Multi-robot cooperation welding track planning method and system based on 3D vision

Abstract

The invention is suitable for the technical field of industrial automatic welding, and provides a multi-robot cooperation welding track planning method and system based on 3D vision, and the method comprises the steps that historical welding data, located in a double-robot handover welding area, of a preset number of welded historical workpieces before a target batch of workpieces is obtained; laser projection patterns in the handover welding areas of the front robot and the rear robot corresponding to each historical workpiece are extracted from the historical welding data, and the maximum change area of each laser projection pattern is determined; according to the method, the maximum change area recognition and 3D visual analysis technology of the laser projection pattern is introduced, the rear robot heat accumulation parameters are combined, an angle correction mechanism based on the deviation trend slope is constructed, and dynamic compensation of the welding deviation along with the time evolution trend under the double-robot handover welding scene is achieved for the first time.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial automated welding, and particularly relates to a welding trajectory planning method and system for multi-robot collaboration based on 3D vision. Background Art

[0002] In modern industrial manufacturing scenarios, the use of multi-robot collaborative welding has become the mainstream technical path to improve welding efficiency and consistency. To achieve efficient welding scheduling for multiple workstations, several workpieces with the same structure are usually grouped into a batch, and multiple welding robots respectively perform parallel processing on their designated welding areas, and perform sequential welding collaboration in the handover welding area with a certain spatial overlap. In such a dual-robot handover welding scenario, to ensure the continuity of the weld seam and the consistency of quality, the rear robot needs to make fine angle adjustments based on the weld seam feature information left by the front robot in the handover welding area to cope with the influence of factors such as weld seam geometric changes and thermal deformation on trajectory planning.

[0003] To support the above-mentioned fine angle adjustment operation, in the prior art, a laser projection device combined with a vision sensing module is widely used to optically scan the weld seam surface, and by identifying the local changes in the laser pattern, features such as weld seam boundaries, curvature changes, and height mutations are assisted in judgment, and then based on these recognition results, a welding angle correction value is generated to guide the rear robot to complete the welding path correction in the handover area. Such technical solutions have been applied in many industrial welding lines, and can correct local trajectory changes caused by workpiece precision errors or thermal deformation to a certain extent, improving the processing precision at the weld seam connection.

[0004] However, the prior art solutions generally have the following technical defects: First, the system defaults that the rear robot can stably execute the angle correction value deduced based on the weld seam features of the front robot, without considering the problem of the decline in motion accuracy of the rear robot body due to heat accumulation during long-term high-intensity welding; Second, when the number of workpieces in the target batch is large, the rear robot suffers from mechanical structure response lag and increased angle execution error due to heat accumulation, and finally the actual deviation between its welding effect and the set correction angle shows a gradually increasing trend. The prior art does not dynamically identify and correct this deviation trend, which easily leads to the deterioration of the quality of the handover weld seam as the batch progresses, and it is difficult to meet the requirements of high-consistency welding quality. Therefore, there is an urgent need to construct a path planning method for a dual-robot handover scenario that can sense the welding deviation trend and dynamically correct the angle compensation value. Summary of the Invention

[0005] The purpose of the present invention is to provide a welding trajectory planning method for multi-robot collaboration based on 3D vision, aiming to solve the problems proposed in the background art.

[0006] The present invention is implemented as follows. A welding trajectory planning method for multi-robot collaboration based on 3D vision, the method includes: Obtain the historical welding data of a preset number of previously welded historical workpieces in the dual-robot handover welding area of the target batch of workpieces; Extract the laser projection patterns in the handover welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data, and determine the maximum change area of each laser projection pattern; Quantify the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots in the handover area, and obtain the thermal accumulation parameters of the rear robot for the preset number of historical workpieces over time; Analyze the preset number of historical workpieces to determine whether there is the following characteristic pattern: as time extends, the change trend of the deviation degree between the maximum change areas of the laser projection patterns of the front and rear robots satisfies a preset correlation relationship with the change trend of the thermal accumulation parameters of the rear robot; If it is determined that the above characteristic pattern exists, obtain the initial angle correction value set by the rear robot for the handover welding area, and generate a correction factor according to the change trend of the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots, and dynamically adjust the initial angle correction value.

[0007] As a further limitation of the technical solution of the embodiment of the present invention, the laser projection pattern refers to a specific light spot or pattern projected by the laser device carried by the robot onto the weld surface during welding, which is used to assist in identifying the weld profile, the geometric changes of the weld bead, and the local deformation conditions. Its pattern will generate recognizable structural changes during welding due to workpiece thermal deformation or changes in surface reflection characteristics.

[0008] As a further limitation of the technical solution of the embodiment of the present invention, the step of extracting the laser projection patterns in the handover welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data and determining the maximum change area of each laser projection pattern includes:

[0009] Extract the laser projection patterns projected by the front robot and the rear robot corresponding to each historical workpiece into the handover welding area from the historical welding data;

[0010] Use 3D vision technology to perform structural reconstruction and curvature analysis on the extracted laser projection patterns, identify the area that changes most significantly during the welding process in the pattern, and determine this area as the corresponding maximum change area.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the step of quantifying the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots in the handover area and obtaining the thermal accumulation parameters of the rear robot for the preset number of historical workpieces over time includes: Based on 3D vision technology, extract the spatial position coordinates of the maximum change region of the laser projection patterns corresponding to the front robot and the rear robot in each historical workpiece. Calculate the deviation amount of the maximum change regions of the laser projection patterns of the front and rear robots in terms of spatial position, and use this deviation amount as the deviation degree of the corresponding historical workpiece. Obtain the thermal accumulation parameters of the rear robot when welding is completed for each historical workpiece. The thermal accumulation parameters include the cumulative operation duration during the welding process, the temperature change value of the key part, and its derivative function.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the preset correlation refers to: among the previous preset number of historical workpieces, there is a positive correlation between the change trend of the thermal accumulation parameters of the rear robot and the change trend of the deviation degree of the maximum change regions of the laser projection patterns of the front and rear robots, and this positive correlation satisfies the following conditions: the change trend slopes of the two within the preset time interval are respectively extracted as the first slope value and the second slope value, and the ratio of the first slope value to the second slope value is within the allowable range expressed by the preset function, or satisfies the preset multiple relationship that the second slope value is a multiple of the first slope value, so as to determine that the trend of the influence of the thermal accumulation of the rear robot on the welding deviation of the butt welding area conforms to the regular requirements.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, if it is determined that the above characteristic pattern exists, the steps of obtaining the initial angle correction value set by the rear robot for the butt welding area and generating a correction factor according to the change trend of the deviation degree of the maximum change regions of the laser projection patterns of the front and rear robots to dynamically adjust the initial angle correction value include: After determining that the above characteristic pattern exists, obtain the initial angle correction value set by the rear robot based on the butt welding area. Obtain the change trend slope of the deviation degree of the maximum change regions of the laser projection patterns of the front and rear robots within the preset time interval: the second slope value. Set the second slope value as the correction factor, and correct the initial angle correction value through the correction factor to obtain the corrected angle correction value. Apply the corrected angle correction value to the welding trajectory planning of the butt welding area of other workpieces to be welded subsequently in the target batch of workpieces by the rear robot, so as to realize the compensatory optimization of the initial angle correction value.

[0014] A welding trajectory planning system for multi-robot cooperation based on 3D vision, the system includes: a data acquisition module, a maximum change region determination module, a deviation degree quantification module, a characteristic pattern judgment module, and an angle correction value adjustment module, where:

[0015] A data acquisition module, configured to acquire historical welding data of a preset number of previously welded historical workpieces in the double-robot handover welding area of the target batch of workpieces; A maximum change area determination module, configured to respectively extract laser projection patterns within the handover welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data, and determine the maximum change area of each laser projection pattern; the laser projection pattern refers to a specific light spot or pattern projected by the laser device carried by the robot onto the weld surface during the welding process, which is used to assist in identifying the weld profile, bead geometry changes, and local deformation conditions, and its pattern will generate recognizable structural changes during the welding process due to workpiece thermal deformation or changes in surface reflection characteristics; A deviation degree quantification module, configured to quantify the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots in the handover area, and obtain the thermal accumulation parameters of the rear robot for the preset number of historical workpieces over time; A feature pattern judgment module, configured to analyze the preset number of historical workpieces to determine whether there is the following feature pattern: over time, the change trend of the deviation degree between the maximum change areas of the laser projection patterns of the front and rear robots satisfies a preset correlation relationship with the change trend of the thermal accumulation parameters of the rear robot; The preset correlation relationship means that: among the preset number of historical workpieces, there is a positive correlation between the change trend of the thermal accumulation parameters of the rear robot and the change trend of the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots, and this positive correlation satisfies the following conditions: the change trend slopes within a preset time interval are respectively extracted as a first slope value and a second slope value, and the ratio of the first slope value to the second slope value is within the allowable range expressed by a preset function, or satisfies a preset multiple relationship where the second slope value is a multiple of the first slope value, so as to determine that the trend of the influence of the thermal accumulation of the rear robot on the welding deviation in the handover welding area conforms to the regularity requirements; An angle correction value adjustment module, configured to, if it is determined that there is the above feature pattern, obtain the initial angle correction value set by the rear robot for the handover welding area, and generate a correction factor according to the change trend of the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots, and dynamically adjust the initial angle correction value.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the maximum change area determination module specifically includes: A pattern extraction unit, configured to extract the laser projection patterns projected by the front robot and the rear robot corresponding to each historical workpiece into the handover welding area from the historical welding data; A pattern change analysis unit is used to perform structural reconstruction and curvature analysis on the extracted laser projection pattern using 3D vision technology, identify the area in the pattern that changes most significantly during the welding process, and determine this area as the corresponding maximum change area.

[0017] As a further limitation of the technical solution of the embodiment of the present invention, the deviation degree quantification module specifically includes: A coordinate extraction unit is used to extract the spatial position coordinates of the maximum change area of the laser projection patterns corresponding to the front robot and the rear robot in each historical workpiece based on 3D vision technology; A deviation amount calculation unit is used to calculate the deviation amount of the maximum change areas of the laser projection patterns of the front and rear robots in terms of spatial position, and use this deviation amount as the deviation degree of the corresponding historical workpiece; A heat accumulation parameter acquisition unit is used to acquire the heat accumulation parameters of the rear robot when each historical workpiece is welded, and the heat accumulation parameters include the cumulative operation duration during the welding process, the temperature change value of the key part and its derivative function.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the angle correction value adjustment module specifically includes: An initial value acquisition unit is used to acquire the initial angle correction value set by the rear robot based on the handover welding area after determining the existence of the above characteristic pattern; A slope value acquisition unit is used to acquire the change trend slope of the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots within a preset time interval: the second slope value; An angle correction value adjustment unit is used to set the second slope value as a correction factor and correct the initial angle correction value through the correction factor to obtain the corrected angle correction value; A correction value application unit is used to apply the corrected angle correction value to the welding trajectory planning of the handover welding area of other workpieces to be welded in the subsequent target batch of workpieces by the rear robot, so as to achieve the compensatory optimization of the initial angle correction value.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] By introducing the recognition of the maximum change area of the laser projection pattern and 3D vision analysis technology, and combining the thermal accumulation parameters of the robot afterwards, the present invention constructs an angle correction mechanism based on the deviation trend slope, and for the first time realizes the dynamic compensation of the evolution trend of welding deviation over time in the double-robot handover welding scenario. Compared with the existing method of setting a fixed angle correction value only based on the weld characteristics of the front robot, the present invention can identify and correct the problem of correction failure caused by the thermal accumulation of the rear robot, ensure that the welding angle adjustment always adapts to the current working conditions, significantly improves the welding consistency and weld quality in the handover area, and has outstanding intelligence, self-adaptability and engineering application value. Brief Description of the Drawings

[0021] Figure 1 It is a flowchart of the method provided by the embodiment of the present invention; Figure 2 It is a flowchart of determining the maximum change area of the laser projection pattern in the method provided by the embodiment of the present invention; Figure 3 It is a flowchart of calculating the deviation degree corresponding to the historical workpiece in the method provided by the embodiment of the present invention; Figure 4 It is a flowchart of correcting the initial angle correction value in the method provided by the embodiment of the present invention; Figure 5 It is an application architecture diagram of the system provided by the embodiment of the present invention; Figure 6 It is a structural block diagram of the maximum change area determination module in the system provided by the embodiment of the present invention; Figure 7 It is a structural block diagram of the deviation degree quantification module in the system provided by the embodiment of the present invention; Figure 8 It is a structural block diagram of the angle correction value adjustment module in the system provided by the embodiment of the present invention. Detailed Embodiment

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, and are not used to limit the present invention.

[0023] Figure 1 It shows a flowchart of the method provided by the embodiment of the present invention.

[0024] Specifically, a welding trajectory planning method for multi-robot cooperation based on 3D vision, the method specifically includes the following steps: Step S100, obtaining the historical welding data of the preset number of welded historical workpieces in the double-robot handover welding area of the target batch of workpieces.

[0025] In the embodiments of the present invention, the target batch of workpieces refers to a group of workpieces to be welded with exactly the same structural shape, material composition, and welding process parameters, usually multiple duplicates of the same model in a production batch.

[0026] The handover welding area refers to the transition weld area where the front robot finishes welding and the rear robot starts welding, usually located in the space range between the end of the respective working paths of the front and rear robots and the starting section. In this area, there is a continuous relationship between the welding tasks of the front and rear robots. The continuity and geometric consistency of the weld directly affect the welding quality, and it is the key part where the welding trajectory is most likely to deviate during welding trajectory planning.

[0027] In the present invention, the historical welding data specifically includes: the welding image data of the completed welded workpieces, especially the laser projection pattern sequence in the handover welding area; the execution information such as the trajectory control parameters, start and end coordinates, movement speed, and angle correction values recorded during the welding tasks performed by the front robot and the rear robot on the corresponding workpieces; the thermal accumulation state parameters formed during the continuous welding process of the rear robot, such as the cumulative operation duration, the temperature change curve of the key parts, and the derived thermal load index.

[0028] The laser projection pattern refers to the specific light spot or pattern projected by the laser device carried by the robot onto the weld surface during the welding process, which is used to assist in identifying the weld profile, the geometric changes of the weld bead, and the local deformation conditions. Its pattern will produce recognizable structural changes during the welding process due to the thermal deformation of the workpiece or the change of the surface reflection characteristics.

[0029] The laser projection pattern refers to the specific light spot or pattern projected by the laser device carried by the robot onto the weld surface during the welding process, which is used to assist in identifying the weld profile, the geometric changes of the weld bead, and the local deformation conditions. Its pattern will produce recognizable structural changes during the welding process due to the thermal deformation of the workpiece or the change of the surface reflection characteristics. This type of laser pattern recognition belongs to a weld seam auxiliary recognition method with a relatively high maturity in the prior art. Usually, it needs to be used in combination with 3D vision technology to improve the recognition accuracy and the response ability to the micro-deformation of the weld seam. In practical applications, both the front robot and the rear robot should be equipped with such laser projection devices to ensure a geometric recognition basis with continuity and symmetry in the handover welding area.

[0030] In the prior art, after the surface state of the weld seam is usually identified by linking the above-mentioned laser pattern with 3D vision technology, the system automatically analyzes the geometric change characteristics of the weld seam after the front robot completes welding. In particular, it includes morphological information such as the linear deflection, curvature change, or discontinuous breakpoints of the weld seam trajectory. Based on this, the angle correction value for the rear robot in the connecting weld seam area is generated to adjust the initial trajectory planning of all workpieces in the target batch of workpieces, ensuring welding continuity and joint accuracy. However, a key defect of the prior art is that the angle correction value is only calculated based on the output of the front robot's weld seam, without fully considering the heat accumulation effect of the rear robot during long-term continuous welding. As the rear robot continues to operate in a batch of workpieces, its internal structure, torch mechanism, or end effector are affected by factors such as thermal expansion, stiffness change, or dynamic response delay, resulting in a gradual deviation of the actual welding effect from the geometric trend of the weld seam reserved by the front robot even when the same angle correction value is used. This deviation trend is not recognized by the original correction model, thus causing the weld seam deviation to gradually intensify, affecting the welding quality and handover stability.

[0031] The present invention is precisely proposed in view of the above problems. By constructing a correlation model between the heat accumulation parameters and the deviation evolution trend of the weld seam pattern, dynamic compensation for the initial angle correction value is realized, enabling the rear robot to still stably achieve high-precision welding connection under different thermal conditions.

[0032] Further, the welding trajectory planning method for multi-robot cooperation based on 3D vision further includes the following steps:

[0033] Step S200, extract the laser projection patterns in the handover welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data, and determine the maximum change area of each laser projection pattern.

[0034] Specifically, Figure 2 The flowchart of determining the maximum change area of the laser projection pattern is shown.

[0035] Among them, extracting the laser projection patterns in the handover welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data and determining the maximum change area of each laser projection pattern specifically include the following steps: Step S201, extract the laser projection patterns projected by the front robot and the rear robot corresponding to each historical workpiece into the handover welding area from the historical welding data; Step S202, use 3D vision technology to perform structural reconstruction and curvature analysis on the extracted laser projection patterns, identify the area that changes most significantly during the welding process in the pattern, and determine this area as the corresponding maximum change area.

[0036] In an embodiment of the present invention, in order to extract the weld seam state change characteristics of each historical workpiece in the handover welding area, it is necessary to separately obtain the laser projection patterns of the corresponding front robot and rear robot in the handover welding area from the historical welding data, and combine 3D vision analysis means to identify the key areas in the pattern that can best reflect the evolution of the welding state. This process includes the following two specific steps: First, through the image decoding and pose matching algorithm, extract the laser projection patterns of each historical workpiece in the handover welding area from the historical welding data. Specifically, the system extracts the corresponding laser pattern image frames of the front robot and the rear robot in their respective operation stages in the handover welding area based on the image timestamp and robot task log matching strategy. The extraction process combines the projection structured light coding information and the historical workpiece positioning information to achieve high-precision restoration and segmented extraction of the pattern in the handover area.

[0037] Subsequently, use 3D vision technology to perform structure reconstruction and curvature analysis on the above laser projection patterns. Specifically, the spatial point cloud reconstruction technology is used to restore the two-dimensional image sequence to a three-dimensional structure contour, and through the regional curvature change detection algorithm, identify the geometric mutation areas in the pattern caused by factors such as welding stress release, thermal deformation, or structural discontinuity. This area usually shows local paragraphs or edge bands where the curvature significantly deviates from the continuous trend, reflecting the response concentration area where the weld appearance is affected by external disturbances.

[0038] The purpose of identifying the maximum change area in the pattern is to obtain a representative feature area that can most effectively characterize the change trend of the weld surface. The change amplitude and stability of this area directly reflect the influence degree of composite factors such as thermal influence, stress disturbance, and robot execution accuracy change on the weld structure during the welding process. Therefore, it becomes the key data basis for judging the welding deviation trend and formulating the angle correction basis. Especially in the multi-robot handover welding scenario, the deviation degree of this maximum change area not only reflects the change of the workpiece state, but may also indirectly expose the micro differences or coordination disorders between the welding behaviors of the two robots, which is an important basis for subsequent trajectory correction judgment.

[0039] Furthermore, the welding trajectory planning method for multi-robot cooperation based on 3D vision further includes the following steps:

[0040] Step S300, quantify the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots in the handover area, and obtain the heat accumulation parameters of the rear robot for the pre-set number of historical workpieces over time.

[0041] Specifically, Figure 3 Shows the flowchart for calculating the deviation degree corresponding to the historical workpiece.

[0042] Among them, the deviation degree of the maximum change area of the laser projection pattern of the robot before and after quantization in the handover area, and obtaining the post-robot heat accumulation parameters of a preset number of historical workpieces extending over time specifically include the following steps: Step S301: Based on 3D vision technology, extract the spatial position coordinates of the maximum change area of the corresponding laser projection patterns of the pre-robot and the post-robot in each historical workpiece. Step S302: Calculate the deviation amount of the maximum change area of the laser projection patterns of the pre-robot and the post-robot in terms of spatial position, and use this deviation amount as the deviation degree of the corresponding historical workpiece. Step S303: Obtain the post-robot heat accumulation parameters when each historical workpiece is welded. The heat accumulation parameters include the cumulative operation duration during the welding process, the temperature change value of the key part, and its derivative function.

[0043] In the embodiment of the present invention, to realize the quantitative analysis of the response difference of the weld surface state in the handover area between the pre-robot and the post-robot, the system performs spatial comparison on the maximum change area of the laser projection pattern based on 3D vision technology, and combines the thermal state parameters to extract the evolution process of the post-robot operation load. The specific implementation process is as follows:

[0044] First, in step S301, the system extracts the spatial position coordinates of the maximum change area corresponding to the laser projection patterns of the pre-robot and the post-robot in the handover area of each historical workpiece based on the spatial point cloud registration technology. Specifically, the multi-view image three-dimensional reconstruction algorithm is used to perform point cloud modeling on the maximum change area in the laser pattern, and spatial registration is performed by combining the laser coding information and the robot pose data, so as to accurately restore the position coordinates of the maximum change area in the actual workpiece coordinate system.

[0045] Subsequently, in step S302, the system performs difference analysis on the spatial position coordinates of the maximum change area corresponding to the pre-robot and the post-robot based on the three-dimensional Euclidean distance calculation method to obtain the offset amount in the three-dimensional space. This offset amount is defined as the "deviation degree" of the corresponding historical workpiece in the present invention, which is used to measure the execution consistency and response error of the two robots for the key area of the weld during the connection welding process. The larger the value, the more significant the dynamic deviation between the actual welding behavior of the post-robot and the expected trajectory of the pre-robot.

[0046] In step S303, to identify the heat accumulation factors affecting the evolution of the deviation degree, the system further extracts the post-robot heat accumulation parameters when each historical workpiece is welded. The heat accumulation parameters mainly include the following contents:

[0047] Cumulative operation duration: It refers to the total continuous operation duration of the post-robot since the start of welding, which is used to measure the total aging effect of the heat source continuous action.

[0048] Temperature change value of key parts: The temperature change curve of the robot body during operation in high-heat load areas (such as the welding end and the joint motor housing) is obtained through embedded or external thermal sensors, reflecting the internal heat diffusion state.

[0049] Derivation function: To facilitate subsequent trend analysis, the system calculates indicators such as the first derivative (temperature rise rate), local extreme point distribution, or heat equilibrium recovery time based on the above temperature change curve to structurally represent the dynamic characteristics of the heat load.

[0050] Combining the above parameters, the heat accumulation characteristics of the robot not only reflect its current heat load level.

[0051] Furthermore, the welding trajectory planning method for multi-robot cooperation based on 3D vision further includes the following steps:

[0052] Step S400: Analyze a preset number of historical workpieces in advance to determine whether there is the following characteristic pattern: as time extends, there is a preset correlation relationship between the change trend of the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots and the change trend of the heat accumulation parameters of the rear robot.

[0053] The preset correlation relationship means that: among the preset number of historical workpieces in advance, there is a positive correlation between the change trend of the heat accumulation parameters of the rear robot and the change trend of the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots, and this positive correlation satisfies the following conditions: the change trend slopes within the preset time interval are respectively extracted as the first slope value and the second slope value, and the ratio of the first slope value to the second slope value is within the allowable range expressed by the preset function, or satisfies the preset multiple relationship of the second slope value to the first slope value, so as to determine that the trend of the influence of the heat accumulation of the rear robot on the welding deviation in the handover welding area conforms to the regular requirements.

[0054] In the embodiment of the present invention, the core of step S400 is to identify a deviation pattern with associated characteristics, which indicates that there is a highly coupled internal relationship between the heat accumulation change trend and the laser projection pattern offset trend of the rear robot during the continuous completion of the handover welding task, thereby providing a reliable judgment basis for the generation of subsequent correction strategies.

[0055] First, if it is observed in the previously preset number of historical workpieces that "as time extends, the change trend of the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots shows a continuous upward trend", it can be preliminarily judged that as the workpiece sequence progresses, the spatial overlap degree between the laser pattern formed by the front robot during welding and the laser pattern formed by the rear robot during actual execution gradually decreases. The gradual expansion of this deviation indicates that the response ability of the rear robot to the existing trajectory or weld seam state during the welding process is decreasing, characterizing the continuous deterioration of its welding stability and connection consistency.

[0056] Furthermore, if the evolution trend of such deviation degree shows a positive correlation with the change trend of the thermal accumulation parameters of the rear robot, that is, during the time progression, the thermal accumulation parameters (such as the temperature of key parts, operation duration, etc.) increase accordingly and synchronously enhance with the deviation degree, it indicates that due to the thermal load accumulation caused by continuous operation of the rear robot, it has significantly affected the mechanical rigidity, positioning accuracy or response rate of its welding head or body structure, resulting in a systematic deviation in its perception and execution of the weld seam state left by the front robot.

[0057] To ensure the stability and applicability of this positive correlation relationship, the system defines a preset time interval as the constraint range for trend slope extraction. This time interval is generally set as the typical stage where thermal accumulation shows continuous change, avoiding including interference data in the initial stage where thermal equilibrium has not been established or in the later stage where the temperature tends to saturate. Specific bases include statistical results of dynamic parameters such as the total number of historical welded workpieces, the average welding duration of a single piece, and the change rate of the temperature rise speed of the thermosensitive point. The system can adaptively adjust this interval according to the actual welding process to ensure that the trend extraction is representative.

[0058] In addition, the positive correlation condition expressed by the slope ratio or multiple relationship is not an empirical setting, but a quantifiable criterion obtained based on statistical analysis of a large number of historical welding sample data. The system identifies the typical coupling modes between the deviation trend and the thermal accumulation trend through offline regression modeling and clustering analysis, and extracts multiple stable slope intervals from the training set, further abstracting them into an allowable range expression function or multiple mapping rule to ensure the traceability and statistical support of this "preset correlation relationship", avoiding the technical solution relying solely on manual subjective judgment.

[0059] The ultimate goal of this step is to identify the regular trend that "the thermal accumulation of the rear robot has a significant promoting effect on the welding deviation in the handover welding area", providing a dynamic judgment basis for whether the angle correction value needs to be adjusted. This regular judgment mechanism not only avoids the problem of insufficient adaptability of static correction values in continuous operation of multiple workpieces, but also enables the system to intelligently regulate the welding strategy based on the thermal state change, thus constituting the core technical highlight and actual innovation basis of the present invention in the dynamic optimization of multi-robot collaborative welding trajectories.

[0060] In the present invention, the "welding deviation" refers to the position or attitude deviation of the welding trajectory or welding angle of the rear robot during the actual welding operation in the handover welding area compared with the expected weld path or weld geometric state. Specifically, when the rear robot connects to the starting end of the weld left by the front robot, due to sensing errors, the influence of thermal expansion and contraction, or inaccurate attitude control, there are deviations in the vertical angle, swing direction, or lateral / longitudinal positioning of its welding torch relative to the weld center line, resulting in problems such as discontinuous weld formation, weld bead deviation, and uneven heat input. Such deviations not only affect the appearance consistency of the welding, but may also cause internal weld defects (such as lack of fusion, slag inclusion, or undercut), thereby reducing the overall strength and service reliability of the welded joint, and are important objects that need to be adjusted in real time in multi-robot continuous collaborative welding.

[0061] Furthermore, the welding trajectory planning method for multi-robot collaboration based on 3D vision further includes the following steps:

[0062] Step S500, if it is determined that the above characteristic pattern exists, obtain the initial angle correction value set by the rear robot for the handover welding area, and generate a correction factor according to the change trend of the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots, and dynamically adjust the initial angle correction value.

[0063] Specifically, Figure 4 The flowchart for correcting the initial angle correction value is shown.

[0064] Among them, if it is determined that the above characteristic pattern exists, obtaining the initial angle correction value set by the rear robot for the handover welding area, and generating a correction factor according to the change trend of the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots, and dynamically adjusting the initial angle correction value specifically includes the following steps: Step S501, after determining that the above characteristic pattern exists, obtain the initial angle correction value set by the rear robot based on the handover welding area; Step S502, obtain the change trend slope within a preset time interval of the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots: the second slope value; Step S503, set the second slope value as the correction factor, and correct the initial angle correction value through the correction factor to obtain the corrected angle correction value; Step S504, apply the corrected angle correction value to the welding trajectory planning of the handover welding area of other workpieces to be welded in the subsequent target batch of workpieces by the rear robot, so as to realize the compensatory optimization of the initial angle correction value.

[0065] In the embodiments of the present invention, the reason for selecting the change trend slope (i.e., the second slope value) of the deviation degree of the maximum change regions of the front and rear robot laser projection patterns as the correction factor is that this slope can dynamically reflect the evolution speed of the difference between the front and rear robot laser patterns over time under the influence of heat accumulation. Compared with the static deviation value or average value, the trend slope can more sensitively capture the evolution law of the gradually increasing welding error in continuous batches of workpieces, so as to realize the forward-looking adjustment of the angle correction strategy. Using this slope as the correction factor has the following advantages: first, it can quantify the evolution intensity of the deviation; second, it can be associated with time; third, it can clearly capture the acceleration of error amplification, which helps to improve the self-adaptability and robustness of the correction strategy.

[0066] In addition to using the trend slope as the correction factor, the following alternative methods can also be considered: firstly, using the standard deviation of the deviation values within a sliding window as a measure of error volatility for correction; secondly, by constructing a non-linear fitting function, analyzing the fitting residuals between heat accumulation and deviation and using the residual trend as the correction factor; thirdly, using an empirical model or a small-sample learning model to predict the error growth and generate a factor. However, relatively speaking, the trend slope still has the advantages of simple implementation, timely response, and low model dependence.

[0067] In the calculation method for correcting the initial angle correction value, the following linear amplification form can be adopted: ; Among them, refers to the corrected initial angle correction value, refers to the initial angle correction value, refers to the correction factor (i.e., the second slope value), refers to the proportionality coefficient, and is greater than 0. This method is simple to implement and convenient for rapid deployment in the system. At the same time, an additive method can also be adopted: ; Or construct a function expression for weighted fusion, but it should be noted to keep the corrected angle value within the physical boundary under reasonable working conditions. During the correction process, the direction constraint of the angle vector needs to be introduced to ensure that the angle adjustment direction is consistent with the actual weld offset trend, so as to avoid overcorrection or directional error.

[0068] In step S504, the corrected angle correction value will serve as a key input parameter in the subsequent robot welding path generation module and will be specifically applied to the trajectory control logic of the subsequent robot in the handover welding area of the workpieces to be welded in the target batch. This trajectory planning generally includes control nodes such as torch attitude adjustment, starting point offset, and transition section rotation angle setting. The correction value will directly act on the attitude angle setting link within the handover area and will be sent to the end effector of the subsequent robot (such as a servo torch mechanism) through motion control instructions for attitude fine-tuning to ensure that the weld seam trajectory fits better with the structural features left by the end point of the weld seam of the previous robot, thereby improving welding continuity and joint quality.

[0069] Furthermore, Figure 5 Fig. shows the application architecture diagram of the system provided by the embodiment of the present invention.

[0070] Among them, in another preferred embodiment provided by the present invention, a welding trajectory planning system for multi-robot cooperation based on 3D vision includes: A data acquisition module 100, configured to acquire historical welding data of a preset number of previously welded historical workpieces in the handover welding area of the target batch of workpieces located in the double-robot handover welding area.

[0071] Furthermore, the welding trajectory planning system for multi-robot cooperation based on 3D vision further includes: A maximum change area determination module 200, configured to respectively extract the laser projection patterns within the handover welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data, and determine the maximum change area of each laser projection pattern; the laser projection pattern refers to a specific light spot or pattern projected by the laser device carried by the robot onto the weld seam surface during the welding process, which is used to assist in identifying the weld seam profile, bead geometry changes, and local deformation conditions, and its pattern will generate recognizable structural changes during the welding process due to workpiece thermal deformation or changes in surface reflection characteristics.

[0072] Specifically, Figure 6 Fig. shows the structural block diagram of the maximum change area determination module 200 in the system provided by the embodiment of the present invention.

[0073] Among them, in the preferred embodiment provided by the present invention, the maximum change area determination module 200 specifically includes: A pattern extraction unit 201, configured to extract the laser projection patterns projected by the front robot and the rear robot corresponding to each historical workpiece into the handover welding area from the historical welding data; A pattern change analysis unit 202, configured to use 3D vision technology to perform structural reconstruction and curvature analysis on the extracted laser projection patterns, identify the area that changes most significantly during the welding process in the pattern, and determine this area as the corresponding maximum change area.

[0074] Further, the welding trajectory planning system for multi-robot cooperation based on 3D vision further includes:

[0075] A deviation degree quantification module 300, configured to quantify the deviation degree of the maximum change region of the laser projection patterns of the front and rear robots in the handover area, and obtain the thermal accumulation parameters of the rear robot extending over time for the pre-set number of historical workpieces.

[0076] Specifically, Figure 7 FIG. shows a structural block diagram of the deviation degree quantification module 300 in the system provided by an embodiment of the present invention.

[0077] Wherein, in the preferred embodiment provided by the present invention, the deviation degree quantification module 300 specifically includes: A coordinate extraction unit 301, configured to extract the spatial position coordinates of the maximum change region of the laser projection patterns corresponding to the front and rear robots in each historical workpiece based on 3D vision technology; A deviation amount calculation unit 302, configured to calculate the deviation amount of the maximum change regions of the laser projection patterns of the front and rear robots in terms of spatial position, and use this deviation amount as the deviation degree of the corresponding historical workpiece; A thermal accumulation parameter acquisition unit 303, configured to acquire the thermal accumulation parameters of the rear robot when each historical workpiece is welded, and the thermal accumulation parameters include the cumulative operation duration during the welding process, the temperature change value of the key part and its derivative function.

[0078] Further, the welding trajectory planning system for multi-robot cooperation based on 3D vision further includes: A feature pattern judgment module 400, configured to analyze the pre-set number of historical workpieces to determine whether there is the following feature pattern: as time extends, the change trend of the deviation degree of the maximum change region of the laser projection patterns of the front and rear robots satisfies a pre-set correlation relationship with the change trend of the thermal accumulation parameters of the rear robot;

[0079] The pre-set correlation relationship means that: among the pre-set number of historical workpieces, there is a positive correlation between the change trend of the thermal accumulation parameters of the rear robot and the change trend of the deviation degree of the maximum change region of the laser projection patterns of the front and rear robots, and this positive correlation satisfies the following conditions: the change trend slopes of the two within the pre-set time interval are respectively extracted as the first slope value and the second slope value, and the ratio of the first slope value to the second slope value is within the allowable range expressed by a pre-set function, or satisfies the second slope value being a pre-set multiple of the first slope value, so as to determine that the trend of the influence of the thermal accumulation of the rear robot on the welding deviation of the handover welding area conforms to the regular requirement.

[0080] Further, the welding trajectory planning system for multi-robot cooperation based on 3D vision further includes:

[0081] The angle correction value adjustment module 500 is configured to, if it is determined that the above feature pattern exists, obtain the initial angle correction value set by the robot for the handover welding area, and generate a correction factor according to the change trend of the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots, and dynamically adjust the initial angle correction value.

[0082] Specifically, Figure 8 FIG. shows a structural block diagram of the angle correction value adjustment module 500 in the system provided by the embodiment of the present invention.

[0083] Among them, in the preferred embodiment provided by the present invention, the angle correction value adjustment module 500 specifically includes: The initial value acquisition unit 501 is configured to, after determining that the above feature pattern exists, obtain the initial angle correction value set by the rear robot based on the handover welding area; The slope value acquisition unit 502 is configured to obtain the change trend slope of the deviation degree of the maximum change area of the laser projection patterns of the front and rear robots within a preset time interval: the second slope value; The angle correction value adjustment unit 503 is configured to set the second slope value as a correction factor, and correct the initial angle correction value by the correction factor to obtain a corrected angle correction value; The correction value application unit 504 is configured to apply the corrected angle correction value to the welding trajectory planning of the handover welding area of other workpieces to be welded in the subsequent target batch of workpieces by the rear robot, so as to realize the compensatory optimization of the initial angle correction value.

[0084] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0085] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above-described embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0086] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0087] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention should be subject to the appended claims.

[0088] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A welding trajectory planning method for multi-robot cooperation based on 3D vision, characterized in that, The method includes: Obtaining historical welding data of a preset number of previously welded historical workpieces in the dual-robot handover welding area for the target batch of workpieces; Respectively extracting the laser projection patterns in the handover welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data, and determining the maximum change area of each laser projection pattern; Quantifying the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots in the handover area, and obtaining the heat accumulation parameters of the rear robot for the preset number of historical workpieces over time; Analyzing the preset number of historical workpieces to determine whether there is the following characteristic pattern: over time, the change trend of the deviation degree between the maximum change areas of the laser projection patterns of the front and rear robots satisfies a preset correlation relationship with the change trend of the heat accumulation parameters of the rear robot; If it is determined that the above characteristic pattern exists, obtaining the initial angle correction value set by the rear robot for the handover welding area, and generating a correction factor according to the change trend of the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots, and dynamically adjusting the initial angle correction value.

2. The welding trajectory planning method for multi-robot cooperation based on 3D vision according to claim 1, wherein The laser projection pattern refers to a specific light spot or pattern projected by the laser device carried by the robot onto the weld surface during welding, which is used to assist in identifying the weld profile, bead geometry changes, and local deformation conditions. Its pattern will generate recognizable structural changes during welding due to workpiece thermal deformation or changes in surface reflection characteristics.

3. The welding trajectory planning method for multi-robot cooperation based on 3D vision according to claim 2, characterized in that The steps of respectively extracting the laser projection patterns in the handover welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data, and determining the maximum change area of each laser projection pattern include: Extracting the laser projection patterns projected by the front robot and the rear robot corresponding to each historical workpiece into the handover welding area from the historical welding data; Using 3D vision technology to perform structural reconstruction and curvature analysis on the extracted laser projection patterns, identifying the area that changes most significantly during the welding process in the pattern, and determining this area as the corresponding maximum change area.

4. The welding trajectory planning method for multi-robot cooperation based on 3D vision according to claim 3, characterized in that The steps of quantifying the deviation degree of the maximum change areas of the laser projection patterns of the front and rear robots in the handover area, and obtaining the heat accumulation parameters of the rear robot for the preset number of historical workpieces over time include: Based on 3D vision technology, extracting the spatial position coordinates of the maximum change areas of the laser projection patterns corresponding to the front robot and the rear robot in each historical workpiece; Calculating the deviation amount of the maximum change areas of the laser projection patterns of the front and rear robots in terms of spatial position, and using this deviation amount as the deviation degree of the corresponding historical workpiece; Obtaining the heat accumulation parameters of the rear robot when each historical workpiece is welded, and the heat accumulation parameters include the cumulative operation duration during welding, the temperature change value of the key part, and its derivative function.

5. The welding trajectory planning method for multi-robot cooperation based on 3D vision according to claim 4, wherein, The preset correlation refers to: among the previous preset number of historical workpieces, there is a positive correlation between the change trend of the heat accumulation parameter of the rear robot and the change trend of the deviation degree between the maximum change regions of the laser projection patterns of the front and rear robots, and this positive correlation satisfies the following conditions: the change trend slopes within the preset time interval of the two are respectively extracted as the first slope value and the second slope value, and the ratio of the first slope value to the second slope value is within the allowable range expressed by the preset function, or satisfies the preset multiple relationship between the second slope value and the first slope value, so as to determine that the trend of the influence of the heat accumulation of the rear robot on the welding deviation in the butt welding area conforms to the regular requirements.

6. The welding trajectory planning method for multi-robot cooperation based on 3D vision according to claim 5, wherein If it is determined that the above characteristic pattern exists, the steps of obtaining the initial angle correction value set by the rear robot for the butt welding area and generating a correction factor according to the change trend of the deviation degree between the maximum change regions of the laser projection patterns of the front and rear robots to dynamically adjust the initial angle correction value include: After determining that the above characteristic pattern exists, obtain the initial angle correction value set by the rear robot based on the butt welding area; Obtain the change trend slope within the preset time interval of the deviation degree between the maximum change regions of the laser projection patterns of the front and rear robots: the second slope value; Set the second slope value as the correction factor, and correct the initial angle correction value through the correction factor to obtain the corrected angle correction value; Apply the corrected angle correction value to the welding trajectory planning of the butt welding area of other workpieces to be welded in the subsequent target batch of workpieces by the rear robot, so as to realize the compensatory optimization of the initial angle correction value.

7. A welding trajectory planning system for multi-robot collaboration based on 3D vision, characterized in that, The system includes: a data acquisition module, a maximum change region determination module, a deviation degree quantification module, a characteristic pattern judgment module, and an angle correction value adjustment module, where: The data acquisition module is used to acquire the historical welding data of the previous preset number of welded historical workpieces of the target batch of workpieces located in the double-robot butt welding area; The maximum change region determination module is used to respectively extract the laser projection patterns in the butt welding areas of the front and rear robots corresponding to each historical workpiece from the historical welding data, and determine the maximum change region of each laser projection pattern; the laser projection pattern refers to the specific light spot or pattern projected by the laser device carried by the robot onto the weld surface during the welding process, which is used to assist in identifying the weld profile, the geometric changes of the weld bead, and the local deformation conditions, and its pattern will generate recognizable structural changes during the welding process due to workpiece thermal deformation or changes in surface reflection characteristics; The deviation degree quantification module is used to quantify the deviation degree between the maximum change regions of the laser projection patterns of the front and rear robots in the butt joint area, and obtain the heat accumulation parameter of the rear robot with the extension of time for the previous preset number of historical workpieces; The characteristic pattern judgment module is used to analyze the previous preset number of historical workpieces to determine whether there is the following characteristic pattern: with the extension of time, the change trend of the deviation degree between the maximum change regions of the laser projection patterns of the front and rear robots and the change trend of the heat accumulation parameter of the rear robot satisfy the preset correlation relationship; The preset correlation refers to: among the previous preset number of historical workpieces, there is a positive correlation between the change trend of the thermal accumulation parameter of the rear robot and the change trend of the deviation degree between the maximum change regions of the laser projection patterns of the front and rear robots, and this positive correlation satisfies the following conditions: the change trend slopes within the preset time interval are respectively extracted as the first slope value and the second slope value, and the ratio of the first slope value to the second slope value is within the allowable range expressed by the preset function, or satisfies the preset multiple relationship that the second slope value is a multiple of the first slope value, so as to determine that the trend of the influence of the thermal accumulation of the rear robot on the welding deviation of the butt welding area conforms to the regular requirements; The angle correction value adjustment module is used to, if it is determined that the above characteristic pattern exists, obtain the initial angle correction value set by the rear robot for the butt welding area, and generate a correction factor according to the change trend of the deviation degree between the maximum change regions of the laser projection patterns of the front and rear robots, and dynamically adjust the initial angle correction value.

8. The welding trajectory planning system for multi-robot cooperation based on 3D vision according to claim 7, characterized in that, The maximum change region determination module specifically includes: The pattern extraction unit is used to extract the laser projection patterns projected by the front robot and the rear robot corresponding to each historical workpiece into the butt welding area from the historical welding data; The pattern change analysis unit is used to perform structure reconstruction and curvature analysis on the extracted laser projection pattern by using 3D vision technology, identify the region that changes most significantly during the welding process in the pattern, and determine this region as the corresponding maximum change region.

9. The welding trajectory planning system for multi-robot collaboration based on 3D vision according to claim 8, characterized in that, The deviation degree quantification module specifically includes: The coordinate extraction unit is used to extract the spatial position coordinates of the maximum change regions of the laser projection patterns of the front robot and the rear robot corresponding to each historical workpiece based on 3D vision technology; The deviation amount calculation unit is used to calculate the deviation amount of the maximum change regions of the laser projection patterns of the front and rear robots in terms of spatial position, and use this deviation amount as the deviation degree of the corresponding historical workpiece; The thermal accumulation parameter acquisition unit is used to acquire the thermal accumulation parameter of the rear robot when each historical workpiece is welded, and the thermal accumulation parameter includes the cumulative operation duration during the welding process, the temperature change value of the key part and its derivative function.

10. The welding trajectory planning system for multi-robot cooperation based on 3D vision according to claim 9, characterized in that, The angle correction value adjustment module specifically includes: The initial value acquisition unit is used to acquire the initial angle correction value set by the rear robot based on the butt welding area after it is determined that the above characteristic pattern exists; The slope value acquisition unit is used to acquire the change trend slope within the preset time interval of the change trend of the deviation degree between the maximum change regions of the laser projection patterns of the front and rear robots: the second slope value; The angle correction value adjustment unit is used to set the second slope value as the correction factor, and correct the initial angle correction value through the correction factor to obtain the corrected angle correction value; The correction value application unit is used to apply the corrected angle correction value to the welding trajectory planning of the butt welding area of other workpieces to be welded in the subsequent target batch of workpieces by the rear robot, so as to realize the compensatory optimization of the initial angle correction value.

Images