Automatic welding control method and system

Abstract

The invention relates to the technical field of welding, and provides an automatic welding control method and system. The automatic welding control method comprises the steps that the current pose and current surface information of a workpiece are determined, and under the condition that it is determined that the workpiece comprises a to-be-treated area according to the current surface information of the workpiece, a machining robot is controlled to conduct welding treatment on the to-be-treated area of the workpiece, dynamically adjusting the scanning path of the scanning robot according to the current pose of the workpiece and the to-be-processed area, controlling the scanning robot to visually sense the welded workpiece along the scanning path so as to track and obtain the pose change and the surface information change of the workpiece, and when it is determined that the workpiece does not comprise the to-be-processed area, determining that the workpiece does not comprise the to-be-processed area. And the stability of pose deviation and surface deformation of the non-rigid component in the welding production line in the welding process can be continuously measured, and the precision of subsequent welding operation is improved.

Description

Technical Field

[0001] This invention relates to the field of welding technology, and provides an automatic welding control method and system. Background Technology

[0002] In large-scale welding manufacturing scenarios such as rail transit equipment, engineering machinery, and ship structural components, non-rigid components such as beams and side beams are prone to complex automatic welding when being welded on the assembly line due to factors such as uneven heat input, insufficient clamping rigidity, and process disturbances.

[0003] The currently widely used automatic welding inspection is static inspection. Typically, the component is moved to a fixed inspection station after welding, and deformation information is obtained through one or a few inspections. It cannot continuously measure the positional displacement and surface deformation of non-rigid components in the welding production line during the welding process, resulting in low accuracy of subsequent welding operations. Summary of the Invention

[0004] This invention provides an automatic welding control method and system to address the limitations of static detection in continuously measuring the positional shifts and surface deformations of non-rigid components during welding in welding production lines, thereby improving the accuracy of subsequent welding operations.

[0005] This invention provides an automatic welding control method, comprising: Determine the current pose and surface information of the workpiece; If the workpiece is determined to include a region to be processed based on its current surface information, the processing robot is controlled to perform welding on the region to be processed of the workpiece. The scanning path of the scanning robot is dynamically adjusted according to the current pose of the workpiece and the area to be processed. The scanning robot is controlled to perform visual perception on the welded workpiece along the scanning path to track and acquire changes in the workpiece's pose and surface information. If it is determined that the workpiece does not include the area to be processed, the welding process of the workpiece is completed.

[0006] According to one embodiment of the present invention, when it is determined that the workpiece includes a region to be processed based on the current surface information of the workpiece, controlling a processing robot to perform welding processing on the region to be processed of the workpiece includes: Obtain the welding task plan for the workpiece; The welding task plan of the workpiece is compared with the current surface information of the workpiece to obtain the first target deviation information. Based on the first target deviation information, it is determined that the workpiece includes a region to be processed, and the processing robot is controlled to weld the region to be processed of the workpiece.

[0007] According to one embodiment of the present invention, after controlling a machining robot to weld the area to be processed on the workpiece, the method further includes: Obtain the standard design information of the workpiece; The standard design information of the workpiece and the surface information of the workpiece are compared to obtain the second target deviation information. The area to be processed of the workpiece is determined according to the second target deviation information, and the processing robot is controlled to perform welding adjustment on the area to be processed of the workpiece.

[0008] According to one embodiment of the present invention, dynamically adjusting the scanning path of the scanning robot based on the current pose of the workpiece and the area to be processed includes: The scanning paths of at least two scanning robots are dynamically determined based on the current pose of the workpiece and the area to be processed. The control of the scanning robot to perform visual perception of the welded workpiece along the scanning path includes: Each scanning robot is controlled to perform collaborative visual perception of the welded workpiece from different angles along the scanning path.

[0009] According to one embodiment of the present invention, the scanning robot includes an image acquisition module and a spatial information acquisition module; The control of the scanning robot to perform visual perception on the welded workpiece along the scanning path, in order to track and acquire changes in the workpiece's pose and surface information, includes: The scanning robot is controlled to collect two-dimensional image data of the workpiece after welding based on the image acquisition module along the scanning path, and to collect three-dimensional spatial information of the workpiece after welding based on the spatial information acquisition module. The workpiece's pose changes and surface information changes are tracked and obtained based on the two-dimensional image data and the three-dimensional spatial information.

[0010] According to one embodiment of the present invention, determining that the workpiece includes a region to be processed based on the current surface information of the workpiece includes: The point cloud model of the workpiece is determined based on the current surface information of the workpiece; Obtain a standard design model of the workpiece, and compare the point cloud model of the workpiece with the standard design model to determine that the workpiece includes the area to be processed.

[0011] According to an embodiment of the present invention, before determining that the workpiece includes a region to be processed by comparing the point cloud model of the workpiece with a standard design model, the method further includes: The point cloud model of the workpiece is matched and aligned with the standard design model based on the structural features of the workpiece.

[0012] According to one embodiment of the present invention, determining that the workpiece includes a region to be processed by comparing the point cloud model of the workpiece with a standard design model includes: Determine the tolerance envelope of the standard design model; Based on the tolerance envelope, the point cloud model of the workpiece is compared with the standard design model to determine that the workpiece includes the area to be processed.

[0013] According to one embodiment of the present invention, the controlled processing robot includes a heating execution robot and a rapid cooling execution robot; The controlled machining robot performs welding processing on the area to be processed of the workpiece, including: Based on the current pose and surface information of the workpiece, the heating execution robot is dynamically controlled to heat the area to be processed, and the quenching execution robot is dynamically controlled to follow the heating execution robot to perform atomized spraying on the area to be processed.

[0014] The present invention also provides an automatic welding control system, comprising: The workpiece information determination module is used to determine the current pose and current surface information of the workpiece. The welding processing module is used to control a processing robot to perform welding processing on the area to be processed of the workpiece when it is determined from the current surface information of the workpiece that the workpiece includes an area to be processed. The scanning path determination module is used to dynamically adjust the scanning path of the scanning robot according to the current pose of the workpiece and the area to be processed. The visual perception module is used to control the scanning robot to perform visual perception on the welded workpiece along the scanning path, so as to track and acquire the positional changes and surface information changes of the workpiece, and complete the welding process of the workpiece when it is determined that the workpiece does not include the area to be processed.

[0015] According to one embodiment of the present invention, the controlled processing robot includes a heating execution robot and a rapid cooling execution robot; The welding processing module is specifically used to dynamically control the heating execution robot to heat the area to be processed based on the current position and surface information of the workpiece, and to dynamically control the quenching execution robot to follow the heating execution robot to perform atomized spraying on the area to be processed based on the current position and surface information of the workpiece.

[0016] According to one embodiment of the present invention, the workpiece information determination module is used to obtain the pose change and surface information change of the workpiece tracked and acquired by the visual perception module, so as to update and determine the current pose and current surface information of the workpiece.

[0017] According to one embodiment of the present invention, a storage unit is further included for storing detection data of the scanning robot visually perceiving the workpiece along the scanning path and execution parameters of the processing robot performing welding processing on the area to be processed of the workpiece, so as to obtain a welding deformation data chain of the workpiece.

[0018] The automatic welding control method and system provided by this invention, by determining the current pose and surface information of the workpiece, determines whether the workpiece includes a region to be processed. If so, it controls a machining robot to perform welding on the region to be processed. Based on the current pose of the workpiece and the region to be processed, it dynamically adjusts the scanning path of a scanning robot, controlling the scanning robot to visually perceive the welded workpiece along the scanning path to track and acquire changes in the workpiece's pose and surface information. This allows for adaptive compensation for dynamic errors in the workpiece. If the workpiece does not include the region to be processed, the welding process is completed. It is understood that when the workpiece includes the region to be processed, the scanning robot can be repeatedly controlled to visually perceive the workpiece to continuously measure the pose shifts and surface deformations of non-rigid components in the welding production line during welding, thereby improving the accuracy of subsequent welding operations. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is one of the schematic flowcharts of the automatic welding control method provided by the present invention.

[0021] Figure 2 This is the second schematic flowchart of the automatic welding control method provided by the present invention.

[0022] Figure 3 This is a schematic structural diagram of the automatic welding control system provided by the present invention. Detailed Implementation

[0023] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and should not be construed as limiting the scope of the invention.

[0024] like Figures 1 to 3 As shown, the present invention provides an automatic welding control method and system.

[0025] Figure 1This is one of the flowcharts illustrating the automatic welding control method provided by this invention. This method can be applied to a robot control unit, also known as a robot control center, etc. Figure 1 As shown, the method includes the following steps.

[0026] Step 101: Determine the current pose and surface information of the workpiece.

[0027] The workpiece, also known as a component, refers to the target metal structural part that needs to be positioned, inspected, and processed during the welding process. For example, the workpiece can be a non-rigid welded component such as a beam or side beam.

[0028] It should be noted that the workpiece can be visually perceived by a scanning robot to determine its posture, position, and other pose information, as well as the three-dimensional morphological information of its surface in the operating space.

[0029] Current pose refers to the position and orientation of the workpiece in the operating space before welding. Current surface information refers to the surface information of the workpiece before welding.

[0030] Step 102: If the workpiece is determined to include a region to be processed based on the current surface information of the workpiece, control the processing robot to perform welding processing on the region to be processed of the workpiece.

[0031] It should be noted that there are many ways to determine whether a workpiece includes the area to be processed based on its current surface information, such as prediction by a large model or comparison of the current surface information of the workpiece with its standard surface information. This embodiment does not limit the methods used.

[0032] The "area to be processed" refers to the area that requires welding. It should be noted that the welding process performed on the area to be processed by the control robot differs at different stages of the workpiece welding production line. For example, the robot may perform welding on the area to be processed during the welding stage, or it may perform welding adjustments on the area to be processed during the post-weld repair stage.

[0033] There are many forms of processing robots, including industrial robots and mobile robots, etc. This embodiment does not limit them.

[0034] Step 103: Dynamically adjust the scanning path of the scanning robot according to the current pose of the workpiece and the area to be processed.

[0035] It should be noted that, on the one hand, in actual industrial environments, especially in assembly line operations, the spatial pose of workpieces is often subject to change. On the other hand, each welding process can at least partially eliminate the area to be processed, but it may also lead to new deviations and thus create new areas to be processed. Therefore, by determining the scanning path of the scanning robot based on the current pose of the workpiece and the area to be processed, the scanning path of the scanning robot can be dynamically adjusted according to the impact of the welding process on the workpiece. That is, trajectory reconstruction is performed based on the dynamic error of the workpiece, so that the scanning path can help the scanning robot accurately track different areas of the workpiece.

[0036] Similar to processing robots, scanning robots can be industrial robots or mobile robots, etc., and this embodiment does not limit them.

[0037] Step 104: Control the scanning robot to perform visual perception on the welded workpiece along the scanning path to track and acquire changes in the workpiece's pose and surface information, and complete the welding process of the workpiece if it is determined that the workpiece does not include the area to be processed.

[0038] It should be noted that the scanning robot can perform visual perception on the welded workpiece along the scanning path to determine the pose and position of the welded workpiece in the operating space, as well as the three-dimensional morphological information of the surface. By comparing the pose of the workpiece before and after welding, the pose change of the workpiece can be obtained. By comparing the surface information of the workpiece before and after welding, the surface information change of the workpiece can be obtained.

[0039] After tracking and acquiring the changes in the workpiece's pose and surface information, the current pose can be updated based on the pose of the workpiece after welding, and the current surface information can be updated based on the surface information of the workpiece after welding to determine whether the workpiece includes the area to be processed. If so, repeat steps 102-104; otherwise, complete the welding process of the workpiece.

[0040] The automatic welding control method provided in this invention determines the current pose and surface information of the workpiece. If the workpiece includes a region to be processed, the method controls a machining robot to weld the region. Based on the workpiece's current pose and the region to be processed, the scanning robot's scanning path is dynamically adjusted. The scanning robot then performs visual perception along the scanning path to track and acquire changes in the workpiece's pose and surface information. This allows for adaptive compensation for dynamic errors in the workpiece. If the workpiece does not include the region to be processed, the welding process is completed. It is understood that when the workpiece includes the region to be processed, the scanning robot can be repeatedly controlled to perform visual perception, continuously measuring the pose shifts and surface deformations of non-rigid components in the welding production line during welding, thereby improving the accuracy of subsequent welding operations.

[0041] Based on the above embodiments, when it is determined that the workpiece includes a region to be processed according to the current surface information of the workpiece, controlling the processing robot to perform welding processing on the region to be processed of the workpiece includes: Obtain the welding task plan for the workpiece; The welding task plan of the workpiece is compared with the current surface information of the workpiece to obtain the first target deviation information. Based on the first target deviation information, it is determined that the workpiece includes a region to be processed, and the processing robot is controlled to weld the region to be processed of the workpiece.

[0042] Welding task planning, also known as welding task plan, welding plan, welding scheme, etc., refers to the planning information such as the target area, operation sequence, welding path and related operational constraints that need to be welded, which are determined in advance based on the workpiece's geometry, weld distribution and process requirements.

[0043] It should be noted that during the welding stage after assembly, the welding process parameters of the workpiece under standard assembly dimensions can be determined based on the workpiece's welding task plan. The assembly deviation of the workpiece can be determined based on its current surface information. Then, based on the assembly deviation and the welding process parameters under standard assembly dimensions, the first target deviation information is determined. This first target deviation information can be used to control the machining robot to weld the areas of the workpiece to be processed, keeping the overall deviation within the expected deviation range of the workpiece. The overall deviation refers to the final deviation obtained based on the workpiece's assembly deviation and welding deviation.

[0044] Specifically, the expected deviation range of the workpiece in the initial welding stage can be determined in advance. Then, it is determined whether the first target deviation information falls within the expected deviation range. If so, welding is carried out according to the original welding task plan. Otherwise, the area is determined as a region to be processed. The welding task plan is dynamically adjusted according to the first target deviation information, and welding is carried out according to the dynamically adjusted welding task plan.

[0045] Understandably, by comparing the welding task plan of the workpiece with the current surface information, and dynamically adjusting the welding task plan of the workpiece, it is possible to automate the initial welding stage of the workpiece welding assembly line operation, while improving the overall accuracy of the welded workpiece.

[0046] Based on any of the above embodiments, after controlling the machining robot to weld the area to be processed on the workpiece, the method further includes: Obtain the standard design information of the workpiece; The standard design information of the workpiece and the surface information of the workpiece are compared to obtain the second target deviation information. The area to be processed of the workpiece is determined according to the second target deviation information, and the processing robot is controlled to perform welding adjustment on the area to be processed of the workpiece.

[0047] Standard design information refers to data established during the design phase of welded components, used to describe parameters such as dimensions, shape, and tolerances of the welded components. It should be noted that there are many ways to obtain standard design information for welded components, such as through engineering drawings or three-dimensional models of the welded components; this embodiment of the invention does not limit this method.

[0048] It should be noted that even when the machining robot is controlled to weld the area to be processed on the workpiece using the first target deviation information, the overall deviation of most areas of the workpiece is generally controlled within the expected deviation range. However, there will still be a small number of areas where the overall deviation falls outside the expected deviation range. At this point, the welding adjustment stage can be entered to further weld the small number of areas.

[0049] In the welding adjustment stage after the initial welding is completed, the second target deviation information of the workpiece can be determined first based on the difference between the surface information of the workpiece at the current stage and the standard design information of the workpiece. Then, it is determined whether the second target deviation information falls within the expected deviation range. If so, it is determined that the area does not need adjustment; otherwise, it is further determined whether it can be corrected through adjustment based on the structural characteristics, material limitations, and process constraints of the workpiece, and then the area is determined to be the area to be processed. Conversely, if it is determined that it cannot be corrected through adjustment based on the structural characteristics, material limitations, and process constraints of the workpiece, the area is also determined to not need adjustment.

[0050] Specifically, based on the difference between the surface information of the workpiece at the current stage and the standard design information of the workpiece, the degree of deformation of the workpiece in the welding adjustment stage can be determined. This can be specifically measured by the second target deviation information and the tolerance of the workpiece in the corresponding area.

[0051] Understandably, by comparing the standard design information and surface information of the workpiece, the area to be processed of the workpiece can be dynamically determined for welding adjustment, which can realize the automation of the welding adjustment stage of the workpiece welding assembly line operation, and at the same time improve the overall accuracy of the workpiece after welding adjustment.

[0052] It is understandable that in a production line environment, the workpiece position is not completely fixed, clamping deviations are common, and deformation will continue to accumulate during the welding process. In this embodiment, by continuously collecting the current pose and surface information of the workpiece at different process stages through a scanning robot, it is possible to capture the positional shift, assembly deviation, and surface deformation caused by heat input of the workpiece in real time during the welding process, and convert the dynamic changes of the workpiece into quantifiable dynamic error data, providing the necessary prerequisite for automated welding control of the production line.

[0053] Furthermore, in this embodiment, by using the same mechanism to cover the perception of workpiece state changes at different process stages, the system complexity can be reduced, a single perception system can cover the entire welding process, and the reusability and platformization capability of the system can be significantly improved.

[0054] Based on any of the above embodiments, the step of dynamically adjusting the scanning path of the scanning robot according to the current pose of the workpiece and the area to be processed includes: The scanning paths of at least two scanning robots are dynamically determined based on the current pose of the workpiece and the area to be processed. The control of the scanning robot to perform visual perception of the welded workpiece along the scanning path includes: Each scanning robot is controlled to perform collaborative visual perception of the welded workpiece from different angles along the scanning path.

[0055] It should be noted that by combining target recognition algorithms with the workpiece's geometric model and welding task planning, the workpiece's pose changes and surface information changes in the operating space can be identified, laying the foundation for subsequent dynamic control.

[0056] Understandably, by deploying multiple scanning robots to perform collaborative visual perception of the welded workpiece from different angles, it is possible to achieve real-time visual perception of the workpiece from various angles, improve the accuracy of perception of changes in the workpiece's pose and surface information, and provide a foundation for subsequent precise tracking of the workpiece.

[0057] In some embodiments, controlling each scanning robot to perform collaborative visual perception of the welded workpiece from different angles along the scanning path includes: Monitor the distance between each pair of the at least two scanning robots; If the spacing is less than the safety value, the scanning path of the corresponding scanning robot is updated, and the corresponding scanning robot is controlled to perform collaborative scanning of the workpiece from different angles along the updated scanning path.

[0058] Taking a scanning robot as an example, it should be noted that when multiple scanning robots are scanning a workpiece collaboratively along their respective scanning paths, if the distance between any two scanning robots is less than a safe value, avoidance can be triggered. First, the corresponding scanning robot stops moving along its respective scanning path, interrupting the current scanning operation on the workpiece. Then, a new scanning path is obtained. With the updated scanning path obtained, collaborative scanning resumes, and the scanning operation on the workpiece continues along the updated scanning path.

[0059] There are many ways to monitor the distance between at least two scanning robots, such as using proximity sensors on the scanning robots or video detection systems deployed around the inspection station. This embodiment does not limit the methods used.

[0060] The specific value of the safety value can be set according to the actual working conditions, and this embodiment does not limit it.

[0061] It is understandable that by monitoring the distance between at least two scanning robots and triggering avoidance in a timely manner when the distance is less than a safe value, the scanning robots can be controlled to resume collaborative scanning along the updated path. This can avoid collision accidents caused by path conflicts or operational errors during multi-device collaborative scanning. Furthermore, in this embodiment, by replanning the scanning path of the scanning robots, the scanning robots can be safely returned to the working state in the shortest possible time, which significantly improves the safety, stability, and overall scanning efficiency of multi-scanning robot collaborative scanning.

[0062] Based on any of the above embodiments, the scanning robot includes an image acquisition module and a spatial information acquisition module.

[0063] Here, the image acquisition module refers to the module that acquires two-dimensional image data, and the spatial information acquisition module refers to the module that acquires three-dimensional spatial data. For example, the image acquisition module can be a high-resolution industrial camera, and the spatial information acquisition module can be a 3D laser scanner.

[0064] In some embodiments, controlling the scanning robot to perform visual perception on the welded workpiece along the scanning path to track and acquire changes in the workpiece's pose and surface information includes: The scanning robot is controlled to collect two-dimensional image data of the workpiece after welding based on the image acquisition module along the scanning path, and to collect three-dimensional spatial information of the workpiece after welding based on the spatial information acquisition module. The workpiece's pose changes and surface information changes are tracked and obtained based on the two-dimensional image data and the three-dimensional spatial information.

[0065] It should be noted that when controlling the scanning robot to move along the scanning path, the image acquisition module can acquire two-dimensional image data of the workpiece along the set direction, and the spatial information acquisition module can acquire three-dimensional spatial information of the workpiece along the same direction. Based on the two-dimensional image data and the three-dimensional spatial information, the pose change and surface information change of the workpiece can be determined, and then the corresponding target deviation information can be determined.

[0066] It is understandable that in an assembly line environment, the position, orientation and shape of a workpiece may change slightly due to its own deformation, loose clamping or changes in heat input. Two-dimensional image data can provide real-time feedback on these slight changes, so as to dynamically adjust the scanning path of the scanning robot to achieve accurate tracking of different areas of the component and obtain the three-dimensional spatial information of the corresponding area.

[0067] In some embodiments, the three-dimensional spatial information of the workpiece can be realigned with the standard design information based on the two-dimensional image data, and the operating posture of the processing robot can be adjusted to improve the accuracy of welding deformation control.

[0068] Based on any of the above embodiments, determining that the workpiece includes a region to be processed based on the current surface information of the workpiece includes: The point cloud model of the workpiece is determined based on the current surface information of the workpiece; Obtain a standard design model of the workpiece, and compare the point cloud model of the workpiece with the standard design model to determine that the workpiece includes the area to be processed.

[0069] It should be noted that the three-dimensional spatial information of the workpiece collected by the spatial information acquisition module of the scanning robot can be the original point cloud. Based on this, the original point cloud can be preprocessed and modeled by filtering, registration, and stitching to generate a point cloud model of the workpiece in a unified coordinate system.

[0070] The standard design model refers to the standard geometric reference model established based on product design data.

[0071] In some embodiments, a point cloud deviation map of the workpiece can be generated by comparing the point cloud model of the workpiece with the standard design model, and the workpiece including the area to be processed can be determined based on the point cloud deviation map.

[0072] Among them, the point cloud deviation map refers to the visualized error distribution obtained by calculating the three-dimensional distance deviation between corresponding points or local areas of the post-weld point cloud model and the standard design model.

[0073] It should be noted that by spatially matching the point cloud model with the standard design model, the deviation distance between corresponding points or local areas of the two can be calculated and determined. The deviation distance is then mapped to a color gradient to obtain a point cloud deviation map that reflects the deformation characteristics of the workpiece surface in a visual form. The deviation distance of each measuring point in the point cloud deviation map is used to determine the area to be processed, and the areas to be processed and the areas that do not need to be processed can be marked accordingly.

[0074] Understandably, by comparing the point cloud model with the standard design model to generate a point cloud deviation map, this invention can simultaneously reflect the deviation of the welded component point by point in a three-dimensional visualization and numerical form, and determine the out-of-tolerance adjustable area, thereby further improving the accuracy of welding deformation control and providing a basis for the subsequent automated generation of adjustment parameters for the out-of-tolerance adjustable area.

[0075] Based on any of the above embodiments, before determining that the workpiece includes a region to be processed by comparing the point cloud model of the workpiece with the standard design model, the method further includes: matching and aligning the point cloud model of the workpiece with the standard design model according to the structural features of the workpiece.

[0076] The structural features of a workpiece are geometric and functional elements used to describe its geometry, assembly datum, and stress-bearing structural characteristics. These structural features may include weld distribution, stiffeners, locating holes, datum planes, and characteristic curved surfaces.

[0077] It should be noted that the structural features of the workpiece can be used as a reference for positioning and alignment through structural matching algorithms. The point cloud model of the workpiece can be matched and aligned with the standard design model of the workpiece in the same spatial coordinate system to achieve correct overlap.

[0078] Understandably, matching and aligning the point cloud model with the standard design model by using the structural features of the workpiece can automatically complete the matching and alignment even when the position or angle of the workpiece in the production line deviates from the ideal position or angle. This eliminates the need for manual coordinate system setting, transforming post-weld deformation control from experience-based control to automated control, and improving the accuracy and efficiency of welding deformation control.

[0079] Based on any of the above embodiments, determining that the workpiece includes a region to be processed by comparing the point cloud model of the workpiece with the standard design model includes: Determine the tolerance envelope of the standard design model; Based on the tolerance envelope, the point cloud model of the workpiece is compared with the standard design model to determine that the workpiece includes the area to be processed.

[0080] The tolerance envelope, also known as the tolerance zone, refers to the envelope region generated on the surface of the standard design model of the welded component based on its geometry and upper and lower tolerance limits. It defines the maximum and minimum allowable geometric deviations of the welded component's shape. The envelope region can include two boundary surfaces: the outer surface and the inner surface of the standard design model.

[0081] It should be noted that the tolerance envelope can be generated based on the upper and lower tolerance limits of the standard design model, or the tolerance envelope of the standard design model can be determined based on empirical parameters, etc. This embodiment does not limit this.

[0082] Specifically, in some embodiments, the standard design model can carry upper and lower tolerance limits. Based on this, the tolerance envelope can be obtained by generating inner and outer boundary surfaces along the surface normal according to the upper and lower tolerance limits.

[0083] Understandably, identifying the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted based on the tolerance envelope can ensure that the repair area of ​​the welded component falls within the design allowable range, thereby achieving high-precision identification and quantitative adjustment of workpiece deformation.

[0084] In some embodiments, the measurement points of the point cloud model can be determined based on the point cloud deviation map to identify out-of-tolerance points. Adjacent out-of-tolerance points can be connected to obtain out-of-tolerance regions, thereby determining the region to be processed.

[0085] Based on any of the above embodiments, the controlled processing robot includes a heating execution robot and a rapid cooling execution robot.

[0086] Among them, the heating execution robot, also known as the high-frequency rapid heating robot or high-frequency heating robot, is a robot used to rapidly heat the area to be processed, so as to cause local stress release or micro-plastic deformation of the workpiece material.

[0087] Rapid cooling robots, also known as atomizing spray cooling robots or atomizing rapid cooling robots, are robots used to perform atomizing spray rapid cooling treatment on areas of workpieces that have experienced localized stress release or micro-plastic deformation, so that the workpiece material can be quickly shaped and secondary rebound can be suppressed.

[0088] In some embodiments, the control of the processing robot to perform welding processing on the area to be processed of the workpiece includes: dynamically controlling the heating execution robot to heat the area to be processed based on the current pose and current surface information of the workpiece, and dynamically controlling the quenching execution robot to follow the heating execution robot to perform atomized spraying on the area to be processed based on the current pose and current surface information of the workpiece.

[0089] It should be noted that after controlling the heating robot to heat the adjustable area, the quenching robot can be immediately controlled to perform atomized spraying on the adjustable area. The specific time interval can be determined according to the material of the welded component, and this embodiment of the invention does not limit it.

[0090] Understandably, compared to correcting the out-of-tolerance adjustable area through flame and mechanical adjustment processes, the hot-cold linkage adjustment method, which controls the rapid cooling execution robot to follow the heating execution robot to perform atomized spraying on the out-of-tolerance adjustable area, reduces the risk of residual stress accumulation inside the material, thereby effectively reducing the risk of secondary deformation and material structure damage, and improving the comprehensive mechanical properties and long-term service stability of welded components.

[0091] It should be noted that after determining the area to be processed, the corresponding adjustment strategy can be determined based on the current surface information of the area to be processed. On this basis, the adjustment parameters of the corresponding heating execution robot or quenching execution robot can be dynamically determined based on the current pose and current surface information of the workpiece, so as to realize precise quantitative adjustment based on vision drive and improve the accuracy of the workpiece after welding.

[0092] Figure 2 This is the second flowchart of the automatic welding control method provided by the present invention, as shown below. Figure 2 As shown, in order to illustrate the function of the automatic welding control method provided in this embodiment, a specific example is provided below.

[0093] First, the initialization of vision servo-based automatic welding control can be performed. For example, multiple robots with visual perception capabilities can establish their own coordinate systems and workpiece poses based on visual information before starting scanning and adjustment operations, ensuring that subsequent vision servo control actions are in a unified and controllable state. Then, the current pose and surface information of the workpiece are determined to dynamically identify the area to be processed. Next, real-time pose analysis of the workpiece's current pose can be performed to obtain offset detection results. Based on the offset detection results and the area to be processed, the scanning path of the scanning robot can be dynamically adjusted. High-frequency heating and atomized cooling can be triggered for shape adjustment. Specifically, based on the current pose and surface information of the workpiece, the heating execution robot can be dynamically controlled to heat the adjustable area out of tolerance, and the cooling execution robot can be dynamically controlled to follow the heating execution robot to perform atomized spraying on the adjustable area out of tolerance. Finally, closed-loop accuracy verification is performed based on changes in workpiece pose and surface information. If the workpiece does not include the area to be processed, the workpiece is determined to be up to standard, and the welding process is completed. If the workpiece includes the area to be processed, the workpiece is determined to be out of standard, and the area to be processed is repeatedly identified dynamically.

[0094] The automatic welding control system provided by the present invention is described below. The automatic welding control system described below can be referred to in correspondence with the automatic welding control method described above.

[0095] Figure 3 This is a schematic diagram of the automatic welding control system provided by the present invention, as shown below. Figure 3 As shown, the system includes the following modules: The workpiece information determination module 310 is used to determine the current pose and current surface information of the workpiece. The welding processing module 320 is used to control a processing robot to perform welding processing on the area to be processed of the workpiece when it is determined from the current surface information of the workpiece that the workpiece includes an area to be processed. The scanning path determination module 330 is used to dynamically adjust the scanning path of the scanning robot according to the current pose of the workpiece and the area to be processed. The visual perception module 340 is used to control the scanning robot to perform visual perception on the workpiece after welding along the scanning path, so as to track and acquire the pose change and surface information change of the workpiece, and complete the welding process of the workpiece when it is determined that the workpiece does not include the area to be processed.

[0096] Based on any of the above embodiments, the controlled processing robot includes a heating execution robot and a rapid cooling execution robot; The welding processing module is specifically used to dynamically control the heating execution robot to heat the area to be processed based on the current position and surface information of the workpiece, and to dynamically control the quenching execution robot to follow the heating execution robot to perform atomized spraying on the area to be processed based on the current position and surface information of the workpiece.

[0097] Understandably, compared to correcting the out-of-tolerance adjustable area through flame and mechanical adjustment processes, the system in this embodiment uses a hot-cold linkage adjustment method that controls the rapid cooling execution robot to follow the heating execution robot to perform atomized spraying on the out-of-tolerance adjustable area. This can reduce the risk of residual stress accumulation inside the material, thereby effectively reducing the risk of secondary deformation and material structure damage, and improving the comprehensive mechanical properties and long-term service stability of the welded components.

[0098] Based on any of the above embodiments, the workpiece information determination module is used to obtain the pose change and surface information change of the workpiece tracked and acquired by the visual perception module, so as to update and determine the current pose and current surface information of the workpiece.

[0099] It should be noted that after tracking and acquiring the workpiece's pose changes, the workpiece's pose after welding can be determined based on the workpiece's pose before welding and the changes in its pose, thus updating the current pose of the workpiece. Similarly, after tracking and acquiring the workpiece's surface information changes, the workpiece's surface information after welding can be determined based on the workpiece's surface information before welding and the changes in its surface information, thus updating the current surface information of the workpiece. This allows for the automatic determination of whether the workpiece includes a processing area requiring welding based on its post-weld pose and surface information. If so, the welding and scanning process is repeated; otherwise, the welding process is completed.

[0100] It is understandable that by using the visual perception module as the control center, and by tracking and acquiring changes in the workpiece's pose and surface information through the visual perception module, and updating the workpiece's current pose and surface information, a closed-loop control between the welding process and deformation deviation of the workpiece by the processing robot can be achieved, so as to realize the intelligent adaptive adjustment of the system.

[0101] Based on any of the above embodiments, a storage unit is further included, used to store the detection data of the scanning robot visually perceiving the workpiece along the scanning path and the execution parameters of the processing robot welding the area to be processed of the workpiece, so as to obtain the welding deformation data chain of the workpiece.

[0102] For example, the storage unit can be the database of the automatic welding control system. Specifically, it can be the local database of the automatic welding control system or a remote cloud database. This embodiment does not limit this.

[0103] It should be noted that the automatic welding control system can be electrically or communicatively connected to the scanning robot and the processing robot respectively, so as to acquire the detection data of the scanning robot and the execution parameters of the processing robot in real time and store them in the storage unit.

[0104] The detection data obtained by the scanning robot through visual perception of the welded workpiece along the scanning path can also be called the adjustment result.

[0105] The detection data and execution parameters of different stages of the same workpiece in the pipeline, as well as the detection data and execution parameters of different iterations of the same stage in the pipeline, can have the same data identifier to associate the relevant data of all welding processes of the workpiece and obtain the welding deformation data chain of the workpiece.

[0106] Understandably, the welding deformation data chain of the workpiece enables accurate and rapid tracing of welding deformation or adjustment anomalies, improving the response speed and handling accuracy in abnormal situations on the production line. On the other hand, the welding deformation data chain of the workpiece can provide effective training data for training relevant prediction models, so that the relevant prediction models can be applied in the process design stage to predict and avoid welding deformation risks in advance.

[0107] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of software products. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic welding control method, characterized in that, include: Determine the current pose and surface information of the workpiece; If the workpiece is determined to include a region to be processed based on its current surface information, the processing robot is controlled to perform welding on the region to be processed of the workpiece. The scanning path of the scanning robot is dynamically adjusted according to the current pose of the workpiece and the area to be processed. The scanning robot is controlled to perform visual perception on the welded workpiece along the scanning path to track and acquire changes in the workpiece's pose and surface information. If it is determined that the workpiece does not include the area to be processed, the welding process of the workpiece is completed.

2. The automatic welding control method according to claim 1, characterized in that, When it is determined from the current surface information of the workpiece that the workpiece includes a region to be processed, controlling the processing robot to perform welding processing on the region to be processed of the workpiece includes: Obtain the welding task plan for the workpiece; The welding task plan of the workpiece is compared with the current surface information of the workpiece to obtain the first target deviation information. Based on the first target deviation information, it is determined that the workpiece includes a region to be processed, and the processing robot is controlled to weld the region to be processed of the workpiece.

3. The automatic welding control method according to claim 2, characterized in that, After controlling the machining robot to weld the area to be processed on the workpiece, the method further includes: Obtain the standard design information of the workpiece; The standard design information of the workpiece and the surface information of the workpiece are compared to obtain the second target deviation information. The area to be processed of the workpiece is determined according to the second target deviation information, and the processing robot is controlled to perform welding adjustment on the area to be processed of the workpiece.

4. The automatic welding control method according to claim 1, characterized in that, The step of dynamically adjusting the scanning path of the scanning robot based on the current pose of the workpiece and the area to be processed includes: The scanning paths of at least two scanning robots are dynamically determined based on the current pose of the workpiece and the area to be processed. The control of the scanning robot to perform visual perception of the welded workpiece along the scanning path includes: Each scanning robot is controlled to perform collaborative visual perception of the welded workpiece from different angles along the scanning path.

5. The automatic welding control method according to claim 1, characterized in that, The scanning robot includes an image acquisition module and a spatial information acquisition module; The control of the scanning robot to perform visual perception on the welded workpiece along the scanning path, in order to track and acquire changes in the workpiece's pose and surface information, includes: The scanning robot is controlled to collect two-dimensional image data of the workpiece after welding based on the image acquisition module along the scanning path, and to collect three-dimensional spatial information of the workpiece after welding based on the spatial information acquisition module. The workpiece's pose changes and surface information changes are tracked and obtained based on the two-dimensional image data and the three-dimensional spatial information.

6. The automatic welding control method according to claim 5, characterized in that, The step of determining that the workpiece includes a region to be processed based on the current surface information of the workpiece includes: The point cloud model of the workpiece is determined based on the current surface information of the workpiece; Obtain a standard design model of the workpiece, and compare the point cloud model of the workpiece with the standard design model to determine that the workpiece includes the area to be processed.

7. The automatic welding control method according to claim 6, characterized in that, Before comparing the point cloud model of the workpiece with the standard design model to determine that the workpiece includes the area to be processed, the method further includes: The point cloud model of the workpiece is matched and aligned with the standard design model based on the structural features of the workpiece.

8. The automatic welding control method according to claim 6, characterized in that, The comparison between the point cloud model of the workpiece and the standard design model determines that the workpiece includes a region to be processed, including: Determine the tolerance envelope of the standard design model; Based on the tolerance envelope, the point cloud model of the workpiece is compared with the standard design model to determine that the workpiece includes the area to be processed.

9. The automatic welding control method according to any one of claims 1-8, characterized in that, The controlled processing robot includes a heating execution robot and a rapid cooling execution robot; The controlled machining robot performs welding processing on the area to be processed of the workpiece, including: Based on the current pose and surface information of the workpiece, the heating execution robot is dynamically controlled to heat the area to be processed, and the quenching execution robot is dynamically controlled to follow the heating execution robot to perform atomized spraying on the area to be processed.

10. An automatic welding control system, characterized in that, include: The workpiece information determination module is used to determine the current pose and current surface information of the workpiece. The welding processing module is used to control a processing robot to perform welding processing on the area to be processed of the workpiece when it is determined from the current surface information of the workpiece that the workpiece includes an area to be processed. The scanning path determination module is used to dynamically adjust the scanning path of the scanning robot according to the current pose of the workpiece and the area to be processed. The visual perception module is used to control the scanning robot to perform visual perception on the welded workpiece along the scanning path, so as to track and acquire the positional changes and surface information changes of the workpiece, and complete the welding process of the workpiece when it is determined that the workpiece does not include the area to be processed.

11. The automatic welding control system according to claim 10, characterized in that, The controlled processing robot includes a heating execution robot and a rapid cooling execution robot; The welding processing module is specifically used to dynamically control the heating execution robot to heat the area to be processed based on the current position and surface information of the workpiece, and to dynamically control the quenching execution robot to follow the heating execution robot to perform atomized spraying on the area to be processed based on the current position and surface information of the workpiece.

12. The automatic welding control system according to claim 10, characterized in that, The workpiece information determination module is used to obtain the pose changes and surface information changes of the workpiece tracked and acquired by the visual perception module, so as to update and determine the current pose and current surface information of the workpiece.

13. The automatic welding control system according to claim 10, characterized in that, It also includes a storage unit for storing the detection data of the scanning robot visually perceiving the workpiece along the scanning path and the execution parameters of the processing robot welding the area to be processed of the workpiece, so as to obtain the welding deformation data chain of the workpiece.

Images