A method and device for detecting welds of a bent plate, and a computer device

Abstract

The application relates to a weld seam detection method and device of a bent plate and a computer device. The method comprises the following steps: acquiring three-dimensional point cloud data of a steel bridge, the steel bridge comprising a bottom plate and a bent plate; determining a plane based on point cloud sets in the three-dimensional point cloud data, acquiring a plane with an inner point quantity conforming to a preset quantity, obtaining bottom plate plane and bent plate point cloud data; obtaining projection point cloud data of the bent plate on the bottom plate plane based on projection data of the bent plate point cloud data on the bottom plate plane; obtaining a weld seam contour based on straight line segments spliced by the projection point cloud data; based on a weld seam starting end, concatenating all straight line segments on the same weld seam from a starting point to an ending point to obtain a straight line segment sequence, the starting point of each straight line segment being determined according to distances of two end points of the straight line segment to the weld seam starting end; and obtaining weld seam key point information based on end points of the straight line segment sequence and intersection points of different straight line segments.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, and computer equipment for inspecting weld seams of bent plates. Background Technology

[0002] Steel bridges have advantages such as large span, strong load-bearing capacity, excellent wind and earthquake resistance, and short construction period. They are the core structural form of large-scale bridge projects. Multi-segment bent plates are important components of key parts of steel bridges such as main beams, towers, and supports. Their welds are multi-segmented and are the core key to ensuring the structural strength and stability of steel bridges. The quality and efficiency of the welding process directly determine the construction quality and progress of steel bridges.

[0003] In related technologies, workpiece point clouds can be collected by a 3D laser scanner and processed by algorithms to detect weld seams, thereby guiding robot welding. However, the structure of multi-segment bent plates of steel bridges has characteristics such as complex contours, weld seams in the form of continuous bends of multi-segment lines, and point cloud noise easily generated on the workpiece surface, resulting in large deviations in the detected weld seam information. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, and computer equipment for inspecting welds of bent plates to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for inspecting welds on bent plates. The method includes:

[0006] Acquire three-dimensional point cloud data of a steel bridge, which includes a base plate and a bent plate;

[0007] Based on the point cloud set in the three-dimensional point cloud data, a plane is determined, and a plane with a number of internal points that meets the preset number is obtained to obtain the bottom plate plane and the bending plate point cloud data.

[0008] Based on the projection data of the bending plate point cloud data on the base plate plane, the projection point cloud data of the bending plate on the base plate plane is obtained;

[0009] The weld contour is obtained by stitching together straight line segments based on the projected point cloud data.

[0010] Based on the starting end of the weld, all straight segments on the same weld are connected in series from the starting point to the ending point to obtain a sequence of straight segments. The starting point of each straight segment is determined according to the distance from the two endpoints of the straight segment to the starting end of the weld.

[0011] Based on the endpoints of the line segment sequence and the intersections of different line segments, key weld point information is obtained. In one embodiment, acquiring the three-dimensional point cloud data of the steel bridge includes:

[0012] The three-dimensional point cloud space of the steel bridge is divided to obtain several cubic voxels;

[0013] Based on the centroid of the point cloud within each voxel, the representative point of the voxel is obtained.

[0014] Three-dimensional point cloud data is obtained based on representative points along the thickness direction of the bent plate that do not exceed a preset filtering threshold.

[0015] In one embodiment, obtaining the weld contour based on the straight line segments stitched from the projected point cloud data includes:

[0016] Randomly sample the projected point cloud data to obtain line segments;

[0017] Clustering of the straight line segments yields weld contour point cloud data that matches the weld features;

[0018] Acquire target points whose distance from the weld contour point cloud data matches a preset distance;

[0019] The intersection point position corresponding to the number of intersections between the ray emitted from the target point and the weld contour point cloud data is 1, and the intersection point position is determined as the contour segmentation position.

[0020] The original point cloud data of the weld contour is processed at the segmentation location to obtain the weld contour.

[0021] In one embodiment, obtaining the target point whose distance from the original point cloud of the weld contour matches a preset distance includes:

[0022] Obtain the centroid of the weld contour point cloud data and any point on the weld contour point cloud data, and determine the direction vector from the centroid of the contour to the arbitrary point.

[0023] The target point is obtained by extending a predetermined distance outward from the centroid of the contour along the direction vector.

[0024] In one embodiment, the weld key point information includes key point coordinates, connection relationships between key points, length of each straight line segment, and bending angle between adjacent straight line segments.

[0025] In one embodiment, obtaining the three-dimensional spatial information of the weld seam includes:

[0026] The three-dimensional spatial information of the weld is converted into a format according to the communication protocol of the welding robot to obtain the converted operation information, which is used by the welding robot to perform welding operations.

[0027] Secondly, this application also provides a weld inspection device for bent plates, the device comprising:

[0028] The acquisition module is used to acquire three-dimensional point cloud data of a steel bridge, which includes a base plate and a bent plate.

[0029] Based on the point cloud set in the three-dimensional point cloud data, a plane is determined, and a plane with a number of internal points that meets the preset number is obtained to obtain the bottom plate plane and the bending plate point cloud data.

[0030] The projection module is used to obtain the projection point cloud data of the bent plate on the base plate plane based on the projection data of the bent plate point cloud data on the base plate plane;

[0031] The detection module is used to obtain the weld contour based on the straight line segments spliced ​​from the projected point cloud data;

[0032] Based on the starting end of the weld, all straight segments on the same weld are connected in series from the starting point to the ending point to obtain a sequence of straight segments. The starting point of each straight segment is determined according to the distance from the two endpoints of the straight segment to the starting end of the weld.

[0033] Based on the endpoints of the line segment sequence and the intersections of different line segments, the key point information of the weld is obtained.

[0034] Thirdly, this disclosure also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of a method for inspecting weld seams in a bent plate.

[0035] Fourthly, this disclosure also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of a method for inspecting weld seams in a bent plate.

[0036] Fifthly, this disclosure also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of a weld seam detection method for a bent plate.

[0037] The above-mentioned method for inspecting welds on bent plates has at least the following beneficial effects:

[0038] The embodiments provided in this disclosure vertically project the point cloud of the three-dimensional bent plate onto the plane of the base plate, transforming the three-dimensional spatial weld detection into two-dimensional planar processing, reducing computational load and improving overall operational efficiency. By extracting the weld contour by stitching together straight line segments from the projected point cloud, the method effectively adapts to the shape of multi-segment bent welds in steel bridges, avoiding contour breaks and line segment merging errors, resulting in high contour integrity. Standardized weld key point information is output, eliminating the need for manual correction of weld coordinates and robot pose, directly guiding the welding robot's operation, and significantly improving welding automation and construction efficiency.

[0039] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments or conventional technologies of this disclosure, the accompanying drawings used in the description of the embodiments or conventional technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is an application environment diagram of a weld inspection method for bent plates in one embodiment;

[0042] Figure 2 This is a flowchart illustrating a weld inspection method for a bent plate in one embodiment.

[0043] Figure 3 This is a structural block diagram of a weld inspection device for a bent plate in one embodiment;

[0044] Figure 4 This is an internal structural diagram of a computer device in one embodiment;

[0045] Figure 5 This is an internal structure diagram of a server in one embodiment. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0047] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure 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 of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitation, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. For example, the use of terms such as "first," "second," etc., is to denote names and does not indicate any specific order.

[0048] This disclosure provides a method for inspecting welds in bent plates, which can be applied to applications such as... Figure 1 In 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 located in the cloud or on other network servers. 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 speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0049] In some embodiments of this disclosure, such as Figure 2 As shown, a method for inspecting welds in bent plates is provided, which can be applied to... Figure 1 The method is illustrated using the example of a server processing point cloud data. It is understood that this method can be applied to a server, and also to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In a specific embodiment, the method may include the following steps:

[0050] S202: Obtain three-dimensional point cloud data of a steel bridge, the steel bridge including a base plate and a bent plate; determine a plane based on the point cloud set in the three-dimensional point cloud data, obtain a plane with an interior point number that meets a preset number, and obtain the base plate plane and bent plate point cloud data.

[0051] The steel bridge consists of a base plate and bent plates. The base plate is the plane with the largest area and the flattest surface. A minimum set of points is randomly selected from the 3D point cloud data. For a plane, three points can be used to generate a candidate plane. Since there are also many points on the bent plates, the algorithm may select points from those plates. Performing more than 1000 random attempts can greatly increase the probability of selecting the base plate point set.

[0052] The plane fitting error threshold can be set to less than or equal to 1 mm, which determines whether a point belongs to a candidate plane. The algorithm calculates the perpendicular distance from each point to the candidate plane. If this distance is ≤ 1 mm, the point is considered an interior point of the plane, i.e., a point that supports the plane; if it is > 1 mm, it is considered an exterior point.

[0053] In the embodiments of this disclosure, 1000 random samples are performed to obtain 1000 candidate planes. For each candidate plane, the number of interior points within the 1mm error threshold is counted. The candidate plane with the most interior points is selected from the 1000 candidate planes as the base plane.

[0054] S204: Based on the projection data of the bending plate point cloud data onto the base plate plane, obtain the projection point cloud data of the bending plate onto the base plate plane.

[0055] In three-dimensional space, the bent plate is a three-dimensional structure with thickness. The intersection line with the base plate is a complex three-dimensional curve. Directly detecting this curve requires handling complex spatial geometric relationships. By projection, the height information of all points is forcibly set to 0, and only their position information on the base plate plane is retained.

[0056] By projecting the point cloud of the bent plate perpendicularly along the normal of the base plate onto the base plate plane, the height information of all points is eliminated, and the complex three-dimensional weld is transformed into a clear two-dimensional planar outline, thus obtaining the projection point cloud data of the bent plate on the base plate plane.

[0057] S206: Based on the straight line segments stitched from the projected point cloud data, the weld contour is obtained; based on the starting end of the weld, all straight line segments on the same weld are connected from the starting point to the ending point to obtain a straight line segment sequence, wherein the starting point of each straight line segment is determined according to the distance from the two endpoints of the straight line segment to the starting end of the weld; based on the endpoints of the straight line segment sequence and the intersections of different straight line segments, the key point information of the weld is obtained.

[0058] Multiple line segments are obtained from the projected point cloud data. Line segments with very close endpoints are connected according to geometric topological relationships to obtain the weld contour. RANSAC line extraction is performed, and the number of samples is increased to 500 to ensure that the line segments inside each contour are extracted accurately and completely, providing high-precision basic data for subsequent sorting and key point extraction.

[0059] The start of a weld can be automatically identified by analyzing the geometric features of the contour. A set of line segments consists of several line segments belonging to the same weld. Each line segment has two endpoints. For each line segment, the Euclidean distance from its two endpoints to the start of the weld is calculated. Among all line segments, the line segment with the shortest distance is found. The endpoint of this line segment that is closer to the start of the weld is the starting point of the entire weld, and this line segment is the first line segment of the weld. Connecting all line segments on the same weld from the start to the end results in a sequence of line segments.

[0060] From the sorted sequence of line segments, the starting point of the first line segment is extracted as the weld start point, the ending point of the last line segment is extracted as the weld end point, and the intersection of adjacent line segments is extracted as the inflection point. The length and turning angle of each segment can be calculated at the same time, and finally the geometric data is transformed into weld key point information with engineering significance.

[0061] In the aforementioned weld inspection method for bent plates, the three-dimensional point cloud of the bent plate is vertically projected onto the base plate plane, transforming the three-dimensional weld inspection into two-dimensional planar processing, reducing computational load and improving overall operational efficiency. By extracting the weld contour by stitching together straight line segments from the projected point cloud, the method effectively adapts to the morphology of multi-segment bent welds in steel bridges, avoiding contour breaks and line segment merging errors, resulting in high contour integrity. Standardized weld key point information is output, eliminating the need for manual correction of weld coordinates and robot pose, directly guiding welding robot operations, and significantly improving welding automation and construction efficiency.

[0062] In some embodiments of this disclosure, acquiring the three-dimensional point cloud data of the steel bridge includes:

[0063] The three-dimensional point cloud space of the steel bridge is divided to obtain several cubic voxels;

[0064] Based on the centroid of the point cloud within each voxel, the representative point of the voxel is obtained.

[0065] Three-dimensional point cloud data is obtained based on representative points along the thickness direction of the bent plate that do not exceed a preset filtering threshold.

[0066] A 3D laser scanner acquires the 3D point cloud space of a steel bridge. A single scan may generate millions or even hundreds of millions of points, which directly leads to a very slow calculation speed for subsequent algorithms. Inevitably, some isolated and outlier noise points will be generated during the scanning process.

[0067] In three-dimensional space, using a set voxel size as the side length, the voxel size is adapted to the point cloud density of the multi-segment curved plate of the steel bridge. This size can be adjusted according to the actual scanning accuracy to create a huge three-dimensional cubic mesh. Each point in the point cloud is assigned to a unique small cube based on its coordinates, resulting in a cubic voxel. For each voxel, the algorithm calculates the centroid of all points within it, with the centroid being the center of the voxel. Redundant noise points within the voxel are removed while preserving the point cloud outline of the weld features, completing the initial noise removal. Finally, all original points in each small cube are deleted, retaining only the calculated centroid, resulting in the representative point of the voxel.

[0068] The base plate is a large flat surface, and the bent plate is welded onto it. All points belonging to the bent plate are concentrated in a strip-shaped area above the base plate plane and within its thickness range. Any point that is too high or too low above the base plate plane may be noise. The filtering direction is along the thickness direction of the bent plate of the polyline of the steel bridge, that is, perpendicular to the base plate. The filtering threshold is set to ±10% of the actual thickness of the bent plate. Outliers exceeding the threshold in this direction are removed, completing the secondary filtering, and obtaining clean point cloud data that is denoised and retains weld features, i.e., 3D point cloud data.

[0069] In some embodiments of this disclosure, obtaining the weld contour based on the straight line segments stitched from the projected point cloud data includes:

[0070] Randomly sample the projected point cloud data to obtain line segments;

[0071] Clustering of the straight line segments yields weld contour point cloud data that matches the weld features;

[0072] Acquire target points whose distance from the weld contour point cloud data matches a preset distance;

[0073] The intersection point position corresponding to the number of intersections between the ray emitted from the target point and the weld contour point cloud data is 1, and the intersection point position is determined as the contour segmentation position.

[0074] The original point cloud data of the weld contour is processed at the segmentation location to obtain the weld contour.

[0075] Projected point cloud data represents the weld as a set of discrete points on a plane, roughly outlining its shape. Two points are randomly selected from the projected point cloud data. A candidate straight line equation is calculated using these two points. The perpendicular distance from all other points to this candidate straight line is calculated, and the number of points whose distance is less than a preset distance is counted; these are called the interior points. Interior points are points that can form this straight line. This candidate straight line and its interior point count are recorded. From all candidate straight lines, the line with the most interior points is selected; this line is the most prominent and longest straight line segment in the point cloud.

[0076] In the embodiments of this disclosure, a random sampling line operation is performed using the projected two-dimensional point cloud as input. The sampling number is set to ≥300 times and the line fitting error threshold is set to ≤5mm. A set of random points is sampled in the two-dimensional point cloud and a line is fitted to initially extract all line segments in the point cloud.

[0077] Due to noise, occlusion, or RANSAC fitting errors, two line segments that should be connected may have tiny gaps, or there may be some extremely short, false line segments that do not belong to the weld. A point cloud clustering algorithm based on Euclidean distance is used, with a clustering distance threshold of ≤2mm, to cluster the point clouds of line segments. For example, if the spatial distance between the endpoints of line segment A and line segment B is ≤2mm, the algorithm considers A and B to be connected and belong to the same weld, resulting in a continuous cluster of multiple line segment point clouds.

[0078] The Alpha Shapes algorithm can be used, with alpha ≤ 2mm, to obtain ordered point cloud data of the weld contour. The Alpha Shapes algorithm can be understood as a small circle with radius α rolling in the point cloud. If this circle can roll from one point to another without containing any other points, then the line connecting these two points is part of the contour. If the circle cannot roll over the other point, then that edge is not part of the contour. The shape formed by all the edges is the weld contour point cloud data.

[0079] The target point that is at a distance from the weld contour point cloud data that meets the preset distance is the point outside the weld contour. Take a point P, and with point P as the center, calculate 3600 rays passing through point P with a direction of 0-360 degrees and a subdivision angle of 0.1 degrees. Calculate the intersection points of these rays with the original contour. Most rays intersect the contour 0 times, that is, they are directed to an open area, or 2 times, that is, they enter the contour and exit the contour. When a ray just passes through the edge of the contour, it may intersect the contour once, and be in a tangent state.

[0080] In the structure of the bent plate of a steel bridge, there are two physically separate weld seams. The intersection point corresponding to the number of intersections between the ray emitted from the target point and the weld seam contour point cloud data is 1, and the intersection point is determined as the contour segmentation point. At the found segmentation point, the original contour is cut off, and the original connected contour is divided into two independent weld seam contours, restoring the true physical structure.

[0081] In some embodiments of this disclosure, obtaining the target point whose distance from the original point cloud of the weld contour matches a preset distance includes:

[0082] Obtain the centroid of the weld contour point cloud data and any point on the weld contour point cloud data, and determine the direction vector from the centroid of the contour to the arbitrary point.

[0083] The target point is obtained by extending a predetermined distance outward from the centroid of the contour along the direction vector.

[0084] Calculate the centroid G of the contour. Select any point from the contour point cloud and denote it as point A. Use the vector from the centroid G to point A as the direction vector and extend it outward by a preset distance to obtain the target point P, which is used for subsequent ray scanning and contour segmentation.

[0085] In some embodiments of this disclosure, the weld key point information includes key point coordinates, connection relationships between key points, length of each straight line segment, and bending angle between adjacent straight line segments.

[0086] The coordinates of key points can be the three-dimensional coordinates of the start point, end point, and all inflection points of the weld. They can be used for welding positioning, path planning, and deviation comparison. The connection relationship between key points can be the topological connection sequence between key points, which determines the direction, segmentation, and adjacency relationship of the weld. The bending angle between adjacent straight segments is the angle at the point where the weld direction changes.

[0087] In some embodiments of this disclosure, obtaining the three-dimensional spatial information of the weld seam includes:

[0088] The three-dimensional spatial information of the weld is converted into a format according to the communication protocol of the welding robot to obtain the converted operation information, which is used by the welding robot to perform welding operations.

[0089] The integrated weld key point information includes all the critical parameters required for robotic welding and is converted according to the robot communication protocol format. This eliminates the need for manual correction by professional engineers, directly guiding the robot to complete the welding operation and lowering the barrier to entry for robotic welding. It significantly improves the welding efficiency of multi-segment bent plates for steel bridges. All parameters can be adjusted according to the actual size and scanning accuracy of the multi-segment bent plates, making it suitable for weld inspection of multi-segment bent plates of different specifications and bending angles, and possessing broad engineering application value.

[0090] It should be understood that although the steps in the flowcharts of the embodiments described above 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 embodiments described above 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 of other steps.

[0091] Based on the same inventive concept, this disclosure also provides a weld inspection device for bending plates to implement the above-described weld inspection method for bending plates. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in the embodiments of the weld inspection device for bending plates provided below can be found in the limitations of the weld inspection method for bending plates described above, and will not be repeated here.

[0092] The apparatus may include a system (including a distributed system), software (application), module, component, server, client, etc., that uses the methods described in the embodiments of this specification, combined with necessary hardware implementation. Based on the same innovative concept, the apparatuses in one or more embodiments provided in this disclosure are as described in the following embodiments. Since the implementation schemes and methods for solving the problem by the apparatus are similar, the implementation of the specific apparatus in the embodiments of this specification can refer to the implementation of the foregoing methods, and repeated details will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatuses described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0093] In one embodiment, such as Figure 3 As shown, a weld inspection device 300 for bent plates is provided. The device can be the aforementioned server, or a module, component, device, or unit integrated into the server. The device 300 may include:

[0094] The acquisition module 302 is used to acquire three-dimensional point cloud data of a steel bridge, which includes a base plate and a bent plate.

[0095] Based on the point cloud set in the three-dimensional point cloud data, a plane is determined, and a plane with a number of internal points that meets the preset number is obtained to obtain the bottom plate plane and the bending plate point cloud data.

[0096] Projection module 304 is used to obtain the projection point cloud data of the bent plate on the base plate plane based on the projection data of the bent plate point cloud data on the base plate plane;

[0097] The detection module 306 is used to obtain the weld contour based on the straight line segments spliced ​​from the projected point cloud data;

[0098] Based on the starting end of the weld, all straight segments on the same weld are connected in series from the starting point to the ending point to obtain a sequence of straight segments. The starting point of each straight segment is determined according to the distance from the two endpoints of the straight segment to the starting end of the weld.

[0099] Based on the endpoints of the line segment sequence and the intersections of different line segments, the key point information of the weld is obtained.

[0100] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0101] The modules in the aforementioned weld inspection device for bent plates can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0102] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. 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, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores point cloud data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for inspecting weld seams in a bent plate.

[0103] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. 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 stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for inspecting weld seams in bent plates. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0104] Those skilled in the art will understand that Figure 4 , Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0105] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods described in any embodiment of this disclosure.

[0106] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods described in any embodiment of this disclosure.

[0107] Those skilled in the art will understand that all or part of the processes in 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, and when executed, it 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 disclosure can include at least one of non-volatile 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 disclosure 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 disclosure may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0108] 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 specification.

[0109] The embodiments described above are merely illustrative of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent disclosure. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these all fall within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the appended claims.

Claims

1. A method for inspecting welds in bent plates, characterized in that, The method includes: Acquire three-dimensional point cloud data of a steel bridge, which includes a base plate and a bent plate; Based on the point cloud set in the three-dimensional point cloud data, a plane is determined, and a plane with a number of internal points that meets the preset number is obtained to obtain the bottom plate plane and the bending plate point cloud data. Based on the projection data of the bending plate point cloud data on the base plate plane, the projection point cloud data of the bending plate on the base plate plane is obtained; The weld contour is obtained by stitching together straight line segments based on the projected point cloud data. Based on the starting end of the weld, all straight segments on the same weld are connected in series from the starting point to the ending point to obtain a sequence of straight segments. The starting point of each straight segment is determined according to the distance from the two endpoints of the straight segment to the starting end of the weld. Based on the endpoints of the line segment sequence and the intersections of different line segments, the key point information of the weld is obtained.

2. The method according to claim 1, characterized in that, The acquisition of the three-dimensional point cloud of the steel bridge The data includes: The three-dimensional point cloud space of the steel bridge is divided to obtain several cubic voxels; Based on the centroid of the point cloud within each voxel, the representative point of the voxel is obtained. Three-dimensional point cloud data is obtained based on representative points along the thickness direction of the bent plate that do not exceed a preset filtering threshold.

3. The method according to claim 1, characterized in that, The weld contour obtained by stitching together the straight line segments based on the projected point cloud data includes: Randomly sample the projected point cloud data to obtain line segments; Clustering of the straight line segments yields weld contour point cloud data that matches the weld features; Acquire target points whose distance from the weld contour point cloud data matches a preset distance; The intersection point position corresponding to the number of intersections between the ray emitted from the target point and the weld contour point cloud data is 1, and the intersection point position is determined as the contour segmentation position. The original point cloud data of the weld contour is processed at the segmentation location to obtain the weld contour.

4. The method according to claim 3, characterized in that, The acquisition of target points whose distance from the original point cloud of the weld contour matches a preset distance includes: Obtain the centroid of the weld contour point cloud data and any point on the weld contour point cloud data, and determine the direction vector from the centroid of the contour to the arbitrary point. The target point is obtained by extending a predetermined distance outward from the centroid of the contour along the direction vector.

5. The method according to claim 1, characterized in that, The key information of the weld includes the coordinates of the key points, the connection relationship between the key points, the length of each straight line segment, and the bending angle between adjacent straight line segments.

6. The method according to claim 5, characterized in that, After obtaining the three-dimensional spatial information of the weld, the process includes: The key weld information is converted into a format according to the communication protocol of the welding robot to obtain the converted operation information, which is used by the welding robot to perform welding operations.

7. A weld inspection device for bent plates, characterized in that, The device includes: The acquisition module is used to acquire three-dimensional point cloud data of a steel bridge, which includes a base plate and a bent plate. Based on the point cloud set in the three-dimensional point cloud data, a plane is determined, and a plane with a number of internal points that meets the preset number is obtained to obtain the bottom plate plane and the bending plate point cloud data. The projection module is used to obtain the projection point cloud data of the bent plate on the base plate plane based on the projection data of the bent plate point cloud data on the base plate plane; The detection module is used to obtain the weld contour based on the straight line segments spliced ​​from the projected point cloud data; Based on the starting end of the weld, all straight segments on the same weld are connected in series from the starting point to the ending point to obtain a sequence of straight segments. The starting point of each straight segment is determined according to the distance from the two endpoints of the straight segment to the starting end of the weld. Based on the endpoints of the line segment sequence and the intersections of different line segments, the key point information of the weld is obtained.

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.

Images