Control method and device of welding robot, electronic equipment and storage medium

Abstract

This application proposes a control method, device, electronic device, and storage medium for a welding robot. The method includes: acquiring multimodal welding commands; determining first welding parameters for the target workpiece corresponding to the multimodal welding commands; determining a three-dimensional model of the weld bead on the target workpiece and the target weld bead morphology features; determining second welding parameters executable by the welding robot based on the first welding parameters and the target weld bead morphology features; generating a welding trajectory based on the three-dimensional model; and welding the target workpiece based on the second welding parameters and the welding trajectory. Therefore, this solution allows welding based on multimodal commands, lowering the operational threshold of the welding robot, enabling it to complete complex welding tasks, and improving the intelligence level of the welding robot. Determining the second welding parameters executable by the robot through the target weld bead morphology features and using these second welding parameters for welding improves welding efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of welding and artificial intelligence, and particularly relates to a welding robot control method and device, an electronic device and a storage medium. BACKGROUND

[0002] In high-risk operations such as welding, how to ensure the accuracy of the instructions and the safety of the operating environment is a problem that has not been well solved. Currently, the human-computer interaction of welding robots mostly relies on device input, such as fixed device industrial personal computers, which need to be operated by professional software through a mouse or a keyboard, or relies on a handheld mobile device for point selection input.

[0003] These methods are relatively cumbersome, and users need to undergo a long period of training and practice before they can use them, which is not efficient. Welding robots can only receive fixed instruction input, and the degree of intelligence is not high. SUMMARY

[0004] The present application aims to at least partially solve one of the problems in the related art.

[0005] To this end, a first object of the present application is to provide a welding robot control method to reduce the operation threshold of the welding robot and improve the degree of intelligence of the welding robot.

[0006] A second object of the present application is to provide a welding robot control device.

[0007] A third object of the present application is to provide an electronic device.

[0008] A fourth object of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above objects, a welding robot control method according to a first aspect of the present application is provided, which comprises: acquiring a multi-modal welding instruction; wherein the multi-modal welding instruction is used to instruct a welding robot to weld a target workpiece; determining a first welding parameter of the target workpiece corresponding to the multi-modal welding instruction; determining a three-dimensional model of a welding bead of the target workpiece and a target welding bead shape feature of the welding bead; wherein the three-dimensional model is used to indicate the welding bead position of the welding bead; determining a second welding parameter executable by the welding robot based on the first welding parameter and the target welding bead shape feature; generating a welding trajectory based on the three-dimensional model, and welding the target workpiece based on the second welding parameter and the welding trajectory.

[0011] To achieve the above object, the second aspect of the present application provides a welding robot control device, comprising: an acquisition module configured to acquire a multi-modal welding instruction; wherein the multi-modal welding instruction is used to instruct a welding robot to weld a target workpiece; a first determination module configured to determine a first welding parameter of the target workpiece corresponding to the multi-modal welding instruction; a second determination module configured to determine a three-dimensional model of a welding bead of the target workpiece and a target welding bead morphology feature of the welding bead; wherein the three-dimensional model is used to indicate a welding bead position of the welding bead; a third determination module configured to determine a second welding parameter executable by the welding robot based on the first welding parameter and the target welding bead morphology feature; and a welding module configured to generate a welding trajectory based on the three-dimensional model, and weld the target workpiece based on the second welding parameter and the welding trajectory.

[0012] To achieve the above object, the third aspect of the present application provides an electronic device, comprising: a processor; and a memory connected to the processor in communication; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, so that the processor can execute the welding robot control method of the first aspect of the present application.

[0013] To achieve the above object, the fourth aspect of the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is used to make the computer execute the welding robot control method of the first aspect of the present application.

[0014] To achieve the above object, the fifth aspect of the present application provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the welding robot control method of the first aspect of the present application.

[0015] The welding robot control method, device, electronic device and storage medium provided by the present application can acquire a multi-modal welding instruction, and determine a first welding parameter according to the multi-modal welding instruction. A three-dimensional model of a welding bead of a target workpiece and a target welding bead morphology feature of the welding bead are determined, so that a second welding parameter executable by a welding robot is determined based on the first welding parameter and the target welding bead morphology feature. A welding trajectory is generated, and the target workpiece is welded based on the second welding parameter and the welding trajectory. Thus, the present application can weld according to the multi-modal instruction, reduce the operation threshold of the welding robot, drive the robot to complete a complex welding task, and improve the intelligent degree of the welding robot. The second welding parameter executable by the robot is determined through the target welding bead morphology feature, and the welding is performed using the second welding parameter, which improves the efficiency and accuracy of the welding.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0018] Figure 1 A schematic flowchart illustrating a control method for a welding robot provided in an embodiment of this application;

[0019] Figure 2 A schematic flowchart illustrating another control method for a welding robot provided in an embodiment of this application;

[0020] Figure 3 This is a schematic diagram illustrating the acquisition of multimodal welding instructions according to an embodiment of this application;

[0021] Figure 4 A schematic flowchart illustrating another control method for a welding robot provided in an embodiment of this application;

[0022] Figure 5 This is a schematic diagram of the process of controlling a welding robot to perform welding according to an embodiment of this application;

[0023] Figure 6 This is a schematic diagram of the structure of a control device for a welding robot provided in an embodiment of this application. Detailed Implementation

[0024] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0025] The control method and apparatus for a welding robot according to embodiments of this application are described below with reference to the accompanying drawings.

[0026] Figure 1 This is a flowchart illustrating a control method for a welding robot provided in an embodiment of this application, as shown below. Figure 1 As shown, the control method for the welding robot in this application includes, but is not limited to, the following steps:

[0027] S101, obtain multimodal welding instructions.

[0028] It should be noted that the execution subject of the welding robot control method provided in this application embodiment is the welding robot. It can also be an electronic device equipped with a welding robot control system. This application embodiment does not impose specific limitations.

[0029] In some embodiments, multimodal welding instructions refer to instructions that combine multiple data modalities. For example, multimodal welding instructions may include text instructions, voice instructions, visual instructions, etc.

[0030] In some embodiments, the system can receive multimodal welding instructions sent by the user and can also monitor the user's behavior and operations. In response to the detection of a target operation by the user, the system can obtain multimodal welding instructions based on the target operation.

[0031] For example, the target operation can be an input operation. When a user is detected to be inputting on an electronic device, the user's input information can be used as a multimodal welding command.

[0032] For example, the target operation is for the user to perform an instruction action in a designated area. When the welding robot's own vision sensor detects the user's instruction action, it will treat the instruction action as a multimodal welding command.

[0033] In some embodiments, multimodal welding instructions are used to instruct a welding robot to weld a target workpiece. That is, the multimodal welding instructions may carry welding parameters for welding the target workpiece.

[0034] S102, determine the first welding parameters of the target workpiece corresponding to the multimodal welding command.

[0035] In some embodiments, the text instruction corresponding to the multimodal welding instruction can be determined and identified to obtain the first welding parameters. The first welding parameters include, but are not limited to, weld position, weld type, welding process, oscillation mode, and current parameters.

[0036] In some embodiments, by performing modal conversion on the multimodal welding instructions, other modal instructions are converted into text instructions, and semantic analysis of the text instructions is performed using natural language processing to obtain the first welding parameters from the text instructions.

[0037] In some embodiments, the multimodal welding command can also be sent to a large language model, which determines the text command corresponding to the multimodal welding command and extracts the first welding parameter from the text command.

[0038] Optionally, key semantic information, such as target description information and process requirement information, can be identified from the text instructions, and then the first welding parameters can be extracted from the key semantic information after the key semantic information is identified.

[0039] S103, determine the three-dimensional model of the target workpiece weld bead, as well as the target weld bead morphological characteristics.

[0040] In some embodiments, the three-dimensional model of the weld bead on the target workpiece can be established based on the weld bead position on the target workpiece. That is, the three-dimensional model is used to indicate the weld bead position. The target workpiece is identified by a vision sensor, and the geometric information such as the start and end points of the weld bead is determined based on the identification results. A three-dimensional model is then constructed based on the geometric information. The geometric information includes, but is not limited to, the start point, end point, direction, and cross-sectional shape.

[0041] In some embodiments, to improve the accuracy and precision of the 3D model, point cloud data of the target workpiece can be collected by a laser sensor and combined with image data collected by a vision sensor to construct a 3D model.

[0042] In some embodiments, the target weld bead morphology features include, but are not limited to, geometric dimensions, surface quality, and internal structure. The target weld bead morphology features can be extracted based on image data and / or point cloud data of the target workpiece.

[0043] In some embodiments, before generating a 3D model, the target workpiece can be subjected to quality inspection to ensure that welding failure or defects caused by the workpiece itself can be avoided when welding the target workpiece, and to provide a basis for precise adjustment of welding parameters during the welding process.

[0044] In some embodiments, the presence of quality problems in the target workpiece can be determined by assessing whether the workpiece meets the welding conditions. Image data of the target workpiece can be analyzed to determine its surface quality, and a three-dimensional model can be constructed if the surface quality meets the welding conditions.

[0045] For example, surface quality meeting welding conditions can mean that the cleanliness of the area to be welded meets welding conditions, that is, the area to be welded is free of dirt.

[0046] By determining whether the target workpiece meets the welding conditions, and if the welding conditions are met, a three-dimensional model is constructed based on the weld bead position of the target workpiece.

[0047] S104, based on the first welding parameters and the target weld bead morphology characteristics, determine the second welding parameters that the welding robot can execute.

[0048] It should be noted that there is a correspondence between different welding parameters and different weld bead morphology characteristics. In other words, workpieces with different weld bead morphology characteristics need to be welded using different welding parameters.

[0049] In some embodiments, a welding parameter library can be established in advance based on the correspondence between different welding parameters and different weld bead morphology features. The first welding parameter and the target weld bead morphology feature can be verified based on the welding parameter library to verify whether the first welding parameter can be used to weld the target weld bead morphology feature. If it can be used, the first welding parameter is determined to be the second welding parameter that the welding robot can execute.

[0050] In some embodiments, if there is a first welding parameter that cannot weld the target weld bead morphology, the welding parameter corresponding to the target weld bead morphology can be obtained from the welding parameter library as the second welding parameter based on the target weld bead morphology.

[0051] In some embodiments, it can be determined whether the first welding parameter has the same correspondence with the target weld bead morphology feature based on the correspondence in the welding parameter library. If so, it can be determined that the first welding parameter can be used to weld the target weld bead morphology feature.

[0052] For example, the first welding parameters include parameter 1, parameter 2 and parameter 3, the target weld bead morphology feature is feature A, and the welding parameters corresponding to feature A in the welding parameter library are parameter 1, parameter 2 and parameter 4. Therefore, the second welding parameters can be determined to be parameter 1, parameter 2 and parameter 4.

[0053] S105: Generate a welding trajectory based on a 3D model, and weld the target workpiece based on the second welding parameters and the welding trajectory.

[0054] In some embodiments, feature parameters of the 3D model can be extracted, and a welding trajectory can be generated based on these feature parameters. For example, feature parameters may include the centerline of the weld bead, the normal vector, curvature, and other features. The welding trajectory can be generated using any method of generating welding trajectories in related technologies, and there is no limitation thereto.

[0055] In some embodiments, the welding robot can be controlled to weld the target workpiece by means of the second welding parameters and the welding trajectory, so that the weld obtained by welding can be formed on the target workpiece according to the preset requirements, and finally achieve high-quality welding.

[0056] In some embodiments, welding control commands can be generated based on the second welding parameters and the welding trajectory, and the welding control commands can be sent to the control system of the welding robot to control the welding robot to weld the target workpiece.

[0057] The control method for a welding robot provided in this application involves acquiring multimodal welding instructions and determining first welding parameters based on these instructions. By determining the three-dimensional model of the target workpiece weld bead and the target weld bead morphology features, second welding parameters executable by the welding robot are determined based on the first welding parameters and the target weld bead morphology features. Furthermore, a welding trajectory is generated, and welding is performed on the target workpiece based on the second welding parameters and the welding trajectory. Therefore, this solution allows welding based on multimodal instructions, lowering the operational threshold of the welding robot, enabling it to complete complex welding tasks, and improving the robot's intelligence level. Determining the second welding parameters executable by the robot based on the target weld bead morphology features and using these parameters for welding improves welding efficiency and accuracy.

[0058] Figure 2 This is a flowchart illustrating another control method for a welding robot provided in an embodiment of this application, as shown below. Figure 2 As shown, the control method for the welding robot in this application includes, but is not limited to, the following steps:

[0059] S201, in response to detecting a text input operation, a multimodal welding instruction is determined based on the first text content corresponding to the text input operation.

[0060] S202, in response to detecting a voice input operation, determines a multimodal welding instruction based on the second text content corresponding to the voice input operation.

[0061] S203, in response to visual information detected in the target area, determines multimodal welding instructions based on the visual information.

[0062] In some embodiments, text input can be performed by a user on a client side, where multimodal welding instructions can be determined by receiving the first text content sent by the client. Text input can also be performed by a user on a terminal associated with the welding robot for real-time monitoring.

[0063] In some embodiments, voice input operations can be monitored based on a voice acquisition device. Since the voice acquisition device collects voice data in real time, keyword recognition can be performed on the collected voice data to determine whether the voice data is a voice input operation related to welding.

[0064] For example, keywords may include welding, weld bead, weld seam, etc.

[0065] In some embodiments, multimodal welding instructions may be determined based on first text content, and / or second text content, and / or visual information.

[0066] In some embodiments, the target area can be monitored based on a visual sensor. If a user is detected making a pointing gesture in the target area, the gesture can be collected as visual information. In other words, the visual information can be image data.

[0067] In this context, "user giving instructions in the target area" refers to the user performing a gesture in the target area.

[0068] Furthermore, visual information is processed to identify the user's gesturing actions. For example, gesture recognition models can be used to identify gesturing actions. Giving gestures can be detected through hand keypoint detection.

[0069] Figure 3 This is a schematic diagram of obtaining multimodal welding instructions according to an embodiment of this application. Figure 3 The camera of the welding robot can monitor the target area. In response to the detection of a user in the target area, it collects the user's image data to obtain visual information, and performs gesture recognition on the visual information to determine the corresponding multimodal welding instructions.

[0070] At the same time, the user's voice can be collected through a voice acquisition device, and the user's "weld this corner joint weld using the oscillating welding process" and the collected visual information can be used as multimodal welding instructions.

[0071] S204, determine the first welding parameters of the target workpiece corresponding to the multimodal welding command.

[0072] S205, determine the three-dimensional model of the weld bead of the target workpiece, as well as the target weld bead morphological characteristics.

[0073] S206, Based on the first welding parameters and the target weld bead morphology characteristics, determine the second welding parameters that the welding robot can execute.

[0074] S207 generates a welding trajectory based on a 3D model, and welds the target workpiece based on the second welding parameters and the welding trajectory.

[0075] In the embodiments of this application, steps S204-S207 can be implemented in any of the embodiments of this application, and no limitation is made here, nor will it be described in detail.

[0076] In the control method for welding robots provided in this application, multimodal welding instructions are obtained by monitoring text input operations, voice input operations, and visual information. This reduces the difficulty of setting welding instructions and enables the welding robot to perform complex welding operations through simple operations.

[0077] Based on any of the above embodiments, the first welding parameters can be determined according to the first text content and / or the second text content. During the process of determining the first welding parameters, the welding parameters can be verified to ensure the accuracy of the first welding parameters.

[0078] In some embodiments, a third welding parameter corresponding to the first and / or second text content is determined by identifying the first and / or second text content. The third welding parameter is then verified for integrity, and after passing the integrity verification, it is used as the first welding parameter.

[0079] In some embodiments, integrity verification refers to verifying whether the third welding parameters contain all the parameters required for the welding process. This can be achieved by pre-setting a parameter template with complete welding parameters and matching the third welding parameters against the parameter template. If all parameters in the parameter template successfully match the third welding parameters, the third welding parameters can be considered to have passed the integrity verification.

[0080] In some embodiments, the parameter template can indicate the parameter type of all welding parameters. If the third welding parameter includes all parameter types, it can be determined that the third welding parameter has passed the integrity verification.

[0081] In some embodiments, if the third welding parameter fails the integrity verification, the missing parameters of the third welding parameter can be supplemented by interacting with the user, thereby obtaining the first welding parameter.

[0082] In some embodiments, in response to the third welding parameter failing integrity verification, a missing fourth welding parameter is determined, and the fourth welding parameter sent by the client is received. Based on the third welding parameter and the fourth welding parameter, a first welding parameter is determined.

[0083] In some embodiments, parameter completion information can be generated based on the fourth welding parameter and sent to the client. The parameter completion information may include the parameter type of the missing fourth welding parameter.

[0084] By receiving the fourth welding parameter sent by the client based on parameter completion information, the third and fourth welding parameters can be used as the first welding parameter.

[0085] Based on the above embodiments, after obtaining the multimodal welding instructions including visual information, the target workpiece can be identified and the weld position of the target workpiece can be determined.

[0086] In some embodiments, by collecting environmental information about the current environment in which the welding robot is located, the weld area of ​​the target workpiece can be determined based on visual information and the current environmental information.

[0087] Optionally, line-of-sight estimation can be performed on the visual information to determine the ray in three-dimensional space that indicates the direction of the action in the visual information, and environmental information can be detected based on the ray to determine the weld area of ​​the weld in the target workpiece.

[0088] Furthermore, the weld position of the target workpiece can be determined based on the weld area. By identifying the weld area, the weld position can be determined.

[0089] Figure 4 This is a flowchart illustrating another control method for a welding robot provided in an embodiment of this application, as shown below. Figure 4 As shown, the control method for the welding robot in this application includes, but is not limited to, the following steps:

[0090] S401, obtain multimodal welding instructions.

[0091] S402, determine the first welding parameters of the target workpiece corresponding to the multimodal welding command.

[0092] S403, determine the three-dimensional model of the target workpiece weld bead, as well as the target weld bead morphological characteristics.

[0093] In the embodiments of this application, steps S401-S403 can be implemented in any of the embodiments of this application, and no limitation is made here, nor will it be described in detail.

[0094] S404, retrieve the pre-set welding parameter library.

[0095] In some embodiments, the welding parameter library includes the correspondence between different welding parameters and different weld bead morphology features.

[0096] It is understandable that for a given welding parameter, it can be used to weld weld bead morphology feature 1, but it cannot be used to weld weld bead morphology feature 2. Therefore, the welding parameter has a corresponding relationship with weld bead morphology feature 1, and this correspondence is stored in the welding parameter library.

[0097] In some embodiments, a correspondence can be established based on the historical weld bead morphology characteristics in the historical welding process and the welding parameters used during welding; alternatively, the corresponding welding parameters can be determined manually based on different weld bead morphology characteristics, thereby establishing a correspondence.

[0098] S405, in response to the correspondence between the first welding parameter and the target weld bead morphology, the first welding parameter is determined to be the second welding parameter that the welding robot can execute.

[0099] S406, in response to the fact that there is no correspondence between the first welding parameter and the target weld bead morphology feature, the welding parameter corresponding to the target weld bead morphology feature is determined from the welding parameter library, and the welding parameter corresponding to the target weld bead morphology feature is determined as the second welding parameter.

[0100] In some embodiments, it can be determined whether the first welding parameter exists in the welding parameter library, and whether the target weld bead morphology features are the same as the weld bead morphology features in the welding parameter library that correspond to the first welding parameter. If they are the same, it can be determined that the first welding parameter and the target weld bead morphology features correspond to each other.

[0101] For example, suppose the welding parameters in the welding parameter library are candidate welding parameters, and the weld bead morphology features that correspond to them are candidate weld bead morphology features. If the first welding parameter is the same as candidate welding parameter 1, then the candidate weld bead morphology feature corresponding to candidate welding parameter 1 is determined. If the candidate weld bead morphology feature corresponding to candidate welding parameter 1 includes feature 1, feature 2 and feature 3, and the target weld bead morphology feature is the same as feature 2, then the first welding parameter and the target weld bead morphology feature are determined to have a correspondence.

[0102] In some embodiments, when it is determined that there is a correspondence between the first welding parameter and the target weld bead morphology, the first welding parameter can be used as the second welding parameter that the welding robot can execute.

[0103] In some embodiments, if the target weld bead morphology features are not the same as the weld bead morphology features in the welding parameter library that correspond to the first welding parameter, it can be determined that there is no correspondence between the first welding parameter and the target weld bead morphology features.

[0104] In other words, the first welding parameters cannot be used to weld the target weld bead feature.

[0105] In some embodiments, since the target weld bead morphology of the target workpiece cannot be changed, the welding parameters can be modified. The welding parameters corresponding to the target weld bead morphology can be determined from the welding parameter library as the second welding parameters, so as to weld the weld bead of the target weld bead morphology using the second welding parameters.

[0106] In some embodiments, welding failure information can be generated, wherein the welding failure information may carry welding parameters from a welding parameter library, and the welding failure information is sent to a client, whereby the client determines whether to use the welding parameters from the welding parameter library as a second welding parameter.

[0107] In some embodiments, the welding parameters set by the client can be received again. In response to the lack of a correspondence between the first welding parameters and the target weld bead morphology, welding failure information is generated, and the first welding parameters resent by the client based on the welding failure information are received.

[0108] Furthermore, the resent first welding parameters are verified to see if there is a correspondence between the resent first welding parameters and the target weld characteristics. If there is a correspondence, the resent first welding parameters can be used as the second welding parameters.

[0109] S407 generates a welding trajectory based on a 3D model, and welds the target workpiece based on the second welding parameters and the welding trajectory.

[0110] In the embodiments of this application, step S407 can be implemented in any of the ways described in the embodiments of this application. This is not limited here and will not be described in detail.

[0111] In the control method of the welding robot provided in this application embodiment, a welding parameter library is obtained, and the correspondence between the first welding parameter and the target weld bead morphology feature is verified based on the welding parameter library. This determines that the first welding parameter that corresponds to the target weld bead morphology feature is the second welding parameter that the welding robot can execute. Then, the second welding parameter can be used to weld the weld bead with the target weld bead morphology feature, thereby improving the accuracy of the welding process and increasing the welding efficiency.

[0112] Based on any of the above embodiments, the welding process of the target workpiece can be monitored. By monitoring the dynamic changes of the weld pool, the welding quality can be monitored and controlled in real time, thereby preventing welding defects.

[0113] In some embodiments, a visual sensor, such as a weld pool camera, can be used to monitor the weld pool during the welding process, update the second welding parameters based on the monitoring results, and continue welding the target workpiece based on the updated second welding parameters.

[0114] Based on any of the above embodiments, after welding is completed, the weld information can be inspected to evaluate the welding quality. By acquiring the weld information of the target workpiece and performing quality inspection on the weld information, a quality inspection result is obtained. This quality inspection can detect whether the weld has visual defects, geometric defects, etc. For example, visual defects may include undercut, weld beads, pits, excessive spatter, etc.; geometric defects may include uneven weld width.

[0115] In some embodiments, image data and point cloud data of the weld can be acquired based on visual sensors and laser sensors as weld information. The image data can be used to identify whether there are appearance defects in the weld, and the point cloud data can be used to identify whether there are geometric defects in the weld.

[0116] In some embodiments, in response to a quality inspection result indicating the presence of welding defects in the weld, a treatment strategy is generated based on the welding defects, and the weld is treated based on the treatment strategy to complete the welding and make the weld quality meet the requirements.

[0117] Figure 5 This is a schematic diagram illustrating the process of controlling a welding robot to perform welding according to an embodiment of this application. Users can issue multimodal welding commands via voice commands and gestures. For voice commands, a voice recognition module can extract the voice commands; for gestures, a visual sensor can collect the gestures to determine the welding area.

[0118] The first welding parameters are obtained from the multimodal welding instructions, and matched with the target weld bead morphology characteristics of the target workpiece in a preset welding parameter library to determine the second welding parameters that the welding robot can execute. Welding is then completed by generating a welding trajectory and performing welding based on the second welding parameters and the welding trajectory.

[0119] Corresponding to the control methods for welding robots proposed in the above embodiments, one embodiment of this application also proposes a control device for welding robots. Since the control device for welding robots proposed in this application corresponds to the control methods for welding robots proposed in the above embodiments, the implementation methods of the above-mentioned control methods for welding robots are also applicable to the control device for welding robots proposed in this application. It will not be described in detail in the following embodiments.

[0120] Figure 6 This is a schematic diagram of the structure of a control device for a welding robot provided in an embodiment of this application.

[0121] like Figure 6 As shown, the control device 600 of the welding robot includes:

[0122] The acquisition module 601 is used to acquire multimodal welding instructions; wherein, the multimodal welding instructions are used to instruct the welding robot to weld the target workpiece;

[0123] The first determining module 602 is used to determine the first welding parameters of the target workpiece corresponding to the multimodal welding command;

[0124] The second determining module 603 is used to determine the three-dimensional model of the weld bead of the target workpiece and the target weld bead morphological features; wherein, the three-dimensional model is used to indicate the weld bead position;

[0125] The third determining module 604 is used to determine the second welding parameters that the welding robot can execute based on the first welding parameters and the target weld bead morphology characteristics;

[0126] The welding module 605 is used to generate a welding trajectory based on the three-dimensional model, and to weld the target workpiece based on the second welding parameters and the welding trajectory.

[0127] In one possible implementation of this application embodiment, the acquisition module 601 is further configured to: determine the multimodal welding instruction based on the first text content corresponding to the text input operation in response to detecting a text input operation; and / or, determine the multimodal welding instruction based on the second text content corresponding to the voice input operation in response to detecting a voice input operation; and / or, determine the multimodal welding instruction based on the visual information in response to detecting visual information in the target area.

[0128] In one possible implementation of this application, the first determining module 602 is further configured to: determine the third welding parameter corresponding to the first text content and / or the second text content; perform integrity verification on the third welding parameter, and after the third welding parameter passes the integrity verification, use the third welding parameter as the first welding parameter.

[0129] In one possible implementation of this application embodiment, the second determining module 603 is further configured to: determine the weld area of ​​the target workpiece based on the visual information and the current environmental information; and determine the weld position of the target workpiece based on the weld area.

[0130] In one possible implementation of this application embodiment, the first determining module 602 is further configured to: determine a missing fourth welding parameter in response to the third welding parameter failing the integrity verification; receive the fourth welding parameter sent by the client; and determine the first welding parameter based on the third welding parameter and the fourth welding parameter.

[0131] In one possible implementation of this application embodiment, the third determining module 604 is further configured to: acquire a pre-set welding parameter library; wherein the welding parameter library includes the correspondence between different welding parameters and different weld bead morphology features; in response to the existence of the correspondence between the first welding parameter and the target weld bead morphology feature, determine the first welding parameter as a second welding parameter executable by the welding robot; in response to the absence of the correspondence between the first welding parameter and the target weld bead morphology feature, determine the welding parameter corresponding to the target weld bead morphology feature from the welding parameter library, and determine the welding parameter corresponding to the target weld bead morphology feature as the second welding parameter.

[0132] In one possible implementation of this application embodiment, the third determining module 604 is further configured to: generate welding failure information in response to the absence of a correspondence between the first welding parameters and the target weld bead morphology features, and receive the first welding parameters resent by the client based on the welding failure information.

[0133] In one possible implementation of this application, the second determining module 603 is further configured to: determine whether the target workpiece meets the welding conditions, and when the welding conditions are met, construct the three-dimensional model based on the weld position of the target workpiece.

[0134] In one possible implementation of this application embodiment, the welding module 605 is further configured to: monitor the molten pool of the weld bead during the welding process, update the second welding parameters according to the monitoring results, and continue welding the target workpiece according to the updated second welding parameters.

[0135] In one possible implementation of this application embodiment, the welding module 605 is further configured to: acquire weld information of the weld of the target workpiece, and perform quality inspection on the weld information to obtain a quality inspection result; in response to the quality inspection result indicating that the weld has welding defects, generate a processing strategy based on the welding defects, and process the weld based on the processing strategy.

[0136] The control device for the welding robot provided in this application acquires multimodal welding instructions and determines first welding parameters based on these instructions. By determining the three-dimensional model of the target workpiece weld bead and the target weld bead morphology features, second welding parameters executable by the welding robot are determined based on the first welding parameters and the target weld bead morphology features. Furthermore, a welding trajectory is generated, and welding is performed on the target workpiece based on the second welding parameters and the welding trajectory. Therefore, this solution can perform welding according to multimodal instructions, lowering the operational threshold of the welding robot, enabling it to complete complex welding tasks, and improving the intelligence level of the welding robot. Determining the second welding parameters executable by the robot through the target weld bead morphology features and using these second welding parameters for welding improves welding efficiency and accuracy.

[0137] It should be noted that the foregoing explanation of the control method embodiment for the welding robot also applies to the control device of the welding robot in this embodiment, and will not be repeated here.

[0138] To implement the above embodiments, this application also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0139] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0140] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0141] The collection, storage, use, processing, transmission, provision, and application of user personal information involved in this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0142] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0143] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this application is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0144] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0145] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0146] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0147] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0148] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0149] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0150] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0151] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A control method for a welding robot, characterized in that, The method includes: Obtain multimodal welding instructions; wherein, the multimodal welding instructions are used to instruct the welding robot to weld the target workpiece; Determine the first welding parameters of the target workpiece corresponding to the multimodal welding command; A three-dimensional model of the weld bead of the target workpiece and the target weld bead morphological features are determined; wherein, the three-dimensional model is used to indicate the weld bead position; Based on the first welding parameters and the target weld bead morphology characteristics, the second welding parameters that the welding robot can execute are determined; A welding trajectory is generated based on the three-dimensional model, and the target workpiece is welded based on the second welding parameters and the welding trajectory. The step of determining the second welding parameters executable by the welding robot based on the first welding parameters and the target weld bead morphology features includes: Obtain a pre-set welding parameter library; wherein, the welding parameter library includes the correspondence between different welding parameters and different weld bead morphology features; In response to the correspondence between the first welding parameter and the target weld bead morphology feature, the first welding parameter is determined to be a second welding parameter that the welding robot can execute. In response to the absence of a correspondence between the first welding parameter and the target weld bead morphology feature, the welding parameter corresponding to the target weld bead morphology feature is determined from the welding parameter library, and the welding parameter corresponding to the target weld bead morphology feature is determined as the second welding parameter.

2. The method according to claim 1, characterized in that, The acquisition of multimodal welding instructions includes: In response to the detection of a text input operation, the multimodal welding instruction is determined based on the first text content corresponding to the text input operation; and / or, In response to the detection of a voice input operation, the multimodal welding command is determined based on the second text content corresponding to the voice input operation; and / or, In response to the detection of visual information in the target area, the multimodal welding command is determined based on the visual information.

3. The method according to claim 2, characterized in that, After obtaining the multimodal welding command, the process further includes: Determine the third welding parameters corresponding to the first text content and / or the second text content; The integrity of the third welding parameter is verified, and after the third welding parameter passes the integrity verification, the third welding parameter is used as the first welding parameter.

4. The method according to claim 2, characterized in that, After obtaining the multimodal welding command, the process further includes: Based on the visual information and the current environmental information, the weld area of ​​the target workpiece is determined; The weld position of the target workpiece is determined based on the weld area.

5. The method according to claim 3, characterized in that, The method further includes: In response to the third welding parameter failing the integrity verification, it is determined that a fourth welding parameter is missing; The system receives the fourth welding parameter sent by the client and determines the first welding parameter based on the third welding parameter and the fourth welding parameter.

6. The method according to claim 1, characterized in that, The method further includes: In response to the absence of a correspondence between the first welding parameters and the target weld bead morphology, welding failure information is generated, and the first welding parameters resent by the client based on the welding failure information are received.

7. The method according to any one of claims 1-5, characterized in that, Before determining the three-dimensional model of the weld bead of the target workpiece, the method further includes: Determine whether the target workpiece meets the welding conditions, and if the welding conditions are met, construct the three-dimensional model based on the weld position of the target workpiece.

8. The method according to any one of claims 1-5, characterized in that, After welding the target workpiece based on the second welding parameters and the welding trajectory, the process further includes: During the welding process, the molten pool of the weld bead is monitored, and the second welding parameters are updated based on the monitoring results. The target workpiece is then welded according to the updated second welding parameters.

9. The method according to any one of claims 1-5, characterized in that, After welding the target workpiece based on the second welding parameters and the welding trajectory, the process further includes: Obtain weld information of the target workpiece weld, and perform quality inspection on the weld information to obtain quality inspection results; In response to the quality inspection result indicating that there is a welding defect in the weld, a processing strategy is generated based on the welding defect, and the weld is processed based on the processing strategy.

10. A control device for a welding robot, characterized in that, The device includes: An acquisition module is used to acquire multimodal welding instructions; wherein, the multimodal welding instructions are used to instruct the welding robot to weld the target workpiece; The first determining module is used to determine the first welding parameters of the target workpiece corresponding to the multimodal welding command; The second determining module is used to determine the three-dimensional model of the weld bead of the target workpiece, and the target weld bead morphological features of the weld bead; wherein, the three-dimensional model is used to indicate the weld bead position; The third determining module is used to determine the second welding parameters that the welding robot can execute based on the first welding parameters and the target weld bead morphology characteristics; A welding module is used to generate a welding trajectory based on the three-dimensional model, and to weld the target workpiece based on the second welding parameters and the welding trajectory. The third determining module is further configured to: Obtain a pre-set welding parameter library; wherein, the welding parameter library includes the correspondence between different welding parameters and different weld bead morphology features; In response to the correspondence between the first welding parameter and the target weld bead morphology feature, the first welding parameter is determined to be a second welding parameter that the welding robot can execute. In response to the absence of a correspondence between the first welding parameter and the target weld bead morphology feature, the welding parameter corresponding to the target weld bead morphology feature is determined from the welding parameter library, and the welding parameter corresponding to the target weld bead morphology feature is determined as the second welding parameter.

11. 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 1-9.

12. 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 1-9.

13. 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 1-9.

Images