Weld type identification method, device, equipment and storage medium

Abstract

This application relates to the technical field of weld identification and discloses a weld type identification method, apparatus, device, and storage medium. The method comprises: obtaining a mesh model to be identified; classifying the weld to be identified based on target weld features to obtain a first classification label; determining the type of the weld to be identified based on the first classification label; if the type of the weld to be identified cannot be determined based on the first classification label, inputting the target model features and the target weld features into a pre-trained weld type identification model, classifying the weld to be identified based on the target model features and the target weld features to obtain a second classification label; and determining the type of the weld to be identified based on the second classification label. Embodiments of the present application can improve the efficiency and accuracy of weld type identification.

Description

Technical Field

[0001] The present application relates to the technical field of weld identification, and in particular to a weld type identification method, device, equipment and storage medium. Background Art

[0002] Welds are high-incidence areas of stress concentration and fatigue failure in engineering structures. The assessment of their fatigue life is directly related to the safety and economy of the equipment. Whether fatigue analysis of weld structures can be performed quickly and efficiently is of great significance.

[0003] In real-world engineering scenarios, such as those in the automotive and engineering machinery sectors, complex structural components often contain a mix of T-welds and lap welds. Existing technologies require manual classification of weld types and component-by-component setting of material and fatigue parameters during modeling. However, this component-by-component definition of weld types and the stringent requirements for weld unit modeling make weld fatigue analysis a tedious and complex process. Manual classification and repetitive parameter setting are time-consuming, failing to meet the demands of rapid design iteration, impacting the efficiency and accuracy of weld structure fatigue life assessment and engineering decision-making. Summary of the Invention

[0004] The purpose of this application is to provide a weld type identification method, device, equipment and storage medium, aiming to improve the efficiency and accuracy of weld type identification.

[0005] The present invention provides a method for identifying weld types, including:

[0006] Acquire a mesh model to be identified; the mesh model to be identified includes a weld to be identified;

[0007] Classifying the weld to be identified according to target weld features to obtain a first classification label; the target weld features include a welding surface angle feature and a welding surface connection feature between welding surfaces of two plates where the weld to be identified is located;

[0008] determining the type of the weld to be identified based on the first classification label;

[0009] When the type of the weld to be identified cannot be determined based on the first classification label, inputting the target model features and the target weld features into a pre-trained weld type identification model, classifying the weld to be identified based on the target model features and the target weld features to obtain a second classification label; the target model features include model topology features and model application features of the mesh model to be identified;

[0010] The type of the weld to be identified is determined based on the second classification label.

[0011] In one embodiment, before classifying the weld to be identified according to the target weld features, the method further includes:

[0012] Acquiring coordinate information of both the welding surface and the plate;

[0013] Calculating a normal vector of the welding surface according to the coordinate information of the welding surface, and determining an angle feature of the welding surface according to the normal vector of the welding surface;

[0014] The connection topology of the welding surface is determined according to the coordinate information of the plate, and the connection characteristics of the welding surface are determined according to the connection topology.

[0015] In one embodiment, classifying the weld to be identified according to target weld features includes:

[0016] The target weld feature is input into a static classifier, and the weld to be identified is classified according to the angle range corresponding to the welding surface angle feature and the connection type of the connection topology of the welding surface corresponding to the welding surface connection feature to obtain the first classification label.

[0017] In one embodiment, classifying the weld to be identified based on the target model features and the target weld features includes:

[0018] Splicing the target model features and the target weld features to obtain splicing features; the model topology features in the target model features include the structural assembly features, weld surface topology features, weld surface material features, and weld surface metallographic features of the mesh model to be identified;

[0019] Mapping the splicing features to a feature space to obtain mapping features;

[0020] Classifying the mapping features to obtain several initial prediction labels and corresponding confidence levels;

[0021] The initial predicted label corresponding to the confidence with the largest value is determined as the second classification label.

[0022] In one embodiment, classifying the mapping features includes:

[0023] Determining a weight value according to a degree of matching between the target model feature and the target weld feature;

[0024] Classifying the mapping features using a classification tree of the weld type recognition model to generate the initial prediction label;

[0025] The confidence level corresponding to the initial predicted label is determined according to the weight value.

[0026] In one embodiment, the weld type identification method further includes:

[0027] Upon receiving a weld type recognition operation, inputting the target model features and the target weld features into the weld type recognition model, classifying the weld to be recognized based on the target model features and the target weld features, and obtaining a second classification label;

[0028] The type of the weld to be identified is determined according to the first classification label or the second classification label.

[0029] In one embodiment, the weld type identification method further includes:

[0030] A model topology performance evaluation is performed on the mesh model to be identified according to the target weld characteristics and the target model characteristics, and corresponding prompt information is generated according to the model topology performance evaluation result.

[0031] The present application also provides a device for identifying weld types, including:

[0032] The first module is used to obtain a grid model to be identified; the grid model to be identified includes a weld to be identified;

[0033] The second module is configured to classify the weld to be identified based on target weld features to obtain a first classification label; the target weld features include a welding surface angle feature and a welding surface connection feature between the welding surfaces of the two plates where the weld to be identified is located;

[0034] A third module is used to determine the type of the weld to be identified based on the first classification label;

[0035] a fourth module configured to input target model features and the target weld features into a pre-trained weld type recognition model when the type of the weld to be identified cannot be determined based on the first classification label, and classify the weld to be identified based on the target model features and the target weld features to obtain a second classification label; the target model features include model topology features and model application features of the mesh model to be identified;

[0036] The fifth module is used to determine the type of the weld to be identified based on the second classification label.

[0037] An embodiment of the present application further provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned weld type identification method when executing the computer program.

[0038] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned weld type identification method is implemented.

[0039] The beneficial effects of the present application are as follows: there is no need to manually classify the welds to be identified. Instead, the welds to be identified are classified according to the target weld features of the welds to be identified and a first classification label is obtained, so that the type of the weld to be identified is determined according to the first classification label. When the type of the weld to be identified cannot be determined according to the first classification label, the target model features of the grid model to be identified and the target weld features of the weld to be identified are input into a pre-trained weld type recognition model, and the welds to be identified are classified according to the target model features and the target weld features and a second classification label is obtained, so that the type of the weld to be identified is determined according to the second classification label. By adaptively and automatically identifying the type of the weld to be identified, the efficiency and accuracy of weld type recognition can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of the weld type identification method provided in an embodiment of the present application.

[0041] Figure 2 This is a flowchart of the method before step S102 provided in an embodiment of the present application.

[0042] Figure 3 It is a flowchart of the specific method of step S104 provided in an embodiment of the present application.

[0043] Figure 4 It is a flowchart of the specific method of step S303 provided in an embodiment of the present application.

[0044] Figure 5 It is a structural schematic diagram of the weld type identification device provided in an embodiment of the present application.

[0045] Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0047] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps illustrated may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. Terms such as "first" and "second" in the specification, claims, and drawings are used to distinguish similar items and are not intended to describe a specific sequence or precedence.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0049] Figure 1 This is a flow chart of a weld type identification method provided by an embodiment of the present application. Figure 1 In one embodiment, the method includes but is not limited to steps S101 to S105.

[0050] Step S101: Obtain a grid model to be identified.

[0051] The mesh model to be identified includes welds to be identified.

[0052] The grid model to be identified is stored in a grid model file. A grid model file is the best model file saved after grid search hyperparameter tuning, or a file containing multiple hyperparameter combinations and their corresponding model performance. Grid search is a hyperparameter optimization method that iterates through all predefined hyperparameter combinations (the "grid"), trains multiple models, evaluates their performance, and ultimately selects the optimal hyperparameter combination. The grid model to be identified is a grid model generated for an industrial product, containing several groups of welds to be identified, such as an automotive chassis or aerospace component.

[0053] Specifically, obtaining the mesh model to be identified can be to read the mesh model file generated from the CAE software, and then parse the coordinate information, type information, connection relationship information and attribute information of each plate, welding surface and node in the mesh model to be identified, and store the parsed information as multiple information sets.

[0054] Step S102: classify the weld to be identified according to the target weld characteristics to obtain a first classification label.

[0055] The target weld features include the weld surface angle features and weld surface connection features between the weld surfaces of the two plates where the weld to be identified is located. The target weld features can be obtained by extracting information related to the weld to be identified from an information set obtained by parsing various types of information in the mesh model to be identified, including the weld surface angle features and weld surface connection features between the weld surfaces of the two plates where the weld to be identified is located. Among them, the weld surface angle features refer to the angle features between the weld surfaces of the two plates where the weld to be identified is located, and the weld surface connection features refer to the connection features of the connection relationship between the weld surfaces of the two plates where the weld to be identified is located.

[0056] Specifically, classifying the weld to be identified based on the target weld feature can involve comparing the target weld feature with various weld features in a preset weld feature rule library to determine the feature space in which the target weld feature resides, thereby determining the type of the weld to be identified and assigning a corresponding classification label based on the comparison result. The weld feature rule library can be configured as a static classifier, which inputs the target weld feature into the static classifier, and outputs a first classification label representing the type of the weld to be identified.

[0057] Figure 2 This is a flowchart of the method before step S102 provided in the embodiment of the present application. Figure 2 In one embodiment, the method includes but is not limited to steps S201 to S203.

[0058] Step S201: Acquire coordinate information of both the welding surface and the plate.

[0059] Specifically, obtaining the coordinate information of both the welding surface and the plate may be performed by extracting the coordinate information of both the welding surface and the plate from an information set obtained by parsing various types of information in the grid model to be identified.

[0060] In step S202 , a normal vector of the welding surface is calculated based on the coordinate information of the welding surface, and an angle feature of the welding surface is determined based on the normal vector of the welding surface.

[0061] Specifically, the weld surface angle feature can be determined by establishing a mapping relationship between each weld surface and other weld surfaces based on the connection relationship between the weld surfaces, and then calculating the normal vector of the weld surface based on the coordinate information of the weld surface. The weld surface angle feature is determined based on the mapping relationship between the weld surface and other weld surfaces and the normal vector of the weld surface. In a specific embodiment, the calculation formulas for the normal vector of the weld surface and the weld surface angle feature are respectively:

[0062] ,

[0063] ,

[0064] ,

[0065] in, is the welding surface angle feature, and is the normal vector of the welding surface, 、 、 and is the element edge vector of the weld surface.

[0066] Step S203 : determining a connection topology of the welding surface according to the coordinate information of the plate, and determining a connection feature of the welding surface according to the connection topology.

[0067] Specifically, to determine the connection characteristics of the welding surface, the mapping relationship between each plate and other plates can be established through the connection relationship between the plates, and then the connection topology of the welding surface can be determined based on the coordinate information of the plates and the mapping relationship between the plates and other plates, and the angle characteristics of the welding surface can be determined based on the mapping relationship between the plates and other plates and the connection topology of the welding surface.

[0068] In one embodiment, the welds to be identified are classified according to the target weld features, including: inputting the target weld features into a static classifier, classifying the welds to be identified according to the angle range corresponding to the welding surface angle features and the connection type of the connection topology of the welding surface corresponding to the welding surface connection features, and obtaining a first classification label.

[0069] Specifically, a weld feature rule library is configured to classify the weld to be identified, the angle interval corresponding to the welding surface angle feature is matched with the corresponding angle interval in the weld feature rule library, and the connection type of the connection topology of the welding surface corresponding to the welding surface connection feature is matched with the corresponding connection type in the weld feature rule library. The two matching results are combined to classify the weld to be identified, thereby obtaining a corresponding first classification label. For example, when the angle corresponding to the welding surface angle feature is in the range of 45° to 90°, if the connection type of the connection topology of the welding surface corresponding to the welding surface connection feature is a spatial orthogonal distribution (i.e., the angle is close to 90° and the center planes of the two plates intersect), then the weld is determined to be a T-shaped weld, and a first classification label is obtained that indicates that the weld to be identified is a T-shaped weld. When the angle corresponding to the welding surface angle feature is in the range less than 45°, if the connection type of the connection topology of the welding surface corresponding to the welding surface connection feature is a plate overlap (by calculating that the ratio of the overlapping area of ​​the two plate projections to the area of ​​the smaller plate is greater than a preset threshold, usually 30%), then the weld is determined to be a T-shaped weld. For a lap weld, a first classification label is obtained, characterizing that the weld to be identified is a lap weld. When the angle corresponding to the welding surface angle feature is close to 180°, if the connection type of the connection topology of the welding surface corresponding to the welding surface connection feature is that the center lines of the two plates are basically coplanar, then the weld is determined to be a butt weld, and the first classification label is obtained, characterizing that the weld to be identified is a butt weld. When the angle corresponding to the welding surface angle feature is in the range of 60° to 120°, if the connection type of the connection topology of the welding surface corresponding to the welding surface connection feature is that the two plates have a common edge, then the weld is determined to be a fillet weld, and the first classification label is obtained, characterizing that the weld to be identified is a fillet weld.

[0070] Step S103: determining the type of the weld to be identified based on the first classification label.

[0071] Specifically, the first classification tag is parsed, and the type information of the weld to be identified in the first classification tag is extracted to obtain the type of the weld to be identified. If the static classifier does not match the angle interval corresponding to the weld surface angle feature and / or the connection type of the weld surface connection topology corresponding to the weld surface connection feature in the weld feature rule base, the obtained first classification tag does not contain the type information of the weld to be identified, and the type of the weld to be identified cannot be determined based on the first classification tag.

[0072] Step S104: When the type of the weld to be identified cannot be determined based on the first classification label, the target model features and the target weld features are input into a pre-trained weld type recognition model, and the weld to be identified is classified based on the target model features and the target weld features to obtain a second classification label.

[0073] Target model features include the model topology features and model application features of the mesh model to be identified. Target model features can be obtained by extracting information related to the topology of the mesh model to be identified from the information set obtained by parsing various types of information in the mesh model to be identified. These features include model topology features and model application features. Model topology features refer to the topology of the mesh model to be identified, while model application features refer to the application scenarios of the mesh model to be identified.

[0074] Specifically, the welds to be identified are classified based on the target model features and the target weld features. This can be done by using a pre-trained weld type recognition model to perform feature classification on the target model features and the target weld features in multiple dimensions based on the learned engineering cases, so as to determine the type of weld to be identified that carries the target weld features under the corresponding target model feature conditions, thereby obtaining a corresponding second classification label. In an embodiment of the present application, the weld type recognition model uses a random forest algorithm to classify the welds to be identified. The weld type recognition model is trained based on a training feature set consisting of sample model features and sample weld features, and a control feature set consisting of control model features and control weld features corresponding to the engineering cases.

[0075] Figure 3 This is a flowchart of the specific method of step S104 provided in the embodiment of the present application. Figure 3 In one embodiment, the method includes but is not limited to steps S301 to S304.

[0076] Step S301: splicing target model features and target weld features to obtain splicing features.

[0077] In this embodiment, the model topology features in the target model features include structural assembly features, weld surface topology features, weld surface material features, and weld surface metallographic features of the mesh model to be identified.

[0078] Step S302: Map the concatenated features to the feature space to obtain mapped features.

[0079] The splicing features are used as input data of the feature mapping layer of the weld type recognition model. During the processing of the feature mapping layer, the splicing features are first mapped to the feature space to obtain mapping features. The mapping features are usually in vector form to facilitate subsequent processing.

[0080] Step S303: classify the mapped features to obtain several initial prediction labels and corresponding confidence levels.

[0081] Here, the mapping features can be optimized to incorporate more effective information as mapping features. This optimization process, such as convolution or integration, is determined by the type of weld type recognition model. The optimized mapping features are then classified to obtain at least one initial predicted label and a confidence level associated with each initial predicted label. The confidence level indicates the degree of trustworthiness of the initial predicted label.

[0082] Step S304: Determine the initial prediction label corresponding to the confidence with the largest value as the second classification label.

[0083] The initial predicted label with the highest confidence value is determined as the predicted label of the image classification model. For example, after classifying the mapped features, an initial predicted label of 0 is obtained, corresponding to a confidence value of 0.3, and another initial predicted label of 1 is obtained, corresponding to a confidence value of 0.7. Therefore, the initial predicted label with a value of 1 is determined as the second classification label.

[0084] Figure 4 This is a flowchart of the specific method of step S303 provided in the embodiment of the present application. Figure 4 In one embodiment, the method includes but is not limited to steps S401 to S403.

[0085] Step S401: determining a weight value based on the matching degree between the target model features and the target weld features.

[0086] When determining the degree of match between the target model feature and the target weld feature, the distance between the target model feature, the target weld feature, and the cluster center point can be calculated. Based on the corresponding relationship between the distance and the degree of match, the degree of match between the target model feature and the target weld feature can be determined. The higher the degree of match, the greater the weight value, and the lower the degree of match, the smaller the weight value.

[0087] Step S402 : Classify the mapping features using the classification tree of the weld type recognition model to generate initial prediction labels.

[0088] The mapping features are classified using the classification tree of the weld type recognition model. The mapping features can be clustered first to obtain the cluster to which the mapping features belong. After determining the cluster to which the mapping features belong, the classification tree corresponding to the cluster to which the mapping features belong can be selected based on the correspondence between the cluster and the classification tree for classification calculation, and the classification to which the mapping features belong can be obtained through the classification tree calculation. Since the classification tree in the random forest in this application is constructed based on the sample subset after clustering, when the welds to be identified are classified, the correspondence between the cluster and the classification tree can be determined based on the cluster of the sample subset when the classification tree is constructed. By performing classification calculation based on the classification tree corresponding to the cluster to which the mapping features belong, the efficiency of the classification calculation can be effectively improved, and since the mapping features are similar to the sample subset of the constructed classification tree, the accuracy of the classification can be effectively guaranteed.

[0089] Step S403: Determine the confidence level corresponding to the initial predicted label based on the weight value.

[0090] The confidence corresponding to the initial prediction label is determined based on the weight value. After obtaining multiple initial prediction labels based on the classification tree of the weld type recognition model, the weight values ​​with the same initial prediction label are fused, for example, the weight values ​​can be summed up to obtain the confidence of the initial prediction label.

[0091] Step S105: determining the type of the weld to be identified based on the second classification label.

[0092] Specifically, the second classification label is parsed, and the type information of the weld to be identified in the second classification label is extracted to obtain the type of the weld to be identified.

[0093] In one embodiment, the weld type identification method further includes: when receiving a weld type identification operation, inputting the target model features and the target weld features into the weld type identification model, classifying the weld to be identified based on the target model features and the target weld features to obtain a second classification label; and determining the type of the weld to be identified based on the first classification label or the second classification label.

[0094] Specifically, after determining the type of weld to be identified based on the first classification label, the user can perform a weld type identification operation to obtain a second classification label. Upon receiving the weld type identification operation, the executing entity inputs the target model features and the target weld features into the weld type identification model, classifies the weld to be identified based on the target model features and the target weld features, and obtains a second classification label. After obtaining the second classification label, the type of the weld to be identified can be determined based on the first classification label or the second classification label.

[0095] In one embodiment, the weld type identification method further includes: performing a model topology performance evaluation on the mesh model to be identified based on the target weld characteristics and the target model characteristics, and generating corresponding prompt information based on the model topology performance evaluation result.

[0096] Specifically, after traversing all weld surfaces and their surrounding adjacent weld surfaces, the mesh quality of these weld surfaces is evaluated, and the weld surfaces with mesh quality lower than the critical requirement are marked and temporarily stored. Next, the target weld features and target model features that have been obtained are used to determine whether each weld surface meets the weld modeling requirements. If not, these weld surfaces are also recorded, and these weld surfaces that may have problems are summarized to generate corresponding prompt information. The generated prompt information includes the specific problems existing on these weld surfaces and the corresponding optimization methods.

[0097] See also Figure 5 The present application also provides a device for identifying weld types, which can implement the above-mentioned weld type identification method. The device includes:

[0098] The first module 501 is used to obtain a mesh model to be identified; the mesh model to be identified includes a weld to be identified;

[0099] The second module 502 is configured to classify the weld to be identified based on target weld features to obtain a first classification label; the target weld features include a weld surface angle feature and a weld surface connection feature between the weld surfaces of the two plates where the weld to be identified is located;

[0100] The third module 503 is used to determine the type of the weld to be identified based on the first classification label;

[0101] The fourth module 504 is configured to input the target model features and the target weld features into a pre-trained weld type recognition model when the type of the weld to be identified cannot be determined based on the first classification label, and classify the weld to be identified based on the target model features and the target weld features to obtain a second classification label; the target model features include the model topology features and the model application features of the mesh model to be identified;

[0102] The fifth module 505 is used to determine the type of the weld to be identified based on the second classification label.

[0103] The specific implementation of the weld type identification device is basically the same as the specific embodiment of the weld type identification method described above, and will not be repeated here.

[0104] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment.

[0105] Refer to the following Figure 6hereinafter, an electronic device 600 according to this embodiment of the present disclosure will be described. Figure 6 The electronic device 600 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0106] like Figure 6 As shown, electronic device 600 is implemented as a general-purpose computing device. Components of electronic device 600 may include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting various system components (including storage unit 620 and processing unit 610), a display unit 640, and the like.

[0107] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps described in the weld type identification method section above according to various exemplary embodiments of the present disclosure.

[0108] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0109] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0110] Bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0111] The electronic device 600 can also communicate with one or more external devices 600' (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 600, and / or any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 650. Furthermore, the electronic device 600 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 via the bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device 600, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0112] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned weld type identification method is implemented.

[0113] The weld type identification method, apparatus, device and storage medium provided in the embodiments of the present application do not require manual classification of the welds to be identified. Instead, the welds to be identified are classified according to the target weld features of the welds to be identified and a first classification label is obtained to determine the type of the weld to be identified according to the first classification label. When the type of the weld to be identified cannot be determined according to the first classification label, the target model features of the grid model to be identified and the target weld features of the weld to be identified are input into a pre-trained weld type identification model, and the welds to be identified are classified according to the target model features and the target weld features to obtain a second classification label to determine the type of the weld to be identified according to the second classification label. By adaptively and automatically identifying the type of the weld to be identified, the efficiency and accuracy of weld type identification can be improved.

[0114] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above-mentioned method according to the embodiments of the present disclosure.

[0115] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0116] Computer-readable storage media may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0117] Those skilled in the art will appreciate that the modules described above can be distributed in the device according to the description of the embodiment, or can be modified accordingly to be used in one or more devices that are different from the embodiment. The modules of the above embodiment can be combined into one module or further divided into multiple submodules.

[0118] While the exemplary embodiments of the present disclosure have been specifically illustrated and described above, it should be understood that the present disclosure is not limited to the detailed structures, configurations, or implementations described herein; rather, the present disclosure is intended to encompass various modifications and equivalent configurations within the spirit and scope of the appended claims.

Claims

1. A method for identifying weld types, characterized in that: include: Obtain the grid model to be identified; The mesh model to be identified includes a weld to be identified; Classifying the weld to be identified according to the target weld characteristics to obtain a first classification label; The target weld features include a weld surface angle feature and a weld surface connection feature between the weld surfaces of the two plates where the weld to be identified is located; determining the type of the weld to be identified based on the first classification label; When the type of the weld to be identified cannot be determined based on the first classification label, inputting the target model features and the target weld features into a pre-trained weld type identification model, classifying the weld to be identified based on the target model features and the target weld features to obtain a second classification label; the target model features include model topology features and model application features of the mesh model to be identified; determining the type of the weld to be identified according to the second classification label; The classifying the weld to be identified according to the target model features and the target weld features includes: Splicing the target model features and the target weld features to obtain splicing features; the model topology features in the target model features include the structural assembly features, weld surface topology features, weld surface material features, and weld surface metallographic features of the mesh model to be identified; Mapping the splicing features to a feature space to obtain mapping features; Classifying the mapping features to obtain several initial prediction labels and corresponding confidence levels; The initial predicted label corresponding to the confidence with the largest value is determined as the second classification label.

2. The weld type identification method according to claim 1, characterized in that: Before classifying the weld to be identified according to the target weld characteristics, the method further includes: Acquiring coordinate information of both the welding surface and the plate; Calculating a normal vector of the welding surface according to the coordinate information of the welding surface, and determining an angle feature of the welding surface according to the normal vector of the welding surface; The connection topology of the welding surface is determined according to the coordinate information of the plate, and the connection characteristics of the welding surface are determined according to the connection topology.

3. The weld type identification method according to claim 1, characterized in that: The classifying the weld to be identified according to the target weld characteristics includes: The target weld feature is input into a static classifier, and the weld to be identified is classified according to the angle range corresponding to the welding surface angle feature and the connection type of the connection topology of the welding surface corresponding to the welding surface connection feature to obtain the first classification label.

4. The weld type identification method according to claim 1, characterized in that: The classifying the mapping features includes: Determining a weight value according to a degree of matching between the target model feature and the target weld feature; Classifying the mapping features using a classification tree of the weld type recognition model to generate the initial prediction label; The confidence level corresponding to the initial predicted label is determined according to the weight value.

5. The weld type identification method according to claim 1, characterized in that: Also includes: Upon receiving a weld type recognition operation, inputting the target model features and the target weld features into the weld type recognition model, classifying the weld to be recognized based on the target model features and the target weld features, and obtaining a second classification label; The type of the weld to be identified is determined according to the first classification label or the second classification label.

6. The weld type identification method according to claim 1, characterized in that: Also includes: A model topology performance evaluation is performed on the mesh model to be identified according to the target weld characteristics and the target model characteristics, and corresponding prompt information is generated according to the model topology performance evaluation result.

7. A weld type identification device, characterized in that: include: The first module is used to obtain the grid model to be identified; The mesh model to be identified includes a weld to be identified; The second module is configured to classify the weld to be identified based on target weld features to obtain a first classification label; the target weld features include a welding surface angle feature and a welding surface connection feature between the welding surfaces of the two plates where the weld to be identified is located; A third module is used to determine the type of the weld to be identified based on the first classification label; a fourth module configured to input target model features and the target weld features into a pre-trained weld type recognition model when the type of the weld to be identified cannot be determined based on the first classification label, and classify the weld to be identified based on the target model features and the target weld features to obtain a second classification label; the target model features include model topology features and model application features of the mesh model to be identified; A fifth module is configured to determine the type of the weld to be identified based on the second classification label; The classifying the weld to be identified according to the target model features and the target weld features includes: Splicing the target model features and the target weld features to obtain splicing features; the model topology features in the target model features include the structural assembly features, weld surface topology features, weld surface material features, and weld surface metallographic features of the mesh model to be identified; Mapping the splicing features to a feature space to obtain mapping features; Classifying the mapping features to obtain several initial prediction labels and corresponding confidence levels; The initial predicted label corresponding to the confidence with the largest value is determined as the second classification label.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the weld type identification method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the weld type identification method according to any one of claims 1 to 6 is implemented.

Images