Welding deformation control method and system
By automatically identifying key adjustment reference points and out-of-tolerance adjustable areas of welded components through 3D point cloud data acquisition and springback prediction models, and combining heating and rapid cooling execution modules for quantitative adjustment, the problem of existing welding deformation control relying on experience has been solved, and efficient and precise welding deformation control has been achieved.
Patent Information
- Application Number
- CN202610007842.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-05
- Publication Date
- 2026-05-05
AI Technical Summary
Existing welding deformation control methods rely on operator experience, resulting in inefficient adjustment processes and damage to material microstructure and properties. They cannot accurately account for the time effects of material plastic recovery and thermal stress release, leading to repeated adjustments and a decline in material properties.
By employing 3D point cloud data acquisition and springback prediction models, key adjustment reference points and out-of-tolerance adjustable areas of welded components are automatically identified. Quantitative adjustments are made through heating and rapid cooling execution modules, and 3D point cloud data verification is used to achieve precise control.
It improves the accuracy and efficiency of welding deformation control, reduces the number of adjustment cycles, avoids secondary deformation and performance damage of materials, and realizes high-precision quantitative adjustment of welded components.
Smart Images
Figure CN121972850A_ABST
Abstract
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] In the manufacturing of high-end equipment such as rail transit and construction machinery, welding is a key process for structural component forming. For large, thin-walled, non-rigid welded components such as beams and side beams, uneven heat input during welding inevitably causes component deformation, directly affecting subsequent assembly accuracy, structural load-bearing capacity, and product appearance. Therefore, post-weld deformation adjustment is a core step in ensuring the quality of the final product.
[0003] Currently, the mainstream post-weld repair methods in industrial settings rely on the experience of operators, employing flame heating for correction or supplemented by mechanical straightening. The typical process is as follows: workers visually assess the area and degree of deformation using templates, calipers, or other tools; then, based on experience, they use a welding torch or specialized flame torch to locally heat specific parts of the component, utilizing the generated thermal stress to induce plastic deformation and correct the shape; after correction, a cooling period is usually required before measurement and verification; if the result is unsatisfactory, the above process is repeated. However, manual operation cannot accurately consider the time effect of material plastic recovery and thermal stress release. It can only operate based on the static measurement results after adjustment, which may not be the final stable state of the component. This leads to the adjustment process falling into a passive cycle of adjustment, waiting, rebound and readjustment. Not only is it inefficient and highly dependent on the operator's personal experience and on-site judgment, but repeated local heating may also aggravate the adverse changes in material microstructure and properties and the accumulation of residual stress. Summary of the Invention
[0004] This invention provides a welding deformation control method and system to solve the problem of repeated local heating in welding deformation control in the prior art, and to achieve quantitative adjustment of welding deformation control.
[0005] This invention provides a method for controlling welding deformation, comprising: Collect three-dimensional point cloud data of the welded components to be repaired; The three-dimensional point cloud data is input into the springback prediction model to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted, which is output by the springback prediction model; wherein, the springback prediction model is trained based on the sample three-dimensional point cloud data and the springback amount of the key adjustment reference point of the sample welded component to be adjusted. The out-of-tolerance adjustable area is identified from the key adjustment reference points of the welded component to be adjusted, and adjustment parameters for adjusting the out-of-tolerance adjustable area are generated according to the adjustment springback amount corresponding to the out-of-tolerance adjustable area, so as to control the welding deformation.
[0006] According to a welding deformation control method provided by the present invention, the step of inputting the three-dimensional point cloud data into a springback prediction model to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted, output by the springback prediction model, includes: Based on the feature recognition layer of the springback prediction model, the three-dimensional point cloud data is processed to obtain the feature representation of the key adjustment reference points of the welded component to be adjusted. Based on the springback prediction layer of the springback prediction model, the feature representation is parsed to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted.
[0007] According to a welding deformation control method provided by the present invention, the step of identifying the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted includes: A post-weld point cloud model of the welded component to be repaired is generated based on the three-dimensional point cloud data. Obtain a standard design model of the welded component to compare the post-weld point cloud model of the welded component with the standard design model, and identify the out-of-tolerance adjustable area and its deformation from the key adjustment reference points of the welded component to be adjusted.
[0008] According to a welding deformation control method provided by the present invention, the step of comparing the post-weld point cloud model of the welded component with a standard design model includes: The post-weld point cloud model of the welded component is matched and aligned with the standard design model based on the structural characteristics of the welded component.
[0009] According to a welding deformation control method provided by the present invention, the step of comparing the post-weld point cloud model of the welded component with a standard design model to identify the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted includes: Determine the tolerance envelope of the standard design model; By comparing the post-weld point cloud model of the welded component with the standard design model, the out-of-tolerance adjustable area and its deformation amount are identified from the key adjustment reference points of the welded component to be adjusted based on the tolerance envelope.
[0010] According to a welding deformation control method provided by the present invention, the step of generating adjustment parameters for adjusting the adjustable region based on the adjustment springback amount corresponding to the adjustable region out of tolerance includes: The corresponding adjustment strategy is determined based on the adjustment rebound amount and the deformation amount corresponding to the out-of-tolerance adjustable area. The adjustment execution equipment for the adjustable region of the out-of-tolerance is determined according to the adjustment strategy, and the adjustment parameters for adjusting the adjustable region of the out-of-tolerance are determined.
[0011] According to a welding deformation control method provided by the present invention, the step of determining the adjustment execution device for the adjustable region of the out-of-tolerance according to the adjustment strategy, and the adjustment parameters for adjusting the adjustable region of the out-of-tolerance, includes: Determine the maintenance execution equipment corresponding to the maintenance strategy; The adjustment parameters for the adjustment execution device to adjust the adjustable area of the out-of-tolerance are determined based on the adjustment rebound amount and the deformation amount corresponding to the out-of-tolerance adjustable area.
[0012] According to a welding deformation control method provided by the present invention, the adjustment execution device includes a heating execution module and a rapid cooling execution module; The process of controlling welding deformation includes: The heating execution module is controlled to heat the adjustable area according to the adjustment parameters, and the rapid cooling execution module is controlled to follow the heating execution module to perform atomized spraying on the adjustable area according to the adjustment parameters.
[0013] According to a welding deformation control method provided by the present invention, after welding deformation control is performed, the method further includes: Obtain the three-dimensional point cloud data of the adjusted welded component; The verification result is obtained by repeating the step of identifying the out-of-tolerance adjustable area and its deformation amount from the key adjustment reference points of the welded component to be adjusted based on the three-dimensional point cloud data; the verification result is used to determine whether to repeat the welding deformation adjustment step of the welded component.
[0014] The present invention also provides a welding deformation control system, comprising: The welding deformation control method and system provided by this invention collects three-dimensional point cloud data of the welded component to be adjusted, analyzes the three-dimensional point cloud data of the welded component to be adjusted through a springback prediction model, obtains the adjustment springback amount of its key adjustment reference points, identifies the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted, and generates adjustment parameters for adjusting the out-of-tolerance adjustable area according to the adjustment springback amount corresponding to the out-of-tolerance adjustable area, thereby controlling welding deformation. This can avoid the influence of the time effect of material plastic recovery and thermal stress release on the final adjustment effect of welding deformation and improve the control accuracy of welding deformation. Attached Figure Description
[0015] 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.
[0016] Figure 1 This is a flowchart illustrating the welding deformation control method provided by the present invention.
[0017] Figure 2 This is a schematic diagram of the architecture of the welding deformation control method provided by the present invention.
[0018] Figure 3 This is a schematic diagram of the welding deformation control system 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 a flowchart illustrating the welding deformation control method provided by the present invention, as shown below. Figure 1 As shown, the method includes the following steps.
[0022] Step 101: Collect three-dimensional point cloud data of the welded component to be repaired.
[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] It should be noted that high-density point cloud data of the welding area of the welded component to be repaired can be acquired using a 3D scanning device to obtain the 3D point cloud data of the welded component. For example, the 3D scanning device can be a 3D laser scanner fixed to a mobile device, or a fully automated scanning robot, etc.
[0025] Step 102: Input the three-dimensional point cloud data into the springback prediction model to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted output by the springback prediction model; wherein, the springback prediction model is trained based on the sample three-dimensional point cloud data and the springback amount of the key adjustment reference point of the sample welded component to be adjusted.
[0026] Among them, the springback prediction model, also known as the springback prediction model or rebound prediction model, is used to analyze the three-dimensional point cloud data of the welded component to be adjusted, and automatically identify the welding deformation area of the welded component to be adjusted and its corresponding adjustment springback amount, also known as adjustment springback amount or rebound trend.
[0027] It should be noted that the springback prediction model can not only locate the deformation area of the welded component to be adjusted based on the three-dimensional point cloud data of the welded component to be adjusted and obtain the key adjustment reference point, but also automatically judge the rebound trend of the key adjustment reference point. This provides a basis for avoiding the influence of the time effect of material plastic recovery and thermal stress release on the adjustment effect of welding deformation and improving the control accuracy of welding deformation.
[0028] For example, the springback prediction model can be a deep learning model integrating a PointNet convolutional neural network. First, 3D point cloud data can be input into the PointNet convolutional neural network to perform deep feature learning, automatically identifying and segmenting potential deformation regions, and obtaining a high-dimensional global feature vector rich in 3D geometric and spatial context information. This high-dimensional global feature vector is then input into a fully connected layer for decoding to obtain the springback amount of the weld deformation region of the welded component to be repaired. In this embodiment, the key repair reference point is the aforementioned weld deformation region.
[0029] A feasible training scheme for the rebound prediction model may include: The initial prediction model is input with sample 3D point cloud data to obtain the predicted springback amount of the key adjustment reference points of the welded component to be adjusted, as output by the initial prediction model. Then, based on the predicted springback amount and the actual springback amount of the key adjustment reference points of the welded component to be adjusted, 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 springback prediction model. The preset number of iterations can be set as needed and is not specifically limited here.
[0030] In some embodiments, the three-dimensional point cloud data can be identified and processed based on the feature recognition layer of the springback prediction model to obtain the feature representation of the key adjustment reference point of the welded component to be adjusted; the feature representation can be parsed based on the springback prediction layer of the springback prediction model to obtain the adjustment springback amount of the key adjustment reference point of the welded component to be adjusted.
[0031] During the training process, the feature recognition layer can be deep-learned using calculation methods related to elastic deformation to establish a mapping relationship between three-dimensional point cloud data and the deformation characteristics of the welded component to be adjusted. The springback prediction layer can be deep-learned using at least calculation methods related to plastic deformation to establish a mapping relationship between three-dimensional point cloud data and the springback amount of the key adjustment reference points of the welded component to be adjusted.
[0032] Step 103: Identify the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted, and generate adjustment parameters for adjusting the out-of-tolerance adjustable area based on the adjustment springback amount corresponding to the out-of-tolerance adjustable area, and control welding deformation.
[0033] Among them, the critical adjustment reference point refers to the point of action of one or more adjustment equipment in the deformation area of the welded component to be adjusted. The deformation area corresponding to the critical adjustment reference point may include the out-of-tolerance adjustable area and the out-of-tolerance non-adjustable area.
[0034] It should be noted that due to the structural characteristics, material limitations, and process constraints of welded components, some areas of the out-of-tolerance zone can be corrected through adjustment, while other areas cannot. The areas of the out-of-tolerance zone that can be effectively corrected through adjustment are called adjustable out-of-tolerance zones, while the areas that cannot be effectively corrected through adjustment are called non-adjustable out-of-tolerance zones.
[0035] Furthermore, due to the time effect of material plastic recovery and thermal stress release, the welded component will generate springback after adjustment, which slowly and continuously changes the shape of the workpiece. In this embodiment, based on the springback amount of the out-of-tolerance adjustable area output by the springback prediction model, adjustment parameters for adjusting the out-of-tolerance adjustable area are generated to control welding deformation. This can avoid the influence of the time effect of material plastic recovery and thermal stress release on the final adjustment effect of welding deformation and improve the control accuracy of welding deformation.
[0036] The welding deformation control method provided in this invention collects three-dimensional point cloud data of the welded component to be adjusted, analyzes the three-dimensional point cloud data of the welded component to be adjusted using a springback prediction model, obtains the adjustment springback amount of its key adjustment reference points, identifies the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted, and generates adjustment parameters for adjusting the out-of-tolerance adjustable area based on the adjustment springback amount corresponding to the out-of-tolerance adjustable area, thereby controlling welding deformation. This method can avoid the influence of the time effect of material plastic recovery and thermal stress release on the final adjustment effect of welding deformation and improve the control accuracy of welding deformation.
[0037] Understandably, by quantifying the amount of springback during adjustment, the consistency of welding deformation adjustment can be improved, the number of cycles in the adjustment process can be reduced, thereby improving adjustment efficiency and avoiding repeated local heating.
[0038] Based on the above embodiments, identifying the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted includes: A post-weld point cloud model of the welded component to be repaired is generated based on the three-dimensional point cloud data. Obtain a standard design model of the welded component to compare the post-weld point cloud model of the welded component with the standard design model, and identify the out-of-tolerance adjustable area and its deformation from the key adjustment reference points of the welded component to be adjusted.
[0039] The standard design model refers to the standard geometric reference model established based on product design data.
[0040] It should be noted that the three-dimensional point cloud data of the welded components obtained by scanning can be preprocessed and modeled to generate a post-weld point cloud model. This model can then be matched with the standard design model to determine the distance between the measurement points corresponding to the key adjustment reference points of the post-weld point cloud model and the standard design model. This allows for the identification of the deformation at the corresponding positions of the key adjustment reference points and the standard design model, as well as whether the position is an adjustable area.
[0041] Specifically, the 3D point cloud data obtained by acquiring high-density point cloud data of the welding area of the welding component to be repaired using a 3D scanning device may include the welding component to be repaired and the clamping fixture of the welding component to be repaired. Under the influence of the clamping fixture, some areas of the welding component to be repaired may not be collected. Based on this, the 3D point cloud data can be preprocessed through a computing layer to realize the identification and extraction of complex features such as points, lines, and surfaces, so as to remove the point cloud data surface corresponding to the clamping fixture and complete the welding component to be repaired to obtain the complete point cloud data corresponding to the welding component to be repaired.
[0042] There are many ways to preprocess the three-dimensional point cloud data of the welded components obtained by scanning, such as through recognition algorithms or deep learning models. This embodiment does not make any further limitations on this.
[0043] It is understandable that by collecting three-dimensional point cloud data of welded components through three-dimensional scanning equipment to generate a post-weld point cloud model, and then comparing the post-weld point cloud model with the standard design model to determine the out-of-tolerance adjustable area, high-precision identification of the post-weld deformation of welded components can be achieved, so as to carry out quantitative adjustment of welded components and improve the consistency and reliability of post-weld adjustment.
[0044] Based on any of the above embodiments, the comparison of the post-weld point cloud model of the welded component with the standard design model includes: The post-weld point cloud model of the welded component is matched and aligned with the standard design model based on the structural characteristics of the welded component.
[0045] The structural features of welded components are geometric and functional elements used to describe their geometry, assembly references, and stress-bearing structural characteristics. These structural features may include weld distribution, stiffeners, locating holes, reference planes, and characteristic curved surfaces.
[0046] It should be noted that the structural features of the welded component can be used as a reference for positioning and alignment through a structural matching algorithm. The post-weld point cloud model of the welded component can be matched and aligned with the standard design model of the welded component in the same spatial coordinate system to achieve correct overlap.
[0047] Understandably, by using the structural features of the welded components to achieve matching and alignment between the post-weld point cloud model and the standard design model, the matching and alignment can be automatically completed even when the position or angle of the welded components 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, thereby improving the accuracy and efficiency of welding deformation control.
[0048] Based on any of the above embodiments, the step of comparing the post-weld point cloud model of the welded component with the standard design model to identify the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted includes: Determine the tolerance envelope of the standard design model; By comparing the post-weld point cloud model of the welded component with the standard design model, the out-of-tolerance adjustable area and its deformation amount are identified from the key adjustment reference points of the welded component to be adjusted based on the tolerance envelope.
[0049] 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.
[0050] It should be noted that the standard design model can carry upper and lower tolerance limits. Based on this, the tolerance envelope of the standard design model can be determined by generating inner and outer boundary surfaces along the surface normal according to the upper and lower tolerance limits. Specifically, by determining whether the deformation of the measurement points corresponding to the key adjustment reference points is within the tolerance envelope range, it is possible to identify whether the area corresponding to the key adjustment reference points is an out-of-tolerance area.
[0051] 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 the deformation of the welded component.
[0052] Based on any of the above embodiments, the step of generating adjustment parameters for adjusting the adjustable region based on the adjustment rebound amount corresponding to the adjustable region includes: The corresponding adjustment strategy is determined based on the adjustment rebound amount and the deformation amount corresponding to the out-of-tolerance adjustable area. The adjustment execution equipment for the adjustable region of the out-of-tolerance is determined according to the adjustment strategy, and the adjustment parameters for adjusting the adjustable region of the out-of-tolerance are determined.
[0053] It should be noted that there are many ways to determine the corresponding adjustment strategy based on the adjustment springback and deformation of the adjustable region. For example, the adjustment strategy can be determined by looking up the adjustment springback and deformation of the adjustable region. Alternatively, the adjustment springback and deformation of the adjustable region can be input into the pre-trained strategy model to obtain the adjustment strategy output by the strategy model. This embodiment does not impose further limitations on this.
[0054] Based on any of the above embodiments, the step of determining the adjustment execution device for the adjustable region according to the adjustment strategy, and the adjustment parameters for adjusting the adjustable region, includes: Determine the maintenance execution equipment corresponding to the maintenance strategy; The adjustment parameters for the adjustment execution device to adjust the adjustable area of the out-of-tolerance are determined based on the adjustment rebound amount and the deformation amount corresponding to the out-of-tolerance adjustable area.
[0055] For example, based on the springback and deformation amount corresponding to the adjustable area, the corresponding adjustment strategy can be determined to be heating adjustment. Thus, the adjustment execution device for the adjustable area can be determined to be the heating execution module. Based on the springback and deformation amount corresponding to the adjustable area, the total plastic deformation amount can be determined, and then the adjustment parameters such as heating power, action time, and action position can be determined to control the heating execution module to adjust the adjustable area.
[0056] Alternatively, based on the springback and deformation amounts corresponding to the adjustable area, the corresponding adjustment strategy can be determined as a combination of high-frequency heating and atomized rapid cooling. This determines that the adjustment execution equipment for the adjustable area is the heating execution module and the rapid cooling execution module. Furthermore, based on the springback and deformation amounts corresponding to the adjustable area, the total plastic deformation amount can be determined. This leads to the determination of adjustment parameters such as heating power, the action time and position of the heating execution module, cooling power, the action time and position of the rapid cooling execution module, etc., to control the combined adjustment of the adjustable area by the heating execution module and the rapid cooling execution module.
[0057] Understandably, automatically determining the adjustment strategy based on the two key diagnostic results of springback and deformation enables intelligent selection at the strategy level. On this basis, for areas with predicted large springback and requiring precise thermal control, the system can automatically select and set adjustment execution equipment such as high-frequency induction heating devices, along with their power and time parameters. This completely eliminates reliance on personal experience during the adjustment process, achieving quantitative control of welding deformation. Consequently, regardless of when, where, or who operates, the same deformation problem can be controlled using essentially consistent adjustment parameters, improving the consistency of welding deformation control.
[0058] Based on any of the above embodiments, the adjustment execution device includes a heating execution module and a rapid cooling execution module.
[0059] 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.
[0060] 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.
[0061] 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.
[0062] In some embodiments, the welding deformation control includes: controlling the heating execution module to heat the adjustable area according to the adjustment parameters, and controlling the quenching execution module to follow the heating execution module to perform atomized spraying on the adjustable area according to the adjustment parameters.
[0063] It should be noted that after the heating execution module heats the adjustable area, the rapid cooling execution module can be immediately controlled to perform atomized spraying on the adjustable area. 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.
[0064] 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.
[0065] Meanwhile, by adjusting parameters for scenario-based and programmable local fine-tuning correction, local deformation in the out-of-tolerance adjustable area can be adjusted in a fixed-point, quantitative, and traceable manner. This controls heat input while reducing the range of the heat-affected zone, ensuring that the structural dimensions and geometry of the welded components after adjustment meet the assembly and usage requirements.
[0066] Based on any of the above embodiments, after controlling welding deformation, the method further includes: Obtain the three-dimensional point cloud data of the adjusted welded component; The verification result is obtained by repeating the step of identifying the out-of-tolerance adjustable area and its deformation amount from the key adjustment reference points of the welded component to be adjusted based on the three-dimensional point cloud data; the verification result is used to determine whether to repeat the welding deformation adjustment step of the welded component.
[0067] The method for obtaining the three-dimensional point cloud data of the welded component after adjustment is basically the same as the method for obtaining the three-dimensional point cloud data of the welded component to be adjusted, and will not be described again here.
[0068] It should be noted that the step of identifying the out-of-tolerance adjustable area and its deformation amount from the key adjustment reference points of the welded component to be adjusted based on the three-dimensional point cloud data can be repeated to obtain the verification result of whether the welding deformation of the welded component has been eliminated. If so, proceed to the next process; otherwise, repeat the welding deformation adjustment steps of the welded component.
[0069] Understandably, after adjusting the out-of-tolerance adjustable area of the welded component, the verification results are dynamically fed back by repeatedly identifying the out-of-tolerance adjustable area and its deformation from the key adjustment reference points of the welded component to be adjusted based on the three-dimensional point cloud data. This can be matched and aligned with the structural characteristics of the welded component to form a data closed loop by using the tolerance envelope to identify the out-of-tolerance adjustable area and its deformation from the key adjustment reference points of the welded component to be adjusted. This achieves adaptive feedback control of welding deformation adjustment, thereby improving the accuracy, consistency and automation level of welded component repair.
[0070] Figure 2 This is a schematic diagram of the architecture 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.
[0071] Three-dimensional point cloud data of the welded component to be repaired is collected and input into a springback prediction model. Deep learning analysis and intelligent identification of key repair reference points are performed on the 3D point cloud data to obtain the springback amount of the key repair reference points of the welded component to be repaired, as output by the springback prediction model. A post-weld point cloud model of the welded component to be repaired is generated based on the 3D point cloud data. A standard design model of the welded component is obtained, and the post-weld point cloud model of the welded component is matched and aligned with the standard design model according to the structural characteristics of the welded component. The tolerance envelope of the standard design model is determined. The post-weld point cloud model of the welded component is compared with the standard design model, and the out-of-tolerance adjustable areas and their deformation amounts are identified from the key repair reference points of the welded component to be repaired based on the tolerance envelope, in order to determine the corresponding repair strategy. The heating execution module and the rapid cooling execution module corresponding to the adjustment strategy are determined. The heating execution module is controlled to heat the adjustable area out of tolerance according to the adjustment parameters. The rapid cooling execution module is controlled to follow the heating execution module to perform atomized spraying on the adjustable area out of tolerance according to the adjustment parameters, so as to realize the coupled control of high frequency heating and atomized spraying. The process involves acquiring three-dimensional point cloud data of the welded component after adjustment, and repeating the steps of identifying the out-of-tolerance adjustable area and its deformation from the key adjustment reference points of the welded component to be adjusted based on the three-dimensional point cloud data to obtain verification results. This achieves closed-loop feedback of process data and re-evaluation of accuracy. If the verification results indicate that the welding deformation adjustment steps of the welded component need to be repeated, the coupled shape control of high-frequency heating and atomized spraying can be repeated. If the verification results indicate that the welding deformation adjustment steps of the welded component do not need to be repeated, the adjustment can be completed.
[0072] 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.
[0073] Figure 3 This is a schematic diagram of the welding deformation control system provided by the present invention, as shown below. Figure 3 As shown, the system includes the following modules: The data acquisition module 310 is used to acquire three-dimensional point cloud data of the welded component to be repaired; The springback prediction module 320 is used to input the three-dimensional point cloud data into the springback prediction model to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted output by the springback prediction model; wherein, the springback prediction model is trained based on the sample three-dimensional point cloud data and the springback amount of the key adjustment reference point of the sample welded component to be adjusted. The deformation control module 330 is used to identify the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted, and generate adjustment parameters for adjusting the out-of-tolerance adjustable area according to the adjustment springback amount corresponding to the out-of-tolerance adjustable area, so as to control the welding deformation.
[0074] 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.
[0075] 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.
[0076] 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: Collect three-dimensional point cloud data of the welded components to be repaired; The three-dimensional point cloud data is input into the springback prediction model to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted, which is output by the springback prediction model; wherein, the springback prediction model is trained based on the sample three-dimensional point cloud data and the springback amount of the key adjustment reference point of the sample welded component to be adjusted. The out-of-tolerance adjustable area is identified from the key adjustment reference points of the welded component to be adjusted, and adjustment parameters for adjusting the out-of-tolerance adjustable area are generated according to the adjustment springback amount corresponding to the out-of-tolerance adjustable area, so as to control the welding deformation.
2. The welding deformation control method according to claim 1, characterized in that, The step of inputting the three-dimensional point cloud data into the springback prediction model to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted, output by the springback prediction model, includes: Based on the feature recognition layer of the springback prediction model, the three-dimensional point cloud data is processed to obtain the feature representation of the key adjustment reference points of the welded component to be adjusted. Based on the springback prediction layer of the springback prediction model, the feature representation is parsed to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted.
3. The welding deformation control method according to claim 1, characterized in that, The process of identifying the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted includes: A post-weld point cloud model of the welded component to be repaired is generated based on the three-dimensional point cloud data. Obtain a standard design model of the welded component to compare the post-weld point cloud model of the welded component with the standard design model, and identify the out-of-tolerance adjustable area and its deformation from the key adjustment reference points of the welded component to be adjusted.
4. The welding deformation control method according to claim 3, characterized in that, The comparison of the post-weld point cloud model of the welded component with the standard design model includes: The post-weld point cloud model of the welded component is matched and aligned with the standard design model based on the structural characteristics of the welded component.
5. The welding deformation control method according to claim 3, characterized in that, The comparison of the post-weld point cloud model of the welded component with the standard design model, and the identification of out-of-tolerance adjustable areas from the key adjustment reference points of the welded component to be adjusted, includes: Determine the tolerance envelope of the standard design model; By comparing the post-weld point cloud model of the welded component with the standard design model, the out-of-tolerance adjustable area and its deformation amount are identified from the key adjustment reference points of the welded component to be adjusted based on the tolerance envelope.
6. The welding deformation control method according to claim 3, characterized in that, The step of generating adjustment parameters for adjusting the adjustable region based on the adjustment rebound amount corresponding to the adjustable region includes: The corresponding adjustment strategy is determined based on the adjustment rebound amount and the deformation amount corresponding to the out-of-tolerance adjustable area. The adjustment execution equipment for the adjustable region of the out-of-tolerance is determined according to the adjustment strategy, and the adjustment parameters for adjusting the adjustable region of the out-of-tolerance are determined.
7. The welding deformation control method according to claim 6, characterized in that, The step of determining the adjustment execution equipment for the adjustable region of excess tolerance according to the adjustment strategy, and the adjustment parameters for adjusting the adjustable region of excess tolerance, include: Determine the maintenance execution equipment corresponding to the maintenance strategy; The adjustment parameters for the adjustment execution device to adjust the adjustable area of the out-of-tolerance are determined based on the adjustment rebound amount and the deformation amount corresponding to the out-of-tolerance adjustable area.
8. The welding deformation control method according to claim 6, characterized in that, The adjustment and maintenance execution equipment includes a heating execution module and a rapid cooling execution module; The process of controlling welding deformation includes: The heating execution module is controlled to heat the adjustable area according to the adjustment parameters, and the rapid cooling execution module is controlled to follow the heating execution module to perform atomized spraying on the adjustable area according to the adjustment parameters.
9. The welding deformation control method according to claim 1, characterized in that, After controlling welding deformation, the method further includes: Obtain the three-dimensional point cloud data of the adjusted welded component; The verification result is obtained by repeating the step of identifying the out-of-tolerance adjustable area and its deformation amount from the key adjustment reference points of the welded component to be adjusted based on the three-dimensional point cloud data; the verification result is used to determine whether to repeat the welding deformation adjustment step of the welded component.
10. A welding deformation control system, characterized in that, include: The data acquisition module is used to acquire three-dimensional point cloud data of the welded components to be repaired; The springback prediction module is used to input the three-dimensional point cloud data into the springback prediction model to obtain the springback amount of the key adjustment reference point of the welded component to be adjusted, which is output by the springback prediction model; wherein, the springback prediction model is trained based on the sample three-dimensional point cloud data and the springback amount of the key adjustment reference point of the sample welded component to be adjusted. The deformation control module is used to identify the out-of-tolerance adjustable area from the key adjustment reference points of the welded component to be adjusted, and generate adjustment parameters for adjusting the out-of-tolerance adjustable area according to the adjustment springback amount corresponding to the out-of-tolerance adjustable area, so as to control the welding deformation.