Sieve plate bar welding teaching method, device and system and storage medium

Abstract

The invention relates to the technical field of welding, and discloses a sieve plate bar welding teaching method, device and system and a storage medium, the method comprises the following steps: in response to an obtained welding area image, identifying target bars in a welding area, and determining position information of each target bar; according to the position information of each target bar, determining a weld line of each target bar in combination with the diameter of the standard bar and the weld parameters; and a welding teaching path is generated according to the welding line of each target bar and the motion parameters of the mechanical arm. Through image recognition and automatic path generation, efficient and accurate welding demonstration can be realized.

Description

Technical Field

[0001] This application relates to the field of welding technology, and in particular to a welding teaching method, apparatus, system and storage medium for sieve plates and bars. Background Technology

[0002] Traditional sieve plate welding processes, especially for welding bar structures, primarily rely on manual teaching for welding path planning and execution. However, this traditional process suffers from the following pressing technical problems: First, manual teaching presents a significant efficiency bottleneck. Because it requires setting weld positions point-by-point or planning welding paths in segments, especially when using circular arc welding, programming efficiency is low and the operator's workload is high. Second, this process struggles to guarantee consistent welding quality. Positioning errors are prone to occur during manual teaching, leading to weld point misalignment and discontinuous welding trajectories, thus affecting product welding quality and consistency. Summary of the Invention In view of this, embodiments of this application provide a method, apparatus, system, and storage medium for teaching the welding of sieve plates and bars.

[0003] In a first aspect, embodiments of this application provide a teaching method for welding sieve plates and bars, including: In response to the acquired welding area image, target bars in the welding area are identified, and the position information of each target bar is determined; Based on the position information of each target bar, the weld line of each target bar is determined in combination with the standard bar diameter and weld parameters; Welding teaching paths are generated based on the weld seam lines of each target bar and the motion parameters of the robotic arm.

[0004] In an optional implementation, the step of identifying target bars in the welding area and determining the position information of each target bar in response to the acquired welding area image includes: Candidate regions are obtained based on the weld area image; Based on the diameter of the bar and the preset diameter deviation, the candidate region is pre-identified to obtain the candidate bars in the candidate region; Based on the point cloud data of all the candidate bars, geometric modeling and consistency correction are performed on all the candidate bars to identify the target bars that meet the set geometric constraints, and the position information of each target bar is output.

[0005] In an optional implementation, the step of performing geometric modeling and consistency correction on all candidate bars based on the point cloud data of all the candidate bars, and identifying the target bar that satisfies the set geometric constraints, includes: Project the point cloud data corresponding to each candidate bar onto the spatial plane where the sieve plate is located to obtain the three-dimensional point set of each candidate bar on the spatial plane. The three-dimensional point set is modeled based on the cylinder fitting algorithm to obtain the circular region where each candidate bar intersects with the spatial plane and the coordinates of the center of the circle; Perform a straight line fit on the center coordinates of all the candidate bars, and calculate the offset of the center of each candidate bar relative to the fitted straight line; The target bar is determined based on the offset.

[0006] In an optional implementation, obtaining candidate regions based on the weld area image includes: Point cloud analysis and preliminary identification are performed on the welding area image to determine at least one initial candidate region; The initial candidate regions are visually marked on the graphical user interface for user confirmation and adjustment; In response to user interaction adjustment commands, the boundaries or positions of the initial candidate region are adjusted to generate the candidate region.

[0007] In an optional implementation, the position information includes the center coordinates of the corresponding target bar and the arrangement direction of all the target bars; The step of determining the weld line of each target bar based on its position information, combined with the standard bar diameter and weld parameters, includes: Based on the center coordinates of each target bar and the diameter of the standard bar, the welding start point and end point of each target bar are determined; Based on the welding start and end points of each target bar and the preset weld parameters, the weld line of each target bar is determined; wherein, the weld parameters include a first distance from the bar, a second distance from the sieve plate, and a welding angle.

[0008] In an optional implementation, the motion parameters include a safety height and a backtracking distance; The step of generating a welding teaching path based on the weld seam lines of each target bar and the motion parameters of the robotic arm includes: The welding teaching path is determined based on the safety height, the weld line of each target bar, and the retreat distance.

[0009] In an optional implementation, the motion parameters further include the moving speed corresponding to the safe height and the retreating speed corresponding to the retreating distance; After generating the welding teaching path based on the weld seam lines of each target bar and the motion parameters of the robotic arm, the method further includes: A welding demonstration animation is generated based on the welding teaching path and the welding parameters of the robotic arm; wherein, the welding parameters include welding speed; If the welding demonstration animation confirms that there are no abnormalities in the welding, then in response to the welding program generation instruction, a welding program is generated based on the welding teaching path, the motion parameters, and the welding parameters, and uploaded to the robotic arm.

[0010] Secondly, embodiments of this application provide a teaching device for welding sieve plates and bars, comprising: The identification module is used to identify target bars in the welding area in response to the acquired welding area image, and to determine the position information of each target bar; The determination module is used to determine the weld line of each target bar based on the position information of each target bar, combined with the standard bar diameter and weld parameters; The generation module is used to generate a welding teaching path based on the weld seam lines of each target bar and the motion parameters of the robotic arm.

[0011] Thirdly, embodiments of this application provide a welding teaching system for sieve plates and bars, comprising: a welding control platform and an image acquisition device; the welding control platform includes a processor and a graphical user interface; The image acquisition device is used to acquire images of the welding area and transmit them to the welding control platform; The processor is used to execute the sieve plate and bar welding teaching method described in the foregoing embodiments; The graphical user interface is used to display the execution progress and receive user input operation commands when performing the sieve plate and bar welding teaching method described in the foregoing embodiments.

[0012] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed on a processor, implements the sieve plate and bar welding teaching method described in the foregoing embodiments.

[0013] The embodiments of this application have the following beneficial effects: This application identifies target bars in the welding area by acquiring welding area images, and then determines the weld line of each target bar based on the position information of each target bar, combined with the standard bar diameter and weld parameters; finally, it generates a welding teaching path based on the weld line of each target bar and the motion parameters of the robotic arm. It has a high degree of intelligence and can solve the problems of low efficiency, large error and complex operation of traditional manual welding teaching. Attached Figure Description To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 A schematic diagram of a sieve plate and bar welding teaching system according to an embodiment of this application is shown; Figure 2 A schematic diagram of a first interface of the graphical user interface according to an embodiment of this application is shown; Figure 3 A schematic diagram of a second interface of the graphical user interface according to an embodiment of this application is shown; Figure 4 A schematic diagram of a third interface of the graphical user interface according to an embodiment of this application is shown; Figure 5 A schematic diagram of a fourth interface of the graphical user interface according to an embodiment of this application is shown; Figure 6 A schematic diagram of the fifth interface of the graphical user interface according to an embodiment of this application is shown; Figure 7 This paper shows a first flowchart of the teaching method for welding sieve plates and bars according to an embodiment of this application; Figure 8 This paper illustrates a second flowchart of the sieve plate and bar welding teaching method according to an embodiment of this application. Figure 9 A third flowchart illustrating the sieve plate and bar welding teaching method according to an embodiment of this application is shown; Figure 10 A schematic diagram of the sixth interface of the graphical user interface according to an embodiment of this application is shown; Figure 11 A fourth flowchart of the sieve plate and bar welding teaching method according to an embodiment of this application is shown; Figure 12 A schematic diagram of the seventh interface of the graphical user interface according to an embodiment of this application is shown; Figure 13 A fifth flowchart illustrating the sieve plate and bar welding teaching method according to an embodiment of this application is shown. Figure 14 A schematic diagram of the eighth interface of the graphical user interface according to an embodiment of this application is shown; Figure 15 A schematic diagram of the ninth interface of the graphical user interface according to an embodiment of this application is shown; Figure 16 A schematic diagram of the tenth interface of the graphical user interface according to an embodiment of this application is shown; Figure 17 A schematic diagram of the eleventh interface of the graphical user interface according to an embodiment of this application is shown; Figure 18 A first structural schematic diagram of the sieve plate and bar welding teaching system according to an embodiment of this application is shown. Detailed Implementation

[0015] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0016] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0017] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0018] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0019] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0020] The following section will first describe the welding teaching system for sieve plates and bars using some specific embodiments.

[0021] Figure 1A schematic diagram of a screen plate / bar welding teaching system according to an embodiment of this application is shown. Exemplarily, the screen plate / bar welding teaching system includes: a welding control platform 100, an image acquisition device 200, and a robotic arm 300; the welding control platform 100 includes a processor 110 and a graphical user interface 120.

[0022] like Figure 2 As shown, the graphical user interface 120 includes a menu bar, a display area, and an operation area. The menu bar includes operation buttons such as "New Shot," "Robot Arm Settings," and "Connect Robot Arm." In this embodiment, the robot arm 300 can be equipped with a welding torch as an end effector to achieve welding operations in any spatial posture. Furthermore, the robot arm 300 has an API interface to support communication with the welding control platform 100. Specifically, the robot arm 300 can connect to the welding control platform 100 via network communication protocols (such as TCP / IP, EtherCAT, Modbus TCP, etc.) to form a one-to-one control relationship. The welding control platform 100 can set operations through the robot arm, such as... Figure 3 As shown, it can set the IP of the robotic arm 300, the tool coordinate system used by the robotic arm 300 for vision, and the movement speed of the robotic arm 300 on the shooting interface.

[0023] The display area is used to display images acquired by the image acquisition device 200, as well as some data displayed during the operation. The operation area is used by the user to input operation commands when performing the sieve plate and bar welding teaching method, so as to realize human-machine interaction.

[0024] As the core hardware device for welding execution, the stable connection and correct initialization of the robotic arm 300 are prerequisites for subsequent operations such as imaging, recognition, and path planning. Before using the intelligent welding system for sieve plates, users need to complete the startup and connection settings of the robotic arm 300 to ensure that the control system can accurately obtain the status of the robotic arm 300 and send control commands to it.

[0025] Before connecting to the robotic arm 300, first ensure that the robotic arm 300 is powered on and that the network connection is normal. Figure 4 As shown, users can click the "Connect Robotic Arm" button on the graphical user interface 120 of the control platform to trigger the following series of connection processes: 1. Connection request initiation: The platform sends a connection request to the preset IP address, attempting to establish a communication link with the specified model of robotic arm 300; 2. Authentication and handshake: The platform and robotic arm 300 perform a protocol handshake to verify the communication protocol version, device ID, and authorization information; 3. Status detection and feedback: If the connection is successful, then... Figure 5As shown, the platform will read the current status information of the robotic arm 300 (such as coordinate system, joint angles, speed limits, etc.); the platform interface will pop up a prompt message "robotic arm connection successful" and display a "connected" icon in the status bar; if the connection fails, the platform will prompt the corresponding problem according to the error code, such as "incorrect IP address", "robotic arm not responding", "API control not enabled", etc., so that users can perform corresponding maintenance; 4. Initial position verification: the platform automatically reads the current position of the robotic arm 300 and determines whether it is at the safe starting point. If it is not at the preset position, it will prompt the user to reset or manually adjust it.

[0026] Image acquisition device 200 is used to acquire images of the welding area and transmit them to welding control platform 100. Image acquisition device 200 can be a camera, mounted on robotic arm 300, capable of flexibly capturing images as the robotic arm 300 moves to different positions; the sieve plate is fixed to the worktable for stable image capture. Before capturing images, the camera position can be set by clicking the settings button on the interface. Figure 4 As shown, when taking a photo, you can click "New Shot" in the toolbar to open the shooting interface (the shooting interface is shown below). Figure 6 As shown in the image, the captured area will be displayed on the right side of the interface. If the camera position is not suitable, it can be readjusted by moving the robotic arm 300. The interface will also display shooting parameters, which users can adjust themselves (e.g., brightness, exposure time, blue light intensity) to ensure the captured image meets requirements. After setting the camera position and shooting parameters, clicking the "Shoot" button triggers the shooting command, and the camera begins acquiring the image. The left side of the interface will then display the shooting results (point cloud and grayscale image) in real time. If the image displayed on the left shows no abnormalities (e.g., blurriness, occlusion), the shooting is complete. This recognition process can be automatic based on preset rules by the platform or by user judgment. If automatic recognition is used, the platform will automatically return to the main interface after receiving a no-abnormality command. If manual recognition is used, clicking the "Complete" button on the interface after receiving a no-abnormality command triggers the return to the main interface.

[0027] The acquired image information can include point cloud data and grayscale images. Point cloud data is used to display the three-dimensional spatial structure of the workpiece, including the three-dimensional shape of the sieve plate and bars, and can be used for subsequent geometric analysis and feature extraction. Grayscale images provide clear two-dimensional images, making it easier for operators to intuitively observe the position and distribution of the bars. Grayscale images are also used to assist in the subsequent bar recognition process.

[0028] Processor 110 is used to execute the following teaching method for welding sieve plates and bars.

[0029] The following examples illustrate the welding method for the sieve plate bars.

[0030] Figure 7 A schematic flowchart of a sieve plate bar welding teaching method according to an embodiment of this application is shown. Exemplarily, the sieve plate bar welding teaching method includes the following steps: Step S100: In response to the acquired welding area image, identify the target bars in the welding area and determine the position information of each target bar.

[0031] As an example, after acquiring images of the welding area through an image acquisition device, the acquired images include 3D point cloud data and grayscale images of the sieve plate and its bar structure. After processing by a point cloud filtering and visualization module, the images are displayed in a graphical user interface for subsequent recognition processing. The platform performs image recognition processes such as point cloud analysis, candidate region extraction, and geometric feature matching, combined with user interaction to confirm or correct the recognition results, thereby accurately identifying the target bars in the welding area to prepare for subsequent welding teaching paths.

[0032] In some implementations, steps such as Figure 8 As shown, step S100 includes steps S110-S130: Step S110: Obtain candidate regions based on the welding area image.

[0033] As an example, after acquiring images of the welding area, the system enters the first stage of the bar recognition process: candidate region acquisition. This step aims to extract regions that may contain the target bar from the original welding area image, providing a data foundation for subsequent target recognition and location. This step mainly improves recognition efficiency and accuracy by combining point cloud analysis, preliminary recognition, and user interaction mechanisms, while enhancing the system's applicability and flexibility, and providing more accurate data input for subsequent bar recognition and weld calculation.

[0034] In some embodiments, such as Figure 9 As shown, step S110 includes sub-steps S111-S113: Step S111: Perform point cloud analysis and preliminary identification on the welding area image to determine at least one initial candidate region.

[0035] In this step, the platform first preprocesses and extracts features from the received welding area image, which includes, but is not limited to, 3D point cloud data and the corresponding grayscale image. Point cloud analysis primarily utilizes point cloud filtering algorithms (such as pass-through filters) to denoise and segment the original point cloud data, removing background interference. Preliminary identification can be based on image feature recognition technology, detecting regions with circular or columnar structural features in the point cloud data as potential target bar regions. After identifying potential target bar regions, these identified regions are marked as initial candidate regions, and their spatial location, size range, and other parameters are saved. It is understood that this embodiment can simultaneously identify multiple initial candidate regions to cover situations where multiple bars may exist within the welding area, ensuring the comprehensiveness of the identification process.

[0036] Step S112: Visually mark the initial candidate region on the graphical user interface for user confirmation and adjustment.

[0037] Step S113: In response to the user's interactive adjustment command, adjust the boundary or position of the initial candidate region to generate a candidate region.

[0038] To further improve the accuracy of the recognition results, the system visualizes all initial candidate regions on a graphical user interface (GUI). Specifically, taking the recognition of an initial candidate region as an example, such as... Figure 10 As shown, the initial candidate region is marked on the image interface as a highlighted box (such as a green rectangle or outline). This highlighted box is a user-adjustable recognition window, usually a rectangle or a custom shape, used to define the area processed by the subsequent recognition algorithm. If the user believes that the highlighted box does not cover the entire area or that the coverage area is too large, they can move the highlighted box to cover the position of the bar by dragging or stretching it with the mouse, or adjust the position and size of the highlighted box according to the recognition parameters displayed on the user interface.

[0039] This embodiment improves recognition accuracy by defining candidate regions. Since non-target structures (such as fixtures, workbench edges, and other parts) may exist in the shooting scene, direct recognition without restrictions can easily lead to misidentification. Manually setting the recognition region effectively eliminates these interferences, allowing the recognition to focus on the true target (the bars on the sieve plate). Furthermore, it improves recognition efficiency. Without defining the recognition region, the system needs to scan and analyze the entire image, which is time-consuming. With candidate regions, the platform only needs to process local data, significantly reducing computation and speeding up recognition. This approach also enhances the system's flexibility and adaptability. Since different batches or models of sieve plates may have different structures and bar positions, manual adjustment of the recognition region by the user gives the system a certain degree of versatility, adapting to welding tasks under different working conditions. Moreover, it provides accurate input for subsequent automated processes. Image data after region definition is purer and clearer, thus providing a high-quality data foundation for subsequent pre-recognition (judging candidate bars), formal recognition (determining the bar center), and weld calculation.

[0040] Step S120: Based on the bar diameter and preset diameter deviation, pre-identify the candidate region to obtain the candidate bars in the candidate region.

[0041] After the candidate regions are set, the system enters the pre-identification process for bar recognition. This step aims to perform feature analysis and preliminary screening of the image data within the selected candidate regions based on the bar parameter information input by the user, quickly determine which bars are likely to be target bars, and mark them as candidate bars, thus providing a foundation for more accurate formal recognition in the future.

[0042] Understandable, such as Figure 10 As shown, before pre-identification, users can input bar recognition parameters through the user display interface. The standard bar diameter is input or selected by the operator in the software interface, such as common specifications like 10mm, 12mm, and 14mm; a preset diameter deviation range is also provided. This is the allowable recognition error range, typically set to ±20% of the standard diameter to handle potential image distortion or dimensional errors under actual working conditions. During pre-identification, the point cloud data within the candidate region is first analyzed to extract structural point sets with circular or near-circular features. Specifically, the RANSAC algorithm can be used to perform circle fitting on the point cloud, detecting multiple potential circular regions. The diameter of each circular region is compared with the standard bar diameter; if the value falls within the set deviation range, it is determined to be a possible target bar. Furthermore, for each identified circular structure, its matching degree with the standard bar is further calculated. The matching degree is defined as: Where: D is the standard rod diameter (i.e., the rod diameter input by the user); D1 is the diameter of the identified circular structure. This matching degree can be used to measure the consistency between the currently identified object and the expected rod; the closer the value is to 1, the better the match.

[0043] After the above processing, structures that meet the diameter range and matching degree standards can be identified as candidate bars, and their position information can be recorded, such as... Figure 10 As shown, the location information may include: center coordinates (x, y, z), diameter estimate, matching score, etc. This information will serve as the basis for the next stage of formal identification.

[0044] To enhance the platform's interactivity and reliability, the platform will highlight all candidate bars in the graphical user interface, such as... Figure 10 The red area shown in the image allows users to view the recognition results through the interface. If a part that the user believes does not belong to the bar is abnormally recognized, the user can click the button on the grayscale image to trigger the cancellation command and cancel the bar. If there are no problems, click "Recognize" to enter the next formal recognition process.

[0045] In this step, candidate regions are pre-identified based on the bar diameter and a preset diameter deviation. This pre-identification process, identifying candidate bars within these regions, is a crucial intermediate step in the entire bar identification process. By introducing standard bar parameters, circular feature extraction, and matching degree evaluation techniques, the platform can quickly filter potential candidate bar regions from complex welding area images, significantly reducing the computational burden of subsequent formal identification and improving identification efficiency and accuracy. Simultaneously, the combination of visual feedback and user interaction mechanisms through a graphical user interface allows for manual intervention while maintaining automatic identification, significantly enhancing overall flexibility and applicability, especially suitable for intelligent welding scenarios with multiple models and operating conditions.

[0046] Step S130: Based on the point cloud data of all candidate bars, perform geometric modeling and consistency correction on all candidate bars, identify the target bars that meet the set geometric constraints, and output the position information of each target bar.

[0047] As an example, after completing the initial screening of candidate regions that may contain bar structures (i.e., pre-identification processing), the second stage of the target bar identification process, namely formal identification, begins. This step aims to further confirm which candidate bars conform to the geometric characteristics and arrangement patterns of the target bars in the sieve plate welding task by performing in-depth geometric analysis and model correction on the point cloud data of all candidate bars, thereby ultimately identifying the real target bars and accurately extracting their position information.

[0048] In some implementations, such as Figure 11As shown, based on the point cloud data of all candidate bars, geometric modeling and consistency correction are performed on all candidate bars to identify the target bars that meet the set geometric constraints, including steps S131-S133: Step S131: Project the point cloud data corresponding to each candidate bar onto the spatial plane where the sieve plate is located to obtain the three-dimensional point set of each candidate bar on the spatial plane.

[0049] Step S132: Model the three-dimensional point set based on the cylinder fitting algorithm to obtain the circular area where each candidate bar intersects with the sieve plate plane and the coordinates of the center of the circle.

[0050] Step S133: Perform a straight line fitting on the center coordinates of all candidate bars and calculate the offset of the center of each candidate bar relative to the fitted straight line.

[0051] As an example, to facilitate 3D geometric modeling, the 3D point cloud data of each candidate bar is first projected onto the welding plane. This process is implemented using the ProjectInliers filter from the PCL library, which projects the inliers in the point cloud onto a fitted plane to form a 3D point set. For instance, assuming the bar is located on the surface of the sieve plate, the platform uses the RANSAC algorithm to fit the plane where the sieve plate is located from the overall point cloud, and then uses the ProjectInliers filter to project the bar point cloud onto this plane to obtain the 3D cylindrical profile of the candidate bar.

[0052] After obtaining the three-dimensional point set, the system uses the RANSAC fitting algorithm to model it and extract the information of each candidate bar, including but not limited to the center coordinates (x, y, z), radius estimate (r), axis, etc. of the circular area where the candidate bar intersects with the sieve plate plane. This process ensures the accurate positioning of the bar center position, which is the key basis for subsequent weld path planning.

[0053] Furthermore, in this embodiment, considering that the bars on the sieve plate are usually arranged in a straight line at regular intervals, it is necessary to perform a straight line fitting on the center of all candidate bars to construct a reference straight line. Then, the offset distance of the center of each candidate bar relative to this reference straight line is calculated. If the offset of a candidate bar exceeds a preset threshold (e.g., ±2mm), it is considered to not meet the arrangement consistency requirement and is discarded. This step can effectively eliminate the influence of misidentified non-bar structures (such as local reflections, foreign object interference, etc.) on the generation of the welding path.

[0054] Furthermore, in this embodiment, it is also necessary to further compare the difference between the actual identification diameter of each candidate bar and the standard bar diameter input by the user. If the deviation exceeds the allowable range (e.g., ±20%), it is also judged as an abnormal item and excluded.

[0055] In addition, this embodiment can also verify the rationality of the number and distribution of bars. The system determines whether the number of remaining candidate bars is reasonable (e.g., it should not be less than 2), and whether the spacing between bars meets the screen plate design specifications. If an abnormal distribution is found (e.g., multiple bars are concentrated in one place), the user is prompted to review or retake the photo.

[0056] After the above process, the system will output a set of target bars that conform to the structural rules of the sieve plate. This will be displayed in the graphical user interface, such as... Figure 12 As shown, the displayed content includes, but is not limited to, the diameter of the target bar, the coordinates of the center, the offset, etc., and these target bars can also be highlighted in the interface.

[0057] This step incorporates multiple geometric analysis and model correction techniques, including point cloud projection, circle fitting, line fitting, offset verification, and diameter consistency judgment, to accurately identify the true target bars that conform to the sieve plate structure from numerous candidate bars and assign them precise spatial positioning information. This process not only improves the accuracy and robustness of identification but also provides high-quality data support for subsequent weld calculation and path generation.

[0058] Step S200: Determine the weld line of each target bar based on the position information of each target bar, combined with the standard bar diameter and weld parameters.

[0059] The positional information includes the center position of the corresponding target bar and the arrangement direction of all target bars. The center position, or center coordinates, represents the point of the bar's central axis in three-dimensional space; the arrangement direction vector represents the axial direction of the bar, usually represented by the direction vector of a reference straight line obtained by fitting multiple bar centers.

[0060] Exemplary, such as Figure 13 As shown, step S200 includes steps S210-S220: Step S210: Based on the center position of each target bar and the diameter of the standard bar, determine the welding start point and end point of each target bar; Step S220: Based on the welding start point and end point of each target bar and the preset weld parameters, determine the weld line of each target bar.

[0061] The weld parameters include the first distance from the bar, the second distance from the sieve plate, and the welding angle, such as... Figure 14 As shown, it can be configured in the graphical user interface.

[0062] The first distance from the bar is the lateral offset distance between the weld and the outer circle of the bar, which can avoid direct contact; the second distance from the screen plate is the longitudinal offset distance between the weld and the surface of the screen plate, which ensures that the welding depth is appropriate; the welding angle is the angle between the welding gun and the axis of the bar, which can affect the welding quality and penetration depth.

[0063] As an example, the platform selects two points on the outer edge of the bar on the sieve plate plane as the welding start and end points, based on the center position of each target bar and the diameter of the standard bar. For example... Figure 15 As shown, when determining the weld line, firstly, based on the first distance from the bar and the welding angle, an offset direction vector is calculated to position the weld at an appropriate position on the side of the bar. The original starting point A and ending point B are then moved a set distance along the offset direction to obtain new weld endpoints A' and B'. Figure 15 The two blue dots above each bar (A' and B') form the weld line of the current target bar, which can be used for subsequent robotic arm path planning. It's important to note that connecting A' and B' requires considering the bar diameter and weld parameters to ensure that the distances from each point in the weld line to the bar meet the requirements. Alternatively, several intermediate points can be inserted between A' and B, and then connected to form the weld line. Figure 15 (The red line is shown in the image). Additionally, the graphical user interface highlights all target bars and their corresponding weld lines, allowing users to check the welding path for rationality and, if not, redefine the weld lines.

[0064] Step S300: Generate a welding teaching path based on the weld seam lines of each target bar and the motion parameters of the robotic arm.

[0065] The motion parameters of the robotic arm include the safe height and backward distance that the robotic arm needs to meet during the welding process, such as... Figure 16 As shown, this can be set in the graphical user interface. The safety height refers to the distance at which the welding torch will not collide with the screen plate when welding is not in progress. The back distance refers to the distance the welding torch must move upwards and then horizontally before moving to the next weld line after the current bar has finished welding along the weld line. Upon reaching the starting point of the next weld line, it must then move downwards. The distance moved upwards or downwards is equal to the back distance.

[0066] Examplely, step S300 specifically includes: determining the welding teaching path based on the safety height, the weld line of each target bar, and the backoff distance.

[0067] First, based on the weld line, a smooth welding path can be formed using linear or circular interpolation. The start and end points of this welding path are the final determined start and end points of the weld line. Then, by combining the safety height and backoff distance, a complete welding teaching path (such as...) can be formed. Figure 17 (As shown by the blue line).

[0068] In some implementations, such as Figure 16 As shown, the motion parameters also include the moving speed corresponding to the safe height. This speed is relatively faster than the retraction speed, mainly because at the safe height, there is still a distance between the welding torch and the weld seam, so the moving speed of the welding torch can be faster at this time. The retraction speed corresponding to the retraction distance refers to the speed when the welding torch moves upward or downward. At this time, the distance to the weld seam is relatively close, so in order to reach a more accurate position, the retraction speed is set to be smaller.

[0069] After generating the welding teaching path based on the weld seam lines of each target bar and the motion parameters of the robotic arm, the process also includes: generating a welding demonstration animation based on the welding teaching path and the welding parameters of the robotic arm; wherein the welding parameters include welding speed; if the welding demonstration animation confirms that there are no abnormalities in the welding, then in response to the welding program generation instruction, a welding program is generated based on the welding teaching path, motion parameters and welding parameters and uploaded to the robotic arm.

[0070] Understandably, after determining the welding teaching path, clicking on the simulation demonstration in the graphical user interface will display a simulated animation of the welding torch based on the welding teaching path and motion parameters. Users can judge whether the path is normal based on the simulation animation. If there are no abnormalities, clicking "Generate Preview Program" or "Generate Welding Program" will generate the teaching program for the robotic arm; the preview program does not contain arc initiation and termination instructions and can be used for effect verification. After generating the program, clicking "Upload Program" will upload the current program to the robotic arm (the robotic arm must be properly connected and does not require API enabling or other operations), while clicking "Load Program" will load the current program into the teach pendant program interface.

[0071] This embodiment automatically identifies the target bar and determines its position information using image recognition technology, significantly reducing the workload of manual teaching and greatly improving welding preparation efficiency. Furthermore, based on the acquired welding area image, this embodiment can accurately identify the center coordinates and arrangement direction of the bar, and calculate the weld line by combining the standard bar diameter and weld parameters, ensuring that the welding trajectory conforms to the actual workpiece structure, thereby improving the consistency and reliability of welding quality. Further, by combining the weld line with the robotic arm motion parameters, this embodiment can automatically generate a teaching path that meets the welding process requirements, achieving a seamless connection from image recognition to path generation. In addition, the introduction of motion parameters such as safety height and backtracking distance during path generation effectively avoids the risk of collision between the welding torch and the workpiece; simultaneously, combined with the simulation demonstration function, the path can be visually verified before formal welding, further ensuring the safety and stability of the welding process. Moreover, this embodiment provides a graphical user interface for functions such as identification area adjustment, weld preview, and path simulation, enabling even operators without professional robot programming skills to easily complete welding task configuration, greatly improving the system's usability and user experience.

[0072] Figure 18 A schematic diagram of a sieve plate and bar welding teaching device according to an embodiment of this application is shown. Exemplarily, the sieve plate and bar welding teaching device includes: The identification module 10 is used to identify target bars in the welding area in response to the acquired welding area image and determine the position information of each target bar; The determination module 20 is used to determine the weld line of each target bar based on the position information of each target bar, combined with the standard bar diameter and weld parameters; The generation module 30 is used to generate welding teaching paths based on the weld lines of each target bar and the motion parameters of the robotic arm.

[0073] It is understood that the device in this embodiment corresponds to the sieve plate and bar welding teaching method in the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described again here.

[0074] The welding control platform mentioned above can be a computer or industrial control computer, and the processor in the platform can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0075] This application also provides a computer-readable storage medium for storing computer programs used in the aforementioned terminal devices. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, in alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0077] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0078] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0079] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A teaching method for welding sieve plates and bars, characterized in that, include: In response to the acquired welding area image, target bars in the welding area are identified, and the position information of each target bar is determined; Based on the position information of each target bar, the weld line of each target bar is determined in combination with the standard bar diameter and weld parameters; Welding teaching paths are generated based on the weld seam lines of each target bar and the motion parameters of the robotic arm.

2. The welding teaching method for sieve plates and bars according to claim 1, characterized in that, The step of responding to the acquired welding area image to identify target bars in the welding area and determine the position information of each target bar includes: Candidate regions are obtained based on the weld area image; Based on the diameter of the bar and the preset diameter deviation, the candidate region is pre-identified to obtain the candidate bars in the candidate region; Based on the point cloud data of all the candidate bars, geometric modeling and consistency correction are performed on all the candidate bars to identify the target bars that meet the set geometric constraints, and the position information of each target bar is output.

3. The welding demonstration method for sieve plates and bars according to claim 2, characterized in that, The step of performing geometric modeling and consistency correction on all candidate bars based on point cloud data, and identifying target bars that satisfy the set geometric constraints, includes: Project the point cloud data corresponding to each candidate bar onto the spatial plane where the sieve plate is located to obtain the three-dimensional point set of each candidate bar on the spatial plane. The three-dimensional point set is modeled based on the cylinder fitting algorithm to obtain the circular region where each candidate bar intersects with the spatial plane and the coordinates of the center of the circle; Perform a straight line fit on the center coordinates of all the candidate bars, and calculate the offset of the center of each candidate bar relative to the fitted straight line; The target bar is determined based on the offset.

4. The welding demonstration method for sieve plates and bars according to claim 2, characterized in that, The step of obtaining candidate regions based on the weld area image includes: Point cloud analysis and preliminary identification are performed on the welding area image to determine at least one initial candidate region; The initial candidate regions are visually marked on the graphical user interface for user confirmation and adjustment; In response to user interaction adjustment commands, the boundaries or positions of the initial candidate region are adjusted to generate the candidate region.

5. The welding teaching method for sieve plates and bars according to claim 3, characterized in that, The location information includes the center coordinates of the circle corresponding to the target bar, and the arrangement direction of all the target bars; The step of determining the weld line of each target bar based on its position information, combined with the standard bar diameter and weld parameters, includes: Based on the center coordinates of each target bar and the diameter of the standard bar, the welding start point and end point of each target bar are determined; Based on the welding start and end points of each target bar and the preset weld parameters, the weld line of each target bar is determined; wherein, the weld parameters include a first distance from the bar, a second distance from the sieve plate, and a welding angle.

6. The welding demonstration method for sieve plates and bars according to claim 1, characterized in that, The motion parameters include safe height and retreat distance; The step of generating a welding teaching path based on the weld seam lines of each target bar and the motion parameters of the robotic arm includes: The welding teaching path is determined based on the safety height, the weld line of each target bar, and the retreat distance.

7. The welding teaching method for sieve plates and bars according to claim 6, characterized in that, The motion parameters also include the moving speed corresponding to the safe height and the retreating speed corresponding to the retreating distance; After generating the welding teaching path based on the weld seam lines of each target bar and the motion parameters of the robotic arm, the method further includes: A welding demonstration animation is generated based on the welding teaching path and the welding parameters of the robotic arm; wherein, the welding parameters include welding speed; If the welding demonstration animation confirms that there are no abnormalities in the welding, then in response to the welding program generation instruction, a welding program is generated based on the welding teaching path, the motion parameters, and the welding parameters, and uploaded to the robotic arm.

8. A teaching device for welding sieve plates and bars, characterized in that, include: The identification module is used to identify target bars in the welding area in response to the acquired welding area image, and to determine the position information of each target bar; The determination module is used to determine the weld line of each target bar based on the position information of each target bar, combined with the standard bar diameter and weld parameters; The generation module is used to generate a welding teaching path based on the weld seam lines of each target bar and the motion parameters of the robotic arm.

9. A teaching system for welding sieve plates and bars, characterized in that, include: Welding control platform and image acquisition device; The welding control platform includes a processor and a graphical user interface; The image acquisition device is used to acquire images of the welding area and transmit them to the welding control platform; The processor is configured to execute the sieve plate and bar welding teaching method according to any one of claims 1-7; The graphical user interface is used to display the execution progress and receive user input operation instructions when performing the sieve plate and bar welding teaching method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed on a processor, implements the sieve plate and bar welding teaching method according to any one of claims 1-7.

Images