Inner flanging welding method for water tank inner container and water tank inner container

Abstract

The invention provides an inner flanging welding method of a water tank inner container and the water tank inner container, and relates to the technical field of welding manufacturing, and the inner flanging welding method comprises the following steps: obtaining three-dimensional point cloud data of an inner flanging interface of the water tank inner container in real time, and registering the point cloud data with a preset three-dimensional geometric model; based on an improved RRT algorithm, in combination with geometric features represented by the registered three-dimensional point cloud data, an initial motion track of a welding gun is planned; welding is conducted on the basis of the initial motion trail, and the weld width, the fusion depth feature and the defect feature are extracted from a molten pool image obtained in the welding process; correcting welding parameters of a welding gun in real time based on the weld width and fusion depth characteristics; and when the defect characteristics do not meet the preset conditions, path re-planning is triggered, a real-time movement track and synchronously-adjusted welding parameters are generated based on the currently-corrected welding parameters and the defect characteristics, and a welding gun is controlled to execute compensation welding. And the welding quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of welding manufacturing, and particularly to an inward flanging welding method for a water tank inner liner and a water tank inner liner. Background Art

[0002] In the field of water tank inner liner manufacturing, the welding quality of the inward flanging interface directly affects the product's sealing performance, pressure resistance, and service life. The traditional welding process has the following technical defects: Poor geometric adaptability: The water tank inner liner mostly adopts a thin-walled curved surface structure, and there are problems such as sudden curvature changes and complex geometric features in the weld transition zone at the inward flanging interface. Conventional automated welding systems rely on offline programming and are difficult to adapt to the real-time changes in the three-dimensional geometric features of the weld, easily leading to deviations in the welding torch posture and uneven heat input, which in turn cause defects such as lack of fusion and cracks.

[0003] Lag in defect response: The dynamic behavior of the molten pool during the welding process is complex. Traditional vision inspection systems can only extract the macroscopic features of the weld through two-dimensional images and cannot accurately quantify three-dimensional defect information such as penetration depth and porosity distribution, resulting in a lag in defect compensation behind the actual working conditions and a low welding qualification rate.

[0004] Severe interference from thermal deformation: The thermal deformation during the welding of the thin-walled structure causes the spatial position of the weld to shift. The traditional Iterative Closest Point (ICP) registration algorithm is sensitive to the local geometric distortion caused by thermal deformation, and the insufficient registration accuracy directly leads to trajectory planning errors, exacerbating the accumulation of welding defects.

[0005] Therefore, it is necessary to provide an inward flanging welding method for a water tank inner liner and a water tank inner liner to solve the above technical problems. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides an inward flanging welding method for a water tank inner liner and a water tank inner liner, which breaks through the geometric adaptability bottleneck of the traditional welding process and improves the welding quality through the collaborative innovation of multi-modal perception, intelligent trajectory planning, and closed-loop parameter control.

[0007] The present invention provides an inward flanging welding method for a water tank inner liner, and the method includes the following steps: Real-time obtain the three-dimensional point cloud data of the inward flanging interface of the water tank inner liner, and register the point cloud data with a preset three-dimensional geometric model; Based on the improved RRT algorithm, combined with the geometric features represented by the registered three-dimensional point cloud data, plan the initial movement trajectory of the welding torch; Perform welding based on the initial movement trajectory, and extract the weld width, penetration depth features, and defect features from the molten pool image obtained during the welding process; Based on the weld width and penetration depth features, real-time correct the welding parameters of the welding torch; When the defect feature does not meet the preset conditions, trigger path replanning, and generate a real-time motion trajectory and synchronously adjusted welding parameters based on the currently corrected welding parameters and the defect feature, and control the welding torch to perform compensation welding.

[0008] Preferably, the real-time acquisition of the three-dimensional point cloud data of the inner flanging interface of the water tank inner liner and the registration of the point cloud data with the preset three-dimensional geometric model include: Collect the initial point cloud data of the inner flanging interface at a preset scanning frequency and preprocess the initial point cloud data; Extract the edge contour features of the preprocessed initial point cloud data, and register the initial point cloud data with the preset three-dimensional geometric model by an improved ICP method to generate geometric features including weld edge contours, curvature distributions, and normal directions.

[0009] Preferably, the registration by the improved ICP method includes: Construct a feature descriptor including the normal direction angle and curvature gradient with the edge contour features of the preprocessed initial point cloud data as constraint conditions, and select a weighted corresponding point pair set based on the similarity measure of the feature descriptor; During the iterative closest point registration process, dynamically adjust the registration error function according to the feature similarity weight of the corresponding point pair, where the feature similarity weight is determined by a joint function composed of the normal direction angle and curvature gradient; Take the dynamically adjusted registration error function as the input, and correct the registration deviation caused by welding thermal deformation through the thin plate spline interpolation algorithm.

[0010] Preferably, the initial motion trajectory of the welding torch is planned based on the improved RRT algorithm and combined with the geometric features characterized by the registered three-dimensional point cloud data, including: During the path extension process of the improved RRT algorithm, dynamically adjust the search weight according to the curvature distribution. When the curvature exceeds the preset threshold, reduce the search weight by a preset ratio; Based on the normal direction and the preset equipment anti-collision constraint, construct a composite constraint condition including an accessibility space model and an obstacle distance field, and generate a candidate path set by restricted random sampling under the limitation of the composite constraint condition; Perform smoothness verification on all candidate paths through the preset weld continuity constraint condition, and select the candidate path that passes the preset heat input uniformity constraint verification from the candidate paths that pass the smoothness verification as the initial motion trajectory.

[0011] Preferably, welding is performed based on the initial motion trajectory, and the weld width, penetration depth features, and defect features are extracted from the molten pool images obtained during the welding process, including: Collect the multi-spectral images of the molten pool in the welding area of the flanging-in interface in real time; Calculate the weld width, penetration characteristics, and defect characteristics from the multi-spectral images of the molten pool, where the defect characteristics include three defect types: pores, lack of fusion, and cracks.

[0012] Preferably, based on the weld width and penetration characteristics, the welding parameters of the welding torch are corrected in real time, including: Compare the weld width and penetration characteristics extracted in real time with the preset target values, and calculate the width deviation and depth deviation; Correct the welding parameters according to the width deviation and depth deviation; Verify the corrected welding parameters based on the preset heat input uniformity constraint until the verified welding parameters are obtained.

[0013] Preferably, the compensated welding includes: Determine the defect area for compensated welding according to the positions and sizes of the defect types in the defect characteristics that do not meet any of the following preset conditions, where the preset conditions are: The diameter of the pores ≤ 0.5 mm, and the distribution density ≤ 3 pieces / cm 2 ; The length of the lack of fusion ≤ 1 mm, and the depth ≤ 0.3 mm; The length of the cracks ≤ 0.3 mm, and the orientation angle deviates from the weld center line ≤ 15°; Based on the currently corrected welding parameters and the normal direction of the defect area, generate a compensation trajectory that meets the composite constraint conditions through an improved RRT algorithm; Dynamically adjust the welding parameters according to the curvature distribution characteristics of the compensation trajectory and verify; Control the welding torch to perform the welding operation according to the compensation trajectory and the verified welding parameters.

[0014] The present invention also provides a water tank inner liner, and the water tank inner liner includes a flanging-in interface formed by welding through the above method.

[0015] Compared with the related art, a flanging-in welding method for a water tank inner liner and the water tank inner liner provided by the present invention have the following beneficial effects: The present invention proposes a method for constructing a feature descriptor based on edge contour constraints, dynamically adjusts the registration error function through a joint function of the normal direction angle and the curvature gradient, and corrects the registration deviation caused by thermal deformation by combining the thin plate spline interpolation algorithm to achieve the registration of weld geometric features.

[0016] Meanwhile, a dynamic adjustment mechanism for search weights sensitive to curvature is introduced to construct a composite constraint model that integrates the normal direction, anti-collision constraints, and heat input uniformity, generating an initial trajectory that meets weld continuity and equipment accessibility. During the compensation welding stage, local path replanning is achieved by improving the RRT* algorithm, incorporating a dynamic obstacle avoidance strategy and a heat-affected zone overlap degree constraint to ensure the process adaptability of the compensation trajectory.

[0017] In addition, three-dimensional defect features such as weld width, penetration depth, and pores / incomplete fusion / cracks are extracted from the multi-spectral images of the molten pool, and a coupled mapping model between width deviation, depth deviation, and welding parameters is established. When the defect features exceed the preset threshold, the welding parameters are dynamically adjusted through the parameter coupling model, and the effectiveness of the parameters is verified based on the heat input uniformity constraint to achieve a full-process closed-loop control of welding quality. Brief Description of the Drawings

[0018] Figure 1 It is a schematic flow chart of an inturned edge welding method for the inner tank of a water tank provided by the present invention.

[0019] Figure 2 It is a schematic structural diagram of the inner tank of the water tank of the present invention. Detailed Description of the Embodiments

[0020] The present invention will be further described in detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention are shown in the drawings rather than all structures. Furthermore, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0021] It should also be noted that for the sake of description, only parts related to the present invention are shown in the drawings rather than all content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operations are completed, but it can also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0022] Embodiment 1 As the core component of a pressure-bearing container (such as a water heater), the inside flanging welding of the water tank inner liner is a key process in the field of container manufacturing. Specifically: By machining a flange structure that folds inward on the edge of the shell opening to form an inside flanging interface, the typical parameters are the flanging height H = 3 - 5 mm, and the bending radius R = 0.5 - 1.5t (t is the sheet thickness).

[0023] However, the traditional welding process has the following defects: During the flanging forming process of thin-walled sheets, springback deformation is likely to occur, resulting in a deviation of 0.3 - 0.8 mm between the actual weld and the theoretical design, and it is difficult to match the traditional off-line programming trajectory.

[0024] The welding heat input causes local shrinkage in the inside flanging area, making the spatial position of the weld shift dynamically, further exacerbating the trajectory tracking error.

[0025] Defects such as pores, lack of fusion, and cracks are likely to expand into crack sources in the complex curved surface stress field, reducing the service life of the product.

[0026] Therefore, the present invention provides an inside flanging welding method for the water tank inner liner to solve the above technical problems.

[0027] Specifically, the method of the present invention includes the following steps: S1: Obtain the three-dimensional point cloud data of the inside flanging interface of the water tank inner liner in real time, and register the point cloud data with a preset three-dimensional geometric model.

[0028] Specifically, step S1 includes the following steps: S11: Collect the initial point cloud data of the inside flanging interface at a preset scanning frequency, and preprocess the initial point cloud data.

[0029] In this embodiment, a 3D line laser scanner (including but not limited to) is used to obtain the initial point cloud data of the inside flanging interface at a scanning frequency of 500 Hz. The specific implementation is as follows: Scanning parameter settings: Laser wavelength: 650 nm (red visible light), scanning line spacing , Z-axis resolution ; Then preprocess the collected initial point cloud data, which includes: Outlier removal: Remove points exceeding the mean range based on statistical filtering, where is the standard deviation of the point cloud density (calculation formula: , where, represents the density of the point neighborhood, represents the average density, represents the total number of points).

[0030] Curvature non-uniform filtering: Set the curvature threshold , and retain the points with curvature greater than (Curvature calculation: , where , are the minimum and maximum eigenvalues of the point cloud covariance matrix). Multi-scale smoothing: Adopt a three-level moving least squares (MLS) filtering with radii , , to eliminate surface ripples.

[0031] S12: Extract the edge contour features of the preprocessed initial point cloud data, and register the initial point cloud data with a preset three-dimensional geometric model through an improved ICP method to generate geometric features including the weld edge contour, curvature distribution, and normal direction.

[0032] In this embodiment, point cloud registration is achieved through an improved ICP algorithm, and the specific process is as follows: First, extract the edge contour features, specifically including: Perform region growing segmentation based on the normal vector on the preprocessed initial point cloud, and extract the curvature continuous region as the weld edge candidate.

[0033] Fit a cylindrical surface (radius tolerance ±0.1 mm) through the RANSAC algorithm, and screen the edge point set that conforms to the geometric features of the inward flange.

[0034] Then, construct the feature descriptor, specifically including: For each point construct a feature vector: where, represents the point index in the current point cloud to be registered (i.e., the preprocessed initial point cloud), represents the corresponding point index in the preset three-dimensional geometric model (determined through nearest neighbor search).

[0035] is the angle between the current normal vector and the normal of the corresponding point in the three-dimensional geometric model, which is used to measure the local geometric direction consistency of the point cloud. If the normal vector angle is too large (e.g., >30°), it indicates that there are significant geometric differences in this area (such as the weld edge or deformation area), and higher weights need to be assigned in the registration.

[0036] , the curvature gradient of the current point and the curvature gradient of the corresponding point in the model The Euclidean distance of the surface can quantify the degree of surface deformation. The greater the difference in curvature gradient (such as stamping springback or thermal deformation area), the more drastic the local geometric change is, and the registration priority needs to be adjusted through dynamic weights.

[0037] is the point density of the current point, defined as The number of points in a sphere with a radius of 3 mm and centered at is used to evaluate data reliability. Data confidence is high in high-density areas (such as flat areas), and weights need to be reduced in low-density areas (such as edges or noise areas) to avoid mismatching.

[0038] Next, the dynamic error function is optimized, including: The feature weight factor is introduced in the ICP iteration, and the optimization objective function is: in, represents a 3×3 rotation matrix, which represents the spatial rotation transformation of the point cloud. represents a 3×1 translation vector, Indicates the total number of corresponding point pairs finally selected, Represents the first Point coordinates, Indicates the point The new coordinates after applying the rotation transformation R, Indicates that the point Rotate first Re-translate , so that it matches the corresponding point in the target point cloud Alignment, Indicates the preset 3D geometric model point cloud The corresponding point coordinates are represents the Euclidean distance operator, Represents the value of the registration error function.

[0039] Indicates The feature similarity weight of the point is calculated according to the following formula: in, Represents the angle between the current normal vector and the normal line of the corresponding point of the 3D geometric model. Represents the curvature gradient difference of the current matching point pair (expressed by Euclidean distance), Indicates the point density of the current point, Indicates the preset baseline density of the corresponding area in the model point cloud.

[0040] Finally, after the dynamic error function optimization is completed, the welding thermal deformation is accurately compensated by the thin plate spline interpolation algorithm.

[0041] During specific implementation, first, no less than 50 control points are selected at intervals of 2 mm along the weld path as the deformation reference. By establishing a non-rigid deformation field model, the local shrinkage characteristics caused by thermal deformation can be accurately described. During the compensation process, the algorithm comprehensively analyzes the three-dimensional residual vectors generated after dynamic registration. When the maximum residual is detected to exceed 0.2 mm, the compensation mechanism is automatically triggered.

[0042] The compensation is executed by using the least squares method to calculate the optimal correction parameters, including the linear transformation matrix and the translation vector, to ensure that the path deviation after compensation is controlled within the tolerance range of ±0.1 mm required by the process.

[0043] After registration, geometric features are generated, specifically including: First, the normal vectors of the registered point cloud are calculated (neighborhood radius 3 mm), and the continuous point sets with the normal vector angle greater than 30° are identified as the initial weld edges. Then, the contour is optimized by RANSAC cylindrical surface fitting (radius tolerance ±0.1 mm), and finally, a weld edge point set with an accuracy of ±0.03 mm is obtained.

[0044] The curvature distribution feature calculates the local surface Gaussian curvature by using the moving least squares method, divides the point cloud into 0.5 mm×0.5 mm×0.2 mm voxel grids, and calculates the average curvature of each grid to generate a gradient field that can identify curvature mutations above 0.3 mm.

[0045] The initial value of the normal direction is estimated by using the PCA method. For high-curvature regions ( ), the neighborhood radius is reduced to 1 mm to improve the accuracy, and then the normal orientations are unified by using the minimum spanning tree algorithm. Finally, a unit normal vector field with an angular dispersion less than 0.8° is obtained.

[0046] S2: Based on the improved RRT algorithm, combined with the geometric features characterized by the registered three-dimensional point cloud data, plan the initial motion trajectory of the welding torch.

[0047] Specifically, step S2 includes the following steps: S21: During the path expansion process of the improved RRT algorithm, the search weight is dynamically adjusted according to the curvature distribution. When the curvature exceeds the preset threshold, the search weight is reduced according to the preset ratio.

[0048] In this embodiment, during the path expansion process of the improved RRT algorithm, the search weight is dynamically adjusted according to the curvature distribution of the registered point cloud to optimize the path planning efficiency and accuracy. The curvature threshold is set to , and this value is calibrated based on the stamping springback test results of common materials such as 304 stainless steel and aluminum alloy, and can effectively distinguish flat regions from high-curvature features (such as weld start and end points or bending regions).

[0049] When it is detected that the curvature of the current path expansion area exceeds the threshold, the algorithm reduces the search weight of this area according to a preset ratio. Exemplarily, when the curvature is , the weight is reduced to 70% of the original value, and when the curvature is , the weight is reduced to 50%. The weight adjustment adopts linear interpolation to ensure smooth transition. At the same time, in the high-curvature area (curvature > ), the path expansion step size is reduced from the default 1 mm to 0.5 mm to avoid path mutations caused by too large a step size. The search direction preferentially expands along the direction of the curvature gradient descent, reducing redundant nodes of the path in complex geometric areas and improving the planning efficiency.

[0050] S22: Based on the normal direction and the preset device anti-collision constraint, construct a composite constraint condition including the reachability space model and the obstacle distance field, and generate a candidate path set through restricted random sampling under the limitation of the composite constraint condition.

[0051] In this embodiment, based on the registered normal direction and the device kinematic parameters, a candidate path set under the composite constraint condition is constructed.

[0052] First, define the reachability space according to the kinematic model of the end effector of the welding torch (Denavit-Hartenberg parameters of a six-degree-of-freedom robotic arm), restricting the joint rotation angle range of the welding torch posture (such as the maximum rotation angle of each axis ±180°) and the working range of the tool center point (TCP) (diameter ≤ 500 mm).

[0053] Combined with the point cloud normal direction, force the angle between the axis of the welding torch and the surface normal to be ≤ 5° to prevent the lack of fusion defect caused by the deviation of the welding wire. Secondly, convert the three-dimensional models of the water tank inner liner and the fixture into an Euclidean distance field, and calculate the minimum safety distance between the welding torch and the obstacle in real time (≥ 3 mm), which is comprehensively set based on the end diameter of the welding torch (10 mm) and the thermal expansion margin (0.2 mm).

[0054] During the path expansion process, adopt a biased sampling strategy guided by a probability threshold: expand in the direction of the target point with a probability of 80% and randomly explore with a probability of 20%. At the same time, introduce a repulsive force field in the collision risk area (distance from the obstacle < 5 mm) to dynamically adjust the sampling direction. The candidate path needs to pass the reachability verification and anti-collision detection to ensure uniform node spacing and no interference.

[0055] S23: Perform smoothness verification on all candidate paths through the preset weld seam continuity constraint condition, and select the candidate path that passes the preset heat input uniformity constraint verification from the candidate paths that pass the smoothness verification as the initial motion trajectory.

[0056] In this embodiment, multi-level verification and optimization are performed on the generated candidate path set to ensure meeting the welding process requirements.

[0057] First, the path is smoothed through cubic B-spline interpolation, controlling the curvature change rate between nodes ≤ 0.15 rad / mm to eliminate sudden attitude changes. The interpolation parameters are set as follows: the control point spacing is 2 mm, and the curve tension coefficient is 0.5, ensuring path continuity and the smoothness of the welding torch movement.

[0058] Secondly, based on the welding current-speed-heat input model (heat input = current × voltage / welding speed), the heat input of each path segment is calculated, requiring the coefficient of variation of the heat input for the entire path ≤ 5% (calculation formula: standard deviation / mean × 100%). For paths that exceed the standard (such as the coefficient of variation > 5%), the welding speed or current parameters are automatically adjusted and re-verified after adjustment.

[0059] Finally, the comprehensive optimal solution is selected from the verified paths: using the total path length (weight 60%) and heat input uniformity (weight 40%) as evaluation indicators, and sorting by the weighted scoring method (total score = 0.6 × length normalization value + 0.4 × heat input uniformity normalization value), and selecting the path with the highest total score as the initial motion trajectory.

[0060] S3: Welding is performed based on the initial motion trajectory, and the weld width, penetration characteristics, and defect characteristics are extracted from the molten pool images obtained during the welding process.

[0061] Specifically, step S3 includes the following steps: S31: The multi-spectral images of the molten pool in the welding area of the inward flanging interface are collected in real time.

[0062] During the welding process, high-precision multi-spectral imaging technology is used to collect the dynamic image data of the molten pool in real time. An industrial-grade camera is configured, equipped with a high-performance sensor, supporting dual-channel synchronous imaging in the visible light (500 - 700 nm) and near-infrared (850 - 1050 nm) bands. The camera is equipped with a standard focal length lens, the aperture is set to f / 2.8, the working distance is fixed at 200 mm, and the depth of field range is ±1.5 mm to ensure clear imaging of the molten pool area. A band-pass filter is installed in the visible light channel, and a special filter is installed in the near-infrared channel, with a filter attenuation rate > 99.5% to effectively suppress the interference of the welding arc light. The imaging resolution is set to 0.02 mm / pixel (corresponding to 2048 × 1536 pixels), covering a 20 mm × 15 mm welding area (including the molten pool and 5 mm heat-affected zones on both sides).

[0063] A trigger signal is sent through the bus of the welding torch motion controller, triggering an exposure every 0.5 mm of the welding torch displacement to achieve continuous spatial sampling. The exposure time is dynamically adjusted (0.1 ms - 1 ms) in the HDR mode to adapt to the drastic change in the brightness of the molten pool.

[0064] In addition, to ensure data reliability, fiber optic transmission is used to transfer image data to shield electromagnetic interference, and an air curtain device (flow rate 5 L / min) is installed to blow away welding fumes in real time to ensure image clarity.

[0065] S32: Calculate the weld width, penetration characteristics, and defect characteristics from the multi-spectral image of the molten pool, where the defect characteristics include three defect types: pores, lack of fusion, and cracks.

[0066] In this embodiment, when extracting welding quality characteristics based on the multi-spectral image, a multi-level processing flow is executed.

[0067] For weld width measurement, first, median filtering (3×3 kernel) is performed on the visible light image to reduce noise, and then an adaptive threshold segmentation algorithm is used to extract the binary contour of the molten pool. Measurement lines are set every 0.2 mm along the normal direction of the weld (based on the normal field data generated in step S12), and the maximum value of the contour edge spacing is calculated as the weld width. The measurement accuracy is calibrated with a standard gauge to ensure an error ≤ ±0.05 mm (95% confidence level).

[0068] The penetration characteristics are inverted through the near-infrared band: Based on the optical law, an intensity-depth model is established, and the formula is expressed as the penetration depth h equals the reciprocal of the material absorption coefficient multiplied by the natural logarithm of the ratio of the reference light intensity to the measured light intensity , where the calibration value of stainless steel is . Penetration depth curves are generated every 0.2 mm along the weld, and areas with a depth change amount > 0.3 mm are detected as lack of fusion defects. .

[0069] Defect detection adopts a multi-algorithm fusion strategy: Pores are extracted by morphological processing to screen for targets with a diameter > 0.5 mm and roundness > 0.7; lack of fusion is determined by combining the visible light edge gradient and the near-infrared depth change amount; cracks are extracted by an edge detection algorithm for linear features with a length > 0.3 mm, aspect ratio > 5:1, and deviation from the weld center line > 15°.

[0070] S4: Based on the weld width and penetration characteristics, the welding parameters of the welding torch are corrected in real time.

[0071] Specifically, step S4 includes the following steps: S41: Compare the weld width and penetration characteristics extracted in real time with the preset target values, and calculate the width deviation and depth deviation.

[0072] During the real-time welding process, the collected weld width and penetration characteristics are dynamically compared with the preset target values. The preset target values are set according to the material thickness and process specifications. For example, for a 304 stainless steel inner liner with a thickness of 2 mm, the target weld width is 2.0 ± 0.1 mm, and the target penetration is 1.5 ± 0.05 mm. Real-time data is extracted every 0.2 mm of the welding torch displacement to calculate the width deviation and the depth deviation : The width deviation is the absolute difference between the measured value and the target value, and the depth deviation is also the absolute difference between the measured value and the target value. The deviation data is processed by sliding window filtering (window length 10 mm), and the smoothed width deviation and depth deviation are output after eliminating local noise interference

[0073] S42: According to the width deviation and depth deviation, the welding parameters are corrected

[0074] In this embodiment, when dynamically adjusting the welding parameters according to the deviation, a multi-variable coupling control strategy is adopted. When the width deviation > 0.1 mm, the welding current is adjusted proportionally For every 0.1 mm increase, the current is reduced by 5 A (for example, from 150 A to 145 A); For every 0.1 mm decrease, the current is increased by 5 A

[0075] If the penetration deviation > 0.05 mm, the current is adjusted synchronously For every 0.05 mm increase, the current is increased by 3 A to compensate for insufficient penetration; For every 0.05 mm decrease, the current is reduced by 3 A to avoid excessive penetration. When and both exceed the standard, the welding speed is adjusted first: the speed adjustment amount = 0.2 × ΔW + 0.3 × ΔD (unit: mm / s). For example = 0.15 mm, = 0.06 mm, = 0.048 mm / s (the speed is adjusted from 5 mm / s to 5.048 mm / s). The voltage is synchronously fine-tuned based on the preset current-voltage characteristic curve to maintain the arc stability, and the adjustment amplitude ≤ ±2 V

[0076] S43: Based on the preset heat input uniformity constraint, verify the corrected welding parameters until the verified welding parameters are obtained

[0077] In this embodiment, the corrected parameters need to be verified by the thermal input uniformity. Calculate the thermal input per unit length Q = (current I × voltage U) / speed V (unit: J / mm) in real time. Divide the weld into analysis segments every 5 mm, and statistically calculate the average value of the Q values of each segment and the standard deviation , and calculate the coefficient of variation C = / × 100%. If C > 5%, trigger secondary correction: for the sections where the Q value fluctuates > 10%, adjust the speed (preferably) or current proportionally, and the adjustment range ≤ ±5%. After correction, collect data again for verification until C of three consecutive analysis segments is ≤ 5%. After passing the verification, lock the parameters and record the historical data. If the correction fails to meet the standard for 5 consecutive times, suspend welding and alarm. After testing, this method can control the coefficient of variation of thermal input within 4.2%, and the fluctuations of weld width and penetration are ≤ ±0.07 mm and ±0.03 mm respectively, meeting the process requirements of the water tank inner liner.

[0078] S5: When the defect characteristics do not meet the preset conditions, trigger path replanning, and generate a real-time motion trajectory and synchronously adjusted welding parameters based on the currently corrected welding parameters and the defect characteristics, and control the welding torch to perform compensated welding.

[0079] Specifically, the compensated welding in step S5 includes:[[]] S51: Determine the defect area for compensated welding according to the position and size of the defect type that does not meet any of the following preset conditions, where the preset conditions are:[[]] The diameter of the pores ≤ 0.5 mm, and the distribution density ≤ 3 pores / cm 2 ; The length of the lack of fusion ≤ 1 mm, and the depth ≤ 0.3 mm; The length of the crack ≤ 0.3 mm, and the orientation angle deviates from the weld center line ≤ 15°.

[0080] In this embodiment, welding defects are detected in real time through multi-spectral image analysis. When the pore diameter exceeds 0.5 mm or the distribution density is greater than 3 pores / cm², determine its geometric center through morphological processing and delimit a compensation area with a radius of 0.75 mm; for lack of fusion defects, combine the penetration curve and edge gradient detection. When the penetration difference of three consecutive points exceeds 0.3 mm and the length is greater than 1 mm, extend 0.5 mm along the weld direction as the compensation area; for crack defects, screen linear features with a length exceeding 0.3 mm and deviating from the weld center line by more than 15° through edge detection, and extend 0.2 mm at both ends to delimit the compensation area. All defect areas are extended outward by 0.3 mm as the anti-leakage welding allowance. When the distance between adjacent defects is less than 0.5 mm, they are automatically merged. Finally, convert the image coordinates to the three-dimensional point cloud space to generate a compensation area model with normal vectors.

[0081] S52: Based on the current corrected welding parameters and the normal direction of the defect area, generate a compensation trajectory that meets the composite constraint conditions through an improved RRT algorithm.

[0082] In this embodiment, based on the normal direction of the defect area and the current welding parameters, generate a compensation trajectory through an improved RRT algorithm. First, load the composite constraint conditions (reachable space model + obstacle distance field) of step S2, and start local path planning in the defect area: Search for the starting point: The geometric center of the defect area is offset by 0.5 mm along the normal direction (to avoid the welded area).

[0083] Target point: Extend 1 mm along the weld direction from the end of the defect.

[0084] Step size adjustment: The step size in the defect area is set to 0.3 mm (30% of the default step size).

[0085] Weight optimization: For the area where the curvature > , the weight is reduced to 40%, and preferentially bypass the defect-dense area During the planning process, continuously detect the distance between the welding torch and the obstacle (≥3 mm), and generate candidate paths that meet the anti-collision constraints. Finally, select the path with a heat input coefficient of variation < 3% and the shortest length as the compensation trajectory.

[0086] S53: Dynamically adjust the welding parameters according to the curvature distribution characteristics of the compensation trajectory and verify.

[0087] In this embodiment, dynamically adjust the welding parameters according to the geometric characteristics of the compensation trajectory: Curvature adaptive adjustment: When the curvature > , the welding speed is reduced by 20% (e.g., from 5 mm / s to 4 mm / s).

[0088] For every increase in curvature of , the current is increased by 3 A (e.g., from 150 A to 153 A).

[0089] Normal direction calibration: When the angle between the axis of the welding torch and the normal is > 3°, trigger fine attitude adjustment, and the maximum adjustment angular velocity is 0.5 rad / s.

[0090] Heat input verification: Calculate the heat input Q of the compensation section = (current × voltage) / speed, and require that the Q value fluctuation ≤ ±5%.

[0091] For the area where the standard is exceeded (Q fluctuation > 5%), automatically reduce the current by 2 A or increase the speed by 0.1 mm / s.

[0092] After parameter adjustment, the feasibility of the trajectory is verified through virtual welding simulation. If a collision risk or excessive heat input is detected, re-planning is performed.

[0093] S54: Control the welding torch to perform welding operations according to the compensated trajectory and the verified welding parameters.

[0094] In this embodiment, when controlling the welding torch to perform compensated welding, the motion trajectory of the welding torch is planned using a fifth-order polynomial interpolation algorithm to ensure that the acceleration ≤ 0.2g to eliminate mechanical vibration.

[0095] During the compensated welding process, multi-spectral images of the molten pool are collected in real time for every 0.1 mm displacement, and the weld width (allowable error ±0.05 mm) and penetration depth (allowable error ±0.03 mm) are verified synchronously.

[0096] Set three termination conditions: 1) Confirm through image processing that the defect area coverage rate > 95%; 2) The coefficient of variation C of the heat input in the compensated section ≤ 3%; 3) Real-time monitoring shows no new defect alarms (porosity / incomplete fusion / cracks).

[0097] The welding parameters are dynamically adjusted according to the geometric characteristics of the compensated area: in the area where the curvature > automatically reduce the welding speed by 20% and increase the current by 3A, while keeping the angle between the axis of the welding torch and the normal ≤ 3°. If the compensation fails to meet the standards for 3 consecutive times (any condition is not satisfied), immediately suspend the operation and trigger a maintenance alarm, and at the same time record the current welding parameters, trajectory coordinates and molten pool image data for fault analysis.

[0098] Embodiment 2 The present invention also provides a water tank inner liner, and the water tank inner liner 1 includes an inward flanging interface 2 formed by welding through the above method.

[0099] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0100] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0101] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

Claims

1. A method for inturned edge welding of a water tank inner liner, characterized in that, The method includes the following steps: Obtain the three-dimensional point cloud data of the inner flanging interface of the water tank inner liner in real time, and register the point cloud data with a preset three-dimensional geometric model; Based on the improved RRT algorithm, combine the geometric features represented by the registered three-dimensional point cloud data to plan the initial motion trajectory of the welding torch; Perform welding based on the initial motion trajectory, and extract the weld width, penetration features, and defect features from the molten pool images obtained during the welding process; Based on the weld width and penetration features, correct the welding parameters of the welding torch in real time; When the defect features do not meet the preset conditions, trigger path replanning, and generate a real-time motion trajectory and synchronously adjusted welding parameters based on the currently corrected welding parameters and the defect features, and control the welding torch to perform compensated welding.

2. The inside flanging welding method of a water tank inner liner according to claim 1, characterized in that The obtaining the three-dimensional point cloud data of the inner flanging interface of the water tank inner liner in real time and registering the point cloud data with a preset three-dimensional geometric model includes: Collect the initial point cloud data of the inner flanging interface at a preset scanning frequency, and preprocess the initial point cloud data; Extract the edge contour features of the preprocessed initial point cloud data, and register the initial point cloud data with the preset three-dimensional geometric model by an improved ICP method to generate geometric features including the weld edge contour, curvature distribution, and normal direction.

3. A method for inward flanging and welding of the inner tank of a water tank according to claim 2, characterized in that, The registration by the improved ICP method includes: Construct a feature descriptor including the normal direction angle and curvature gradient with the edge contour features of the preprocessed initial point cloud data as the constraint conditions, and select a weighted corresponding point pair set based on the similarity measure of the feature descriptor; During the iterative closest point registration process, dynamically adjust the registration error function according to the feature similarity weight of the corresponding point pairs, where the feature similarity weight is determined by a joint function composed of the normal direction angle and curvature gradient; Take the dynamically adjusted registration error function as the input, and correct the registration deviation caused by welding thermal deformation through the thin plate spline interpolation algorithm.

4. A method for inward flanging and welding of the inner tank of a water tank according to claim 3, characterized in that, The planning the initial motion trajectory of the welding torch based on the improved RRT algorithm and combining the geometric features represented by the registered three-dimensional point cloud data includes: During the path expansion process of the improved RRT algorithm, dynamically adjust the search weight according to the curvature distribution. When the curvature exceeds the preset threshold, reduce the search weight by a preset ratio; Construct a composite constraint condition including an accessibility space model and an obstacle distance field based on the normal direction and the preset equipment anti-collision constraint, and generate a candidate path set through restricted random sampling under the limitation of the composite constraint condition; Perform smoothness verification on all candidate paths through the preset weld continuity constraint condition, and select the candidate path that passes the verification of the preset heat input uniformity constraint from the candidate paths that pass the smoothness verification as the initial motion trajectory.

5. A method for inward flanging and welding of the inner tank of a water tank according to claim 4, characterized in that, The performing welding based on the initial motion trajectory and extracting the weld width, penetration features, and defect features from the molten pool images obtained during the welding process includes: Collect the multi-spectral images of the molten pool in the welding area of the inner flanging interface in real time; The weld width, penetration characteristics, and defect characteristics are calculated from the multi-spectral image of the molten pool, where the defect characteristics include three defect types: pores, lack of fusion, and cracks.

6. A method for inturned edge welding of the inner tank of a water tank according to claim 5, characterized in that Based on the weld width and penetration characteristics, the welding parameters of the welding torch are corrected in real time, including: Comparing the weld width and penetration characteristics extracted in real time with the preset target values, and calculating the width deviation and depth deviation; Correcting the welding parameters according to the width deviation and depth deviation; Verifying the corrected welding parameters based on the preset heat input uniformity constraint until the verified welding parameters are obtained.

7. A method for inward flanging and welding of the inner tank of a water tank according to claim 6, characterized in that, The compensated welding includes: Determining the defect area for compensated welding according to the positions and sizes of the defect types that do not meet any of the following preset conditions in the defect characteristics, where the preset conditions are: The diameter of the stomata is ≤ 0.5 mm, and the distribution density is ≤ 3 pieces / cm 2 ; The length of the lack of fusion ≤ 1 mm and the depth ≤ 0.3 mm; The length of the crack ≤ 0.3 mm and the orientation angle deviates from the weld center line ≤ 15°; Generating a compensation trajectory that meets the composite constraint conditions through an improved RRT algorithm based on the currently corrected welding parameters and the normal direction of the defect area; Dynamically adjusting the welding parameters and verifying according to the curvature distribution characteristics of the compensation trajectory; Controlling the welding torch to perform welding operations according to the compensation trajectory and the verified welding parameters.

8. A water tank inner liner, characterized in that, The inner tank of the water tank includes an inward flanging interface formed by welding using the method according to any one of claims 1 to 7.

Images