Friction stir welding control method and system based on welding analysis model

Abstract

The invention provides a friction stir welding control method and system based on a welding analysis model, and relates to the technical field of friction stir welding. According to the technical scheme provided by the invention, the region division method based on the morphological characteristics and the structural characteristics of the cracks enables the repair process to adopt differentiated processing strategies according to the crack characteristics of different regions. The first repair scheme is preferentially implemented in the key area, and the crack extension information and the welding quality information are evaluated in combination with the welding analysis model, so that the crack propagation risk in the repair process can be effectively controlled. And after the repair effect of the key area meets the preset requirement, a second repair scheme is implemented on the general area, the partition and step-by-step repair strategy is based on real-time monitoring and analysis of multi-modal images and welding information, the repair process has the self-adaptive adjustment capacity, the problems in the repair process can be found and solved in time, and the repair efficiency is improved. And the welding effect of friction stir welding is remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of friction stir welding, and particularly relates to a friction stir welding control method and system based on a welding analysis model. Background Art

[0002] Friction stir welding is a solid-state joining technology. Its working principle is to utilize the frictional heat and plastic deformation generated between a high-speed rotating stirring head and workpiece material, so that the materials in the joining area are softened and fully mixed, thereby realizing the connection of metal materials. This welding method has the advantages of small deformation, low residual stress, and no need for filler materials, and is particularly suitable for materials such as aluminum alloys that are difficult to use traditional fusion welding. Since the materials are always in a solid state during the friction stir welding process, the weld microstructure is fine and uniform, and the mechanical properties are excellent. Therefore, it has broad application prospects in the field of crack repair.

[0003] When using friction stir welding for crack repair in related technologies, a unified welding parameter is usually adopted to repair the entire crack area. This method not only easily causes crack propagation. At the same time, due to the lack of effective monitoring of the welding quality during the crack repair process, problems such as insufficient welding and insufficient joint strength are likely to occur. In summary, the friction stir welding control method in related technologies has the defect of poor welding effect. Summary of the Invention

[0004] The present application provides a friction stir welding control method and system based on a welding analysis model, which can improve the welding repair effect.

[0005] In a first aspect, the present application provides a friction stir welding control method based on a welding analysis model, and the method includes: Obtain multi-modal images of the crack area, and extract the crack morphology features and crack structure features in the multi-modal images; According to the crack morphology features and crack structure features, divide the crack area into a key area and a general area; Generate a first repair plan for the friction stir welding method of the key area, and control the stirring head to execute the first repair plan; Respectively obtain the image information of the crack area and the welding information of the key area, and input the image information and the welding information into the welding analysis model to obtain crack extension information and welding quality information; When both the crack extension information and the welding quality information meet the preset welding requirements, generate a second repair plan for the friction stir welding method of the general area, and control the stirring head to execute the second repair plan.

[0006] By adopting the above technical solution, the regional division method based on crack morphological characteristics and structural characteristics enables the repair process to adopt differential treatment strategies according to the crack characteristics of different regions. By preferentially implementing the first repair plan for key regions and combining the welding analysis model to evaluate the crack extension information and welding quality information, the risk of crack propagation during the repair process can be effectively controlled. After the repair effect of the key region meets the preset requirements, the second repair plan is implemented for the general region. This step-by-step repair strategy based on the real-time monitoring and analysis of multimodal images and welding information endows the repair process with the ability of adaptive adjustment, can timely detect and solve problems during the repair process, and significantly improves the welding effect of friction stir welding.

[0007] Optionally, the crack morphological characteristics include crack shape characteristics and crack width characteristics, and the crack structural characteristics include crack depth characteristics and crack surface characteristics. Dividing the crack region into key regions and general regions according to the crack morphological characteristics and crack structural characteristics includes: Based on the crack morphological characteristics, identify the main path and branch paths of the crack region; According to the crack width characteristic and the crack depth characteristic, calculate the product of the crack width and crack depth of the main path, and determine the main path with the product greater than the preset first threshold as the first key region; Based on the crack surface characteristic, determine the surface curvature of the crack region, and determine the second key region where the crack surface is in a bulging state or a concave state according to the surface curvature; Determine the first key region and the second key region as key regions, and divide the region other than the key regions in the crack region into general regions.

[0008] By adopting the above technical solution, identifying the main path and branch paths of the crack, and combining the calculation of the product of the crack width and depth, the harm degree of the crack can be accurately judged. At the same time, based on the curvature analysis of the crack surface characteristic, the bulging or concave region with stress concentration can be identified. By dividing the main path region with high harm degree and the surface deformation region with high stress concentration into key regions, targeted repair measures can be implemented, thereby improving the welding effect of subsequent friction stir welding.

[0009] Optionally, generating the first repair plan for the friction stir welding method of the key region and controlling the stirring head to execute the first repair plan includes: Obtain the material properties of the key region, and determine the model parameters of the stirring head used for welding by the friction stir welding method; Determine the welding parameters of the stirring head according to the crack morphology characteristics and crack structure characteristics of the key area, where the welding parameters include rotational speed, traveling speed, downward pressure depth, and tilt angle; Obtain the crack direction of the key area, and plan the welding path of the key area according to the crack direction; Generate a first repair plan for the friction stir welding method of the key area according to the model parameters of the stirring head, the welding parameters, and the welding path, and control the stirring head to execute the first repair plan.

[0010] By adopting the above technical solutions, the material properties of the key area can be obtained, and the most suitable stirring head model can be selected to ensure that the geometric characteristics of the stirring tool match the material properties. Based on the morphological and structural characteristics of the crack, welding parameters such as rotational speed, traveling speed, downward pressure depth, and tilt angle are determined, realizing precise control of heat input and plastic deformation during the welding process. Planning the welding path in combination with the crack direction ensures that the spatial position relationship between the stirring head and the crack is always in the optimal state. This unified planning method of stirring head model parameters, welding parameters, and welding path establishes the correlation between material properties, crack characteristics, and welding processes, enabling the repair plan to fully adapt to the actual conditions of the key area. By controlling the stirring head to strictly execute the generated first repair plan, a stable and reliable repair effect can be ensured for the key area, significantly improving the quality level of friction stir welding repair.

[0011] Optionally, before generating the first repair plan for the friction stir welding method of the key area and controlling the stirring head to execute the first repair plan, it further includes: When there are multiple key areas, obtain the physical structure of the workpiece in the crack area; Analyze the stress distribution in the crack area according to the physical structure of the workpiece, and determine the priority order of each key area in descending order of the stress distribution.

[0012] By adopting the above technical solutions, the physical structure of the workpiece in the crack area is obtained. Combining with the stress distribution analysis, the stress levels borne by different key areas can be accurately identified. Determining the priority order of each key area in descending order of the stress distribution enables the areas with higher stress to be repaired first, and this repair order arrangement based on the stress state effectively reduces the risk of secondary damage in the high-stress areas.

[0013] Optionally, the welding analysis model includes a crack analysis sub-model and a welding quality inspection sub-model. The method of respectively obtaining the image information of the crack area and the welding information of the key area, and inputting the image information and the welding information into the welding analysis model to obtain crack extension information and welding quality information includes: Obtain the image information of the crack area after implementing the first repair plan; Input the multimodal image before welding and the image information into the crack analysis sub-model, and detect whether new cracks are initiated or the original cracks expand during the welding process through image comparison, and generate crack extension information; Collect the welding information of the key area in real time during the welding process; Input the welding information into the welding quality inspection sub-model, and generate the welding quality information of the key area through process parameter matching analysis.

[0014] By adopting the above technical solution, obtaining the image information before and after welding and inputting it into the crack analysis sub-model can timely detect the formation of new cracks or the expansion of original cracks during the welding process, providing a reliable means for monitoring the crack evolution behavior. At the same time, by collecting welding information in real time and inputting it into the welding quality inspection sub-model, the dynamic evaluation of the matching of welding process parameters is realized, ensuring that the welding process is always in the optimal state. This analysis method based on the dual sub-models organically combines crack monitoring and quality inspection, which can not only comprehensively evaluate the repair effect, but also timely detect potential quality problems.

[0015] Optionally, the welding information includes axial stress, transverse shear stress, plastic strain distribution and temperature field data. The inputting the welding information into the welding quality inspection sub-model and generating welding quality information through process parameter matching analysis includes: Input the axial stress, the transverse shear stress, the plastic strain distribution and the temperature field data into the welding quality inspection sub-model; Calculate the deviation value between the axial stress and the preset axial stress threshold, and generate an axial stress matching degree index; Calculate the ratio of the transverse shear stress to the critical shear stress based on the mechanical properties parameters of the material, and generate a shear stress safety factor; Analyze the spatial gradient characteristics of the plastic strain distribution, and calculate a strain uniformity index, where the strain uniformity index is used to characterize the plastic deformation consistency of the key area; Match the temperature field data with the standard welding temperature field distribution, and calculate a temperature field similarity coefficient; Generate the welding quality information of the key area based on the axial stress matching degree index, the shear stress safety factor, the strain uniformity index and the temperature field similarity coefficient.

[0016] By adopting the above technical solutions, the deviation value between the axial stress and the preset threshold can be calculated to evaluate the rationality of the welding stress; by calculating the ratio of the transverse shear stress to the critical shear stress, the shear safety state of the material can be judged; by analyzing the spatial gradient characteristics of the plastic strain distribution, the uniformity of the plastic deformation can be evaluated; by the matching analysis of the temperature field data and the standard distribution, the rationality of the heat input can be evaluated. This multi-index collaborative evaluation method comprehensively considers key factors such as the stress state, plastic deformation, and temperature distribution, and forms a complete evaluation system including the axial stress matching degree index, shear stress safety factor, strain uniformity index, and temperature field similarity coefficient. By comprehensively analyzing these indexes to generate welding quality information, it can not only comprehensively reflect the performance state of the welded joint, but also provide a reliable basis for optimizing the welding process parameters, significantly improving the accuracy and reliability of the welding quality evaluation.

[0017] Optionally, the preset welding requirements include the first welding requirement and the second welding requirement. When both the crack extension information and the welding quality information meet the preset welding requirements, a second repair plan for the friction stir welding method in the general area is generated, and the control of the stirring head to execute the second repair plan includes: Based on the crack extension information, verify whether the welding in the key area inhibits crack propagation. When the crack propagation length is less than the preset second threshold, it is determined that the first welding requirement is met; Compare the welding quality information with the corresponding preset third threshold to judge whether the welding quality information meets the second welding requirement; When both the first welding requirement and the second welding requirement are met, extract the crack morphology characteristics and crack structure characteristics of the general area; Adjust the welding parameters of the stirring head according to the crack characteristics of the general area to generate a second repair plan with at least one strength level lower than the first repair plan; Control the stirring head to perform repair welding on the general area according to the second repair plan, and monitor the welding quality information at the joint between the general area and the adjacent key area in real time during the welding process.

[0018] By adopting the above technical solutions, the double verification of the crack extension information and the welding quality information ensures that the repair of the key area achieves the expected effect. By comparing the crack propagation length with the preset second threshold to verify the crack inhibition effect and performing matching analysis on the welding quality information and the preset third threshold, a comprehensive evaluation of the repair quality is realized. After confirming that the repair of the key area meets the double requirements, the welding parameters are adjusted based on the crack characteristics of the general area. By reducing the repair strength level, both the repair effect and the repair efficiency are improved.

[0019] Second aspect, the present application provides a friction stir welding control system based on a welding analysis model, the system comprising: A feature extraction module, configured to obtain a multi-modal image of a crack region, and extract crack morphology features and crack structure features from the multi-modal image; A region division module, configured to divide the crack region into a key region and a general region according to the crack morphology features and the crack structure features; A first execution module, configured to generate a first repair plan for the friction stir welding method of the key region, and control the stirring head to execute the first repair plan; An analysis module, configured to respectively obtain image information of the crack region and welding information of the key region, and input the image information and the welding information into the welding analysis model to obtain crack extension information and welding quality information; A second execution module, configured to generate a second repair plan for the friction stir welding method of the general region when both the crack extension information and the welding quality information meet preset welding requirements, and control the stirring head to execute the second repair plan.

[0020] Third aspect, the present application provides a computer storage medium, the computer storage medium storing multiple instructions, the instructions being adapted to be loaded and executed by a processor to perform any one of the above methods.

[0021] Fourth aspect, the present application provides an electronic device, comprising a processor, a memory and a transceiver, the memory being used to store instructions, the transceiver being used to communicate with other devices, and the processor being used to execute the instructions stored in the memory so that the electronic device performs any one of the above methods.

[0022] In summary, the beneficial effects brought by the technical solution of the present application include: By adopting the above technical solution, the region division method based on crack morphology features and structural features enables the repair process to adopt a differentiated processing strategy according to the crack characteristics of different regions. By preferentially implementing the first repair plan for the key region and combining the welding analysis model to evaluate the crack extension information and the welding quality information, the risk of crack propagation during the repair process can be effectively controlled. When the repair effect of the key region meets the preset requirements, the second repair plan is then implemented for the general region. This step-by-step repair strategy based on the real-time monitoring and analysis of multi-modal images and welding information enables the repair process to have an adaptive adjustment ability, can timely discover and solve problems during the repair process, and significantly improves the welding effect of friction stir welding. Description of the Drawings

[0023] Figure 1It is a schematic flowchart of a friction stir welding control method based on a welding analysis model according to an embodiment of the present application; Figure 2 It is a schematic structural diagram of a friction stir welding control system based on a welding analysis model according to an embodiment of the present application; Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0024] Explanation of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed implementation manners

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0026] In the description of the embodiments of the present application, words such as "exemplary", "for example" or "for illustration" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary", "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary", "for example" or "for illustration" aims to present relevant concepts in a specific manner.

[0027] In the description of the embodiments of the present application, the meaning of the term "plurality" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0028] Please refer to Figure 1 , which is a schematic flowchart of a friction stir welding control method based on a welding analysis model provided by an embodiment of the present application. This method can be implemented depending on a computer program, can be implemented depending on a single-chip microcomputer, or can run on a friction stir welding control system based on a von Neumann architecture and based on a welding analysis model. This computer program can be integrated in an application or can run as an independent tool application. The following will make a detailed description of the specific steps of the friction stir welding control method based on the welding analysis model.

[0029] S101: Obtain the multimodal images of the crack area, and extract the crack morphology features and crack structure features in the multimodal images; Among them, the crack area refers to the cracking position and its surrounding area on the surface of metal workpieces such as aluminum alloy and magnesium alloy that are suitable for repair by friction stir welding process. Due to factors such as fatigue, stress concentration, and material defects, this area not only includes the morphological features of the crack itself, but also the affected material structure around the crack.

[0030] Among them, the crack morphology features refer to the appearance features presented by the crack on the surface of the workpiece, mainly including plane features such as the external contour, trend, length, surface width, and crack propagation path of the crack.

[0031] Among them, the crack structure features refer to the three-dimensional space features of the crack area, mainly including three-dimensional geometric features such as the depth distribution, surface curvature, crack cross-sectional shape, and crack propagation direction of the crack. By analyzing the three-dimensional solid model constructed from the multimodal images, specific depth values, surface flatness and other spatial information of the crack area can be obtained.

[0032] In this embodiment, due to the complexity of the crack information, a single image acquisition method is difficult to comprehensively reflect all the features of the crack. Therefore, multiple imaging devices are used to collect images of the crack area to obtain multimodal images including visible light images, infrared thermal imaging images, ultrasonic images, etc. These images of different modalities can reflect the characteristic information of the crack from different angles. Among them, the visible light image is mainly used to observe the surface features of the crack, the infrared thermal imaging can reflect the temperature distribution and the internal state of the material in the crack area, and the ultrasonic image can detect the depth information of the crack. The obtained multimodal images are input into the image recognition system, and edge detection algorithms are used to extract the morphological features such as the shape, trend, and length of the crack, and the structural features such as the depth distribution and surface curvature of the crack are obtained by combining the depth information analysis.

[0033] S102: Divide the crack area into key areas and general areas according to the crack morphology features and crack structure features; Among them, the key area refers to a specific part in the crack area with a higher priority for welding repair. It can be understood that: based on the quantitative analysis of the crack morphology features and structural features, the area is identified as the area that needs to be processed first and uses enhanced welding parameters. The division criterion is that the crack features in this area indicate that if not processed first, it will lead to a significant increase in the risk of crack propagation during welding or the repair quality not meeting the standard.

[0034] Among them, the general area refers to the remaining part of the crack area except the key area. It can be understood that: based on the collaborative analysis of crack morphology characteristics and structural characteristics, the area identified as having a relatively low welding repair priority, whose crack characteristics indicate that the repair of this area can be completed in the key area and after being verified by the welding analysis model, can be safely implemented using standard or downgraded welding parameters.

[0035] In the embodiment of the present application, the division of the crack area is based on the collaborative analysis of crack morphology characteristics and crack structural characteristics. By quantitatively evaluating the geometric characteristics and mechanical effects of the crack, the repair area is differentially processed to achieve precise control. Specifically in implementation, first, a multi-modal imaging system is used to extract the topological structure data of the crack, including but not limited to the distribution of crack width along the path, depth profile characteristics, and surface morphology curvature. For the section where the product of the crack width and depth exceeds the material-related threshold, the significantly increased cross-sectional characteristic quantity indicates that there is a high risk of stress concentration in this area. If not processed preferentially, it may induce secondary crack propagation under the action of the welding thermal cycle. Therefore, it is designated as the first key area. At the same time, the arched or sunken morphology areas identified based on surface curvature analysis, because they will cause poor contact between the stirring head and the substrate and generate lack of fusion defects, these areas are listed as the second key area. For the remaining crack sections not covered by the above criteria, whose geometric characteristics indicate that the mechanical response caused by heat input is relatively controllable, they are classified as general areas.

[0036] On the basis of the above embodiment, as an optional implementation manner, the division method of the key area and the general area can be specifically implemented through the following steps S201 - S204.

[0037] S201: Based on the crack morphology characteristics, identify the main path and branch paths of the crack area; In specific implementation, the crack area usually presents a complex network structure, including the main propagation direction and secondary branch directions. To accurately identify the main path and branch paths of the crack area, first, a multi-modal image acquisition device is used to obtain the image information of the crack area. The multi-modal images include visible light images, infrared thermal imaging images, and ultrasonic scanning images. The multi-modal images are denoised and enhanced through image preprocessing techniques to extract the edge contour information of the crack. Subsequently, a skeleton extraction algorithm is used to thin the processed image, simplifying the crack network into a single-pixel-width skeleton line for subsequent path recognition.

[0038] Based on the crack skeleton line, the minimum spanning tree algorithm is used to construct a crack propagation network. The starting point of the crack is set as the root node, and the main direction of crack propagation is determined by calculating the connectivity weights between nodes. On this basis, morphological analysis methods are used to extract the shape characteristics of the crack, including the extension length, curvature change, and bifurcation characteristics of the crack. Among them, the path with a larger extension length and a gentle curvature change is identified as the main path, and the path with a bifurcation connection to the main path and a relatively short extension length is identified as the branch path.

[0039] S202: According to the crack width feature and the crack depth feature, calculate the product of the crack width and the crack depth of the main path, and determine the main path with the product greater than the preset first threshold as the first key area; Detection points are set at fixed intervals on the main path, and the crack width data and crack depth data of each detection point are collected separately by the detection device. Calculate the product value of the crack width and the crack depth at each detection point according to the collected data to form crack damage distribution data, which characterizes the damage change of the crack along the main path. Compare the crack damage distribution data with the preset first threshold. When the product values of multiple consecutive detection points are all greater than the preset first threshold, delimit this section of the main path and its surrounding affected areas as the first key area.

[0040] S203: Determine the surface curvature of the crack area based on the crack surface feature, and determine the second key area where the crack surface is in a domed state or a sunken state according to the surface curvature; Among them, the crack surface feature refers to the geometric morphological features of the crack area surface, including features such as surface height distribution, local concavity and convexity, and surface deformation state.

[0041] Among them, the surface curvature refers to the degree of deviation of the crack area surface from the plane state, which is quantitatively characterized by calculating the surface curvature, mainly including two indicators: Gaussian curvature and mean curvature. The Gaussian curvature is the product of the principal curvatures, and the mean curvature is the arithmetic mean of the principal curvatures.

[0042] Among them, the domed state refers to the deformation state in which the crack surface bulges upward relative to the reference plane, usually caused by local plastic deformation of the material due to internal stress; the sunken state refers to the deformation state in which the crack surface sinks downward relative to the reference plane, which is often related to internal crack propagation and material damage.

[0043] A variety of detection means are used to analyze the surface characteristics of the crack, and multi-dimensional measurement data including laser three-dimensional scan data, digital speckle images, surface strain nephograms, etc. are obtained. These different types of measurement data can reflect the deformation characteristics of the crack surface from different angles. Among them, laser three-dimensional scanning is mainly used to obtain the point cloud data of the surface contour, digital speckle images can analyze the surface strain distribution state, and surface strain nephograms can display the gradient distribution of deformation. The obtained measurement data is input into the surface analysis system, and the local surface curvature is calculated through the least squares surface fitting algorithm, and the abnormal deformation of the surface is determined by combining the principal curvature analysis. For the area with abnormal curvature, the arching or sinking state is further determined by combining the strain distribution, so as to identify the second key area that needs to be focused on.

[0044] S204: Determine the first key area and the second key area as the key areas, and divide the area in the crack area except the key areas into general areas.

[0045] In this embodiment, since there are significant differences in the damage degree and repair difficulty of different areas, a strategy of zoned governance needs to be adopted for welding repair. Specifically, first, the spatial positions of the first key area obtained by crack size calculation and the second key area obtained by surface curvature analysis are marked, and the boundary range of the key area is demarcated on the workpiece surface using a special marking pen. On this basis, the remaining part of the crack area that is not marked as a key area is determined as a general area, forming a complete area classification map.

[0046] S103: Generate a first repair plan for the friction stir welding method in the key area, and control the stirring head to execute the first repair plan; During the specific implementation, the analysis results of the key area in the previous step are first used. Based on the material properties of the key area that have been obtained, the system will select the model parameters of the stirring head to ensure that the selected stirring head can adapt to the welding requirements of the specific material and can effectively handle the crack characteristics of the key area. Next, the welding parameters of the stirring head will be carefully determined according to the crack morphology and crack structure characteristics of the key area, including but not limited to rotation speed, travel speed, pressing depth and tilt angle. The setting of these parameters is intended to optimize the heat input, material flow and plastic deformation behavior during the welding process, in order to obtain the best crack closure effect and joint structure. At the same time, the crack direction of the key area is obtained, and the welding path of the key area is planned according to this crack direction to ensure that the stirring head can accurately cover and repair the entire key crack area. Finally, the system will integrate the determined stirring head model parameters, calculated welding parameters and planned welding path to generate a complete first repair plan for the stir friction welding method for the key area. Subsequently, the first repair plan is transmitted to the control system of the friction stir welding equipment, and the control system accurately drives the stirring head to perform repair welding operations on key areas according to the parameters and paths set in the plan.

[0047] On the basis of the above embodiment, as an optional implementation manner, the manner of controlling the stirring head to execute the first repair solution can be specifically implemented through the following steps S301-S304.

[0048] S301: Obtaining material properties of a key area and determining model parameters of a stirring head for friction stir welding; During implementation, the material type of the workpiece in the key area is determined, and the relevant material parameters, such as yield strength, tensile strength, melting point, and thermal conductivity, are accurately obtained. Next, based on these material parameters and the requirements of the friction stir welding process for the stir head model, a comprehensive analysis is conducted to determine the optimal stir head model parameters, primarily including geometric parameters such as the stir head shoulder diameter, taper angle, and probe length and diameter.

[0049] S302: Determine welding parameters of the stirring head based on the crack morphology and structural characteristics of the key area. The welding parameters include rotation speed, travel speed, pressing depth, and tilt angle. During specific implementation, the system analyzes the crack morphological characteristics of the key area obtained. For example, the width and overall contour of the crack affect the setting of the rotation speed and the travel speed. Wider or more complexly shaped cracks may require specific combinations of rotation speeds to generate sufficient heat and plastic material flow to ensure full filling; at the same time, the travel speed also needs to match it to ensure sufficient stirring action time and material transport per unit length. The crack depth feature in the crack structural characteristics is the key basis for determining the downward pressure depth. The downward pressure depth must be set to enable the stirring head to effectively act on the crack root to ensure that the original crack interface is completely eliminated. In addition, crack surface characteristics, such as the presence of oxidation or contaminants, will in turn affect the selection of the rotation speed to ensure sufficient cleaning and activation effects. The determination of the tilt angle comprehensively considers the crack morphological characteristics and the desired material flow pattern. A suitable tilt angle helps control the migration path of the plastic metal and promotes dense filling and good surface forming of the weld.

[0050] S303: Obtain the crack direction of the key area and plan the welding path of the key area according to the crack direction; During specific implementation, based on the crack direction information, combined with the crack width feature and the crack depth feature, the system plans the welding path of friction stir welding. The planning of the welding path needs to consider the following technical points: First, the welding path should maintain a certain angle with the crack direction, which can ensure that the stirring area of the stirring head can fully cover the crack area to achieve effective material plasticization and mixing. Second, when planning the path, it is necessary to consider the changes in the crack surface characteristics in the key area. When encountering a cracked surface in an arched state or a sunken state, the welding path should be adjusted accordingly to adapt to the surface topography changes. Third, the planning of the welding path also needs to consider the model parameters of the stirring head to ensure that the path planning meets the motion characteristic requirements of the stirring head.

[0051] S304: Generate a first repair plan for the friction stir welding method in the key area according to the model parameters of the stirring head, the welding parameters, and the welding path, and control the stirring head to execute the first repair plan.

[0052] The model parameters of the stirring head include the geometric dimension characteristics of the stirring head, which directly affect the material flow state during the welding process; the rotation speed, travel speed, downward pressure depth, and tilt angle in the welding parameters determine the heat input and the degree of plastic deformation; and the welding path ensures the complete coverage of the repair area.

[0053] When generating the first repair plan, it is necessary to comprehensively consider the crack morphological characteristics and crack structural characteristics in key areas, and systematically match the stirrer head model parameters with the welding parameters. First, determine the pressing depth based on the crack depth characteristics to ensure that the stirring action of the stirrer head can fully reach the bottom of the crack. Secondly, adjust the tilt angle of the stirrer head based on the crack width characteristics to obtain appropriate advance angle and working angle, and enhance the plasticization effect of the material. At the same time, it is also necessary to optimize the ratio of the rotational speed and the traveling speed according to the crack surface characteristics to avoid overheating while ensuring sufficient heat input.

[0054] Optionally, when there are multiple key areas, obtain the physical structure of the workpiece in the crack area; Analyze the stress distribution in the crack area according to the physical structure of the workpiece, and determine the priority order of each key area according to the stress distribution from large to small.

[0055] During specific implementation, first, it is necessary to obtain the physical structure information of the workpiece in the crack area, including basic information such as the geometric characteristics, structural characteristics, and material properties of the workpiece. These information are the basis for stress distribution analysis. Through the analysis of the physical structure of the workpiece, combined with the crack morphological characteristics and crack structural characteristics, the stress state borne by each key area during the service of the workpiece can be determined. Stress distribution analysis needs to consider the force characteristics of the workpiece, and at the same time, it also needs to consider the influence of the geometric discontinuity of the workpiece structure on the stress distribution. On this basis, calculate the stress levels of each key area, and sort these areas according to the stress distribution from large to small, so as to determine the priority order of repair.

[0056] S104: Respectively obtain the image information of the crack area and the welding information of the key area, and input the image information and the welding information into the welding analysis model to obtain crack extension information and welding quality information; The image information of the crack area refers to the information obtained by imaging the entire crack area through a multi-modal imaging device. These information contain visually recognizable characteristics such as the appearance characteristics, surface topography, and regional distribution of the crack. By comparing the image information before and after welding, the change in the crack state can be intuitively observed. The welding information of the key area is the data information reflecting the welding state collected in real time by various sensors during the welding process. These information can characterize the stability and reliability of the welding process.

[0057] After inputting these two types of information into the welding analysis model, the model will generate crack extension information and welding quality information respectively. The crack extension information reflects whether the welding process has caused the expansion of the original crack or generated new cracks, which is of great significance for evaluating the effectiveness of the repair. The welding quality information comprehensively reflects the performance state of the welded joint, including the evaluation results of multiple aspects such as the integrity and strength of the joint.

[0058] Based on the above embodiments, as an alternative embodiment, the welding analysis model includes a crack analysis sub-model and a welding quality inspection sub-model, and a specific evaluation is carried out after the first repair plan is executed on the stirring head, which can be specifically realized through the following steps S401 - S404.

[0059] S401: Obtain the image information of the crack area after the first repair plan is executed; Specifically, after the welding repair of the key area of the stirring head is completed, an image acquisition device is used to image the entire crack area. The image acquisition device includes a visible light camera and an infrared camera. The surface topography information of the crack area is obtained through the visible light camera, and the temperature distribution information of the crack area is obtained through the infrared camera. When obtaining the image, first adjust the position and angle of the image acquisition device to ensure that its field of view can completely cover the crack area and maintain the same imaging conditions as before welding. Subsequently, control the image acquisition device to perform synchronous acquisition to obtain the multi-modal image information of the crack area after welding. This image information not only includes the surface features of the welded repair area, but also reflects the possible generation of new cracks or the propagation of original cracks during the welding process.

[0060] S402: Input the multi-modal image before welding and the image information into the crack analysis sub-model, and detect whether new cracks are initiated or the original cracks are extended during the welding process through image comparison, and generate crack extension information; In specific implementation, first perform registration processing on the multi-modal image obtained before welding and the image information after welding to ensure that the two sets of images are accurately corresponding in spatial position. Subsequently, extract the crack features in the two sets of images through image processing techniques, including information such as the position, length, and direction of the cracks. Based on the feature extraction, use the image difference algorithm to compare and analyze the crack features before and after welding to identify possible crack changes during the welding process. By calculating the offset of the crack tip position, the extent of the original crack propagation can be quantitatively evaluated; by detecting whether new crack features appear around the welding area, it can be determined whether new cracks are initiated during the welding process.

[0061] S403: Real-time collect the welding information of the key area during the welding process; Specifically, during the implementation of the first repair plan by the stirring head, the welding status of the key area is continuously monitored through the sensor system configured on the welding equipment. The sensor system includes a stress sensor, a temperature sensor, and a strain sensor, which are respectively used to collect the axial stress, transverse shear stress, temperature field data, and plastic strain distribution information during the welding process. During the welding process, the sensor system continuously collects data at a preset sampling frequency to ensure that transient changes during the welding process can be captured. These sensors are arranged at key positions around the stirring head to obtain the most representative welding parameter information. Through the real-time data acquisition system, various types of information collected are synchronously integrated to form a complete welding information data stream.

[0062] S404: Input the welding information into the welding quality inspection sub-model, and generate the welding quality information of the key area through process parameter matching analysis.

[0063] In the specific implementation process, it is first necessary to preprocess the collected welding information, including signal filtering and data standardization, to eliminate possible interference factors and ensure the reliability of the data. Subsequently, based on the process parameter matching analysis method, the processed welding information is compared and analyzed with the standard welding process parameters to evaluate the matching degree between the actual welding parameters and the ideal parameters. Through this parameter matching analysis, the stability and reliability of the welding process can be comprehensively evaluated, and comprehensive information reflecting the welding quality status of the key area can be generated.

[0064] Based on the above embodiments, as an optional implementation manner, the welding information includes axial stress, transverse shear stress, plastic strain distribution, and temperature field data, and step S404 specifically includes steps S501 - S506.

[0065] S501: Input the axial stress, transverse shear stress, plastic strain distribution, and temperature field data into the welding quality inspection sub-model; Among them, axial stress refers to the stress generated along the welding direction during the stir friction welding process, which can be understood in the embodiment of the present application as a physical quantity used to characterize the stress state of the material during the welding process; transverse shear stress refers to the shear stress perpendicular to the welding direction, which can be understood in the embodiment of the present application as a physical quantity used to characterize the stress state of the material during the welding process; plastic strain distribution refers to the permanent deformation distribution state of the material during the welding process, which can be understood in the embodiment of the present application as a distribution feature used to characterize the flow and deformation degree of the material; temperature field data refers to the temperature distribution at various positions of the workpiece during the welding process, which can be understood in the embodiment of the present application as temperature information used to reflect the welding heat input and heat conduction characteristics; welding quality inspection sub-model refers to an analysis tool for evaluating welding quality, which can be understood in the embodiment of the present application as a processing unit used to comprehensively analyze welding process parameters and evaluate welding quality.

[0066] In practice, the collected data on axial stress, transverse shear stress, plastic strain distribution, and temperature field are first preprocessed. This preprocessing process includes three steps: data cleaning, standardization, and outlier removal. The data cleaning stage removes noise and redundant data generated during the acquisition process. Standardization converts different physical quantities into dimensionless parameters with a unified dimension, eliminating the impact of dimensional differences on the analysis results. Outlier removal filters out abnormal data points that fall outside the normal process parameter range by setting a reasonable fluctuation range.

[0067] The preprocessed data is fed into the welding quality inspection submodel. The submodel's input layer contains four data channels, one for axial stress, the other for transverse shear stress, the other for plastic strain distribution, and the other for temperature field. The model's training set consists of a large amount of historical welding data, derived from experimental records under various welding conditions and labeled with corresponding weld quality grades. By analyzing the training data, a correspondence between various physical quantities and weld quality is established, forming a welding quality assessment criterion.

[0068] In practical applications, the welding quality inspection sub-model performs a multi-dimensional analysis of input physical quantities: first, it assesses whether each physical quantity is within a reasonable range; then, it analyzes the coupling relationships between physical quantities, including the synergy between stress and temperature fields, and the matching degree between plastic deformation and stress distribution; finally, it comprehensively judges the welding quality status based on established evaluation criteria. This comprehensive analysis method based on multiple physical quantities can comprehensively reflect the welding status from the perspective of material mechanical properties and thermal-mechanical coupling, and effectively identify problems such as stress anomalies and uneven deformation during the welding process.

[0069] S502: Calculate the deviation between the axial stress and a preset axial stress threshold value to generate an axial stress matching index; The axial stress matching degree index refers to an evaluation parameter that reflects the degree of conformity between the actual axial stress and the preset axial stress threshold. In the embodiments of the present application, it can be understood as a technical index used to quantitatively evaluate the axial stress control level during the welding process. This index is obtained by calculating the deviation value between the actual axial stress and the preset axial stress threshold.

[0070] During specific implementation, the axial stress threshold is set based on the welding process requirements. This threshold reflects the ideal stress state required to ensure welding quality. Subsequently, the collected actual axial stress data is preprocessed, including data smoothing and noise elimination, to improve the reliability of the data. On this basis, by calculating the deviation value between the actual axial stress and the preset axial stress threshold, quantitative stress difference information is obtained. According to the calculated deviation value and in combination with the allowable range of stress deviation, an axial stress matching degree index reflecting the stress state during the welding process is generated.

[0071] S503: Calculate the ratio of the transverse shear stress to the critical shear stress based on the material mechanical property parameters to generate a shear stress safety factor; The shear stress safety factor refers to the reciprocal of the ratio of the transverse shear stress to the critical shear stress, reflecting the ability of the material to resist shear failure during the welding process. In the embodiments of the present application, it can be understood as a quantitative index used to evaluate the safety degree of the material shear stress state during the welding process. This index is obtained by calculating the ratio of the actual transverse shear stress to the material critical shear stress and is used to characterize the shear safety margin of the material during the welding process.

[0072] During specific implementation, first determine the critical shear stress value according to the mechanical property parameters of the material to be repaired. This value characterizes the ultimate bearing capacity of the material under shear action. Subsequently, the real-time collected transverse shear stress data is preprocessed, including signal filtering and data normalization, to improve the data quality. On this basis, based on the material mechanical property parameters, calculate the ratio of the transverse shear stress to the critical shear stress to generate a shear stress safety factor. This safety factor reflects the safety margin of the material under shear action during the welding process and can intuitively characterize the safety state of the welding process.

[0073] S504: Analyze the spatial gradient characteristics of the plastic strain distribution and calculate the strain uniformity index. The strain uniformity index is used to characterize the consistency of plastic deformation in the key area; In specific implementation, first, the collected plastic strain distribution data is discretized spatially to obtain the strain values of each measurement point within the key area. Subsequently, the strain gradient between adjacent measurement points is calculated to analyze the spatial variation characteristics of the strain distribution. After obtaining the strain gradient data, by calculating the variation degree of the strain gradient within the key area, a quantitative index reflecting the uniformity of plastic deformation, namely the strain uniformity index, is obtained. This index can effectively characterize the degree of consistency of plastic deformation within the key area by evaluating the spatial distribution characteristics of the strain gradient.

[0074] S505: Match the temperature field data with the standard welding temperature field distribution and calculate the temperature field similarity coefficient. In specific implementation, first, a standard welding temperature field distribution is established according to the welding process requirements, which reflects the temperature distribution characteristics under the ideal welding state. Subsequently, the collected actual temperature field data is preprocessed, including spatial alignment and data smoothing of the temperature data, to ensure comparability with the standard temperature field. On this basis, by calculating the spatial distribution difference between the actual temperature field and the standard temperature field, the temperature field similarity coefficient is obtained. This coefficient reflects the degree of closeness between the temperature field distribution in the actual welding process and the ideal state, and can intuitively characterize the accuracy of temperature field control.

[0075] S506: Generate the welding quality information of the key area based on the axial stress matching degree index, shear stress safety factor, strain uniformity index, and temperature field similarity coefficient.

[0076] During the friction stir welding repair process, in order to comprehensively evaluate the welding quality status of the key area, it is necessary to comprehensively analyze various quality indicators. The axial stress matching degree index reflects the stress control level, the shear stress safety factor characterizes the shear safety margin of the material, the strain uniformity index reflects the consistency of plastic deformation, and the temperature field similarity coefficient reflects the rationality of the temperature field distribution. These indicators describe the quality characteristics of the welding process from different perspectives. In specific implementation, first, weight allocation is performed on these four indicators, and the corresponding weight coefficients are determined according to the influence degree of each indicator on the welding quality. Subsequently, each indicator and its weight are substituted into the quality evaluation function, and the evaluation result reflecting the comprehensive welding quality is obtained through calculation. Based on the evaluation result, welding quality information including welding quality grade, quality characteristic description, etc. is generated.

[0077] S105: When both the crack propagation information and the welding quality information meet the preset welding requirements, generate a second repair plan for the friction stir welding method in the general area and control the stirring head to execute the second repair plan.

[0078] When the crack extension information indicates that no new cracks are initiated or the original cracks do not propagate during the welding process, and the welding quality information shows that the performance of the welded joint meets the preset welding requirements, it indicates that the implementation effect of the first repair plan is good, and the repair work in the general area can continue. At this time, based on the repair experience in the key area and combined with the characteristics of the general area, a second repair plan needs to be generated. In specific implementation, first analyze the crack characteristics and material state of the general area, and combine the welding parameter optimization experience obtained in the repair of the key area to determine the friction stir welding process parameters applicable to the general area. Subsequently, according to the geometric characteristics and spatial position of the general area, plan the movement trajectory and posture of the stirring head to generate a complete second repair plan. After the plan is generated, drive the stirring head to execute the repair task according to the planned path and parameters through the control system.

[0079] Based on the above embodiments, as an alternative implementation, the preset welding requirements include the first welding requirement and the second welding requirement, and step S105 specifically includes steps S601 - S605.

[0080] S601: Verify whether the welding in the key area inhibits crack propagation based on the crack extension information. When the crack propagation length is less than the preset second threshold, it is determined that the first welding requirement is met; Among them, the first welding requirement refers to the crack inhibition standard for evaluating the welding repair effect in the key area. In the embodiments of the present application, it can be understood as a technical index for determining whether the crack propagation control is effective during the friction stir welding repair process. This requirement determines whether the welding process effectively inhibits crack propagation by comparing the crack propagation length with the preset second threshold.

[0081] In specific implementation, first analyze and process the crack extension information, extract the change data of the crack tip position before and after welding through image processing technology, and calculate the crack propagation length during the welding process. Subsequently, compare the calculated crack propagation length with the pre - set second threshold, which represents the maximum acceptable crack propagation degree. When the crack propagation length is less than the preset second threshold, it indicates that the welding process effectively inhibits crack propagation, and it is determined that the first welding requirement is met.

[0082] S602: Compare the welding quality information with the corresponding preset third threshold to determine whether the welding quality information meets the second welding requirement; In specific implementation, first compare the generated welding quality information, including the axial stress matching degree index, shear stress safety factor, strain uniformity index, temperature field similarity coefficient, etc., with the corresponding preset third threshold. These preset third thresholds represent the minimum standards that each index of welding quality needs to reach. Through comparison and analysis, determine whether the welding quality information meets the second welding requirement.

[0083] S603: When the first welding requirement and the second welding requirement are both met, extract the crack morphological features and crack structural features of the general area; In specific implementation, first confirm that the first welding requirement and the second welding requirement are both met, indicating that the repair work in the key area has achieved the expected effect. Subsequently, obtain the crack image information of the general area through the image acquisition device, and extract the morphological features and structural features of the crack from it. The crack morphological features include appearance features such as the geometric shape, orientation, and distribution density of the crack, and the crack structural features include internal features such as the depth, width, and bifurcation of the crack.

[0084] S604: Adjust the welding parameters of the stirring head according to the crack features of the general area, and generate a second repair plan with at least one strength level lower than the first repair plan; In specific implementation, first analyze the crack features of the general area, including the depth, length, and distribution of the crack, and determine the required welding strength level based on these features. Subsequently, based on the welding parameters of the first repair plan, adjust the welding process strength by reducing parameters such as the rotation speed, feed speed, and axial pressure of the stirring head to make it at least one strength level lower, thereby generating a second repair plan applicable to the general area. This parameter adjustment method based on crack features can not only ensure the repair quality but also improve the welding efficiency.

[0085] S605: Control the stirring head to perform repair welding on the general area according to the second repair plan, and monitor the welding quality information at the joint between the general area and the adjacent key area in real time during the welding process.

[0086] In specific implementation, first control the stirring head to perform welding repair on the general area according to the generated second repair plan according to the planned path and parameters. During the welding process, collect the welding quality information in real time through the sensor system, and focus on the joint between the general area and the adjacent key area. The content of real-time monitoring includes the axial stress, transverse shear stress, plastic strain distribution, and temperature field data at the joint, and judge the welding state at the joint through the change trend of these parameters.

[0087] On this basis, if the first welding requirement and / or the second welding requirement are not met, re-execute the steps of S102 - S105 until the welding requirements are met.

[0088] The following is an embodiment of the system of the present application, which can be used to execute the method embodiment of the present application. For the details not disclosed in the system embodiment of the present application, please refer to the method embodiment of the application.

[0089] Please refer to Figure 2, which shows a schematic structural diagram of a friction stir welding control system based on a welding analysis model provided by an exemplary embodiment of the present application. This system can be implemented as all or part of the system through software, hardware, or a combination of both. The friction stir welding control system based on the welding analysis model includes: A feature extraction module, configured to obtain multimodal images of a crack area and extract crack morphology features and crack structure features from the multimodal images; A region division module, configured to divide the crack area into a key area and a general area according to the crack morphology features and the crack structure features; A first execution module, configured to generate a first repair plan for the friction stir welding method of the key area and control the stirring head to execute the first repair plan; An analysis module, configured to respectively obtain image information of the crack area and welding information of the key area, and input the image information and the welding information into the welding analysis model to obtain crack extension information and welding quality information; A second execution module, configured to generate a second repair plan for the friction stir welding method of the general area and control the stirring head to execute the second repair plan when both the crack extension information and the welding quality information meet the preset welding requirements.

[0090] Based on the above embodiment, as an optional embodiment, the region division module is further configured to identify the main path and branch paths of the crack area based on the crack morphology features; calculate the product of the crack width and crack depth of the main path according to the crack width feature and crack depth feature, and determine the main path with the product greater than a preset first threshold as the first key area; determine the surface curvature of the crack area based on the crack surface features, and determine the second key area where the crack surface is in an arched state or a sunken state according to the surface curvature; determine the first key area and the second key area as the key areas, and divide the area other than the key areas in the crack area into the general area.

[0091] Based on the above embodiment, as an optional embodiment, the first execution module is further configured to obtain the material properties of the key area, and determine the model parameters of the stirring head used for welding by the friction stir welding method; determine the welding parameters of the stirring head according to the crack morphology features and crack structure features of the key area, where the welding parameters include rotational speed, travel speed, downward pressure depth, and tilt angle; obtain the crack direction of the key area, and plan the welding path of the key area according to the crack direction; generate a first repair plan for the friction stir welding method of the key area according to the model parameters, welding parameters, and welding path of the stirring head, and control the stirring head to execute the first repair plan.

[0092] Based on the above embodiments, as an alternative embodiment, the first execution module is further configured to, when there are multiple key areas, obtain the workpiece physical structure of the crack area; analyze the stress distribution of the crack area according to the workpiece physical structure, and determine the priority order of each key area in descending order of the stress distribution.

[0093] Based on the above embodiments, as an alternative embodiment, the analysis module is further configured to obtain the image information of the crack area after implementing the first repair plan; input the multi-modal image before welding and the image information into the crack analysis sub-model, detect whether new cracks are initiated or the original cracks expand during the welding process through image comparison, and generate crack extension information; collect the welding information of the key area during the welding process in real time; input the welding information into the welding quality inspection sub-model, and generate the welding quality information of the key area through process parameter matching analysis.

[0094] Based on the above embodiments, as an alternative embodiment, the analysis module is further configured to input the axial stress, transverse shear stress, plastic strain distribution, and temperature field data into the welding quality inspection sub-model; calculate the deviation value between the axial stress and the preset axial stress threshold, and generate an axial stress matching degree index; calculate the ratio of the transverse shear stress to the critical shear stress based on the material mechanical property parameters, and generate a shear stress safety factor; analyze the spatial gradient characteristics of the plastic strain distribution, calculate the strain uniformity index, and the strain uniformity index is used to characterize the plastic deformation consistency of the key area; match the temperature field data with the standard welding temperature field distribution, and calculate the temperature field similarity coefficient; generate the welding quality information of the key area based on the axial stress matching degree index, shear stress safety factor, strain uniformity index, and temperature field similarity coefficient.

[0095] Based on the above embodiments, as an alternative embodiment, the second execution module is further configured to verify whether the welding of the key area inhibits crack propagation based on the crack extension information, and determine that the first welding requirement is met when the crack propagation length is less than the preset second threshold; compare the welding quality information with the corresponding preset third threshold to determine whether the welding quality information meets the second welding requirement; when both the first welding requirement and the second welding requirement are met, extract the crack morphology characteristics and crack structure characteristics of the general area; adjust the welding parameters of the stirring head according to the crack characteristics of the general area, and generate a second repair plan with at least one strength level lower than the first repair plan; control the stirring head to perform repair welding on the general area according to the second repair plan, and monitor the welding quality information at the junction of the general area and the adjacent key area in real time during the welding process.

[0096] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded and executed by a processor to perform the friction stir welding control method based on the welding analysis model as described in the above embodiments. The specific execution process can refer to the specific description of the embodiments and will not be elaborated here.

[0097] Please refer to Figure 3 , which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 3 shown, the electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0098] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0099] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera).

[0100] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0101] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines, and executes various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0102] Among them, the memory 305 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 305 can also be at least one storage device located far from the aforementioned processor 301. As Figure 3 shown, in the memory 305 as a computer storage medium, it may include an operating system, a network communication module, a user interface module, and an application program of a friction stir welding control method based on a welding analysis model.

[0103] In Figure 3 the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user to obtain the data input by the user; while the processor 301 can be used to call the application program of a friction stir welding control method stored in the memory 305. When executed by one or more processors, the electronic device executes the method as one or more of the above embodiments.

[0104] An electronic device-readable storage medium stores instructions. When executed by one or more processors, the electronic device executes the method as one or more of the above embodiments.

[0105] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0106] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0107] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0108] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0110] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0111] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will readily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth. The present application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include the common general knowledge or conventional technical means in the technical field not recorded in the present disclosure.

Claims

1. A friction stir welding control method based on a welding analysis model, characterized in that The method includes: Obtain multimodal images of the crack area, and extract the crack morphology features and crack structure features in the multimodal images; Divide the crack area into a key area and a general area according to the crack morphology features and crack structure features; Generate a first repair plan for the friction stir welding method of the key area, and control the stirring head to execute the first repair plan; Obtain the image information of the crack area and the welding information of the key area respectively, and input the image information and the welding information into a welding analysis model to obtain crack extension information and welding quality information; When both the crack extension information and the welding quality information meet the preset welding requirements, generate a second repair plan for the friction stir welding method of the general area, and control the stirring head to execute the second repair plan.

2. The method according to claim 1, characterized in that The crack morphology features include crack shape features and crack width features, and the crack structure features include crack depth features and crack surface features. Dividing the crack area into a key area and a general area according to the crack morphology features and crack structure features includes: Based on the crack morphology features, identify the main path and branch paths of the crack area; According to the crack width feature and the crack depth feature, calculate the product of the crack width and crack depth of the main path, and determine the main path with the product greater than a preset first threshold as the first key area; Determine the surface curvature of the crack area based on the crack surface feature, and determine a second key area where the crack surface is in a convex state or a concave state according to the surface curvature; Determine the first key area and the second key area as the key areas, and divide the area other than the key areas in the crack area into general areas.

3. The method according to claim 1, wherein Generating the first repair plan for the friction stir welding method of the key area and controlling the stirring head to execute the first repair plan includes: Obtain the material properties of the key area, and determine the model parameters of the stirring head for welding using the friction stir welding method; According to the crack morphology features and crack structure features of the key area, determine the welding parameters of the stirring head, and the welding parameters include rotational speed, travel speed, downward pressure depth, and tilt angle; Obtain the crack direction of the key area, and plan the welding path of the key area according to the crack direction; Generate a first repair plan for the friction stir welding method of the key area according to the model parameters of the stirring head, the welding parameters, and the welding path, and control the stirring head to execute the first repair plan.

4. The method according to claim 1 or 3, characterized in that, Before generating the first repair plan for the friction stir welding method of the key area and controlling the stirring head to execute the first repair plan, it further includes: When there are multiple key areas, obtain the workpiece physical structure of the crack area; Analyze the stress distribution of the crack area according to the workpiece physical structure, and determine the priority order of each key area in descending order of the stress distribution.

5. The method according to claim 1, characterized in that The welding analysis model includes a crack analysis sub-model and a welding quality inspection sub-model. Respectively obtaining the image information of the crack area and the welding information of the key area, and inputting the image information and the welding information into the welding analysis model to obtain crack extension information and welding quality information, including: Obtaining the image information of the crack area after implementing the first repair plan; Inputting the multi-modal image before welding and the image information into the crack analysis sub-model, and detecting whether new cracks are initiated or the original cracks expand during the welding process through image comparison to generate crack extension information; Real-time collecting the welding information of the key area during the welding process; Inputting the welding information into the welding quality inspection sub-model, and generating the welding quality information of the key area through process parameter matching analysis.

6. The method according to claim 5, wherein The welding information includes axial stress, transverse shear stress, plastic strain distribution and temperature field data. Inputting the welding information into the welding quality inspection sub-model and generating welding quality information through process parameter matching analysis, including: Inputting the axial stress, the transverse shear stress, the plastic strain distribution and the temperature field data into the welding quality inspection sub-model; Calculating the deviation value between the axial stress and the preset axial stress threshold to generate an axial stress matching degree index; Calculating the ratio of the transverse shear stress to the critical shear stress based on the material mechanical property parameters to generate a shear stress safety factor; Analyzing the spatial gradient characteristics of the plastic strain distribution and calculating a strain uniformity index, where the strain uniformity index is used to characterize the plastic deformation consistency of the key area; Matching the temperature field data with the standard welding temperature field distribution and calculating a temperature field similarity coefficient; Generating the welding quality information of the key area based on the axial stress matching degree index, the shear stress safety factor, the strain uniformity index and the temperature field similarity coefficient.

7. The method according to claim 1 or 6, characterized in that, The preset welding requirements include a first welding requirement and a second welding requirement. When both the crack extension information and the welding quality information meet the preset welding requirements, generating a second repair plan for the friction stir welding method in the general area and controlling the stirring head to execute the second repair plan, including: Verifying whether the welding in the key area inhibits crack extension based on the crack extension information, and determining that the first welding requirement is met when the crack extension length is less than a preset second threshold; Comparing the welding quality information with the corresponding preset third threshold to determine whether the welding quality information meets the second welding requirement; When both the first welding requirement and the second welding requirement are met, extracting the crack morphology characteristics and crack structure characteristics of the general area; Adjusting the welding parameters of the stirring head according to the crack characteristics of the general area to generate a second repair plan with at least one strength level lower than the first repair plan; Controlling the stirring head to perform repair welding on the general area according to the second repair plan, and real-time monitoring the welding quality information at the junction between the general area and the adjacent key area during the welding process.

8. A friction stir welding control system based on a welding analysis model, characterized in that, The system includes: A feature extraction module, which is used to obtain multimodal images of the crack area and extract the crack morphology features and crack structure features in the multimodal images; A region division module, which is used to divide the crack area into a key area and a general area according to the crack morphology features and crack structure features; A first execution module, which is used to generate a first repair plan for the friction stir welding method of the key area and control the stirring head to execute the first repair plan; An analysis module, which is used to respectively obtain the image information of the crack area and the welding information of the key area, and input the image information and the welding information into a welding analysis model to obtain crack extension information and welding quality information; A second execution module, which is used to generate a second repair plan for the friction stir welding method of the general area and control the stirring head to execute the second repair plan when both the crack extension information and the welding quality information meet the preset welding requirements.

9. A computer storage medium, characterized in that, The computer storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes a processor, a memory and a transceiver. The memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

Images