Feedback control method for laser welding

Abstract

The present invention discloses a feedback control method for laser welding, which relates to the field of laser welding technology. The method comprises: obtaining target design information of a target assembly and a target sub-design information set of a sub-component set; performing clamping positioning analysis to obtain a clamping feature point set and a workpiece alignment vector set; performing welding control analysis to obtain welding path control; pre-building a welding repair analysis module; performing sub-component clamping of the sub-component set to obtain a body to be welded; during the automated welding process of the body to be welded, a laser interferometer collects and feeds back a real-time interference fringe sequence to the welding repair analysis module; performing welding repair analysis based on the real-time interference fringe sequence to obtain a repair path control, and performing feedback control optimization on the body to be welded using the repair path control as a constraint on the target welding assembly. The present invention solves the technical problems of insufficient laser welding control accuracy and poor stability in the prior art, thereby achieving the technical effect of improving welding quality and efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of laser welding, and in particular to a feedback control method for laser welding. Background Art

[0002] In the field of laser welding, the stability and precision of weld quality have a crucial impact on the final performance and reliability of the product. With the rapid development of the manufacturing industry and intensified market competition, laser welding has gained widespread application in industries such as aviation, automotive, and electronics. However, the laser welding process is a highly complex and variable physical process involving the interaction of light, heat, and force, placing extremely high demands on precise control of the welding process.

[0003] While traditional laser welding feedback control methods can achieve stable control of the welding process to a certain extent, they often suffer from problems such as insufficient control accuracy and poor stability. These problems can lead to welding defects such as uneven welds, porosity, and cracks, thus affecting product quality and service life.

[0004] As modern manufacturing continues to improve production efficiency and product quality, higher requirements are being placed on the intelligence and automation of laser welding processes. Traditional feedback control methods are no longer able to meet the efficiency, precision, and safety requirements of modern laser welding processes. Summary of the Invention

[0005] The present application provides a feedback control method for laser welding, which is used to solve the technical problems of insufficient laser welding control accuracy and poor stability in the prior art.

[0006] In view of the above problems, the present application provides a feedback control method for laser welding.

[0007] In a first aspect of the present application, a feedback control method for laser welding is provided, the method comprising:

[0008] Interactively obtain target design information of a target assembly and a target sub-design information set of a sub-component set, wherein the target assembly is obtained by laser welding the sub-component set; perform clamping positioning analysis based on the target design information and the target sub-design information to obtain a clamping feature point set and a workpiece alignment vector set; perform welding control analysis based on the target design information and the target sub-design information to obtain welding path control, wherein the welding path control includes welding trajectory parameters and welding control parameters; pre-construct a welding repair analysis module, wherein the welding repair analysis module is in communication connection with the laser interferometer of the target welding component; target clamping assembly The target welding component and the target clamping component clamp the subcomponents of the subcomponent set with the clamping feature point set and the workpiece alignment vector set as constraints to obtain a to-be-welded entity, wherein the target welding component and the target clamping component constitute an automated laser welding device; during the automated welding process performed by the target welding component on the to-be-welded entity with the welding path control as a constraint, the laser interferometer collects and feeds back a real-time interference fringe sequence to the welding repair analysis module; the welding repair analysis module performs welding repair analysis according to the real-time interference fringe sequence to obtain a repair path control, and the target welding component performs feedback control optimization on the to-be-welded entity with the repair path control as a constraint.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The present application interactively obtains target design information of a target assembly and a target sub-design information set of a sub-component set, wherein the target assembly is obtained by laser welding the sub-component set; performs clamping positioning analysis based on the target design information and the target sub-design information to obtain a clamping feature point set and a workpiece alignment vector set; performs welding control analysis based on the target design information and the target sub-design information to obtain a welding path control, wherein the welding path control includes welding trajectory parameters and welding control parameters; pre-constructs a welding repair analysis module, wherein the welding repair analysis module is communicatively connected to a laser interferometer of a target welding component; the target clamping component clamps the sub-components of the sub-component set with the clamping feature point set and the workpiece alignment vector set as constraints to obtain a to-be-welded entity, wherein the target welding component and the target clamping component constitute an automated laser welding device; during the process of performing automated welding on the to-be-welded entity with the welding path control as a constraint, the laser interferometer collects and feeds back a real-time interference fringe sequence to the welding repair analysis module; the welding repair analysis module performs welding repair analysis based on the real-time interference fringe sequence to obtain a repair path control, and the target welding component performs feedback control optimization on the to-be-welded entity with the repair path control as a constraint. The present invention solves the technical problems of insufficient laser welding control accuracy and poor stability in the existing technology. By real-time monitoring of key parameters in the welding process and real-time adjustment of welding parameters according to the monitoring results, precise control of the welding process is achieved, thereby achieving the technical effect of improving welding quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of a feedback control method for laser welding provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the process of obtaining a clamping feature point set and a workpiece alignment vector set in a feedback control method for laser welding provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] This application provides a feedback control method for laser welding to solve the technical problems of insufficient laser welding control accuracy and poor stability in the existing technology. By real-time monitoring of key parameters in the welding process and real-time adjustment of welding parameters based on the monitoring results, precise control of the welding process can be achieved, thereby achieving the technical effect of improving welding quality and efficiency.

[0015] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] Example 1

[0018] like Figure 1 As shown, the present application provides a feedback control method for laser welding, the method comprising:

[0019] Step S100: interactively obtaining target design information of a target assembly and a target sub-design information set of a sub-component set, wherein the target assembly is obtained by laser welding the sub-component set;

[0020] In the embodiment of the present application, target design information of a target assembly and target sub-design information set of a sub-assembly set are obtained through interaction. The interaction is achieved in various ways, including but not limited to manual input by a user, file import, and the like.

[0021] In this application, the user manually inputs the design information of the target assembly and subassembly. The target design information and target sub-design information set include geometric dimensions, material information, assembly requirements, etc.

[0022] Geometric dimensions include the length, width, height, and angles of assemblies and subassemblies. Material information includes the type, thickness, and thermal conductivity of the materials used in assemblies and subassemblies.

[0023] Step S200: performing clamping positioning analysis based on the target design information and the target sub-design information to obtain a clamping feature point set and a workpiece alignment vector set;

[0024] In an embodiment of the present application, based on the acquired target design information and target sub-design information, and according to factors such as the structural characteristics of the assembly, the shape and size of the sub-components, an appropriate clamping strategy is determined, and the location, number, and clamping method of the clamping points are selected.

[0025] Clamping feature points are key locations used to secure subassemblies. The specific locations of these clamping feature points are determined based on the geometric dimensions and assembly requirements in the design information. Once these points are located, a clamping feature point set is generated. This set contains the coordinate information for all necessary clamping points.

[0026] Workpiece alignment vectors are vectors used to determine the correct position and orientation of a subcomponent relative to the assembly. Workpiece alignment vectors are calculated based on the assembly requirements and geometric relationships in the design information. These vectors ensure that the subcomponent is accurately aligned with the assembly before welding. Based on the analysis of these vectors, a workpiece alignment vector set is generated. This set contains all necessary alignment vector information.

[0027] Step S300: performing welding control analysis according to the target design information and the target sub-design information to obtain welding path control, wherein the welding path control includes welding trajectory parameters and welding control parameters;

[0028] In this embodiment, the target design information and target sub-design information are first analyzed, but the overall structure of the assembly, the layout and relative positions of the sub-components, and the type and location of the welded joints are underestimated. The welded joints are then analyzed to determine the type, size, shape, and material properties of the joints. Joint types include butt joints, corner joints, and T-joints.

[0029] When planning weld trajectories, the weld trajectory is generated based on the assembly requirements and weld joint analysis results from the design information. The weld trajectory is the path the weld head follows during the welding process. The weld trajectory is generated based on the location, orientation, and shape of the weld joint, as well as the overall structure of the assembly, ensuring that the weld trajectory covers all areas requiring welding and avoids interference with other components.

[0030] Welding trajectory parameters include welding speed, welding angle, and welding depth. These parameters directly impact welding quality and efficiency. Based on the material properties, joint type, and expected weld quality, as determined by empirical formulas, welding trajectory parameters are determined. For example, welding speed and current are adjusted for different materials, while welding angle and depth are adjusted for different joint types.

[0031] In addition to welding trajectory parameters, welding control parameters are also key to ensuring a smooth welding process. Welding control parameters include welding current, welding voltage, welding time, etc. Welding control parameters are set based on the material thickness, weld joint size and shape, and expected weld quality in the design information.

[0032] Finally, the welding trajectory parameters and welding control parameters are integrated to generate the welding path control.

[0033] Step S400: pre-building a welding repair analysis module, wherein the welding repair analysis module is communicatively connected to a laser interferometer of a target welding component;

[0034] In the embodiments of this application, the welding repair analysis module is a comprehensive module that integrates data analysis, defect identification, and repair strategy generation. The module communicates with the laser interferometer to acquire real-time data from the welding process. It then uses built-in algorithms and models to analyze the data, identify welding defects, and provide corresponding repair solutions.

[0035] The communication interface between the welding repair analysis module and the laser interferometer uses a standard data transmission protocol to ensure data accuracy and real-time performance. The laser interferometer transmits real-time welding data, such as welding speed and temperature distribution, to the welding repair analysis module via the communication interface.

[0036] The welding repair analysis module performs preprocessing operations such as denoising and filtering on the received welding data to improve data quality. It then uses a machine learning algorithm to extract characteristic parameters related to welding quality from the preprocessed data. Based on these extracted characteristic parameters, a pre-set defect recognition model is used to determine whether defects such as porosity, cracks, and lack of fusion are present during the welding process. For identified welding defects, the module can accurately locate the defect's location and size.

[0037] Finally, a repair plan is generated based on the type and severity of the defect, combined with the material properties and design requirements of the target welded component. The repair plan may include adjusting welding parameters, replacing welding materials, etc.

[0038] Step S500: The target clamping assembly clamps the subcomponents of the subcomponent set using the clamping feature point set and the workpiece alignment vector set as constraints to obtain a solid body to be welded, wherein the target welding assembly and the target clamping assembly constitute an automated laser welding device;

[0039] In the embodiments of this application, the target clamping assembly includes mechanical grippers, a servo drive system, sensors, and a control system. The mechanical grippers directly contact and secure the subassembly, while the servo drive system controls the opening, closing, and movement of the grippers. Sensors monitor various parameters during the clamping process, such as gripping force and position, in real time to ensure accurate and stable clamping. The control system receives instructions from the welding control system.

[0040] The gripping feature point set, derived from previous design information analysis and gripping positioning analysis, contains the coordinates of key points on the subcomponent used for gripping. The target gripper uses this feature point set to precisely adjust the position and angle of the mechanical gripper, ensuring it accurately grasps the subcomponent at its intended location. Furthermore, the gripper calculates the optimal gripping force and method based on this feature point set to avoid damage to the subcomponent.

[0041] The workpiece alignment vector set describes the correct position and orientation of the subcomponent relative to the assembly. When gripping the subcomponent, the target clamping assembly strictly adheres to the workpiece alignment vector set, using a servo drive system to precisely control the movement of the gripper jaws, accurately placing the subcomponent in the predetermined welding position.

[0042] The target welding assembly and target clamping assembly comprise the automated laser welding equipment. During the clamping process, the welding control system sends instructions to the clamping assembly based on the welding path control requirements. Upon receiving these instructions, the clamping assembly clamps and positions the subcomponent according to a pre-defined set of clamping feature points and workpiece alignment vectors. Once the subcomponent is precisely clamped and positioned in the desired location, the welding assembly begins the welding operation. Through the precise clamping and positioning of the target clamping assembly, the subcomponent is stably secured to the assembly, forming the solid body to be welded.

[0043] Step S600: The target welding component performs automated welding on the entity to be welded with the welding path control as a constraint, and the laser interferometer collects and feeds back a real-time interference fringe sequence to the welding repair analysis module;

[0044] In an embodiment of the present application, after the target welding assembly receives the welding path control instruction sent by the welding control system, it starts to perform automated welding according to the preset welding trajectory parameters and welding control parameters. In this process, the laser interferometer works by emitting a laser beam and receiving its reflected light. When the laser beam is irradiated to the welding area of the entity to be welded, due to factors such as thermal deformation and dynamic changes in the molten pool generated during the welding process, the reflected light of the laser beam will change, forming interference fringes. These interference fringe sequences contain real-time status information of the welding area, such as temperature distribution, molten pool morphology, welding defects, etc. The laser interferometer continuously collects these real-time interference fringe sequences and converts them into digital signals. Then, these digital signals are transmitted to the welding repair analysis module in real time through the communication interface.

[0045] Step S700: the welding repair analysis module performs welding repair analysis according to the real-time interference fringe sequence to obtain a repair path control, and the target welding assembly performs feedback control optimization on the entity to be welded with the repair path control as a constraint.

[0046] In this embodiment of the present application, after receiving the real-time interference fringe sequence, the weld repair analysis module first performs preprocessing, including noise removal and filtering, to improve the accuracy and reliability of the data. Next, it uses built-in algorithms and models to conduct in-depth analysis of the preprocessed interference fringe sequence, extracting and quantifying features such as the morphology, density, and rate of change of the interference fringes to obtain real-time status information of the weld area.

[0047] Based on the analysis of the interference fringe patterns, the Weld Repair Analysis Module identifies various defects that may occur during the welding process, such as pores, cracks, and lack of fusion. The module compares the actual interference fringes with pre-set standard interference fringes, and, based on welding process parameters and material properties, determines the type and location of the defect. Once a weld defect is identified, the Weld Repair Analysis Module immediately generates repair path control instructions. These instructions guide the targeted weld component in precisely repairing the defect. The repair path control includes parameters such as the location of the repair point, repair speed, and repair energy.

[0048] After receiving the repair path control instructions, the target weld assembly executes the repair operation on the target weld entity according to the instructions. During this process, the weld assembly maintains real-time communication with the weld repair analysis module, feeding back real-time data on the repair process. The weld repair analysis module uses this feedback data to monitor and evaluate the repair process in real time. If the repair effect is unsatisfactory or new defects are found, the module immediately adjusts the repair path control parameters and sends them back to the weld assembly to achieve feedback control optimization.

[0049] In this way, the Weld Repair Analysis module can continuously optimize the repair process and ensure improved weld quality.

[0050] Further, such as Figure 2 As shown, step S200 in the method provided in the application embodiment further includes:

[0051] Perform digital modeling and restoration of the target assembly according to the target design information to generate a target assembly model;

[0052] Performing digital modeling restoration of the subcomponent set according to the target sub-design information to generate a target subcomponent model set, wherein the subcomponent set includes M subcomponents, the target sub-design information includes M subcomponent design information and M assembly association information of the M subcomponents, and the target subcomponent model set includes M subcomponent models of the M subcomponents;

[0053] Performing welding apparent center point recognition on the M sub-component models to obtain M clamping feature points, wherein the M clamping feature points constitute the clamping feature point set;

[0054] Performing component edge feature point recognition on the M sub-component models to obtain M edge feature points;

[0055] According to the M assembly association information, the M sub-component models are assembled and fitted into the target assembly model, and the M clamping feature points are used as workpiece alignment constraints, and the M edge feature points are used as alignment vector constraints to generate M workpiece alignment vectors, which constitute the workpiece alignment vector set.

[0056] In the embodiments of the present application, based on the target design information, computer-aided design software, such as CAD or a digital modeling tool, is used to digitally model the target assembly. Based on the dimensions, shape, material, and other parameters in the design information, corresponding digital models are constructed one by one. Ultimately, a complete target assembly model that is highly consistent with the actual assembly is obtained.

[0057] Next, based on the target sub-design information, the sub-component set is digitally modeled and restored. This sub-component set includes M sub-components, each with corresponding sub-component design information and assembly-related information. Similarly, using CAD software or digital modeling tools, the corresponding sub-component models are constructed one by one based on the design information of each sub-component, resulting in a target sub-component model set containing M sub-component models.

[0058] After generating the subcomponent model, identify clamping feature points. Clamping feature points are key points that guide the clamping assembly in clamping the subcomponent. Using digital model processing software or algorithms, such as Geomagic Design X, identify the apparent weld center points of the M subcomponent models. These apparent weld center points are locations on the subcomponent suitable for clamping and constitute the clamping feature point set.

[0059] In addition to the clamping feature points, the edge feature points of the subcomponent are identified. These subcomponent edge feature points are located at the edge of the subcomponent and are used for subsequent alignment vector generation. Similarly, digital model processing software or algorithms are used to identify the edge feature points of the M subcomponent models to obtain M edge feature points.

[0060] According to the M assembly association information in the target sub-design information, the M sub-component models are assembled and fitted to the target assembly model according to the preset assembly order and association relationship. In this process, the relative positions and angles between the sub-components are ensured to be consistent with the design information. After the assembly fitting is completed, the workpiece alignment vector is generated using the M clamping feature points as the workpiece alignment constraints and the M edge feature points as the alignment vector constraints. The alignment vector is an important parameter to guide the precise alignment of the welded assembly, which describes the position and direction information of the sub-component relative to the target assembly model during the assembly process. By calculating the relative position and angle relationship between each sub-component model and the target assembly model, M workpiece alignment vectors are obtained, which together constitute the workpiece alignment vector set.

[0061] Furthermore, the method further comprises:

[0062] Assembling and fitting the M subcomponent models to the target assembly model according to the M assembly association information, and performing difference set calculation with the target assembly model as a subtracted set and the M subcomponent models as a subtracted set to obtain a weld frame model;

[0063] Performing connection point identification on the weld frame model, and decomposing the weld frame model into multiple welding trajectories based on the connection point identification results;

[0064] Based on the continuity of the welding trajectories, the connection schemes of the multiple welding trajectories are enumerated in the weld frame model to obtain multiple groups of welding trajectory connection schemes and multiple welding space jump distances;

[0065] The plurality of welding space jump distances are serialized and minimum value calls are performed to obtain the welding trajectory parameters.

[0066] In an embodiment of the present application, the exact position and orientation of each subcomponent in the target assembly model is first determined based on M assembly association information. The association information includes the relative position, angle, alignment, etc. between the subcomponents. Using this information, the M subcomponent models are accurately placed in the corresponding positions of the target assembly model according to the preset assembly order and association relationship. The target assembly model is used as the subtrahend set, and the M subcomponent models are used as the subtracted sets to perform difference set solution. Difference set solution is a geometric operation used to subtract one geometric shape from another to obtain the difference between them. In this scenario, the weld frame model is obtained by difference set solution. The weld frame model represents the area where welding is required to complete the final assembly after the subcomponent models are assembled. These areas are the gaps or contact surfaces between the subcomponent models, and they are firmly connected together by welding.

[0067] After obtaining the weld frame model, its connection points are identified. Connection points refer to the specific locations in the weld frame model where welding is required. These connection points are located at the boundaries or intersections of the weld frame model and are the starting and ending points of the welding trajectory. By identifying these connection points, the weld frame model is disassembled into multiple welding trajectories. Each welding trajectory represents a welding path from one connection point to another. After being disassembled into multiple welding trajectories, the connection problem between these trajectories is considered. Based on the continuity of the welding trajectories, the connection schemes of multiple welding trajectories are enumerated on the weld frame model. That is, all possible trajectory connection methods are tried to find the optimal welding sequence and path. During the enumeration process, multiple sets of welding trajectory connection schemes and multiple welding space jump distances are obtained. The welding space jump distance refers to the spatial distance that the welding head needs to move from one welding trajectory to another.

[0068] Finally, these weld space jump distances are serialized and minimized. This serialization process arranges these distances in a specific order for subsequent processing. The minimum value is found among these serialized distances through the minimization process. This minimum value represents the optimal weld trajectory connection solution, specifically the shortest distance the weld head must travel during the welding process. Through this process, the weld trajectory parameters are obtained.

[0069] Furthermore, the method further comprises:

[0070] Interactively obtaining material parameters and thickness parameters of the target assembly, and using the material parameters and thickness parameters as constraints to obtain a sample welding control parameter set, wherein the sample welding control parameter set includes a plurality of sample weld parameters, a plurality of sample welding strengths, and a plurality of sample welding control parameters;

[0071] Constructing a laser control analysis model based on a CNN neural network, and using the sample welding control parameter set to perform training optimization on the laser control analysis model;

[0072] Presetting a multi-level weld width constraint, and traversing the multiple welding trajectories based on the multi-level weld width constraint, and splitting the multiple welding trajectories into multiple groups of connecting weld widths at a secondary level;

[0073] Interactively obtaining multi-region welding strength constraints of the target assembly, and dividing the multi-region welding strength constraints according to the multiple welding trajectories to obtain multiple groups of connection welding strengths;

[0074] Synchronizing the multiple sets of connection weld widths and the multiple sets of connection weld strengths to the laser control analysis model to obtain multiple sets of local welding control parameters, and serializing the multiple sets of local welding control parameters according to the welding trajectory parameters to generate the welding control parameters;

[0075] The welding trajectory parameters and the welding control parameters are fitted to generate the welding path control.

[0076] In the embodiment of the present application, the material parameters and thickness parameters of the target assembly are obtained through interaction. The material parameters include the type, melting point, thermal conductivity, etc. of the material, and the thickness parameters describe the thickness of different parts of the assembly.

[0077] A pre-prepared sample welding control parameter set is called with material parameters and thickness parameters as constraints. The set contains multiple sample weld parameters, sample weld strength, and sample welding control parameters.

[0078] Next, a CNN neural network was used to build a laser control analysis model. The model was trained and optimized using a sample welding control parameter set, enabling it to learn and identify the optimal welding control parameters for different materials and thicknesses.

[0079] Next, analyze the required weld width based on the target assembly's material, structure, and operating conditions. Based on the analysis results, determine the weld width range for each weld area using industry standards, experimental data, or empirical formulas. Set multiple levels of weld width constraints based on the characteristics and importance of each area. For example, critical stress-bearing areas may require stricter weld width requirements, while non-critical areas may have a certain width range.

[0080] Next, based on the multi-level weld width constraints, the system traverses multiple welding trajectories. For each welding trajectory segment, the actual weld width generated by the calculated or simulated welding trajectory is checked to see if the corresponding weld width meets the preset multi-level weld width constraints. If the predicted weld width of a welding trajectory segment does not meet the preset multi-level weld width constraints, it is split. The location of the split point is determined based on the specific circumstances of the constraint violation, the change in weld width, the requirements of the welding process, and the structural characteristics of the assembly. Finally, at the determined split point, the multi-segment welding trajectory is split into multiple groups of connecting weld widths.

[0081] Through interaction with engineers, technicians, or relevant experts, clarify the strength constraints of each welding area. The welding area strength constraints include the minimum and maximum welding strengths required for each area, as well as the possible strength variation range. Analyze the correspondence between each welding trajectory and the welding area. Determine which areas each trajectory is responsible for welding, as well as the relative position and length of these areas in the trajectory. Based on the correspondence between the welding trajectory and the welding area, divide the determined welding strength constraints into each welding trajectory by calculating the average strength requirement and maximum strength requirement of the area covered by each trajectory. After completing the division of the welding strength constraints, calculate the connection welding strength of each trajectory based on the specific parameters of each welding trajectory, such as welding speed, temperature, pressure, etc. and the characteristics of the welding material, and obtain multiple groups of connection welding strengths.

[0082] Multiple sets of data on the width and strength of the connecting welds are synchronized into the laser control analysis model. The laser control analysis model then performs internal calculations and analysis based on the synchronized weld width and strength data. Based on the model analysis results, the various control parameters during the welding process are optimized to ensure that the welding quality is maximized while meeting the weld width and weld strength requirements. Multiple sets of local welding control parameters are extracted from the optimized control parameters. These parameters include laser power, welding speed, focal length, gas flow rate, etc. The multiple sets of local welding control parameters are serialized according to the order of the welding trajectory, and the local parameters are matched and mapped to the trajectory parameters to ensure that each trajectory point has a corresponding control parameter. The serialized welding control parameters are integrated with the welding trajectory parameters to form a complete set of welding control parameters.

[0083] When fitting the welding trajectory parameters and welding control parameters, an appropriate fitting method is selected based on their specific characteristics. These characteristics include data distribution, noise level, and degree of nonlinearity. Fitting methods include linear regression, polynomial regression, spline interpolation, and neural networks. After selecting a fitting method, a corresponding mathematical model or algorithm is established. This model or algorithm describes the relationship between the welding trajectory parameters and welding control parameters. For example, when using a neural network for fitting, parameters such as the number of layers, number of neurons, and activation function are determined, and the network structure is constructed. After the model or algorithm is established, model parameters are adjusted using methods such as gradient descent and least squares to minimize the difference between the predicted and actual values, thereby better fitting the model to the actual data and improving prediction accuracy. The fitting process involves multiple iterations and optimization. In each iteration, model parameters are adjusted based on the current fitting results, and the difference between the predicted and actual values is recalculated. Through multiple iterations, the optimal model parameters are gradually found, achieving the best fitting results. After the fitting is completed, the fitting effect is evaluated through methods such as goodness-of-fit calculation and residual analysis. Finally, the fitting welding control parameters are mapped to the welding trajectory to generate the welding path control.

[0084] Furthermore, the welding repair analysis module performs welding repair analysis according to the real-time interference fringe sequence to obtain repair path control, and the method further includes:

[0085] The welding repair analysis module includes a welding quality identification submodule and a repair path analysis submodule;

[0086] The welding quality identification submodule dynamically identifies welding deviations according to the real-time interference fringe sequence to obtain a welding deviation node set, wherein the welding deviation node set includes K deviation node position information and K deviation node image features;

[0087] The repair path analysis submodule performs welding repair analysis based on the welding deviation node set to obtain a welding repair control set;

[0088] The welding repair control set is fitted to the welding trajectory parameters to obtain the repair path control.

[0089] In the embodiment of the present application, the welding repair analysis module identifies welding quality problems and performs corresponding repair path analysis. The welding repair analysis module is composed of two submodules: a welding quality identification submodule and a repair path analysis submodule.

[0090] The welding quality identification submodule's primary responsibility is to dynamically identify welding deviations based on the real-time interference fringe sequence. Using image processing, the submodule analyzes the real-time interference fringe sequence and dynamically identifies deviations that occur during the welding process. This includes identifying defects such as unevenness, lack of fusion, and slag inclusions in weld joints. Once a welding deviation is identified, the submodule generates a welding deviation node set. This set contains K deviation node position information and K deviation node image features. The deviation node position information indicates the specific location of the deviation on the weld trajectory, while the deviation node image features provide a visual description of the deviation.

[0091] The repair path analysis submodule performs weld repair analysis based on the weld deviation node set. Based on the image features within the weld deviation node set, the submodule analyzes the type and severity of the deviation. Deviation types include lack of fusion and slag inclusion, while the severity of the deviation includes its size and impact range.

[0092] Based on the type and extent of the deviation, the repair path analysis submodule selects an appropriate repair strategy. This strategy involves adjusting welding parameters and changing the welding trajectory. Adjusting welding parameters includes adjusting welding speed and laser power. Based on the selected repair strategy, the repair path analysis submodule then generates a welding repair control set. This welding repair control set contains all the control parameters and instructions required for the repair process.

[0093] After obtaining the welding repair control set, it is fitted to the welding trajectory parameters to obtain the repair path control. During the fitting process, the control parameters in the welding repair control set are mapped to the corresponding welding trajectory parameters, matching the repair instructions with the specific parameters of the welding trajectory, such as position and speed. By adjusting the welding trajectory parameters, the repair path control is generated.

[0094] Furthermore, the welding quality identification submodule dynamically identifies welding deviations based on the real-time interference fringe sequence to obtain a welding deviation node set, wherein the welding deviation node set includes K deviation node position information and K deviation node image features. The method further includes:

[0095] Classifying the plurality of real-time interference fringe images of the real-time interference fringe sequence based on interference fringe overlap to obtain a plurality of groups of real-time interference fringe images, wherein the plurality of real-time interference fringe images have a plurality of image acquisition position identifiers;

[0096] Presetting a frequency threshold, and screening the multiple groups of real-time interference fringe images to obtain H groups of abnormal interference fringe images based on the preset frequency threshold;

[0097] splicing a plurality of real-time interference fringe images of the real-time interference fringe sequence based on interference fringe overlap to obtain an interference fringe splicing image, and calculating the spacing between adjacent interference fringes based on the interference fringe splicing image to obtain a plurality of interference fringe spacings;

[0098] Clustering the plurality of interference fringe spacings to obtain a plurality of groups of interference fringe spacings, and screening the plurality of groups of interference fringe spacings to obtain N groups of interference fringes with abnormal spacings according to the preset frequency threshold;

[0099] The H groups of abnormal interference fringes and the N groups of abnormal spacing interference fringes are divided into groups to obtain the K deviation node image features, and image acquisition site identification calls are performed on the multiple real-time interference fringe images based on the K deviation node image features to obtain the K deviation node position information.

[0100] In the present embodiment, the real-time interference fringe images are preprocessed to eliminate noise, enhance image contrast, and highlight the characteristics of the interference fringes. Using image processing techniques, edge detection, threshold segmentation, and other steps are used to extract interference fringe information from each preprocessed real-time interference fringe image, separating the interference fringes from the background or other irrelevant information.

[0101] For any two real-time interference fringe images, the degree of overlap is calculated by comparing the degree of overlap of the interference fringes based on their shape, position, density, and other characteristics. This degree of overlap is calculated using similarity metrics such as Euclidean distance and correlation coefficient. Based on the calculated degree of overlap, multiple images in the real-time interference fringe sequence are divided into different groups. During this division, a threshold for overlap is set through comparison. When two images exceed this threshold, they are grouped together. This threshold is set based on historical experience.

[0102] Through the above steps, multiple sets of real-time interference fringe images with similar interference fringe patterns are obtained. Since each real-time interference fringe image is marked with the image acquisition location, these identifiers are associated with the classification results to determine which position or area on the welding track each set of interference fringe images corresponds to.

[0103] The preset frequency threshold is a key parameter used in the screening process for abnormal interference fringe images, distinguishing normal from abnormal interference fringe images. The threshold is determined based on historical data, empirical knowledge, or expert judgment. By statistically analyzing interference fringe images from a large number of welding processes, the frequency of occurrence of various interference fringe patterns under normal welding conditions is determined. Based on these statistical data, a reasonable threshold is set, and images with a frequency below this threshold are considered abnormal.

[0104] To screen for abnormal interference fringe images based on a preset frequency threshold, a statistical analysis is performed on multiple sets of real-time interference fringe images. By traversing the interference fringe sequence and counting the number of occurrences of each set of images, the frequency of each set of images in the entire interference fringe sequence is calculated. Next, the calculated frequency of each set of interference fringe images is compared with the preset frequency threshold. If the frequency of a set of images falls below the threshold, that set is marked as an abnormal interference fringe image. Through this comparison and screening, H sets of abnormal interference fringe images are ultimately obtained.

[0105] When stitching together multiple real-time interference fringe images from a real-time interference fringe sequence, a reference image is selected from the sequence. This image exhibits clear, stable interference fringes and represents a typical state of the welding process. Each image in the sequence is compared with the reference image, and the overlapping areas between them are identified by comparing the image's feature points, edge information, or similarity in the interference fringes. Based on the identified overlapping areas, each image is translated, rotated, or scaled to ensure a seamless connection when stitched together. The aligned and transformed images are then stitched together according to their chronological order or spatial position in the welding process to form a stitched interference fringe image.

[0106] The interference fringe stitching image is extracted using image processing techniques such as edge detection and binarization to clearly identify the interference fringes. Within the extracted interference fringes, the centerline of each fringe is further identified and extracted. For adjacent interference fringe centerlines, the distance between them is measured in pixels and calculated using the calibration information from the image acquisition system as the interference fringe spacing. This process is repeated to calculate the spacing between all adjacent interference fringes in the stitched image, yielding multiple interference fringe spacing values.

[0107] When clustering multiple interference fringe spacings, data preprocessing is first performed on the multiple interference fringe spacings to remove noise data, process outliers, or fill missing values to ensure the accuracy and completeness of the data. Based on the characteristics of the interference fringe spacing data and analysis requirements, an appropriate clustering algorithm, such as K-means clustering, hierarchical clustering, density clustering, etc., is selected to cluster the multiple interference fringe spacings. The algorithm divides them into different groups based on the similarity of the data. For each group of interference fringe spacings obtained after clustering, the frequency of its occurrence in the entire data set is calculated by traversing the data and counting the number of spacings in each group. The calculated frequency of each group of spacings is compared with the preset frequency threshold. Groups with frequencies below the preset threshold are marked as abnormal spacing interference fringes. Through the screening process, N groups of abnormal spacing interference fringes are finally obtained.

[0108] When splitting the H groups of abnormal interference fringes and the N groups of abnormal spacing interference fringes into groups, first, match the H groups of abnormal interference fringes with the N groups of abnormal spacing interference fringes based on their correspondence in time series or spatial position. Through matching, it is determined which abnormal interference fringes are associated with which abnormal spacing. After matching is completed, the groups are split according to the similarity of the abnormal interference fringes and abnormal spacing. The similarity is evaluated based on factors such as the morphology of the interference fringes and the stability of the spacing. Through splitting, similar abnormal interference fringes and abnormal spacing are combined into new groups. For each split group, image features that can represent its deviation characteristics are selected. Image features include the morphology, direction, density, contrast, etc. of the interference fringes. Image processing techniques such as edge detection, filtering, morphological analysis, etc. are used to extract the selected features from the interference fringe images of each group. Finally, the extracted features are integrated to form the deviation node image features of each group.

[0109] When identifying image acquisition locations across multiple real-time interference fringe images based on K deviation node image features, a mapping relationship between the image acquisition location identifiers and the real-time interference fringe images is established by recording the location information of each image at the time of acquisition, such as coordinates and timestamps. The extracted K deviation node image features are then used to match the multiple real-time interference fringe images using methods such as template matching and feature point matching to identify regions with similar deviation node features. Once matching regions are found, the corresponding image acquisition location identifiers are retrieved to obtain their location information. This location information represents the specific locations of the K deviation nodes. Finally, the acquired K deviation node location information is integrated to form a deviation node location information set.

[0110] Furthermore, the method further comprises:

[0111] Obtaining a sample repair control parameter set by calling the material parameter and the thickness parameter as constraints, wherein the sample repair control parameter set includes a density repair control parameter set and a shape repair control parameter set; and

[0112] The density repair control parameter set includes a plurality of sample abnormal stripe densities, a plurality of sample standard stripe densities and a plurality of sample repair control parameters; and

[0113] The shape restoration control parameter set includes a plurality of sample abnormal stripe shapes, a plurality of sample standard stripe shapes, and a plurality of sample restoration control parameters;

[0114] A first welding repair branch is constructed based on the density repair control parameter set, a second welding repair branch is constructed based on the shape repair control parameter set, and the first welding repair branch and the second welding repair branch are connected in parallel to generate a welding repair analysis network.

[0115] In this embodiment, a sample repair control parameter set matching the current welding task is retrieved from a pre-stored sample database, using material and thickness parameters as constraints. This parameter set includes repair control parameters tailored to different welding deviations. The sample repair control parameter set includes a density repair control parameter set and a shape repair control parameter set.

[0116] The density repair control parameter set includes a plurality of sample abnormal stripe densities, a plurality of sample standard stripe densities, and a plurality of sample repair control parameters.

[0117] Sample abnormal fringe density is extracted from historical welding data and represents the abnormal interference fringe density under different welding deviation conditions. Multiple sample standard fringe density samples are obtained under normal welding conditions and serve as a comparison and reference. Multiple sample repair control parameters are derived through analysis and optimization algorithms based on these abnormal fringe density and standard fringe density, and are used to guide density adjustment during the weld repair process.

[0118] The shape restoration control parameter set includes multiple sample abnormal stripe shapes, multiple sample standard stripe shapes, and multiple sample restoration control parameters.

[0119] Sample abnormal fringe shapes are extracted from historical data and represent abnormal interference fringe shapes under different welding deviations. Sample standard fringe shapes are interference fringe shapes obtained under normal welding conditions and serve as a comparison and reference. Sample restoration control parameters are derived through analysis and optimization algorithms based on the abnormal and standard fringe shapes and are used to guide shape adjustments during the weld repair process.

[0120] When constructing the first welding repair branch based on the density repair control parameter set, key repair control parameters are extracted from the density repair control parameter set. The repair control parameters include abnormal stripe density, standard stripe density, and corresponding repair control parameters. These parameters are preprocessed, such as standardization and normalization, to ensure the consistency and comparability of the parameters. Then, a density repair model is constructed based on the extracted density repair control parameters using machine learning or deep learning algorithms, such as support vector machines. The model predicts the corresponding repair control parameters based on the input abnormal stripe density to guide the adjustment of the density during the welding process. Through the above training process, the first welding repair branch is formed. This branch receives density data during the welding process in real time and calculates the repair control parameters through the density repair model.

[0121] When constructing the second welding repair branch based on the shape repair control parameter set, key repair control parameters are extracted from the shape repair control parameter set. The repair control parameters include abnormal stripe shape, standard stripe shape and corresponding restoration control parameters. These parameters are preprocessed to eliminate noise and outliers to ensure the validity and accuracy of the parameters. A shape repair model is constructed based on the extracted shape repair control parameters using machine learning or deep learning algorithms, such as support vector machines. The model can predict the corresponding restoration control parameters based on the input abnormal stripe shape to guide the adjustment of the shape during the welding process. Through the above training process, the second welding repair branch is formed. This branch receives the shape data of the welding process in real time, calculates the restoration control parameters through the shape repair model, and outputs these parameters to the welding control system to adjust the welding parameters and achieve shape repair.

[0122] The first welding repair branch and the second welding repair branch are connected in parallel to form a welding repair analysis network. During the welding repair process, the welding repair analysis network calls the first welding repair branch and the second welding repair branch to perform calculations and repairs based on the real-time welding data received.

[0123] Furthermore, the repair path analysis submodule performs welding repair analysis based on the welding deviation node set to obtain a welding repair control set. The method further includes:

[0124] Screening the multiple sets of real-time interference fringe images to obtain real-time standard interference fringes based on the preset frequency threshold, and screening the multiple sets of interference fringe spacings to obtain real-time standard fringe density based on the preset frequency threshold;

[0125] The K deviation node image features, the real-time standard interference fringes and the real-time standard fringe density are input into the welding repair analysis network to obtain K welding repair controls, which constitute the welding repair control set.

[0126] In the embodiments of the present application, when screening for real-time standard interference fringes based on a preset frequency threshold, the frequency of each real-time interference fringe image appearing in multiple sets of data is first calculated by comparing the unique identifier or feature of each image. The frequency of each image is then compared with a preset frequency threshold. When the frequency of a real-time interference fringe image exceeds the preset threshold, it is identified as a real-time standard interference fringe image. For multiple sets of interference fringe spacing data, the fringe density of each set is calculated by measuring the distance between adjacent fringes and counting the number of fringes per unit length.

[0127] Similar to screening real-time standard interference fringes, the fringe density of each group is compared with a preset frequency threshold. When the density value of the interference fringe spacing of a group is within the preset frequency threshold, it is identified as the real-time standard fringe density.

[0128] The K previously extracted deviation node image features, the screened real-time standard interference fringes, and the real-time standard fringe density are integrated to form a complete dataset. This integrated dataset is then input into a pre-built weld repair analysis network. The weld repair analysis network calculates K weld repair control parameters based on the input deviation node image features, real-time standard interference fringes, and real-time standard fringe density.

[0129] Finally, the obtained K welding repair control parameters are integrated into the welding repair control set.

[0130] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0131] The present application interactively obtains target design information of a target assembly and a target sub-design information set of a sub-component set, wherein the target assembly is obtained by laser welding the sub-component set; performs clamping positioning analysis based on the target design information and the target sub-design information to obtain a clamping feature point set and a workpiece alignment vector set; performs welding control analysis based on the target design information and the target sub-design information to obtain a welding path control, wherein the welding path control includes welding trajectory parameters and welding control parameters; pre-constructs a welding repair analysis module, wherein the welding repair analysis module is communicatively connected to a laser interferometer of a target welding component; the target clamping component clamps the sub-components of the sub-component set with the clamping feature point set and the workpiece alignment vector set as constraints to obtain a to-be-welded entity, wherein the target welding component and the target clamping component constitute an automated laser welding device; during the process of performing automated welding on the to-be-welded entity with the welding path control as a constraint, the laser interferometer collects and feeds back a real-time interference fringe sequence to the welding repair analysis module; the welding repair analysis module performs welding repair analysis based on the real-time interference fringe sequence to obtain a repair path control, and the target welding component performs feedback control optimization on the to-be-welded entity with the repair path control as a constraint. The present invention solves the technical problems of insufficient laser welding control accuracy and poor stability in the existing technology. By real-time monitoring of key parameters in the welding process and real-time adjustment of welding parameters according to the monitoring results, precise control of the welding process is achieved, thereby achieving the technical effect of improving welding quality and efficiency.

[0132] It should be noted that the above-mentioned order of the embodiments of the present application is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0133] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. This specification and the drawings are merely illustrative illustrations of the present application and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these modifications and variations.

Claims

1. A feedback control method for laser welding, characterized in that: The method comprises: Interactively obtaining target design information of a target assembly and a target sub-design information set of a sub-component set, wherein the target assembly is obtained by laser welding the sub-component set; Performing clamping positioning analysis according to the target design information and the target sub-design information to obtain a clamping feature point set and a workpiece alignment vector set includes: Perform digital modeling and restoration of the target assembly according to the target design information to generate a target assembly model; Performing digital modeling restoration of the subcomponent set according to the target sub-design information to generate a target subcomponent model set, wherein the subcomponent set includes M subcomponents, the target sub-design information includes M subcomponent design information and M assembly association information of the M subcomponents, and the target subcomponent model set includes M subcomponent models of the M subcomponents; Performing welding apparent center point recognition on the M sub-component models to obtain M clamping feature points, wherein the M clamping feature points constitute the clamping feature point set; Performing component edge feature point recognition on the M sub-component models to obtain M edge feature points; Assembling and fitting the M subcomponent models to the target assembly model according to the M assembly association information, and using the M clamping feature points as workpiece alignment constraints and the M edge feature points as alignment vector constraints to generate M workpiece alignment vectors, wherein the M workpiece alignment vectors constitute the workpiece alignment vector set; Performing welding control analysis based on the target design information and the target sub-design information to obtain welding path control, wherein the welding path control includes welding trajectory parameters and welding control parameters; pre-constructing a welding repair analysis module, wherein the welding repair analysis module is communicatively connected to a laser interferometer of a target welding assembly; The target clamping assembly clamps the subcomponents of the subcomponent set based on the clamping feature point set and the workpiece alignment vector set as constraints to obtain a solid body to be welded, wherein the target welding assembly and the target clamping assembly constitute an automated laser welding device; During the process in which the target welding assembly performs automated welding on the entity to be welded with the welding path control as a constraint, the laser interferometer collects and feeds back a real-time interference fringe sequence to the welding repair analysis module; The welding repair analysis module performs welding repair analysis according to the real-time interference fringe sequence to obtain a repair path control, and the target welding assembly performs feedback control optimization on the entity to be welded with the repair path control as a constraint.

2. The method according to claim 1, wherein The method further comprises: Assembling and fitting the M subcomponent models to the target assembly model according to the M assembly association information, and performing difference set calculation with the target assembly model as a subtracted set and the M subcomponent models as a subtracted set to obtain a weld frame model; Performing connection point identification on the weld frame model, and decomposing the weld frame model into multiple welding trajectories based on the connection point identification results; Based on the continuity of the welding trajectories, the connection schemes of the multiple welding trajectories are enumerated in the weld frame model to obtain multiple groups of welding trajectory connection schemes and multiple welding space jump distances; The plurality of welding space jump distances are serialized and minimum value calls are performed to obtain the welding trajectory parameters.

3. The method according to claim 2, wherein The method further comprises: Interactively obtaining material parameters and thickness parameters of the target assembly, and using the material parameters and thickness parameters as constraints to obtain a sample welding control parameter set, wherein the sample welding control parameter set includes a plurality of sample weld parameters, a plurality of sample welding strengths, and a plurality of sample welding control parameters; Constructing a laser control analysis model based on a CNN neural network, and using the sample welding control parameter set to perform training optimization on the laser control analysis model; Presetting a multi-level weld width constraint, and traversing the multiple welding trajectories based on the multi-level weld width constraint, and splitting the multiple welding trajectories into multiple groups of connecting weld widths at a secondary level; Interactively obtaining multi-region welding strength constraints of the target assembly, and dividing the multi-region welding strength constraints according to the multiple welding trajectories to obtain multiple groups of connection welding strengths; Synchronizing the multiple sets of connection weld widths and the multiple sets of connection weld strengths to the laser control analysis model to obtain multiple sets of local welding control parameters, and serializing the multiple sets of local welding control parameters according to the welding trajectory parameters to generate the welding control parameters; The welding trajectory parameters and the welding control parameters are fitted to generate the welding path control.

4. The method according to claim 3, wherein The welding repair analysis module performs welding repair analysis according to the real-time interference fringe sequence to obtain repair path control, and the method further includes: The welding repair analysis module includes a welding quality identification submodule and a repair path analysis submodule; The welding quality identification submodule dynamically identifies welding deviations according to the real-time interference fringe sequence to obtain a welding deviation node set, wherein the welding deviation node set includes K deviation node position information and K deviation node image features; The repair path analysis submodule performs welding repair analysis based on the welding deviation node set to obtain a welding repair control set; The welding repair control set is fitted to the welding trajectory parameters to obtain the repair path control.

5. The method according to claim 4, wherein The welding quality identification submodule dynamically identifies welding deviations based on the real-time interference fringe sequence to obtain a welding deviation node set, wherein the welding deviation node set includes K deviation node position information and K deviation node image features. The method further includes: Classifying the plurality of real-time interference fringe images of the real-time interference fringe sequence based on interference fringe overlap to obtain a plurality of groups of real-time interference fringe images, wherein the plurality of real-time interference fringe images have a plurality of image acquisition position identifiers; Presetting a frequency threshold, and screening the multiple groups of real-time interference fringe images to obtain H groups of abnormal interference fringe images based on the preset frequency threshold; splicing a plurality of real-time interference fringe images of the real-time interference fringe sequence based on interference fringe overlap to obtain an interference fringe splicing image, and calculating the spacing between adjacent interference fringes based on the interference fringe splicing image to obtain a plurality of interference fringe spacings; Clustering the plurality of interference fringe spacings to obtain a plurality of groups of interference fringe spacings, and screening the plurality of groups of interference fringe spacings to obtain N groups of interference fringes with abnormal spacings according to the preset frequency threshold; The H groups of abnormal interference fringes and the N groups of abnormal spacing interference fringes are divided into groups to obtain the K deviation node image features, and image acquisition site identification calls are performed on the multiple real-time interference fringe images based on the K deviation node image features to obtain the K deviation node position information.

6. The method according to claim 5, wherein The method further comprises: Obtaining a sample repair control parameter set by calling the material parameter and the thickness parameter as constraints, wherein the sample repair control parameter set includes a density repair control parameter set and a shape repair control parameter set; and The density repair control parameter set includes a plurality of sample abnormal stripe densities, a plurality of sample standard stripe densities and a plurality of sample repair control parameters; and The shape restoration control parameter set includes a plurality of sample abnormal stripe shapes, a plurality of sample standard stripe shapes, and a plurality of sample restoration control parameters; A first welding repair branch is constructed based on the density repair control parameter set, a second welding repair branch is constructed based on the shape repair control parameter set, and the first welding repair branch and the second welding repair branch are connected in parallel to generate a welding repair analysis network.

7. The method according to claim 6, wherein The repair path analysis submodule performs welding repair analysis based on the welding deviation node set to obtain a welding repair control set. The method further includes: Screening the multiple sets of real-time interference fringe images to obtain real-time standard interference fringes based on the preset frequency threshold, and screening the multiple sets of interference fringe spacings to obtain real-time standard fringe density based on the preset frequency threshold; The K deviation node image features, the real-time standard interference fringes and the real-time standard fringe density are input into the welding repair analysis network to obtain K welding repair controls, which constitute the welding repair control set.

Images