Electron beam welding path adjustment method and apparatus

Abstract

The present application relates to the technical field of welding, in particular to an electron beam welding path adjusting method and device, comprising the steps of: obtaining weld geometry data of a workpiece to be welded, scanning the workpiece to be welded according to the weld geometry data to obtain spatial data of a welding position; layering the spatial data to obtain preliminary path data, and controlling a welding torch to perform preliminary welding on the workpiece to be welded according to the preliminary path data; obtaining secondary electron signals in the preliminary welding process, generating feedback data according to the deviation of the secondary electron signals and the preliminary path data; adjusting welding parameters of the welding torch according to the feedback data, and controlling the welding torch to perform secondary welding on the workpiece to be welded until the welding is completed. The present application improves the welding seam centering ability and energy deposition uniformity of the electron beam on complex curved surfaces, large-thickness components and workpieces with geometric and assembly deviations, effectively ensuring the consistency and reliability of the welding seam forming quality, internal compactness and mechanical properties.

Description

Technical Field

[0001] This invention relates to the field of welding technology, and more specifically, to a method and apparatus for adjusting the electron beam welding path. Background Technology

[0002] Electron beam welding is a high-energy-density, high-vacuum joining technology that utilizes a high-speed focused electron beam to bombard the workpiece surface, efficiently converting kinetic energy into heat energy to achieve deep penetration and narrow weld seams. However, existing electron beam welding processes still face significant technical limitations in practical applications.

[0003] Current electron beam welding methods primarily rely on offline programming or pre-defined welding trajectory planning. This involves calculating and inputting the welding torch's movement path, beam current parameters, and scanning mode in advance based on the workpiece's design drawings or CAD model. This approach ensures repeatability and consistency in the welding process when the workpiece geometry is regular, assembly precision is high, and batches are stable. However, in complex curved surfaces, thick components, or actual production environments with manufacturing tolerances, minor geometric deviations, changes in assembly gaps, or thermal deformation inevitably occur on the workpiece surface. These factors can cause a misalignment between the pre-defined path and the actual weld position, thus affecting the precise alignment of the electron beam with the weld and the uniformity of energy deposition.

[0004] Therefore, there is an urgent need to develop an electron beam welding method that can achieve dynamic path optimization and adaptive parameter adjustment based on the acquisition of the true geometric information of the weld, so as to overcome the overall technical shortcomings of the existing technology, such as frequent welding defects and unstable quality caused by path deviation. Summary of the Invention

[0005] The main objective of this invention is to provide an electron beam welding path adjustment method and apparatus, which aims to overcome the technical problem that existing technologies cannot adjust the path according to the actual weld position of the workpiece.

[0006] To address the aforementioned problems, this invention proposes an electron beam welding path adjustment method, the method comprising: Obtain the weld geometry data of the workpiece to be welded, and scan the workpiece to be welded based on the weld geometry data to obtain the spatial data of the welding area; The spatial data is hierarchically planned to obtain preliminary path data, and the welding torch is controlled to perform preliminary welding on the workpiece to be welded based on the preliminary path data; Secondary electronic signals are acquired during the initial welding process, and feedback data is generated based on the deviation between the secondary electronic signals and the initial path data. The welding parameters of the welding torch are adjusted based on the feedback data, and the welding torch is controlled to perform secondary welding on the workpiece to be welded until the welding is completed.

[0007] Furthermore, the step of obtaining the weld geometry data of the workpiece to be welded includes: Collect the weld position and height information of the workpiece to be welded, as well as the raw data of the height from the welding torch to the weld; The raw data is preprocessed and filtered to obtain the weld geometry data.

[0008] Further, the step of scanning the workpiece to be welded based on the weld geometry data to obtain the spatial data of the welding area includes: Based on the weld geometry data, the initial positioning position of the welding torch in the weld area of ​​the workpiece to be welded is calculated, and a scanning path sequence is generated. The scanning device is controlled to perform a three-dimensional scan of the workpiece to be welded according to the scanning path sequence, so as to obtain the original point cloud data of the welding part. The original point cloud data is subjected to denoising and registration processing to obtain the spatial data of the welding area.

[0009] Furthermore, the step of performing hierarchical path planning on the spatial data to obtain preliminary path data includes: Curve fitting is performed on the spatial data of the welded area to obtain continuous weld trajectory data; The continuous weld trajectory data is divided into layers along the depth direction according to the weld depth variation. The sub-trajectory point sequence corresponding to each layer is extracted to obtain the set of weld sub-trajectories for each layer, where each layer corresponds to a weld filling height range. For each layer of weld seam sub-trajectory set, the rate of change of welding gun posture between adjacent points is calculated sequentially. The trajectory is then segmented according to a preset angle change threshold to obtain segmented trajectory data. Welding gun constraints are sequentially superimposed on each segment of the segmented trajectory data, and initial welding parameters are set for each segment to obtain preliminary path data.

[0010] Furthermore, the step of controlling the welding torch to perform preliminary welding on the workpiece according to the preliminary path data includes: Welding control commands are generated based on the preliminary path data and sent to the welding torch. The welding torch is then driven to perform initial attitude alignment and height calibration based on the welding control commands. According to the welding control command, the welding torch is controlled to move along the preliminary path and to carry out electron beam bombardment, and preliminary welding process data is collected.

[0011] Furthermore, the step of acquiring secondary electronic signals during the initial welding process includes: The secondary electronic signals in the preliminary welding process data are acquired to obtain the original secondary electronic signal data. The original secondary electronic signal data is amplified and filtered to obtain a denoised secondary electronic signal. The denoised secondary electronic signal is subjected to feature extraction processing to obtain characteristic parameters such as weld pool width, weld depth, welding torch projection height, and actual welding angle deviation.

[0012] Further, the step of generating feedback data based on the deviation between the secondary electronic signal and the preliminary path data includes: The intensity and distribution characteristics of the secondary electronic signal are extracted to obtain weld pool data; The weld pool data is compared with the preset theoretical feature value of the corresponding position in the preliminary path data to obtain the position deviation value and feature deviation value. Feedback data containing the deviation amount, spatial location information, and corresponding parameter adjustment direction is generated based on the position deviation value and characteristic deviation value.

[0013] Furthermore, the step of adjusting the welding parameters of the welding torch based on the feedback data and controlling the welding torch to perform secondary welding on the workpiece until welding is completed includes: The feedback data is processed by deviation classification and threshold judgment to obtain the adjustment requirement identifier of the current welding segment and the corresponding deviation type set; The parameter correction amount is calculated and processed by the set of deviation types and the preliminary path data of the current segment to obtain the welding gun attitude correction amount, beam intensity adjustment amount, height compensation amount and scanning deflection amount; The initial path data and initial welding parameters of the current segment are locally updated based on the welding torch attitude correction amount, beam intensity adjustment amount, height compensation amount, and scanning deflection amount to obtain the updated welding parameters. Based on the updated welding parameters, a secondary welding control command is generated to control the welding torch to continue performing electron beam welding along the updated path until all layered path segments are welded.

[0014] This application also discloses an electron beam welding path adjustment device, comprising: The acquisition module is used to acquire the weld geometry data of the workpiece to be welded, and scan the workpiece to be welded based on the weld geometry data to obtain the spatial data of the welding part; The control module is used to perform hierarchical path planning on the spatial data to obtain preliminary path data, and to control the welding torch to perform preliminary welding on the workpiece to be welded according to the preliminary path data; The generation module is used to acquire secondary electronic signals during the initial welding process and generate feedback data based on the deviation between the secondary electronic signals and the initial path data. The execution module is used to adjust the welding parameters of the welding torch according to the feedback data, and control the welding torch to perform secondary welding on the workpiece to be welded until the welding is completed.

[0015] Beneficial effects: This application provides an electron beam welding path adjustment method. By acquiring and scanning the weld geometry data of the workpiece to be welded in real time, accurate spatial data is obtained, thereby fully understanding the true three-dimensional geometry of the weld before welding. Based on this spatial data, a layered path planning is performed to generate a preliminary path and conduct preliminary welding. During the welding process, highly sensitive secondary electron signals are simultaneously acquired to accurately capture the changes in beam current and material interaction characteristics caused by path deviation when the electron beam bombards the workpiece, and reliable feedback data is generated accordingly. This enables real-time and adaptive adjustment of multi-dimensional welding parameters such as welding torch position, beam current parameters, focusing state, and scanning mode. Subsequently, secondary welding is performed until completion. This method improves the electron beam's ability to center welds and the uniformity of energy deposition on complex curved surfaces, thick components, and workpieces with geometric and assembly deviations, effectively ensuring the consistency and reliability of weld formation quality, internal density, and mechanical properties. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the steps of an electron beam welding path adjustment method according to an embodiment of the present invention; Figure 2 This is a schematic block diagram of an electron beam welding path adjustment device according to an embodiment of the present invention.

[0017] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

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

[0019] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of features, integers, steps, operations, elements, modules, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and / or groups thereof. It should be understood that when an element is referred to as “connected” or “coupled” to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein may include wireless connection or wireless coupling. The term “and / or” as used herein includes all or any modules and all combinations of one or more associated listed items.

[0020] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0021] Reference Figure 1 This invention provides a method for adjusting the electron beam welding path, comprising the following steps: S1: Obtain the weld geometry data of the workpiece to be welded, and scan the workpiece to be welded according to the weld geometry data to obtain the spatial data of the welding part; In step S1, the workpiece to be welded refers to the target component that has completed the preceding manufacturing process and entered the electron beam welding process. It can be two or more metal components that need to be spliced, or it can be a cavity, shell, ring, flange structure, or complex spatial curve connector with an irregular curved surface. Weld geometry data is a set of data characterizing the geometric shape of the weld in space. This set of data is not limited to a single centerline, but includes the coordinates of the weld start point, the coordinates of the weld end point, the coordinates of multiple discrete sampling points distributed along the weld direction, the weld centerline, the boundary lines on both sides of the weld, the weld opening width, the estimated weld depth, the assembly gap, the misalignment, the local curvature, the tangent direction, the normal vector, the surface slope, and the reference datum information of the weld neighborhood. In actual implementation, obtaining weld geometry data first requires establishing a measurement datum, that is, defining the workpiece coordinate system, including three directions: X-axis, Y-axis, and Z-axis. The workpiece length direction can be defined as the X-axis, the workpiece width direction as the Y-axis, and the direction perpendicular to the clamping datum plane as the Z-axis. After obtaining the baseline, initial geometry acquisition is carried out around the weld. This can be done using laser scanning, structured light scanning, visual measurement, contact probe measurement, coordinate measuring machine (CMM), laser tracking, or multi-sensor fusion. Non-contact 3D scanning is preferred. During scanning, the workpiece design model, assembly positioning relationships, preset weld positions, or the approximate weld distribution obtained from initial measurements are used to determine the scanning area, scanning posture, scanning resolution, scanning path, and key scanning sections before targeted scanning. After scanning, data processing is performed, including noise reduction, which uses statistical filtering, median filtering, radius filtering, or surface fitting residual judgment to remove obviously abnormal scattered points. Then, point cloud registration is performed, which involves stitching data acquired from different perspectives and times together into the workpiece coordinate system. Finally, weld feature extraction is performed, identifying the weld center region, weld edges, bevel shape, surface normal vector, and local curvature changes from the complete point cloud. The bevel shape is the cross-sectional morphology of the component to be welded at the weld joint to ensure penetration and form, such as V-shaped, U-shaped, I-shaped, or composite bevels. Its geometry directly affects the electron beam focal point position and energy distribution. Through feature extraction, disordered point clouds can be transformed into structured data. For example, the weld can be represented by a series of sequentially arranged path points. Each path point contains not only X, Y, and Z coordinates, but also parameters such as the tangential direction, normal direction, local surface inclination angle, weld width, estimated weld depth, and neighboring surface height. The local surface inclination angle is the angle of inclination of the base material surface at the weld joint relative to the reference plane, and the neighboring surface height is the basis for the relative distance change between the welding torch and the workpiece surface. This yields spatial data of the welded area, including the geometric information of the weld itself and the spatial environment information surrounding the weld, which can be used to support welding torch position control, attitude control, and parameter adjustment.

[0022] S2: Perform hierarchical path planning on the spatial data to obtain preliminary path data, and control the welding torch to perform preliminary welding on the workpiece to be welded according to the preliminary path data; In step S2, layered path planning involves decomposing the welding trajectory to be executed into multiple levels, segments, and nodes according to predetermined rules based on the spatial shape, thickness characteristics, curvature changes, attitude changes, and electron beam welding process requirements of the welding area. Each level, segment, and node is then assigned corresponding motion and process parameters. Geometrically, layers are defined along the weld depth direction, weld spatial height direction, or complex curved envelope relationships; alternatively, they can be defined as process-related layers, grouped according to the energy input requirements, attitude change amplitude, path complexity, or risk level of different welding areas. During layered path planning, spatial data is layered and determined. The determination criteria may include the rate of curvature change along the weld length direction. The entire weld can be divided into several layered regions, such as a base layer, transition layer, and high-risk layer, or a stable attitude layer and an abrupt attitude change layer. A high-risk layer refers to an area where the welding torch may experience incident angle deviation, beam focus shift, unstable welding depth, or localized molten pool anomalies. After completing the hierarchical division, path fitting and trajectory generation are performed within each layer. This involves determining the continuous spatial trajectory of the welding torch or electron beam's point of action along the weld seam during time progression. This can be achieved by fitting the weld seam centerline using Bezier curves, spline curves, or piecewise polynomial curves, transforming the originally discrete spatial sampling points into a continuous trajectory equation. This allows the subsequent control system to generate motion commands for the welding torch point-by-point based on time parameters. It is worth noting that the welding torch has multiple degrees of freedom, such as translational degrees of freedom along the X, Y, and Z axes, and rotational degrees of freedom around the A, B, C, or AC axes (or a combined A and C axis). The A axis can be understood as the pitch rotation axis, used to adjust the forward and backward tilt angle of the electron beam relative to the workpiece surface; the C or AC axes typically involve circumferential rotation or combined attitude adjustment, used to change the deflection angle of the electron beam around the weld seam direction. Because the mechanical structure of the welding torch has limitations on maximum rotation angle, maximum speed, maximum acceleration, and attitude switching inertia, when the normal vector of a certain weld area changes too quickly, theoretically the welding torch can continuously adjust its angle to track the surface changes. However, if the angle change between adjacent control points is too large, it will exceed the instantaneous response capability of the motor. Therefore, it is necessary to further subdivide the segment into multiple smaller segments so that the attitude change between each segment is kept within the allowable threshold, i.e., the pre-set maximum acceptable change amount. For example, the pitch angle change of the welding torch between adjacent nodes should not exceed 5°, or the rotation angle change should not exceed 3°. The purpose is to prevent violent oscillations that could cause beam deviation, focus drift, or molten pool fluctuations.

[0023] Further, the welding parameters are initially set, and the preliminary path data is input into the welding equipment control system. The control system converts the path points, attitude angles, welding parameters, and timing logic into servo motor control commands, electron beam emission control commands, and multi-axis linkage synchronization commands, causing the welding torch to perform the first welding along the weld seam in a predetermined manner. Preliminary welding does not imply low quality or merely a trial weld; rather, it refers to the first formal welding process performed according to a pre-planned baseline path before real-time feedback correction is introduced. The term "preliminary" here is used to distinguish it from the secondary welding in step S4 after parameter adjustments based on feedback data. Preliminary welding is the forward execution stage of the closed-loop system, its purpose being not only to begin welding formation but also to generate raw process data for real-time detection and deviation analysis. During control, the welding torch is driven to move smoothly along the X, Y, and Z directions according to the path point sequence, and the A-axis, C-axis, and other rotational axes are driven as needed to complete continuous attitude adjustments, ensuring that the electron beam is always aligned with the weld seam center as much as possible and maintains a reasonable incident angle, thus forming preliminary welding.

[0024] S3: Acquire secondary electronic signals during the initial welding process, and generate feedback data based on the deviation between the secondary electronic signals and the initial path data; In step S3, during electron beam welding, when the high-energy electron beam bombards the surface of the workpiece and the weld area, the surface material of the workpiece will release surface electrons after being subjected to the electron beam, some of which manifest as secondary electron signals. Since the secondary electron signal is related to the beam bombardment position, surface morphology, local material state, weld edge characteristics, molten pool morphology, and electron beam incident conditions, this signal can reflect the true state of the current welding area. A secondary electron detection device corresponding to the welding area is arranged in the electron beam welding equipment. This detection device can be placed near the electron gun system or integrated into a signal acquisition unit suitable for vacuum chamber operation, so as to continuously receive the secondary electrons released from the welding area when the welding gun welds along the preliminary path data generated in step S2. The signal received by the detection device is not directly usable for control, but is first converted into an electrical signal, and then processed through amplification, filtering, analog-to-digital conversion, etc., to form a digital signal sequence that can be recognized by the computing module. The acquired secondary electron signals undergo time and spatial synchronization processing. Image processing or feature analysis algorithms are used to extract information such as the weld centerline position, weld pool width, welding depth-related features, welding torch projection position, and actual incident direction. These real-time extracted features are compared with theoretical features in the preliminary path data to obtain various types of deviation values. For example, the lateral offset of the weld center relative to the preset path center can be obtained to reflect whether the welding trajectory has deviated; the difference between the weld area morphology and the theoretical weld depth model can be obtained to reflect whether the welding depth is insufficient or excessive; or the angle difference between the electron beam incident trace direction and the preset normal angle can be obtained to reflect whether the welding torch attitude has deviated. Feedback data is generated based on the deviations. The feedback data should at least include the location of the deviation, the type of deviation, the magnitude of the deviation, and, if necessary, trend information.

[0025] S4: Adjust the welding parameters of the welding torch according to the feedback data, and control the welding torch to perform secondary welding on the workpiece to be welded until the welding is completed; In step S4, the feedback data is analyzed and classified. For example, when the feedback data shows that the weld imaging center deviates from the preset path center, it indicates that there is a deviation between the welding torch's trajectory or the actual weld position of the workpiece and the initial path. In this case, the welding torch's path tracking position or attitude angle should be corrected first. When the system identifies that the deviation is a local angle mismatch, the rotation angle of the welding torch around the relevant axis can be adjusted to allow the electron beam to act on the weld again with a more reasonable incident direction. When the system identifies that the welding depth is too shallow, the beam current power can be increased, the travel speed reduced, or the focal position finely adjusted to allow the electron beam to form a higher energy density in that area, thereby increasing the penetration depth. It is worth noting that secondary welding is not a complete re-welding of the entire weld from scratch. Rather, it is based on the initial welding, and for the area where the deviation has been identified or the subsequent area to be welded, compensatory welding or corrective welding is continued using adjusted welding parameters. In actual implementation, the starting point, ending point, and corresponding parameter combination for secondary welding can be determined according to the spatial position corresponding to the feedback data, and then the welding torch is driven to act on that area again along the corrected trajectory. For cases with small deviations, secondary welding can be manifested as local continuous compensation, that is, the welding torch continues to weld while detecting, correcting and welding without interrupting the overall welding cycle. For cases with large deviations, secondary welding can be manifested as pausing the execution of the original parameters in a specific path segment, calling the updated path and parameters, and re-fusion or repairing the local weld segment to eliminate the quality risks generated by the initial welding.

[0026] It should also be noted that in this embodiment, "until welding is completed" does not mean the end of the welding time. Rather, it means that the aforementioned feedback, adjustment, and re-welding process can be executed cyclically. That is, after one parameter adjustment and a second welding operation, the system can continue to collect new welding process signals and determine again whether the corrected welding state has met the preset requirements. If, after adjustment, the weld imaging features corresponding to the secondary electronic signal indicate that the weld center is re-aligned, the penetration depth reaches the standard, and the welding torch posture error returns to the allowable range, the system can maintain the current corrected parameters and continue to complete the remaining welding. However, if new local deviations still exist after the second welding, new feedback data can be generated again, and the parameter adjustment logic in step S4 can be triggered again, i.e., multiple rounds of iterative optimization are performed throughout the welding process.

[0027] Furthermore, after the feedback data enters the control module, the module performs four consecutive steps: deviation threshold judgment, correction calculation, parameter mapping, and execution output. The control module compares the feedback data with the preset process tolerance to determine if the current deviation meets the conditions for triggering correction. Secondly, when the conditions are met, a correction model is established based on the magnitude and type of the deviation, calculating specific parameter adjustments, such as the angle by which the welding torch increases around the A-axis, the distance by which the welding torch height is compensated, the percentage increase in beam power, and the numerical reduction in welding speed. This adjustment is then mapped into control commands that the welding equipment can recognize. The control commands are output to the welding torch actuator and the electron beam generator, causing the welding torch attitude and beam parameters to change in real time. Since electron beam welding is typically highly sensitive to energy density, focal position, and incident direction, the feedback control module can adjust these sensitive variables in a coordinated manner without interrupting the process objective, thus enabling the secondary welding to truly achieve a deviation correction effect.

[0028] In summary, this application acquires and scans the weld geometry data of the workpiece in real time to obtain accurate spatial data, thereby comprehensively understanding the true three-dimensional geometry of the weld before welding. This effectively overcomes the fundamental defects of traditional offline programming or preset trajectories, which rely solely on design drawings or CAD models and cannot reflect actual manufacturing tolerances, assembly errors, thermal deformation, and minor surface undulations, resulting in significant deviations between the path and the actual weld. Subsequently, based on this spatial data, layered path planning is performed to generate a preliminary path and conduct preliminary welding. During the welding process, highly sensitive secondary electron signals are simultaneously acquired to accurately capture changes in beam current and material interaction characteristics caused by path deviations when the electron beam bombards the workpiece, and reliable feedback data is generated accordingly. This enables the monitoring of welding torch position, beam current parameters, focusing state, and scanning mode. The dynamic, real-time, and adaptive adjustment of multi-dimensional welding parameters, including the welding pattern, followed by secondary welding until completion, enhances the electron beam's ability to precisely align welds and improve energy deposition uniformity for complex curved surfaces, thick components, and workpieces with geometric and assembly deviations. This significantly reduces the probability of typical welding defects caused by path deviation, such as incomplete fusion, porosity, cracks, uneven weld width, insufficient penetration, or localized overheating. It effectively ensures the consistency and reliability of weld formation quality, internal density, and mechanical properties. Furthermore, because it can continuously sense and quickly correct deviations online throughout the welding process, it significantly improves the first-time welding success rate, reduces post-weld non-destructive testing rework and scrap rates, shortens the overall production cycle, and enhances the stability and economy of mass production for electron beam welding of complex high-end components.

[0029] In one embodiment, the step of acquiring the weld geometry data of the workpiece to be welded includes: Collect the weld position and height information of the workpiece to be welded, as well as the raw data of the height from the welding torch to the weld; The raw data is preprocessed and filtered to obtain the weld geometry data.

[0030] In the above embodiments, a suitable measuring device for the welding scenario is used to collect raw information about the weld area of ​​the workpiece to be welded. The weld position and height information includes the spatial distribution of the weld in the workpiece coordinate system, the position of the weld centerline, the undulations of the base material boundaries on both sides, and the height change of the weld surface relative to the reference plane. The raw data on the height from the welding torch to the weld reflects the relative distance between the electron beam emitter and the actual welding area. Because factors such as workpiece assembly errors, surface reflection, local burrs, and environmental disturbances can cause noise in the raw sampling results, preprocessing and filtering are performed on the raw data after acquisition. This includes removing outliers, correcting sampling jumps, smoothing local fluctuations, and unifying the coordinate reference, making the spatial position and height profile of the weld more continuous and stable. After the above processing, weld geometric data that characterizes the true geometric state of the weld is output.

[0031] In one embodiment, the step of scanning the workpiece to be welded based on the weld geometry data to obtain the spatial data of the welded area includes: Based on the weld geometry data, the initial positioning position of the welding torch in the weld area of ​​the workpiece to be welded is calculated, and a scanning path sequence is generated. The scanning device is controlled to perform a three-dimensional scan of the workpiece to be welded according to the scanning path sequence, so as to obtain the original point cloud data of the welding part. The original point cloud data is subjected to denoising and registration processing to obtain the spatial data of the welding area.

[0032] In the above embodiments, weld geometry data is read, and based on the weld centerline, weld height variation, and the relative positional relationship between the welding torch and the weld, the initial positioning position of the welding torch or scanning device relative to the weld area of ​​the workpiece is calculated. Based on this, a scanning path sequence adapted to the weld orientation is generated. This scanning path sequence defines the motion trajectory of the scanning device in terms of order, spacing, and coverage when scanning the weld and its adjacent areas. According to this scanning path sequence, the scanning device is controlled to perform a three-dimensional scan of the workpiece to be welded, acquiring the original point cloud data of the welding area. This point cloud data reflects the spatial morphology, curvature variation, and actual three-dimensional contour of the weld area's surrounding surface. Noise reduction and registration processing is then performed on this data, removing stray and invalid points, and unifying the data from different scanning perspectives into the same coordinate system. This ensures the complete and continuous three-dimensional morphology of the weld area, forming spatial data of the welding area that can be used for path planning.

[0033] In one embodiment, the step of performing hierarchical path planning on the spatial data to obtain preliminary path data includes: Curve fitting is performed on the spatial data of the welded area to obtain continuous weld trajectory data; The continuous weld trajectory data is divided into layers along the depth direction according to the weld depth variation. The sub-trajectory point sequence corresponding to each layer is extracted to obtain the set of weld sub-trajectories for each layer, where each layer corresponds to a weld filling height range. For each layer of weld seam sub-trajectory set, the rate of change of welding gun posture between adjacent points is calculated sequentially. The trajectory is then segmented according to a preset angle change threshold to obtain segmented trajectory data. Welding gun constraints are sequentially superimposed on each segment of the segmented trajectory data, and initial welding parameters are set for each segment to obtain preliminary path data.

[0034] In the above embodiments, the spatial data of the welding area is subjected to curve fitting processing. That is, based on the weld contour points, centerline points, and surface normal information extracted from the point cloud, continuous weld trajectory data is constructed, transforming the originally discrete set of spatial points into a trajectory curve whose position and direction can be continuously determined. The continuous weld trajectory is divided into multiple sub-trajectory sets corresponding to different filling height intervals according to the weld depth variation along the depth direction. This allows the welding process to adapt to the energy input requirements at different depth positions and facilitates layered control of penetration depth and weld formation. Furthermore, within each layer of weld sub-trajectory set, the rate of change of welding torch attitude between adjacent points is calculated point by point, and the trajectory is segmented according to a preset angle change threshold, thereby obtaining segmented trajectory data. This breaks down the originally continuous but potentially complex trajectory with large attitude changes into multiple smaller segments with relatively gentle attitude changes, preventing the welding torch from undergoing violent rotation or unstable deflection during execution. Welding gun constraints, such as reachable attitude range, kinematic restrictions, and attitude switching continuity requirements, are superimposed on each segment in sequence. Initial welding parameters, such as beam intensity, welding speed, and focal point position, are set for each segment to obtain preliminary path data that can be directly used to control the welding gun.

[0035] In one embodiment, the step of controlling the welding torch to perform preliminary welding on the workpiece according to the preliminary path data includes: Welding control commands are generated based on the preliminary path data and sent to the welding torch. The welding torch is then driven to perform initial attitude alignment and height calibration based on the welding control commands. According to the welding control command, the welding torch is controlled to move along the preliminary path and to carry out electron beam bombardment, and preliminary welding process data is collected.

[0036] In the above embodiments, welding control commands are generated based on preliminary path data. These commands include the coordinate trajectory of the welding torch along the weld seam and the attitude angle, welding speed, beam parameters, and height control information corresponding to each path segment. These commands are then sent to the welding torch control system. Upon receiving the control commands, the welding torch performs initial attitude alignment and height calibration according to the command content. Specifically, the welding torch is first adjusted to a suitable spatial orientation for the current weld seam segment, and the relative height between the welding torch and the weld seam surface is corrected to a predetermined range to ensure that the electron beam focus accurately falls on the target welding area. After completing these preparatory actions, the welding torch continues to move along the preliminary path according to the welding control commands, simultaneously bombarding the workpiece with the electron beam. This causes the workpiece to form a preliminary weld pool and weld seam on the preset path. Simultaneously, preliminary welding process data is collected, including the welding torch's real-time position, attitude changes, beam state, and relevant detection signals generated during the welding process.

[0037] In one embodiment, the step of acquiring secondary electronic signals during the initial welding process includes: The secondary electronic signals in the preliminary welding process data are acquired to obtain the original secondary electronic signal data. The original secondary electronic signal data is amplified and filtered to obtain a denoised secondary electronic signal. The denoised secondary electronic signal is subjected to feature extraction processing to obtain characteristic parameters such as weld pool width, weld depth, welding torch projection height, and actual welding angle deviation.

[0038] In the above embodiments, during electron beam welding, a secondary electron detection unit positioned within the vacuum welding environment acquires secondary electron signals from the preliminary welding process data in real time, forming raw secondary electron signal data. This data is then further amplified and filtered. Signal amplification enhances the identifiability of weak secondary electron responses, while filtering suppresses stray pulses and random noise to obtain a denoised secondary electron signal. After obtaining a relatively stable signal, feature extraction is performed. This involves analyzing signal intensity changes, distribution contours, and corresponding image grayscale features to extract characteristic parameters such as weld pool width, weld depth, welding torch projection height, and actual welding angle deviation.

[0039] In one embodiment, the step of generating feedback data based on the deviation between the secondary electronic signal and the preliminary path data includes: The intensity and distribution characteristics of the secondary electronic signal are extracted to obtain weld pool data; The weld pool data is compared with the preset theoretical feature value of the corresponding position in the preliminary path data to obtain the position deviation value and feature deviation value. Feedback data containing the deviation amount, spatial location information, and corresponding parameter adjustment direction is generated based on the position deviation value and characteristic deviation value.

[0040] In the above embodiments, the intensity and distribution features of the secondary electronic signal, after denoising and feature extraction, are further extracted to obtain weld pool data. This weld pool data reflects the weld pool boundary, energy distribution center, weld pool width variation, and local forming state within the current welding area; in other words, it essentially represents the actual welding image features during the welding process. The weld pool data is compared with the theoretical feature values ​​preset at corresponding positions in the preliminary path data. The corresponding position refers to matching the current welding torch path point, welding segment, or current layer as a reference. By comparing the difference between the actual weld state and the theoretical target state, positional deviation and feature deviation values ​​are obtained. The former mainly reflects whether the welding trajectory deviates from the predetermined position, while the latter mainly reflects whether the weld pool shape, welding depth, and angle state meet preset requirements. Based on this, feedback data is generated according to the aforementioned positional deviation and feature deviation values, ensuring that the feedback data includes at least the deviation amount, spatial position information, and the corresponding parameter adjustment direction.

[0041] In one embodiment, the step of adjusting the welding parameters of the welding torch based on the feedback data and controlling the welding torch to perform secondary welding on the workpiece until welding is completed includes: The feedback data is processed by deviation classification and threshold judgment to obtain the adjustment requirement identifier of the current welding segment and the corresponding deviation type set; The parameter correction amount is calculated and processed by the set of deviation types and the preliminary path data of the current segment to obtain the welding gun attitude correction amount, beam intensity adjustment amount, height compensation amount and scanning deflection amount; The initial path data and initial welding parameters of the current segment are locally updated based on the welding torch attitude correction amount, beam intensity adjustment amount, height compensation amount, and scanning deflection amount to obtain the updated welding parameters. Based on the updated welding parameters, a secondary welding control command is generated to control the welding torch to continue performing electron beam welding along the updated path until all layered path segments are welded.

[0042] In the above embodiments, the feedback data undergoes deviation classification and threshold judgment processing. Specifically, based on the magnitude, direction, and nature of the deviation, it is determined whether the current welding segment requires adjustment, generating an adjustment requirement identifier and a corresponding set of deviation types. This set of deviation types is then combined with the preliminary path data of the current segment to calculate parameter corrections, resulting in welding torch attitude corrections, beam intensity adjustments, height compensation, and scanning deflection. After obtaining these corrections, the preliminary path data and initial welding parameters of the current segment are locally updated, specifically correcting the segment's path in terms of spatial position, attitude angle, beam input, and height control, thus generating updated welding parameters. Based on these updated welding parameters, a secondary welding control command is generated, controlling the welding torch to continue electron beam welding along the updated path until all layered path segments are welded.

[0043] Reference Figure 2 This application also discloses an electron beam welding path adjustment device, comprising: The acquisition module 100 is used to acquire the weld geometry data of the workpiece to be welded, and scan the workpiece to be welded according to the weld geometry data to obtain the spatial data of the welding part; The control module 200 is used to perform hierarchical path planning on the spatial data to obtain preliminary path data, and to control the welding torch to perform preliminary welding on the workpiece to be welded according to the preliminary path data; The generation module 300 is used to acquire secondary electronic signals during the initial welding process and generate feedback data based on the deviation between the secondary electronic signals and the initial path data. The execution module 400 is used to adjust the welding parameters of the welding torch according to the feedback data, and control the welding torch to perform secondary welding on the workpiece to be welded until the welding is completed.

[0044] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for adjusting the electron beam welding path, characterized in that, include: Obtain the weld geometry data of the workpiece to be welded, and scan the workpiece to be welded based on the weld geometry data to obtain the spatial data of the welding area; The spatial data is hierarchically planned to obtain preliminary path data, and the welding torch is controlled to perform preliminary welding on the workpiece to be welded based on the preliminary path data; Secondary electronic signals are acquired during the initial welding process, and feedback data is generated based on the deviation between the secondary electronic signals and the initial path data. The welding parameters of the welding torch are adjusted based on the feedback data, and the welding torch is controlled to perform secondary welding on the workpiece to be welded until the welding is completed.

2. The electron beam welding path adjustment method according to claim 1, characterized in that, The step of obtaining the weld geometry data of the workpiece to be welded includes: Collect the weld position and height information of the workpiece to be welded, as well as the raw data of the height from the welding torch to the weld; The raw data is preprocessed and filtered to obtain the weld geometry data.

3. The electron beam welding path adjustment method according to claim 1, characterized in that, The step of scanning the workpiece to be welded based on the weld geometry data to obtain the spatial data of the welding area includes: Based on the weld geometry data, the initial positioning position of the welding torch in the weld area of ​​the workpiece to be welded is calculated, and a scanning path sequence is generated. The scanning device is controlled to perform a three-dimensional scan of the workpiece to be welded according to the scanning path sequence, so as to obtain the original point cloud data of the welding part. The original point cloud data is subjected to denoising and registration processing to obtain the spatial data of the welding area.

4. The electron beam welding path adjustment method according to claim 1, characterized in that, The step of performing hierarchical path planning on the spatial data to obtain preliminary path data includes: Curve fitting is performed on the spatial data of the welded area to obtain continuous weld trajectory data; The continuous weld trajectory data is divided into layers along the depth direction according to the weld depth variation. The sub-trajectory point sequence corresponding to each layer is extracted to obtain the set of weld sub-trajectories for each layer, where each layer corresponds to a weld filling height range. For each layer of weld seam sub-trajectory set, the rate of change of welding gun posture between adjacent points is calculated sequentially. The trajectory is then segmented according to a preset angle change threshold to obtain segmented trajectory data. Welding gun constraints are sequentially superimposed on each segment of the segmented trajectory data, and initial welding parameters are set for each segment to obtain preliminary path data.

5. The electron beam welding path adjustment method according to claim 1, characterized in that, The step of controlling the welding torch to perform preliminary welding on the workpiece according to the preliminary path data includes: Welding control commands are generated based on the preliminary path data and sent to the welding torch. The welding torch is then driven to perform initial attitude alignment and height calibration based on the welding control commands. According to the welding control command, the welding torch is controlled to move along the preliminary path and to carry out electron beam bombardment, and preliminary welding process data is collected.

6. The electron beam welding path adjustment method according to claim 5, characterized in that, The step of acquiring secondary electronic signals during the initial welding process includes: The secondary electronic signals in the preliminary welding process data are acquired to obtain the original secondary electronic signal data. The original secondary electronic signal data is amplified and filtered to obtain a denoised secondary electronic signal. The denoised secondary electronic signal is subjected to feature extraction processing to obtain characteristic parameters such as weld pool width, weld depth, welding torch projection height, and actual welding angle deviation.

7. The electron beam welding path adjustment method according to claim 1, characterized in that, The step of generating feedback data based on the deviation between the secondary electronic signal and the preliminary path data includes: The intensity and distribution characteristics of the secondary electronic signal are extracted to obtain weld pool data; The weld pool data is compared with the preset theoretical feature value of the corresponding position in the preliminary path data to obtain the position deviation value and feature deviation value. Feedback data containing the deviation amount, spatial location information, and corresponding parameter adjustment direction is generated based on the position deviation value and characteristic deviation value.

8. The electron beam welding path adjustment method according to claim 1, characterized in that, The step of adjusting the welding parameters of the welding torch based on the feedback data and controlling the welding torch to perform secondary welding on the workpiece until the welding is completed includes: The feedback data is processed by deviation classification and threshold judgment to obtain the adjustment requirement identifier of the current welding segment and the corresponding deviation type set; The parameter correction amount is calculated and processed by the set of deviation types and the preliminary path data of the current segment to obtain the welding gun attitude correction amount, beam intensity adjustment amount, height compensation amount and scanning deflection amount; The initial path data and initial welding parameters of the current segment are locally updated based on the welding torch attitude correction amount, beam intensity adjustment amount, height compensation amount, and scanning deflection amount to obtain the updated welding parameters. Based on the updated welding parameters, a secondary welding control command is generated to control the welding torch to continue performing electron beam welding along the updated path until all layered path segments are welded.

9. An electron beam welding path adjustment device for implementing the electron beam welding path adjustment method of claim 1, characterized in that, include: The acquisition module is used to acquire the weld geometry data of the workpiece to be welded, and scan the workpiece to be welded based on the weld geometry data to obtain the spatial data of the welding part; The control module is used to perform hierarchical path planning on the spatial data to obtain preliminary path data, and to control the welding torch to perform preliminary welding on the workpiece to be welded according to the preliminary path data; The generation module is used to acquire secondary electronic signals during the initial welding process and generate feedback data based on the deviation between the secondary electronic signals and the initial path data. The execution module is used to adjust the welding parameters of the welding torch according to the feedback data, and control the welding torch to perform secondary welding on the workpiece to be welded until the welding is completed.

Images