Welding method and system

Abstract

According to the welding method and system, the intersecting neighborhoods of the point cloud segmentation areas are obtained after the point cloud information of the to-be-welded workpiece is collected, the welding seam position can be recognized and determined without inputting a manually-marked drawing, the welding seam information serves as model information to be stored, the same workpiece does not need to be modeled again, and the welding efficiency is improved. Labor cost is reduced to a great extent, welding application scenes are improved, the method is suitable for more complex and changeable non-standard scenes, and the welding robot can be effectively applied to intelligent welding in the non-standard field.

Description

Technical Field

[0001] The present invention relates to the field of welding technology, and in particular to a welding method; in addition, the present invention also relates to a welding system. Background Art

[0002] The current method of welding workpieces requires providing workpiece drawings and manual marking, which requires high technical skills of operators and is cumbersome to operate. Moreover, it is difficult to provide drawings for a variety of non-standard workpieces, and the types of workpieces vary greatly. Furthermore, existing visual products are difficult to identify weld information and cannot be used in non-standard scenarios. Summary of the invention

[0003] In order to solve the problems existing in the prior art, at least one embodiment of the present invention provides a welding method, which can identify and determine the weld position without inputting manually marked drawings, thereby greatly reducing labor costs and improving welding application scenarios. To this end, at least one embodiment of the present invention also provides a welding system.

[0004] In a first aspect, an embodiment of the present invention provides a welding method, comprising: Collect point cloud information of the workpiece to be welded; Segment the point cloud surface to obtain multiple point cloud segmentation areas; Get the intersection neighborhood of the point cloud segmentation area; Weld locations are determined by intersecting neighbors.

[0005] In some embodiments, the present invention provides a welding method, wherein collecting point cloud information of a workpiece to be welded includes: Collect multiple images of the workpiece to be welded and generate corresponding point cloud information, and perform iterative registration through the ICP algorithm.

[0006] In some embodiments, the present invention provides a welding method that performs denoising on point cloud information.

[0007] In some embodiments, the present invention provides a welding method, wherein segmenting a point cloud surface to obtain a plurality of point cloud segmentation regions comprises: Multiple seed points are randomly selected in the point cloud, and the point cloud surface is segmented using the region growing algorithm.

[0008] In some embodiments, the present invention provides a welding method, wherein obtaining an intersecting neighborhood of a point cloud segmentation area includes: Detect the boundary points of adjacent areas in all point cloud segmentation areas, and determine whether the adjacent areas intersect by the distance between the boundary points; obtain the intersection points of adjacent areas through a spatial search algorithm and obtain the neighborhood of the intersection points.

[0009] In a second aspect, an embodiment of the present invention further provides a welding system, characterized in that it includes: An acquisition module, used to acquire point cloud information of the workpiece to be welded; A segmentation module is used to segment the point cloud surface to obtain multiple point cloud segmentation areas; The intersection neighborhood acquisition module is used to obtain the intersection neighborhood of the point cloud segmentation area; The weld position determination module is used to determine the weld position through the intersection neighborhood.

[0010] In some embodiments, the present invention provides a welding system, wherein the acquisition module comprises: The registration module is used to iteratively register point cloud information through the ICP algorithm; Denoising module, used to perform denoising on point cloud information.

[0011] In a third aspect, an embodiment of the present invention further provides a welding device, comprising at least one processor; a memory coupled to the at least one processor, the memory storing executable instructions, which, when executed by the at least one processor, implement the steps of any one of the methods of the first aspect above.

[0012] In a fourth aspect, an embodiment of the present invention further provides a chip for executing the steps of the method in the first aspect. Specifically, the chip includes: a processor for calling and running a computer program from a memory, so that a device equipped with the chip is used to execute the steps of the method in the first aspect.

[0013] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect above are implemented.

[0014] It can be seen that a welding method and system in an embodiment of the present invention obtains the intersecting neighborhood of the point cloud segmentation area after collecting the point cloud information of the workpiece to be welded, and can identify and determine the weld position without inputting manually annotated drawings. The weld information is saved as model information, so that the same workpiece does not need to be modeled again, which greatly reduces the labor cost and improves the welding application scenarios. It is suitable for more complex and changeable non-standard scenarios, so that the welding robot can be effectively used for intelligent welding in non-standard fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0016] Figure 1 Shown is a flow chart of a welding method in an embodiment of the present invention; Figure 2 Shown is an overall flow chart of welding operation in an embodiment of the present invention; Figure 3 Shown is a schematic diagram of the framework of a welding system in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. In this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0019] [Example 1] The inventor of this solution found that in the prior art, the method of welding a workpiece requires providing a workpiece drawing and manual marking, which requires high technical skills of the operator and is cumbersome to operate. Moreover, it is difficult to provide drawings for a variety of non-standard workpieces, and the types of workpieces vary greatly. Furthermore, existing visual products are difficult to identify weld information and cannot be used in non-standard scenarios. Embodiment 1 of the present invention provides the following solution: like Figure 1 to Figure 2 As shown, this embodiment provides a welding method, which includes the following steps: Step 101, collecting point cloud information of the workpiece to be welded.

[0020] In some embodiments, multiple images of the workpieces to be welded are collected and corresponding point cloud information is generated, and iterative registration is performed using an ICP algorithm.

[0021] Specifically, when the workpiece to be welded is placed on the welding table, multiple images of the workpiece to be welded are taken, and a point cloud is generated using a visual odometer or a depth camera. The ICP algorithm includes the following steps: For each point in the source point cloud, find the point in the target point cloud that is closest to it through the KD tree algorithm; Compute the best rigid transformation from the source point cloud to the target point cloud, which includes a rotation matrix and a displacement vector, using least squares or singular value decomposition; Calculate the Euclidean distance between the source point cloud and the target point cloud, set a threshold according to actual needs, and if it is less than the threshold or the number of iterations reaches the upper limit, stop iterative convergence to complete the reverse modeling.

[0022] In some embodiments, the point cloud information is denoised. Specifically, statistical outlier removal or voxel grid filtering is used to remove noise points to improve the quality of the point cloud.

[0023] Step 102, segmenting the point cloud surface to obtain a plurality of point cloud segmentation regions.

[0024] In some embodiments, multiple seed points in the point cloud are randomly selected, and the point cloud surface is segmented using a region growing algorithm.

[0025] Specifically, multiple seed points are randomly selected from each target area, and the seed points represent the characteristics of the corresponding area, such as grayscale value and color. Furthermore, the conditions for merging pixels or voxels are determined. The conditions may include pixel value similarity, texture feature similarity or other features of interest. Thresholds can be used to judge the grayscale or color difference of adjacent pixels. For each pixel or voxel in the current area, its neighborhood is checked, such as 4 neighborhoods or 8 neighborhoods. It should be noted that the 4 neighborhoods include adjacent pixels in the four directions of up, down, left and right, while the 8 neighborhoods also include pixels in the diagonal direction. If a point in the neighborhood meets the growth condition, the point is added to the current area and marked as processed. In some embodiments, a marker array can be used to track which pixels have been processed to prevent repeated processing. Repeat the above steps until no more points can be added to the area, that is, there are no neighboring pixels that meet the growth conditions. When no new pixels can be added to the current area, the region growing algorithm terminates, and the final result is a connected area.

[0026] Step 103, obtaining the intersection neighborhood of the point cloud segmentation area.

[0027] In some embodiments, the boundary points of adjacent regions in all point cloud segmentation regions are detected, and whether the adjacent regions intersect is determined by the distance between the boundary points. The intersection points of the adjacent regions are obtained by a spatial search algorithm, and the neighborhood of the intersection points is obtained.

[0028] It should be noted that the distance between the boundary points can be set to a suitable threshold according to actual needs. If it is within the set threshold, it is determined that the adjacent areas intersect.

[0029] Step 104, determining the weld position by intersecting the neighborhood.

[0030] It should be noted that after the weld position is determined by the intersecting neighborhood, the weld coordinate position can be obtained through the neighborhood point cloud computing, and the welding gun posture and process parameters can be set according to the weld coordinate position, so as to set the welding path planning and obstacle avoidance measures. The weld configuration information is saved as a model configuration. When the same workpiece is encountered later, there is no need to re-model it and load the existing model configuration. After determining the weld configuration information, the weld position is scanned and accurately located by a line scan 3D camera, and then the welding operation is carried out.

[0031] [Example 2] like Figure 3 As shown, this embodiment provides a welding system, comprising: The acquisition module 201 is used to acquire point cloud information of the workpiece to be welded; A registration module 202, configured to iteratively register the point cloud information using an ICP algorithm; The denoising module 203 is used to perform denoising processing on the point cloud information.

[0032] In some embodiments, multiple images of the workpieces to be welded are collected and corresponding point cloud information is generated, and iterative registration is performed using an ICP algorithm.

[0033] Specifically, when the workpiece to be welded is placed on the welding table, multiple images of the workpiece to be welded are taken, and a point cloud is generated using a visual odometer or a depth camera. The ICP algorithm includes the following steps: For each point in the source point cloud, find the point in the target point cloud that is closest to it through the KD tree algorithm; Compute the best rigid transformation from the source point cloud to the target point cloud, which includes a rotation matrix and a displacement vector, using least squares or singular value decomposition; Calculate the Euclidean distance between the source point cloud and the target point cloud, set a threshold according to actual needs, and if it is less than the threshold or the number of iterations reaches the upper limit, stop iterative convergence to complete the reverse modeling.

[0034] In some embodiments, the point cloud information is denoised. Specifically, statistical outlier removal or voxel grid filtering is used to remove noise points to improve the quality of the point cloud.

[0035] The segmentation module 204 is used to segment the point cloud surface to obtain a plurality of point cloud segmentation regions.

[0036] In some embodiments, multiple seed points in the point cloud are randomly selected, and the point cloud surface is segmented using a region growing algorithm.

[0037] Specifically, multiple seed points are randomly selected from each target area, and the seed points represent the characteristics of the corresponding area, such as grayscale value and color. Furthermore, the conditions for merging pixels or voxels are determined. The conditions may include pixel value similarity, texture feature similarity or other features of interest. Thresholds can be used to judge the grayscale or color difference of adjacent pixels. For each pixel or voxel in the current area, its neighborhood is checked, such as 4 neighborhoods or 8 neighborhoods. It should be noted that the 4 neighborhoods include adjacent pixels in the four directions of up, down, left and right, while the 8 neighborhoods also include pixels in the diagonal direction. If a point in the neighborhood meets the growth condition, the point is added to the current area and marked as processed. In some embodiments, a marker array can be used to track which pixels have been processed to prevent repeated processing. Repeat the above steps until no more points can be added to the area, that is, there are no neighboring pixels that meet the growth conditions. When no new pixels can be added to the current area, the region growing algorithm terminates, and the final result is a connected area.

[0038] The intersection neighborhood acquisition module 205 is used to obtain the intersection neighborhood of the point cloud segmentation area.

[0039] In some embodiments, the boundary points of adjacent regions in all point cloud segmentation regions are detected, and whether the adjacent regions intersect is determined by the distance between the boundary points. The intersection points of the adjacent regions are obtained by a spatial search algorithm, and the neighborhood of the intersection points is obtained.

[0040] It should be noted that the distance between the boundary points can be set to a suitable threshold according to actual needs. If it is within the set threshold, it is determined that the adjacent areas intersect.

[0041] The welding position determination module 206 is used to determine the welding position through the intersection neighborhood.

[0042] It should be noted that after the weld position is determined by the intersecting neighborhood, the weld coordinate position can be obtained through the neighborhood point cloud computing, and the welding gun posture and process parameters can be set according to the weld coordinate position, so as to set the welding path planning and obstacle avoidance measures. The weld configuration information is saved as a model configuration. When the same workpiece is encountered later, there is no need to re-model it and load the existing model configuration. After determining the weld configuration information, the weld position is scanned and accurately located by a line scan 3D camera, and then the welding operation is carried out.

[0043] [Example 3] This embodiment provides a welding device, comprising: At least one processor; a memory coupled to the at least one processor, the memory storing executable instructions, wherein the executable instructions, when executed by the at least one processor, implement the method steps of embodiment 1 of the present invention.

[0044] In a welding device provided by an embodiment of the present invention, a processor and a memory may be provided separately or integrated together.

[0045] For example, the memory may include a random access memory, a flash memory, a read-only memory, a programmable read-only memory, a non-volatile memory or a register, etc. The processor may be a central processing unit (CPU), etc., or a graphic processing unit (GPU). The memory may store executable instructions. The processor may execute the executable instructions stored in the memory to implement the various processes described herein.

[0046] It can be understood that the memory in this embodiment can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a ROM (Read-Only Memory), a PROM (Programmable ROM), an EPROM (Erasable PROM), an EEPROM (Electrically EPROM), or a flash memory. The volatile memory can be a RAM (Random Access Memory), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as SRAM (Static RAM), DRAM (Dynamic RAM), SDRAM (Synchronous DRAM), DDR SDRAM (Double Data Rate SDRAM), ESDRAM (Enhanced SDRAM), SLDRAM (Synchlink DRAM), and DRRAM (Direct Rambus RAM). The memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0047] In some embodiments, the memory stores the following elements, upgrade packages, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system and an application program.

[0048] The operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application program includes various application programs, which are used to implement various application services. The program for implementing the method of the embodiment of the present invention can be included in the application program.

[0049] In the embodiment of the present invention, the processor calls a program or instruction stored in the memory, specifically, a program or instruction stored in an application program, and the processor is used to execute the method steps of the embodiment 1 of the present invention.

[0050] [Example 4] This embodiment provides a chip for executing the method of the above-mentioned embodiment 1 of the present invention. Specifically, the chip includes: a processor for calling and running a computer program from a memory, so that a device equipped with the chip is used to execute the method of the embodiment 1 of the present invention.

[0051] [Example 5] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method of Embodiment 1 of the present invention are implemented.

[0052] For example, machine-readable storage media may include, but are not limited to, various known and unknown types of non-volatile memory.

[0053] In summary, embodiments 1-5 of the present invention provide a welding method and system, which obtains the intersecting neighborhood of the point cloud segmentation area after collecting the point cloud information of the workpiece to be welded, and can identify and determine the weld position without inputting manually annotated drawings. The weld information is saved as model information, so that the same workpiece does not need to be modeled again, which greatly reduces the labor cost and improves the welding application scenarios. It is suitable for more complex and changeable non-standard scenarios, so that the welding robot can be effectively used for intelligent welding in non-standard fields.

[0054] It will be appreciated by those skilled in the art that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0055] In the embodiments of the present application, the disclosed systems, devices and methods can be implemented in other ways. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system. In addition, the coupling between the various units can be direct coupling or indirect coupling. In addition, the various functional units in the embodiments of the present application can be integrated into a processing unit, or can be separate physical existences, etc.

[0056] It should be understood that in the various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0057] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a machine-readable storage medium. Therefore, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a machine-readable storage medium, which can include several instructions to enable an electronic device to perform all or part of the technical solution described in the embodiments of the present application. The above-mentioned storage medium may include various media that can store program codes, such as ROM, RAM, removable disk, hard disk, magnetic disk or optical disk.

[0058] The above contents are only specific implementation methods of the present application, and the protection scope of the present application is not limited thereto. Those skilled in the art may make changes or substitutions within the technical scope disclosed in the present application, and these changes or substitutions shall be within the protection scope of the present application.

Claims

1. A welding method, characterized in that: include: Collect point cloud information of the workpiece to be welded; Segment the point cloud surface to obtain multiple point cloud segmentation areas; Obtaining the intersection neighborhood of the point cloud segmentation area; The weld position is determined by the intersection neighborhood.

2. The welding method according to claim 1, characterized in that: The step of collecting point cloud information of the workpiece to be welded includes: A plurality of images of the workpiece to be welded are collected and corresponding point cloud information is generated, and iterative registration is performed using an ICP algorithm.

3. The welding method according to claim 2, characterized in that: The point cloud information is subjected to denoising processing.

4. The welding method according to claim 1, characterized in that: The step of segmenting the point cloud surface to obtain a plurality of point cloud segmentation regions comprises: Multiple seed points are randomly selected in the point cloud, and the point cloud surface is segmented using the region growing algorithm.

5. The welding method according to claim 1, characterized in that: The obtaining of the intersection neighborhood of the point cloud segmentation area comprises: Detect the boundary points of adjacent areas in all point cloud segmentation areas, and determine whether the adjacent areas intersect by the distance between the boundary points; obtain the intersection points of adjacent areas through a spatial search algorithm and obtain the neighborhood of the intersection points.

6. A welding system, characterized in that: include: An acquisition module, used to acquire point cloud information of the workpiece to be welded; A segmentation module is used to segment the point cloud surface to obtain multiple point cloud segmentation areas; An intersecting neighborhood acquisition module, used to obtain the intersecting neighborhood of the point cloud segmentation area; The weld position determination module is used to determine the weld position through the intersection neighborhood.

7. The welding system according to claim 6, characterized in that The acquisition module comprises: A registration module, used for iteratively registering the point cloud information through an ICP algorithm; The denoising module is used to perform denoising on the point cloud information.

8. A welding device, comprising at least one processor; a memory coupled to the at least one processor, the memory storing executable instructions, characterized in that: The executable instructions, when executed by the at least one processor, enable the steps of the method according to any one of claims 1 to 5 to be implemented.

9. A chip, characterized in that: It comprises a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes the steps of the method as claimed in any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images