A method, apparatus, and readable storage medium for weld grinding

Abstract

The application provides a welding seam polishing method, device and readable storage medium, and the method comprises the following steps: acquiring a welding seam to be polished; adjusting the posture of a polishing robot and an electric control unit, so that the welding seam starting point of the welding seam to be polished and the base material within the radius range of the grinding wheel on both sides of the welding seam are within the corresponding field of view range of a 3D camera; collecting the welding seam data of the whole welding seam to be polished and the plane data of the base material through the 3D camera; screening the area needing polishing according to the Z-axis information in the welding seam data, and calculating the flatness information of the base material according to the plane data of the base material; collecting the area needing polishing, and planning the polishing path and setting the polishing angle in combination with the flatness information of the base material; and sending the planned polishing path and the corresponding polishing angle to the robot control cabinet. The method, device and readable storage medium can solve the problems of low overall polishing accuracy of the existing welding seam polishing method and the damage to the base material in the polishing process.

Description

Technical Field

[0001] This invention relates to the field of grinding technology, and more particularly to a method, apparatus, and readable storage medium for grinding weld seams. Background Technology

[0002] Currently, grinding processes can be categorized from coarse to fine into milling, grinding, and polishing, and are widely used in industries such as sanitary ware, auto parts, furniture, medical devices, military, communications, lighting, and building hardware. Weld grinding falls under the category of grinding. Current grinding methods are mainly divided into manual grinding and non-manual grinding. Non-manual grinding includes production line grinding and robotic grinding. Existing robotic grinding primarily relies on human instruction to help the robot plan its motion trajectory for grinding standard parts. Programming adjusts parameters such as the grinding wheel angle and speed to ensure the robot can complete the grinding of parts placed in a fixed position.

[0003] However, existing robot-based weld grinding methods have two main drawbacks. First, current teach-and-grind robots cannot perform precise grinding based on the height of the workpiece, resulting in low overall grinding accuracy. Second, teach-and-grind robots typically perform weld grinding at preset points, which can easily damage the base material during the grinding process. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to address the above-mentioned shortcomings of the prior art by providing a method, apparatus and readable storage medium for grinding welds, so as to solve the problems of low overall grinding accuracy and easy damage to the base material during the grinding process in the existing weld grinding methods.

[0005] In a first aspect, the present invention provides a method for grinding weld seams, the method comprising:

[0006] Obtain the weld seam to be ground;

[0007] Adjust the posture of the grinding robot and the electronic control unit so that the base material within the radius of the grinding wheel on both sides of the weld to be ground is within the corresponding field of view of the 3D camera.

[0008] The weld data of the entire weld seam to be ground and the planar data of the base material are acquired by a 3D camera;

[0009] The area that needs to be ground is selected based on the Z-axis information in the weld data, and the flatness information of the base material is calculated based on the planar data of the base material.

[0010] The areas that need to be sanded are grouped together, and the sanding path and sanding angle are planned and set in combination with the flatness information of the base material.

[0011] The planned grinding path and corresponding grinding angle are sent to the robot control cabinet, so that the robot control cabinet can send corresponding instructions to control the grinding robot to complete the corresponding weld grinding work.

[0012] Furthermore, obtaining the weld seam to be ground specifically includes:

[0013] Determine if there are any incompletely ground welds on the workpiece;

[0014] In response to the presence of incompletely ground welds on the workpiece, the weld to be ground is obtained from the incompletely ground welds.

[0015] Furthermore, the 3D camera is based on a line structured light mode. Before acquiring weld data of the entire weld seam to be ground and the planar data of the base material through the 3D camera, the method further includes:

[0016] The sampling points and sampling intervals of the 3D camera's line structured light are set according to the polishing requirements.

[0017] Furthermore, the step of acquiring weld data of the entire weld seam to be ground and planar data of the base material using a 3D camera specifically includes:

[0018] While ensuring consistent depth of field of the 3D camera, the 3D camera is controlled by the electronic control unit to scan the entire weld seam to be ground and the base material within the radius of the grinding wheel on both sides of the weld seam, so as to collect the weld seam data of the entire weld seam to be ground and the planar data of the base material.

[0019] Furthermore, the step of filtering out the areas requiring grinding based on the Z-axis information in the weld data specifically includes:

[0020] Based on the height information required for grinding, the Z-axis information in the collected weld data is filtered to identify the coordinates that need to be ground by the grinding robot, thus obtaining the area that needs to be ground.

[0021] Furthermore, the process of grouping the areas to be sanded and combining the flatness information of the base material to plan the sanding path and set the sanding angle specifically includes:

[0022] The areas that need to be ground are grouped together, with the direction from the start to the end of the weld as the x-axis, the weld width as the y-axis, and the weld height as the z-axis. The grinding path is planned for the grouped grinding areas along the x-axis.

[0023] The grinding angle is set according to the planned grinding path and the flatness information of the base material. The grinding angle can ensure that the grinding wheel is level with the flatness of the base material in the grinding area.

[0024] Furthermore, the method also includes:

[0025] Set the grinding height of the non-grinding areas along the grinding path during its movement to increase the Z-axis height;

[0026] The grinding height of the non-grinding area is sent to the robot control cabinet.

[0027] Secondly, the present invention provides an apparatus for grinding weld seams, comprising:

[0028] The weld seam acquisition module is used to acquire the weld seam to be ground.

[0029] The attitude adjustment module is connected to the weld acquisition module and is used to adjust the attitude of the grinding robot and the electronic control unit so that the base material within the radius of the grinding wheel on both sides of the weld to be ground is within the corresponding field of view of the 3D camera.

[0030] The data acquisition module, connected to the attitude adjustment module, is used to acquire weld data of the entire weld seam to be ground and planar data of the base material through a 3D camera.

[0031] The filtering and calculation module is connected to the data acquisition module and is used to filter out the area that needs to be ground based on the Z-axis information in the weld data, and to calculate the flatness information of the base material based on the plane data of the base material.

[0032] The path angle planning module, connected to the filtering calculation module, is used to collect the areas that need to be polished and combine the flatness information of the base material to plan the polishing path and set the polishing angle.

[0033] The weld grinding module, connected to the path angle planning module, is used to send the planned grinding path and corresponding grinding angle to the robot control cabinet, so that the robot control cabinet can send corresponding instructions to control the grinding robot to complete the corresponding weld grinding work.

[0034] Thirdly, the present invention provides an apparatus for grinding welds, comprising a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to implement the weld grinding method described in the first aspect above.

[0035] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the weld grinding method described in the first aspect.

[0036] This invention provides a method, apparatus, and readable storage medium for weld grinding. First, the weld to be ground is acquired; then, the posture of the grinding robot and electronic control unit is adjusted so that the base material within the radius of the grinding wheel on both sides of the weld, from the weld start point, is within the corresponding field of view of the 3D camera; next, the 3D camera acquires weld data of the entire weld to be ground and planar data of the base material; then, the area to be ground is selected based on the Z-axis information in the weld data, and the flatness information of the base material is calculated based on the planar data; finally, the areas to be ground are aggregated, and the grinding path and grinding angle are planned based on the flatness information of the base material; then, the planned grinding path and corresponding grinding angle are sent to the robot control cabinet, so that the robot control cabinet sends corresponding instructions to control the grinding robot to complete the corresponding weld grinding work. This invention uses 3D machine vision to identify the weld reinforcement on the weld seam to be ground, select the area that needs to be ground, and set the grinding path and angle of the grinding wheel based on the area to be ground and the flatness information of the surrounding base material. This can further improve the grinding accuracy and guide the grinding robot to complete the grinding work on the weld seam without damaging the base material. It solves the problems of low overall grinding accuracy and easy damage to the base material in existing weld grinding methods. Attached Figure Description

[0037] Figure 1 This is a flowchart of a weld grinding method according to Embodiment 1 of the present invention;

[0038] Figure 2 This is a schematic diagram illustrating the connection between the polishing robot, the electronic control unit, and the 3D camera in an embodiment of the present invention.

[0039] Figure 3 This is a schematic diagram of the polishing path planning according to an embodiment of the present invention;

[0040] Figure 4 This is an architectural diagram of the weld grinding system according to an embodiment of the present invention;

[0041] Figure 5 This is a schematic diagram of a weld grinding device according to Embodiment 2 of the present invention;

[0042] Figure 6 This is a schematic diagram of a weld grinding device according to Embodiment 3 of the present invention. Detailed Implementation

[0043] To enable those skilled in the art to better understand the technical solution of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0044] It is understood that the specific embodiments and accompanying drawings described herein are merely for explaining the invention and are not intended to limit the invention.

[0045] It is understood that, without conflict, the various embodiments and features in the embodiments of the present invention can be combined with each other.

[0046] It is understood that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, while the parts unrelated to the present invention are not shown in the drawings.

[0047] It is understood that each unit or module involved in the embodiments of the present invention may correspond to only one entity structure, or may be composed of multiple entity structures, or multiple units or modules may be integrated into one entity structure.

[0048] It is understood that the terms "first," "second," etc., in the embodiments of the present invention are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0049] It is understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of this invention may occur in a different order than that marked in the accompanying drawings.

[0050] It is understood that the flowcharts and block diagrams of this invention illustrate the possible architecture, functions, and operations of systems, apparatuses, devices, and methods according to various embodiments of this invention. Each block in the flowchart or block diagram may represent a unit, module, program segment, or code, containing executable instructions for implementing the specified function. Furthermore, each block or combination of blocks in the block diagram and flowchart can be implemented using a hardware-based system to achieve the specified function, or using a combination of hardware and computer instructions.

[0051] It is understood that the units and modules involved in the embodiments of the present invention can be implemented by software or by hardware. For example, the units and modules can be located in a processor.

[0052] Application Overview

[0053] Existing robot-based weld grinding methods have the following technical problems during the grinding process:

[0054] 1. Teaching-in-the-loop grinding robots, which perform grinding work by using preset points, are prone to damaging the base material.

[0055] The teaching robot completes the grinding by pre-setting grinding points. This grinding method requires the grinding wheel to move along the weld path and grind the entire relevant area of ​​the weld to achieve the grinding requirements. In actual work, grinding the entire weld path can easily cause scratches on the base material surface, and if the weld is lower than the welded part, it can also easily damage the base material.

[0056] 2. Current teach-and-grind robots cannot perform precise grinding based on the height of the workpiece.

[0057] Existing teaching grinding robots can only grind the entire weld seam at a fixed height standard using a wheel grinder at a fixed angle. Moreover, they cannot accurately cut into and grind the parts that need to be ground after identifying them, so the overall grinding accuracy is not high.

[0058] To address the aforementioned technical problems, this application proposes a method, apparatus, and readable storage medium for weld grinding. It utilizes 3D machine vision to identify the weld reinforcement on the weld to be ground, selecting the areas requiring grinding. Based on the area to be ground and the flatness information of the surrounding base material, the grinding wheel's grinding path and angle are set, further improving grinding accuracy. This guides the grinding robot to complete the weld grinding work without damaging the base material. This solves the problems of low overall grinding accuracy and easy damage to the base material in existing weld grinding methods.

[0059] Example 1:

[0060] This embodiment provides a method for grinding weld seams, such as... Figure 1 As shown, the method includes:

[0061] Step S101: Obtain the weld seam to be ground.

[0062] It should be noted that the weld grinding method provided in this embodiment is designed for weld grinding scenarios. It combines the existing weld coordinate information of the teaching robot, the application of line structured light and 3D camera machine vision, and a six-axis robot (hereinafter referred to as the grinding robot) to accurately identify grinding points, plan grinding wire diameter, and guide the grinding robot to complete high-precision welding work. The connection method between the grinding robot and the electronic control unit and the 3D camera can be as follows: Figure 2 As shown, the grinding robot may include a base (1), joint 1 (2), waist link (3), joint 2 (4), upper arm link (5), joint 3 (6), forearm rear link (7), joint 4 (8), forearm front link (9), joint 5 (10), wrist link (11), joint 6 (12), and grinding wheel (13). A bracket (16) is added to the wrist link (11) of the grinding robot to connect a 3D camera (15). An electronic control unit (17) is present at the corresponding connection to control the rotation of the 3D camera and the structured light generator, so as to facilitate scanning the weld data of the weld to be ground and the plane data of the base material in the grinding part (18) on the worktable (19). This can ensure accurate identification of the points to be ground during the data reading process.

[0063] It should be noted that a teach pendant robot is an improvement on a robot to enable it to teach. A six-axis robot is the basis for this improvement and belongs to a type of industrial robot. This invention is aimed at a six-axis robot, but it uses the teaching data of a teach pendant robot and does not directly apply the teach pendant robot.

[0064] Optionally, obtaining the weld seam to be ground specifically includes:

[0065] Determine if there are any incompletely ground welds on the workpiece;

[0066] In response to the presence of incompletely ground welds on the workpiece, the weld to be ground is obtained from the incompletely ground welds.

[0067] In this embodiment, taking a steel plate as the grinding part, it can first determine whether there are multiple welds that need to be ground based on the starting point and ending point information of the teaching robot grinding the weld. If there are multiple welds on the steel plate, it can then determine whether there are any welds on the steel plate that have not been ground based on the initial weld information. If all are completed, the whole process ends. If there are welds that have not been ground, the welds to be ground are obtained sequentially from the welds that have not been ground.

[0068] Step S102: Adjust the posture of the grinding robot and the electronic control unit so that the base material within the radius of the grinding wheel on both sides of the weld to be ground is within the corresponding field of view of the 3D camera.

[0069] In this embodiment, the grinding robot and the electronic control unit can be controlled according to the coordinate information of the weld start point, process point and end point stored in the teaching information so that the base material within the radius of the grinding wheel on both sides of the weld start point and weld is within the corresponding field of view of the 3D camera.

[0070] Step S103: Collect weld data of the entire weld seam to be ground and the planar data of the base material using a 3D camera.

[0071] Optionally, the 3D camera is based on a line structured light mode. Before acquiring weld data of the entire weld seam to be ground and planar data of the base material using the 3D camera, the method further includes:

[0072] The sampling points and sampling intervals of the 3D camera's line structured light are set according to the polishing requirements.

[0073] In this embodiment, to further mitigate error factors, the present invention utilizes line structured light as the light source for the 3D camera. The 3D camera based on the line structured light mode comprises an optical projector, a camera, and a computer system, forming a structured light 3D vision system. The system projects a light beam onto an object. The light beam is modulated due to variations in the object's surface depth and possible gaps, resulting in distortion and discontinuity in the image. The degree of distortion is proportional to the depth. The 3D information of the object's surface is obtained from the distorted light beam image information. When the relative position between the optical projector and the camera is constant, the 3D shape and contour of the object's surface can be reconstructed from the coordinates of the distorted 2D light beam image.

[0074] In this embodiment, the 3D camera includes a structured light emitter. The number and spacing of the horizontal sampling points of the line structured light can be set according to the width of the weld to be ground. Then, the vertical sampling reference point information is set according to the grinding requirements, which include flatness, weld reinforcement, weld height, and other information.

[0075] Optionally, the step of acquiring weld data of the entire weld seam to be ground and planar data of the base material using a 3D camera specifically includes:

[0076] While ensuring consistent depth of field of the 3D camera, the 3D camera is controlled by the electronic control unit to scan the entire weld seam to be ground and the base material within the radius of the grinding wheel on both sides of the weld seam, so as to collect the weld seam data of the entire weld seam to be ground and the planar data of the base material.

[0077] In this embodiment, by controlling the electronic control unit and the grinding robot, while ensuring that the depth of field of the 3D camera remains unchanged, i.e. the distance between the 3D camera and the weld remains unchanged, the structured light emitted by the structured light emitter scans the entire weld to be ground and the base material within the radius of the grinding wheel on both sides of the weld. The 3D camera collects weld data and surrounding base material plane data from the start point to the end point of the weld.

[0078] Step S104: Select the area that needs to be ground based on the Z-axis information in the weld data, and calculate the flatness information of the base material based on the plane data of the base material.

[0079] Specifically, the Z-axis information in the collected weld data can be filtered according to the height information required for grinding (i.e., weld height) to select the coordinates that need to be ground by the grinding robot, thereby obtaining the area that needs to be ground. At the same time, the flatness of the base material data on both sides of the collected weld is calculated.

[0080] Step S105: Collect the areas that need to be sanded, and combine the flatness information of the base material to plan the sanding path and set the sanding angle.

[0081] Optionally, the step of grouping the areas to be sanded and combining the flatness information of the base material to plan the sanding path and set the sanding angle specifically includes:

[0082] The areas that need to be ground are grouped together, with the direction from the start to the end of the weld as the x-axis, the weld width as the y-axis, and the weld height as the z-axis. The grinding path is planned for the grouped grinding areas along the x-axis.

[0083] The grinding angle is set according to the planned grinding path and the flatness information of the base material. The grinding angle can ensure that the grinding wheel is level with the flatness of the base material in the grinding area.

[0084] In this embodiment, the schematic diagram of the grinding path planning can be as follows: Figure 3 As shown, the x-axis is from the starting point to the ending point of the weld, the y-axis is the weld width, and the z-axis is the weld height. Path planning is performed on the selected areas that need to be ground along the x-axis, that is, two adjacent grinding areas are connected by a straight line and this is used as the trajectory of the grinding wheel.

[0085] Step S106: Send the planned grinding path and corresponding grinding angle to the robot control cabinet so that the robot control cabinet can send corresponding instructions to control the grinding robot to complete the corresponding weld grinding work.

[0086] In this embodiment, the precise grinding path and the corresponding grinding wheel angle information are sent to the robot control cabinet, and then the robot control cabinet sends corresponding instructions to control the grinding robot to perform the grinding work.

[0087] Optionally, the method further includes:

[0088] Set the grinding height of the non-grinding areas along the grinding path during its movement to increase the Z-axis height;

[0089] The grinding height of the non-grinding area is sent to the robot control cabinet.

[0090] In this embodiment, non-polished areas encountered during path travel can be avoided by increasing the Z-axis height.

[0091] This invention utilizes line structured light as a light source and identifies the weld reinforcement on the weld seam through 3D machine vision. Based on the spatial coordinates of 3D machine vision, the grinding wheel is guided to plan the grinding path and grinding angle, which can further improve the grinding accuracy and guide the robot to complete the grinding work of the weld seam without damaging the base material.

[0092] In one specific embodiment, the weld grinding method may include the following steps:

[0093] 1. Determine if there are any welds that have not been properly ground. If so, proceed to the next step; otherwise, end the process.

[0094] 2. Set the line structured light sampling points and sampling intervals according to the polishing requirements;

[0095] 3. Adjust the posture of the grinding robot and the electronic control unit so that the base material within the radius of the grinding wheel at the weld start point and on both sides of the weld is within the corresponding field of view of the 3D camera.

[0096] 4. By controlling the electronic control unit, the line structured light and 3D camera are used to scan and sample the base material within the radius of the grinding wheel on both sides of the weld seam under the condition of consistent depth of field;

[0097] 5. Filter the collected data using Z-axis information, select the areas that need to be polished, and calculate the flatness information of the base material at the same time;

[0098] 6. Group the areas that need to be sanded, and plan the sanding path and set the angles based on the flatness of the base material;

[0099] 7. Send precise coordinates to the robot control cabinet, and then the robot control cabinet sends instructions to control the grinding wheel to complete the corresponding grinding work.

[0100] This invention uses machine vision to precisely correct existing grinding paths and guide grinding robots to complete tasks, thus avoiding the adverse effects on components caused by traditional teach-and-play grinding robots during weld grinding.

[0101] In another specific embodiment, the weld grinding method is applied to, for example... Figure 4 The weld grinding system shown includes a 3D camera (15), a gateway (20), a vision server (21), a computing server (22), a robot control cabinet (23), a grinding robot (24), and an electrical control unit (17). The vision server (21) and the computing server (22) can be combined or set up independently. The weld grinding method may include the following steps:

[0102] 1. Based on the starting point and ending point information of the teaching robot grinding the weld, determine whether there are multiple welds that need to be ground. For the case where there are multiple welds on the grinding part (such as steel plate), the computing server (22) determines whether there are welds on the steel plate that have not been ground based on the initial weld information. If all are completed, the whole process ends; otherwise, proceed to step 2.

[0103] 2. Preset weld parameters: The 3D camera (15) contains a structured light emitter. The vision server (21) sets the number and spacing of horizontal sampling points of the line structured light according to the width of the weld to be ground, and then sets the vertical sampling reference point information according to the grinding requirements.

[0104] 3. Camera position adjustment: Based on the coordinate information of the weld start point, process point and end point stored in the teaching information, control the grinding robot (24) and the electrical control unit (17) to make the base material within the radius of the grinding wheel (13) on both sides of the weld start point and the weld within the corresponding field of view of the 3D camera (15).

[0105] 4. Weld seam data acquisition: By controlling the electrical control unit (17) and the grinding robot (24), while ensuring that the depth of field of the 3D camera (15) remains unchanged, i.e. the distance between the 3D camera and the weld seam remains unchanged, the structured light emitted by the structured light emitter scans the entire weld seam and the base material within the radius of the grinding wheel (13) on both sides of the weld seam. The 3D camera (15) collects weld seam data and surrounding base material plane data from the start point to the end point of the weld seam.

[0106] 5. Weld data cleaning: The computing server (22) filters the Z-axis information of the collected weld data based on the height information of the grinding requirements (i.e., weld height), filters out the coordinates that need to be ground by the robot, and calculates the flatness of the base material data on both sides of the collected weld.

[0107] 6. Grinding Path Planning: The computing server (22) then collects all the coordinates that need to be ground, with the starting point of the weld and the end point as the x-axis, the weld width as the y-axis, and the weld height as the z-axis. Along the x-axis, the server plans the path for the areas that need to be ground according to step 5, that is, two adjacent grinding areas are connected by a straight line and this is used as the trajectory of the grinding wheel (13). For non-grinding areas encountered during the path movement, the Z-axis height can be increased to avoid them. At the same time, the flatness information of the base material within the radius of the grinding wheel (13) on both sides of the weld is collected. By ensuring that the grinding wheel is level with the flatness of the base material in the grinding area, the grinding angle can be adjusted.

[0108] 7. Precision grinding implementation: The computing server (22) sends the precise grinding path and corresponding grinding wheel (13) grinding angle information to the robot control cabinet (23), and then the robot control cabinet (23) sends corresponding instructions to control the grinding robot (24) to carry out the grinding work.

[0109] The weld grinding method provided in this embodiment of the invention first acquires the weld to be ground; then adjusts the posture of the grinding robot and the electronic control unit so that the base material within the radius range of the grinding wheel on both sides of the weld starting point and the weld to be ground is within the corresponding field of view of the 3D camera; then, the 3D camera acquires the weld data of the entire weld to be ground and the planar data of the base material; then, the area to be ground is selected according to the Z-axis information in the weld data, and the flatness information of the base material is calculated according to the planar data of the base material; finally, the area to be ground is collected, and the grinding path is planned and the grinding angle is set in combination with the flatness information of the base material; then, the planned grinding path and the corresponding grinding angle are sent to the robot control cabinet so that the robot control cabinet sends corresponding instructions to control the grinding robot to complete the corresponding weld grinding work. This invention uses 3D machine vision to identify the weld reinforcement on the weld seam to be ground, select the area that needs to be ground, and set the grinding path and angle of the grinding wheel based on the area to be ground and the flatness information of the surrounding base material. This can further improve the grinding accuracy and guide the grinding robot to complete the grinding work on the weld seam without damaging the base material. It solves the problems of low overall grinding accuracy and easy damage to the base material in existing weld grinding methods.

[0110] Example 2:

[0111] like Figure 5 As shown, this embodiment provides an apparatus for grinding welds, used to perform the above-described weld grinding method, including:

[0112] Weld seam acquisition module 31 is used to acquire the weld seam to be ground;

[0113] The posture adjustment module 32 is connected to the weld acquisition module 31 and is used to adjust the posture of the grinding robot and the electronic control unit so that the base material within the radius of the grinding wheel on both sides of the weld to be ground is within the corresponding field of view of the 3D camera.

[0114] The data acquisition module 33 is connected to the attitude adjustment module 32 and is used to acquire the weld data of the entire weld seam to be ground and the planar data of the base material through a 3D camera.

[0115] The filtering and calculation module 34 is connected to the data acquisition module 33 and is used to filter out the area that needs to be ground based on the Z-axis information in the weld data, and to calculate the flatness information of the base material based on the plane data of the base material.

[0116] The path angle planning module 35 is connected to the screening calculation module 34 and is used to collect the areas that need to be polished and combine the flatness information of the base material to plan the polishing path and set the polishing angle.

[0117] The weld grinding module 36 is connected to the path angle planning module 35 and is used to send the planned grinding path and corresponding grinding angle to the robot control cabinet so that the robot control cabinet can send corresponding instructions to control the grinding robot to complete the corresponding weld grinding work.

[0118] Furthermore, the weld seam acquisition module 31 specifically includes:

[0119] The judgment unit is used to determine whether there are any welds that have not been properly ground on the workpiece.

[0120] The selection unit is used to select the weld to be ground from the unground welds in response to the presence of unground welds on the workpiece.

[0121] Furthermore, the 3D camera is based on a line structured light mode, and the device further includes:

[0122] The setting module is used to set the sampling points and sampling intervals of the 3D camera line structured light according to the polishing requirements.

[0123] Furthermore, the data acquisition module 33 is specifically used for:

[0124] While ensuring consistent depth of field of the 3D camera, the 3D camera is controlled by the electronic control unit to scan the entire weld seam to be ground and the base material within the radius of the grinding wheel on both sides of the weld seam, so as to collect the weld seam data of the entire weld seam to be ground and the planar data of the base material.

[0125] Furthermore, the screening calculation module 34 includes:

[0126] The grinding area acquisition unit is used to filter the Z-axis information in the collected weld data according to the height information required for grinding, and filter out the coordinates that need to be ground by the grinding robot to obtain the area that needs to be ground.

[0127] Furthermore, the path angle planning module 35 specifically includes:

[0128] The path planning unit is used to group the areas that need to be ground, with the direction from the start to the end of the weld as the x-axis, the weld width as the y-axis, and the weld height as the z-axis, and to plan the grinding path for the grouped grinding areas along the x-axis.

[0129] An angle planning unit is used to set the grinding angle based on the planned grinding path and the flatness information of the base material. The grinding angle can ensure that the grinding wheel is level with the flatness of the base material in the grinding area.

[0130] Furthermore, the device also includes:

[0131] The grinding height setting module is used to set the grinding height of the non-grinding areas traversed during the grinding path movement, in order to increase the Z-axis height;

[0132] The grinding height sending module is used to send the grinding height of the non-grinding area to the robot control cabinet.

[0133] Example 3:

[0134] refer to Figure 6 This embodiment provides a weld grinding apparatus, including a memory 41 and a processor 42. The memory 41 stores a computer program, and the processor 42 is configured to run the computer program to perform the weld grinding method in Embodiment 1.

[0135] The memory 41 is connected to the processor 42. The memory 41 can be a flash memory, a read-only memory or other memory, and the processor 42 can be a central processing unit or a microcontroller.

[0136] Example 4:

[0137] This embodiment provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the weld grinding method described in Embodiment 1 above.

[0138] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules, or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other memory technologies, CD-ROM (Compact Disc Read-Only Memory), DVD or other optical disc storage, cartridges, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer.

[0139] In summary, the weld grinding method, apparatus, and readable storage medium provided in this embodiment of the invention first acquire the weld to be ground; then, the posture of the grinding robot and the electronic control unit is adjusted so that the base material within the radius range of the grinding wheel on both sides of the weld starting point and the weld to be ground is within the corresponding field of view of the 3D camera; then, the weld data of the entire weld to be ground and the planar data of the base material are acquired by the 3D camera; then, the area to be ground is selected according to the Z-axis information in the weld data, and the flatness information of the base material is calculated according to the planar data of the base material; finally, the area to be ground is collected, and the grinding path is planned and the grinding angle is set in combination with the flatness information of the base material; then, the planned grinding path and the corresponding grinding angle are sent to the robot control cabinet so that the robot control cabinet sends corresponding instructions to control the grinding robot to complete the corresponding weld grinding work. This invention uses 3D machine vision to identify the weld reinforcement on the weld seam to be ground, select the area that needs to be ground, and set the grinding path and angle of the grinding wheel based on the area to be ground and the flatness information of the surrounding base material. This can further improve the grinding accuracy and guide the grinding robot to complete the grinding work on the weld seam without damaging the base material. It solves the problems of low overall grinding accuracy and easy damage to the base material in existing weld grinding methods.

[0140] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of the present invention, and the present invention is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A method of weld grinding, characterized by, The method comprises: acquiring a weld seam to be polished; adjusting the posture of the polishing robot and the electric control unit, so that the weld seam starting point of the weld seam to be polished and the base material within the radius range of the grinding wheel on both sides of the weld seam are within the corresponding field of view range of the 3D camera; acquiring weld seam data and plane data of the base material of the entire weld seam to be polished by the 3D camera; screening the area to be polished according to the Z-axis information in the weld seam data, and calculating the flatness information of the base material according to the plane data of the base material; collecting the area to be polished, and planning the polishing path and setting the polishing angle in combination with the flatness information of the base material; sending the planned polishing path and the corresponding polishing angle to the robot control cabinet, so that the robot control cabinet sends corresponding instructions to control the polishing robot to complete the corresponding weld seam polishing work; the collecting of the area to be polished, the planning of the polishing path and the setting of the polishing angle in combination with the flatness information of the base material specifically comprise: collecting the area to be polished, taking the direction from the weld seam starting point to the ending point as the x-axis direction, the weld seam width as the y-axis, and the weld seam height as the z-axis, and planning the polishing path along the x-axis direction for the collected polishing area, wherein adjacent two polishing areas are connected in a straight line; setting the polishing angle according to the planned polishing path in combination with the flatness information of the base material, wherein the polishing angle can guarantee that the grinding wheel is in the same level as the flatness of the base material in the polishing area; the method further comprises: setting the polishing height of the non-polishing area in the polishing path to improve the Z-axis height; sending the polishing height of the non-polishing area to the robot control cabinet.

2. The method of claim 1, wherein, the acquiring of the weld seam to be polished specifically comprises: judging whether there is an unfinished polishing weld seam on the polishing part; in response to the existence of the unfinished polishing weld seam on the polishing part, acquiring the weld seam to be polished from the unfinished polishing weld seam.

3. The method of claim 1, wherein, The 3D camera is based on a line structured light mode, and before the acquiring of the weld seam data and the plane data of the base material of the entire weld seam to be polished by the 3D camera, the method further comprises: setting the sampling points and sampling intervals of the 3D camera line structured light according to polishing requirements.

4. The method of claim 1, wherein, the acquiring of the weld seam data and the plane data of the base material of the entire weld seam to be polished by the 3D camera specifically comprises: under the condition of ensuring the consistency of the depth of field of the 3D camera, controlling the 3D camera to scan the entire weld seam to be polished and the base material within the radius range of the grinding wheel on both sides of the weld seam by the electric control unit, so as to acquire the weld seam data and the plane data of the base material of the entire weld seam to be polished.

5. The method of claim 1, wherein, the screening of the area to be polished according to the Z-axis information in the weld seam data specifically comprises: screening the Z-axis information in the acquired weld seam data according to the height information of the polishing requirements, screening the coordinates to be polished by the polishing robot, and obtaining the area to be polished.

6. A device for weld grinding, characterized by comprise: a weld seam acquisition module for acquiring a weld seam to be polished; a posture adjustment module connected with the weld seam acquisition module, for adjusting the posture of the polishing robot and the electric control unit, so that the weld seam starting point of the weld seam to be polished and the base material within the radius range of the grinding wheel on both sides of the weld seam are within the corresponding field of view range of the 3D camera; The data acquisition module is connected with the posture adjustment module, and is configured to acquire weld data of the whole weld to be polished and plane data of the base material by using a 3D camera. The screening calculation module is connected with the data acquisition module, and is configured to screen out a region to be polished according to Z-axis information in the weld data, and calculate flatness information of the base material according to the plane data of the base material. The path angle planning module is connected with the screening calculation module, and is configured to collect the region to be polished, and plan a polishing path and set a polishing angle according to the flatness information of the base material. The weld polishing module is connected with the path angle planning module, and is configured to send the planned polishing path and the corresponding polishing angle to a robot control cabinet, so that the robot control cabinet sends corresponding instructions to control a polishing robot to complete corresponding weld polishing work. The path angle planning module specifically includes: A path planning unit configured to collect the region to be polished, and plan a polishing path for the collected polishing region along an x-axis direction from a weld start point to a weld end point, a weld width as a y-axis, and a weld height as a z-axis, wherein two adjacent polishing regions are connected in a straight line. An angle planning unit configured to set a polishing angle according to the planned polishing path and the flatness information of the base material, wherein the polishing angle can ensure that a grinding wheel is in a flatness level with the base material in the polishing region. The device further includes: A polishing height setting module configured to set a polishing height of a non-polishing region passed in a polishing path to improve the Z-axis height. A polishing height sending module configured to send the polishing height of the non-polishing region to the robot control cabinet.

7. A device for weld grinding, characterized by A computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method for polishing a weld as claimed in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium has a computer program stored thereon, wherein the computer program is executed by a processor to implement the method for polishing a weld as claimed in any one of claims 1-5.

Images