Welding deformation control method and system

Abstract

The invention provides a welding deformation control method and system, and relates to the technical field of welding. The method comprises the steps of determining a to-be-adjusted welding component, performing path planning according to the welding component to obtain a corresponding global scanning path, determining scanning tasks of at least two pieces of three-dimensional scanning equipment, and performing global optimization on the global scanning path according to the scanning tasks to obtain a to-be-adjusted welding component; the method comprises the following steps of: obtaining a three-dimensional scanning path of each piece of three-dimensional scanning equipment, controlling each piece of three-dimensional scanning equipment to carry out cooperative scanning on a welding component along the three-dimensional scanning path to obtain post-welding surface information of the welding component, and determining an out-of-tolerance adjustable area according to the post-welding surface information of the welding component to carry out adjustment and repair. The time for scanning the welding component can be shortened, so that the efficiency of determining the out-of-tolerance adjustable area for adjustment and repair in the welding correction process is improved.

Description

Technical Field

[0001] This invention relates to the field of welding technology, and in particular to a method and system for controlling welding deformation. Background Technology

[0002] With the development of rail transit equipment towards lightweight, high-precision, and multi-variety flexible manufacturing, and the widespread application of large welded components in the fields of rail transit, engineering machinery and heavy equipment manufacturing, the spatial distortion generated during the welding process has become a major factor affecting the dimensional accuracy and assembly quality of components.

[0003] To improve the accuracy of identifying spatial distortions generated during the welding process, 3D scanning is currently the most common method for acquiring information about the workpiece surface. However, during the 3D scanning of the workpiece surface, for welded components with complex structures and large dimensions, the scanning time is too long due to the large number of scanning areas and the limited detection angle, which affects the adjustment efficiency of the welding correction process. Summary of the Invention

[0004] This invention provides a welding deformation control method and system to solve the problem of excessively long scanning time for welded components in the prior art, and to improve the adjustment efficiency of the welding correction process.

[0005] This invention provides a method for controlling welding deformation, comprising: Identify the welding component to be repaired, and perform path planning based on the welding component to obtain the corresponding global scan path; The scanning tasks of at least two 3D scanning devices are determined, and the global scanning path is globally optimized based on the scanning tasks to obtain the 3D scanning path of each 3D scanning device. Each of the three-dimensional scanning devices is controlled to perform a collaborative scan of the welded component along the three-dimensional scanning path to obtain the post-weld surface information of the welded component; The welded component is adjusted and repaired based on the post-weld surface information.

[0006] According to a welding deformation control method provided by the present invention, the step of globally optimizing the global scanning path based on the scanning task includes: Identify at least two optimization directions; The global scan path is globally optimized based on the scan task and the at least two optimization directions.

[0007] According to a welding deformation control method provided by the present invention, the method of controlling each of the three-dimensional scanning devices to perform collaborative scanning of the welded component along the three-dimensional scanning path includes: Monitor the distance between each pair of the at least two 3D scanning devices; If the spacing is less than the safety value, the corresponding 3D scanning path of the 3D scanning device is updated, and the corresponding 3D scanning device is controlled to perform a collaborative scan of the welded component along the updated 3D scanning path.

[0008] According to a welding deformation control method provided by the present invention, the step of adjusting the welded component based on the post-weld surface information includes: The out-of-tolerance areas are determined based on the post-weld surface information of the welded components, and the out-of-tolerance areas are prioritized according to at least two target factors to obtain the priority of the repair task. The adjustment execution equipment is determined, and an adjustment path for the adjustment execution equipment is generated according to the priority of the adjustment task. The welded component is adjusted according to the post-weld surface information.

[0009] According to a welding deformation control method provided by the present invention, the step of generating a repair path for the repair execution equipment based on the priority of the repair task includes: Obtain the component features of the welded component; The maintenance path for the maintenance execution device is generated based on the priority of the maintenance task and the characteristics of the component.

[0010] According to the welding deformation control method provided by the present invention, the adjustment and execution equipment includes a heating execution module and a rapid cooling execution module; The adjustment of the welded component based on the post-weld surface information includes: Based on the post-weld surface information, the heating execution module is controlled to heat the adjustable area of ​​the welded component that exceeds the tolerance; based on the post-weld surface information, the rapid cooling execution module is controlled to follow the heating execution module to perform atomized spraying on the adjustable area of ​​the welded component that exceeds the tolerance.

[0011] According to a welding deformation control method provided by the present invention, the step of adjusting the welded component based on the post-weld surface information includes: Input the target parameters of the out-of-tolerance area corresponding to the adjustment task into the judgment model, and obtain the line-yielding logic execution result output by the judgment model; Based on the result of the line-letting logic execution, the welded component is adjusted and repaired according to the post-weld surface information; The judgment model is trained based on the target parameters of the out-of-range regions of the samples and the corresponding sample line logic execution results; the judgment model is periodically updated.

[0012] According to a welding deformation control method provided by the present invention, the step of adjusting the welded component based on the post-weld surface information includes: Obtain the post-weld point cloud model and the standard design model of the welded component, and compare the post-weld point cloud model with the standard design model to generate a point cloud deviation map of the welded component; A tolerance envelope is generated based on historical qualified samples, and the out-of-tolerance region is identified from the point cloud deviation map using the tolerance envelope.

[0013] According to a welding deformation control method provided by the present invention, after adjusting the welded component based on the post-weld surface information, the method further includes: Obtain the surface information of the welded component after adjustment; The verification results are obtained by comparing the surface information after adjustment with the standard design information; the verification results are used to determine whether the welding deformation adjustment step of the welded component needs to be repeated.

[0014] The present invention also provides a welding deformation control system, comprising: A data processing terminal is used to determine the welded component to be repaired, and to perform path planning based on the welded component to obtain the corresponding global scanning path; to determine the scanning tasks of at least two three-dimensional scanning devices, and to perform global optimization of the global scanning path based on the scanning tasks to obtain the three-dimensional scanning path of each three-dimensional scanning device, and to send the three-dimensional scanning path to the three-dimensional scanning device. A three-dimensional scanning device is used to receive the three-dimensional scanning path sent by the data processing terminal, perform collaborative scanning on the welded component, and obtain the post-weld surface information of the welded component; The adjustment module is used to determine the out-of-tolerance adjustable area for adjustment based on the post-weld surface information of the welded component.

[0015] The welding deformation control method and system provided by this invention obtains a corresponding global scanning path by path planning based on the welded component to be repaired, and optimizes the global scanning path globally based on the scanning tasks of at least two three-dimensional scanning devices to obtain the three-dimensional scanning path of each three-dimensional scanning device. It can reasonably plan the three-dimensional scanning paths of multiple three-dimensional scanning devices and control each three-dimensional scanning device to perform collaborative scanning of the welded component along the three-dimensional scanning path. It can collect the post-weld surface information of the welded component in an orderly manner through multiple three-dimensional scanning devices, shorten the scanning time of the welded component, and improve the efficiency of identifying and repairing out-of-tolerance adjustable areas during the welding correction process. Attached Figure Description

[0016] 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.

[0017] Figure 1 This is one of the flowcharts of the welding deformation control method provided by the present invention.

[0018] Figure 2 This is the second flowchart of the welding deformation control method provided by the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention.

[0021] Figure 1 This is one of the flowcharts illustrating the welding deformation control method provided by the present invention, such as... Figure 1 As shown, the method includes the following steps.

[0022] Step 101: Determine the welding component to be repaired, and perform path planning based on the welding component to obtain the corresponding global scan path.

[0023] Welded components, also known as welded parts, welded structural components, post-weld parts, or welded parts, refer to components formed by connecting them through welding processes. For example, a welded component can be formed by connecting two or more metal parts through methods such as fusion welding, pressure welding, or brazing.

[0024] The global scan path, also known as the global path, scan path, or detection path, is a path planned globally based on the overall three-dimensional structure of the welded component to be adjusted.

[0025] It should be noted that after identifying the welded component to be repaired, a perception model of the welded component can be established, and the global scanning path of the welded component can be obtained by path planning based on the perception model of the welded component.

[0026] Step 102: Determine the scanning tasks of at least two 3D scanning devices, and perform global optimization on the global scanning path based on the scanning tasks to obtain the 3D scanning path for each 3D scanning device.

[0027] Among them, 3D scanning equipment refers to equipment that performs high-density point cloud data acquisition on the welding area of ​​the welded component to be repaired in order to obtain the current 3D shape of the welded component. For example, 3D scanning equipment can be a 3D laser scanner fixed on a mobile device, or a fully automated scanning robot, etc.

[0028] A scanning task is a collection of scanning areas and scanning postures of a 3D scanning device for scanning welded components. It is used to clarify the inspection range, inspection sequence, and coverage requirements that each device needs to complete.

[0029] A 3D scanning path, also known as a 3D detection path, local scanning path, or local path, is a local scanning path of a single 3D scanning device obtained by decomposing and optimizing the global scanning path. It should be noted that the optimized global scanning path is obtained by combining the 3D scanning paths of each 3D scanning device.

[0030] It should be noted that the global scanning path can be decomposed according to the workspace and collaborative scheduling requirements of the 3D scanning equipment. Based on this, global optimization is performed according to the scanning task of each 3D scanning equipment to obtain the final 3D scanning path of each 3D scanning equipment.

[0031] Step 103: Control each of the three-dimensional scanning devices to perform collaborative scanning of the welded component along the three-dimensional scanning path to obtain the post-weld surface information of the welded component.

[0032] It should be noted that after the workpiece is welded, it can be automatically transported to the inspection station. The positioning device ensures the stability of the workpiece's position and posture at the inspection station. Then, each 3D scanning device can be controlled to simultaneously scan the welding area of ​​the welded component along its own 3D scanning path using a laser scanning device. This collaboratively collects high-density point cloud data of the surface of the welded component, obtaining the post-weld surface information of the welded component.

[0033] Among them, post-weld surface information refers to data obtained through measurement that describes parameters such as the actual size and shape of the welded component.

[0034] Step 104: Adjust and repair the welded component according to the post-weld surface information.

[0035] It should be noted that there are many ways to adjust the welded component based on the post-weld surface information, such as manual adjustment or automatic adjustment by machine equipment. This embodiment does not further limit this.

[0036] The welding deformation control method provided in this invention involves planning a path based on the welded component to be repaired to obtain a corresponding global scanning path. The global scanning path is then globally optimized based on the scanning tasks of at least two 3D scanning devices to obtain the 3D scanning path for each device. This method can rationally plan the 3D scanning paths of multiple 3D scanning devices and control each device to collaboratively scan the welded component along its 3D scanning path. It can also systematically collect post-weld surface information of the welded component through multiple 3D scanning devices, shortening the scanning time and improving the efficiency of identifying and adjusting out-of-tolerance areas during welding correction.

[0037] Based on the above embodiments, the step of globally optimizing the global scan path according to the scan task includes: Identify at least two optimization directions; The global scan path is globally optimized based on the scan task and the at least two optimization directions.

[0038] The optimization direction is a target indicator used to evaluate the quality of a 3D scanning path. For example, the optimization direction may include path length, coverage, workload, number of pose switching times, and multi-device interference cost.

[0039] Taking path length and coverage as examples where at least two optimization directions are path length and coverage, the global scanning path obtained by global optimization can balance the shortest path length and the maximum scanning coverage, significantly improving detection efficiency and job coordination.

[0040] It should be noted that a genetic algorithm can be used to perform selection, crossover, and mutation operations based on the scanning task and at least two optimization directions, thereby comprehensively optimizing at least two optimization directions. This allows for the automatic allocation and order adjustment of the scanning area among different 3D scanning devices while meeting the constraints of the scanning task. After multiple iterations, a scanning path that meets the requirements of each scanning task and performs optimally in at least two optimization directions can be obtained, ultimately yielding the optimal 3D scanning path for each 3D scanning device.

[0041] It is understandable that a global scanning path is obtained by establishing a perception model of the welded component to be repaired and performing path planning. Based on this, the scanning task is determined, and a genetic algorithm is used to perform global optimization based on the scanning task and at least two optimization directions to obtain the 3D scanning path of each 3D scanning device. By using the joint optimization of the perception model and the genetic algorithm, the idle travel, repeated scanning and invalid posture switching of the scanning devices can be significantly reduced, making multi-device collaborative scanning more compact and efficient. This effectively shortens the overall 3D inspection time and improves the efficiency of identifying and adjusting out-of-tolerance areas during the welding correction process.

[0042] Based on any of the above embodiments, controlling each of the three-dimensional scanning devices to collaboratively scan the welded component along the three-dimensional scanning path includes: Monitor the distance between each pair of the at least two 3D scanning devices; If the spacing is less than the safety value, the corresponding 3D scanning path of the 3D scanning device is updated, and the corresponding 3D scanning device is controlled to perform a collaborative scan of the welded component along the updated 3D scanning path.

[0043] Taking a 3D scanning device as an example, it should be noted that when multiple scanning robots are collaboratively scanning a welded component along their respective 3D 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 3D scanning path, interrupting the current scanning operation on the welded component. Then, a new 3D scanning path is obtained. With the updated 3D scanning path obtained, collaborative scanning resumes, and the scanning operation on the welded component continues along the updated 3D scanning path.

[0044] There are many ways to monitor the distance between at least two 3D scanning devices, such as using proximity sensors on the 3D scanning devices or video detection systems arranged around the detection station. This embodiment does not limit the methods.

[0045] Specifically, a second global scanning path can be obtained by replanning the path based on the currently unscanned area of ​​the welded component. The second global scanning path is then globally optimized based on the scanning task and the same optimization direction to obtain the updated 3D scanning path of the corresponding 3D scanning device.

[0046] The specific value of the safety value can be set according to the actual working conditions, and this embodiment does not limit it.

[0047] It is understandable that by monitoring the distance between at least two 3D scanning devices and triggering avoidance in a timely manner when the distance is less than a safe value, the 3D scanning devices 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 3D scanning path of the 3D scanning devices, the 3D scanning devices can be safely returned to the working state in the shortest possible time, significantly improving the safety, stability, and overall scanning efficiency of collaborative scanning of multiple 3D scanning devices.

[0048] Based on any of the above embodiments, the adjustment of the welded component according to the post-weld surface information includes: The out-of-tolerance areas are determined based on the post-weld surface information of the welded components, and the out-of-tolerance areas are prioritized according to at least two target factors to obtain the priority of the repair task. The adjustment execution equipment is determined, and an adjustment path for the adjustment execution equipment is generated according to the priority of the adjustment task. The welded component is adjusted according to the post-weld surface information.

[0049] In some embodiments, a post-weld point cloud model and a standard design model of the welded component can be obtained to compare the post-weld point cloud model with the standard design model to generate a point cloud deviation map of the welded component; a tolerance envelope is generated based on historical qualified samples to identify and determine out-of-tolerance areas from the point cloud deviation map using the tolerance envelope.

[0050] It should be noted that multiple 3D scanning devices can perform collaborative scanning of the welded components along their respective 3D scanning paths to obtain the original point cloud, which can then be preprocessed and modeled by filtering, registration, and stitching to generate a post-weld point cloud model of the welded components in a unified coordinate system.

[0051] The standard design model refers to the standard geometric reference model established based on product design data. The point cloud deviation map is a 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.

[0052] It should be noted that by spatially matching the post-weld 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 visually reflects the deformation characteristics of the welded component surface. Threshold judgment is performed on the deviation distance of each measuring point in the point cloud deviation map to determine the adjustable area of ​​the deviation. The adjustable area and the non-adjustable area of ​​the deviation can be marked accordingly.

[0053] It is understandable that by generating a point cloud deviation map by registering the post-weld point cloud model with the standard design model based on structural features, this invention can simultaneously reflect the deviation of the post-weld component point by point in a three-dimensional visualization and numerical form and determine the out-of-tolerance adjustable area, 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.

[0054] Furthermore, compared to models built solely based on theoretical design data, this embodiment introduces a large number of verified qualified samples from actual production through historical qualified samples. This can truly reflect the deformation distribution law of welded components in the actual manufacturing environment, effectively avoiding inconsistencies between the design model and the actual manufacturing state, thereby improving the accuracy of weld deformation area identification and out-of-tolerance judgment.

[0055] The target factors refer to a set of key indicators for evaluating the importance and urgency of repairing out-of-tolerance areas. These indicators are used to prioritize each out-of-tolerance area, thereby generating the execution order of the repair tasks. For example, target factors may include the magnitude of deformation, location importance, and accessibility.

[0056] It should be noted that after identifying the out-of-tolerance areas, these areas can be prioritized based on at least two target factors to obtain the priority of each out-of-tolerance area. Then, each out-of-tolerance area can be directly used as a repair task or a component unit of a repair task, thereby determining the priority of the repair tasks based on the priority of the out-of-tolerance areas.

[0057] There are many ways to generate the adjustment path of the adjustment execution equipment based on the priority of the adjustment task. The order in which the adjustment execution equipment adjusts the out-of-tolerance area can be determined according to the priority of the adjustment task to generate the adjustment path of the adjustment execution equipment. Alternatively, the adjustment path of the adjustment execution equipment can be generated based on the priority of the adjustment task and other set factors. This embodiment does not limit this.

[0058] Based on any of the above embodiments, generating the maintenance path for the maintenance execution equipment according to the priority of the maintenance task includes: Obtain the component features of the welded component; The maintenance path for the maintenance execution device is generated based on the priority of the maintenance task and the characteristics of the component.

[0059] Among them, component features, also known as structural features, are geometric and functional elements used to describe the geometry, assembly reference, and stress-bearing structural characteristics of welded components. Structural features of welded components may include weld distribution, stiffeners, positioning holes, reference planes, and characteristic curved surfaces, etc.

[0060] It should be noted that the priority of the adjustment task can determine which out-of-tolerance area to adjust first, and the adjustment plan for that out-of-tolerance area can be determined based on the component characteristics, thereby generating a specific adjustment path for the adjustment execution equipment.

[0061] Understandably, by combining the priority of the adjustment task with the component characteristics of the welded component to generate the adjustment path of the adjustment execution equipment, it is possible to automatically select an accessible, adjustable, and interference-free adjustment path based on the actual structural characteristics of the component. This reduces the risk of invalid adjustments, frequent attitude switching, and path conflicts caused by simply sorting based on priority, thereby significantly improving adjustment efficiency and quality.

[0062] Based on any of the above embodiments, the adjustment execution device includes a heating execution module and a rapid cooling execution module.

[0063] The heating execution module, also known as a high-frequency rapid heating system or high-frequency heating device, is used to rapidly heat the adjustable area of ​​the welded component at high frequency, causing local stress release or micro-plastic deformation of the material.

[0064] The rapid cooling execution module, also known as the atomized spray cooling system or atomized rapid cooling device, is used to perform atomized spray rapid cooling treatment on areas of welded components that experience localized stress release or micro-plastic deformation, so that the material of the welded components can be quickly shaped and secondary rebound can be suppressed.

[0065] Specifically, based on preset adjustment criteria, a first adjustment path and first operating parameters for the heating execution module are automatically generated according to the identified adjustable out-of-tolerance area. Similarly, a second adjustment path and second operating parameters for the rapid cooling execution module are automatically generated based on the identified adjustable out-of-tolerance area. The first and second adjustment paths may each include a movement route between the adjustment parts. The first operating parameters may include the heating frequency and heating time of the heating execution module, while the second operating parameters may include the atomization spray rate. Specific adjustment parameters such as heating frequency, heating time, and atomization spray rate can be determined based on the material of the welded component; this embodiment of the invention does not limit this.

[0066] In some embodiments, adjusting the welded component based on the post-weld surface information includes: Based on the post-weld surface information, the heating execution module is controlled to heat the adjustable area of ​​the welded component that exceeds the tolerance; based on the post-weld surface information, the rapid cooling execution module is controlled to follow the heating execution module to perform atomized spraying on the adjustable area of ​​the welded component that exceeds the tolerance.

[0067] It should be noted that after the heating execution module heats the adjustable area of ​​the welded component according to the post-weld surface information, bringing the adjustable area of ​​the welded component into a state of plastic deformation, the rapid cooling execution module can be immediately controlled to spray the adjustable area of ​​the welded component with atomized water to form a directional internal stress reaction, eliminating or offsetting the original deformation. The specific time interval can also be determined according to the material of the welded component, and this embodiment of the invention does not limit it.

[0068] After adjustment, the heating temperature, time, location, results and other control parameters can be written into the database for storage.

[0069] 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 module to follow the heating execution module 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.

[0070] Furthermore, in this embodiment, multiple 3D scanning devices collaboratively perform laser scanning on the welded components along their respective 3D scanning paths to collect point cloud data of the welded workpieces, achieving a measurement accuracy on the order of 0.1mm. By comparing the post-weld point cloud model with the standard design model, the out-of-tolerance area and deviation can be accurately located. Based on this, high-frequency induction heating is used to bring the out-of-tolerance area into a plastic deformation state, and immediate atomized spray cooling is used to form a directional internal stress reaction, eliminating or offsetting the original deformation. This achieves a control accuracy of ±0.5mm and is applicable to various complex structural components such as crossbeams and side beams, as well as the automatic generation of differentiated adjustment paths for the framework.

[0071] Based on any of the above embodiments, the step of adjusting the welded component according to the post-weld surface information includes: inputting the target parameters of the out-of-tolerance area corresponding to the adjustment task into a judgment model to obtain the line-yielding logic execution result output by the judgment model; adjusting the welded component according to the post-weld surface information based on the line-yielding logic execution result; wherein, the judgment model is trained based on the target parameters of the sample out-of-tolerance area and the corresponding sample line-yielding logic execution result; the judgment model is periodically updated.

[0072] The target parameters for the out-of-tolerance area corresponding to the adjustment task can be set according to actual needs; this embodiment does not impose any limitations on this. The result of the line logic execution is used to indicate whether the current cycle can perform adjustment operations on the out-of-tolerance area corresponding to the adjustment task.

[0073] The target parameters and corresponding sample out-of-tolerance regions of the sample can be obtained from historical data such as the corresponding parameters of the out-of-tolerance regions of the welded components and the adjustment of the execution equipment.

[0074] For example, if the result of the line-letting logic execution meets the adjustment conditions, the adjustment execution equipment can be controlled to adjust the welded component based on the post-weld surface information; if the result of the line-letting logic execution does not meet the adjustment conditions, the line-letting logic can be executed automatically to control the adjustment execution equipment to skip the out-of-tolerance area.

[0075] In some embodiments, while controlling the adjustment and maintenance execution equipment to skip the out-of-tolerance area, the area can be recorded as uncontrollable deformation, providing a basis for subsequent data optimization processes.

[0076] A feasible training scheme for the judgment model may include: The target parameters of the out-of-range regions of the samples are input into the initial judgment model to obtain the predicted results of the line-letting logic execution output by the initial judgment model. Then, based on the actual results and predicted results of the line-letting logic execution, the loss function value is calculated. Finally, the model parameters of the initial judgment model are updated based on the loss function value. The above input and calculation processes are iteratively executed until the loss function converges or the preset number of iterations is reached, thus obtaining the judgment model. The preset number of iterations can be set as needed and is not specifically limited here.

[0077] The update cycle of the judgment model can be set according to actual needs, and this embodiment does not impose any restrictions on it. The training data for the periodic update of the judgment model can be historical data from the previous cycle, or historical data from the previous 1 to 3 cycles, and this embodiment does not impose any restrictions on it either.

[0078] It is understandable that iterative iteration can improve the accuracy of the judgment model.

[0079] Based on any of the above embodiments, after obtaining the standard design information and post-weld surface information of the welded component, the method further includes: comparing the post-weld surface information with the standard design information to determine the non-adjustable out-of-tolerance area of ​​the welded component; generating an early warning prompt based on the non-adjustable out-of-tolerance area, and sending the early warning prompt to the user.

[0080] It should be noted that a digital identifier can be added to the non-adjustable area out of tolerance, and it can be bound to the welded component. When the deformation of the welded component is determined to be eliminated and enters the manufacturing process, an early warning can be generated based on the digital identifier and sent to the manufacturing operator to prompt the manufacturing operator to take indirect correction and process compensation measures.

[0081] The early warning system may include uncontrollable deformation areas, and record information such as location, amount of deformation, and cause.

[0082] Understandably, by generating early warning prompts based on areas with out-of-tolerance and unadjustable limits, data tracking can be achieved. Sending early warning prompts to users in downstream processes of welded components can realize data closure and dynamic feedback in the manufacturing process.

[0083] Based on any of the above embodiments, after determining the out-of-tolerance adjustable area based on the post-weld surface information of the welded component and performing adjustments, the method further includes: Obtain the surface information of the welded component after adjustment; The verification results are obtained by comparing the adjusted surface information with the standard design information; the verification results are used to determine whether the welding deformation adjustment step of the welded component needs to be repeated. The method for obtaining surface information of welded components after adjustment is basically the same as the method for obtaining surface information of welded components after welding, and will not be repeated here.

[0084] It should be noted that the out-of-tolerance area can be obtained by comparing the surface information after adjustment with the standard design information. By checking whether there is an adjustable area in the out-of-tolerance area, the verification result of whether the welding deformation of the welded component has been eliminated can be obtained. If so, proceed to the next process; otherwise, repeat the welding deformation adjustment steps for the welded component.

[0085] Understandably, after adjusting the adjustable area of ​​the welded component, the verification results obtained by comparing the adjusted surface information with the standard design information are dynamically fed back. This is then matched and aligned with the structural characteristics of the welded component to generate a point cloud deviation map. The adjustable area is identified from the point cloud deviation map using the tolerance envelope. Based on the adjustable area, adjustment parameters are automatically planned to form a data closed loop, realizing adaptive feedback control for welding deformation adjustment. This improves the accuracy, consistency, and automation level of welded component repair.

[0086] Figure 2 This is the second flowchart of the welding deformation control method provided by the present invention, as shown below. Figure 2 As shown, in order to illustrate the function of the welding deformation control method provided in this embodiment, a specific example is provided below.

[0087] Once the welded component to be repaired is identified, a perception model of the welded component can be established. Based on the perception model of the welded component, path planning can be performed to obtain the global scanning path of the welded component.

[0088] The optimization directions for the global scanning path are path length and coverage. The optimal 3D scanning path for each 3D scanning device can be obtained by using a genetic algorithm to perform selection, crossover, and mutation operations based on the scanning task and at least two optimization directions, and by comprehensively optimizing from at least two optimization directions.

[0089] Then, multiple 3D scanning devices can be controlled to dynamically scan the welded component along their respective 3D scanning paths, collaboratively collecting high-density point cloud data of the welded component surface to obtain post-weld surface information of the welded component.

[0090] During dynamic scanning, the spacing between scanning robots is monitored: if the spacing is less than the safe value, avoidance can be triggered. The corresponding scanning robot stops moving along its respective 3D scanning path, interrupts the current scanning operation on the welded component, and then quickly replans the path to obtain a new 3D scanning path. If the updated 3D scanning path is obtained, collaborative scanning resumes, and the scanning operation on the welded component continues along the updated 3D scanning path; otherwise, collaborative scanning continues.

[0091] Based on the high-density point cloud data of the welded component surface, a post-weld point cloud model of the welded component can be obtained. Then, a standard design model of the welded component can be obtained. The post-weld point cloud model and the standard design model are compared to generate a point cloud deviation map of the welded component. A tolerance envelope is generated based on historical qualified samples. The tolerance envelope is used to identify and determine the out-of-tolerance area from the point cloud deviation map, and the adjustment execution equipment is controlled to adjust and repair the welded component.

[0092] The welding deformation control system provided by the present invention is described below. The welding deformation control system described below can be referred to in correspondence with the welding deformation control method described above.

[0093] The system includes: A data processing terminal is used to determine the welded component to be repaired, and to perform path planning based on the welded component to obtain the corresponding global scanning path; to determine the scanning tasks of at least two three-dimensional scanning devices, and to perform global optimization of the global scanning path based on the scanning tasks to obtain the three-dimensional scanning path of each three-dimensional scanning device, and to send the three-dimensional scanning path to the three-dimensional scanning device. A three-dimensional scanning device is used to receive the three-dimensional scanning path sent by the data processing terminal, perform collaborative scanning on the welded component, and obtain the post-weld surface information of the welded component; The adjustment module is used to determine the out-of-tolerance adjustable area for adjustment based on the post-weld surface information of the welded component.

[0094] 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.

[0095] 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 part that contributes to the prior art, can be embodied in the form of a software product. 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.

[0096] 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. A method for controlling welding deformation, characterized in that, include: Identify the welding component to be repaired, and perform path planning based on the welding component to obtain the corresponding global scan path; The scanning tasks of at least two 3D scanning devices are determined, and the global scanning path is globally optimized based on the scanning tasks to obtain the 3D scanning path of each 3D scanning device. Each of the three-dimensional scanning devices is controlled to perform a collaborative scan of the welded component along the three-dimensional scanning path to obtain the post-weld surface information of the welded component; The welded component is adjusted and repaired based on the post-weld surface information.

2. The welding deformation control method according to claim 1, characterized in that, The step of globally optimizing the global scan path based on the scan task includes: Identify at least two optimization directions; The global scan path is globally optimized based on the scan task and the at least two optimization directions.

3. The welding deformation control method according to claim 1, characterized in that, The control of each of the three-dimensional scanning devices to perform collaborative scanning of the welded component along the three-dimensional scanning path includes: Monitor the distance between each pair of the at least two 3D scanning devices; If the spacing is less than the safety value, the corresponding 3D scanning path of the 3D scanning device is updated, and the corresponding 3D scanning device is controlled to perform a collaborative scan of the welded component along the updated 3D scanning path.

4. The welding deformation control method according to claim 1, characterized in that, The adjustment of the welded component based on the post-weld surface information includes: The out-of-tolerance areas are determined based on the post-weld surface information of the welded components, and the out-of-tolerance areas are prioritized according to at least two target factors to obtain the priority of the repair task. The adjustment execution equipment is determined, and an adjustment path for the adjustment execution equipment is generated according to the priority of the adjustment task. The welded component is adjusted according to the post-weld surface information.

5. The welding deformation control method according to claim 4, characterized in that, The step of generating the maintenance path for the maintenance execution equipment based on the priority of the maintenance task includes: Obtain the component features of the welded component; The maintenance path for the maintenance execution device is generated based on the priority of the maintenance task and the characteristics of the component.

6. The welding deformation control method according to claim 1, characterized in that, The adjustment and maintenance equipment includes a heating execution module and a rapid cooling execution module; The adjustment of the welded component based on the post-weld surface information includes: Based on the post-weld surface information, the heating execution module is controlled to heat the adjustable area of ​​the welded component that exceeds the tolerance; based on the post-weld surface information, the rapid cooling execution module is controlled to follow the heating execution module to perform atomized spraying on the adjustable area of ​​the welded component that exceeds the tolerance.

7. The welding deformation control method according to claim 1, characterized in that, The adjustment of the welded component based on the post-weld surface information includes: Input the target parameters of the out-of-tolerance area corresponding to the adjustment task into the judgment model, and obtain the line-yielding logic execution result output by the judgment model; Based on the result of the line-letting logic execution, the welded component is adjusted and repaired according to the post-weld surface information; The judgment model is trained based on the target parameters of the out-of-range regions of the samples and the corresponding sample line logic execution results; the judgment model is periodically updated.

8. The welding deformation control method according to claim 1, characterized in that, The adjustment of the welded component based on the post-weld surface information includes: Obtain the post-weld point cloud model and the standard design model of the welded component, and compare the post-weld point cloud model with the standard design model to generate a point cloud deviation map of the welded component; A tolerance envelope is generated based on historical qualified samples, and the out-of-tolerance region is identified from the point cloud deviation map using the tolerance envelope.

9. The welding deformation control method according to claim 1, characterized in that, After adjusting the welded component based on the post-weld surface information, the method further includes: Obtain the surface information of the welded component after adjustment; The verification results are obtained by comparing the surface information after adjustment with the standard design information; the verification results are used to determine whether the welding deformation adjustment step of the welded component needs to be repeated.

10. A welding deformation control system, characterized in that, include: A data processing terminal is used to determine the welding component to be repaired and to perform path planning based on the welding component to obtain the corresponding global scan path. The scanning tasks of at least two 3D scanning devices are determined, and the global scanning path is globally optimized according to the scanning tasks to obtain the 3D scanning path of each 3D scanning device, and the 3D scanning path is sent to the 3D scanning device. A three-dimensional scanning device is used to receive the three-dimensional scanning path sent by the data processing terminal, perform collaborative scanning on the welded component, and obtain the post-weld surface information of the welded component; The adjustment module is used to determine the out-of-tolerance adjustable area for adjustment based on the post-weld surface information of the welded component.

Images