Artificial welding seam identification method and computer equipment

Abstract

The invention provides an artificial weld joint recognition method and computer equipment, and relates to the technical field of welding control. On the basis of determining the original plane set of the to-be-detected workpiece, each original plane included in the original plane set is traversed, and the target plane forming the concave dihedral angle with the traversed original plane in the original plane set is searched; dividing a theoretical intersection line segment between the searched target plane and the traversed original plane into a plurality of local line segments which are continuously distributed, and performing line segment distribution clustering on the plurality of local line segments according to the minimum point cloud projection distances of the target plane and the original plane on different local line segments; and performing artificial welding seam distribution detection according to the line segment clustering results of the target plane and the original plane at the plurality of local line segments, and determining whether an artificial welding seam exists between the target plane and the original plane, thereby performing accurate positioning identification on all the artificial welding seams substantially existing on the to-be-detected workpiece.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of welding control, in particular to a manual weld seam identification method and a computer device. BACKGROUND

[0002] With the rapid development of welding automation technology, various industries (for example, automobile industry, electronic assembly, metallurgical chemical industry, etc.) have higher requirements for welding precision, welding quality and welding safety. As the core link of the automatic welding system, the positioning result of the weld seam identification and positioning directly affects the final welding quality and production efficiency.

[0003] However, in the actual use process of the weld seam identification and positioning technology, there are often manual welding marks (i.e. manual weld seams) on the workpiece to be detected, and the manual weld seams need to be accurately identified so that the subsequent automatic welding operation can avoid the existing manual weld seams, or the identified manual weld seams can be welded and repaired to improve the overall welding quality. It is worth noting that the existing manual weld seam identification method is constructed on the basis of regarding the space region between planes as a whole, and its essence is suitable for identifying manual weld seams with continuous welding characteristics (i.e. continuous distribution of welding marks), which leads to the omission of manual weld seams with non-continuous welding characteristics (i.e. segmented and spaced distribution of welding marks) in the corresponding identification result, and cannot accurately position and identify all manual weld seams actually existing on the workpiece to be detected. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a manual weld seam identification method and a computer device, which can realize high-precision manual weld seam identification function by combining manual weld seam distribution detection operation on the basis of plane intersection line segment segmentation and clustering results (which include line segment clustering results of two intersecting planes respectively determined according to their own point cloud projection distance distribution details under the same intersection line segment division result), and can accurately position and identify all manual weld seams actually existing on any workpiece to be detected (whether they involve continuous welding characteristics or non-continuous welding characteristics).

[0005] In order to achieve the above purpose, the technical solutions adopted by the embodiments of the present application are as follows: In a first aspect, the present application provides a manual weld seam identification method, which comprises: plane detection on surface point cloud data of a workpiece to be detected to obtain an original plane set of the workpiece to be detected; traversing each original plane included in the original plane set to find a target plane in the original plane set which forms a concave dihedral angle with the traversed original plane; For each target plane found, the theoretical intersection segment between the target plane and the traversed original plane is divided into a plurality of locally distributed partial segments, and the plurality of partial segments are clustered according to the minimum point cloud projection distances of the target plane and the original plane on different partial segments, to obtain the segment clustering results of the target plane and the original plane on the plurality of partial segments; According to the segment clustering results of the target plane and the original plane, artificial weld distribution detection is performed to determine whether there is an artificial weld between the target plane and the original plane.

[0006] In an optional embodiment, for each to-be-clustered plane in any one of the target planes and the original plane traversed, the plurality of partial segments are clustered according to the minimum point cloud projection distances of the to-be-clustered plane on the plurality of partial segments, to obtain the segment clustering results of the to-be-clustered plane on the plurality of partial segments, including: The minimum point cloud projection distance of the to-be-clustered plane on any one partial segment less than a first preset distance threshold is zeroed, wherein the first preset distance threshold is a positive number close to 0; According to the relative arrangement relationship between the plurality of partial segments, a target segment group is extracted from the plurality of partial segments; wherein the minimum point cloud projection distances of all partial segments in any one target segment group are greater than 0, and all partial segments in the same target segment group are arranged in sequence according to the relative arrangement relationship; For each target segment group extracted, the segment clustering is performed according to the minimum point cloud projection distances of all partial segments included in the target segment group, to obtain at least one original clustering cluster matched with the target segment group; wherein all partial segments belonging to the same original clustering cluster are arranged in sequence according to the relative arrangement relationship, and the distance difference absolute value between the minimum point cloud projection distances of adjacent two partial segments in the same original clustering cluster is less than or equal to a preset distance difference threshold; The original clustering cluster with a number of corresponding segments greater than a preset segment number threshold and an average projection distance greater than a second preset distance threshold is taken as a target clustering cluster in the segment clustering results of the to-be-clustered plane; wherein the second preset distance threshold is greater than the first preset distance threshold.

[0007] In an optional embodiment, the step of performing artificial weld distribution detection according to the segment clustering results of the target plane and the original plane to determine whether there is an artificial weld between the target plane and the original plane, includes: It is detected whether there is a target clustering cluster with an average projection distance greater than a second preset distance threshold in the segment clustering results of the target plane and the original plane; In a case where at least one target cluster is detected in the line segment clustering results of the target plane and / or the original plane, the target plane and the original plane are determined to have no artificial weld joint therebetween.

[0008] In an optional embodiment, the step of detecting the artificial weld joint distribution according to the line segment clustering results of the target plane and the original plane to determine whether the target plane and the original plane have an artificial weld joint therebetween further comprises: In a case where at least one target cluster is detected in the line segment clustering results of the target plane and the original plane, all target clusters involved in the target plane and the original plane are combined and paired to obtain at least one set of effective cluster pairs between the target plane and the original plane. For each set of effective cluster pairs, an intermediate plane matching the set of effective cluster pairs is constructed; wherein a first plane intersection segment between the intermediate plane and the original plane is located in the original plane, an actual distance between the first plane intersection segment and a corresponding theoretical intersection segment is an average projection distance of the effective cluster corresponding to the original plane in the set of effective cluster pairs, a second plane intersection segment between the intermediate plane and the target plane is located in the target plane, and an actual distance between the second plane intersection segment and a corresponding theoretical intersection segment is an average projection distance of the effective cluster corresponding to the target plane in the set of effective cluster pairs. For each intermediate plane, whether there is an artificial weld joint structure feature near the intermediate plane is detected according to target point clouds near the intermediate plane on each reference plane except the target plane and the original plane in the original plane set. When it is detected that there is an artificial weld joint structure feature near at least one intermediate plane, it is determined that the target plane and the original plane have an artificial weld joint therebetween. When it is detected that there is no artificial weld joint structure feature near all intermediate planes, it is determined that the target plane and the original plane have no artificial weld joint therebetween.

[0009] In an optional embodiment, the step of combining and pairing all target clusters involved in the target plane and the original plane to obtain at least one set of effective cluster pairs between the target plane and the original plane comprises: Detecting whether the total number of target clusters corresponding to the target plane and the original plane remains consistent; When the total number of target cluster corresponding to the target plane and the original plane respectively is consistent, traversing all target clusters involved in the target plane, taking each traversed target cluster as one effective cluster in a single set of effective cluster pair, and taking target clusters involved in the target plane and maintaining the same arrangement order with the traversed target cluster as the other effective cluster in the single set of effective cluster pair; wherein the arrangement order between all target clusters involved in the target plane and the original plane respectively matches the relative arrangement relationship between the plurality of local line segments.

[0010] In optional embodiments, the step of combining and pairing all target clusters involved in the target plane and the original plane to obtain at least one set of effective cluster pairs between the target plane and the original plane further comprises: When the total number of target cluster corresponding to the target plane and the original plane respectively is not consistent, determining a first plane with a smaller total number of target clusters and a second plane with a larger total number of target clusters in the target plane and the original plane; Traversing all first target clusters involved in the first plane, taking each traversed first target cluster as one effective cluster in a single set of effective cluster pair, and for each traversed first target cluster, performing cluster merging on a plurality of second target clusters involved in the second plane, so that the corresponding merged cluster is the other effective cluster in the single set of effective cluster pair.

[0011] In optional embodiments, for each traversed first target cluster, the step of performing cluster merging on a plurality of second target clusters involved in the second plane comprises: Constructing an initial cluster interval matching the traversed first target cluster, wherein the two interval boundary endpoints of the initial cluster interval are consistent with the two cluster boundary endpoints of the traversed first target cluster; Traversing all second target clusters involved in the second plane, detecting whether each traversed second target cluster is in a merged state; If the traversed second target cluster is in a merged state, traversing the next second target cluster, otherwise detecting whether at least one cluster boundary endpoint of the traversed second target cluster is between the two interval boundary endpoints; when both of the two cluster boundary endpoints of the second target cluster traversed are not between the two interval boundary endpoints, traversing the next second target cluster, otherwise, marking the second target cluster traversed as a merged state, and updating the target boundary endpoint of the two interval boundary endpoints close to the reference boundary endpoint of the second target cluster according to the reference boundary endpoint of the second target cluster which is not between the two interval boundary endpoints; in the case of traversing all the second target clusters, performing cluster merging on all the second target clusters covered by the initial clustering interval to obtain a merged cluster matching the first target cluster traversed.

[0012] In an optional embodiment, for each intermediate plane, the step of detecting whether there is a manual weld structure feature near the intermediate plane according to the target point cloud close to the intermediate plane on each reference plane in the original plane set except the target plane and the original plane, comprises: generating a plurality of initial sampling points in the intermediate plane uniformly, and counting the number of effective sampling points in the plurality of initial sampling points based on all target point clouds close to the intermediate plane; wherein the average distance from each effective sampling point to a preset number of target discrete points adjacent to the effective sampling point in the target point cloud is less than a third preset distance threshold; detecting whether a first actual ratio between the total number of discrete points of all target point clouds and the maximum plane intersection segment length of the intermediate plane is greater than or equal to a first proportion threshold, and whether a second actual ratio between the number of effective sampling points and the total number of initial sampling points of the intermediate plane is greater than or equal to a second proportion threshold; if it is detected that the first actual ratio is greater than or equal to the first proportion threshold, and the second actual ratio is greater than or equal to the second proportion threshold, it is determined that there is a manual weld structure feature near the intermediate plane, otherwise it is determined that there is no manual weld structure feature near the intermediate plane.

[0013] In an optional embodiment, the identification method further comprises: detecting whether the original plane traversed belongs to a manual weld structure plane in the process of traversing each original plane included in the original plane set; if it is detected that the original plane traversed belongs to a manual weld structure plane, traversing the next original plane, otherwise, performing the step of finding the target plane constituting a concave dihedral angle with the original plane traversed in the original plane set, and detecting whether each target plane found belongs to a manual weld structure plane; If the target plane is detected to be an artificial weld structure plane, the step of finding the target plane that forms a concave dihedral angle with the original plane set and the traversed original plane continues; otherwise, the step of dividing the theoretical intersection line segment between the target plane and the traversed original plane into multiple continuously distributed local line segments is executed. The step of detecting whether any original plane in the set of original planes belongs to the artificial weld structure plane includes: Whether the number of target discrete points on the original plane associated with existing artificial weld structure features exceeds a preset discrete point number threshold. If the number of target discrete points on the original plane exceeds a preset discrete point count threshold, the original plane is determined to belong to the artificial weld structure plane; otherwise, the original plane is determined not to belong to the artificial weld structure plane.

[0014] Secondly, this application provides a computer device, including a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the manual weld identification method described in any of the foregoing embodiments.

[0015] In this case, the beneficial effects of the embodiments of this application may include the following: This application, based on the surface point cloud data of the workpiece to be inspected, determines the original set of planes of the workpiece. It then traverses each original plane in the original set and finds the target plane that forms a concave dihedral angle with the traversed original planes. For each target plane, the theoretical intersection line segment between the target plane and the traversed original plane is divided into multiple continuously distributed local line segments. Based on the minimum point cloud projection distance between the target plane and the original plane on different local line segments, the multiple local line segments are clustered to obtain the line segment clustering results for the target plane and the original plane at multiple local line segments. Finally, based on the line segment clustering results for the target plane and the original plane, manual weld seam segmentation is performed. The detection method is used to determine whether there is an artificial weld between the target plane and the original plane. Based on the segmentation and clustering results of intersecting planes (which include the segment clustering results of the two intersecting planes determined by their own point cloud projection distance distribution details under the same segmentation results), and combined with the artificial weld distribution detection operation (which involves hierarchical detection of artificial weld structure features in the three-dimensional point cloud data within the concave space range between planes (i.e., the three-dimensional space range enclosed by the concave two-sided structure formed by the two intersecting planes), a high-precision artificial weld identification function can be achieved. It can accurately locate and identify all artificial welds that actually exist on any workpiece to be inspected (regardless of whether they involve continuous or discontinuous welding features).

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the device composition of a computer device provided in an embodiment of this application; Figure 2 One of the flowcharts for the manual weld identification method provided in the embodiments of this application; Figure 3 for Figure 2 A flowchart illustrating the sub-steps included in step S230; Figure 4 for Figure 2 A flowchart illustrating the sub-steps included in step S240; Figure 5 for Figure 4 A flowchart illustrating the execution process of sub-step S243 in the diagram; Figure 6 for Figure 4 A flowchart illustrating the execution process of sub-step S245 in the diagram; Figure 7 This is a second schematic flowchart of the manual weld identification method provided in the embodiments of this application.

[0019] Icons: 10-Computer equipment; 11-Memory; 12-Processor; 13-Communication unit. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0023] In the description of this application, it should be understood that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product is in use, or the orientation or positional relationship commonly understood by those skilled in the art. They are used only for the convenience of describing this application and simplifying the description, and are not intended to indicate or imply that the equipment or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0024] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0025] Furthermore, it is understood in the description of this application that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, 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, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

[0026] Through painstaking research, the applicant discovered that existing manual weld seam recognition solutions, after detecting all workpiece planes using point cloud data of the workpiece surface, iterate through all workpiece planes to check whether any two intersecting planes conform to the concave dihedral structure construction standard (this standard is used to determine whether the dihedral structure formed by two corresponding intersecting planes presents a concave structure relative to the point cloud acquisition device). For these two intersecting planes that conform to the concave dihedral structure construction standard, edge detection is performed separately to obtain the edge point sets near the intersection line segment of each of the two intersecting planes. Then, by performing line fitting on the edge point sets of each of the two intersecting planes, two line segments are obtained (each line segment is located independently within the aforementioned two...). Within one of the intersecting planes), these two line segments can directly construct a bounded plane. Based on this, the number of point clouds near the bounded plane can be counted from other workpiece planes or unassigned point clouds (i.e., point cloud data that has not been screened to construct workpiece planes). At the same time, the number of valid sampling points (i.e., sampling points on the bounded plane that are close to the external point clouds) can be counted within the bounded plane. Then, by detecting whether the number of point clouds near the bounded plane and the number of valid sampling points on the bounded plane each meet the requirements for artificial weld discrimination, it can be directly determined that there is an artificial weld between the two intersecting planes when the aforementioned number of point clouds and the aforementioned number of valid sampling points each meet the requirements for artificial weld discrimination.

[0027] However, it is worth noting that for artificial welds with discontinuous welding characteristics, the edge points of the two intersecting planes in the local spatial region where the artificial weld exists are located on the edge of the artificial weld, while the edge points of the two intersecting planes in the local spatial region where the artificial weld does not exist are located on the plane intersection line. Therefore, when using existing artificial weld identification schemes to process artificial welds with discontinuous welding characteristics, the edge point sets of any two intersecting planes will contain both edge points corresponding to the artificial weld and edge points corresponding to the plane intersection line. This causes the positions of the two line segments fitted later to be more biased towards the plane intersection line, failing to effectively represent the distribution of discontinuous artificial welds. Furthermore, because the aforementioned existing artificial weld identification schemes perform overall statistics on the concave space range between planes in the point count discrimination stage, without considering the differences in the distribution characteristics of the nearby point clouds of continuous and discontinuous artificial welds, the final artificial weld identification results cannot effectively count discontinuous artificial welds.

[0028] To address this issue, the applicant has developed a method and computer equipment for identifying artificial weld seams, which can accurately locate and identify all artificial weld seams that actually exist on any workpiece to be inspected (regardless of whether they involve continuous or discontinuous welding features), thereby solving the technical problems existing in the above-mentioned artificial weld seam identification schemes.

[0029] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0030] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the equipment composition of the computer device 10 provided in this application embodiment. In this application embodiment, the computer device 10 can realize the artificial weld recognition function with different welding features (including continuous welding features and discontinuous welding features) for any workpiece to be inspected that needs to identify artificial welds, and can effectively ensure the reliability of the final recognition result, and achieve the effect of accurate positioning and recognition of artificial welds. The computer device 10 can be a welding robot equipped with a visual perception system (which can be implemented using sensing devices such as depth cameras and lidar), or it can be an independent electronic device communicatively connected to a welding robot equipped with a visual perception system. The independent electronic device can be, but is not limited to, a server, personal computer, laptop computer, etc.

[0031] In this embodiment, the computer device 10 may include a memory 11, a processor 12, and a communication unit 13. The memory 11, the processor 12, and the communication unit 13 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines.

[0032] In this embodiment, the memory 11 may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 11 is used to store computer programs, and the processor 12 can execute the computer programs accordingly after receiving execution instructions.

[0033] In this embodiment, the processor 12 can be an integrated circuit chip with signal processing capabilities. The processor 12 can be a general-purpose processor, including at least one of a central processing unit (CPU), graphics processing unit (GPU), network processor (NP), digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0034] In this embodiment, the communication unit 13 is used to establish a communication connection between the computer device 10 and other electronic devices through a network, and to send and receive data through the network, wherein the network includes wired communication networks and wireless communication networks. For example, the computer device 10 can obtain surface point cloud data of the workpiece to be inspected (i.e., the real point cloud data of the surface of the workpiece to be inspected in three-dimensional space) from the visual perception system through the communication unit 13, and perform manual weld identification based on the surface point cloud data.

[0035] In this embodiment, the computer device 10 may pre-store a specific computer program related to the manual weld seam recognition function in the memory 11, and by driving the processor 12 to execute the specific computer program, a high-precision manual weld seam recognition function can be achieved through the organic combination of the planar intersecting line segment segmentation clustering operation and the manual weld seam distribution detection operation. It can accurately locate and identify all the manual weld seams that actually exist on any workpiece to be inspected (regardless of whether they involve continuous welding features or discontinuous welding features).

[0036] Understandable Figure 1 The block diagram shown is only a schematic diagram of one configuration of the computer device 10. The computer device 10 may also include components such as... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0037] In this application, to ensure that the computer device 10 can accurately locate and identify all artificial welds that actually exist on any workpiece to be inspected, this application embodiment provides an artificial weld identification method to achieve the aforementioned objective. The artificial weld identification method provided by this application will be described in detail below.

[0038] Please refer to Figure 2 , Figure 2 This is one of the flowcharts illustrating the manual weld identification method provided in this application. In this application embodiment, Figure 2 The manual weld identification method shown may include steps S210 to S250.

[0039] Step S210: Perform planar detection on the surface point cloud data of the workpiece to be inspected to obtain the original planar set of the workpiece to be inspected.

[0040] In this embodiment, the original plane set of the workpiece to be inspected consists of multiple original planes of the workpiece. These multiple original planes are obtained by processing the surface point cloud data using traditional plane detection algorithms (e.g., region growing algorithm, RANSAC (Random Sample Consensus) algorithm, etc.). Each original plane in the original plane set can be assigned a unique plane number (which can be used to identify the original plane), and all original planes are arranged in ascending order of their plane numbers within the original plane set.

[0041] Step S220: Traverse each original plane included in the original plane set and find the target plane in the original plane set that forms a concave dihedral angle with the traversed original plane.

[0042] In this embodiment, for any original plane in the set of original planes, each target plane that matches the original plane is another original plane that intersects with the aforementioned original plane and whose corresponding dihedral structure is concave; that is, for any original plane, any target plane that matches the original plane in the set of original planes will form a concave dihedral angle with the original plane, and the two target planes that form the concave dihedral angle have a concave three-dimensional space required for artificial weld formation.

[0043] Once the original set of planes of the workpiece to be inspected is obtained, each original plane can be traversed sequentially according to its arrangement. For each traversed original plane, the step "find the target plane in the original set that forms a concave dihedral angle with the traversed original plane" is executed. Specifically, if for a traversed original plane, if no matching target plane can be found in the original set, or if all matching target planes have already been found in the original set, the traversal operation for that original plane can be terminated, and the traversal operation for the next original plane can begin.

[0044] In one embodiment of this invention, to improve the efficiency of manual weld seam identification and avoid unnecessary target plane search operations, the computer device 10 can introduce a non-repeating combination mechanism during the target plane search process to achieve the aforementioned objective. Specifically, when traversing to a certain original plane in the original plane set, the target plane search can be performed on the remaining planes in the original plane set that follow that original plane (i.e., all original planes whose corresponding plane number is greater than the currently traversed plane number (i.e., the actual plane number of the currently traversed original plane)) to avoid duplicate plane combinations globally.

[0045] Step S230: For each target plane found, the theoretical intersection line segment between the target plane and the traversed original plane is divided into multiple continuously distributed local line segments. Based on the minimum point cloud projection distance between the target plane and the original plane on different local line segments, the multiple local line segments are clustered to obtain the line segment clustering results of the target plane and the original plane at the multiple local line segments.

[0046] In this embodiment, for each original plane traversed, when any target plane matched by the original plane is determined, the theoretical intersection line segment between the two workpiece planes (i.e., the traversed original plane and its matched target plane) is calculated. Then, the theoretical intersection line segment is divided into multiple continuously distributed local line segments according to a preset line segment length (e.g., 1.5mm). Next, for each of the two workpiece planes, the minimum point cloud projection distance of the local plane point cloud of the surface point cloud data on the corresponding workpiece plane when projected into each local line segment is calculated (its essence is used to characterize the shortest distance from the plane boundary contour of the corresponding workpiece plane close to the theoretical intersection line segment to each local line segment of the theoretical intersection line segment). Specifically, for any given local line segment, if there exists a minimum point cloud projection distance of a related workpiece plane at that local line segment that is close to 0, it indicates that there is essentially no artificial weld in the local three-dimensional space where the local line segment is located for the aforementioned workpiece plane; and if there exists a minimum point cloud projection distance of a workpiece plane at that local line segment that is a large value (for example, exceeding a preset number greater than 0), it indicates that there may be an artificial weld in the local three-dimensional space where the local line segment is located for the aforementioned workpiece plane.

[0047] Once the minimum point cloud projection distances for the same intersecting line segments (i.e., the aforementioned multiple local line segments) are determined for each of the two workpiece planes, line segment distribution clustering (which can be implemented using an adaptive clustering algorithm) can be performed on all local line segments based on the minimum point cloud projection distances of the workpiece plane on the relevant local line segments and the relative arrangement relationship between the local line segments (which describes the arrangement order between the multiple local line segments) of each workpiece plane. This ensures that all local line segments belonging to the same cluster (each cluster corresponds to a separate point cloud projection distance value interval) are arranged sequentially according to the relative arrangement relationship, and the absolute value of the distance difference between the minimum point cloud projection distances of two adjacent local line segments in the same cluster is less than or equal to a preset distance difference threshold. This yields the line segment clustering result of the workpiece plane at the multiple local line segments (which consists of the clusters corresponding to each point cloud projection distance value interval).

[0048] Alternatively, please refer to Figure 3 , Figure 3 yes Figure 2 The flowchart of the sub-steps included in step S230 is shown below. In this embodiment of the application, in order to ensure that the line segment clustering results determined based on the line segment distribution clustering operation can describe the possibility of artificial welds as intuitively and accurately as possible, this application, for each plane to be clustered in the original plane and any target plane, performs the relevant step in step S230, "based on the minimum point cloud projection distance corresponding to the multiple local line segments involved in the plane to be clustered, performs line segment distribution clustering on the multiple local line segments to obtain the line segment clustering results of the plane to be clustered at the multiple local line segments," in detail (i.e., ...) Figure 3 In the manner of sub-steps S231 to S234, clusters that clearly indicate the absence of artificial welds in the corresponding line segment clustering results are filtered out.

[0049] Sub-step S231: Set the minimum point cloud projection distance of the plane to be clustered to zero at any local line segment where it is less than the first preset distance threshold.

[0050] In this embodiment, the first preset distance threshold is a positive number close to 0. The sub-step S231 is used to directly set the local line segments with a minimum point cloud projection distance close to 0 to a state where there are no artificial welds.

[0051] Sub-step S232: Extract target line segment groups from multiple local line segments according to the relative arrangement relationship between multiple local line segments.

[0052] In this embodiment, the minimum point cloud projection distance of all local line segments in any extracted target line segment group is greater than 0, and all local line segments in the same target line segment group are arranged sequentially according to the relative arrangement relationship. At this time, any target line segment group can essentially represent an intersection line segment region with suspected artificial welds at the corresponding clustering plane.

[0053] Sub-step S233: For each extracted target line segment group, perform line segment clustering based on the minimum point cloud projection distance of each local line segment included in the target line segment group to obtain at least one original cluster that matches the target line segment group.

[0054] In this embodiment, different original clusters within the same target line segment group each correspond to a single point cloud projection distance value range. Some original clusters involved in different target line segment groups may correspond to the same point cloud projection distance value range. The number of local line segments involved in different original clusters may be the same or different. All local line segments belonging to the same original cluster are arranged sequentially according to the relative arrangement relationship, and the absolute value of the distance difference between the minimum point cloud projection distances of two adjacent local line segments in the same original cluster is less than or equal to a preset distance difference threshold.

[0055] Sub-step S234: The original clusters with a corresponding number of line segments greater than a preset line segment number threshold and an average projection distance greater than a second preset distance threshold are taken as a target cluster in the line segment clustering results of the plane to be clustered.

[0056] In this embodiment, the average projection distance of any original cluster is the average distance between the minimum point cloud projection distances of all local line segments involved in the original cluster at the same clustering plane (e.g., the original plane traversed, or its corresponding target plane); the second preset distance threshold is greater than the first preset distance threshold, that is, the second preset distance threshold is used to initially identify whether the local three-dimensional space involved in each cluster does not have artificial welds or is suspected to have artificial welds. In other words, when any clustering plane (e.g., the original plane traversed) has at least one target cluster in its own line segment clustering results, there may be artificial welds in the concave space between the clustering plane and another clustering plane (e.g., any target plane matched with the traversed original plane), but when the clustering plane does not have a target cluster in its own line segment clustering results, there must be no artificial welds in the concave space between the clustering plane and another clustering plane.

[0057] Therefore, this application can ensure that the line segment clustering results of each plane to be clustered can describe the possibility of artificial welds as intuitively and accurately as possible for each plane to be clustered in the original plane and any target plane that has been traversed, by executing the above sub-steps S231 to S234.

[0058] Step S240: Based on the line segment clustering results of the target plane and the original plane, perform artificial weld distribution detection to determine whether there is an artificial weld between the target plane and the original plane.

[0059] In this embodiment, after determining the line segment clustering results of the traversed target plane and any matching target plane under the same intersection line segment division result, the distribution information of the target clusters in the line segment clustering results of the two workpiece planes (which may include the total number of target clusters corresponding to a single workpiece plane, the arrangement order of all target clusters belonging to the same workpiece plane on the corresponding theoretical intersection line segment, the cluster coverage of all target clusters belonging to the same workpiece plane on the corresponding theoretical intersection line segment, etc.) can be combined with the specific distribution of the local plane point clouds of other original planes (which may be called "reference planes") in the original plane set other than the aforementioned two workpiece planes (i.e., the traversed original planes and their matching target planes). Layered artificial weld structure feature detection is then performed in the concave space between the aforementioned two workpiece planes, thereby realizing the artificial weld distribution detection operation of the aforementioned two workpiece planes and effectively determining whether there is an artificial weld between the aforementioned two workpiece planes. Optionally, when it is determined that there is an artificial weld between the two workpiece planes, a weld information array representing the formation position of the artificial weld can be constructed separately based on the plane number of each of the two workpiece planes, so as to effectively determine the distribution details of the artificial weld on the workpiece to be inspected by reading the array.

[0060] Alternatively, please refer to Figure 4 , Figure 4 yes Figure 2 The flowchart of step S240 is shown below. In this embodiment, step S240 may include sub-steps S241 to S247, so as to achieve a detailed identification effect of artificial welds by using a hierarchical artificial weld structure feature detection method based on the results of planar intersecting line segmentation and clustering, thereby avoiding the phenomenon of missed detection of artificial welds.

[0061] Sub-step S241: Detect whether there is a target cluster whose average projection distance is greater than the second preset distance threshold in the line segment clustering results of the target plane and the original plane respectively.

[0062] In this embodiment, for any target plane that has been traversed and any target plane that it matches, if at least one of the two workpiece planes (e.g., the traversed target plane and / or the target plane that matches the original plane) does not involve any target cluster, it indicates that there is no possibility of an artificial weld between the two workpiece planes, and sub-step S242 will be executed accordingly; while if at least one of the two workpiece planes (e.g., the traversed target plane and / or the target plane that matches the original plane) involves one or more target clusters, it indicates that there is a possibility of an artificial weld between the two workpiece planes, and sub-step S243 will be executed accordingly.

[0063] Sub-step S242: Determine that there is no artificial weld between the target plane and the original plane.

[0064] Sub-step S243: Combine and pair all target clusters involved in the target plane and the original plane respectively to obtain at least one effective cluster pair between the target plane and the original plane.

[0065] In this embodiment, each effective cluster pair includes an effective cluster corresponding to the original traversed plane and an effective cluster corresponding to the target plane found. Each effective cluster pair corresponds individually to a single artificial weld layer detection space within the concave space between the two related workpiece planes.

[0066] Alternatively, please refer to Figure 5 , Figure 5 yes Figure 4 The flowchart of sub-step S243 is shown in the figure. In the embodiments of this application, sub-step S243 may include sub-steps S243a to S243d, which are used to perform artificial weld layer detection spatial delineation between two related workpiece planes based on the results of planar intersecting line segmentation and clustering.

[0067] Sub-step S243a: Detect whether the total number of target clusters corresponding to the target plane and the original plane are consistent.

[0068] In this embodiment, when the two related workpiece planes involved in the segmentation and clustering results of the intersecting line segments have the same total number of target clusters, it means that all the target clusters involved in each of the two related workpiece planes can be paired one by one to form at least one effective cluster pair. At this time, sub-step S243b can be executed. When the total number of target clusters of the two related workpiece planes is different, it means that cluster fusion is needed to ensure that the number of effective clusters involved in each of the two related workpiece planes is aligned to form at least one effective cluster pair. At this time, sub-step S243c can be executed.

[0069] Sub-step S243b: Traverse all target clusters involved in the original plane, take each traversed target cluster as one of the valid clusters in a single effective cluster pair, and take the target clusters involved in the target plane that maintain the same arrangement order as the traversed target clusters as another valid cluster in a single effective cluster pair.

[0070] In this embodiment, the arrangement order of all target clusters involved in the two related workpiece planes (i.e., the original planes traversed and their matching target planes) participating in the cluster combination is matched with the relative arrangement relationship between multiple local line segments involved in these two related workpiece planes. For example, when the two related workpiece planes involve local line segments 1 to 8 arranged sequentially, the target clusters involved in one workpiece plane are arranged sequentially as "{local line segment 1, local line segment 2}, {local line segment 5, local line segment 6}, and {local line segment 7, local line segment 8}", while the target clusters involved in the other workpiece plane are arranged sequentially as "{local line segment 1, local line segment 2, local line segment 3}, {local line segment 4, local line segment 5}, and {local line segment 6, local line segment 7, local line segment 8}". If the target cluster {local line segment 1, local line segment 2} and the target cluster {local line segment 1, local line segment 2, local line segment 3} are combined to form a pair of effective clusters, the target cluster {local line segment 5, local line segment 6} and the target cluster {local line segment 4, local line segment 5} are combined to form a pair of effective clusters, and the target cluster {local line segment 7, local line segment 8} and the target cluster {local line segment 6, local line segment 7, local line segment 8} are combined to form a pair of effective clusters.

[0071] Sub-step S243c: In the target plane and the original plane, determine the first plane with a smaller total number of target clusters and the second plane with a larger total number of target clusters.

[0072] Sub-step S243d involves traversing all first target clusters involved in the first plane, taking each traversed first target cluster as one of the effective clusters in a single effective cluster pair, and for each traversed first target cluster, merging multiple second target clusters involved in the second plane, so that the corresponding merged cluster is another effective cluster in a single effective cluster pair.

[0073] In this embodiment, for each first target cluster traversed, the step "merging multiple second target clusters involved in the second plane" in the above sub-step S243d may include sub-steps A to E, as shown below.

[0074] Sub-step A: Construct initial clustering intervals that match the first target cluster encountered during traversal.

[0075] Wherein, the two boundary endpoints of the initial clustering interval on the corresponding theoretical intersection line segment are consistent with the two cluster boundary endpoints of the first target cluster traversed; wherein, the two cluster boundary endpoints of the first target cluster are respectively the two line segment endpoints of the first merged line segment of the first target cluster (which is formed by splicing together all the local line segments involved in the first target cluster).

[0076] Sub-step B: Traverse all second target clusters involved in the second plane and check whether the second target cluster encountered each time is in a merged state.

[0077] Sub-step C: If the second target cluster being traversed is in a merged state, then traverse the next second target cluster; otherwise, check whether at least one cluster boundary endpoint of the second target cluster being traversed is between the two interval boundary endpoints.

[0078] In this context, the two cluster boundary endpoints of any second target cluster are the two line segment endpoints of the second merged line segment of the second target cluster (which is formed by splicing together all the local line segments involved in the second target cluster).

[0079] Sub-step D: When the two cluster boundary endpoints of the traversed second target cluster are not located between the two interval boundary endpoints, traverse the next second target cluster; otherwise, mark the traversed second target cluster as merged, and update the target boundary endpoints of the two interval boundary endpoints that are closer to the reference boundary endpoint according to the reference boundary endpoint of the second target cluster that is not located between the two interval boundary endpoints.

[0080] Sub-step E: After traversing all the second target clusters, merge all the second target clusters covered by the initial clustering interval to obtain a merged cluster that matches the traversed first target clusters.

[0081] Therefore, this application can ensure the alignment of the number of effective clusters involved in each of the two related workpiece planes by performing the above sub-steps A to E and using cluster fusion methods.

[0082] This application can perform artificial weld layer detection spatial delineation between two related workpiece planes by executing the above sub-steps S243a to S243d, based on the results of planar intersecting line segmentation and clustering.

[0083] Sub-step S244: For each valid cluster pair, construct an intermediate plane that matches that valid cluster pair.

[0084] In this embodiment, for any pair of valid clusters, the corresponding intermediate plane can be used to characterize the central plane of the corresponding artificial weld layer detection space. The first plane intersection segment between the intermediate plane and the currently traversed original plane is located within the original plane, and the actual distance between the first plane intersection segment and the relevant theoretical intersection segment is the average projection distance of the valid clusters in the pair of valid clusters corresponding to the original plane. At the same time, the second plane intersection segment between the intermediate plane and the found target plane is located within the target plane, and the actual distance between the second plane intersection segment and the corresponding theoretical intersection segment is the average projection distance of the valid clusters in the pair of valid clusters corresponding to the target plane.

[0085] Sub-step S245: For each intermediate plane, based on the target point cloud on each reference plane other than the target plane and the original plane in the original plane set, detect whether there are artificial weld structure features near the intermediate plane.

[0086] In this embodiment, for any intermediate plane, the actual distance from the target point cloud (which belongs to a portion of the local planar point cloud of the corresponding reference plane) on each reference plane to the intermediate plane or the planar boundary of the intermediate plane is less than a preset distance threshold. When artificial weld structure features are detected near one or more intermediate planes, it indicates that artificial welds actually exist in the partial artificial weld layer detection space within the concave space between two related workpiece planes, and sub-step S246 can be executed accordingly; when no artificial weld structure features are detected near any of the intermediate planes, it indicates that no artificial welds exist at all within the aforementioned concave space, and sub-step S247 can be executed accordingly.

[0087] Alternatively, please refer to Figure 6 , Figure 6 yes Figure 4 The flowchart of sub-step S245 is shown in the figure. In this embodiment of the application, for each intermediate plane, the above-mentioned sub-step S245 may include sub-steps S245a to S245d, so as to perform artificial weld structural feature detection for any artificial weld layer detection space within the concave space range.

[0088] Sub-step S245a: Generate multiple initial sampling points uniformly within the intermediate plane, and count the number of valid sampling points among the multiple initial sampling points based on all target point clouds near the intermediate plane.

[0089] In this embodiment, for each generated initial sampling point, a preset number (e.g., 8) of target discrete points closest to the initial sampling point can be found in the target point cloud of each reference plane near the corresponding intermediate plane. Then, the average distance between the actual distances of each of these preset number of target discrete points to the initial sampling point is calculated. Next, by determining whether the calculated average distance is less than a third preset distance threshold, it is determined whether the initial sampling point is a valid sampling point that may involve artificial weld seam structural features. Specifically, when the average distance corresponding to an initial sampling point is less than the third preset distance threshold, it can be determined that the initial sampling point is a valid sampling point that may involve artificial weld seam structural features.

[0090] Sub-step S245b: Detect whether the first actual ratio between the total number of discrete points of all target point clouds and the length of the maximum plane intersection segment of the intermediate plane is greater than or equal to a first ratio threshold, and whether the second actual ratio between the number of effective sampling points and the total number of initial sampling points of the intermediate plane is greater than or equal to a second ratio threshold.

[0091] In this embodiment, the maximum length of the intersecting line segment of a single intermediate plane is the maximum value among the first and second intersecting line segments involved in the intermediate plane. When the first actual ratio is detected to be greater than or equal to the first ratio threshold, and the second actual ratio is detected to be greater than or equal to the second ratio threshold, it indicates that there is a substantial artificial weld structure feature within the artificial weld layer detection space corresponding to the intermediate plane, and sub-step S245c can be executed accordingly; while when the first actual ratio is detected to be less than the first ratio threshold, and / or the second actual ratio is less than the second ratio threshold, it indicates that there is no substantial artificial weld structure feature within the artificial weld layer detection space corresponding to the intermediate plane, and sub-step S245d can be executed accordingly.

[0092] Sub-step S245c determines that there are artificial weld seam structural features near the intermediate plane.

[0093] In this embodiment, when it is determined that there is an artificial weld structure feature near a certain intermediate plane, the target discrete points of each reference plane in the corresponding target point cloud can be directly associated with the detected artificial weld structure feature.

[0094] Sub-step S245d determines that there are no artificial weld seam structural features near the intermediate plane.

[0095] In this embodiment, when it is determined that there are no artificial weld seam structural features near a certain intermediate plane, the target discrete points of each reference plane in the corresponding target point cloud cannot actually establish a correlation with the artificial weld seam structural features.

[0096] Therefore, this application can perform the above sub-steps S245a to S245d to detect the structural features of artificial welds in any artificial weld layer detection space within the concave space range.

[0097] Sub-step S246: When an artificial weld structure feature is detected near at least one intermediate plane, it is determined that an artificial weld exists between the target plane and the original plane.

[0098] Sub-step S247: When it is detected that there are no artificial weld seam structural features near all intermediate planes, it is determined that there is no artificial weld seam between the target plane and the original plane.

[0099] Therefore, by executing the above sub-steps S241 to S247, based on the results of the segmentation and clustering of intersecting line segments in the plane, this application can achieve a detailed identification effect of artificial welds by using a hierarchical artificial weld structure feature detection method, thereby avoiding the phenomenon of missed detection of artificial welds.

[0100] This application can achieve a high-precision artificial weld identification function by performing the above steps S210 to S240, through the organic combination of planar intersecting line segment segmentation and clustering operation and artificial weld distribution detection operation, and can accurately locate and identify all artificial welds that actually exist on any workpiece to be inspected.

[0101] Alternatively, please refer to Figure 7 , Figure 7 This is the second schematic flowchart of the manual weld identification method provided in this application embodiment. In this application embodiment, with Figure 2 Compared to the manual weld identification method shown, Figure 7 The differences between the manual weld identification methods shown are as follows: Figure 7 The manual weld identification method shown is implemented in the following way. Figure 2 In step S220, step S310 is executed before step S220a, "finding the target plane that forms a concave dihedral angle with the original plane set and the traversed original plane". Step S320 is inserted between the original steps S220 and S230 to verify the necessity of manual weld identification for the traversed original plane and any target plane found through steps S310 and S320, so as to improve the overall efficiency of manual weld identification.

[0102] Step S310: Traverse each original plane included in the original plane set and check whether the traversed original plane belongs to the artificial weld structure plane.

[0103] In this embodiment, the artificial weld structure plane is used to represent the surface smoothing result of the artificial weld; during the process of traversing each original plane included in the original plane set, the computer device 10 will prioritize performing artificial weld structure plane detection on each traversed original plane before executing step S220a, in order to determine whether it is necessary to continue to execute the subsequent method steps (including steps S220a, S320, S230 and S240) for the currently traversed original plane.

[0104] When it is detected that the original plane being traversed belongs to the artificial weld structure plane, it means that the original plane itself is part of the artificial weld. There is no need to further identify the artificial weld on the original plane. At this time, the traversal operation of the original plane can be ended directly, and the traversal operation of the next original plane can be started (the next original plane can be traversed by jumping back to execute step S310).

[0105] When it is detected that the original plane currently being traversed does not belong to the artificial weld structure plane, it indicates that the original plane itself is not part of the artificial weld. There is a need to further identify the artificial weld on the original plane. At this time, step S220a "find the target plane that forms a concave dihedral angle with the original plane being traversed" can be executed.

[0106] In this embodiment, the step of detecting whether any original plane in the set of original planes (including traversed original planes and found target planes) belongs to the artificial weld structure plane may include: Whether the number of target discrete points on the original plane associated with existing artificial weld structure features exceeds a preset discrete point number threshold. If the number of target discrete points on the original plane exceeds a preset discrete point count threshold, the original plane is determined to belong to the artificial weld structure plane; otherwise, the original plane is determined not to belong to the artificial weld structure plane.

[0107] Step S320: Detect whether the target plane found each time belongs to the artificial weld structure plane.

[0108] In this embodiment, when one or more target planes matching the original plane are found for any original plane that does not belong to the artificial weld structure plane, artificial weld structure plane detection can be performed on each found target plane to determine whether it is necessary to continue to execute subsequent method steps (including steps S230 and S240) for the currently found target plane.

[0109] When it is detected that the currently found target plane belongs to the artificial weld structure plane, it means that the target plane itself is part of the artificial weld. There is no need for the target plane to identify the artificial weld with the matching original plane. At this time, the further processing of the target plane can be ended directly, and the search operation for the next target plane can be started (the next target plane that matches the traversed original plane can be found by re-jumping to execute step S220a).

[0110] When it is detected that the target plane currently found does not belong to the artificial weld structure plane, it means that the target plane itself does not belong to the artificial weld. There is a need for the target plane to identify the artificial weld with the matching original plane. At this time, steps S230 and S240 can be continued for the target plane and the original plane that do not belong to the artificial weld plane.

[0111] Therefore, this application can be passed Figure 7 The manual weld identification method shown effectively improves the overall efficiency of manual weld identification in achieving accurate positioning and identification of manual welds on any workpiece to be inspected.

[0112] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0113] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. If the various functions provided in this application are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, including several instructions to cause a computer device (e.g., a laptop computer, a welding robot equipped with a visual perception system, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned readable storage medium includes: USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0114] The above descriptions are merely various embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for manually identifying weld seams, characterized in that, The identification method includes: Planar detection is performed on the surface point cloud data of the workpiece to be inspected to obtain the original plane set of the workpiece to be inspected; Traverse each original plane included in the original plane set, and find the target plane in the original plane set that forms a concave dihedral angle with the traversed original plane; For each target plane found, the theoretical intersection line segment between the target plane and the traversed original plane is divided into multiple continuously distributed local line segments. Based on the minimum point cloud projection distance between the target plane and the original plane on different local line segments, the multiple local line segments are clustered to obtain the line segment clustering results of the target plane and the original plane at the multiple local line segments. Artificial weld distribution detection is performed based on the line segment clustering results of the target plane and the original plane to determine whether there is an artificial weld between the target plane and the original plane.

2. The identification method according to claim 1, characterized in that, For each plane to be clustered in the traversed original plane and any target plane, the step of performing line segment distribution clustering on the multiple local line segments corresponding to the minimum point cloud projection distance at the multiple local line segments involved in the multiple local line segments, and obtaining the line segment clustering result of the plane to be clustered at the multiple local line segments, includes: The minimum point cloud projection distance of the plane to be clustered at any local line segment that is less than a first preset distance threshold is set to zero, wherein the first preset distance threshold is a positive number close to 0; Based on the relative arrangement relationship between the multiple local line segments, target line segment groups are extracted from the multiple local line segments; wherein, the minimum point cloud projection distance of each local line segment in any extracted target line segment group is greater than 0, and all local line segments in the same target line segment group are arranged sequentially according to the relative arrangement relationship. For each extracted target line segment group, line segment clustering is performed based on the minimum point cloud projection distance of each local line segment included in the target line segment group to obtain at least one original cluster that matches the target line segment group; wherein all local line segments belonging to the same original cluster are arranged sequentially according to the relative arrangement relationship, and the absolute value of the distance difference between the minimum point cloud projection distances of two adjacent local line segments in the same original cluster is less than or equal to a preset distance difference threshold. The original clusters with a corresponding number of line segments greater than a preset line segment number threshold and an average projection distance greater than a second preset distance threshold are taken as a target cluster in the line segment clustering results of the plane to be clustered; wherein, the second preset distance threshold is greater than the first preset distance threshold.

3. The identification method according to claim 1, characterized in that, The step of detecting the distribution of artificial welds based on the line segment clustering results of the target plane and the original plane to determine whether there are artificial welds between the target plane and the original plane includes: Detect whether there are target clusters in the line segment clustering results of the target plane and the original plane respectively, whose average projected distance is greater than a second preset distance threshold; If no target cluster is detected in the line segment clustering results of the target plane and / or the original plane respectively, it is determined that there is no artificial weld between the target plane and the original plane.

4. The identification method according to claim 3, characterized in that, The step of detecting the distribution of artificial welds based on the line segment clustering results of the target plane and the original plane to determine whether there are artificial welds between the target plane and the original plane further includes: If at least one target cluster is detected in the line segment clustering results of both the target plane and the original plane, all target clusters involved in the target plane and the original plane are combined and paired to obtain at least one effective cluster pair between the target plane and the original plane. For each pair of valid clusters, an intermediate plane matching that pair is constructed. The first plane intersection segment between the intermediate plane and the original plane lies within the original plane, and the actual distance between the first plane intersection segment and its corresponding theoretical intersection segment is the average projected distance between the valid clusters in that pair that correspond to the original plane. The second plane intersection segment between the intermediate plane and the target plane lies within the target plane, and the actual distance between the second plane intersection segment and its corresponding theoretical intersection segment is the average projected distance between the valid clusters in that pair that correspond to the target plane. For each intermediate plane, based on the target point cloud on each reference plane in the original plane set other than the target plane and the original plane, detect whether there are artificial weld structure features near the intermediate plane; When an artificial weld structure feature is detected near at least one intermediate plane, it is determined that an artificial weld exists between the target plane and the original plane; When no artificial weld seam structure features are detected near any intermediate plane, it is determined that there is no artificial weld seam between the target plane and the original plane.

5. The identification method according to claim 4, characterized in that, The step of combining and pairing all target clusters involved in the target plane and the original plane to obtain at least one set of valid cluster pairs between the target plane and the original plane includes: Check whether the total number of target clusters corresponding to the target plane and the original plane are consistent; When the total number of target clusters corresponding to the target plane and the original plane is consistent, all target clusters involved in the original plane are traversed. Each traversed target cluster is taken as one of the valid clusters in a single effective cluster pair, and the target clusters involved in the target plane that maintain the same arrangement order as the traversed target clusters are taken as the other valid cluster in the single effective cluster pair. The arrangement order between all target clusters involved in the target plane and the original plane matches the relative arrangement relationship between the multiple local line segments.

6. The identification method according to claim 5, characterized in that, The step of combining and pairing all target clusters involved in the target plane and the original plane to obtain at least one set of valid cluster pairs between the target plane and the original plane further includes: When the total number of target clusters corresponding to the target plane and the original plane are not consistent, a first plane with a smaller total number of target clusters and a second plane with a larger total number of target clusters are determined between the target plane and the original plane. Traverse all first target clusters involved in the first plane, and take each traversed first target cluster as one of the effective clusters in a single effective cluster pair. For each traversed first target cluster, merge the multiple second target clusters involved in the second plane, so that the corresponding merged cluster is another effective cluster in the single effective cluster pair.

7. The identification method according to claim 6, characterized in that, For each first target cluster encountered during traversal, the step of merging multiple second target clusters involved in the second plane includes: Construct an initial clustering interval that matches the first target clustering cluster traversed, wherein the two boundary endpoints of the initial clustering interval are consistent with the two cluster boundary endpoints of the first target clustering cluster traversed; Traverse all second target clusters involved in the second plane and check whether the second target cluster encountered each time is in a merged state; If the second target cluster encountered is already merged, then the next second target cluster is encountered; otherwise, it is checked whether at least one cluster boundary endpoint of the second target cluster encountered is between the two interval boundary endpoints. When the two cluster boundary endpoints of the second target cluster are not located between the two interval boundary endpoints, the next second target cluster is traversed; otherwise, the traversed second target cluster is marked as merged, and the target boundary endpoints of the two interval boundary endpoints that are closer to the reference boundary endpoint are updated according to the reference boundary endpoint of the second target cluster that is not located between the two interval boundary endpoints. After traversing all the second target clusters, all second target clusters covered by the initial clustering interval are merged to obtain a merged cluster that matches the traversed first target clusters.

8. The identification method according to any one of claims 4-7, characterized in that, For each intermediate plane, the step of detecting whether there are artificial weld structure features near the intermediate plane based on the target point cloud on each reference plane other than the target plane and the original plane in the original plane set includes: Multiple initial sampling points are uniformly generated within the intermediate plane, and the number of valid sampling points among the multiple initial sampling points is counted based on all target point clouds near the intermediate plane; wherein, the average distance from each valid sampling point to a preset number of target discrete points adjacent to the valid sampling point in the target point cloud is less than a third preset distance threshold. The system detects whether the first actual ratio between the total number of discrete points in all target point clouds and the length of the maximum plane intersection segment in the intermediate plane is greater than or equal to a first ratio threshold, and whether the second actual ratio between the number of effective sampling points and the total number of initial sampling points in the intermediate plane is greater than or equal to a second ratio threshold. If the first actual ratio is detected to be greater than or equal to the first ratio threshold, and the second actual ratio is greater than or equal to the second ratio threshold, then it is determined that there is an artificial weld structure feature near the intermediate plane; otherwise, it is determined that there is no artificial weld structure feature near the intermediate plane.

9. The identification method according to claim 8, characterized in that, The identification method further includes: During the process of traversing each original plane included in the original plane set, it is detected whether the traversed original plane belongs to the artificial weld structure plane. If the original plane detected during the traversal belongs to the artificial weld structure plane, then the next original plane is traversed; otherwise, the step of finding the target plane that forms a concave dihedral angle with the original planes traversed is executed, and it is checked whether the target plane found each time belongs to the artificial weld structure plane. If the target plane is detected to be an artificial weld structure plane, the step of finding the target plane that forms a concave dihedral angle with the original plane set and the traversed original plane continues; otherwise, the step of dividing the theoretical intersection line segment between the target plane and the traversed original plane into multiple continuously distributed local line segments is executed. The step of detecting whether any original plane in the set of original planes belongs to the artificial weld structure plane includes: Whether the number of target discrete points on the original plane associated with existing artificial weld structure features exceeds a preset discrete point number threshold. If the number of target discrete points on the original plane exceeds a preset discrete point count threshold, the original plane is determined to belong to the artificial weld structure plane; otherwise, the original plane is determined not to belong to the artificial weld structure plane.

10. A computer device, characterized in that, It includes a processor and a memory, the memory storing a computer program that can be executed by the processor, the processor being able to execute the computer program to implement the manual weld identification method according to any one of claims 1-9.

Images