Welding planning method and apparatus, welding robot, storage medium and program product
Patent Information
- Application Number
- CN202611063009.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-16
- Publication Date
- 2026-09-18
Smart Images
Figure CN122769976A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of welding technology, and in particular to a welding planning method and apparatus, a welding robot, a storage medium, and a program product. Background Technology
[0002] Currently, structural component welding bevel recognition and path planning systems mainly focus on regular, uniform cross-section bevel scenarios. For example, trained machine learning models can be used to process images of welding bevels to identify the bevel type. Another example is using machine vision technology to acquire bevel cross-section data, grouping it to construct a 3D model, analyzing weld, material, and heat-affected zone characteristics to determine welding sequence principles, generating a comprehensive welding path, and dynamically adjusting the optimal path by monitoring key parameters in real time during the welding process and setting up an early warning mechanism. Summary of the Invention
[0003] The inventors noted that in heavy industries such as engineering machinery and new energy equipment, the weld bevel cross-sections of many components are not constant structures, but rather exhibit continuous gradual changes or segmented jumps along the welding direction. This is commonly seen in butt welds of circular arc pipes, diaphragm welds of box beams, and lap welds of irregular cross-sections, all of which involve dynamically changing bevel dimensions, placing extremely high demands on welding path accuracy and process matching. Because related technologies are only applicable to regular, uniform cross-section bevels and lack continuous modeling capabilities, they cannot guarantee weld formation accuracy and welding stability in scenarios with variable cross-section bevels.
[0004] Accordingly, this disclosure provides a welding planning method, which constructs a parametric model of the variable cross-section bevel using the travel data of the variable cross-section bevel, and plans the welding path and welding process parameters of the welding robot based on the parametric model of the variable cross-section bevel, thereby achieving coordinated and precise control of the welding path and welding process parameters, effectively improving the welding forming accuracy and welding stability of the variable cross-section weld.
[0005] In a first aspect of this disclosure, a welding planning method is provided, comprising: acquiring three-dimensional point cloud data of a weld region in a variable cross-section groove and a two-dimensional grayscale image of the variable cross-section groove; obtaining along-path data of the variable cross-section groove based on the three-dimensional point cloud data and the two-dimensional grayscale image to construct a parametric model of the variable cross-section groove; and planning the welding path and welding process parameters of a welding robot based on the parametric model of the variable cross-section groove.
[0006] In some embodiments, the planning of the welding path and welding process parameters of the welding robot includes: dynamically adjusting the target offset of the welding torch in the welding robot relative to the weld centerline, as well as the lateral oscillation amplitude and oscillation frequency of the welding torch, according to the parametric model of the variable cross-section bevel; dynamically adjusting the number of welding passes according to the parametric model of the variable cross-section bevel; and dynamically adjusting at least one of the welding current, wire feed speed, and welding speed according to the parametric model of the variable cross-section bevel.
[0007] In some embodiments, the dynamic adjustment of the target offset of the welding torch relative to the weld centerline includes: determining the target offset of the welding torch relative to the weld centerline based on the groove gap G(s) at the s-th cross-section position in the parameterized model of the variable cross-section groove, wherein when the groove gap G(s) is greater than the gap threshold, the centerline of the welding torch is offset to the side with the larger gap on both sides of the weld centerline.
[0008] In some embodiments, the dynamic adjustment of the lateral oscillation amplitude and oscillation frequency of the welding torch includes: dynamically adjusting the lateral oscillation amplitude and oscillation frequency of the welding torch according to the bevel width W(s) at the s-th cross-section position in the parameterized model of the variable cross-section bevel, wherein the lateral oscillation amplitude and the bevel width W(s) are positively correlated, and the oscillation frequency and the bevel width W(s) are inversely correlated.
[0009] In some embodiments, the dynamic adjustment of the number of weld passes includes: dynamically adjusting the number of weld passes according to the groove depth D(s) at the s-th cross-section position in the parameterized model of the variable cross-section groove, wherein the number of weld passes and the groove depth D(s) are positively correlated.
[0010] In some embodiments, the dynamic adjustment of at least one of the welding current, wire feed speed, and welding speed includes: increasing the welding current and the wire feed speed and decreasing the welding speed when the groove gap G(s) at the s-th cross-section position in the parametric model of the variable cross-section groove is greater than the average groove gap of the welding section and the groove width W(s) at the s-th cross-section position is greater than the average groove width of the welding section; decreasing the welding current and the wire feed speed and increasing the welding speed when the groove gap G(s) at the s-th cross-section position is less than the average groove gap of the welding section and the groove width W(s) at the s-th cross-section position is less than the average groove width of the welding section; and smoothing the welding process parameters and decreasing the welding speed in the region adjacent to the abrupt change point of the weld cross-section in the parametric model of the variable cross-section groove.
[0011] In some embodiments, obtaining the edge data of the variable cross-section bevel includes: performing edge detection on the two-dimensional grayscale image to extract the left and right edge contours of the variable cross-section bevel to obtain the weld centerline; projecting the three-dimensional point cloud data onto a cross-sectional plane perpendicular to the weld centerline; and determining the edge data at each cross-sectional position, wherein the edge data at the s-th cross-sectional position includes the bevel width W(s), bevel depth D(s), bevel gap G(s), and left bevel angle parameter at the s-th cross-sectional position. and right bevel angle parameters Interpolate the data along the entire cross-section to construct a parametric model of the variable cross-section bevel; determine the abrupt change points of the weld cross-section based on the parametric model of the variable cross-section bevel, and delineate the boundaries of the welding sections.
[0012] In some embodiments, the bevel width W(s) is the difference between the left and right abscissas of the s-th cross-section position; the bevel depth D(s) is the difference between the Z-coordinate value of the workpiece surface and the Z-coordinate value of the bevel bottom at the s-th cross-section position; the bevel gap G(s) is the distance between the left and right bevel surfaces at the bottom of the s-th cross-section position; and the left bevel angle parameter... The angle between the left bevel face at the s-th cross-section position and the vertical direction; the right bevel angle parameter Let be the angle between the right bevel face at the s-th cross-section position and the vertical direction.
[0013] In some embodiments, acquiring three-dimensional point cloud data of the weld area in the variable cross-section bevel and a two-dimensional grayscale image of the variable cross-section bevel includes: controlling the welding robot to move along the weld direction at a preset speed so as to acquire three-dimensional point cloud data of the weld area using a vision sensor mounted on the welding robot; and acquiring a two-dimensional grayscale image of the variable cross-section bevel using an image acquisition device mounted on the welding robot.
[0014] In some embodiments, during the welding process, the operating status of the welding torch in the welding robot is collected at a predetermined frequency; based on the operating status of the welding torch, the path deviation of the welding torch relative to the planned path at the s-th cross-section position is determined, wherein the path deviation includes lateral deviation and height deviation; based on the path deviation, the target offset of the welding torch at the s-th cross-section position, and the bevel compensation amount at the s-th cross-section position, a comprehensive correction amount is determined; the comprehensive correction amount is converted into motion increments of each joint of the welding robot; the welding robot is controlled using the motion increments of each joint of the welding robot to control the welding torch to track the planned path.
[0015] In some embodiments, the comprehensive correction amount includes a lateral correction amount and a longitudinal correction amount. Determining the comprehensive correction amount includes: calculating the sum of the lateral deviation and the target offset to obtain the lateral correction amount; and calculating the height deviation and the bevel compensation amount to obtain the longitudinal correction amount.
[0016] In some embodiments, after welding is completed, weld data is collected to evaluate weld quality; based on the deviation between the weld data and the preset planning data, the corresponding optimization and correction data is stored in the process database to achieve the accumulation and reuse of welding process knowledge.
[0017] In a second aspect of this disclosure, a welding planning apparatus is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute instructions stored in the memory to implement the welding planning method as described in any of the above embodiments.
[0018] In a third aspect of this disclosure, a welding robot is provided, comprising: a welding planning device as described in any of the above embodiments; a robot controller configured to control a welding torch in the welding robot to perform welding operations according to a welding path and welding process parameters planned by the welding planning device; an image acquisition device configured to acquire a two-dimensional grayscale image of a variable cross-section bevel; and a vision sensor configured to acquire three-dimensional point cloud data of the weld area in the variable cross-section bevel.
[0019] In a fourth aspect of this disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method as described in any of the above embodiments.
[0020] In a fifth aspect of this disclosure, a computer program product is provided, including computer instructions, wherein the computer instructions, when executed by a processor, implement the method as described in any of the above embodiments.
[0021] Other features and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description
[0022] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0023] Figure 1 This is a schematic flowchart of a welding planning method according to an embodiment of the present disclosure; Figure 2 This is a schematic diagram of a multi-weld pass layout plan according to an embodiment of the present disclosure; Figure 3 This is a schematic flowchart of a welding planning method according to another embodiment of the present disclosure; Figure 4 This is a schematic diagram of the structure of a welding planning apparatus according to an embodiment of the present disclosure; Figure 5 This is a schematic diagram of the structure of a welding robot according to an embodiment of the present disclosure. Detailed Implementation
[0024] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.
[0025] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of this disclosure.
[0026] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.
[0027] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.
[0028] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.
[0029] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.
[0030] Figure 1 This is a schematic flowchart of a welding planning method according to an embodiment of the present disclosure. In some embodiments, the following welding planning method is performed by a welding planning device, including steps 11-13.
[0031] In step 11, three-dimensional point cloud data of the weld area in the variable cross-section groove and two-dimensional grayscale image of the variable cross-section groove are acquired.
[0032] In some embodiments, the welding robot is controlled to move along the weld seam at a preset speed so as to acquire three-dimensional point cloud data of the weld seam area using the vision sensor mounted on the welding robot, and to acquire two-dimensional grayscale images of the variable cross-section bevel using the image acquisition device mounted on the welding robot.
[0033] For example, by using a visual sensor to project laser stripes, three-dimensional point cloud data of the weld area can be collected based on the principle of triangulation.
[0034] For example, vision sensors include structured light vision sensors, and image acquisition devices include industrial cameras.
[0035] In step 12, the friction data of the variable cross-section bevel is obtained based on the three-dimensional point cloud data and the two-dimensional grayscale image to construct a parametric model of the variable cross-section bevel.
[0036] In some embodiments, the step of obtaining the travel data of the variable cross-section bevel includes steps S101-S105.
[0037] S101. Perform edge detection on the two-dimensional grayscale image and extract the left and right edge contour lines of the variable cross-section bevel to obtain the weld center line.
[0038] For example, Canny edge detection is performed on the acquired two-dimensional grayscale image to extract the left and right edge contours of the variable cross-section bevel. The weld centerline C(s) is extracted by combining distance transformation and skeleton thinning algorithms, where s is the arc length parameter along the centerline.
[0039] S102. Project the three-dimensional point cloud data onto a cross-sectional plane perpendicular to the weld centerline.
[0040] S103. Determine the friction data for each cross-section location, where the friction data for the s-th cross-section location includes the bevel width W(s), bevel depth D(s), bevel gap G(s), and left bevel angle parameter for the s-th cross-section location. and right bevel angle parameters .
[0041] For example, for the s-th cross-section position, the RANSAC algorithm is used to fit the plane equations of the left and right bevel surfaces cross-section by cross-section to obtain the bevel width W(s), bevel depth D(s), bevel gap G(s), and left bevel angle parameters. and right bevel angle parameters .
[0042] In some embodiments, the bevel width W(s) is the difference between the abscissas of the left and right edges at the s-th cross-section position. The bevel depth D(s) is the difference between the Z-coordinate value of the workpiece surface at the s-th cross-section position and the Z-coordinate value of the bevel bottom. The bevel gap G(s) is the distance between the left and right bevel surfaces at the bottom at the s-th cross-section position. Left bevel angle parameter. Let be the angle between the left bevel face and the vertical direction at the s-th cross-section position. Right bevel angle parameters. Let be the angle between the right bevel face at the s-th cross-section and the vertical direction.
[0043] S104. Interpolate the data along the entire cross-section to construct a parametric model of the variable cross-section bevel.
[0044] For example, the friction data obtained for the s-th cross-section position is {W(s), D(s), G(s),} , The obtained data along the entire cross-section location are processed by cubic spline interpolation to construct a continuous parametric model of the variable cross-section bevel.
[0045] S105. Determine the abrupt change points of the weld cross section based on the parametric model of the variable cross section groove, and delineate the boundaries of the welding section.
[0046] For example, by using a parameter mutation rate threshold to determine and mark mutation points in the weld section, the boundary of the weld section can be delineated.
[0047] In step 13, the welding path and welding process parameters of the welding robot are planned based on the parametric model of the variable cross-section bevel.
[0048] In some embodiments, the steps of planning the welding path and welding process parameters of the welding robot include steps S201-S203.
[0049] S201. Based on the parametric model of the variable cross-section bevel, dynamically adjust the target offset of the welding torch in the welding robot relative to the weld centerline, as well as the lateral swing amplitude and swing frequency of the welding torch.
[0050] In some embodiments, the target offset of the welding torch relative to the weld centerline is determined based on the bevel gap G(s) at the s-th cross-section position in the parametric model of the variable cross-section bevel.
[0051] For example, the target offset of the welding torch relative to the weld centerline. As shown in formula (1).
[0052] (1)
[0053] In formula (1), k is an empirical coefficient. For example, the value of coefficient k ranges from 0.6 to 0.8.
[0054] In some embodiments, when the bevel gap G(s) is greater than the gap threshold, the centerline of the welding torch shifts to the side with the larger gap on both sides of the weld centerline, thereby ensuring uniform fusion on both sides of the weld. Correspondingly, when G(s) is small, the offset δ(s) also decreases. When G(s) approaches zero, the offset δ(s) also approaches zero, thus enabling the welding torch to accurately align with the weld centerline for centering welding.
[0055] In some embodiments, the lateral oscillation amplitude and oscillation frequency of the welding torch are dynamically adjusted according to the bevel width W(s) at the s-th cross-section position in the parametric model of the variable cross-section bevel. The lateral oscillation amplitude and the bevel width W(s) are positively correlated, and the oscillation frequency and the bevel width W(s) are inversely correlated.
[0056] For example, the lateral oscillation amplitude A(s) of the welding torch is shown in formula (2).
[0057] (2)
[0058] In formula (2), This refers to the coverage coefficient. For example, the coefficient... The value range is from 0.7 to 0.85.
[0059] It should be noted that as the bevel width W(s) increases, the oscillation amplitude A(s) increases accordingly, while the oscillation frequency f(s) decreases accordingly. Conversely, as the bevel width W(s) decreases, the oscillation amplitude A(s) decreases accordingly, while the oscillation frequency f(s) increases accordingly.
[0060] S202. Based on the parametric model of the variable cross-section bevel, dynamically adjust the number of welding passes.
[0061] In some embodiments, the number of weld passes is dynamically adjusted based on the groove depth D(s) at the s-th cross-section position in the parametric model of the variable cross-section groove, wherein the number of weld passes and the groove depth D(s) are positively correlated.
[0062] For example, the number of weld passes N(s) is shown in formula (3).
[0063] (3)
[0064] In formula (3), This represents the maximum melting depth in a single pass.
[0065] For example, when the bevel depth D(s) is greater than the maximum melting depth of a single pass. In the case of [the above], the number of welding passes is automatically calculated according to the above formula (3).
[0066] For example, such as Figure 2 As shown, there are multiple welding passes in the current scenario. , , , These represent the corresponding weld widths, and parameter d represents the single-pass melting depth.
[0067] S203. Based on the parametric model of the variable cross-section groove, dynamically adjust at least one of the welding current, wire feed speed, and welding speed.
[0068] In some embodiments, when the groove gap G(s) at the s-th cross-section position in the parameterized model of the variable cross-section groove is greater than the average groove gap of the welding section and the groove width W(s) at the s-th cross-section position is greater than the average groove width of the welding section, the welding current and wire feed speed are increased, and the welding speed is decreased.
[0069] For example, when the bevel gap G(s) is greater than the average bevel gap in the welding section and the bevel width W(s) is greater than the average bevel width in the welding section, the welding current I(s) increases. to The wire feeding speed V(s) increases to The welding speed U(s) decreased to .
[0070] In some embodiments, when the bevel gap G(s) at the s-th cross-section position is less than the average bevel gap of the welding section and the bevel width W(s) at the s-th cross-section position is less than the average bevel width of the welding section, the welding current and wire feed speed are reduced, and the welding speed is increased.
[0071] For example, when the groove gap G(s) is less than the average groove gap in the welding section and the groove width W(s) is less than the average groove width in the welding section, the welding current I(s) decreases. to The wire feeding speed V(s) decreases to The welding speed U(s) increases to .
[0072] In some embodiments, welding process parameters are smoothed and welding speed is reduced in the region near the abrupt change point of the weld cross-section in the parametric model of the variable cross-section groove.
[0073] Through the above treatment, welding defects in abrupt change areas can be effectively avoided, thereby achieving integrated adaptive and precise planning of the geometric path and welding process parameters of the variable cross-section groove weld.
[0074] In the welding planning method provided in the above embodiments of this disclosure, a parametric model of the variable cross-section groove is constructed by utilizing the travel data of the variable cross-section groove. The welding path and welding process parameters of the welding robot are planned according to the parametric model of the variable cross-section groove, thereby achieving coordinated and precise control of the welding path and welding process parameters, effectively improving the welding forming accuracy and welding stability of the variable cross-section weld.
[0075] Figure 3 This is a schematic flowchart illustrating a welding planning method according to another embodiment of the present disclosure. In some embodiments, the following welding planning method is performed by a welding planning device, including steps 31-35. It should be noted that steps 31-33 in this embodiment are different from... Figure 1 Steps 11-13 in the illustrated embodiment are the same.
[0076] In step 31, three-dimensional point cloud data of the weld area in the variable cross-section groove and two-dimensional grayscale image of the variable cross-section groove are acquired.
[0077] In step 32, the friction data of the variable cross-section bevel is obtained based on the three-dimensional point cloud data and the two-dimensional grayscale image to construct a parametric model of the variable cross-section bevel.
[0078] In step 33, the welding path and welding process parameters of the welding robot are planned based on the parametric model of the variable cross-section bevel.
[0079] In step 34, path correction is performed during the welding process.
[0080] In some embodiments, the step of path correction during welding includes steps S301-S305.
[0081] S301. During the welding process, the operating status of the welding torch in the welding robot is collected at a predetermined frequency.
[0082] For example, by controlling a vision sensor, the operating status of the welding torch can be collected at a frequency of no less than 80Hz.
[0083] S302. Based on the operating status of the welding torch, determine the path deviation of the welding torch at the s-th cross-section position relative to the planned path.
[0084] It should be noted here that path deviation includes lateral deviation e_x(s) and height deviation e_z(s).
[0085] S303. Determine the comprehensive correction amount based on the path deviation, the target offset of the welding torch at the s-th cross-section position, and the bevel compensation amount at the s-th cross-section position.
[0086] It should be noted that the total correction amount includes both lateral correction amount and longitudinal correction amount.
[0087] In some embodiments, the sum of the lateral deviation and the target offset is calculated to obtain the lateral correction amount, and the height deviation and the bevel compensation amount are calculated to obtain the longitudinal correction amount.
[0088] For example, lateral correction amount As shown in formula (4).
[0089] (4)
[0090] In formula (4), This is the lateral deviation. This is the target offset.
[0091] For example, the longitudinal correction amount is shown in formula (5).
[0092] (5)
[0093] In formula (5), For height deviation, This is the amount of compensation for the bevel.
[0094] S304. Convert the overall correction amount into the motion increment of each joint of the welding robot.
[0095] For example, by establishing a coordinate transformation matrix through pre-completed hand-eye calibration, the comprehensive correction amount can be accurately converted into the motion increments of each joint of the robot.
[0096] S305. The welding robot is controlled by the motion increments of each joint of the welding robot, so as to control the welding torch to follow the planned path.
[0097] It should be noted that by utilizing the motion increments of each joint of the welding robot, the welding torch is driven in real time to perform dynamic correction, thereby enabling the welding torch to accurately track the planned welding path.
[0098] In some embodiments, a preset segment length is completed after each welding step. Afterwards, the system will automatically execute the bevel parameter identification process, update the bevel parameterized model, and dynamically correct the welding path in subsequent intervals. This effectively adapts to on-site interference factors such as workpiece clamping errors and welding thermal deformation, achieving full-process rolling adaptive optimization welding and ensuring stable and controllable overall welding accuracy.
[0099] In step 35, welding quality evaluation and path optimization feedback are performed.
[0100] In some embodiments, after welding is completed, weld data for evaluating weld quality is collected, including key quality indicators such as weld width, reinforcement height, and undercut. Based on the deviation between the weld data and the preset planning data, the corresponding optimized correction data is stored in the process database to achieve the accumulation and reuse of welding process knowledge.
[0101] It should be noted that by entering the corrected and optimized data into the process database and updating the initial path and process planning parameters of similar variable cross-section welds, continuous iterative optimization of the welding process can be effectively achieved.
[0102] Figure 4 This is a schematic diagram of the structure of a welding planning apparatus according to an embodiment of the present disclosure.
[0103] like Figure 4 As shown, the welding planning device 40 can be represented in the form of a general-purpose computing device. The welding planning device 40 includes a memory 41, a processor 42, and a bus 43 connecting different system components.
[0104] The memory 41 may include, for example, system memory, non-volatile storage media, etc. System memory may store, for example, an operating system, application programs, a boot loader, and other programs. System memory may include volatile storage media, such as random access memory (RAM) and / or cache memory. Non-volatile storage media may store, for example, instructions for a corresponding embodiment of at least one welding planning method being executed. Non-volatile storage media include, but are not limited to, disk storage, optical storage, flash memory, etc.
[0105] The processor 42 can be implemented using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete hardware components such as discrete gates or transistors. Accordingly, each module, such as the acquisition module, the calculation module, and the adjustment module, can be implemented by executing instructions in the central processing unit (CPU) running memory to perform the corresponding steps, or by implementing dedicated circuits that perform the corresponding steps.
[0106] For example, processor 42 is configured for memory-based instruction execution implementation such as Figure 1 or Figure 3 The method involved in any of the embodiments.
[0107] Bus 43 can use any of the various bus architectures. For example, bus architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MCA) bus, and the Peripheral Component Interconnect (PCI) bus.
[0108] The interfaces 44, 45, and 46 of the welding planning device 40, as well as the memory 41 and processor 42, can be connected via bus 43. Input / output interface 44 provides a connection interface for input / output devices such as monitors, mice, and keyboards. Network interface 45 provides a connection interface for various networked devices. Storage interface 46 provides a connection interface for external storage devices such as floppy disks, USB flash drives, and SD cards.
[0109] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations thereof, can be implemented by computer-readable program instructions.
[0110] These computer-readable program instructions are provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable device to produce a machine, such that execution of the instructions by the processor produces means for implementing the functions specified in one or more boxes of the flowchart and / or block diagram.
[0111] These computer-readable program instructions may also be stored in a computer-readable storage medium. These instructions cause a computer to work in a particular manner to produce an article of manufacture, including instructions that implement the functions specified in one or more boxes in a flowchart and / or block diagram.
[0112] This disclosure may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.
[0113] This disclosure also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement... Figure 1 or Figure 3 The method involved in any of the embodiments.
[0114] This disclosure also provides a computer program product, including computer instructions, wherein the computer instructions, when executed by a processor, implement as follows: Figure 1 or Figure 3 The method involved in any of the embodiments.
[0115] Figure 5 This is a schematic diagram of the structure of a welding robot according to an embodiment of the present disclosure.
[0116] like Figure 5 As shown, the welding robot 50 includes a welding planning device 51, a robot controller 52, an image acquisition device 53, a vision sensor 54, and a welding torch 55. The welding planning device 51 is... Figure 4 The welding planning apparatus involved in any of the embodiments.
[0117] The robot controller 52 is configured to control the welding torch 55 in the welding robot to perform welding operations according to the welding path and welding process parameters planned by the welding planning device 51.
[0118] The image acquisition device 53 is configured to acquire a two-dimensional grayscale image of the variable cross-section bevel.
[0119] The vision sensor 54 is configured to acquire three-dimensional point cloud data of the weld area in the variable cross-section bevel.
[0120] For example, image acquisition device 53 includes an industrial camera, and vision sensor 54 includes a structured light vision sensor.
[0121] By implementing the above embodiments of this disclosure, the following beneficial effects can be obtained.
[0122] 1. By simultaneously acquiring two-dimensional grayscale images and three-dimensional point cloud data of the weld, continuous extraction and modeling of multi-dimensional geometric parameters such as groove width, depth, gap, and angle can be achieved. This breaks the limitations of traditional welding path planning that relies solely on single-section groove features and fragmented parameter information, and realizes the integration and unification of geometric information throughout the entire process of variable cross-section grooves. This is conducive to the coordinated and precise control of welding path and process parameters, and significantly improves the welding forming accuracy and operational stability of variable cross-section welds.
[0123] 2. Based on the continuous parametric model of variable cross-section bevel, the system adaptively completes the integrated planning of welding torch trajectory deviation, oscillation parameters, multi-layer and multi-pass arrangement, welding current, wire feed speed, and welding speed. At the same time, it performs process smoothing and speed reduction control in the bevel abrupt change area. Combined with the real-time deviation correction and rolling path update mechanism, it outputs the optimal welding operation plan. It can effectively adapt to complex working conditions such as gradual changes and segmented jumps along the weld seam, avoid defects such as welding torch deviation, incomplete penetration, burn-through, and path jitter, and significantly reduce the welding failure rate of variable cross-section weld seams.
[0124] 3. By inspecting the weld formation quality and comparing parameters after welding, the deviation correction data is iteratively stored in the process database, realizing the continuous accumulation and reuse of welding process knowledge, forming a closed-loop iterative system of "identification-modeling-planning-correction-optimization", effectively solving the problems of rigid traditional welding paths and lagging manual adaptation of process parameters, continuously improving the adaptive capability and batch production consistency of intelligent welding of complex variable cross-section components, and providing technical support for the automated high-quality welding of irregular and variable cross-section welds in the heavy industry field.
[0125] In some embodiments, the functional units described above may be implemented as general-purpose processors, programmable logic controllers (PLCs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any suitable combination thereof for performing the functions described herein.
[0126] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.
[0127] The description in this disclosure is provided for illustrative and descriptive purposes only and is not intended to be exhaustive or to limit the disclosure to its forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of this disclosure and to enable those skilled in the art to understand this disclosure and to design various embodiments with various modifications suitable for a particular purpose.
Claims
1. A welding planning method, comprising: Collect three-dimensional point cloud data of the weld area in the variable cross-section groove, and a two-dimensional grayscale image of the variable cross-section groove; Based on the three-dimensional point cloud data and the two-dimensional grayscale image, the friction data of the variable cross-section bevel is obtained to construct a parametric model of the variable cross-section bevel. Based on the parametric model of the variable cross-section bevel, the welding path and welding process parameters of the welding robot are planned.
2. The welding planning method according to claim 1, wherein, The planned welding robot's welding path and welding process parameters include: Based on the parametric model of the variable cross-section bevel, the target offset of the welding torch in the welding robot relative to the weld centerline, as well as the lateral swing amplitude and swing frequency of the welding torch, are dynamically adjusted. The number of welding passes is dynamically adjusted based on the parametric model of the variable cross-section bevel. Based on the parametric model of the variable cross-section bevel, at least one of the welding current, wire feed speed, and welding speed is dynamically adjusted.
3. The welding planning method according to claim 2, wherein, The target offset of the welding torch relative to the weld centerline includes: Based on the groove gap G(s) at the s-th cross-section position in the parametric model of the variable cross-section groove, the target offset of the welding torch relative to the weld centerline is determined, wherein when the groove gap G(s) is greater than the gap threshold, the centerline of the welding torch is offset to the side with the larger gap on both sides of the weld centerline.
4. The welding planning method according to claim 2, wherein, The dynamic adjustment of the welding torch's lateral oscillation amplitude and oscillation frequency includes: Based on the bevel width W(s) at the s-th cross-section position in the parameterized model of the variable cross-section bevel, the lateral oscillation amplitude and the oscillation frequency of the welding torch are dynamically adjusted, wherein the lateral oscillation amplitude and the bevel width W(s) are positively correlated, and the oscillation frequency and the bevel width W(s) are inversely correlated.
5. The welding planning method according to claim 2, wherein, The dynamic adjustment of the number of welding passes includes: The number of welding passes is dynamically adjusted based on the bevel depth D(s) at the s-th cross-section position in the parametric model of the variable cross-section bevel, wherein the number of welding passes and the bevel depth D(s) are positively correlated.
6. The welding planning method according to claim 2, wherein, The dynamic adjustment of welding current, wire feed speed, and welding speed includes at least one of the following: If the groove gap G(s) at the s-th cross-section position in the parameterized model of the variable cross-section groove is greater than the average groove gap of the welding section, and the groove width W(s) at the s-th cross-section position is greater than the average groove width of the welding section, then increase the welding current and the wire feeding speed, and decrease the welding speed. If the bevel gap G(s) at the s-th cross-section position is less than the average bevel gap of the welding section and the bevel width W(s) at the s-th cross-section position is less than the average bevel width of the welding section, reduce the welding current and the wire feeding speed, and increase the welding speed. In the parametric model of the variable cross-section groove, the welding process parameters are smoothed in the region near the abrupt change point of the weld cross-section, and the welding speed is reduced.
7. The welding planning method according to claim 1, wherein, The process of obtaining the friction data of the variable cross-section bevel includes: Edge detection is performed on the two-dimensional grayscale image to extract the left and right edge contour lines of the variable cross-section bevel, so as to obtain the weld center line; The three-dimensional point cloud data is projected onto a cross-sectional plane perpendicular to the center line of the weld. Determine the friction data for each cross-section location, where the friction data for the s-th cross-section location includes the bevel width W(s), bevel depth D(s), bevel gap G(s), and left bevel angle parameter for the s-th cross-section location. and right bevel angle parameters ; Interpolate the friction data at all cross-section locations to construct a parametric model of the variable cross-section bevel. The abrupt change point of the weld cross section is determined based on the parametric model of the variable cross section bevel, and the boundary of the welding section is delineated.
8. The welding planning method according to claim 7, wherein, The bevel width W(s) is the difference between the left and right abscissas of the s-th cross-section position; The bevel depth D(s) is the difference between the Z-coordinate value of the workpiece surface at the s-th cross-section position and the Z-coordinate value of the bottom of the bevel. The bevel gap G(s) is the distance between the left and right bevel faces at the bottom of the s-th cross-section position; The left slope angle parameters Let be the angle between the left bevel face at the s-th cross-section position and the vertical direction; The right bevel angle parameters Let be the angle between the right bevel face at the s-th cross-section position and the vertical direction.
9. The welding planning method according to claim 1, wherein, The acquisition of three-dimensional point cloud data of the weld area in the variable cross-section groove and the two-dimensional grayscale image of the variable cross-section groove include: The welding robot is controlled to move along the weld seam at a preset speed so as to collect three-dimensional point cloud data of the weld seam area using the vision sensor mounted on the welding robot. The image acquisition device mounted on the welding robot is used to acquire a two-dimensional grayscale image of the variable cross-section bevel.
10. The welding planning method according to any one of claims 1-9, further comprising: During the welding process, the operating status of the welding torch in the welding robot is collected at a predetermined frequency; Based on the operating status of the welding torch, the path deviation of the welding torch relative to the planned path at the s-th cross-section position is determined, wherein the path deviation includes lateral deviation and height deviation; The comprehensive correction amount is determined based on the path deviation, the target offset of the welding torch at the s-th cross-section position, and the bevel compensation amount at the s-th cross-section position. The overall correction amount is converted into the motion increment of each joint of the welding robot; The welding robot is controlled by using the motion increments of each joint, so as to control the welding torch to follow the planned path.
11. The welding planning method according to claim 10, wherein, The overall correction amount includes lateral correction amount and longitudinal correction amount. The determination of the overall correction amount includes: The lateral correction amount is obtained by calculating the sum of the lateral deviation and the target offset. The longitudinal correction amount is obtained by calculating the height deviation and the bevel compensation amount.
12. The welding planning method according to claim 10, further comprising: After welding is completed, weld data is collected to assess weld quality; Based on the deviation between the weld data and the preset planning data, the corresponding optimized correction data is stored in the process database to realize the accumulation and reuse of welding process knowledge.
13. A welding planning device, comprising: Memory; A processor, coupled to a memory, is configured to implement the welding planning method as described in any one of claims 1-12 based on the memory-stored instructions.
14. A welding robot, comprising: The welding planning apparatus as described in claim 13; The robot controller is configured to control the welding torch in the welding robot to perform welding operations according to the welding path and welding process parameters planned by the welding planning device. The image acquisition device is configured to acquire a two-dimensional grayscale image of a variable cross-section bevel. A vision sensor is configured to acquire three-dimensional point cloud data of the weld area in the variable cross-section bevel.
15. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the welding planning method as described in any one of claims 1-12.
16. A computer program product comprising computer instructions, wherein the computer instructions, when executed by a processor, implement the welding planning method as described in any one of claims 1-12.