Weld bead morphological feature recognition method and device, electronic equipment and storage medium

Abstract

The invention provides a weld bead morphological feature recognition method and device, electronic equipment and a storage medium. The method comprises the steps that an imaging result of a workpiece to be welded is collected through three-dimensional imaging equipment, and the imaging result comprises point cloud data and image data of the workpiece; abstracting the point cloud data and the image data to obtain target geometric elements of the workpiece, and determining a spatial position relationship among the target geometric elements based on the point cloud data; building a weld bead model of the workpiece based on the target geometric element and the spatial position relation; and identifying target weld bead morphological characteristics of the workpiece based on the weld bead model. Therefore, according to the scheme, the weld bead model is constructed, and the target weld bead morphological characteristics of the weld bead are identified according to the weld bead model, so that accurate design and optimization of the welding process can be realized, the welding efficiency can be remarkably improved, and the welding cost can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of welding, in particular to a weld shape feature recognition method and device, electronic equipment and storage medium. BACKGROUND

[0002] At present, the intelligent degree of industrial robot welding technology in different welding scenes presents significant differences. Specifically, single-layer single-pass welding has achieved a high degree of intelligence, and can complete automatic recognition and tracking of welds through sensor fusion and algorithm optimization; while multi-layer multi-pass welding still highly depends on manual dragging teaching or offline programming, the automation level is limited, which leads to the inability to automatically perform multi-layer multi-pass welding according to the shape of the weld. SUMMARY

[0003] The purpose of the present application is to at least solve one of the technical problems in the related art to some extent.

[0004] To this end, the first purpose of the present application is to propose a weld shape feature recognition method to realize accurate recognition of weld features, so that multi-layer multi-pass welding can be accurately performed.

[0005] The second purpose of the present application is to propose a weld shape feature recognition device.

[0006] The third purpose of the present application is to propose an electronic device.

[0007] The fourth purpose of the present application is to propose a computer-readable storage medium.

[0008] The fifth purpose of the present application is to propose a computer program product.

[0009] To achieve the above purpose, the first aspect of the present application proposes a weld shape feature recognition method, comprising: collecting imaging results of a workpiece to be welded by a three-dimensional imaging device, the imaging results comprising point cloud data and image data of the workpiece; abstractly processing the point cloud data and image data to obtain target geometric elements of the workpiece, and determining the spatial position relationship between the target geometric elements based on the point cloud data; based on the target geometric elements and the spatial position relationship, constructing a weld model of the workpiece; based on the weld model, identifying the target weld shape feature of the workpiece.

[0010] To achieve the above object, the second aspect of the present application provides a weld bead morphology feature recognition device, comprising: a collection module, configured to collect imaging results of a workpiece to be welded by a three-dimensional imaging device, wherein the imaging results comprise point cloud data and image data of the workpiece; a processing module, configured to perform abstract processing on the point cloud data and the image data to obtain target geometric elements of the workpiece, and determine spatial position relationships between the target geometric elements based on the point cloud data; a construction module, configured to construct a weld bead model of the workpiece based on the target geometric elements and the spatial position relationships; and an identification module, configured to identify target weld bead morphology features of the workpiece based on the weld bead model.

[0011] To achieve the above object, the third aspect of the present application provides an electronic device, comprising: a processor; and a memory connected with the processor; the memory stores computer execution instructions; and the processor executes the computer execution instructions stored in the memory, so that the processor can execute the weld bead morphology feature recognition method of the first aspect of the present application.

[0012] To achieve the above object, the fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the computer instructions are used to make the computer execute the weld bead morphology feature recognition method of the first aspect of the present application.

[0013] To achieve the above object, the fifth aspect of the present application provides a computer program product, comprising a computer program, which is executed by a processor to implement the weld bead morphology feature recognition method of the first aspect of the present application.

[0014] The weld bead morphology feature recognition method, device, electronic device and storage medium provided by the present application can effectively identify weld beads of different morphologies, so that welding can be performed according to weld beads of different morphologies, and automatic multi-layer and multi-pass welding of weld beads can be realized, thereby improving the quality and reliability of welding. By constructing a weld bead model and identifying target weld bead morphology features of the weld bead based on the weld bead model, precise design and optimization of the welding process can be realized, and welding efficiency can be significantly improved and welding cost can be reduced.

[0015] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description, taken in conjunction with the following drawings of exemplary embodiments of the present application, and where:

[0017] Figure 1 A flowchart of a weld bead morphology feature recognition method provided by an embodiment of the present application;

[0018] Figure 2 A flowchart of another weld bead morphology feature recognition method provided by an embodiment of the present application;

[0019] Figure 3 A schematic diagram of a cross-section type weld bead geometric abstract representation provided by an embodiment of the present application;

[0020] Figure 4 A flowchart of another weld bead morphology feature recognition method provided by an embodiment of the present application;

[0021] Figure 5 A flowchart of a welding process for a workpiece provided by an embodiment of the present application;

[0022] Figure 6 A structural schematic diagram of a weld bead morphology feature recognition device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0023] Embodiments of the present application are described in detail below with reference to the accompanying drawings, in which like reference numerals designate identical or similar elements or elements having identical or similar functions throughout the several views. The embodiments described below are examples in which the present application is applied, and are intended to explain the present application, and cannot be understood as limiting the present application.

[0024] A weld bead morphology feature recognition method and device of an embodiment of the present application are described below with reference to the accompanying drawings.

[0025] Figure 1 A flowchart of a weld bead morphology feature recognition method provided by an embodiment of the present application, as shown in FIG. 1, the weld bead morphology feature recognition method of the present embodiment includes, but is not limited to, the following steps: Figure 1

[0026] S101, acquiring an imaging result of a workpiece to be welded by a three-dimensional imaging device, the imaging result including point cloud data and image data of the workpiece.

[0027] ​It should be noted that the execution subject of the weld bead morphology feature recognition method provided in the embodiments of the present application is an electronic device, which can be a terminal device. Alternatively, the terminal device can be a mobile electronic device or a non-mobile electronic device. Illustratively, the mobile electronic device can be a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a personal computer (PC), a television, etc. The embodiments of the present application are not limited in this regard.

[0028] In some embodiments, a three-dimensional imaging device can project a known pattern of light, such as a stripe, a grid, or a random dot array, onto the workpiece to be welded, and then the three-dimensional imaging device can capture the light pattern after the deformation of the workpiece surface from different angles, so as to determine the point cloud data of the workpiece according to the deformation of the light pattern as the imaging result. For example, taking the stripe pattern as an example, the point cloud data of the workpiece can be determined by determining the shift of the stripe.

[0029] In some embodiments, the three-dimensional imaging device can also capture images of the workpiece to obtain grayscale images and RGB images of the workpiece as image data in the imaging result.

[0030] Alternatively, the three-dimensional imaging device can be a structured light camera, a binocular stereo vision camera, etc.

[0031] S102, abstracting the point cloud data and the image data to obtain target geometric elements of the workpiece, and determining the spatial position relationship between the target geometric elements based on the point cloud data.

[0032] In some embodiments, the point cloud data and the image data can be abstracted by a deep learning model to obtain target geometric elements related to the weld bead of the workpiece in the imaging result. Alternatively, the target geometric elements include but are not limited to weld beads, welding surfaces, cross sections, etc.

[0033] In some embodiments, the target abstract representation corresponding to the target geometric element can be determined in advance, and a plurality of abstract representations can be extracted from the point cloud data and the image data, and then the target abstract representation can be determined from the plurality of abstract representations, and the target geometric element can be determined.

[0034] In some embodiments, the distance and angle between the target geometric elements can be calculated based on the point cloud data, and the spatial positional relationship between the target geometric elements can be determined according to the distance and angle. Optionally, the spatial positional relationship between the target geometric elements can be determined according to the Euclidean distance between the target geometric elements, the vertical distance between the target geometric elements and the plane, and the included angle between the target geometric elements.

[0035] Optionally, the spatial coordinate position of the target geometric element in the point cloud coordinate system can be obtained and used as the spatial positional relationship.

[0036] It should be noted that, in order to ensure data quality, the point cloud data and the image data can be pre-processed before being abstracted based on the point cloud data and the image data. For example, the pre-processing methods can include denoising filtering, downsampling, and the like.

[0037] S103, constructing a weld model of the workpiece based on the target geometric elements and the spatial positional relationship.

[0038] In some embodiments, the weld model of the workpiece can be constructed based on a deep learning model, that is, after the target geometric elements and the spatial positional relationship are obtained based on the point cloud data and the image data by the deep learning model, the weld of the workpiece can be automatically modeled according to the target geometric elements and the spatial positional relationship, so as to obtain the weld model.

[0039] In some embodiments, the target geometric elements and the spatial positional relationship can also be input into a modeling tool, so as to obtain the weld model of the workpiece.

[0040] In some embodiments, the weld model of the workpiece can be obtained by determining the size information of the target geometric elements and modeling according to the size information and the spatial positional relationship. The size information can be the size compressed according to a set ratio.

[0041] S104, identifying a target weld form feature of the workpiece based on the weld model.

[0042] In some embodiments, a plurality of candidate weld form features and a plurality of identification conditions corresponding to the candidate weld form features can be determined in advance, and whether the weld form feature of the weld model satisfies any identification condition can be determined, and when any identification condition is satisfied, the candidate weld form feature corresponding to the identification condition can be determined as the target weld form feature.

[0043] In some embodiments, the weld form feature of the weld model can be determined by feature extraction on the weld model, and the weld form feature can be compared with the identification conditions, so as to determine the identification condition satisfied by the weld form feature.

[0044] For example, the candidate weld shape features include, but are not limited to, no-cut butt joint, no-cut corner joint, single-sided V-shaped weld, and V-shaped weld. By determining the identification conditions corresponding to each candidate weld shape feature, if the weld shape feature of the weld model satisfies the identification conditions of the V-shaped weld, the target weld shape feature is determined as the V-shaped weld.

[0045] In some embodiments, the weld shape feature of the weld model can also be matched with a plurality of candidate weld shape features, and the candidate weld shape feature matched with the weld shape feature of the weld model is determined as the target weld shape feature.

[0046] In some embodiments, after determining the target weld shape feature, the welding process parameters used during welding can also be determined according to the target weld shape feature, and welding is performed based on the welding process parameters, so that the welding process parameters can be flexibly adjusted, and the welding quality is optimized.

[0047] In the weld shape feature recognition method provided by the embodiments of the present application, the imaging result of the workpiece to be welded is obtained, and the target geometric element of the workpiece is obtained according to the point cloud data and the image data in the imaging result, so as to construct the weld model of the workpiece according to the target geometric element, thereby the target weld shape feature of the workpiece can be recognized according to the weld model. Therefore, the present scheme can effectively recognize welds of different shapes, so that welding can be performed according to welds of different shapes, and automatic multi-layer and multi-pass welding of the weld can be realized, thereby improving the quality and reliability of the welding. By constructing the weld model and recognizing the target weld shape feature of the weld according to the weld model, the precision design and optimization of the welding process can be realized, and the welding efficiency and cost can be significantly improved.

[0048] Figure 2 is a flowchart of a weld shape feature recognition method according to an embodiment of the present application, as shown in Figure 2 The weld shape feature recognition method of the present application includes, but is not limited to, the following steps:

[0049] S201, acquiring the imaging result of the workpiece to be welded by a three-dimensional imaging device, the imaging result including the point cloud data and the image data of the workpiece.

[0050] In the embodiments of the present application, the implementation of step S201 can be realized by any one of the embodiments of the present application, and here it is not limited, nor will be described again.

[0051] S202, abstracting the point cloud data to determine the first geometric abstract representation of the workpiece.

[0052] S203, abstracting the image data to determine the second geometric abstract representation of the workpiece.

[0053] S204, fusing the first geometric abstract representation and the second geometric abstract representation to obtain a target geometric abstract representation.

[0054] In some embodiments, the geometric abstract representation can include lines, surfaces, and profiles. For example, a non-keyhole weld can be abstracted as a line and a surface, and a keyhole weld can be abstracted as a line, a profile, and a surface. Figure 3 A schematic diagram of a keyhole weld geometric abstract representation.

[0055] In some embodiments, the first geometric abstract representation corresponding to the point cloud data and the second geometric abstract representation corresponding to the image data can be obtained by a deep learning model. For example, the point cloud data can be compressed to obtain a low-dimensional vector, and the low-dimensional vector can be decoded and reconstructed to obtain the first geometric abstract representation of the workpiece. For another example, the image data can be compressed to obtain a low-dimensional vector, and the low-dimensional vector can be decoded and reconstructed to obtain the second geometric abstract representation of the workpiece.

[0056] Further, in order to improve the comprehensiveness of the geometric abstract representation, the first geometric abstract representation and the second geometric abstract representation can be fused to obtain a more comprehensive target geometric abstract representation. Optionally, the fusion can be based on a set rule, or based on an optimization objective function, or through a neural network to automatically learn the fusion manner of the two representations, thereby obtaining the target geometric abstract representation.

[0057] S205, determining a target geometric element based on the target geometric abstract representation.

[0058] In some embodiments, the target geometric element corresponding to the target geometric abstract representation can be determined according to the corresponding relationship between the abstract element and the geometric element.

[0059] That is, by determining the target abstract element in the target geometric abstract representation, and obtaining the corresponding relationship between the candidate abstract element and the candidate geometric element established in advance, the target geometric element can be determined based on the target abstract element and the corresponding relationship.

[0060] Optionally, based on the query of the target abstract element in the corresponding relationship, the same candidate abstract element as the target abstract element in the corresponding relationship can be determined, and the candidate geometric element corresponding to the candidate abstract element can be determined as the target geometric element.

[0061] S206, determining the spatial position relationship between the target geometric elements based on the point cloud data.

[0062] In the embodiments of the present application, the implementation manner of step S206 can be implemented by any of the embodiments of the present application, and the present application does not make any limitation on this, and will not be repeated here.

[0063] S207, constructing a welding bead model of the workpiece based on the target geometric element and the spatial position relationship.

[0064] In some embodiments, the welding bead of the workpiece can be modeled according to the size information of the target geometric element and the spatial position relationship, to obtain the welding bead model of the workpiece. The size information of the target geometric element refers to the size information of the welding bead on the workpiece.

[0065] In some embodiments, the size information of the target geometric element is determined according to the size information of the workpiece by determining the size information of the workpiece from the point cloud data and the image data. For example, the size information of the workpiece indicates that the size of the welding bead is A, the size of the welding surface is B, and the target geometric element includes the welding bead and the welding surface. Then, it can be determined that the size information includes the welding bead with size A and the welding surface with size B.

[0066] Further, the target geometric element can be modeled based on the size information and the spatial position relationship to obtain the welding bead model, so that the welding bead model has the same size as the welding bead of the workpiece.

[0067] S208, identifying the target welding bead morphological feature of the workpiece based on the welding bead model.

[0068] In the embodiments of the present application, the implementation manner of step S208 can be implemented by any of the embodiments of the present application, and the present application does not make any limitation on this, and will not be repeated here.

[0069] In the welding bead morphological feature identification method provided by the embodiments of the present application, the target geometric element of the workpiece is obtained by abstracting the point cloud data and the image data, which can reduce the cost of welding bead morphological feature identification and improve the accuracy and efficiency of geometric element identification, thereby realizing the rapid identification of complex geometric elements.

[0070] Figure 4 is a flow chart of a welding bead morphological feature identification method according to the embodiments of the present application, as shown in Figure 4 The welding bead morphological feature identification method of the present application includes but is not limited to the following steps:

[0071] S401, acquiring imaging results of a workpiece to be welded by a three-dimensional imaging device, the imaging results including point cloud data and image data of the workpiece.

[0072] S402, abstracting the point cloud data and the image data to obtain target geometric elements of the workpiece, and determining spatial position relationships between the target geometric elements based on the point cloud data.

[0073] S403, constructing a weld bead model of the workpiece based on the target geometric elements and the spatial position relationships.

[0074] In the embodiments of the present application, the implementation manners of steps S401-S403 can be implemented by any one of the embodiments of the present application, which will not be limited herein and will not be described again.

[0075] S404, determining candidate recognition conditions of the plurality of candidate weld bead morphological features respectively.

[0076] S405, in response to the weld bead model satisfying any candidate recognition condition, determining a candidate weld bead morphological feature corresponding to the any candidate recognition condition as a target weld bead morphological feature.

[0077] In some embodiments, by determining the plurality of candidate weld bead morphological features and determining the candidate recognition conditions of the plurality of candidate weld bead morphological features respectively, it can be determined whether the weld bead model satisfies any candidate recognition condition, and if the weld bead model satisfies any candidate recognition condition, a candidate weld bead morphological feature corresponding to the any candidate recognition condition can be determined as a target weld bead morphological feature.

[0078] In some embodiments, feature extraction can be performed on the weld bead model to determine a weld bead morphological feature of the weld bead model, so as to determine whether the weld bead morphological feature of the weld bead model satisfies any candidate recognition condition.

[0079] For example, the candidate weld bead morphological features are respectively: butt joint without sectioning, corner joint without sectioning, single-sided V-shaped weld bead, and V-shaped weld bead, and the corresponding candidate recognition conditions are respectively: condition 1, condition 2, condition 3, and condition 4. If the weld bead morphological feature of the weld bead model satisfies condition 3, the target weld bead morphological feature of the weld bead can be determined as a single-sided V-shaped weld bead.

[0080] In some embodiments, after determining the target weld bead morphological feature of the workpiece, the workpiece can be welded based on the target weld bead morphological feature. Alternatively, the workpiece can be welded by determining a welding process parameter and using the welding process parameter.

[0081] It can be understood that different weld bead morphological features correspond to different welding process parameters, and the target welding process parameter can be determined from the pre-set candidate welding process parameters based on the target weld bead morphological feature, and the workpiece can be welded by using the target welding process parameter.

[0082] In some embodiments, the welding process parameters can be used to indicate the offset amount in the welding process, by determining the welding bead position and welding according to the offset amount, multi-layer multi-pass welding can be achieved. Optionally, the welding bead position can be determined based on the welding bead model, and the welding bead position offset amount can be determined based on the target welding process parameters, and welding can be performed at the welding bead position according to the offset amount.

[0083] For example, the welding bead position is at position A, and the target welding process parameters determine that the welding bead position offset amount is B, then welding can be performed at position A+B.

[0084] Optionally, the welding bead position and the offset amount can be input into the welding robot, and the welding robot can weld the welding bead based on the welding bead position and the offset amount.

[0085] In the welding bead morphology feature recognition method provided by the embodiments of the present application, by judging whether the welding bead morphology feature of the welding bead model meets any candidate recognition condition corresponding to any candidate welding bead morphology feature, the candidate welding bead morphology feature corresponding to any candidate recognition condition can be taken as the target welding bead morphology feature, the rapid recognition of the welding bead morphology feature can be achieved, and the accuracy of the welding bead feature recognition is improved. After obtaining the target welding bead morphology feature, the target welding process parameters are determined based on the target welding bead morphology feature, and welding is performed based on the target welding process parameters, so that the welding process parameters can be flexibly adjusted, the multi-layer multi-pass welding mode can be achieved, the welding quality is optimized, and the welding efficiency is improved.

[0086] Figure 5 A flowchart for welding a workpiece is shown. By obtaining the RGB image, point cloud data and grayscale image of the workpiece to be welded, and using a deep learning model based on the RGB image, point cloud data and grayscale image, the target geometric elements of the workpiece are determined, including: welding bead, welding surface and cross section, and then the welding bead model of the workpiece is constructed according to the target geometric elements. Further, the feature recognition of the welding bead model is performed, and it is judged whether the welding bead morphology feature of the welding bead model meets the candidate recognition conditions corresponding to the butt joint without cross section, the corner joint without cross section, the single-sided V-shaped welding bead and the V-shaped welding bead, and when any candidate recognition condition is met, the candidate welding bead morphology feature corresponding to any candidate recognition condition is determined as the target welding bead morphology feature, so that the target welding process parameters can be determined from the preset welding process library according to the target welding bead morphology feature, and the welding bead is welded using the target welding process parameters. Further, in the welding process, by determining the welding bead position and the offset amount of the welding bead position according to the target welding process parameters, welding can be performed at the welding bead position according to the offset amount, and multi-layer multi-pass welding can be achieved.

[0087] Corresponding to the weld bead shape feature recognition method proposed in the above several embodiments, one embodiment of the present application also proposes a weld bead shape feature recognition device. Since the weld bead shape feature recognition device proposed in the embodiment of the present application corresponds to the weld bead shape feature recognition method proposed in the above several embodiments, the implementation manners of the above weld bead shape feature recognition method are also applicable to the weld bead shape feature recognition device proposed in the embodiment of the present application, which will not be described in detail in the following embodiments.

[0088] In order to realize the above-mentioned embodiments, the present application also proposes a weld bead shape feature recognition device.

[0089] Figure 6 A structural schematic diagram of a weld bead shape feature recognition device provided by an embodiment of the present application.

[0090] As shown in Figure 6 , the weld bead shape feature recognition device 600 includes:

[0091] The acquisition module 601 is configured to acquire imaging results of a workpiece to be welded by a three-dimensional imaging device, the imaging results including point cloud data and image data of the workpiece.

[0092] The processing module 602 is configured to perform abstract processing on the point cloud data and the image data to obtain target geometric elements of the workpiece, and determine spatial position relationships between the target geometric elements based on the point cloud data.

[0093] The construction module 603 is configured to construct a weld bead model of the workpiece based on the target geometric elements and the spatial position relationships.

[0094] The recognition module 604 is configured to recognize target weld bead shape features of the workpiece based on the weld bead model.

[0095] In a possible implementation manner of the embodiment of the present application, the processing module 602 is further configured to: perform abstract processing on the point cloud data to determine a first geometric abstract representation of the workpiece; perform abstract processing on the image data to determine a second geometric abstract representation of the workpiece; fuse the first geometric abstract representation and the second geometric abstract representation to obtain a target geometric abstract representation; and determine the target geometric elements based on the target geometric abstract representation.

[0096] In a possible implementation manner of the embodiment of the present application, the processing module 602 is further configured to: determine a target abstract element in the target geometric abstract representation; obtain a pre-established corresponding relationship between a candidate abstract element and a candidate geometric element; and determine the target geometric elements based on the target abstract element and the corresponding relationship.

[0097] In a possible implementation of the embodiment of the present application, the construction module 603 is further configured to: determine size information of the target geometric element; and model the target geometric element based on the size information and the spatial position relationship, to obtain the weld bead model.

[0098] In a possible implementation of the embodiment of the present application, the identification module 604 is further configured to: determine a plurality of candidate identification conditions of the candidate weld bead morphology features respectively; and in response to the weld bead model satisfying any candidate identification condition, determine the candidate weld bead morphology feature corresponding to the any candidate identification condition as the target weld bead morphology feature.

[0099] In a possible implementation of the embodiment of the present application, the identification module 604 is further configured to: determine the target welding process parameter from the pre-set candidate welding process parameters based on the target weld bead morphology feature, and perform welding on the workpiece through the target welding process parameter.

[0100] In a possible implementation of the embodiment of the present application, the identification module 604 is further configured to: determine the weld bead position based on the weld bead model; determine a weld bead position offset based on the target welding process parameter, and perform welding at the weld bead position according to the offset.

[0101] In the weld bead morphology feature identification device provided by the embodiment of the present application, the imaging result of the workpiece to be welded is obtained, and the target geometric element of the workpiece is obtained based on the point cloud data and the image data in the imaging result, so as to construct the weld bead model of the workpiece according to the target geometric element, thereby the target weld bead morphology feature of the workpiece can be identified according to the weld bead model. Therefore, the weld bead of different morphologies can be effectively identified, so that welding can be performed according to the weld bead of different morphologies, and automatic multi-layer and multi-pass welding can be realized, thereby the quality and reliability of the welding are improved. The weld bead model is constructed, and the target weld bead morphology feature of the weld bead is identified according to the weld bead model, thereby the precise design and optimization of the welding process can be realized, and the welding efficiency can be improved and the welding cost can be reduced.

[0102] It should be noted that the foregoing explanation and description of the weld bead morphology feature identification method embodiment are also applicable to the weld bead morphology feature identification device of the embodiment, which will not be described here.

[0103] In order to implement the above-mentioned embodiments, the present application further provides an electronic device, comprising: a processor and a memory connected with the processor in communication; the memory stores computer execution instructions; and the processor executes the computer execution instructions stored in the memory to implement the method provided by the foregoing embodiments.

[0104] To achieve the above-mentioned embodiments, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the method provided by the foregoing embodiments.

[0105] To achieve the above-mentioned embodiments, the present application further provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the method provided by the foregoing embodiments.

[0106] In the foregoing embodiment description, the description of the terms “one embodiment”, “some embodiments”, “an example”, “a specific example”, or “some examples” means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0107] In addition, the terms “first”, “second” are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with “first”, “second” can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of “plurality” is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0108] Any process or method descriptions in flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing the specified logical functions or processes, and the preferred embodiments of the present application also include additional implementation involving other processes or methods. It should be understood that the order of the steps in the process or method described in the flow charts or otherwise described herein is not mandatory and that the steps can be performed in any order unless otherwise specifically noted.

[0109] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of executable instructions stored in a computer readable medium, which can be executed by an instruction execution system, apparatus or device, such as a computer-based system, processor- based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or a combination thereof. For the purposes of this specification, a "computer readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer readable medium can specifically include the following, which are non-exhaustive list: electrical connection (electrical device having one or more wires), portable computer diskette (magnetic device), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fiber device, and portable compact disc read-only memory (CDROM). In addition, the computer readable medium can even be paper or other suitable medium upon which the program is printed, as the program can be electronically captured, for example, by optically scanning the paper or other suitable medium, then electronically converted into a form that can be edited, compiled, or interpreted, or otherwise processed in electronic form into an executable form suitable for use in the instruction execution system, apparatus or device.

[0110] It should be understood that portions of the application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or a combination thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0111] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0112] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0113] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for identifying weld bead morphology features, characterized in that, The method includes: The imaging results of the workpiece to be welded are acquired by a three-dimensional imaging device, and the imaging results include point cloud data and image data of the workpiece. The point cloud data and image data are abstracted to obtain the target geometric elements of the workpiece, and the spatial positional relationship between the target geometric elements is determined based on the point cloud data. Based on the target geometric elements and the spatial positional relationship, a weld bead model of the workpiece is constructed; Based on the weld bead model, the target weld bead morphology features of the workpiece are identified.

2. The method according to claim 1, characterized in that, The abstraction process of the point cloud data and image data to obtain the target geometric elements of the workpiece includes: The point cloud data is abstracted to determine the first geometric abstract representation of the workpiece; The image data is abstracted to determine a second geometric abstract representation of the workpiece; The first geometric abstract representation and the second geometric abstract representation are fused to obtain the target geometric abstract representation; Based on the target geometric abstract representation, the target geometric elements are determined.

3. The method according to claim 2, characterized in that, The process of determining the target geometric elements based on the target geometric abstract representation includes: Determine the target abstract elements in the target geometric abstract representation; Obtain the pre-established correspondence between candidate abstract elements and candidate geometric elements; The target geometric element is determined based on the target abstract element and the corresponding relationship.

4. The method according to any one of claims 1-3, characterized in that, The step of constructing the weld bead model of the workpiece based on the target geometric elements and the spatial positional relationship includes: Determine the dimensional information of the target geometric element; Based on the size information and the spatial positional relationship, the target geometric elements are modeled to obtain the weld bead model.

5. The method according to any one of claims 1-3, characterized in that, The step of identifying the target weld bead morphology features of the workpiece based on the weld bead model includes: Determine the candidate identification conditions for each of the multiple candidate weld bead morphological features; In response to the weld bead model satisfying any candidate identification condition, the candidate weld bead morphology feature corresponding to any candidate identification condition is determined as the target weld bead morphology feature.

6. The method according to claim 1, characterized in that, After identifying the target weld bead morphology features of the workpiece, the method further includes: Based on the target weld bead morphology characteristics, target welding process parameters are determined from pre-set candidate welding process parameters, and the workpiece is welded using the target welding process parameters.

7. The method according to claim 6, characterized in that, The welding of the workpiece using the target welding process parameters includes: The weld bead position is determined based on the weld bead model; The offset of the weld bead position is determined based on the target welding process parameters, and welding is performed at the weld bead position according to the offset.

8. A weld bead morphology identification device, characterized in that, The device includes: The acquisition module is used to acquire the imaging results of the workpiece to be welded through a three-dimensional imaging device. The imaging results include point cloud data and image data of the workpiece. The processing module is used to abstract the point cloud data and image data to obtain the target geometric elements of the workpiece, and to determine the spatial positional relationship between the target geometric elements based on the point cloud data. A construction module is used to construct a weld bead model of the workpiece based on the target geometric elements and the spatial positional relationship; The identification module is used to identify the target weld morphology features of the workpiece based on the weld model.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-7.

Images