinates of the starting point of the vertical weld based on the point cloud data of the first shoe plate horizontal plane includes: performing linear segmentation on the point cloud data of the first shoe plate horizontal plane to divide it into main shoe plate point cloud data and secondary shoe plate point cloud data; extracting the edge information of the main shoe plate point cloud data and the secondary shoe plate point cloud data, and performing linear fitting on the edges of the main shoe plate and the secondary shoe plate respectively to obtain the two long sides of the top surface of the main shoe plate and the two long sides of the top surface of the secondary shoe plate; calculating the distance between the two long sides of the top surface of the main shoe plate to obtain the thickness information of the main shoe plate; calculating the distance between the two long sides of the top surface of the secondary shoe plate to obtain the thickness information of the secondary shoe plate; and determining the coordinates of the starting point of the vertical weld based on the coordinates of the intersection of the two long sides of the top surface of the main shoe plate and the two long sides of the top surface of the secondary shoe plate.

[0012] Preferably, the step of processing the tower foot side view point cloud data and obtaining the coordinates of the vertical weld endpoint, horizontal weld endpoint, first horizontal weld start point, second horizontal weld start point, and plate angle in the first quadrant by combining the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate includes: segmenting the tower foot side view point cloud data using a planar segmentation algorithm, and extracting the tower foot side view main body data based on the segmented side view point cloud data; extracting the tower foot bottom surface feature information and tower foot side surface feature information from the tower foot side view main body data, and determining the tower foot bottom surface feature information and tower foot side surface feature information based on the tower foot bottom surface feature information and tower foot side surface feature information. The intersection lines of the main shoe plate and the base plate, the intersection lines of the secondary shoe plate and the base plate, and the corner points between the main shoe plate, secondary shoe plate, and base plate are determined. These corner points serve as the endpoints of the horizontal and vertical welds. The centroids of the overall point cloud of the tower foot, the plane containing the base plate, the side surface containing the main shoe plate, and the side surface containing the secondary shoe plate are extracted from the side view data of the tower foot. Three direction vectors are formed based on these vectors. The plane containing the base plate, the side surface containing the main shoe plate, and the side surface containing the secondary shoe plate are then calculated. The angle between the normal vectors of the sides where the plate is located is determined. If the angle is greater than 90 degrees, the direction of the normal vector of the corresponding plane is adjusted to the opposite direction. The angle between the plates is calculated using the normal vectors of the plane where the base plate is located, the normal vectors of the sides where the main shoe plate is located, and the normal vectors of the sides where the secondary shoe plate is located. The angle between the plates includes the angle between the base plate and the main shoe plate, the angle between the base plate and the secondary shoe plate, and the angle between the main shoe plate and the secondary shoe plate. The horizontal point cloud data of the second shoe plate is extracted from the side view of the tower foot, and the clipping plane is determined based on the horizontal point cloud data of the second shoe plate. The side view of the tower foot is then clipped according to the clipping plane to obtain... Obtain point cloud data of the second tower foot bottom surface; extract the edge of the base plate based on the point cloud data of the second tower foot bottom surface, and perform straight line fitting on the edge of the base plate. Take the straight line that is parallel to the intersection line of the main shoe plate and the base plate and is farthest away as the first outer edge straight line of the base plate, and take the straight line that is parallel to the intersection line of the auxiliary shoe plate and the base plate and is farthest away as the second outer edge straight line of the base plate. Determine the coordinates of the starting point of the first horizontal weld based on the coordinates of the intersection point of the first outer edge straight line of the base plate and the intersection line of the main shoe plate and the base plate, and determine the coordinates of the starting point of the second horizontal weld based on the coordinates of the intersection point of the second outer edge straight line of the base plate and the intersection line of the auxiliary shoe plate and the base plate.

[0013] A second aspect of the present invention provides a tower foot weld information extraction device, comprising: an acquisition module for acquiring tower foot top-view point cloud data and tower foot side-view point cloud data; a first processing module for processing the tower foot top-view point cloud data to acquire the thickness of the main boot plate, the thickness of the secondary boot plate, the size of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant; a second processing module for processing the tower foot side-view point cloud data and, in conjunction with the thickness of the main boot plate, the thickness of the secondary boot plate, and the size of the base plate, acquiring the coordinates of the end point of the vertical weld, the end point of the horizontal weld, the starting point of the first horizontal weld, the starting point of the second horizontal weld, and the inter-plate angle in the first quadrant; and a calculation module for calculating the vertical weld starting point in the first quadrant. The starting point coordinates, the starting point coordinates of the first horizontal weld, the starting point coordinates of the second horizontal weld, the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate determine the starting point coordinates of the first horizontal weld, the starting point coordinates of the second horizontal weld, the starting point coordinates of the vertical weld, and the inter-plate angle in the second, third, and fourth quadrants. An integration module is used to integrate the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate as tower foot size information, and to integrate the starting point coordinates of the first horizontal weld, the starting point coordinates of the second horizontal weld, the starting point coordinates of the vertical weld, the ending point coordinates of the horizontal weld, the ending point coordinates of the vertical weld, and the inter-plate angle in the first, second, third, and fourth quadrants as tower foot weld information.

[0014] A third aspect of the present invention provides a tower foot weld information extraction device, comprising: a memory and at least one processor, wherein the memory stores computer-readable instructions, and the memory and the at least one processor are interconnected via a circuit; the at least one processor invokes the computer-readable instructions in the memory to cause the tower foot weld information extraction device to perform the various steps of the tower foot weld information extraction method described above.

[0015] A fourth aspect of the present invention provides a computer-readable storage medium storing computer-readable instructions that, when executed on a computer, cause the computer to perform the steps of the tower foot weld information extraction method described above.

[0016] The tower foot weld information extraction method provided by this invention acquires tower foot top-view point cloud data and tower foot side-view point cloud data, and processes and calculates these data to obtain tower foot size information and tower foot weld information. This allows for precise weld positioning via a weld tracking device. This method can identify any tower foot, exhibits strong stability and high accuracy. Furthermore, by utilizing machine vision and point cloud data processing technology, combined with geometric and spatial calculation methods, this method can accurately extract tower foot size information and weld information, solving the problem of tower foot assembly errors. In addition, this method eliminates the need for manual parameter input, enabling automated welding without teaching. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the tower foot weld information extraction method provided in the embodiments of the present invention;

[0019] Figure 2 This is a schematic diagram of the tower foot main body data from a top view provided in an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of the feature plane of the main boot plate and the secondary boot plate provided in an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of the side view of the main body data of the tower foot provided in an embodiment of the present invention. Figure 1 ;

[0022] Figure 5 This is a schematic diagram of the side view of the main body data of the tower foot provided in an embodiment of the present invention. Figure 2 ;

[0023] Figure 6 This is a schematic diagram of the tower foot weld information extraction device provided in an embodiment of the present invention;

[0024] Figure 7 This is a schematic diagram of the tower foot weld information extraction device provided in an embodiment of the present invention. Detailed Implementation

[0025] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” or “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 In this embodiment of the invention, a method for extracting tower foot weld information includes:

[0027] S101. Obtain the top-view point cloud data and the side-view point cloud data of the tower base.

[0028] In this embodiment, the tower foot includes a base plate, a main shoe plate, and a secondary shoe plate, which are arranged in a cross shape on the base plate.

[0029] S102. Process the top-view point cloud data of the tower foot to obtain the thickness of the main shoe plate, the thickness of the secondary shoe plate, the size of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant.

[0030] S103. Process the point cloud data of the tower foot side view, and combine the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate to obtain the coordinates of the vertical weld end point, the horizontal weld end point, the coordinates of the first horizontal weld start point, the coordinates of the second horizontal weld start point, and the plate angle in the first quadrant.

[0031] S104. Based on the coordinates of the starting point of the vertical weld in the first quadrant, the starting point of the first horizontal weld, the starting point of the second horizontal weld, the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate, determine the coordinates of the starting point of the first horizontal weld, the starting point of the second horizontal weld, the starting point of the vertical weld, and the angle between the plates in the second, third, and fourth quadrants.

[0032] S105. Integrate the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate into tower foot dimension information. Integrate the coordinates of the starting point of the first horizontal weld, the starting point of the second horizontal weld, the starting point of the vertical weld, the ending point of the horizontal weld, the ending point of the vertical weld, and the inter-plate angle in the first, second, third, and fourth quadrants into tower foot weld information.

[0033] During use, the tower leg size information and tower leg weld information are converted into robot coordinates and transmitted to the robot. The weld is used to achieve precise weld positioning, thereby enabling intelligent welding of the tower legs without teaching.

[0034] The tower foot weld information extraction method in this embodiment acquires tower foot top-view point cloud data and tower foot side-view point cloud data, and processes and calculates these data to obtain tower foot size information and tower foot weld information. This allows for precise weld positioning using a weld tracking device. This method can identify any tower foot, exhibits strong stability and high accuracy. Furthermore, by utilizing machine vision and point cloud data processing technology, combined with geometric and spatial calculation methods, this method can accurately extract tower foot size information and weld information, solving the problem of tower foot assembly errors. In addition, this method can eliminate the need for manual parameter input, achieving automated welding without teaching.

[0035] In this embodiment, in step S101, the tower foot is photographed from the top and side views using an industrial 3D camera to obtain the top view point cloud data and the side view point cloud data of the tower foot.

[0036] Specifically, an industrial 3D camera is mounted at the end of a robot arm, and a hand-eye calibration algorithm is used to convert the camera coordinate system to the robot coordinate system. The tower legs are fixed on a dual-axis positioner. Since the industrial 3D camera acquires workpiece depth information through the cooperation of two cameras, a single shot cannot capture the entire workpiece model. Therefore, in this implementation, the industrial 3D camera takes a top-down shot from directly above the tower legs to obtain top-view point cloud data, and then takes a side shot to obtain side-view point cloud data. The side shot mainly captures the quadrant containing the main and secondary boot plates, facilitating accurate data extraction. Finally, the point cloud data from the two shots are converted to the robot coordinate system for tower leg stitching.

[0037] In step S102, the tower foot top-view point cloud data is processed to obtain the thickness of the main shoe plate, the thickness of the secondary shoe plate, the dimensions of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant. This includes: segmenting the tower foot top-view point cloud data using a planar segmentation algorithm, and extracting the tower foot top-view main body data (such as...) from the segmented top-view point cloud data. Figure 2 (As shown); Extract the point cloud data of the bottom surface of the first tower foot from the top-view main body data of the tower foot, and obtain the side length information of the bottom plate based on the point cloud data of the bottom surface of the first tower foot; Perform point cloud cropping on the top-view main body data of the tower foot according to the preset angle threshold to obtain the point cloud data of the horizontal plane of the first shoe plate, and obtain the thickness information of the main shoe plate, the thickness information of the secondary shoe plate, and the coordinates of the starting point of the vertical weld based on the point cloud data of the horizontal plane of the first shoe plate.

[0038] In this embodiment, before using the planar segmentation algorithm to segment the tower foot top-view point cloud data, the tower foot top-view point cloud data can be denoised and filtered to ensure data quality.

[0039] In this embodiment, the plane segmentation algorithm can be the RANSAC algorithm or a geometric feature-based method.

[0040] Understandably, since the tower base is fixed to the dual-axis positioner, the point cloud data package obtained by taking a top-down view of the tower base using an industrial 3D camera contains the dual-axis positioner data.

[0041] Using a planar segmentation algorithm to segment the tower foot top-view point cloud data, multiple planar information can be obtained. It is necessary to find the planar information whose plane normal vector is consistent with the Z-axis direction of the robot, mainly including the planar information of the dual-axis positioner and the planar information of the tower foot bottom surface. Then, the planar information of the dual-axis positioner and the planar information of the tower foot bottom surface are distinguished according to the height threshold. Based on this, the planar information of the dual-axis positioner is removed, and the remaining point cloud data is the main top-view data of the tower foot.

[0042] Furthermore, based on the distinction between the planar information of the dual-axis positioner and the planar information of the tower foot bottom, the thickness information of the base plate can be obtained according to the height difference, so as to determine the tower foot size in the subsequent welding process.

[0043] In this embodiment, a plane fitting method (such as least squares fitting) is used to process the top-view data of the tower base to fit a planar model of the tower base bottom surface. Using the fitted planar model, the top-view data of the tower base can be projected onto this plane, or the range of the top-view data can be limited according to the plane equation to extract the point cloud data near the bottom surface as the first tower base bottom surface point cloud data.

[0044] In this embodiment, since the base of the tower foot is a square, the two points that are furthest apart in the point cloud are found based on the point cloud data of the first base of the tower foot, and these two points are used as the two diagonal corner points to obtain the side length information of the base plate.

[0045] In this embodiment, the feature vectors of the horizontal planes of the main boot plate and the secondary boot plate are in the same direction as the feature vectors of the base of the tower. Therefore, by cropping the point cloud data of the tower base from above according to a preset angle threshold, the point cloud data of the horizontal plane of the first boot plate can be obtained.

[0046] In this embodiment, the thickness information of the main shoe plate, the thickness information of the secondary shoe plate, and the coordinates of the starting point of the vertical weld are obtained based on the point cloud data of the first shoe plate's horizontal plane. Specifically, this includes: performing linear segmentation on the point cloud data of the first shoe plate's horizontal plane, classifying the point cloud data of the main shoe plate and the secondary shoe plate, extracting the edge information of the point cloud data of the main shoe plate and the secondary shoe plate respectively, and performing linear fitting on the edges of the main shoe plate and the secondary shoe plate respectively to obtain the two long sides of the top surface of the main shoe plate and the two long sides of the top surface of the secondary shoe plate (e.g., ...). Figure 3 As shown, the thickness information of the main shoe plate is obtained by calculating the distance between the two long sides of the top surface of the main shoe plate, and the thickness information of the secondary shoe plate is obtained by calculating the distance between the two long sides of the top surface of the secondary shoe plate. The coordinates of the starting point of the vertical weld are determined based on the coordinates of the intersection of the two long sides of the top surface of the main shoe plate and the two long sides of the top surface of the secondary shoe plate.

[0047] In step S103, the side view point cloud data of the tower foot is processed, and the coordinates of the vertical weld end point, horizontal weld end point, first horizontal weld start point, and second horizontal weld start point, as well as the plate angle, are obtained in the first quadrant by combining the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate. This includes:

[0048] The side view point cloud data of the tower base was segmented using a planar segmentation algorithm, and the main side view data of the tower base (such as...) was extracted from the segmented side view point cloud data. Figure 4 (as shown);

[0049] Extract the base and side features of the tower foot from the side-view data, and determine the intersection line between the main shoe plate and the base plate based on these features (e.g., ...). Figure 4 L1), the intersection line between the secondary shoe plate and the bottom plate (e.g., L1), Figure 4 L2 in the middle) and the corner points between the main boot plate, the secondary boot plate and the sole plate (such as ... Figure 4 In point A), the corner point serves as the endpoint of both the horizontal and vertical weld seams;

[0050] The centroids of the overall point cloud of the tower base, the plane containing the base plate, the side of the main boot plate, and the side of the secondary boot plate are extracted from the side view data of the tower base. Three directional vectors are then formed based on these centroids (e.g., [missing information]). Figure 5 (n1, n2, n3 in the text);

[0051] Calculate the angle between the normal vectors of the plane containing the base plate, the side containing the main boot plate, and the side containing the secondary boot plate. If the angle is greater than 90 degrees, adjust the direction of the normal vector of the corresponding plane to the opposite direction.

[0052] The angle between the plates is obtained by using the normal vector of the plane where the base plate is located, the normal vector of the side where the main shoe plate is located, and the normal vector of the side where the secondary shoe plate is located. The angle between the plates includes the angle between the base plate and the main shoe plate, the angle between the base plate and the secondary shoe plate, and the angle between the main shoe plate and the secondary shoe plate.

[0053] Extract the horizontal point cloud data of the second boot plate from the side view of the main body data of the tower foot, determine the clipping plane based on the horizontal point cloud data of the second boot plate, and clip the side view of the main body data of the tower foot based on the clipping plane to obtain the point cloud data of the bottom surface of the second tower foot.

[0054] The edges of the base plate are extracted based on the point cloud data of the second tower foot surface, and straight lines are fitted to the edges of the base plate. The straight line that is parallel to the intersection line of the main shoe plate and the base plate and is farthest away is taken as the first outer edge straight line of the base plate (e.g., Figure 4 In L3), the straight line that is parallel to and furthest from the intersection line of the secondary shoe plate and the bottom plate is taken as the second outer edge straight line of the bottom plate (e.g., L3). Figure 4 L4 in the diagram represents the coordinates of the intersection point of the straight line of the first outer edge of the base plate and the intersection line of the auxiliary shoe plate and the base plate (e.g., L4). Figure 4 In the diagram, B) is used as the coordinate of the starting point of the first horizontal weld, and the coordinate of the intersection of the straight line of the second outer edge of the base plate and the line of intersection between the main shoe plate and the base plate is used as the coordinate of the starting point of the second horizontal weld (e.g., B) is used as the coordinate of the starting point of the second horizontal weld. Figure 4 (C in the middle).

[0055] In this embodiment, before using the planar segmentation algorithm to segment the tower foot side view point cloud data, the tower foot side view point cloud data can be denoised and filtered to ensure data quality.

[0056] In this embodiment, the plane segmentation algorithm can be the RANSAC algorithm or a geometric feature-based method.

[0057] Understandably, since the tower legs are fixed to the dual-axis positioner, the point cloud data package obtained by taking pictures of the tower legs from the side using an industrial 3D camera contains the dual-axis positioner data.

[0058] Using a planar segmentation algorithm to segment the tower foot top-view point cloud data, multiple planar information can be obtained. It is necessary to find the planar information whose plane normal vector is consistent with the Z-axis direction of the robot, mainly including the planar information of the dual-axis positioner and the planar information of the tower foot bottom surface. Then, the planar information of the dual-axis positioner and the planar information of the tower foot bottom surface are distinguished according to the height threshold. Based on this, the planar information of the dual-axis positioner is removed, and the remaining point cloud data is the main top-view data of the tower foot.

[0059] In step S104, given the direction vector of the line, the distance between two points, and the coordinates of one point, the coordinates of the other point can be calculated. Given that the angle between two adjacent quadrants is 180 degrees, and knowing the angle vector of the main shoe plate in one quadrant and the angle between the plates, the angle between the plates of the plane in the other quadrant can be calculated.

[0060] Based on this principle, the coordinates of the starting point of the vertical weld in the first quadrant, the starting point of the first horizontal weld, the starting point of the second horizontal weld, the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate are used to determine the coordinates of the starting point of the first horizontal weld, the starting point of the second horizontal weld, the starting point of the vertical weld, and the angle between the plates in the second, third, and fourth quadrants.

[0061] The settlement method for the purchased equipment project in the embodiments of the present invention has been described above. The apparatus in the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 6 The implementation methods of the equipment procurement project settlement device in this invention include:

[0062] The acquisition module 201 is used to acquire the top view point cloud data and the side view point cloud data of the tower foot.

[0063] The first processing module 202 is used to process the tower foot top view point cloud data to obtain the thickness of the main shoe plate, the thickness of the secondary shoe plate, the size of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant.

[0064] The second processing module 203 is used to process the tower foot side view point cloud data, and combine the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate to obtain the coordinates of the vertical weld end point, the horizontal weld end point, the coordinates of the first horizontal weld start point, the coordinates of the second horizontal weld start point, and the plate angle in the first quadrant.

[0065] Calculation module 204 is used to determine the coordinates of the first horizontal weld start point, the second horizontal weld start point, and the plate angle in the second, third, and fourth quadrants based on the coordinates of the vertical weld start point in the first quadrant, the coordinates of the first horizontal weld start point, the coordinates of the second horizontal weld start point, the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate.

[0066] The integration module 205 is used to integrate the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate into tower foot size information, and to integrate the coordinates of the first horizontal weld start point, the second horizontal weld start point, the vertical weld start point, the horizontal weld end point, the vertical weld end point, and the plate angle in the first quadrant, the second quadrant, the third quadrant, and the fourth quadrant into tower foot weld information.

[0067] In this embodiment, by acquiring top-view and side-view point cloud data of the tower foot, and processing and calculating these data, tower foot size information and weld information are obtained. This allows for precise weld positioning via a weld tracking device. This method can identify any tower foot, exhibiting strong stability and high accuracy. Furthermore, by utilizing machine vision and point cloud data processing technologies, combined with geometric and spatial calculation methods, this method can accurately extract tower foot size and weld information, resolving tower foot assembly errors. In addition, this method eliminates the need for manual parameter input, enabling automated welding without teaching.

[0068] above Figure 6 The procurement equipment project settlement device in this embodiment of the invention is described in detail from the perspective of modular functional entities. The procurement equipment project settlement device in this embodiment of the invention is described in detail below from the perspective of hardware processing.

[0069] Figure 7 This is a schematic diagram of the structure of a procurement equipment project settlement device provided in an embodiment of the present invention. The device 300 can vary significantly due to different configurations or performance, and may include one or more central processing units (CPUs) 310 (e.g., one or more processors) and a memory 320, and one or more storage media 330 (e.g., one or more mass storage devices) for storing application programs 333 or data 332. The memory 320 and storage media 330 can be temporary or persistent storage. The program stored in the storage media 330 may include one or more modules (not shown), each module including a series of instruction operations on the device 300. Furthermore, the processor 310 may be configured to communicate with the storage media 330 and execute the series of instruction operations in the storage media on the device 300.

[0070] Device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input / output interfaces 360, and / or one or more operating systems 331, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.

[0071] This invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the procurement equipment project settlement method.

[0072] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0073] If the integrated unit 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, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0074] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0075] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for extracting tower foot weld information, characterized in that, include: Acquire the top-view point cloud data and the side-view point cloud data of the tower base; The top-view point cloud data of the tower foot is processed to obtain the thickness of the main shoe plate, the thickness of the secondary shoe plate, the size of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant; The point cloud data of the tower foot side view is processed, and the coordinates of the vertical weld end point, horizontal weld end point, first horizontal weld start point, second horizontal weld start point, and plate angle in the first quadrant are obtained by combining the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate. Based on the coordinates of the starting point of the vertical weld in the first quadrant, the coordinates of the starting point of the first horizontal weld, the coordinates of the starting point of the second horizontal weld, the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate, determine the coordinates of the starting point of the first horizontal weld, the coordinates of the starting point of the second horizontal weld, the coordinates of the starting point of the vertical weld, and the coordinates of the starting point of the second horizontal weld, and the coordinates of the starting point of the third vertical weld, and the angle between the plates in the fourth quadrant. The thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate are integrated to form the tower foot size information. The coordinates of the starting point of the first horizontal weld, the starting point of the second horizontal weld, the starting point of the vertical weld, the ending point of the horizontal weld, the ending point of the vertical weld, and the inter-plate angle in the first, second, third, and fourth quadrants are integrated to form the tower foot weld information. The process of processing the tower foot side view point cloud data and combining the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate to obtain the coordinates of the vertical weld end point, the horizontal weld end point, the coordinates of the first horizontal weld start point, the coordinates of the second horizontal weld start point, and the plate angle in the first quadrant includes: using a plane segmentation algorithm to segment the tower foot side view point cloud data, and extracting the tower foot side view main body data based on the segmented side view point cloud data; The base surface feature information and side surface feature information of the tower foot are extracted from the side view main body data of the tower foot. Based on the base surface feature information and the side surface feature information of the tower foot, the intersection line between the main shoe plate and the base plate, the intersection line between the secondary shoe plate and the base plate, and the corner points between the main shoe plate, the secondary shoe plate, and the base plate are determined. These corner points serve as the endpoints of the horizontal and vertical welds. The overall point cloud centroid of the tower foot, the point cloud centroid of the plane where the base plate is located, the point cloud centroid of the side surface where the main shoe plate is located, and the secondary shoe plate are extracted from the side view main body data of the tower foot. The centroid of the point cloud on the side of the base plate is determined, and three direction vectors are formed based on the centroid of the overall point cloud of the tower foot, the centroid of the point cloud on the plane of the base plate, the centroid of the point cloud on the side of the main shoe plate, and the centroid of the point cloud on the side of the secondary shoe plate. The angle between the normal vectors of the plane of the base plate, the side of the main shoe plate, and the side of the secondary shoe plate is calculated respectively. If the angle is greater than 90 degrees, the direction of the normal vector of the corresponding plane is adjusted to the opposite direction. The normal vectors of the plane of the base plate, the side of the main shoe plate, and the secondary shoe plate are used to determine the direction of the point cloud. The angles between plates are calculated using the normal vector of the side where the plate is located. These angles include the angle between the base plate and the main shoe plate, the angle between the base plate and the auxiliary shoe plate, and the angle between the main shoe plate and the auxiliary shoe plate. The horizontal point cloud data of the second shoe plate is extracted from the side-view main body data of the tower foot. A cutting plane is determined based on this data, and the side-view main body data of the tower foot is cut according to the cutting plane to obtain the bottom point cloud data of the second tower foot. The edge of the base plate is extracted from the bottom point cloud data of the second tower foot, and a straight line is fitted to the edge of the base plate. The straight line parallel to the intersection line of the main shoe plate and the base plate and furthest away is taken as the first outer edge straight line of the base plate. The straight line parallel to the intersection line of the auxiliary shoe plate and the base plate and furthest away is taken as the second outer edge straight line of the base plate. The coordinates of the starting point of the first horizontal weld are determined based on the coordinates of the intersection point of the first outer edge straight line of the base plate and the intersection line of the main shoe plate and the base plate. The coordinates of the starting point of the second horizontal weld are determined based on the coordinates of the intersection point of the second outer edge straight line of the base plate and the intersection line of the auxiliary shoe plate and the base plate.

2. The method for extracting tower foot weld information as described in claim 1, characterized in that, The tower base is captured by an industrial 3D camera from both top and side views to obtain top-view point cloud data and side-view point cloud data.

3. The method for extracting tower foot weld information as described in claim 1, characterized in that, The process of processing the top-view point cloud data of the tower foot to obtain the thickness of the main shoe plate, the thickness of the secondary shoe plate, the dimensions of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant includes: The planar segmentation algorithm is used to segment the top view point cloud data of the tower base, and the top view main body data of the tower base is extracted based on the segmented top view point cloud data; Extract the point cloud data of the bottom surface of the first tower foot from the top-view main body data of the tower foot, and obtain the side length information of the base plate based on the point cloud data of the bottom surface of the first tower foot; The point cloud data of the tower foot viewed from above is cropped according to a preset angle threshold to obtain the point cloud data of the first boot plate horizontal plane. The thickness information of the main boot plate, the thickness information of the secondary boot plate, and the coordinates of the starting point of the vertical weld are obtained based on the point cloud data of the first boot plate horizontal plane.

4. The method for extracting tower foot weld information as described in claim 3, characterized in that, Before segmenting the tower foot top-view point cloud data using a planar segmentation algorithm, the following steps are performed: denoising and filtering are applied to the tower foot top-view point cloud data.

5. The method for extracting tower foot weld information as described in claim 3, characterized in that, The plane segmentation algorithm is the RANSAC algorithm.

6. The method for extracting tower foot weld information as described in claim 3, characterized in that, The step of obtaining the thickness information of the main shoe plate, the thickness information of the secondary shoe plate, and the coordinates of the vertical weld start point based on the point cloud data of the first shoe plate horizontal plane includes: The point cloud data of the first boot plate horizontal plane is segmented by a straight line and divided into main boot plate point cloud data and secondary boot plate point cloud data; The edge information of the point cloud data of the main boot plate and the point cloud data of the secondary boot plate is extracted, and the edges of the main boot plate and the secondary boot plate are fitted with straight lines respectively to obtain the two long sides of the top surface of the main boot plate and the two long sides of the top surface of the secondary boot plate. The thickness information of the main boot plate is obtained by calculating the distance between the two long sides of the top surface of the main boot plate; The thickness information of the secondary shoe plate is obtained by calculating the distance between the two long sides of the top surface of the secondary shoe plate; The coordinates of the starting point of the vertical weld are determined by the coordinates of the intersection of the two long sides of the top surface of the main shoe plate and the two long sides of the top surface of the secondary shoe plate.

7. A device for extracting tower foot weld information, characterized in that, include: The acquisition module is used to acquire top-view point cloud data and side-view point cloud data of the tower base; The first processing module is used to process the top-view point cloud data of the tower foot to obtain the thickness of the main shoe plate, the thickness of the secondary shoe plate, the size of the base plate, and the coordinates of the starting point of the vertical weld in the first quadrant. The second processing module is used to process the tower foot side view point cloud data and, in conjunction with the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate, obtain the coordinates of the vertical weld endpoint, the horizontal weld endpoint, the coordinates of the first horizontal weld start point, the coordinates of the second horizontal weld start point, and the plate angle in the first quadrant. This processing of the tower foot side view point cloud data, and combining the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate to obtain the coordinates of the vertical weld endpoint, the horizontal weld endpoint, the coordinates of the first horizontal weld start point, the coordinates of the second horizontal weld start point, and the plate angle in the first quadrant, includes: segmenting the tower foot side view point cloud data using a planar segmentation algorithm, and based on... The side view point cloud data of the tower foot is extracted. From the side view point cloud data, the bottom surface feature information and side surface feature information of the tower foot are extracted. Based on the bottom surface feature information and side surface feature information, the intersection lines of the main shoe plate and the base plate, the intersection lines of the secondary shoe plate and the base plate, and the corner points between the main shoe plate, secondary shoe plate, and base plate are determined. These corner points serve as the endpoints of the horizontal and vertical weld seams. From the side view point cloud data of the tower foot, the centroid of the overall point cloud of the tower foot, the centroid of the point cloud on the plane where the base plate is located, the centroid of the point cloud on the side where the main shoe plate is located, and the centroid of the point cloud on the side where the secondary shoe plate is located are extracted. Based on the overall point cloud centroid of the tower foot, the centroid of the point cloud on the plane where the base plate is located, and the centroid of the point cloud on the side where the main shoe plate is located, the centroid of the point cloud on the side where the secondary shoe plate is located, the centroid of the point cloud on the side where the main shoe plate is located, and the centroid of the point cloud on the side where the secondary shoe plate is located, the centroid of the point cloud on the side where the base plate is located, and the centroid of the point cloud on the side where the base plate is located, ... base plate is located, the centroid of the point cloud on the side where the base plate is located, and the centroid of the point cloud on the side where the base plate is located, the centroid of the point cloud on the side where the base plate is located, and the centroid of the point cloud on the side where the base plate is located, Three directional vectors are formed by the centroid of the side point cloud and the centroid of the side point cloud where the secondary boot plate is located. The angle between the normal vectors of the plane where the base plate is located, the side where the main boot plate is located, and the side where the secondary boot plate is located is calculated respectively. If the angle is greater than 90 degrees, the direction of the normal vector of the corresponding plane is adjusted to the opposite direction. The inter-plate angle is obtained by using the normal vector of the plane where the base plate is located, the normal vector of the side where the main boot plate is located, and the normal vector of the side where the secondary boot plate is located. The inter-plate angle includes the angle between the base plate and the main boot plate, the angle between the base plate and the secondary boot plate, and the angle between the main boot plate and the secondary boot plate. The horizontal point cloud data of the second boot plate is extracted from the side view of the main body data of the tower foot, and the shear is determined based on the horizontal point cloud data of the second boot plate. The cutting plane is used to cut the side view of the tower foot main body data to obtain the second tower foot bottom surface point cloud data. The edge of the base plate is extracted based on the second tower foot bottom surface point cloud data, and the edge of the base plate is fitted with a straight line. The straight line that is parallel to the intersection line of the main shoe plate and the base plate and is farthest away is taken as the first outer edge straight line of the base plate. The straight line that is parallel to the intersection line of the auxiliary shoe plate and the base plate and is farthest away is taken as the second outer edge straight line of the base plate. The coordinates of the first horizontal weld start point are determined based on the intersection coordinates of the first outer edge straight line of the base plate and the intersection line of the main shoe plate and the base plate. The coordinates of the second horizontal weld start point are determined based on the intersection coordinates of the second outer edge straight line of the base plate and the intersection line of the auxiliary shoe plate and the base plate. The calculation module is used to determine the coordinates of the first horizontal weld start point, the second horizontal weld start point, and the plate angle in the second, third, and fourth quadrants based on the coordinates of the vertical weld start point in the first quadrant, the coordinates of the first horizontal weld start point, the coordinates of the second horizontal weld start point, the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the dimensions of the base plate. The integration module is used to integrate the thickness of the main shoe plate, the thickness of the secondary shoe plate, and the size of the base plate into tower foot size information, and to integrate the coordinates of the first horizontal weld start point, the second horizontal weld start point, the vertical weld start point, the horizontal weld end point, the vertical weld end point, and the plate angle in the first quadrant, the second quadrant, the third quadrant, and the fourth quadrant into tower foot weld information.

8. A device for extracting tower foot weld information, characterized in that, It includes a memory and at least one processor, wherein the memory stores computer-readable instructions; The at least one processor invokes the computer-readable instructions in the memory to perform the steps of the tower foot weld information extraction method as described in any one of claims 1-6.

9. A computer-readable storage medium storing computer-readable instructions thereon, characterized in that, When the computer-readable instructions are executed by a processor, they implement the various steps of the tower foot weld information extraction method as described in any one of claims 1-6.

Images