Symmetric workpiece cutting methods, apparatuses, devices, and media

Abstract

Embodiments of the present application provide a symmetrical workpiece cutting method, device, equipment and medium, relating to the field of robot technology, the method comprises: obtaining registration related data, obtaining at least one candidate cutting plane based on registration related data analysis, for each candidate cutting plane, consistent cutting is carried out on complete workpiece point cloud and corresponding surface structure point cloud, the surface structure after consistent cutting is combined two by two and the space intersection line is calculated, the end point or feature point of the space intersection line is extracted, and the weld point set of the corresponding cutting scheme is constructed. The weld point set is matched with the complete weld database in space, the candidate cutting scheme meeting the weld integrity requirement is screened out, each candidate cutting scheme is traversed, and the target cutting scheme is determined, so that the reliability of the cutting scheme is improved.

Description

Technical Field

[0001] This invention relates to the field of robotics, and more specifically, to a method, apparatus, equipment, and medium for cutting symmetrical workpieces. Background Technology

[0002] In robotic welding and automated machining of complex workpieces, implementing reasonable workpiece spatial segmentation and ensuring weld integrity are prerequisites for generating reliable welding paths. In related technologies, the assessment of weld integrity after segmentation mainly employs indirect analysis methods based on planar structures, but their reliability needs improvement.

[0003] Among them, weld integrity requires that the weld topology remain consistent before and after cutting, that is, no new welds are generated and no original welds are lost, so as to ensure the continuity and availability of the welding path. Summary of the Invention

[0004] One of the objectives of this invention includes, for example, providing a method, apparatus, device, and medium for cutting symmetrical workpieces to at least partially improve the reliability of cutting scheme determination and ensure weld integrity.

[0005] The embodiments of the present invention can be implemented as follows: In a first aspect, embodiments of the present invention provide a method for cutting symmetrical workpieces, including: Obtain registration-related data, which includes a complete workpiece point cloud, a set of surface structure point clouds, and a complete weld database; At least one candidate cutting plane is obtained based on the registration-related data analysis. For each candidate cutting plane, the complete workpiece point cloud and the corresponding surface structure point cloud are uniformly cut; The surface structures after uniform cutting are combined in pairs and spatial intersection lines are calculated. By extracting the endpoints or feature points of the spatial intersection lines, the weld point set of the corresponding cutting scheme is constructed. Spatial matching is performed between the weld point set and the complete weld database to filter out candidate cutting schemes that meet the weld integrity requirements; The target cutting scheme is determined by iterating through all the candidate cutting schemes.

[0006] In an optional implementation, the step of spatially matching the weld point set with the complete weld database to filter out candidate cutting schemes that meet the weld integrity requirements includes: The set of weld points is spatially matched with the complete weld database. The correspondence is determined by nearest neighbor search and tolerance constraints to identify all abnormal weld points. The number of abnormal weld points was counted, and the difference index was calculated. Determine whether the difference index exceeds the weld integrity safety threshold; If not, the cutting scheme corresponding to the weld point set is determined as a candidate cutting scheme that meets the weld integrity requirements.

[0007] In an optional implementation, the step of spatially matching the weld point set with the complete weld database, determining the correspondence through nearest neighbor search and tolerance constraints, and identifying all abnormal weld points includes: Spatial matching is performed between the weld point set and the complete weld database. Nearest neighbor search is performed on each weld point in the weld point set. The point closest to the weld point is determined in the complete weld database, and the spatial distance between the two is calculated. The spatial distance is compared with a preset tolerance threshold, and abnormal weld points are identified based on the comparison results.

[0008] In an optional implementation, the step of counting the number of abnormal weld points and calculating the difference index includes: Identify the abnormal type of each abnormal weld point, divide the number of abnormal weld points of each abnormal type by the total number of weld points in the weld point set, and obtain the basic abnormal ratio of abnormal weld points of each abnormal type. Obtain the weight coefficients corresponding to each of the aforementioned anomaly types, and obtain the weighted anomaly ratio by weighted summation based on the basic anomaly ratio and weight coefficients of the abnormal weld points for each of the aforementioned anomaly types. Calculate the error contribution factor and the standard deviation penalty factor; Multiply the weighted outlier ratio, error contribution factor, and standard deviation penalty factor to obtain the difference index.

[0009] In an optional implementation, the step of traversing each of the candidate cutting schemes to determine the target cutting scheme includes: Iterate through each of the candidate cutting schemes to determine whether there is a cutting scheme that satisfies the constraints. If so, the optimal cutting scheme is determined from the cutting schemes that satisfy the constraints as the target cutting scheme; If not, return a failure status.

[0010] In an optional implementation, the constraints include the symmetry score of the candidate cutting plane being higher than a first preset value; and the difference index being lower than a second preset value.

[0011] In an optional implementation, obtaining at least one candidate cutting plane based on the registration correlation data analysis includes: A set of candidate cutting planes is generated based on symmetry analysis; or, A set of candidate cutting planes is generated based on the principal component analysis strategy.

[0012] Secondly, embodiments of the present invention provide a symmetrical workpiece cutting device, comprising: The information acquisition module is used to acquire registration-related data, which includes a complete workpiece point cloud, a set of surface structure point clouds, and a complete weld database. The information processing module is used to obtain at least one candidate cutting plane based on the registration-related data analysis; for each candidate cutting plane, to perform consistent cutting on the complete workpiece point cloud and the corresponding surface structure point cloud; to combine the surface structures after consistent cutting in pairs and calculate the spatial intersection line, and to construct the weld point set of the corresponding cutting scheme by extracting the endpoints or feature points of the spatial intersection line; to perform spatial matching between the weld point set and the complete weld database, and to filter out candidate cutting schemes that meet the weld integrity requirements; and to traverse each candidate cutting scheme to determine the target cutting scheme.

[0013] Thirdly, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the symmetrical workpiece cutting method described in any of the foregoing embodiments.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a computer program, wherein the computer program, when running, controls the electronic device on which the computer-readable storage medium is located to perform the symmetrical workpiece cutting method described in any of the foregoing embodiments.

[0015] The beneficial effects of this invention include, for example, obtaining a complete workpiece point cloud, a set of surface structure point clouds, and a complete weld database to comprehensively and accurately acquire geometric information. Based on this data analysis, multiple candidate cutting planes are obtained, and consistent cutting is performed, ensuring high precision and consistency in cutting. By calculating spatial intersection lines and extracting endpoints or feature points to construct a weld point set, explicit reconstruction of the weld is achieved. Through spatial matching with the complete weld database, candidate cutting schemes that meet the weld integrity requirements are selected, thereby optimizing the final cutting scheme selection and improving cutting reliability. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, 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 the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1The diagram illustrates an application scenario provided by an embodiment of the present invention.

[0018] Figure 2 A schematic flowchart of a symmetrical workpiece cutting method provided by an embodiment of the present invention is shown.

[0019] Figure 3 It shows Figure 2 A flowchart of the S150 process.

[0020] Figure 4 It shows Figure 3 A flowchart of S152.

[0021] Figure 5 This diagram illustrates another flow chart of a symmetrical workpiece cutting method provided by an embodiment of the present invention.

[0022] Figure 6 An exemplary structural block diagram of a symmetrical workpiece cutting device provided by an embodiment of the present invention is shown.

[0023] Icons: 100 - Electronic device; 110 - Memory; 120 - Processor; 130 - Communication module; 140 - Symmetrical workpiece cutting device; 141 - Information acquisition module; 142 - Information processing module. Detailed Implementation

[0024] In related technologies, assessing the integrity of the segmented weld is one of the key technical prerequisites for generating a reliable welding path. In application, indirect analysis methods based on planar structures can be considered for assessing the integrity of segmented welds. For example, indirect analysis methods based on planar structures can include the following three categories: (1) Weld integrity assessment method based on surface structure inclusion relationship: The surface structure point cloud data of the workpiece is extracted by model-free construction technology. After cutting, the integrity is assessed by judging whether each surface structure is completely included by a certain sub-point cloud. The core principle is: if a certain surface structure still exists completely in a certain sub-region after cutting, it is determined that the surface structure has not been destroyed, thereby indirectly inferring that the corresponding weld has not been cut off and remains intact.

[0025] This method essentially uses "surface structure retention" to indirectly characterize "weld integrity".

[0026] (2) Segmentation evaluation method based on geometric property consistency: The rationality of the segmentation scheme is evaluated by comparing the volume, surface area or local geometric feature distribution of the point cloud before and after the segmentation.

[0027] This method focuses on overall geometric consistency but does not model the weld, a key engineering feature.

[0028] (3) Weld identification methods based on semantic rules or empirical rules: Weld areas are identified through manual rules or learning models, and matching judgment is performed after cutting. However, this method relies on prior information or training data, has weak generalization ability, and is difficult to adapt to complex industrial scenarios.

[0029] Research has revealed the following problems with indirect analysis methods based on planar structures: (1) Inability to accurately handle two-sided structural weld scenarios: When a weld is formed by the intersection of two planes, the cutting operation may damage the surface structure but not actually cut the weld. Assessment methods based on the integrity of the surface structure will produce misjudgments in such scenarios.

[0030] Among them, the two-sided structure refers to the structure formed by the intersection of two spatial planes. The line of intersection corresponds geometrically to the potential weld position and is the basic structural unit for weld generation.

[0031] (2) The weld is represented implicitly and is difficult to analyze directly: the weld is attached to the surface structure or the overall geometric relationship and lacks independent expression, which makes it impossible to achieve stable evaluation when the surface structure is damaged or the point cloud is incomplete.

[0032] (3) Lack of a unified quantitative evaluation mechanism: It is mostly driven by experience or rules, lacks unified numerical evaluation indicators, and makes it difficult to make objective comparisons and automatic optimizations among multiple cutting schemes.

[0033] Based on the above research, this invention provides a symmetrical workpiece cutting scheme to realize weld integrity assessment for symmetrical workpiece cutting verification. By constructing a unified mechanism of "explicit weld reconstruction - anomaly detection - quantitative assessment - scheme optimization", the scheme achieves automated determination of weld integrity and improves reliability.

[0034] Among them, explicit weld reconstruction refers to converting the weld information implicitly existing in the surface structure into an explicit geometric point set expression by calculating the spatial intersection line between any two surface structures, extracting the endpoints or key points of the intersection line.

[0035] The shortcomings of the above solutions are the result of the inventors' practical experience and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the embodiments of the present invention in the following text should be considered as contributions made by the inventors during the invention process.

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0037] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0038] It should be noted that 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 limitation, 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.

[0039] 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.

[0040] It should be noted that, where there is no conflict, the features in the embodiments of the present invention can be combined with each other.

[0041] Please refer to Figure 1 This is a block diagram of an electronic device 100 provided in this embodiment. The electronic device 100 in this embodiment can be a server, processing device, processing platform, etc., capable of data interaction and processing. For example, the electronic device 100 can be a control device for a cutting robot, or a control server capable of communicating with the robot. The electronic device 100 includes a memory 110, a processor 120, and a communication module 130. The memory 110, processor 120, and communication module 130 are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0042] The memory 110 is used to store programs or data. The memory 110 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.

[0043] The processor 120 is used to read / write data or programs stored in the memory 110 and to perform corresponding functions.

[0044] The communication module 130 is used to establish a communication connection between the electronic device 100 and other communication terminals through the network, and to send and receive data through the network.

[0045] It should be understood that, Figure 1 The structure shown is only a schematic diagram of the electronic device 100. The electronic device 100 may also include components that are larger than... 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.

[0046] Please refer to the following: Figure 2 This is a flowchart illustrating a symmetrical workpiece cutting method provided in an embodiment of the present invention. It can be derived from... Figure 1 The electronic device 100 performs the operation, for example, by a processor 120 within the electronic device 100. The symmetrical workpiece cutting method includes steps S110 to S160. S110, obtain registration-related data, which includes complete workpiece point cloud, surface structure point cloud set, and complete weld database.

[0047] S120, at least one candidate cutting plane is obtained based on the registration-related data analysis.

[0048] S130, for each of the candidate cutting planes, perform consistent cutting on the complete workpiece point cloud and the corresponding surface structure point cloud.

[0049] S140: Combine the surface structures after consistent cutting in pairs and calculate the spatial intersection lines. By extracting the endpoints or feature points of the spatial intersection lines, construct the weld point set of the corresponding cutting scheme.

[0050] S150, Spatial matching is performed between the weld point set and the complete weld database to select candidate cutting schemes that meet the weld integrity requirements. S160, traverse all the candidate cutting schemes and determine the target cutting scheme.

[0051] In this embodiment, after consistent cutting, the weld point set of the corresponding cutting scheme is constructed by calculating the spatial intersection line, realizing the transformation of the weld from implicit expression to explicit expression, which significantly improves the analyzability of subsequent cutting schemes. By spatially matching the weld point set with the complete weld database, candidate cutting schemes that meet the weld integrity requirements are screened and the target cutting scheme is determined, ensuring weld integrity and improving cutting reliability.

[0052] In S110, the complete workpiece point cloud can be generated by sampling the complete workpiece or the computer-aided design (CAD) model of the complete workpiece using a high-precision 3D scanning device, and saved as standard point cloud data (PCD) format, denoted as complete workpiece 3D point cloud data (model.pcd).

[0053] The surface structure point cloud set can be obtained by preprocessing the original point cloud of the complete workpiece, such as model.pcd (e.g., normal vector estimation, plane segmentation, region growth, etc.), extracting the point cloud subset belonging to the set surface structure, and storing it, denoted as the surface structure point cloud set (filter_1 folder).

[0054] A complete weld database can be built upon welding process data of complete workpieces, either manually annotated or automatically extracted. It can extract weld centerlines, key feature points, and corresponding process parameters (such as position, angle, and gap), storing them in structured text format for registration and error analysis. This database is denoted as the complete weld database (point_base.txt).

[0055] After obtaining the registration-related data in S110, the process of analyzing the registration-related data in S120 to obtain at least one candidate cutting plane can be flexibly implemented. For example, a set of candidate cutting planes can be generated based on symmetry analysis. Alternatively, a set of candidate cutting planes can be generated based on a principal component analysis (PCA) strategy. The generated candidate cutting planes are then used as a set of cutting schemes to be evaluated.

[0056] Among them, the principal component analysis strategy is used to obtain three principal directions based on point cloud PCA, and to generate cutting planes along the principal directions with the centroid as the origin.

[0057] After obtaining each candidate cutting plane based on S120, the point cloud and surface structure are simultaneously cut through S130. For each candidate cutting plane, the complete workpiece point cloud (overall workpiece point cloud) and all its corresponding surface structure point clouds are cut in a consistent manner, so that the geometric relationships are maintained synchronously.

[0058] Consistent cutting refers to simultaneously cutting all corresponding surface structure point clouds when cutting the overall point cloud of a workpiece, ensuring that the geometric relationships after cutting remain consistent with the original spatial relationships. This can be achieved by first defining a unified cutting plane equation, and then applying the same cutting logic to all point clouds based on this plane equation, ensuring that each point cloud is segmented according to the exact same spatial geometric relationships.

[0059] After consistent cutting based on S130, two-sided structure combination and weld reconstruction are performed through S140. All surface structures after consistent cutting are combined in pairs, their spatial intersection lines are calculated, and the endpoints or feature points of the intersection lines are extracted to construct the weld point set under the current cutting scheme, thereby realizing the explicit reconstruction of the weld.

[0060] In this embodiment, the weld representation method breaks through the traditional indirect judgment method that relies on the integrity of the surface structure, transforming the weld from an "implicit geometric relationship attached to the surface structure" into "explicit spatial information that can be analyzed independently." By combining the point clouds of the surface structure in pairs, the spatial intersection lines between each plane are calculated, thereby reconstructing the geometric position of the weld and its endpoint set. This process does not rely on the complete surface structure; even if the surface structure is damaged during the cutting process, the weld representation can still be stably obtained, achieving decoupling and explicit modeling of weld information, laying the foundation for subsequent analysis.

[0061] Please refer to the following: Figure 3 After the explicit reconstruction of the weld seam is achieved based on S140, the weld seam point set is spatially matched with the complete weld seam database in S150, and candidate cutting schemes that meet the weld seam integrity requirements can be selected through S151, S152, S153 and S154.

[0062] S151, Spatial matching is performed between the weld point set and the complete weld database, and the correspondence is determined by nearest neighbor search and tolerance constraints to identify all abnormal weld points.

[0063] S152, count the number of abnormal weld points and calculate the difference index.

[0064] S153, determine whether the difference index exceeds the weld integrity safety threshold; if not, proceed to S154.

[0065] S154, the cutting scheme corresponding to the weld point set is determined as a candidate cutting scheme that meets the weld integrity requirements.

[0066] Abnormal weld points in S151 can be obtained through analysis as follows: Spatial matching is performed between the weld point set and the complete weld database; a nearest neighbor search is performed on each weld point in the weld point set; the point closest to the weld point in the complete weld database is determined; and the spatial distance between the two is calculated. The spatial distance is compared with a preset tolerance threshold, and abnormal weld points are identified based on the comparison result.

[0067] For example, the weld point set obtained by consistent cutting can be spatially matched with the complete weld database, and the correspondence can be determined by nearest neighbor search and tolerance constraints to identify all abnormal weld points.

[0068] The process and criteria for identifying abnormal weld points include: spatially matching the reconstructed weld point set after cutting with the complete weld database; performing a nearest neighbor search for each reconstructed weld point to find the nearest point in the complete weld database; calculating the spatial distance between matching point pairs; comparing the calculated distance with a preset tolerance threshold; and marking and classifying abnormal points based on the comparison results. If the distance between a reconstructed weld point and a weld point in the complete weld database exceeds the preset maximum tolerance threshold (e.g., exceeding 5 mm), it is marked as an abnormal point. This type of abnormality indicates a significant shift in the weld position after cutting. If a weld point in the complete weld database cannot find a corresponding point in the reconstruction results, meaning the nearest neighbor distance of that weld point exceeds the tolerance threshold, this type of abnormality indicates that the cutting caused the original weld point to be deleted.

[0069] Regarding weld integrity assessment, a detection mechanism for abnormal weld points is constructed. The weld point set reconstructed after cutting is spatially matched with a complete weld database. Points that cannot be matched within a set tolerance range are identified as abnormal weld points. These abnormal points directly reflect weld fractures or structural anomalies caused by the cutting operation, thus transforming the question of "whether the weld has been damaged" into a computable point-level determination problem, enabling quantitative analysis.

[0070] Please refer to the following: Figure 4 The difference index in S152 can be obtained through S1521, S1522, S1523 and S1524.

[0071] S1521, identify the abnormal type of each abnormal weld point, divide the number of abnormal weld points of each abnormal type by the total number of weld points in the weld point set, and obtain the basic abnormal ratio of abnormal weld points of each abnormal type.

[0072] S1522, obtain the weight coefficients corresponding to each of the above-mentioned abnormality types, and obtain the weighted abnormality ratio by weighted summation based on the basic abnormality ratio and weight coefficient of the abnormal weld points of each of the above-mentioned abnormality types.

[0073] S1523, calculate the error contribution factor and standard deviation penalty factor.

[0074] S1524, multiply the weighted anomaly ratio, error contribution factor and standard deviation penalty factor to obtain the difference index.

[0075] In this embodiment, the number of abnormal weld points is counted, and a difference index is calculated to quantify the degree of damage to the weld structure caused by the current cutting scheme, including: First, calculate the basic anomaly ratio by dividing the total number of all types of anomalies by the total number of weld points. This basic anomaly ratio reflects the overall proportion of anomalies.

[0076] Secondly, the weighted anomaly ratio is calculated. Considering that different types of anomalies have different degrees of impact on weld integrity, different weight coefficients need to be assigned. For example, missing anomalies cause the most severe damage to the weld and have the highest weight coefficient; location anomalies are next; and redundant anomalies have a relatively smaller impact. The weighted anomaly ratio is obtained by weighted summation.

[0077] Then, the error contribution factor for abnormal weld points is calculated. Based on the average matching error and the maximum matching error, the error contribution factor is constructed. The larger the average error, the more severe the overall deviation. The error contribution factor reflects the amplifying effect of the error degree on the degree of difference.

[0078] Calculate the standard deviation penalty factor for abnormal weld points. The standard deviation reflects the stability of the matching error; a larger standard deviation indicates more severe error fluctuations and less stable cutting results. The difference is corrected using the standard deviation penalty factor.

[0079] Based on the calculated data, the degree of difference is calculated comprehensively. The weighted anomaly ratio, error contribution factor, and standard deviation penalty factor are multiplied to obtain the final degree of difference index, with a value normalized to between 0 and 1. A degree of difference closer to 0 indicates a smaller impact of the cutting scheme on weld integrity, while a degree closer to 1 indicates more severe damage.

[0080] Based on the difference index obtained in S152, candidate cutting schemes are determined through the threshold-based scheme screening mechanism in S153. For example, a weld integrity safety threshold of 5% can be set. If the difference index is lower than this threshold, the cutting scheme is deemed to meet the weld integrity requirements; otherwise, it is rejected.

[0081] After determining the candidate cutting schemes that meet the weld integrity requirements based on S150, the target cutting scheme in S160 can be the cutting scheme that meets the constraints determined from the candidate cutting schemes. For example, iterate through each of the candidate cutting schemes to determine whether there is a cutting scheme that meets the constraints. If so, determine the optimal cutting scheme from the cutting schemes that meet the constraints as the target cutting scheme. If not, return to a failure state.

[0082] The constraints may include the symmetry score of the candidate cutting plane being higher than a first set value; and the difference index being lower than a second set value.

[0083] For example, all candidate cutting planes can be traversed, and the optimal solution that satisfies the constraints can be selected first. The constraints may include the minimum symmetry ratio: the symmetry score of the cutting plane should be as high as possible; and the weld should be kept intact and not cut off, that is, the smaller the calculated difference, the better.

[0084] If there are two or more cutting schemes that satisfy the constraints, the optimal scheme is selected as the target cutting scheme, such as the one with the highest symmetry score and the smallest difference. If none of the cutting schemes satisfy the constraints, a failure result indicating a failure in weld integrity verification is returned.

[0085] A difference index is introduced to quantitatively assess weld integrity. A unified evaluation standard is established by statistically analyzing the proportion of abnormal weld points to the total number of baseline weld points. Based on this, a safety threshold is set to enable automatic screening and optimization decisions for different symmetrical cutting schemes. When the difference exceeds the threshold, the current cutting scheme is deemed unacceptable, and new candidate cutting planes are automatically iterated. When the difference meets the requirements, the optimal cutting scheme is determined.

[0086] In summary, the embodiments of the present invention realize a closed-loop evaluation from weld reconstruction and anomaly detection to scheme optimization. It can stably and accurately determine the integrity of the weld after cutting in the case of complex symmetrical structures and incomplete surface structures, and significantly improves robustness and automation level.

[0087] Taking a welding robot as an example, in a scenario requiring automated welding of six symmetrical automotive chassis brackets, these brackets exhibit bilateral symmetry but may experience minor asymmetric deformations during actual production. To achieve symmetrical workpiece registration, the welding robot first builds a model and identifies weld seams on the first workpiece, establishing a complete weld seam database. Subsequently, it registers and positions the remaining five workpieces. Due to the symmetrical structure of the workpieces, the registration algorithm may encounter a "reverse registration" error (identifying the left side as the right side), leading to incorrect welding paths. Therefore, during the registration process, the workpieces are symmetrically cut for verification to ensure correct registration direction while guaranteeing that the cutting operation does not damage the integrity of the original weld seams.

[0088] Based on this, the scheme described in this embodiment of the invention can be set in the software. When the workpiece to be welded is a symmetrical workpiece, the scheme is triggered. First, n sets of candidate cutting planes are generated based on symmetry analysis. Then, for each candidate cutting plane, the overall point cloud of the workpiece to be registered and all its surface structures are uniformly cut, and the cut weld point set is explicitly reconstructed by finding the intersection lines of the surface structures pairwise. Next, the reconstructed weld is matched with the complete weld database in two-way nearest neighbor matching to identify three types of weld points: positional anomalies, missing anomalies, and redundant anomalies. The difference index is calculated by comprehensively considering the anomaly ratio, matching error, and stability. Finally, schemes with a difference index lower than a safety threshold (e.g., 5%) are selected, and the cutting plane with the smallest difference index is chosen as the optimal scheme to divide the workpiece into an asymmetrical half-side point cloud, thereby achieving unambiguous and accurate registration. Please refer to the relevant documentation. Figure 5 This is a schematic diagram of the overall process provided in this embodiment.

[0089] The symmetrical workpiece cutting method in this embodiment of the invention employs explicit weld reconstruction using a two-sided combination. By combining the surface structures in the point cloud pairwise, their spatial intersection lines are calculated to reconstruct the geometric position and endpoint information of the weld. This decouples the weld from the surface structure dependency relationship, forming an explicit spatial expression that can be analyzed independently, providing basic data support for subsequent integrity assessment. An abnormal weld point determination mechanism based on spatial matching is adopted. The cut weld points are spatially matched with the original weld reference data in the complete weld database. Points that cannot be matched within a set tolerance range are defined as abnormal weld points. Abnormal weld points serve as a direct criterion for whether the weld has been cut or the structure is abnormal, realizing a shift from structural-level judgment to precise point-level judgment. A difference quantification model for the proportion of abnormal weld points is adopted. By statistically analyzing the ratio of the number of abnormal weld points to the total number of reference weld points, a unified difference index is constructed, transforming the weld integrity problem into a quantifiable evaluation function. This provides a unified evaluation standard for different cutting schemes, improving the reliability of cutting.

[0090] To perform the corresponding steps in the above embodiments and various possible methods, an implementation of a symmetrical workpiece cutting device is given below. Please refer to... Figure 6 , Figure 6 This is a functional block diagram of a symmetrical workpiece cutting device 140 provided in an embodiment of the present invention. The symmetrical workpiece cutting device 140 can be applied to... Figure 1 The electronic device 100 is shown. It should be noted that the symmetrical workpiece cutting device 140 provided in this embodiment has the same basic principle and technical effects as the embodiments described above. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above embodiments. The symmetrical workpiece cutting device 140 includes an information acquisition module 141 and an information processing module 142.

[0091] The information acquisition module 141 is used to acquire registration-related data, which includes a complete workpiece point cloud, a set of surface structure point clouds, and a complete weld database.

[0092] The information processing module 142 is used to obtain at least one candidate cutting plane based on the registration-related data analysis; for each candidate cutting plane, the complete workpiece point cloud and the corresponding surface structure point cloud are uniformly cut; the surface structures after uniform cutting are combined in pairs and spatial intersection lines are calculated; by extracting the endpoints or feature points of the spatial intersection lines, a weld point set of the corresponding cutting scheme is constructed; the weld point set is spatially matched with the complete weld database to filter out candidate cutting schemes that meet the weld integrity requirements; and each candidate cutting scheme is traversed to determine the target cutting scheme.

[0093] Based on the above, embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium including a computer program, wherein the computer program, when running, controls the electronic device where the computer-readable storage medium is located to execute the above-described symmetrical workpiece cutting method.

[0094] The above-described solutions in the embodiments of the present invention have the following advantages: (1) The transformation of weld seam from implicit to explicit representation significantly improves analyzability and stability: Through the two-plane intersection reconstruction mechanism, the weld seam information that was originally attached to the surface structure is transformed into an independent spatial geometric object, so that the weld seam no longer depends on the integrity of the surface structure. Even in the case of cutting or local missing parts, the weld seam geometric information can still be stably obtained, which fundamentally improves the adaptability to complex structures and incomplete data.

[0095] (2) Achieve direct determination of weld integrity and avoid errors in traditional indirect reasoning: Based on the detection mechanism of abnormal weld points, the problem of "whether the weld has been cut off" is transformed into a point-level matching problem. Direct judgment is made by whether there is a corresponding matching point, avoiding the misjudgment problem caused by traditional reasoning based on surface structure or topological relationship, and improving the accuracy and interpretability of the judgment result.

[0096] (3) Establish a unified quantitative evaluation standard to achieve comparability of multiple schemes: By constructing a difference index, the impact of different cutting schemes on the weld is transformed into a unified numerical evaluation system, so that the candidate cutting schemes are comparable, providing a clear basis for subsequent automatic decision-making and avoiding human experience intervention.

[0097] In summary, the symmetrical workpiece cutting scheme in this embodiment effectively improves cutting reliability.

[0098] In the several embodiments provided by this invention, 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 various embodiments of the invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing 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.

[0099] In addition, the functional modules in the various embodiments of the present invention 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.

[0100] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for cutting symmetrical workpieces, characterized in that, include: Obtain registration-related data, which includes a complete workpiece point cloud, a set of surface structure point clouds, and a complete weld database; At least one candidate cutting plane is obtained based on the registration-related data analysis. For each candidate cutting plane, the complete workpiece point cloud and the corresponding surface structure point cloud are uniformly cut; The surface structures after uniform cutting are combined in pairs and spatial intersection lines are calculated. By extracting the endpoints or feature points of the spatial intersection lines, the weld point set of the corresponding cutting scheme is constructed. Spatial matching is performed between the weld point set and the complete weld database to filter out candidate cutting schemes that meet the weld integrity requirements; The target cutting scheme is determined by iterating through all the candidate cutting schemes.

2. The symmetrical workpiece cutting method according to claim 1, characterized in that, The step of spatially matching the weld point set with the complete weld database to filter out candidate cutting schemes that meet the weld integrity requirements includes: The set of weld points is spatially matched with the complete weld database. The correspondence is determined by nearest neighbor search and tolerance constraints to identify all abnormal weld points. The number of abnormal weld points was counted, and the difference index was calculated. Determine whether the difference index exceeds the weld integrity safety threshold; If not, the cutting scheme corresponding to the weld point set is determined as a candidate cutting scheme that meets the weld integrity requirements.

3. The symmetrical workpiece cutting method according to claim 2, characterized in that, The step of spatially matching the weld point set with the complete weld database, determining the correspondence through nearest neighbor search and tolerance constraints, and identifying all abnormal weld points includes: Spatial matching is performed between the weld point set and the complete weld database. Nearest neighbor search is performed on each weld point in the weld point set. The point closest to the weld point is determined in the complete weld database, and the spatial distance between the two is calculated. The spatial distance is compared with a preset tolerance threshold, and abnormal weld points are identified based on the comparison results.

4. The symmetrical workpiece cutting method according to claim 2, characterized in that, The process of counting the number of abnormal weld points and calculating the difference index includes: Identify the abnormal type of each abnormal weld point, divide the number of abnormal weld points of each abnormal type by the total number of weld points in the weld point set, and obtain the basic abnormal ratio of abnormal weld points of each abnormal type. Obtain the weight coefficients corresponding to each of the aforementioned anomaly types, and obtain the weighted anomaly ratio by weighted summation based on the basic anomaly ratio and weight coefficients of the abnormal weld points for each of the aforementioned anomaly types. Calculate the error contribution factor and the standard deviation penalty factor; Multiply the weighted outlier ratio, error contribution factor, and standard deviation penalty factor to obtain the difference index.

5. The method for cutting symmetrical workpieces according to any one of claims 2 to 4, characterized in that, The step of traversing each of the candidate cutting schemes to determine the target cutting scheme includes: Iterate through each of the candidate cutting schemes to determine whether there is a cutting scheme that satisfies the constraints. If so, the optimal cutting scheme is determined from the cutting schemes that satisfy the constraints as the target cutting scheme; If not, return a failure status.

6. The symmetrical workpiece cutting method according to claim 5, characterized in that, The constraints include that the symmetry score of the candidate cutting plane is higher than a first set value; and that the difference index is lower than a second set value.

7. The symmetrical workpiece cutting method according to claim 6, characterized in that, The step of obtaining at least one candidate cutting plane based on the registration correlation data analysis includes: A set of candidate cutting planes is generated based on symmetry analysis; or, A set of candidate cutting planes is generated based on the principal component analysis strategy.

8. A symmetrical workpiece cutting device, characterized in that, include: The information acquisition module is used to acquire registration-related data, which includes a complete workpiece point cloud, a set of surface structure point clouds, and a complete weld database. The information processing module is used to analyze the registration-related data to obtain at least one candidate cutting plane; and to perform consistent cutting on the complete workpiece point cloud and the corresponding surface structure point cloud for each candidate cutting plane. The surface structures after consistent cutting are combined in pairs and spatial intersection lines are calculated. By extracting the endpoints or feature points of the spatial intersection lines, a weld point set for the corresponding cutting scheme is constructed. The weld point set is spatially matched with the complete weld database to filter out candidate cutting schemes that meet the weld integrity requirements. Each candidate cutting scheme is traversed to determine the target cutting scheme.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the symmetrical workpiece cutting method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program that, when executed, controls the electronic device containing the computer-readable storage medium to perform the symmetrical workpiece cutting method according to any one of claims 1 to 7.

Images