A laser welding trajectory real-time optimization control system

Abstract

The application provides a laser welding track real-time optimization control system, and relates to the technical field of laser welding.The system comprises a track fitting module, a correction key point generation module, an initial optimization module, a control analysis module and an optimization compensation module.The track fitting module is used to establish an initial welding track and generate track coordinates.The correction key point generation module is used to configure correction key points.The initial optimization module is used to perform track offset optimization to generate a first optimization result.The control analysis module is used to establish track verification coordinates, perform coordinate offset authentication and generate a control offset result.The optimization compensation module is used to compensate the first optimization result through the control offset result and perform welding track real-time optimization.The application can solve the technical problem that the existing method has poor accuracy and rationality in setting an initial laser welding track, cannot correct welding track deviation in a timely manner during welding, and causes poor welding quality and welding efficiency, and can ensure the stability and accuracy of the welding track, thereby improving the quality and efficiency of laser welding.

Description

Technical Field

[0001] This application relates to the field of laser welding technology, and in particular to a real-time optimization control system for laser welding trajectory. Background Technology

[0002] Laser welding is a highly efficient and precise welding method that uses a high-energy-density laser beam as a heat source. It is an important application of laser material processing technology and has many advantages, including fast welding speed, high welding precision, large welding depth, and minimal deformation. When performing laser welding, it is necessary to comprehensively consider factors such as material properties, welding requirements, and equipment conditions, and rationally design the welding trajectory to ensure welding quality and efficiency. Simultaneously, it is also necessary to ensure the stability and accuracy of the welding trajectory through real-time monitoring and adjustment of welding parameters.

[0003] Currently, existing laser welding methods suffer from poor accuracy and rationality in setting the initial laser welding trajectory, and cannot promptly optimize and correct deviations in the welding trajectory during the welding process, resulting in poor welding quality and efficiency. Summary of the Invention

[0004] The purpose of this application is to provide a real-time optimization and control system for laser welding trajectory, in order to solve the technical problems of poor accuracy and rationality of the initial laser welding trajectory setting in existing laser welding methods, and the inability to timely optimize and correct welding trajectory deviations during the welding process, resulting in poor welding quality and welding efficiency.

[0005] In view of the above problems, this application provides a real-time optimization and control system for laser welding trajectory. The system includes: a feature establishment module, used to establish an initial image set of the workpiece, perform weld seam fitting based on the initial image set, and establish weld seam features, wherein the weld seam features are the features of the workpiece before welding, and the weld seam features include weld seam position features, weld seam shape features, and weld seam depth features; a trajectory fitting module, used to establish a unified coordinate system, perform weld seam fitting based on the weld seam position features, establish an initial weld seam trajectory, and generate trajectory coordinates; and a key point correction generation module, used to configure an initial correction density, perform position key analysis of the initial weld seam trajectory based on the weld seam features, and establish key value features, so as to achieve the desired result. The system comprises: a key value feature and an initial correction density configuration for key correction points; an initial optimization module for trajectory offset optimization based on the key correction points and the initial weld trajectory to generate a first optimization result; a control analysis module for image acquisition of the weld completion area based on machine vision, establishing trajectory verification coordinates through the image acquisition results, performing coordinate offset authentication using the trajectory verification coordinates and the trajectory coordinates, and generating a control offset result; and an optimization compensation module for compensating the first optimization result using the control offset result to establish a second optimization result, and performing real-time optimization of the laser welding trajectory using the second optimization result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] A feature establishment module is constructed to establish an initial image set of the workpiece, perform weld seam fitting based on the initial image set, and establish weld seam features, wherein the weld seam features are the features of the workpiece before welding, and the weld seam features include weld seam position features, weld seam shape features, and weld seam depth features; a trajectory fitting module is constructed to establish a unified coordinate system, perform weld seam fitting based on the weld seam position features, establish an initial weld seam trajectory, and generate trajectory coordinates; a correction key point generation module is constructed to configure an initial correction density, perform position key analysis of the initial weld seam trajectory based on the weld seam features, establish key value features, and configure correction key points with the key value features and the initial correction density; an initial optimization module is constructed to optimize the trajectory offset based on the correction key points and the initial weld seam trajectory, and generate a first optimization result; a control analysis module is constructed to acquire images of the welded area based on machine vision, establish trajectory verification coordinates based on the image acquisition results, perform coordinate offset authentication with the trajectory verification coordinates and the trajectory coordinates, and generate a control offset result; an optimization compensation module is constructed to compensate the first optimization result with the control offset result, establish a second optimization result, and perform real-time optimization of the laser welding trajectory with the second optimization result. In other words, by fitting the weld seam based on its positional features, an initial weld seam trajectory is established, and trajectory coordinates are generated. Then, based on the weld seam features, a criticality analysis of the welding position is performed on the initial weld seam trajectory to establish key value features of the weld seam position. Correction key points are then configured based on these key value features and the initial correction density. Next, the initial weld seam trajectory is optimized based on the correction key points to obtain a first optimization result. Furthermore, during laser welding, trajectory verification coordinates are established based on image acquisition results of the welded area. Coordinate offset authentication is performed using the trajectory verification coordinates and the trajectory coordinates to generate a control offset result. Finally, the first optimization result is compensated based on the control offset result to establish a second optimization result. Real-time optimization of the laser welding trajectory is then performed based on the second optimization result. This improves the accuracy of the initial laser welding trajectory setting and achieves timely correction of welding trajectory deviations, ensuring the stability and accuracy of the welding trajectory. Ultimately, this improves the technical effect of enhancing the quality and efficiency of laser welding.

[0008] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0010] Figure 1 This is a schematic diagram of the structure of a real-time optimization control system for laser welding trajectory according to this application;

[0011] Figure 2 This is a schematic diagram of the process for generating the first optimization result in a real-time optimization control system for laser welding trajectory according to this application.

[0012] Explanation of reference numerals in the attached figures:

[0013] Feature creation module 11, trajectory fitting module 12, correction key point generation module 13, initial optimization module 14, control analysis module 15, optimization compensation module 16. Detailed Implementation

[0014] This application provides a real-time optimization and control system for laser welding trajectories, which solves the technical problems of poor accuracy and rationality in the initial laser welding trajectory setting of existing laser welding methods, and the inability to timely and targetedly optimize and correct welding trajectory deviations during the welding process, resulting in poor welding quality and efficiency. It can improve the accuracy of the initial laser welding trajectory setting, while achieving the goal of timely correction of welding trajectory deviations, ensuring the stability and accuracy of the welding trajectory, and ultimately achieving the technical effect of improving laser welding quality and efficiency.

[0015] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0016] Example

[0017] Please see the appendix Figure 1 This application provides a real-time optimization and control system for laser welding trajectory, comprising:

[0018] The feature establishment module 11 is used to establish an initial image set of the workpiece, perform weld fitting based on the initial image set, and establish weld features, wherein the weld features are the workpiece features before welding, and the weld features include weld position features, weld shape features, and weld depth features.

[0019] Specifically, laser welding is a highly efficient and precise welding method that uses a high-energy-density laser beam as a heat source. This technology is widely used in many fields, including automobile manufacturing, aerospace, electronic assembly, and medical device manufacturing. The principle of laser welding includes two main aspects: heat conduction welding and laser deep penetration welding.

[0020] First, the target workpiece is acquired, which refers to the object to be laser welded. This target workpiece can be set according to the actual situation, such as a car frame or aerospace equipment. Next, images of the welding area of ​​the target workpiece are acquired using an image sensor, obtaining an initial image set of the welding area. Then, weld seam fitting is performed based on the weld seam information in the initial image set to construct weld seam features. These weld seam features refer to the characteristics of the welding area of ​​the target workpiece before welding, including weld seam location features, weld seam shape features, and weld seam depth features. The weld seam shape features include weld seam shape and size information. Obtaining these weld seam features provides a basis for the next step of welding analysis and the construction of the initial welding trajectory.

[0021] The trajectory fitting module 12 is used to establish a unified coordinate system, perform weld fitting based on the weld position features, establish an initial weld trajectory, and generate trajectory coordinates.

[0022] Specifically, firstly, a suitable reference point is selected as the origin of the coordinate system, such as the starting welding point, and a unified coordinate system is established based on the origin of the coordinate system. Then, within the unified coordinate system, the weld positions are fitted and connected sequentially from the origin of the coordinate system based on the weld position characteristics to generate an initial weld trajectory. Within the initial weld trajectory, multiple weld positions are marked based on the weld position characteristics to generate trajectory coordinates, which include multiple weld position coordinates.

[0023] The key point generation module 13 is used to configure the initial correction density, perform position key analysis of the initial weld trajectory based on the weld features, establish key value features, and configure correction key points with the key value features and the initial correction density.

[0024] Specifically, firstly, the initial calibration density is configured. The initial calibration density is the calibration density, which is the number of calibration points within a certain size range. Those skilled in the art can set it according to the welding accuracy requirements. The higher the welding accuracy requirement, the greater the initial calibration density. For example, if the weld trajectory is 10 centimeters and the initial calibration density is 10, it means that there are 10 calibration points in the weld trajectory. In the initial state, the interval between the calibration points is the same. Next, a criticality analysis is performed on the weld position of the initial weld trajectory based on the weld features. The more complex the weld shape, the larger the weld area, and the deeper the weld depth, the higher the importance of the weld position, and thus the more critical the weld position is in the initial weld trajectory. A comprehensive evaluation is performed based on the weld shape features, weld depth features, and weld position importance, such as by setting adaptation weights for weighted calculations. Based on the comprehensive evaluation results, a key value feature of the weld position is established, where a larger comprehensive evaluation result results in a larger key value feature. Finally, the correction points configured based on the initial correction density in the initial weld trajectory are optimized based on the key value features. Specifically, the interval between correction points is adjusted so that weld positions with larger key value features are prioritized for correction points, while the number of correction points remains unchanged, generating correction key points. By optimizing the initial correction points based on the key values ​​of the weld position, the accuracy and rationality of the initial correction point settings can be improved.

[0025] The initial optimization module 14 is used to optimize the trajectory offset based on the correction key points and the initial weld trajectory, and generate a first optimization result;

[0026] Specifically, trajectory offset optimization is performed using the correction key points and the initial weld trajectory. That is, the trajectory angle compensation is performed on the offset trajectory in the real-time welding process based on the correction key points and the initial weld trajectory to determine the optimal turning angle and obtain the first optimization result. The first optimization result is the optimal turning angle, which is the angle that the welding head needs to be adjusted during the welding process in order to better track the real-time weld trajectory and enable the welding head to weld more accurately along the weld.

[0027] The control analysis module 15 is used to acquire images of the welding completion area based on machine vision, establish trajectory verification coordinates through the image acquisition results, perform coordinate offset authentication using the trajectory verification coordinates and the trajectory coordinates, and generate control offset results.

[0028] Specifically, the welding completed area is image acquired using machine vision technology. Machine vision refers to an integrated image acquisition system, including a high-resolution industrial camera, appropriate light source, and image processing software, to clearly capture images of the welding completed area and obtain image acquisition results of the welding completed area. Then, trajectory verification coordinates are established based on the image acquisition results. The trajectory verification coordinates refer to the weld coordinate information of the actual weld trajectory. The trajectory verification coordinates are compared with the trajectory coordinates through a traversal of coordinate offsets to determine multiple coordinate deviations and generate control offset results.

[0029] The optimization compensation module 16 is used to compensate the first optimization result through the control offset result, establish a second optimization result, and perform real-time optimization of the laser welding trajectory using the second optimization result.

[0030] Specifically, the first optimization result is compensated by the control offset result, that is, the trajectory deviation caused by the control offset result is subtracted from the first optimization result to eliminate the trajectory deviation caused by the control deviation, resulting in a second optimization result. Finally, the laser welding trajectory is optimized in real time based on the second optimization result. By performing coordinate offset verification based on the real-time weld trajectory and the initial weld trajectory, a control offset result is generated. Then, the first optimization result is compensated based on the control offset result, which can improve the precision and accuracy of the welding trajectory optimization, thereby ensuring the stability and accuracy of the welding trajectory.

[0031] A real-time optimization and control system for laser welding trajectories is provided. The system includes: a feature establishment module for establishing an initial image set of the workpiece, performing weld seam fitting based on the initial image set, and establishing weld seam features, wherein the weld seam features are the workpiece features before welding, and the weld seam features include weld seam position features, weld seam shape features, and weld seam depth features; a trajectory fitting module for establishing a unified coordinate system, performing weld seam fitting based on the weld seam position features, establishing an initial weld seam trajectory, and generating trajectory coordinates; and a key point correction generation module for configuring an initial correction density, performing position key analysis of the initial weld seam trajectory based on the weld seam features, and establishing... The system comprises: a key value feature module, which configures correction key points based on the key value feature and the initial correction density; an initial optimization module, which optimizes the trajectory offset based on the correction key points and the initial weld trajectory to generate a first optimization result; a control analysis module, which acquires images of the welded area using machine vision, establishes trajectory verification coordinates based on the image acquisition results, performs coordinate offset authentication using the trajectory verification coordinates and the trajectory coordinates, and generates a control offset result; and an optimization compensation module, which compensates for the first optimization result using the control offset result to establish a second optimization result, and performs real-time optimization of the laser welding trajectory using the second optimization result. This system addresses the technical problems of existing laser welding methods, such as poor accuracy and rationality in setting the initial laser welding trajectory, and the inability to promptly and specifically optimize and correct welding trajectory deviations during the welding process, resulting in poor welding quality and efficiency. By fitting the weld seam based on its positional features, an initial weld seam trajectory is established, and trajectory coordinates are generated. Then, based on the weld seam features, a criticality analysis of the welding position is performed on the initial weld seam trajectory to establish key value features of the weld seam position. Correction key points are then configured based on the key value features and the initial correction density. Next, the initial weld seam trajectory is optimized based on the correction key points to obtain a first optimization result. Furthermore, during laser welding, trajectory verification coordinates are established based on image acquisition results of the welded area. Coordinate offset authentication is performed using the trajectory verification coordinates and the trajectory coordinates to generate control offset results. Finally, the first optimization result is compensated based on the control offset results to establish a second optimization result. Real-time optimization of the laser welding trajectory is then performed based on the second optimization result. This improves the accuracy of the initial laser welding trajectory setting and achieves timely correction of welding trajectory deviations, ensuring the stability and accuracy of the welding trajectory, ultimately improving the technical effect of improving laser welding quality and efficiency.

[0032] Further details are attached. Figure 2 As shown, the initial optimization module 14 is further configured to:

[0033] Configure a search starting point, wherein the search starting point is the starting node for trajectory search compensation, and the search starting point is determined by adjacent correction key points and real-time weld trajectory;

[0034] Obtain the next adjacent correction key point corresponding to the search starting point, use it as the aiming point, and determine the aiming distance based on the aiming point and the search starting point;

[0035] The offset trajectory is determined by the real-time weld trajectory and the initial weld trajectory, and the trajectory compensation optimization of the offset trajectory is performed based on the pre-aiming distance to establish the optimization turning angle;

[0036] The optimized steering angle is taken as the first optimization result.

[0037] Specifically, firstly, a search starting point is configured, which is the starting node for trajectory search compensation. This starting point is determined by adjacent correction key points and the real-time weld trajectory. Next, the next adjacent correction key point corresponding to the search starting point is obtained and used as a preview point. Then, a preview distance is determined based on the preview point and the search starting point; this preview distance is the weld distance between the search starting point and the preview point.

[0038] Then, the real-time weld trajectory is compared with the initial weld trajectory to determine the offset trajectory. Next, the offset trajectory is optimized for trajectory compensation based on the pre-aiming distance. The optimized turning angle is obtained based on the optimization result. The optimized turning angle refers to the angle that the welding head needs to adjust during the welding process to better track the real-time weld trajectory, enabling the welding head to weld more accurately along the weld. Finally, the optimized turning angle is taken as the first optimization result.

[0039] Furthermore, the initial optimization module 14 is also used for:

[0040] The calibration trajectory direction of the aiming point is determined by the initial weld trajectory;

[0041] When performing trajectory compensation optimization for the offset trajectory, the fitting trajectory direction of the pre-aiming point corresponding to each steering angle is obtained;

[0042] The consistency of the fitted trajectory direction and the calibrated trajectory direction is evaluated, and the optimization judgment is made based on the consistency evaluation results to establish the optimization steering angle.

[0043] Specifically, the calibration trajectory direction of the pre-aiming point is determined based on the initial weld trajectory, and the calibration trajectory direction is the trajectory direction from the search starting point to the pre-aiming point. When performing trajectory compensation optimization for the offset trajectory, firstly, multiple turning angles are set based on a preset step size, where the preset step size is the angle change range, for example, setting the step size to 0.5, that is, setting a turning angle every 0.5°. Then, based on the multiple turning angles, combined with the search starting point, multiple pre-aiming point fitted trajectory directions are generated, where each turning angle corresponds to a pre-aiming point fitted direction. Then, the consistency between the multiple pre-aiming point fitted trajectory directions and the calibration trajectory direction is evaluated, that is, the trajectory deviation between the multiple pre-aiming point fitted trajectory directions and the calibration trajectory direction is calculated respectively, and the pre-aiming point fitted trajectory direction with the smallest trajectory deviation is taken as the optimized trajectory direction, and the turning angle of the optimized trajectory direction is set as the optimized turning angle.

[0044] Furthermore, the initial optimization module 14 is also used for:

[0045] An approximation stage is established based on the offset trajectory, wherein the approximation stage includes an initial approximation stage and an end approximation stage;

[0046] Configure the stage approximation strategy according to the aforementioned approximation stage, and establish the stage approximation turning angle;

[0047] The optimal steering angle is established by approximating the steering angle at the aforementioned stage.

[0048] Specifically, in laser welding, establishing an approximation phase is a common strategy to ensure the accuracy and reliability of the welding trajectory, especially when dealing with complex welds or requiring high-precision control. First, an approximation phase is established based on the offset trajectory. This phase includes an initial approximation phase and an end approximation phase. The purpose of the initial approximation phase is to quickly and accurately guide the welding head or laser beam to a position close to the weld start point, preparing for subsequent fine welding operations. The purpose of the end approximation phase is to provide more precise control over the welding head or laser beam before the weld ends, ensuring the quality and integrity of the weld.

[0049] Next, a stage approximation strategy is configured based on the aforementioned approximation stages. Establishing the stage approximation turning angle is crucial to ensuring a smooth and accurate transition between stages for the welding head or laser beam. The stage approximation turning angle is typically related to factors such as the offset of the welding trajectory, the moving speed of the welding head, and welding quality requirements. The initial approximation stage requires rapid and stable approach to the weld initiation point, therefore the turning angle adjustment range is relatively large. The final approximation stage requires more precise and accurate control, hence the smaller turning angle adjustment range, which improves the accuracy of the turning angle setting. Finally, an optimal turning angle is established based on the stage approximation turning angle, which improves the accuracy and rationality of the optimal turning angle setting, thereby enhancing the accuracy and efficiency of laser welding.

[0050] Furthermore, the system also includes an anomaly detection module, which is used for:

[0051] The deviation of the offset trajectory is determined based on a preset threshold, and a deviation determination result is established;

[0052] If the deviation determination result is a result that cannot meet the preset threshold, a shutdown abnormality command is reported, and shutdown management is performed using the shutdown abnormality command.

[0053] Specifically, firstly, deviation analysis is performed on the offset trajectory to determine the trajectory deviation degree. The trajectory deviation degree can be set according to the deviation angle and deviation distance of the welding trajectory. The larger the deviation angle and the larger the deviation distance, the greater the corresponding deviation degree. Next, the deviation degree is judged based on a preset threshold to generate a deviation judgment result. The preset threshold can be set by those skilled in the art based on actual conditions. When the deviation degree is greater than the preset threshold, it indicates that the deviation judgment result cannot meet the preset threshold, indicating that an abnormality or deviation has occurred in the welding process, which may affect the welding quality and safety. At this time, a shutdown abnormality command is reported, and shutdown management is performed based on the shutdown abnormality command to ensure welding quality and safety.

[0054] Furthermore, the control analysis module 15 is also used for:

[0055] The initial weld trajectory is mapped to the image acquisition result, and the search area is configured based on the mapping result;

[0056] The search region is traversed and identified based on convolution kernels, and trajectory verification coordinates are established based on the traversal and identification results.

[0057] Specifically, firstly, the initial weld trajectory and the image acquisition results are unified using a coordinate system. Then, the initial weld trajectory is mapped to the image acquisition results, and a search region is configured based on the mapping result. For example, a search threshold can be set, and the mapping result is expanded based on the search threshold to obtain the search region. By configuring the search region based on the initial weld trajectory mapping result, the weld position can be located more accurately, thereby reducing the amount of image data processing and improving the analysis efficiency and accuracy of trajectory verification coordinates. Then, an appropriate convolutional kernel type is selected based on the weld features, and a convolutional neural network is used to traverse and identify weld features and extract features from the search region using the convolutional kernel. The trajectory verification coordinates are constructed based on the feature extraction results.

[0058] Furthermore, the control analysis module 15 is also used for:

[0059] Based on the correction key points, key coordinates are extracted from the trajectory verification coordinates to establish key coordinate extraction results;

[0060] Configure the temporal correlation coefficient, perform coordinate offset authentication of key coordinate extraction results and initial weld trajectory, compensate the coordinate offset authentication results based on the temporal correlation coefficient, and generate control offset results based on the compensation results.

[0061] Specifically, key coordinates are extracted from the trajectory verification coordinates based on the correction key points to obtain key coordinate extraction results. A temporal correlation coefficient is configured, which describes the degree of welding correlation between different key coordinates. This coefficient can be set according to actual conditions, such as: collecting time-series data during the welding process, including real-time values ​​of welding parameters and corresponding weld trajectory coordinates; then calculating the temporal correlation coefficient based on the Pearson correlation coefficient principle; then, based on the temporal correlation coefficient, verifying the coordinate offset between the key coordinate extraction results and the initial weld trajectory, i.e., calculating the trajectory deviation of the key coordinates; then, compensating the coordinate offset verification results based on the temporal correlation coefficient, i.e., optimizing the weld offset results according to the correlation of the weld trajectory coordinates; finally, generating control offset results from the compensation results.

[0062] Furthermore, the control analysis module 15 is also used for:

[0063] The welding status is evaluated based on the image acquisition results, and a status evaluation result is generated.

[0064] Construct the formula for calculating laser power density per unit area:

[0065] ;

[0066] in, Laser power density per unit area The output power of the laser. The duration of laser action. For laser processing and welding speed, The diameter of the light spot;

[0067] Based on the state evaluation results and the formula for calculating laser power density per unit area, the laser control parameters are optimized through coordination, and the optimization results are established.

[0068] The control optimization of the laser is performed based on the aforementioned coordination optimization results.

[0069] Specifically, firstly, welding state features are extracted based on the image acquisition results. These features include weld shape, weld width, surface flatness, and weld pool morphology. Then, welding state evaluation is performed based on these features. The evaluation method can construct a state evaluation model based on a feedforward neural network and evaluate the welding state features based on the model. Finally, a state evaluation result is generated, where the welding state evaluation result characterizes the quality of the welding; a higher result indicates better welding quality.

[0070] Construct the formula for calculating laser power density per unit area: In the formula for calculating laser power density per unit area, Laser power density per unit area The output power of the laser. The duration of laser action. For laser processing and welding speed, Let the laser be the spot diameter. Then, based on the state evaluation results and the formula for calculating laser power density per unit area, the laser control parameters are optimized in a coordinated manner. First, the laser control parameter thresholds are obtained. Then, using the laser control parameter thresholds as the optimization space, the laser control parameters are optimized using optimization algorithms. Commonly used optimization algorithms include genetic algorithms and particle swarm optimization algorithms. The appropriate optimization method can be selected according to the actual situation to obtain the coordinated optimization result. The coordinated optimization result is the laser control parameter with the highest state evaluation result during the optimization process. Finally, the laser control is optimized based on the coordinated optimization result.

[0071] The above method can solve the technical problems of poor accuracy and rationality in the initial laser welding trajectory setting of existing laser welding methods, as well as the inability to timely optimize and correct welding trajectory deviations during the welding process, resulting in poor welding quality and efficiency. It can improve the accuracy of the initial laser welding trajectory setting, and at the same time achieve the purpose of timely correction of welding trajectory deviations, ensuring the stability and accuracy of the welding trajectory, and ultimately achieving the technical effect of improving the quality and efficiency of laser welding.

[0072] In summary, the real-time optimization control system for laser welding trajectory provided in this application has the following technical effects:

[0073] By fitting the weld seam based on its positional features, an initial weld seam trajectory is established, and trajectory coordinates are generated. Then, based on the weld seam features, a criticality analysis of the welding position is performed on the initial weld seam trajectory to establish key value features of the weld seam position. Correction key points are then configured based on the key value features and the initial correction density. Next, the initial weld seam trajectory is optimized based on the correction key points to obtain a first optimization result. Furthermore, during laser welding, trajectory verification coordinates are established based on image acquisition results of the welded area. Coordinate offset authentication is performed using the trajectory verification coordinates and the trajectory coordinates to generate control offset results. Finally, the first optimization result is compensated based on the control offset results to establish a second optimization result. Real-time optimization of the laser welding trajectory is then performed based on the second optimization result. This improves the accuracy of the initial laser welding trajectory setting and achieves timely correction of welding trajectory deviations, ensuring the stability and accuracy of the welding trajectory, ultimately improving the technical effect of improving laser welding quality and efficiency.

[0074] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0075] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A laser welding trajectory real-time optimization control system, characterized in that, The system comprises: a feature establishing module, configured to establish an initial image set of a workpiece, perform weld fitting based on the initial image set, and establish weld features, wherein the weld features are features of the workpiece before welding, and the weld features include weld position features, weld shape features, and weld depth features; a trajectory fitting module, configured to establish a unified coordinate system, perform weld fitting based on the weld position features, establish an initial weld trajectory, and generate trajectory coordinates; a correction key point generating module, configured to configure an initial correction density, perform position key analysis of the initial weld trajectory based on the weld features, establish key value features, and configure correction key points based on the key value features and the initial correction density; an initial optimization module, configured to perform trajectory offset optimization based on the correction key points and the initial weld trajectory, and generate a first optimization result; a control analysis module, configured to perform image acquisition of a welding completion area based on machine vision, establish trajectory verification coordinates based on the image acquisition result, perform coordinate offset authentication based on the trajectory verification coordinates and the trajectory coordinates, and generate a control offset result; an optimization compensation module, configured to compensate the first optimization result based on the control offset result, establish a second optimization result, and perform real-time optimization of a laser welding trajectory based on the second optimization result; the initial optimization module is further configured to: configure a search starting point, wherein the search starting point is a starting node for trajectory search compensation, and the search starting point is determined based on adjacent correction key points and a real-time weld trajectory; obtain a next adjacent correction key point corresponding to the search starting point, use the next adjacent correction key point as a preview point, and determine a preview distance based on the preview point and the search starting point; determine an offset trajectory based on the real-time weld trajectory and the initial weld trajectory, perform trajectory compensation optimization of the offset trajectory based on the preview distance, and establish an optimization turning angle; use the optimization turning angle as the first optimization result; the control analysis module is further configured to: extract key coordinates from the trajectory verification coordinates based on the correction key points, and establish a key coordinate extraction result; configure a time sequence correlation coefficient, the time sequence correlation coefficient is used to describe a welding correlation degree between different key coordinates, perform coordinate offset authentication of the key coordinate extraction result and the initial weld trajectory, compensate a coordinate offset authentication result based on the time sequence correlation coefficient, and generate the control offset result based on a compensation result.

2. The system of claim 1, wherein, the initial optimization module is further configured to: determine a calibration trajectory direction of a preview point based on the initial weld trajectory; when performing trajectory compensation optimization of the offset trajectory, obtain a preview point fitting trajectory direction corresponding to each turning angle; perform consistency evaluation based on the fitting trajectory direction and the calibration trajectory direction, perform optimization determination based on a consistency evaluation result, and establish the optimization turning angle.

3. The system of claim 2, wherein, the initial optimization module is further configured to: establish an approximation phase based on the offset trajectory, wherein the approximation phase includes an initial approximation phase and a terminal approximation phase; configure a phase approximation strategy based on the approximation phase, and establish a phase approximation turning angle; establish the optimization turning angle based on the phase approximation turning angle.

4. The system of claim 1, wherein, The system further comprises an abnormality judgment module, which is configured to: perform a deviation degree judgment on the offset trajectory based on a preset threshold, and establish a deviation judgment result; if the deviation judgment result is a result that cannot satisfy the preset threshold, issue a stop abnormality instruction, and perform stop management according to the stop abnormality instruction.

5. The system of claim 1, wherein, The control analysis module is further configured to: map the initial weld seam trajectory to the image acquisition result, and configure a search area according to a mapping result; perform a convolution kernel-based traversal identification on the search area, and establish a trajectory verification coordinate according to a traversal identification result.

6. The system of claim 1, wherein, The control analysis module is further configured to: perform a state evaluation on a welding state according to the image acquisition result, and generate a state evaluation result; construct a laser power density per unit area calculation formula: ； wherein, is the laser power density per unit area, is the laser output power, is the laser action time, is the laser processing welding speed, is the spot diameter; perform a coordinated optimization of laser control parameters based on the state evaluation result and the laser power density per unit area calculation formula, and establish a coordinated optimization result; perform a control optimization of the laser according to the coordinated optimization result.

Images