Method, device and equipment for adjusting welding process parameters of multi-layer multi-pass weld

Abstract

This application relates to a method, apparatus, and equipment for debugging welding process parameters of multi-layer, multi-channel welds. The method includes: acquiring a process parameter library storing welding process parameters of multi-layer, multi-channel welds, providing a comprehensive and accurate data foundation for debugging welding process parameters, which helps to quickly determine the appropriate parameter range; extracting the root weld trajectory from the bevel scan as the first weld reference trajectory; generating an initial welding trajectory by combining the process parameter library, ensuring the accuracy of the first weld trajectory; for subsequent welds, dynamically adjusting based on the previous weld trajectory and six-degree-of-freedom pose offset parameters, and generating the current trajectory by combining the process parameter library, which can flexibly adapt to changes in the position and posture of different welds, ensuring the accuracy of each weld trajectory; and finally combining the trajectories and parameters of different welds to obtain the debugging result, achieving efficient and accurate debugging of welding process parameters.

Description

Technical Field

[0001] This application relates to the field of welding robot technology, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for adjusting welding process parameters of multi-layer and multi-channel welds. Background Technology

[0002] In the industrial manufacturing sector, robotic multi-layer, multi-pass welding technology, with its unique advantages, occupies an indispensable position in key industrial scenarios such as pressure vessels and thick-walled structures. This technology has extremely high requirements for welding trajectory accuracy and parameter coordination. The welding trajectory error must be strictly controlled within a very small range (e.g., ±0.5mm), while parameters such as current, voltage, and welding speed must be dynamically and precisely matched to ensure that the welding quality meets high industry standards.

[0003] Currently, the industry commonly employs the traditional "trial and error" method for developing multi-layer, multi-pass welding processes. This method determines the final parameter combination through repeated cycles of teaching the trajectory, actual welding, and manual parameter adjustments. However, this traditional debugging method reveals numerous problems during the trajectory and parameter debugging process for multi-layer, multi-pass welding. For example, it results in lengthy debugging cycles, low average efficiency, and long development cycles for the complete process; poor quality consistency, easy exceeding of welding error limits, and challenges in controlling the shape precision of large and complex components; significant resource waste, high material costs, and difficulty in handling dynamic variables leading to increased rework rates.

[0004] However, as industrial manufacturing demands increasingly higher production efficiency and product quality, traditional debugging methods are no longer sufficient to meet actual needs. In particular, when faced with complex working conditions, their limitations become increasingly apparent, making it impossible to achieve efficient and accurate parameter debugging. Summary of the Invention

[0005] Therefore, it is necessary to provide an efficient and accurate method, apparatus, computer equipment, computer-readable storage medium, and computer program product for debugging welding process parameters of multi-layer and multi-channel welds, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a method for adjusting welding process parameters for multi-layer, multi-channel welds. The method includes: Obtain the process parameter library for multi-layer and multi-channel welding. The process parameter library stores the welding process parameters for multi-layer and multi-channel welds. The bevel after welding assembly is scanned to extract the root weld trajectory, and the root weld trajectory is used as the reference trajectory for the first weld. By combining the baseline trajectory and the welding process parameters corresponding to the first weld in the process parameter library, the initial welding trajectory of the first weld is generated. For each subsequent weld, the six-degree-of-freedom pose offset parameters corresponding to the current weld are obtained. Based on the welding trajectory of the previous weld, the six-degree-of-freedom pose offset parameters are dynamically adjusted, and combined with the welding process parameters corresponding to the current weld in the process parameter library, the welding trajectory of the current weld is generated. By combining welding trajectories and welding process parameters of different weld seams, the welding process parameter debugging results of multi-layer and multi-channel weld seams are obtained.

[0007] In one embodiment, the process parameter library also stores layered structures; The layer structure in the process parameter library is generated in the following way: Scan the bevel after welding assembly and extract the bevel geometry parameters; Based on the bevel geometry parameters, the optimal number of welds, the center position of each weld, and the stacking order between layers are calculated by an automatic weld arrangement algorithm combined with preset weld overlap rate, welding torch swing limit, and weld deposition section model, thus determining the layer structure. Combining the baseline trajectory and the welding process parameters corresponding to the first weld in the process parameter library, the initial welding trajectory for the first weld is generated, including: Obtain the welding parameters and layer structure corresponding to the first weld in the process parameter library; Based on the baseline trajectory and the acquired welding parameters and layer structure, the initial welding trajectory of the first weld is generated.

[0008] In one embodiment, scanning the bevel after welding assembly, extracting the root weld trajectory, and using the root weld trajectory as the reference trajectory for the first weld includes: Perform a 3D visual scan on the bevel after welding and assembly to obtain point cloud data of the bevel area; Point cloud processing algorithms are used to process the point cloud data of the bevel area and extract the center trajectory of the root weld bead. The center trajectory of the root weld bead is used as the reference trajectory for the first weld bead.

[0009] In one embodiment, scanning the bevel after welding assembly, extracting the root weld trajectory, and using the root weld trajectory as the reference trajectory for the first weld includes: The contour of the welded bevel is extracted by using a contact probe, line laser positioning, or arc sensing method. Extracting the center trajectory of the root weld bead based on the bevel profile; The center trajectory of the root weld bead is used as the reference trajectory for the first weld bead.

[0010] In one embodiment, obtaining the six-degree-of-freedom pose offset parameters corresponding to the current weld seam includes: The actual weld bead profile after the previous weld seam was completed was obtained by line laser scanning; Extract the absolute spatial position of the actual weld bead profile; Calculate the adaptive offset between the absolute spatial position and the ideal weld trajectory, where the ideal weld trajectory is determined based on the weld trajectory corresponding to the previous weld and the six-degree-of-freedom pose offset parameters; Based on the adaptive offset, generate the pose transformation matrix required for the current weld. Obtain the initial six-degree-of-freedom pose offset parameters corresponding to the current weld; The initial six-degree-of-freedom pose offset parameters are corrected based on the pose transformation matrix to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld.

[0011] In one embodiment, calculating the adaptive offset between the absolute spatial position and the ideal weld bead trajectory includes: The adaptive offset between the absolute spatial position and the ideal weld bead trajectory is calculated by point cloud volume difference calculation or based on molten pool image analysis. After correcting the initial six-DOF pose offset parameters based on the pose transformation matrix to obtain the six-DOF pose offset parameters corresponding to the current weld, the following steps are also included: Based on the six-degree-of-freedom pose offset parameters corresponding to the current weld, a single-step debugging mode is used to perform a no-load run with the welding control software, and the rationality of the welding torch trajectory and attitude is judged. Alternatively, the automatic welding mode can be started to perform welding operations based on the six-degree-of-freedom pose offset parameters corresponding to the current weld.

[0012] Secondly, this application also provides a device for adjusting welding process parameters for multi-layer, multi-channel welds. The device includes: The database acquisition module is used to acquire the process parameter library for multi-layer and multi-channel welding. The process parameter library stores the welding process parameters for multi-layer and multi-channel welds. The reference trajectory determination module is used to scan the bevel after welding assembly, extract the root weld trajectory, and use the root weld trajectory as the reference trajectory for the first weld. The initial welding trajectory determination module is used to combine the reference trajectory and the welding process parameters corresponding to the first weld in the process parameter library to generate the initial welding trajectory of the first weld. The iteration module is used to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld for each subsequent weld. Based on the welding trajectory of the previous weld, the six-degree-of-freedom pose offset parameters are dynamically adjusted, and combined with the welding process parameters corresponding to the current weld in the process parameter library, the welding trajectory of the current weld is generated. The combined adjustment module is used to combine the welding trajectories and welding process parameters of different welds to obtain the welding process parameter debugging results of multi-layer and multi-channel welds.

[0013] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps: Obtain the process parameter library for multi-layer and multi-channel welding. The process parameter library stores the welding process parameters for multi-layer and multi-channel welds. The bevel after welding assembly is scanned to extract the root weld trajectory, and the root weld trajectory is used as the reference trajectory for the first weld. By combining the baseline trajectory and the welding process parameters corresponding to the first weld in the process parameter library, the initial welding trajectory of the first weld is generated. For each subsequent weld, the six-degree-of-freedom pose offset parameters corresponding to the current weld are obtained. Based on the welding trajectory of the previous weld, the six-degree-of-freedom pose offset parameters are dynamically adjusted, and combined with the welding process parameters corresponding to the current weld in the process parameter library, the welding trajectory of the current weld is generated. By combining welding trajectories and welding process parameters of different weld seams, the welding process parameter debugging results of multi-layer and multi-channel weld seams are obtained.

[0014] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps: Obtain the process parameter library for multi-layer and multi-channel welding. The process parameter library stores the welding process parameters for multi-layer and multi-channel welds. The bevel after welding assembly is scanned to extract the root weld trajectory, and the root weld trajectory is used as the reference trajectory for the first weld. By combining the baseline trajectory and the welding process parameters corresponding to the first weld in the process parameter library, the initial welding trajectory of the first weld is generated. For each subsequent weld, the six-degree-of-freedom pose offset parameters corresponding to the current weld are obtained. Based on the welding trajectory of the previous weld, the six-degree-of-freedom pose offset parameters are dynamically adjusted, and combined with the welding process parameters corresponding to the current weld in the process parameter library, the welding trajectory of the current weld is generated. By combining welding trajectories and welding process parameters of different weld seams, the welding process parameter debugging results of multi-layer and multi-channel weld seams are obtained.

[0015] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps: Obtain the process parameter library for multi-layer and multi-channel welding. The process parameter library stores the welding process parameters for multi-layer and multi-channel welds. The bevel after welding assembly is scanned to extract the root weld trajectory, and the root weld trajectory is used as the reference trajectory for the first weld. By combining the baseline trajectory and the welding process parameters corresponding to the first weld in the process parameter library, the initial welding trajectory of the first weld is generated. For each subsequent weld, the six-degree-of-freedom pose offset parameters corresponding to the current weld are obtained. Based on the welding trajectory of the previous weld, the six-degree-of-freedom pose offset parameters are dynamically adjusted, and combined with the welding process parameters corresponding to the current weld in the process parameter library, the welding trajectory of the current weld is generated. By combining welding trajectories and welding process parameters of different weld seams, the welding process parameter debugging results of multi-layer and multi-channel weld seams are obtained.

[0016] The aforementioned method, apparatus, computer equipment, storage medium, and computer program products for debugging welding process parameters of multi-layer, multi-channel welds provide a comprehensive and accurate data foundation for debugging welding process parameters by acquiring a process parameter library containing welding process parameters of multi-layer, multi-channel welds. This helps to quickly determine the appropriate parameter range. The root weld trajectory extracted by bevel scanning is used as the reference trajectory for the first weld. Combined with the process parameter library, an initial welding trajectory is generated, ensuring the accuracy of the first weld trajectory. For subsequent welds, dynamic adjustments are made based on the previous weld trajectory and the six-degree-of-freedom pose offset parameters. Combined with the process parameter library, the current trajectory is generated, which can flexibly adapt to changes in the position and posture of different welds, ensuring the accuracy of each weld trajectory. Finally, the debugging results are obtained by combining the trajectories and parameters of different welds, achieving efficient and accurate debugging of welding process parameters. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a method for adjusting welding process parameters for multi-layer, multi-channel welds in one embodiment. Figure 2 This is a flowchart illustrating the method for adjusting welding process parameters for multi-layer, multi-channel welds in another embodiment. Figure 3 This is a structural block diagram of a welding process parameter adjustment device for multi-layer, multi-channel welds in one embodiment; Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] In one embodiment, such as Figure 1 As shown, a method for adjusting welding process parameters for multi-layer, multi-channel welds is provided, including the following steps: S100: Obtain the process parameter library for multi-layer, multi-channel welding. The process parameter library stores the welding process parameters for multi-layer, multi-channel welds.

[0020] The process parameter library, constructed through extensive experiments and theoretical analysis, stores welding process parameters for multi-layer, multi-channel welds. These parameters cover key parameters such as welding current, voltage, and welding speed under various working conditions, including different materials, thicknesses, and welding positions. In practical applications, a multi-layer, multi-channel welding process parameter library can be pre-established through process qualification experiments for specific materials, groove types, and welding processes. This parameter library contains welding process parameters corresponding to each layer and each weld pass, including: welding speed, voltage, current, welding torch oscillation amplitude and frequency, arc initiation / outgoing parameters, welding torch posture angles (such as tilt angle and rotation angle), and inter-pass offset.

[0021] S200: Scan the bevel after welding assembly, extract the root weld trajectory, and use the root weld trajectory as the reference trajectory for the first weld.

[0022] Specifically, the completed bevel of the welded assembly can be scanned using either visual or sensor methods. Taking visual scanning as an example, advanced visual sensing technologies, such as laser scanning or 3D visual scanning, can be employed to perform high-precision scanning of the completed bevel. Through specific image processing algorithms, the root weld trajectory is accurately extracted from the scanned bevel image information. The root weld trajectory serves as the reference trajectory for the first weld, providing a precise starting point for the generation of subsequent weld trajectories. Because the welding quality of the first weld plays a crucial foundational role in the overall welding quality of the multi-layer, multi-channel weld, a precise reference trajectory ensures the accurate welding position of the first weld, avoiding welding defects caused by positional deviations, such as incomplete penetration and porosity.

[0023] S300: Combines the reference trajectory and the welding process parameters corresponding to the first weld in the process parameter library to generate the initial welding trajectory of the first weld.

[0024] Based on the root trajectory extracted visually and combined with the welding process parameters corresponding to the first weld seam in the process parameter library, a trajectory planning algorithm is used to automatically generate the robot motion trajectory for the first weld seam. Simultaneously, the welding torch posture and electrical parameters are set to ensure that the welding torch angle and various electrical indicators meet the welding requirements during the welding process.

[0025] S400: For each subsequent weld, obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld. Based on the welding trajectory of the previous weld, dynamically adjust the six-degree-of-freedom pose offset parameters and combine them with the welding process parameters corresponding to the current weld in the process parameter library to generate the welding trajectory of the current weld.

[0026] Six-degree-of-freedom (DOF) pose offset parameters can include spatial position offsets, i.e., translations along the X, Y, and Z coordinate axes. Furthermore, in applications requiring higher precision, these parameters can also include attitude angle offsets, i.e., rotation angles (Rx, Ry, Rz) around the X, Y, and Z axes; and the distance the path between the starting and ending points is extended or shortened. These parameters accurately describe the spatial position and attitude changes of each weld seam relative to the previous weld seam. Based on the welding trajectory of the previous weld seam, kinematic algorithms are used to dynamically adjust the trajectory of the previous weld seam in real time according to the acquired six-degree-of-freedom pose offset parameters. Simultaneously, the welding trajectory is further optimized by combining the welding process parameters corresponding to the current weld seam in the process parameter library. The six-degree-of-freedom pose offset parameters corresponding to the current weld seam can be set manually; that is, the industrial control host provides a parameter setting interface, and the operator sets the six-degree-of-freedom pose offset parameters based on their own experience on the parameter setting interface. Furthermore, the six-DOF pose offset parameters corresponding to the current weld can be automatically set. Specifically, after the previous weld is completed, the vision sensor scans the post-weld morphology, extracts the absolute spatial position of the actual weld contour, calculates its deviation from the ideal weld trajectory, and automatically generates the pose transformation matrix required for the next weld, thereby updating the offset parameters. This fully considers the complex spatial positions and orientation relationships between welds in multi-layer, multi-channel welding, as well as the weld position changes caused by factors such as workpiece deformation and assembly errors. By dynamically adjusting and generating a welding trajectory that highly matches the actual position and orientation of the current weld, it ensures that each weld can be performed under optimal process conditions.

[0027] S500: Combine welding trajectories and welding process parameters of different weld seams to obtain the welding process parameter debugging results of multi-layer and multi-channel weld seams.

[0028] The welding trajectories and corresponding welding process parameters of the different welds generated in the previous steps need to be systematically integrated. This process requires considering the sequence and interrelationships between the welds to ensure the continuity and coordination of the entire welding process. For example, for multi-layer, multi-channel welding, the integration should proceed in the order of welding the bottom layer welds first, followed by the upper layer welds. Simultaneously, it is essential to ensure a reasonable spatial and temporal match between the welding trajectories and parameters of each weld to avoid problems such as welding interference or parameter conflicts.

[0029] The aforementioned method for debugging welding process parameters for multi-layer, multi-channel welds provides a comprehensive and accurate data foundation for debugging by acquiring a process parameter library containing welding process parameters for multi-layer, multi-channel welds. This helps to quickly determine the appropriate parameter range. The root weld trajectory extracted by bevel scanning is used as the reference trajectory for the first weld. Combined with the process parameter library, an initial welding trajectory is generated, ensuring the accuracy of the first weld trajectory. For subsequent welds, dynamic adjustments are made based on the previous weld trajectory and the six-degree-of-freedom pose offset parameters. Combined with the process parameter library, the current trajectory is generated, which can flexibly adapt to changes in the position and posture of different welds, ensuring the accuracy of each weld trajectory. Finally, the debugging results are obtained by combining the trajectories and parameters of different welds, achieving efficient and accurate debugging of welding process parameters.

[0030] In one embodiment, the process parameter library also stores layer structures; the layer structures in the process parameter library are generated in the following manner: Step 1: Scan the bevel after welding assembly and extract the bevel geometry parameters.

[0031] Visual scanning technology is used to comprehensively scan the bevel after welding assembly. A high-precision industrial camera acquires images of the bevel from multiple angles, ensuring complete capture of its shape features. Advanced image processing algorithms analyze and process the acquired images to accurately extract the bevel's geometric parameters, such as opening width, depth, and sidewall inclination angle. These parameters accurately reflect the actual shape and size of the bevel, providing crucial data for subsequent automated bevel routing algorithms.

[0032] Step 2: Based on the bevel geometry parameters, the optimal number of weld beads, the center position of each weld bead, and the stacking order between layers are calculated by using an automatic bead arrangement algorithm combined with preset weld bead overlap rate, welding torch swing limit, and fusion cross section model, thus determining the layer structure.

[0033] Based on the extracted bevel geometry parameters, an automatic weld bead arrangement algorithm is used for calculation. During the calculation process, preset weld overlap rates (typically set between 10% and 30%), welding torch swing limits, and the weld deposition cross-section model are comprehensively considered. The automatic weld bead arrangement algorithm automatically calculates the optimal number of weld beads, the center position of each weld bead, and the interlayer stacking order based on these parameters and the model, through complex mathematical calculations and optimization algorithms. For example, based on the bevel opening width and depth, combined with the weld overlap rate and the weld deposition cross-section model, it determines how many weld beads are needed to completely fill the bevel; and based on the welding torch swing limits, it adjusts the center position of each weld bead to ensure that the welding torch does not exceed its swing range during welding.

[0034] Combining the baseline trajectory and the welding process parameters corresponding to the first weld in the process parameter library, the initial welding trajectory for the first weld is generated, including: Step 1: Obtain the welding parameters and layer structure corresponding to the first weld in the process parameter library.

[0035] Accurately obtain the welding parameters and layer structure corresponding to the first weld from the process parameter library. Welding parameters include welding current, voltage, etc., which directly affect the energy input and deposition effect during the welding process; the layer structure contains the position information of the first weld in the overall layout, such as the weld center position and the stacking order between layers.

[0036] Step 2: Based on the reference trajectory and the acquired welding parameters and layer structure, generate the initial welding trajectory for the first weld.

[0037] Based on the acquired reference trajectory, welding parameters, and layer structure, a specific trajectory generation algorithm is used to generate the initial welding trajectory for the first weld pass. This algorithm comprehensively considers the shape and direction of the reference trajectory, the influence of electrical parameters on the welding process, and the position information of the first weld pass in the layer structure. Through mathematical calculations and model fitting, it generates a smooth and accurate initial welding trajectory. For example, based on the center position of the first weld pass in the layer structure, combined with the starting point and direction of the reference trajectory, the starting point and general direction of the initial welding trajectory are determined. Then, based on the influence of electrical parameters on welding speed and deposition amount, the shape and parameters of the trajectory are fine-tuned to conform to the actual welding requirements.

[0038] In one embodiment, such as Figure 2 As shown, scanning the bevel after welding assembly to extract the root weld trajectory, and using the root weld trajectory as the reference trajectory for the first weld, includes: S220: Perform a 3D visual scan on the bevel after welding assembly to obtain point cloud data of the bevel area.

[0039] Three-dimensional vision sensors, such as structured light sensors or laser scanners, are used to perform three-dimensional visual scanning of the welded bevel. Structured light sensors project a specific pattern of light onto the bevel surface, capture the reflected light with a camera, and calculate the three-dimensional coordinates of the bevel surface based on the deformation of the light. Laser scanners, on the other hand, emit a laser beam and measure the time it takes for the laser to travel from emission to reflection, combining this with the laser's emission angle to accurately calculate the three-dimensional coordinates of each point on the bevel surface. Either of these methods can comprehensively and accurately acquire point cloud data of the bevel area. This point cloud data contains the three-dimensional coordinates of a large number of discrete points on the bevel surface, accurately reflecting the actual shape and size of the bevel.

[0040] S240: The point cloud processing algorithm is used to process the point cloud data of the bevel area and extract the center trajectory of the root weld bead.

[0041] Point cloud processing algorithms are used to process the acquired bevel area point cloud data. These algorithms include, but are not limited to, filtering, segmentation, and feature extraction algorithms. First, filtering algorithms are used to remove noise and outliers from the point cloud data, improving data quality. Then, segmentation algorithms are used to separate the bevel area point cloud data from the entire scanning scene, further focusing on the bevel portion. Finally, feature extraction algorithms are used to automatically extract the root weld bead center trajectory from the bevel point cloud data based on the geometric features of the root weld bead, such as width and curvature.

[0042] S260: Use the center trajectory of the root weld bead as the reference trajectory for the first weld bead.

[0043] The root weld center trajectory extracted from S240 is directly used as the reference trajectory for the first weld. This operation is based on the special position of the root weld in the welding process. The root weld is the foundation of the entire welded structure, and its position and shape have an important impact on the welding quality of subsequent welds and the stability of the overall structure.

[0044] In one embodiment, scanning the bevel after welding assembly, extracting the root weld trajectory, and using the root weld trajectory as the reference trajectory for the first weld includes: Step 1: Use a contact probe, line laser positioning, or arc sensing method to extract the contour of the welded bevel and obtain the bevel contour.

[0045] A contact probe is a measuring element with a slender rod-like structure and a contact point at its end. During measurement, the probe moves along the bevel surface at a certain speed, and the contact point makes contact with the bevel surface. A sensor inside the probe records the position coordinates of the contact point in three-dimensional space in real time. Through continuous measurement, the coordinate information of a series of discrete points on the bevel surface is obtained, thereby constructing the bevel profile. This method allows direct contact with the bevel surface, obtaining relatively accurate local geometric information.

[0046] Line laser positioning utilizes a line laser generator to emit a linear laser beam, which is projected onto the bevel surface. Due to the varying shapes and heights of the bevel surface, the reflected light from the line laser beam undergoes corresponding deformation. A high-precision camera, positioned at an appropriate location, captures the reflected light, obtaining an image containing information about the bevel surface shape. After obtaining this image, contour extraction is performed to obtain the bevel contour.

[0047] Arc sensing utilizes the inherent characteristics of the welding arc to detect the shape of the bevel. During welding, the arc length and parameters such as current and voltage change as the bevel evolves. By monitoring the arc's current and voltage signals in real time, converting them into electrical signals for processing and analysis, the bevel profile can be inferred based on the patterns of these signal changes. This method eliminates the need for additional contact measuring equipment and allows for simultaneous bevel profile extraction during the welding process.

[0048] Step 2: Extract the center trajectory of the root weld bead based on the bevel profile.

[0049] Specific algorithms are used to analyze and process the bevel contour data obtained in step 1. First, the bevel contour data is preprocessed to remove noise and outliers, improving data quality. Then, based on the geometric characteristics of the root weld bead, such as its typical location at the bottom of the bevel and its defined width and shape, edge detection and curve fitting algorithms are used to accurately extract the edge information of the root weld bead from the bevel contour. Further, through analysis and calculation of the root weld bead edge information, the center position of the root weld bead is determined, and these center position points are connected to form the center trajectory of the root weld bead.

[0050] Step 3: Use the center trajectory of the root weld as the reference trajectory for the first weld.

[0051] The root weld center trajectory extracted in step 2 is directly applied to the welding plan of the first weld pass as its reference trajectory. During the welding process, the welding equipment will perform motion control based on this reference trajectory to ensure that the welding torch performs welding operations along the root weld center trajectory.

[0052] In one embodiment, obtaining the six-degree-of-freedom pose offset parameters corresponding to the current weld seam includes: Step 1: Obtain the actual weld bead profile after the previous weld is completed by line laser scanning.

[0053] After the previous weld seam is completed, a pre-installed and calibrated vision sensor can be activated to scan the weld seam to accurately obtain its actual contour. Various types of vision sensors are available, such as structured light sensors and laser scanners. Here, a line laser scanner is used to obtain the actual weld seam contour, and its working principle is based on optical measurement technology. The line laser scanner is equipped with a high-precision line laser generator that emits a uniform, straight line of laser light. This line laser beam is projected onto the weld seam surface at a specific angle. Because the weld seam surface is not perfectly flat, but has undulations and slope variations, the line laser beam will be reflected and scattered on the weld seam surface.

[0054] Step 2: Extract the absolute spatial position of the actual weld bead profile.

[0055] Point cloud processing algorithms are used to analyze and process the point cloud data of the actual weld contour obtained in step 1. First, the point cloud data is filtered to remove noise and outliers, improving data quality. Then, through coordinate transformation and positioning algorithms, the point cloud data of the actual weld contour is transformed into a unified absolute spatial coordinate system to determine the accurate position of the actual weld contour in space.

[0056] Step 3: Calculate the adaptive offset between the absolute spatial position and the ideal weld trajectory, where the ideal weld trajectory is determined based on the weld trajectory corresponding to the previous weld and the six-degree-of-freedom pose offset parameters.

[0057] The ideal weld bead trajectory is determined based on the weld bead trajectory corresponding to the previous weld and the six-degree-of-freedom pose offset parameters. By comparing the absolute spatial position of the actual weld bead profile with the ideal weld bead trajectory, the spatial position offset (translation along the X, Y, and Z coordinate axes) and the pose angle offset (rotation angles Rx, Ry, and Rz around the X, Y, and Z axes) are calculated respectively. Mathematical methods such as the least squares method can be used to minimize the error between the actual weld bead profile and the ideal weld bead trajectory when calculating the offset, thereby obtaining the adaptive offset.

[0058] Step 4: Generate the pose transformation matrix required for the current weld seam based on the adaptive offset.

[0059] Based on the adaptive offset calculated in step 3, a pose transformation matrix (which can be a 4×4 matrix) is generated using homogeneous coordinate transformation theory. This matrix contains information on translation and rotation transformations. By substituting the translation and rotation angles from the adaptive offset into the corresponding transformation formulas, the elements of the pose transformation matrix are calculated.

[0060] Step 5: Obtain the initial six-degree-of-freedom pose offset parameters corresponding to the current weld.

[0061] The initial six-DOF pose offset parameters can be preset according to welding process requirements, workpiece geometry, and other factors. These parameters include the spatial position offset, attitude angle offset, and the initial values ​​of the path extension or shortening distance between the arc initiation point and the arc termination point. These parameters can be pre-cached in the process parameter library and correspond to the weld pass number.

[0062] Step 6: Correct the initial six-degree-of-freedom pose offset parameters according to the pose transformation matrix to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld.

[0063] Perform matrix operations between the pose transformation matrix generated in step 4 and the initial six-DOF pose offset parameters obtained in step 5. Through matrix multiplication and other operations, apply the effect of the pose transformation matrix to the initial parameters to obtain the corrected six-DOF pose offset parameters corresponding to the current weld.

[0064] In one embodiment, calculating the adaptive offset between the absolute spatial position and the ideal weld bead trajectory includes: The adaptive offset between the absolute spatial position and the ideal weld bead trajectory is calculated by point cloud volume difference calculation or based on molten pool image analysis.

[0065] When acquiring the actual weld bead contour after the previous weld pass using line laser scanning, a vision sensor (such as a structured light sensor or laser scanner) is used to scan the weld bead surface, obtaining point cloud data containing the three-dimensional coordinates of numerous discrete points on the weld bead surface. This point cloud data can accurately describe the geometry and spatial position of the actual weld bead contour. The acquired point cloud data is filtered to remove noise and outliers, improving its quality. Simultaneously, the point cloud data is simplified to reduce its volume and improve the efficiency of subsequent matching calculations. The Iterative Closest Point (ICP) algorithm or other suitable point cloud volume difference algorithms can be used to perform volume difference calculations between the point cloud data of the actual weld bead contour and the point cloud data corresponding to the ideal weld bead trajectory. During the volume difference calculation process, the position and orientation of the actual point cloud are continuously adjusted to minimize the error between it and the ideal point cloud. Based on the results of point cloud volume difference calculation, the translation (along the X, Y, and Z coordinate axes) and rotation (rotation angles Rx, Ry, and Rz around the X, Y, and Z axes) of the actual weld contour relative to the ideal weld trajectory in space are calculated. These translation and rotation amounts are the adaptive offsets.

[0066] Additionally, industrial cameras can be used to capture images of the molten pool in real time during the welding process. These cameras should have high resolution and frame rate to ensure clear capture of detailed changes in the molten pool. The captured molten pool images are preprocessed, including noise reduction and contrast enhancement, to improve image quality and facilitate subsequent analysis. Key features, such as the width and symmetry of the molten pool, are extracted from the preprocessed images. The molten pool width can be measured by measuring the pixel width of a specific region in the image and converting it to the actual physical width using the camera's calibration parameters. The symmetry of the molten pool can be evaluated by analyzing the similarity between the two edges of the image. Based on the extracted molten pool features and a pre-established relationship model between these features and the welding trajectory correction, the correction amount between the actual weld bead and the ideal weld bead trajectory is indirectly derived.

[0067] After correcting the initial six-degree-of-freedom pose offset parameters based on the pose transformation matrix to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld, the process also includes: using the welding control software in a single-step debugging mode to perform a no-load run based on the six-degree-of-freedom pose offset parameters corresponding to the current weld, and judging the rationality of the welding torch trajectory and attitude; or, starting the automatic welding mode to execute the welding operation based on the six-degree-of-freedom pose offset parameters corresponding to the current weld.

[0068] Specifically, when adjusting the six-DOF pose offset parameters corresponding to the current weld, users can choose between a single-step debugging mode or a full-select automatic welding mode. In single-step debugging mode, for each weld (starting from the second weld), the user can turn off "welding enable" before welding, only performing a robot idle run (without arc ignition) to verify whether the trajectory and welding torch posture under the current offset parameters are reasonable. If the requirements are not met, the offset parameters can be repeatedly modified and the idle run repeated until the trajectory is acceptable before turning on welding enable for actual welding. In full-select automatic welding mode, once the process parameters and offset parameters of all weld passes have been confirmed and solidified, the user can select all weld passes at once, enable all welding capabilities, and click "Process Selected Weld Passes." The system will then automatically complete the welding of the entire multi-layer, multi-pass weld in sequence without manual intervention.

[0069] Here, the key improvement of this application is: the traditional trajectory adjustment process that relies on manual point-by-point teaching with a teach pendant is transformed into a parameterized six-degree-of-freedom offset mechanism based on the first reference trajectory, and closed-loop optimization is achieved by combining visual feedback, thereby greatly reducing the dependence on operator experience and improving debugging efficiency and welding consistency.

[0070] Overall, in practical applications, the welding process parameter adjustment method for multi-layer, multi-channel welds in this application has the following significant technical advantages: 1. Significantly shorten the debugging cycle. By replacing manual teaching with parametric offset, the tedious operation of adjusting the robot path point by point is avoided. For complex curved welds with more than 10 layers, the debugging time can be reduced from several days to several hours, improving efficiency by more than 5 times.

[0071] 2. Improve welding quality consistency. Based on a unified reference trajectory and quantifiable offset parameters, ensure that the trajectory generation logic of each weld is consistent; combined with adaptive adjustment based on visual feedback, it can effectively compensate for workpiece assembly errors and the effects of thermal deformation.

[0072] 3. Reduce material and labor costs. The single-step debugging mode supports no-workout verification without welding material consumption, reducing the number of invalid welds; fully automated execution reduces manual intervention, decreases reliance on highly skilled engineers, and reduces waste of special welding materials due to rework.

[0073] 4. Enhanced process flexibility and reusability. The decoupled design of the process parameter library and offset parameters allows the same set of parameter templates to be adapted to different batches of geometrically similar workpieces. Deployment can be achieved quickly by simply adjusting the offset, improving the efficiency of process migration.

[0074] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0075] Based on the same inventive concept, this application also provides a welding process parameter debugging device for multi-layer, multi-channel welds to implement the above-mentioned method for debugging welding process parameters of multi-layer, multi-channel welds. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the welding process parameter debugging device for multi-layer, multi-channel welds provided below can be found in the limitations of the welding process parameter debugging method for multi-layer, multi-channel welds described above, and will not be repeated here.

[0076] In one embodiment, such as Figure 3 As shown, a welding process parameter adjustment device for multi-layer, multi-channel welds is provided, comprising: The database acquisition module 100 is used to acquire the process parameter library for multi-layer and multi-channel welding. The process parameter library stores the welding process parameters for multi-layer and multi-channel welds. The reference trajectory determination module 200 is used to scan the bevel after welding assembly, extract the root weld trajectory, and use the root weld trajectory as the reference trajectory for the first weld. The initial welding trajectory determination module 300 is used to combine the reference trajectory and the welding process parameters corresponding to the first weld in the process parameter library to generate the initial welding trajectory of the first weld. The iteration module 400 is used to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld for each subsequent weld. Based on the welding trajectory of the previous weld, the six-degree-of-freedom pose offset parameters are dynamically adjusted, and the welding trajectory of the current weld is generated by combining the welding process parameters corresponding to the current weld in the process parameter library. The combined adjustment module 500 is used to combine the welding trajectories and welding process parameters of different welds to obtain the welding process parameter debugging results of multi-layer and multi-channel welds.

[0077] In one embodiment, the process parameter library also stores the layer structure; the database acquisition module 100 is also used to scan the bevel after welding assembly and extract the bevel geometric parameters; based on the bevel geometric parameters, the optimal number of welds, the center position of each weld and the interlayer stacking order are calculated by an automatic weld arrangement algorithm combined with preset weld overlap rate, welding torch swing limit and fusion cross-section model, to determine the layer structure; the initial welding trajectory determination module 300 is also used to acquire the welding parameters and layer structure corresponding to the first weld in the process parameter library; based on the reference trajectory and the acquired welding parameters and layer structure, the initial welding trajectory of the first weld is generated.

[0078] In one embodiment, the reference trajectory determination module 200 is further used to perform a three-dimensional visual scan of the bevel after welding assembly to obtain point cloud data of the bevel area; to process the point cloud data of the bevel area using a point cloud processing algorithm to extract the center trajectory of the root weld bead; and to use the center trajectory of the root weld bead as the reference trajectory of the first weld bead.

[0079] In one embodiment, the reference trajectory determination module 200 is further used to extract the contour of the welded and assembled bevel using a contact probe, line laser positioning or arc sensing method to obtain the bevel contour; extract the root weld center trajectory based on the bevel contour; and use the root weld center trajectory as the reference trajectory of the first weld.

[0080] In one embodiment, the iteration module 400 is further configured to acquire the actual weld bead contour after the previous weld bead is completed by line laser scanning; extract the absolute spatial position of the actual weld bead contour; calculate the adaptive offset between the absolute spatial position and the ideal weld bead trajectory, wherein the ideal weld bead trajectory is determined based on the weld bead trajectory corresponding to the previous weld bead and the six-degree-of-freedom pose offset parameters; generate the pose transformation matrix required for the current weld bead based on the adaptive offset; acquire the initial six-degree-of-freedom pose offset parameters corresponding to the current weld bead; and correct the initial six-degree-of-freedom pose offset parameters according to the pose transformation matrix to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld bead.

[0081] In one embodiment, the iteration module 400 is also used to calculate the adaptive offset between the absolute spatial position and the ideal weld trajectory by point cloud volume difference calculation or based on molten pool image analysis.

[0082] Each module in the aforementioned multi-layer, multi-channel weld seam welding process parameter debugging device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0083] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for adjusting welding process parameters for multi-layer, multi-channel welds. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0084] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0085] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method for adjusting welding process parameters of multi-layer, multi-channel welds.

[0086] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the above-described method for adjusting welding process parameters of multi-layer, multi-channel welds.

[0087] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described method for adjusting welding process parameters for multi-layer, multi-channel welds.

[0088] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0089] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0090] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for adjusting welding process parameters for multi-layer, multi-channel welds, characterized in that, The method includes: A process parameter library for multi-layer, multi-channel welding is obtained, wherein the process parameter library stores welding process parameters for multi-layer, multi-channel welds; The bevel after welding assembly is scanned to extract the root weld trajectory, and the root weld trajectory is used as the reference trajectory for the first weld. By combining the reference trajectory and the welding process parameters corresponding to the first weld in the process parameter library, the initial welding trajectory of the first weld is generated. For each subsequent weld, the six-degree-of-freedom pose offset parameters corresponding to the current weld are obtained. Based on the welding trajectory of the previous weld, the six-degree-of-freedom pose offset parameters are dynamically adjusted, and combined with the welding process parameters corresponding to the current weld in the process parameter library, the welding trajectory of the current weld is generated. By combining welding trajectories and welding process parameters of different weld seams, the welding process parameter debugging results of multi-layer and multi-channel weld seams are obtained.

2. The method according to claim 1, characterized in that, The process parameter library also stores layered structures; The layer structure in the process parameter library is generated in the following way: Scan the bevel after welding assembly and extract the bevel geometry parameters; Based on the aforementioned bevel geometry parameters, the optimal number of weld beads, the center position of each weld bead, and the interlayer stacking sequence are calculated by using an automatic bead arrangement algorithm combined with preset weld bead overlap rate, welding torch swing limit, and weld deposition section model, thereby determining the layer structure. The step of generating the initial welding trajectory for the first weld by combining the reference trajectory and the welding process parameters corresponding to the first weld in the process parameter library includes: Obtain the welding parameters and layer structure corresponding to the first weld in the process parameter library; Based on the reference trajectory and the obtained welding parameters and layer structure, the initial welding trajectory of the first weld is generated.

3. The method according to claim 1, characterized in that, The step of scanning the bevel after welding assembly, extracting the root weld trajectory, and using the root weld trajectory as the reference trajectory for the first weld includes: Perform a 3D visual scan on the bevel after welding and assembly to obtain point cloud data of the bevel area; The point cloud data of the bevel area is processed using a point cloud processing algorithm to extract the center trajectory of the root weld bead. The center trajectory of the root weld bead is used as the reference trajectory for the first weld bead.

4. The method according to claim 1, characterized in that, The step of scanning the bevel after welding assembly, extracting the root weld trajectory, and using the root weld trajectory as the reference trajectory for the first weld includes: The contour of the welded bevel is extracted by using a contact probe, line laser positioning, or arc sensing method. The center trajectory of the root weld bead is extracted based on the bevel profile. The center trajectory of the root weld bead is used as the reference trajectory for the first weld bead.

5. The method according to claim 1, characterized in that, Obtaining the six-DOF pose offset parameters corresponding to the current weld includes: The actual weld bead profile after the previous weld seam was completed was obtained by line laser scanning; Extract the absolute spatial position of the actual weld bead profile; Calculate the adaptive offset between the absolute spatial position and the ideal weld trajectory, wherein the ideal weld trajectory is determined based on the weld trajectory corresponding to the previous weld and the six-degree-of-freedom pose offset parameters; Based on the adaptive offset, generate the pose transformation matrix required for the current weld. Obtain the initial six-degree-of-freedom pose offset parameters corresponding to the current weld; The initial six-degree-of-freedom pose offset parameters are corrected based on the pose transformation matrix to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld.

6. The method according to claim 5, characterized in that, The calculation of the adaptive offset between the absolute spatial position and the ideal weld bead trajectory includes: The adaptive offset between the absolute spatial position and the ideal weld bead trajectory is calculated by point cloud volume difference calculation or based on molten pool image analysis. After correcting the initial six-degree-of-freedom pose offset parameters according to the pose transformation matrix to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld, the method further includes: Based on the six-degree-of-freedom pose offset parameters corresponding to the current weld, a single-step debugging mode is used to perform a no-load run with the welding control software, and the rationality of the welding torch trajectory and posture is judged. Alternatively, the welding operation can be performed by starting an automatic welding mode based on the six-degree-of-freedom pose offset parameters corresponding to the current weld.

7. A device for adjusting welding process parameters for multi-layer, multi-channel welds, characterized in that, The device includes: The database acquisition module is used to acquire the process parameter library for multi-layer and multi-channel welding, which stores the welding process parameters for multi-layer and multi-channel welds. The reference trajectory determination module is used to scan the bevel after welding assembly, extract the root weld trajectory, and use the root weld trajectory as the reference trajectory of the first weld. The initial welding trajectory determination module is used to combine the reference trajectory and the welding process parameters corresponding to the first weld in the process parameter library to generate the initial welding trajectory of the first weld. The iteration module is used to obtain the six-degree-of-freedom pose offset parameters corresponding to the current weld for each subsequent weld. Based on the welding trajectory of the previous weld, the six-degree-of-freedom pose offset parameters are dynamically adjusted, and the welding trajectory of the current weld is generated by combining the welding process parameters corresponding to the current weld in the process parameter library. The combined adjustment module is used to combine the welding trajectories and welding process parameters of different welds to obtain the welding process parameter debugging results of multi-layer and multi-channel welds.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images