Welding seam information extraction method, device and equipment, storage medium and program product
By acquiring workpiece point clouds and constructing bounding boxes to identify weld edge application type and stiffener height, the problem of traditional weld information extraction relying on manual labor is solved, achieving automated and efficient weld information extraction.
Patent Information
- Application Number
- CN202511476100.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-16
- Publication Date
- 2025-11-14
- Estimated Expiration
- 2045-10-16
AI Technical Summary
Traditional weld information extraction relies heavily on manual teaching, resulting in low efficiency and an inability to quickly and accurately identify weld locations and types.
By acquiring the point cloud of the target workpiece, fitting the weld seam based on the point cloud, and constructing a bounding box to identify the weld edge application type and stiffener height, manual intervention is reduced and extraction efficiency is improved.
It achieves automated weld seam information extraction, reduces manual intervention, improves weld seam information extraction efficiency, and adapts to the deformation and installation deviation of the target workpiece.
Smart Images

Figure CN120953278A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent manufacturing technology, and in particular to a method, apparatus, equipment, storage medium, and program product for extracting weld information. Background Technology
[0002] In the field of modern shipbuilding, group assembly is a production management method and process adopted to speed up shipbuilding, improve shipbuilding quality, and achieve large-scale production. It mainly includes the assembly, welding, repair and grinding of bottom plates and stiffeners.
[0003] Traditional weld information extraction relies heavily on manual instruction, requiring prior knowledge of the workpiece model, weld location, and type, which is then manually set by the operator, resulting in extremely low efficiency in extracting weld information. Summary of the Invention
[0004] Therefore, it is necessary to provide a weld information extraction method, apparatus, equipment, storage medium, and program product that can improve the efficiency of weld information extraction in response to the above-mentioned technical problems.
[0005] Firstly, this application provides a method for extracting weld information, including:
[0006] The workpiece point cloud of the target workpiece is obtained, and the fitted weld is obtained based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the upper surface point cloud of the stiffener plate.
[0007] The first bounding box is constructed based on the fitted weld, and the weld edge application type of the fitted weld is determined based on the first point cloud in the first bounding box of the base plate plane point cloud.
[0008] A second bounding box is constructed based on the fitted weld seam, and the height of the stiffener is determined according to the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box.
[0009] In one embodiment, constructing a first bounding box based on the fitted weld, and determining the weld edge application type of the fitted weld based on the first point cloud within the first bounding box of the base plate planar point cloud, includes:
[0010] Select at least one first search point on the fitted weld, and construct a first bounding box with the first search point as the center;
[0011] Determine the mass points of the first point cloud within the first bounding box of the base plane point cloud;
[0012] If the distance between the mass point of the first point cloud and the search point is less than a predetermined distance threshold, the weld edge application type of the fitted weld is determined to be double-sided welding;
[0013] If the distance between the mass point of the first point cloud and the search point is greater than or equal to a predetermined distance threshold, the weld edge application type of the fitted weld is determined to be single-sided welding.
[0014] In one embodiment, a second bounding box is constructed based on the fitted weld, and the height of the stiffener is determined according to the height difference between the point cloud on the upper surface of the stiffener and the point cloud within the second bounding box, including:
[0015] Select at least one second search point on the fitted weld, and construct a second bounding box with the second search point as the center;
[0016] Determine the lowest point of the second point cloud within the second bounding box of the point cloud on the upper surface of the stiffener plate, and find the neighboring points within a predetermined radius centered on the lowest point;
[0017] If the number of neighboring points exceeds a set threshold, determine the average height of each neighboring point.
[0018] The difference between the average height and the height value of the second search point is determined as the stiffener height.
[0019] In one embodiment, obtaining the fitted weld seam based on workpiece point cloud fitting includes:
[0020] Extract the bottom plate plane point cloud and at least one stiffener upper surface point cloud from the workpiece point cloud, and project the stiffener upper surface point cloud onto the bottom plate plane of the target workpiece to obtain the stiffener projection point cloud.
[0021] Traverse the projection point cloud of the stiffener plate to obtain the weld endpoints, and determine the type of weld to be extracted based on the weld endpoints;
[0022] When the weld type to be extracted is a straight weld, iterative straight line extraction is performed based on the stiffener projection point cloud to obtain the fitted line segment.
[0023] When there are multiple corresponding fitted line segments in the projection point cloud of the stiffener plate, the fitted line segments are merged to obtain the fitted weld.
[0024] In one embodiment, when there are multiple corresponding fitted line segments in the rib plate projection point cloud, the fitted line segments are merged to obtain the fitted weld, which includes:
[0025] When there are multiple corresponding fitted line segments in the projection point cloud of the stiffener plate, determine the angle between each pair of fitted line segments, and the shortest distance from the endpoint of one fitted line segment to the other fitted line segment within a pair of fitted line segments.
[0026] When the angle between line segments is less than a set angle threshold and the shortest distance is less than a predetermined distance threshold, construct an adjacency graph of a pair of fitted line segments.
[0027] Based on the adjacency graph, determine the fitted line segments to be merged;
[0028] Merge the interior points of the fitted line segments to be merged into a point cloud to be fitted, and determine the point cloud boundary of the point cloud to be fitted.
[0029] The fitted weld is obtained by fitting a straight line based on the boundary of the point cloud to be fitted.
[0030] In one embodiment, the method further includes:
[0031] The relative position of the welding equipment and the first welding direction is obtained, and the fitted weld is sampled according to the preset welding distance to obtain multiple welding points;
[0032] When the welding edge is applied as a single-sided welding, if the side to be welded in the single-sided welding is consistent with the relative orientation, then the first welding direction is determined as the weld advance direction.
[0033] If the side to be welded in a single-sided weld is not in the same orientation as the opposite side, then the second welding direction is determined as the weld advance direction, wherein the second welding direction is opposite to the first welding direction;
[0034] When the welding edge is applied with a double-sided welding type, the first welding direction and the second welding direction are determined as the weld advance direction;
[0035] The welding points are sorted according to the direction of weld advancement to obtain a welding point sequence.
[0036] Secondly, this application also provides a weld information extraction device, comprising:
[0037] The weld fitting module is used to obtain the workpiece point cloud of the target workpiece, and to obtain the fitted weld based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the stiffener plate surface point cloud.
[0038] The weld edge application type determination module is used to construct a first bounding box based on the fitted weld and determine the weld edge application type of the fitted weld according to the first point cloud in the first bounding box based on the base plate plane point cloud.
[0039] The stiffener height determination module is used to construct a second bounding box based on the fitted weld and determine the stiffener height according to the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box.
[0040] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0041] The workpiece point cloud of the target workpiece is obtained, and the fitted weld is obtained based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the upper surface point cloud of the stiffener plate.
[0042] The first bounding box is constructed based on the fitted weld, and the weld edge application type of the fitted weld is determined based on the first point cloud in the first bounding box of the base plate plane point cloud.
[0043] A second bounding box is constructed based on the fitted weld seam, and the height of the stiffener is determined according to the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box.
[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:
[0045] The workpiece point cloud of the target workpiece is obtained, and the fitted weld is obtained based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the upper surface point cloud of the stiffener plate.
[0046] The first bounding box is constructed based on the fitted weld, and the weld edge application type of the fitted weld is determined based on the first point cloud in the first bounding box of the base plate plane point cloud.
[0047] A second bounding box is constructed based on the fitted weld seam, and the height of the stiffener is determined according to the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box.
[0048] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:
[0049] The workpiece point cloud of the target workpiece is obtained, and the fitted weld is obtained based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the upper surface point cloud of the stiffener plate.
[0050] The first bounding box is constructed based on the fitted weld, and the weld edge application type of the fitted weld is determined based on the first point cloud in the first bounding box of the base plate plane point cloud.
[0051] A second bounding box is constructed based on the fitted weld seam, and the height of the stiffener is determined according to the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box.
[0052] The aforementioned weld information extraction method, apparatus, equipment, storage medium, and program products obtain a workpiece point cloud of the target workpiece, and then fit a weld seam based on the workpiece point cloud. The workpiece point cloud includes the bottom plate planar point cloud and the upper surface point cloud of the stiffener plate. A first bounding box is then constructed based on the fitted weld seam. The weld edge application type of the fitted weld seam is determined based on the first point cloud within the first bounding box of the bottom plate planar point cloud. Thus, the first bounding box is constructed based on the fitted weld seam. Based on the bottom plate planar point cloud within the first bounding box, it can be identified whether there is a bottom plate on both sides of the fitted weld seam, i.e., whether bilateral welding (weld edge application type) is required. On the other hand, a second bounding box can be constructed based on the fitted weld. The height of the stiffener is determined by the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box. Thus, a second bounding box is constructed based on the fitted weld. The height of the stiffener can be identified based on the height difference between the midpoints of the point cloud on the stiffener plane within the second bounding box. After the fitted weld is obtained by fitting the workpiece point cloud of the target workpiece, the method of distinguishing the weld edge application type and identifying the stiffener height by constructing a bounding box based on the fitted weld reduces the influence of messy point clouds. It is also highly adaptable to the actual deformation and installation deviation of the target workpiece, greatly reducing manual intervention and improving the efficiency of weld information extraction. Attached Figure Description
[0053] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0054] Figure 1 This is an application environment diagram of the weld information extraction method in one embodiment;
[0055] Figure 2 This is a flowchart illustrating a weld information extraction method in one embodiment;
[0056] Figure 3 This is a schematic diagram of a workpiece point cloud in one embodiment;
[0057] Figure 4 This is a scene diagram of the projection point cloud of the rib plate in one embodiment;
[0058] Figure 5 This is a schematic diagram of a scenario where a line segment is fitted, as shown in one embodiment.
[0059] Figure 6 This is a schematic diagram of a scenario for fitting a weld in one embodiment;
[0060] Figure 7This is a schematic diagram of a scenario with the first bounding box in one embodiment;
[0061] Figure 8 This is a flowchart illustrating the weld information extraction method in another embodiment;
[0062] Figure 9 This is a flowchart illustrating the weld information extraction method in yet another embodiment;
[0063] Figure 10 This is a flowchart illustrating a specific embodiment of a weld information extraction method;
[0064] Figure 11 This is a structural block diagram of a weld information extraction device in one embodiment;
[0065] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0066] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0067] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.
[0068] The weld information extraction method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. It should be noted that the weld information extraction method provided in this embodiment can be executed by terminal 102, server 104, or jointly by terminal 102 and server. Taking the joint execution by terminal 102 and server 104 as an example, terminal 102 can request the workpiece point cloud of the target workpiece from server 104. After server 104 sends the workpiece point cloud of the target workpiece to terminal 102, terminal 102 can fit a fitted weld based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the stiffener plate upper surface point cloud. A first bounding box is constructed based on the fitted weld. The weld edge application type of the fitted weld is determined based on the first point cloud within the first bounding box of the bottom plate plane point cloud. A second bounding box is constructed based on the fitted weld. The stiffener plate height is determined based on the height difference between the second point cloud within the second bounding box of the stiffener plate upper surface point cloud. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart TVs, smart robots, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.
[0069] In one exemplary embodiment, such as Figure 2 As shown, a method for extracting weld information is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 210 to 240. Wherein:
[0070] Step 210: Obtain the workpiece point cloud of the target workpiece, and obtain the fitted weld based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the stiffener plate surface point cloud.
[0071] The target workpiece is the workpiece from which weld information is to be extracted. This workpiece includes a base plate and at least one stiffening plate disposed on the base plate. The workpiece point cloud is the point cloud obtained by scanning the target workpiece using a scanning device (such as a laser scanner or structured light camera). The workpiece point cloud includes the base plate planar point cloud and the stiffening plate upper surface point cloud. The base plate planar point cloud corresponds to the point cloud on the base plate plane of the target workpiece, and the stiffening plate upper surface point cloud corresponds to the point cloud on the upper surface of the stiffening plate of the target workpiece.
[0072] For example, in this embodiment, after obtaining the workpiece point cloud of the target workpiece, the bottom plate plane point cloud and at least one stiffener upper surface point cloud can be extracted from the workpiece point cloud. The stiffener upper surface point cloud is then projected onto the bottom plate plane of the target workpiece to obtain the stiffener projection point cloud. The stiffener projection point cloud is traversed to obtain the weld endpoints. Based on the weld endpoints, the type of weld to be extracted is determined. If the type of weld to be extracted is a straight weld, iterative straight line extraction is performed based on the stiffener projection point cloud to obtain a fitted line segment. If the stiffener projection point cloud has only one corresponding fitted line segment, the fitted line segment is used as the fitted weld. If the stiffener projection point cloud has multiple corresponding fitted line segments, the fitted line segments are merged to obtain the fitted weld. If the type of weld to be extracted is a curved weld, the stiffener projection point cloud can be piecewise linearly fitted to obtain a local line segment sequence. Then, the endpoints of each local line segment in the local line segment sequence are used as control points to fit and obtain the curved weld. For example, by setting a predetermined minimum value as the consensus set threshold or the maximum number of iterations, the stiffener projection point cloud can be fitted to obtain local line segments. The purpose of this is to avoid fitting the entire curve with a long straight line, but rather to fit the straightest part of the curve (i.e., local line segments). After fitting the first and most significant local line segment (such as a tangent to the curve), the interior points of this local line segment in the stiffener projection point cloud are removed. The fitting process is then repeated to fit the straightest local line segment of the remaining points in the stiffener projection point cloud, until the number of remaining points in the entire stiffener projection point cloud is less than the set threshold. The fitting process then stops, resulting in a series of ordered (or spatially ordered) local line segments (i.e., a sequence of local line segments). The endpoints of these local line segments are roughly distributed on the original curve corresponding to the weld. Using the endpoints of each local line segment in the sequence as control points, these control points are fitted using B-spline curves or Bézier curves to generate a smooth curve that passes through (or approximates) these control points, thus obtaining the curved weld. For acquiring the workpiece point cloud of the target workpiece, this embodiment can acquire the scanned point cloud obtained by scanning the target workpiece with a scanning device, and convert the scanned point cloud to the robot base coordinate system of a predetermined welding robot to obtain the workpiece point cloud. For example, this embodiment can set up a welding system for a target workpiece composed of a base plate and reinforcing ribs (stiffening plates), consisting of a welding robot, a ground rail cantilever, a line scan camera, a weld seam tracking sensor, a welding machine, a PLC (Programmable Logic Controller), and an industrial control computer. The welding robot is suspended upside down on the ground rail cantilever, and the line scan camera is mounted on the ground rail cantilever with its relative position to the robot base coordinate system of the welding robot remaining unchanged. The ground rail cantilever moves at a constant speed, driving the line scan camera to scan the target workpiece and acquire the scanned point cloud. The scanned point cloud is then converted to the robot base coordinate system using the visual calibration parameters of the line scan camera to obtain the workpiece point cloud. Figure 3 The point cloud of the target workpiece shown. Figure 3 The set of white dots in the middle is the workpiece point cloud.
[0073] In some embodiments, obtaining the fitted weld seam based on workpiece point cloud fitting includes steps 211 to 214:
[0074] Step 211: Extract the bottom plate plane point cloud and at least one upper surface point cloud of the rib from the workpiece point cloud, and project the upper surface point cloud of the rib onto the bottom plate plane of the target workpiece to obtain the rib projection point cloud.
[0075] Step 212: Traverse the projection point cloud of the stiffener plate to obtain the weld endpoints. Based on the weld endpoints, determine the type of weld to be extracted.
[0076] Step 213: When the weld type to be extracted is a straight weld, iterative straight line extraction is performed based on the stiffener projection point cloud to obtain the fitted line segment.
[0077] Step 214: If there are multiple corresponding fitted line segments in the projection point cloud of the stiffener plate, merge the fitted line segments to obtain the fitted weld.
[0078] Among them, the weld type to be extracted is the type that describes the weld morphology, such as straight weld, curved weld, intersecting weld (i.e., weld when there is an intersection of stiffeners), etc.
[0079] This embodiment can obtain the base plate plane based on the workpiece point cloud fitting. Based on the base plate plane, the base plate plane point cloud and the rib plate surface point cloud are separated from the workpiece point cloud. After projecting the rib plate surface point cloud onto the base plate plane, the projected rib plate surface point cloud is clustered to obtain at least one rib plate projection point cloud. For example, this embodiment can first fit the base plate plane based on the workpiece point cloud, set a plane distance threshold to extract the points within the base plate plane, and obtain the base plate plane point cloud. The remaining points in the workpiece point cloud besides the base plate plane point cloud are the rib plate surface points, which may also contain some interference points. Then, this embodiment can project the rib plate surface point cloud onto the base plate plane, and after filtering, noise reduction, and clustering operations, the rib plate surface point cloud is segmented to obtain the rib plate projection point cloud for each rib plate on the corresponding base plate. Of course, to reduce the point cloud density and improve computational efficiency, a downsampling operation can be performed before clustering, such as uniform downsampling or mass point downsampling. The downsampled rib plate projection point cloud is as follows: Figure 4As shown in the figure, the white dots represent points in the downsampled rib plate projection point cloud. For example, since the target workpiece is scanned from top to bottom, the Z-axis in the world coordinate system is vertically downward. Therefore, this embodiment can also find the minimum Z-value of points within the base plate plane. This minimum Z-value is used as the maximum Z-value to perform pass-through filtering on the remaining point cloud in the workpiece point cloud, excluding the base plate plane point cloud. This filters out interference point clouds below the base plate plane, obtaining the rib plate surface point cloud. The rib plate surface point cloud is then projected onto the base plate plane. Statistical filtering for noise reduction, uniform downsampling to reduce point cloud density, and clustering segmentation are used to segment the rib plate surface point cloud individually, obtaining each segmented rib plate projection point cloud corresponding to a rib plate on the base plate. Furthermore, this embodiment can traverse the rib plate projection point cloud to obtain the weld endpoint. For example, multiple local windows can be constructed based on the rib plate projection point cloud, where each local window is a preset search range centered on a specified point, such as a range with a radius of r centered on a specified point P. Calculate the cosine of the vector formed by a specified point and other points within the local window. If all cosine values are positive or negative, the specified point is considered a candidate endpoint. Cluster the candidate endpoints again to obtain clusters. For each cluster, take its geometric center as the weld endpoint to avoid duplicate endpoints. Then, based on the number of weld endpoints, determine the type of weld to be extracted.
[0080] For example, determining the type of weld to be extracted based on weld endpoints includes: if no weld endpoints exist, determining the type of weld to be extracted as a closed curve weld; if more than two weld endpoints exist, determining the type of weld to be extracted as an intersecting weld; if more than two weld endpoints exist, constructing a weld line based on the two weld endpoints and determining the average vertical distance from each point in the stiffener projection point cloud to the weld line; if the average vertical distance is less than a predetermined vertical distance threshold, determining the type of weld to be extracted as a straight weld; and if the average vertical distance is greater than or equal to the predetermined vertical distance threshold, determining the type of weld to be extracted as a curved weld.
[0081] like Figure 5 As shown, since a straight weld may result in multiple fitted line segments when the stiffener is wide, this embodiment can perform iterative straight line extraction based on the stiffener projection point cloud when the weld type to be extracted is a straight weld to obtain fitted line segments. Thus, multiple corresponding fitted line segments exist in the stiffener projection point cloud (e.g., ...). Figure 5In the case of multiple fitted line segments (shown within the red dashed box), the fitted line segments are merged to obtain a fitted weld. For example, merging fitted line segments can be done by setting an angle threshold and a distance threshold. If the angle between fitted line segments is less than the angle threshold or the distance between fitted line segments is less than the distance threshold, redundant fitted line segments are excluded. This can be done by merging multiple fitted segments that meet the criteria into a single fitted weld, or by retaining only the longest fitted line segment as the fitted weld, to obtain the fitted weld. For instance, in this embodiment, when multiple corresponding fitted line segments exist in the rib projection point cloud, the angle between each pair of fitted line segments and the shortest distance from the endpoint of one fitted line segment to the other within a pair of fitted line segments are determined. When the angle between the line segments is less than the set angle threshold and the shortest distance is less than the predetermined distance threshold, an adjacency graph of the pair of fitted line segments is constructed, indicating that this pair of fitted line segments is actually a weld. The adjacency graph is the graph obtained by connecting this pair of fitted line segments. Since a single weld seam may yield more than two fitted line segments, the fitted line segments to be merged are determined based on the adjacency graph. These segments are the connected fitted line segments within the adjacency graph. The adjacency graph is essentially designed to achieve continuous merging of multiple line segments. For example, if fitted line segment A connects to fitted line segment B, and fitted line segment B connects to fitted line segment C, then fitted line segments A, B, and C are the fitted line segments to be merged.
[0082] Therefore, in this embodiment, the interior points of the fitted line segments to be merged can be merged into a point cloud to be fitted. The interior points of the fitted line segments are the points in the stiffener projection point cloud used to fit the fitted line segments. The boundary of the point cloud to be fitted can be the minimum bounding box of the point cloud to be fitted. For example, in this embodiment, a minimum cuboid (i.e., minimum bounding box) can be constructed with the center of the point cloud to be fitted as the center. The eight vertices of this minimum bounding box can then be used as the point cloud boundary. Alternatively, the set of some points on each face of the minimum bounding box and the eight vertices can be used as the point cloud boundary. Then, a straight line is fitted based on the point cloud boundary to obtain the fitted weld. The fitted weld is as follows: Figure 6 The line segment within the red dashed box is shown.
[0083] This embodiment, on the one hand, constructs an adjacency graph of a pair of fitted line segments when the included angle of the line segments is less than a set angle threshold and the shortest distance is less than a predetermined distance threshold. Based on this adjacency graph, it determines the fitted line segments to be merged, thereby achieving the filtering of multiple line segments corresponding to the same weld. On the other hand, it uses the point cloud boundaries of the point clouds corresponding to all the line segments to be fitted as representatives for fitting, which greatly improves the computational efficiency of fitting the weld and significantly enhances the accuracy and robustness of the fitted weld.
[0084] Step 220: Construct a first bounding box based on the fitted weld, and determine the weld edge application type of the fitted weld based on the first point cloud in the first bounding box of the base plate planar point cloud.
[0085] The first bounding box is a bounding box centered on a point on the fitted weld, and there is at least one first bounding box. The first point cloud is the set of points in the base plate plane point cloud that are located within the first bounding box.
[0086] like Figure 7 As shown, three first bounding boxes are formed with the two endpoints and one midpoint of the fitted weld as centers. This embodiment can determine the first point cloud of the base plate planar point cloud within the first bounding box, and determine the distribution of the first point cloud on both sides of the fitted weld. Based on the distribution of the first point cloud on both sides of the fitted weld, the weld edge application type of the fitted weld is determined. For example, in this embodiment, at least one first search point can be selected on the fitted weld, and a first bounding box can be constructed with the first search point as the center. The mass points of the first point cloud in the base plate plane point cloud within the first bounding box are determined. If the distance between the mass points of the first point cloud and the search point is less than a predetermined distance threshold, it indicates that the first point cloud is relatively evenly distributed on both sides of the weld, that is, the number of points of the first point cloud on both sides of the fitted weld is similar, indicating that there is a base plate on both sides of the fitted weld, and the weld edge application type of the fitted weld is determined to be double-sided welding. If the distance between the mass points of the first point cloud and the search point is greater than or equal to the predetermined distance threshold, it indicates that the first point cloud is extremely unevenly distributed on both sides of the weld, that is, most of the points in the first point cloud are distributed on one side, and there are very few points on the other side, indicating that there is a base plate on only one side of the fitted weld, and the weld edge application type of the fitted weld is determined to be single-sided welding. In addition, this embodiment can also count the number of first points and the number of second points on both sides of the fitted weld. If the difference between the number of first points and the number of second points is less than a predetermined number threshold, the weld edge application type of the fitted weld is determined to be double-sided welding. If the difference between the number of first points and the number of second points is equal to or greater than the predetermined number threshold, the weld edge application type of the fitted weld is determined to be single-sided welding.
[0087] In some embodiments, constructing a first bounding box based on the fitted weld, and determining the weld edge application type of the fitted weld according to the first point cloud within the first bounding box based on the base plate planar point cloud, includes steps 221 to 224:
[0088] Step 221: Select at least one first search point on the fitted weld and construct a first bounding box with the first search point as the center.
[0089] Step 222: Determine the mass points of the first point cloud within the first bounding box of the base plate planar point cloud.
[0090] Step 223: If the distance between the mass point of the first point cloud and the search point is less than a predetermined distance threshold, determine that the weld edge application type of the fitted weld is double-sided welding.
[0091] Step 224: If the distance between the mass point of the first point cloud and the search point is greater than or equal to a predetermined distance threshold, determine that the weld edge application type of the fitted weld is single-sided welding.
[0092] In this embodiment, at least one first search point can be selected on the fitted weld, and a first bounding box can be constructed with the first search point as the center. For example, in this embodiment, the two endpoints and the center point of the fitted weld can be selected as the first search point. Then, the mass points of the first point cloud within the first bounding box are determined. For example, in this embodiment, the arithmetic mean of the coordinates of all points in the first point cloud can be calculated to obtain the mass points of the first point cloud. If the distance between the mass points of the first point cloud and the search point is less than a predetermined distance threshold, it indicates that the first point cloud is relatively evenly distributed on both sides of the weld, that is, the number of points of the first point cloud on both sides of the fitted weld is similar, indicating that there is a base plate on both sides of the fitted weld, and the weld edge application type of the fitted weld is determined to be double-sided welding. If the distance between the mass points of the first point cloud and the search point is greater than or equal to the predetermined distance threshold, it indicates that the first point cloud is extremely unevenly distributed on both sides of the weld, that is, most points in the first point cloud are distributed on one side, and very few points are on the other side, indicating that there is a base plate on only one side of the fitted weld, and the weld edge application type of the fitted weld is determined to be single-sided welding.
[0093] In this embodiment, a first bounding box is constructed based on the fitted weld. Based on the first point cloud in the first bounding box of the base plate plane point cloud, the distribution of the first point cloud on both sides of the fitted weld is identified, thereby accurately identifying whether the fitted weld has a base plate on only one side or on both sides, so as to determine whether the weld edge application type of the fitted weld is single-sided welding or double-sided welding.
[0094] Step 230: Construct a second bounding box based on the fitted weld, and determine the height of the stiffener plate according to the height difference between the point cloud on the upper surface of the stiffener plate and the second point cloud in the second bounding box;
[0095] The second bounding box is a bounding box centered on a point on the fitted weld, and there is at least one second bounding box. The second point cloud is the set of points on the upper surface of the stiffener that are located within the second bounding box.
[0096] In this embodiment, at least one second search point can be selected on the fitted weld, and a second bounding box can be constructed with the second search point as the center. For example, in this embodiment, the two endpoints and the center point of the fitted weld can be selected as the second search point. Then, the second point cloud of the upper surface point cloud of the stiffener is determined within the second bounding box. For example, in this embodiment, the lowest point of the second point cloud can be selected, and neighborhood points within a predetermined radius can be found with the lowest point as the center. If the number of neighborhood points is greater than a set threshold, the average height of each neighborhood point is determined, and the difference between the average height and the height of the second search point is determined as the stiffener height. In this embodiment, a first number of lowest points and a second number of highest points in the first point cloud can also be selected, and the first average height of the first number of lowest points and the second average height of the second number of highest points are determined. The difference between the first average height and the second average height is taken as the stiffener height.
[0097] In some embodiments, constructing a second bounding box based on the fitted weld, and determining the stiffener height according to the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box includes steps 231 to 234:
[0098] Step 231: Select at least one second search point on the fitted weld and construct a second bounding box with the second search point as the center.
[0099] Step 232: Determine the lowest point of the second point cloud within the second bounding box of the point cloud on the upper surface of the stiffener plate, and find the neighboring points within a predetermined radius with the lowest point as the center.
[0100] Step 233: If the number of neighboring points is greater than the set threshold, determine the average height of each neighboring point.
[0101] Step 234: Determine the height of the stiffener by the difference between the average height and the height of the second search point.
[0102] The predetermined radius is the radius value used to make the second enclosure box encompass the entire stiffening plate.
[0103] In this embodiment, at least one second search point can be selected on the fitted weld, and a second bounding box can be constructed with the second search point as the center. For example, in this embodiment, the two endpoints and the midpoint of the fitted weld can be selected as the second search points. Of course, in this embodiment, at least two predetermined points can be selected at equal intervals on the fitted weld. For each predetermined point, it is first moved a predetermined distance along the Z-axis and then used as the second search point. A cuboid bounding box centered on the second search point is used as the second bounding box. Then, the second point cloud located within the second bounding box in the point cloud of the upper surface of the stiffener is searched, and the lowest point of the second point cloud in the second bounding box (i.e., the point with the smallest Z value) is determined. With the lowest point as the center, neighboring points within a predetermined radius (i.e., points in the second point cloud other than the lowest point that are within the predetermined radius) are searched. To avoid errors caused by a small number of points, in this embodiment, when the number of neighboring points is greater than a set threshold, the average height of each neighboring point is determined, and the difference between the average height and the height value of the second search point is determined as the stiffener height.
[0104] Therefore, this embodiment can determine at least one of the following as weld information: the fitted weld describing the spatial location of the weld, the weld edge application type describing the application method of the weld edge, and the stiffener height, for use in subsequent welding work, so as to efficiently provide more comprehensive weld information.
[0105] In the above-described weld information extraction method, a workpiece point cloud of the target workpiece is acquired, and a fitted weld is obtained based on the workpiece point cloud. The workpiece point cloud includes the bottom plate planar point cloud and the upper surface point cloud of the stiffener plate. Then, a first bounding box is constructed based on the fitted weld. According to the first point cloud of the bottom plate planar point cloud within the first bounding box, the weld edge application type of the fitted weld is determined. Thus, the first bounding box is constructed based on the fitted weld. Based on the bottom plate planar point cloud within the first bounding box, it can be identified whether there is a bottom plate on both sides of the fitted weld, i.e., whether bilateral welding (weld edge application type) is required. On the other hand, a second bounding box can be constructed based on the fitted weld. The height of the stiffener is determined by the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box. Thus, a second bounding box is constructed based on the fitted weld. The height of the stiffener can be identified based on the height difference between the midpoints of the point cloud on the stiffener plane within the second bounding box. After the fitted weld is obtained by fitting the workpiece point cloud of the target workpiece, the method of distinguishing the weld edge application type and identifying the stiffener height by constructing a bounding box based on the fitted weld reduces the influence of messy point clouds. It is also highly adaptable to the actual deformation and installation deviation of the target workpiece, greatly reducing manual intervention and improving the efficiency of weld information extraction.
[0106] In some embodiments, such as Figure 8 As shown, when there are multiple corresponding fitted line segments in the point cloud on the upper surface of the stiffener, the fitted line segments are merged to obtain the fitted weld, including steps 310 to 350:
[0107] Step 310: In the case that there are multiple corresponding fitted line segments in the rib plate projection point cloud, determine the angle between each pair of fitted line segments and the shortest distance from the endpoint of one fitted line segment to the other fitted line segment within a pair of fitted line segments.
[0108] Step 320: If the angle between the line segments is less than a set angle threshold and the shortest distance is less than a predetermined distance threshold, construct an adjacency graph of a pair of fitted line segments.
[0109] Step 330: Based on the adjacency graph, determine the fitted line segments to be merged.
[0110] Step 340: Merge the interior points of the fitted line segments to be merged into a point cloud to be fitted, and determine the point cloud boundary of the point cloud to be fitted.
[0111] Step 350: Perform straight line fitting based on the point cloud boundary of the point cloud to be fitted to obtain the fitted weld.
[0112] This embodiment can determine the angle between each pair of fitted line segments and the shortest distance from the endpoint of one fitted line segment to the other when there are multiple corresponding fitted line segments in the rib projection point cloud. If the angle between the line segments is less than a set angle threshold and the shortest distance is less than a predetermined distance threshold, an adjacency graph of the pair of fitted line segments is constructed, indicating that this pair of fitted line segments is actually a weld. The adjacency graph is the graph obtained by connecting this pair of fitted line segments. Since a weld may also yield more than two fitted line segments, the fitted line segments to be merged are determined based on the adjacency graph. The fitted line segments to be merged are the fitted line segments connected within the adjacency graph. The adjacency graph is essentially for achieving continuous merging of multiple line segments. For example, if fitted line segment A connects to fitted line segment B, and fitted line segment B connects to fitted line segment C in the adjacency graph, then fitted line segments A, B, and C are the fitted line segments to be merged. Therefore, in this embodiment, the interior points of the fitted line segments to be merged can be merged into a point cloud to be fitted. The interior points of the fitted line segments are the points in the point cloud on the upper surface of the stiffener used to fit the fitted line segments. The boundary of the point cloud to be fitted can be the minimum bounding box of the point cloud to be fitted. For example, in this embodiment, a minimum cuboid (i.e., minimum bounding box) can be constructed with the center of the point cloud to be fitted as the center. Then, the 8 vertices of this minimum bounding box can be used as the boundary of the point cloud. Of course, the set of some points on each face of the minimum bounding box and the 8 vertices can also be used as the boundary of the point cloud. Then, a straight line is fitted based on the boundary of the point cloud to be fitted to obtain the fitted weld.
[0113] In one exemplary embodiment, such as Figure 9 As shown, the method further includes steps 410 to 450. Wherein:
[0114] Step 410: Obtain the relative position of the welding equipment and the first welding direction, and sample the fitted weld according to the preset welding distance to obtain multiple welding points.
[0115] Step 420: When the welding edge is applied as a single-sided weld, if the side to be welded in the single-sided weld is consistent with the relative orientation, then the first welding direction is determined as the weld advance direction.
[0116] Step 430: If the side to be welded for single-sided welding is not in the same orientation as the relative position, then the second welding direction is determined as the weld advance direction, wherein the second welding direction is opposite to the first welding direction.
[0117] Step 440: When the welding edge is applied with a double-sided welding type, the first welding direction and the second welding direction are determined as the weld advance direction.
[0118] Step 450: Sort the welding points according to the direction of weld advance to form a welding point sequence.
[0119] The welding equipment refers to the device used to weld the target workpiece, such as a welding torch. The first welding direction is the pre-defined forward direction of the welding equipment, and the relative orientation is whether the welding equipment is to the left or right of the first welding direction. The predetermined welding distance is the pre-set distance between welding points, which can be set according to welding requirements.
[0120] This embodiment can obtain the relative orientation of the welding equipment and the first welding direction, and sample the fitted weld according to a predetermined welding torch to obtain multiple welding points. When the welding edge application type is single-sided welding, if the side to be welded in the single-sided welding is consistent with the relative orientation, the first welding direction is determined as the weld advancement direction. The side to be welded in the single-sided welding can be determined based on the particle position of the first point cloud within the first enclosure of the base plate plane point cloud; that is, the side where the particle position of the first point cloud is located is the side to be welded. If the side to be welded in the single-sided welding is inconsistent with the relative orientation, the second welding direction is determined as the weld advancement direction, wherein the second welding direction is opposite to the first welding direction. For example, taking the relative orientation of the welding equipment and the first welding direction as the left side (i.e., the welding equipment is to the left of the first welding direction), when the side to be welded in the single-sided welding is on the left side (consistent with the relative orientation), the first welding direction can be determined as the welding advancement direction. When the side to be welded in single-sided welding is the right side (not consistent with the relative orientation), since the welding equipment is located to the left of the first welding direction, if the first welding direction is determined as the welding advance direction, the welding equipment cannot weld the stiffener. Therefore, a second welding direction opposite to the first welding direction needs to be used as the welding advance direction. When the weld edge application type is double-sided welding, since welding is required on both sides of the stiffener, both the first and second welding directions can be determined as the weld advance direction. The welding points are then sorted based on the weld advance direction to form a welding point sequence. In addition to fitting the weld, weld edge application type, and stiffener height, the welding point sequence can also be determined as weld information to further reduce manual intervention and improve the efficiency and comprehensiveness of weld information extraction.
[0121] This embodiment obtains the relative position of the welding equipment and the first welding direction, samples the fitted weld seam according to a preset weld distance, and obtains multiple welding points. When the welding edge application type is single-sided welding, if the side to be welded in the single-sided welding is consistent with the relative position, the first welding direction is determined as the weld seam advancing direction; if the side to be welded in the single-sided welding is inconsistent with the relative position, the second welding direction is determined as the weld seam advancing direction. The second welding direction is opposite to the first welding direction. When the welding edge application type is double-sided welding, both the first and second welding directions are determined as the weld seam advancing directions. Based on the weld seam advancing directions, the welding points are sorted to form a welding point sequence. Thus, this embodiment achieves a reasonable sorting of welding points, ensuring a reasonable and continuous welding path for the welding equipment.
[0122] To more clearly describe the weld information extraction method of this application, an embodiment is provided below. This embodiment focuses on a target workpiece consisting of a bottom plate and stiffeners (ribs) in ship assembly, and proposes a weld information extraction method as follows: Figure 10As shown, the weld information includes the spatial location of the weld, whether double-sided welding is required, the sequence of weld points, and the height of the corresponding stiffener. The welding system can consist of a welding robot, a ground-rail cantilever, a line scan camera, a weld tracking sensor, a welding machine, a PLC (Programmable Logic Controller), and an industrial computer.
[0123] Step 1: The welding robot is suspended upside down on the ground rail cantilever. The line scan camera is mounted on the ground rail cantilever and its relative position to the robot's base coordinate system remains unchanged. The ground rail cantilever moves at a constant speed, driving the line scan camera to scan the target workpiece and obtain the point cloud. The point cloud is then converted to the robot's base coordinate system using the line scan camera's visual calibration parameters to obtain the workpiece point cloud.
[0124] Step 2: In order to improve the accuracy of the workpiece point cloud, the workpiece point cloud can also be filtered and noise reduced to remove interfering point clouds.
[0125] Step 3: Fit the base plate plane using the RANSAC (Random Sample Consensus) algorithm, set the plane distance threshold, extract the points in the plane from the workpiece point cloud to obtain the planar base plate point cloud, and the remaining point cloud is the workpiece upper surface point cloud and interference points.
[0126] Step 4: Since Z is vertically downward in the world coordinate system, find the minimum value of Z at a point in the base plate plane. Use this value as the maximum value of Z to perform a pass-through filter on the upper surface point cloud and interfering point cloud obtained in Step 2. This filters out the point cloud below the base plate, resulting in the upper surface point cloud of the stiffener plate. Project the upper surface point cloud of the stiffener plate onto the base plate plane. Use statistical filtering to reduce noise, uniform downsampling to reduce point cloud density, and clustering to segment the stiffener plate point cloud individually. For each segmented point cloud, find the centroid within a radius R and downsample to obtain the projected point cloud of the stiffener plate.
[0127] Step 5: Traverse the points of the sampled stiffener projection point cloud, construct a local window, and calculate the cosine value of the vector formed by the point and other points in the window. If there is only a positive or negative value, it is an endpoint. Perform radius clustering on the candidate endpoints again. For each cluster, take its geometric center point as the weld endpoint to avoid multiple endpoints from appearing repeatedly.
[0128] Step 6: The weld type can be determined based on the number of weld endpoints. If there are two weld endpoints, it is further determined whether it is a straight weld or an open curve weld. If there are more than two weld endpoints, it is a weld with intersections in the stiffener plate. If there are no weld endpoints, it is a closed curve weld. For the case of two weld endpoints, a line to be determined is constructed using the two weld endpoints. For each point in the downsampled stiffener plate projection point cloud, its projection point on the line to be determined is calculated, and its vertical distance to the line to be determined is calculated. The average vertical distance is calculated. If the average vertical distance is less than a predetermined vertical distance threshold, the weld type is determined to be a straight weld; otherwise, the weld type is determined to be a curve weld. For straight welds, the RANSAC algorithm is repeatedly used to extract straight lines based on the point cloud on the upper surface of the stiffener plate until the number of remaining points is less than a set threshold. The straight line obtained from each fitting is used as the fitted line segment, and the interior points of the fitted line segment are extracted and projected onto the fitted line segment. The weld endpoints are re-determined using the method shown in Step 5, thereby achieving straight line fitting. Since a stiffening rib has only one weld, if multiple fitted line segments are extracted after step 8, it indicates that the target workpiece has a wide stiffening rib or a cover plate on the stiffening rib. In this case, the fitted line segments that meet the conditions need to be merged. Calculate the included angle of each pair of fitted line segments. If the included angle is less than a set included angle threshold, calculate the nearest distance from the endpoint of one fitted line segment to a point in another line segment. If the nearest distance is also less than a set distance threshold, then the pair of fitted line segments meets the merging requirements. Construct an adjacency graph based on the included angle and the nearest distance. Starting from a starting node in the adjacency graph, visit all adjacent nodes layer by layer outwards until all reachable nodes have been visited, traversing the connection graph to filter out all fitted line segments to be merged. Merge the interior points of the fitted line segments to be merged into a point cloud to be merged. Calculate the point cloud boundary of this point cloud. Based on the point cloud boundary, use the RANSAC algorithm to fit a straight line to obtain a fitted straight line. Use this fitted straight line as the final fitted weld of the stiffening rib's projected point cloud, thus removing redundant fitted line segments.
[0129] Step 7: Construct a weld coordinate system. The vector formed by the two endpoints of the fitted weld is used as the X-axis of the first weld coordinate system. The Z-axis is vertically upward by default; the cross product yields the Y-axis. Construct a cuboid using the midpoint and endpoints of the fitted weld as the first search points. Use the X-axis of the first weld coordinate system as the long side direction, the Y-axis as the wide side direction, and the Z-axis as the height direction to construct a cuboid region of a certain size, serving as the first bounding box. Search within the first bounding box to obtain the first point cloud of the base plate plane point cloud. Calculate the distance between the centroid of the first point cloud and the first search point. If the distance is less than a first distance threshold, the weld edge application type is determined to be bilateral welding; if it is greater than the first distance threshold, the weld edge application type is determined to be single-sided welding. This identifies whether the fitted weld should be bilateral or single-sided welded. For identifying the welding point sequence, the welding equipment (such as a welding torch) can be predefined to always be on the left side of the predetermined weld seam advancing direction. The fitted weld seam is sampled according to the predetermined welding torch to obtain multiple welding points. If the weld edge application type is single-sided welding, the welding points need to be sorted. The unit vector formed by the order of welding points in the predetermined weld seam advancing direction is defined as the X-axis of the second weld seam coordinate system, and the unit vector pointing from the first welding point to the centroid of the first point cloud is defined as the Y-axis of the second weld seam coordinate system. The cross product yields the Z-axis of the second weld seam coordinate system. Since the Z-axis of the second weld seam coordinate system is opposite in direction to the Z-axis of the first weld seam coordinate system, the order of welding points in the predetermined weld seam advancing direction is used as the welding point sequence.
[0130] Step 8: Construct target line segments using the weld endpoints of the fitted weld. Sample at equal intervals on the target line segments to obtain undetermined search points. For each undetermined search point, first move it a predetermined search distance along the Z-axis of the first weld coordinate system to obtain a second search point. Construct a cuboid bounding box centered on this second search point (i.e., the second bounding box). Search the second point cloud within the second bounding box in the point cloud on the upper surface of the stiffener. Find the point with the smallest Z-value (i.e., the lowest point) in this second point cloud. Using this lowest point as the center, find neighboring points within a radius R. If the number of neighboring points is greater than a set threshold, calculate the average Z-value of these neighboring points. The difference between the average Z-value and the Z-value of the second search point is the stiffener height.
[0131] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.
[0132] Based on the same inventive concept, this application also provides a weld information extraction device for implementing the weld information extraction method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more weld information extraction device embodiments provided below can be found in the limitations of the weld information extraction method described above, and will not be repeated here.
[0133] In one exemplary embodiment, such as Figure 11 As shown, a weld information extraction device 500 is provided, including: a weld fitting module 510, a weld edge application type determination module 520, and a stiffener height determination module 530, wherein:
[0134] The weld fitting module 510 is used to obtain the workpiece point cloud of the target workpiece and to obtain the fitted weld based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the upper surface point cloud of the stiffener plate.
[0135] The weld edge application type determination module 520 is used to construct a first bounding box based on the fitted weld and determine the weld edge application type of the fitted weld according to the first point cloud in the first bounding box based on the base plate plane point cloud.
[0136] The stiffener plate height determination module 530 is used to construct a second bounding box based on the fitted weld and determine the stiffener plate height according to the height difference between the point cloud on the upper surface of the stiffener plate and the second point cloud in the second bounding box.
[0137] In one embodiment, the weld edge application type determination module 520 is further configured to:
[0138] At least one first search point is selected on the fitted weld. A first bounding box is constructed with the first search point as the center. The mass points of the first point cloud in the base plate plane point cloud within the first bounding box are determined. If the distance between the mass points of the first point cloud and the search point is less than a predetermined distance threshold, the weld edge application type of the fitted weld is determined to be double-sided welding. If the distance between the mass points of the first point cloud and the search point is greater than or equal to the predetermined distance threshold, the weld edge application type of the fitted weld is determined to be single-sided welding.
[0139] In one embodiment, the stiffener height determining module 530 is further configured to:
[0140] At least one second search point is selected on the fitted weld. A second bounding box is constructed with the second search point as the center. The lowest point of the second point cloud on the upper surface of the stiffener plate is determined within the second bounding box. With the lowest point as the center, neighboring points within a predetermined radius are searched. If the number of neighboring points is greater than the set threshold, the average height of each neighboring point is determined. The difference between the average height and the height of the second search point is determined as the stiffener plate height.
[0141] In one embodiment, the weld fitting module 510 is further configured to:
[0142] Extract the base plate planar point cloud and at least one stiffener upper surface point cloud from the workpiece point cloud, and project the stiffener upper surface point cloud onto the base plate plan of the target workpiece to obtain the stiffener projection point cloud. Traverse the stiffener projection point cloud to obtain the weld endpoints. Based on the weld endpoints, determine the type of weld to be extracted. If the type of weld to be extracted is a straight weld, perform iterative straight line extraction based on the stiffener projection point cloud to obtain the fitted line segment. If there are multiple corresponding fitted line segments in the stiffener projection point cloud, merge the fitted line segments to obtain the fitted weld.
[0143] In one embodiment, the weld fitting module 510 is further configured to:
[0144] When there are multiple corresponding fitted line segments in the projection point cloud of the stiffener plate, the included angle between each pair of fitted line segments and the shortest distance from the endpoint of one fitted line segment to the other fitted line segment are determined. When the included angle is less than a set angle threshold and the shortest distance is less than a predetermined distance threshold, an adjacency graph of a pair of fitted line segments is constructed. Based on the adjacency graph, the fitted line segments to be merged are determined, the interior points of the fitted line segments to be merged are merged into the point cloud to be fitted, and the point cloud boundary of the point cloud to be fitted is determined. Based on the point cloud boundary of the point cloud to be fitted, a straight line is fitted to obtain the fitted weld.
[0145] In one embodiment, the weld information extraction device further includes a weld point determination module, used for:
[0146] The relative position of the welding equipment and the first welding direction is obtained. The fitted weld is sampled according to the preset welding distance to obtain multiple welding points. When the welding edge application type is single-sided welding, if the side to be welded in the single-sided welding is consistent with the relative position, the first welding direction is determined as the weld advancement direction. If the side to be welded in the single-sided welding is inconsistent with the relative position, the second welding direction is determined as the weld advancement direction. The second welding direction is opposite to the first welding direction. When the welding edge application type is double-sided welding, the first welding direction and the second welding direction are determined as the weld advancement direction. The welding points are sorted based on the weld advancement direction to form a welding point sequence.
[0147] Each module in the aforementioned weld information extraction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.
[0148] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for extracting weld information. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.
[0149] Those skilled in the art will understand that Figure 12The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0150] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the embodiments described above.
[0151] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above embodiments.
[0152] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the above embodiments.
[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0154] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0156] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for extracting weld information, characterized in that, The method includes: The workpiece point cloud of the target workpiece is obtained, and the fitted weld is obtained based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the upper surface point cloud of the stiffener plate. A first bounding box is constructed based on the fitted weld, and the weld edge application type of the fitted weld is determined according to the first point cloud of the base plate planar point cloud within the first bounding box. A second bounding box is constructed based on the fitted weld, and the height of the stiffener is determined according to the height difference between the point cloud on the upper surface of the stiffener and the second point cloud within the second bounding box.
2. The method according to claim 1, characterized in that, The process of constructing a first bounding box based on the fitted weld, and determining the weld edge application type of the fitted weld according to the first point cloud of the base plate planar point cloud within the first bounding box, includes: Select at least one first search point on the fitted weld, and construct a first bounding box with the first search point as the center; Determine the mass points of the first point cloud within the first bounding box of the base plate planar point cloud; If the distance between the particles of the first point cloud and the search point is less than a predetermined distance threshold, the weld edge application type of the fitted weld is determined to be double-sided welding; If the distance between the mass point of the first point cloud and the search point is greater than or equal to a predetermined distance threshold, the weld edge application type of the fitted weld is determined to be single-sided welding.
3. The method according to claim 1, characterized in that, The construction of the second bounding box based on the fitted weld, and the determination of the stiffener height based on the height difference between the point cloud on the upper surface of the stiffener and the point cloud within the second bounding box, include: Select at least one second search point on the fitted weld, and construct a second bounding box with the second search point as the center; Determine the lowest point of the second point cloud within the second bounding box of the point cloud on the upper surface of the stiffener, and find neighboring points within a predetermined radius centered on the lowest point; If the number of neighboring points is greater than a set threshold, determine the average height of each neighboring point. The difference between the average height and the height value of the second search point is determined as the rib height.
4. The method according to claim 1, characterized in that, The fitted weld obtained based on the workpiece point cloud includes: Extract the bottom plate plane point cloud and at least one upper surface point cloud of the rib plate from the point cloud of the workpiece, and project the upper surface point cloud of the rib plate onto the bottom plate plane of the target workpiece to obtain the rib plate projection point cloud. Traverse the projection point cloud of the stiffener plate to obtain the weld endpoints, and determine the type of weld to be extracted based on the weld endpoints; When the weld type to be extracted is a straight weld, iterative straight line extraction is performed based on the stiffener projection point cloud to obtain a fitted line segment. When there are multiple corresponding fitted line segments in the projection point cloud of the stiffener plate, the fitted line segments are merged to obtain the fitted weld.
5. The method according to claim 4, characterized in that, When multiple corresponding fitted line segments exist in the projection point cloud of the stiffener plate, the fitted line segments are merged to obtain the fitted weld, which includes: In the case that there are multiple corresponding fitted line segments in the projection point cloud of the stiffener plate, determine the angle between each pair of fitted line segments and the shortest distance from the endpoint of one fitted line segment to the other fitted line segment within a pair of fitted line segments. When the included angle of the line segments is less than a set angle threshold and the shortest distance is less than a predetermined distance threshold, an adjacency graph of the pair of fitted line segments is constructed. Based on the adjacency graph, the fitted line segments to be merged are determined; The interior points of the fitted line segments to be merged are merged into a point cloud to be fitted, and the point cloud boundary of the point cloud to be fitted is determined. Based on the point cloud boundary of the point cloud to be fitted, a straight line is fitted to obtain the fitted weld.
6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The relative position of the welding equipment and the first welding direction is obtained, and the fitted weld is sampled according to the preset welding distance to obtain multiple welding points; When the welding edge is applied as a single-sided weld, if the side to be welded in the single-sided weld is consistent with the relative orientation, then the first welding direction is determined as the weld advance direction. If the side to be welded in the single-sided welding is not consistent with the relative orientation, then the second welding direction is determined as the weld advance direction, wherein the second welding direction is opposite to the first welding direction; When the welding edge is subjected to double-sided welding, the first welding direction and the second welding direction are determined as the weld advance direction; The welding points are sorted according to the direction of weld advancement to obtain a welding point sequence.
7. A weld seam information extraction device, characterized in that, The device includes: The weld fitting module is used to obtain the workpiece point cloud of the target workpiece, and to obtain the fitted weld based on the workpiece point cloud. The workpiece point cloud includes the bottom plate plane point cloud and the upper surface point cloud of the stiffener plate. The weld edge application type determination module is used to construct a first bounding box based on the fitted weld and determine the weld edge application type of the fitted weld according to the first point cloud of the base plate plane point cloud within the first bounding box. The stiffener plate height determination module is used to construct a second bounding box based on the fitted weld, and determine the stiffener plate height according to the height difference between the point cloud on the upper surface of the stiffener plate and the second point cloud within the second bounding box; The weld information determination module is used to determine the fitted weld, the weld edge application type, and the stiffener height as weld information.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Ultra-high power laser welding whole process monitoring method and system
CN117340459A
Ship group welding seam identification method, system and equipment and storage medium
CN118616984A
Weld joint identification method, storage medium and computer system
CN119579971A
Weld joint path planning method and device, computer equipment and readable storage medium
CN119600320A
Laser radar point cloud registration method for construction site robot
CN120031932A
Cited By
Thin and narrow weld joint identification method, computer equipment and readable storage medium
CN121258989A
