Slag removal method, slag removal device and automatic welding and slag removal system

Abstract

The invention provides a slag removal method, a slag removal device and an automatic welding and slag removal system. The slag removing method comprises the steps that a welding slag image of welding slag on a current welding bead is obtained; determining a plurality of welding slag pixel points of welding slag in the welding slag image; determining an initial circle and determining the circle center of the initial circle as an initial point, wherein the initial circle takes one of the welding slag pixel points as the circle center and takes the preset length as the radius; the welding slag pixel points, located on the edge of the welding slag, in the multiple welding slag pixel points are determined as boundary points; for each uncovered boundary point, a corresponding boundary circle is determined, the circle center of the boundary circle is determined as a path point, the boundary circle takes a preset length as the radius and can cover the boundary point, and the circle center of the boundary circle, the boundary point and the initial point are located on the same straight line and located between the boundary point and the initial point; determining a slag removal track according to the initial point and the path point; and the slag removing tool is controlled to move along the slag removing track so as to remove welding slag on the current welding bead, and the slag removing outline of the slag removing tool at least covers a circle with the preset length as the radius.

Description

Technical Field

[0001] The present invention relates to the technical field of slag cleaning, and in particular to a slag cleaning method, a slag cleaning device, and an automated welding and slag cleaning system. Background Art

[0002] In the field of engineering machinery manufacturing, welding technology (such as multi-layer and multi-pass welding) is widely used in the connection processing of large steel structures (such as crane frames, mine car frames, large excavator arms, bucket arms and other large structural parts) and thick plates.

[0003] During the welding process, welding materials are often required to be filled multiple times to form a thick weld structure, thereby ensuring the strength and durability of the welded joint. The non-metallic substances in the welding materials melt at high temperatures, and after cooling and solidification, they will form what is also called welding slag (for example, including oxide scale) on the surface of the weld layer. If it is not removed in time, it will affect the subsequent welding quality, resulting in defects such as slag inclusions, pores or unfused welds inside the weld, and ultimately reduce the mechanical properties and service life of the welded joint. Therefore, slag removal needs to be carried out in a timely manner. Summary of the invention

[0004] In the related art, slag cleaning is mainly carried out manually, which is labor-intensive and has certain personal risks, and the slag cleaning quality and efficiency are low.

[0005] In order to solve the above problems, the embodiments of the present disclosure propose the following solutions.

[0006] According to a first aspect of an embodiment of the present disclosure, a slag cleaning method is provided, comprising: acquiring a slag image of the slag on a current weld bead; determining a plurality of slag pixel points of the slag in the slag image; determining an initial circle and determining the center of the initial circle as an initial point, the initial circle having one of the plurality of slag pixel points as a center and a preset length as a radius; determining a boundary point, the boundary point being a slag pixel point located at an edge of the slag among the plurality of slag pixel points; for each uncovered boundary point, determining a corresponding boundary circle and determining the center of the boundary circle as a path point, the boundary circle having the preset length as a radius and being able to cover the boundary point, the center of the boundary circle being located on the same straight line as the boundary point and the initial point and being located between the boundary point and the initial point; determining a slag cleaning trajectory according to the initial point and the path point; and controlling a slag cleaning tool to move along the slag cleaning trajectory, thereby cleaning the slag on the current weld bead, the slag cleaning contour of the slag cleaning tool at least covering a circle having the preset length as a radius.

[0007] In some embodiments, determining the initial circle includes: determining a corresponding circle for each welding slag pixel point among the multiple welding slag pixel points, the corresponding circle being a circle with the welding slag pixel point as the center and with the preset length as the radius; and determining a corresponding circle among the corresponding circles of the multiple welding slag pixel points that covers the largest number of welding slag pixel points as the initial circle.

[0008] In some embodiments, determining the slag cleaning trajectory according to the initial point and the path point includes: connecting the initial point and the path point in sequence according to a preset direction to obtain the slag cleaning trajectory.

[0009] In some embodiments, the slag cleaning tool is a circular slag cleaning brush, and the radius of the slag cleaning brush is greater than or equal to the preset length; controlling the slag cleaning tool to move along the slag cleaning trajectory includes: controlling the center of the slag cleaning brush to move along the slag cleaning trajectory.

[0010] In some embodiments, obtaining a slag image of welding slag on a current weld bead includes: obtaining a weld bead image of the current weld bead; and extracting the slag image according to the grayscale value of each pixel in the weld bead image.

[0011] In some embodiments, obtaining a slag image of the welding slag on the current weld bead includes: obtaining a weld bead image of the current weld bead; and extracting the slag image according to the RGB value and grayscale value of each pixel point in the weld bead image.

[0012] In some embodiments, the slag image is extracted according to the RGB value and grayscale value of each pixel in the weld image, including: determining the RGB value and grayscale value of each pixel in the weld image; for each pixel in the weld image, calculating a first absolute value of the difference between the R value and the grayscale value, a second absolute value of the difference between the G value and the grayscale value, and a third absolute value of the difference between the B value and the grayscale value; calculating a color change value, the color change value being the sum of the first absolute value, the second absolute value and the third absolute value; and judging whether there is slag in the area corresponding to the pixel according to the color change value.

[0013] In some embodiments, judging whether welding slag exists in the area corresponding to the pixel point according to the color change value includes: judging whether welding slag exists in the area corresponding to the pixel point according to a weighted sum of the color change value and the gray value.

[0014] In some embodiments, obtaining a weld bead image of the current weld bead includes: obtaining a captured image and corresponding point cloud data, the captured image showing at least one weld bead; determining a weld bead boundary based on the corresponding point cloud data; determining a spacing between each weld bead according to a distance between two adjacent weld bead boundaries; and extracting a portion of the captured image corresponding to the weld bead with the largest spacing from the weld bead image as the weld bead image of the current weld bead.

[0015] According to a second aspect of an embodiment of the present disclosure, an embodiment of the present disclosure further provides a slag cleaning device, comprising: a memory; and a processor coupled to the memory, configured to execute the method described in any one of the above embodiments based on instructions stored in the memory.

[0016] According to a third aspect of the embodiments of the present disclosure, the embodiments of the present disclosure also provide an automated welding and slag cleaning system, comprising: a welding device, used to perform a welding operation on a workpiece to be welded to form a weld on the workpiece to be welded, the weld comprising at least one weld bead; a slag cleaning device, comprising a visual mechanism and a slag cleaning tool, the visual mechanism being used to scan the weld to obtain a photographed image, and the slag cleaning tool being used to remove the welding slag generated on the weld bead; a robot, configured to be connected to the welding device or the slag cleaning device; a controller, configured to: control the robot to connect to the welding device to perform welding of the current weld bead on the workpiece to be welded; after the welding of the current weld bead is completed, control the robot to switch to connecting to the slag cleaning device; control the visual mechanism to capture the weld bead image of the current weld bead to obtain the weld slag image of the weld slag on the current weld bead and determine the slag cleaning trajectory according to the method described in any one of the above embodiments; control the robot to drive the slag cleaning tool of the slag cleaning device to move along the slag cleaning trajectory to clean the weld slag on the current weld bead, and the slag cleaning contour of the slag cleaning tool at least covers a circle with the preset length as the radius.

[0017] In some embodiments, the slag cleaning device further comprises a force control device, and the force control device is configured to adjust the pressure and angle of the slag cleaning tool.

[0018] In some embodiments, the controller is further configured to: control the force control device to adjust the pressure and angle of the slag cleaning tool according to the slag cleaning trajectory while the robot drives the slag cleaning tool of the slag cleaning device to move along the slag cleaning trajectory.

[0019] In some embodiments, the robot realizes the switching connection between the slag cleaning device and the welding device through a flange.

[0020] In some embodiments, the controller is further configured to: control the robot to perform multi-layer and multi-pass welding on the workpiece to be welded, wherein, after the welding of the current weld pass is completed and before the welding of the next weld pass, the robot is controlled to drive the slag cleaning tool of the slag cleaning device to move along the slag cleaning track to clean the welding slag on the current weld pass.

[0021] According to a fourth aspect of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an automated welding and slag removal method, comprising: the robot receives a welding instruction; the robot performs welding of the current layer / current pass; the robot switches from being connected to a welding device to being connected to a slag removal device; obtaining a slag image of the welding slag on the current weld pass; determining a slag removal trajectory; performing slag removal; a controller determines whether the welding instruction is completed; if the welding instruction is not completed, the robot switches from being connected to the slag removal device to being connected to the welding device, and performs welding of the next weld pass. If the welding instruction is completed, then the process ends.

[0022] According to a fifth aspect of the embodiments of the present disclosure, the embodiments of the present disclosure further provide a slag cleaning device, comprising a module configured to execute the method described in any one of the above embodiments.

[0023] According to a sixth aspect of an embodiment of the present disclosure, there is provided an automated welding and slag cleaning device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the method described in any one of the above embodiments based on instructions stored in the memory.

[0024] According to a seventh aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, comprising computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method described in any one of the above embodiments.

[0025] According to an eighth aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method described in any one of the above embodiments is implemented.

[0026] In the embodiment of the present disclosure, an automated slag removal method is proposed, which removes the slag by visually extracting the slag area and planning the slag removal path. The proposed slag removal method has the following advantages:

[0027] First, the slag cleaning method of the above embodiment can be automatically executed by the machine, and the operator only needs to monitor and maintain the machine, which greatly reduces the labor intensity of the relevant personnel and improves the safety of the operation. Moreover, the automated execution of the slag cleaning method can achieve high consistency and repeatability of the slag cleaning process, which is conducive to ensuring the quality stability of each batch of welded products. Furthermore, it is also conducive to reducing the impact of manual operation time and human factors on welding quality, reducing the defective rate and rework cost, and reducing the cost of welding processing.

[0028] Second, the above embodiment obtains the welding slag image, identifies the welding slag pixel points, and then plans the slag cleaning path to automate the slag cleaning. Specifically, when planning the slag cleaning path, the initial point and the initial circle are first determined. For the uncovered boundary points, the boundary circle is determined so that the boundary points can be covered by the boundary circle. Since the boundary points are the points on the edge of the welding slag, the boundary points can be covered, which can ensure that the points inside the welding slag are also covered, which is conducive to ensuring that the welding slag can be comprehensively and effectively removed. Therefore, the above embodiment can accurately identify and plan the slag cleaning path, ensure the surface quality of the weld before welding, avoid welding defects such as inclusions, pores and unfusion caused by welding slag residue, thereby improving the overall mechanical properties and service life of the weld.

[0029] Third, in the above embodiment, boundary circles are determined only for uncovered boundary points, and there is no need to determine boundary circles for covered boundary points. Compared with the method of determining boundary circles for all boundary points, the above embodiment reduces the number of boundary circles and correspondingly reduces the number of path points, thereby forming a shorter slag removal path, which can achieve comprehensive removal of welding slag with a shorter slag removal path, and is conducive to improving the efficiency of slag removal.

[0030] Fourth, the above-mentioned embodiment determines the welding slag pixel points through visual processing and automatically plans the slag cleaning path. When the welding slag distribution is uncertain, the actual welding slag distribution can be determined according to the welding slag image obtained by visual processing, and then the slag cleaning path of the slag cleaning tool can be adjusted in real time. It has good versatility and flexibility, and is suitable for welding of workpieces of various shapes and sizes.

[0031] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, 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 disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 It is a schematic flow chart of a slag cleaning method according to some embodiments of the present disclosure.

[0034] Figure 2 is a schematic diagram of a welding slag image according to some embodiments of the present disclosure.

[0035] Figure 3 is a schematic diagram of a local welding slag image according to some embodiments of the present disclosure.

[0036] Figure 4is a schematic diagram of slag removal path planning according to some embodiments of the present disclosure.

[0037] Figure 5 is a schematic diagram of capturing images according to some embodiments of the present disclosure.

[0038] Figure 6 is a schematic diagram of an automated welding and slag removal system according to some embodiments of the present disclosure.

[0039] Figure 7 It is a schematic diagram of the structure of a slag cleaning device according to some embodiments of the present disclosure.

[0040] Figure 8 It is a schematic flow chart of an automated welding and slag cleaning method according to some embodiments of the present disclosure.

[0041] Fig. 9 It is a schematic diagram of the structure of an automated welding and slag cleaning device according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0043] Unless specifically stated otherwise, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0044] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0045] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0046] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0047] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0048] As mentioned above, the slag removal process of structural parts such as cranes and mine car frames mainly relies on manual operation, which is dangerous, labor-intensive, inefficient, and difficult to ensure the quality of slag removal, which can easily cause hidden dangers of welding defects. In addition, the automatic slag removal method in the relevant technology has poor versatility, cannot be flexibly applied to different engineering machinery products, and cannot achieve fast slag removal.

[0049] Based on this, the embodiment of the present disclosure proposes a slag cleaning solution that can be flexibly applied to different engineering machinery products, has high slag cleaning efficiency and can be implemented automatically.

[0050] The slag cleaning scheme proposed in the embodiment of the present disclosure can be applied to various welding methods, such as multi-layer welding, multi-pass welding, multi-layer multi-pass welding, etc.

[0051] Figure 1 It is a schematic flow chart of a slag cleaning method according to some embodiments of the present disclosure. Figure 2 is a schematic diagram of a welding slag image according to some embodiments of the present disclosure. Figure 3 is a partial schematic diagram of a welding slag image according to some embodiments of the present disclosure. Figure 4 is a schematic diagram of slag removal path planning according to some embodiments of the present disclosure.

[0052] like Figure 1 As shown, some embodiments of the present disclosure firstly propose a slag cleaning method that can be automatically performed, including steps S110-S170.

[0053] In step S110, a slag image of the slag on the current weld bead is acquired.

[0054] Weld slag image Figure 2 shown. Figure 3 A local welding slag image is shown. In some embodiments, the weld may include at least one weld bead, especially multiple weld bead, the multiple weld bead are formed in sequence, and the current weld bead is the weld bead that has been welded currently, that is, the latest weld bead formed among the multiple weld bead.

[0055] In step S120, a plurality of welding slag pixel points of welding slag in the welding slag image are determined. Figure 3 As shown, black pixels are used to represent welding slag pixels. Figure 4 The blue dots in the graph are Figure 3 The black pixels in the figure correspond to the black pixels in the figure and are used to represent the welding slag pixels.

[0056] In step S130, an initial circle is determined, and the center of the initial circle is determined as the initial point. Here, the initial circle has one of the plurality of welding slag pixel points as the center and a preset length as the radius.

[0057] like Figure 4As shown, the center of the initial circle may be point B, and point B is the welding slag pixel point where the red “×” is located.

[0058] In step S140, a boundary point is determined, which is a welding slag pixel point located at the edge of the welding slag among the plurality of welding slag pixel points.

[0059] The edge of the welding slag is, for example, a line formed by the outermost part of the welding slag pixel points. Figure 4 As shown in the figure, the black line is the edge of the welding slag. Points G, H and I are all welding slag pixels located at the edge of the welding slag, that is, boundary points.

[0060] As some implementations, the boundary points may be determined by calculating the convex hull, that is, by using a method of enclosing all points with the smallest area.

[0061] In step S150, for each uncovered boundary point, a corresponding boundary circle is determined and the center of the boundary circle is determined as a path point. The boundary circle has a preset length as a radius and can cover the boundary point, and the center of the boundary circle is located on the same straight line as the boundary point and the initial point and is located between the boundary point and the initial point. It should be understood that the radius of the boundary circle is the same as the radius of the initial circle, and both are preset lengths.

[0062] The uncovered boundary points here include boundary points that are not covered by the initial circle and the currently determined boundary circle.

[0063] like Figure 4 As shown, it is assumed that the initial circle is a circle with point B as the center and a preset length as the radius, and no boundary circle has been determined yet. For boundary point G, since boundary point G is not covered by the initial circle and no boundary circle has been determined yet, boundary point G belongs to an uncovered boundary point. It is necessary to determine a boundary circle for boundary point G. The boundary circle should satisfy the requirement of having a preset length as the radius and being able to cover the boundary point G, with the center of the circle being on the same straight line as the boundary point G and the initial point B, and the center of the circle being between the boundary point a and the initial point B. For example, it can be determined that the boundary circle corresponding to boundary point G is a circle with point A as the center and a preset length as the radius. Accordingly, point A is determined as a path point.

[0064] For the boundary point I, since the initial circle and the boundary circle with point A as the center and a preset length as the radius do not cover the boundary point I, the boundary point I is also not covered. The boundary circle corresponding to the boundary point I can be determined based on the requirements for the boundary circle in step S150. For example, the boundary circle corresponding to the boundary point I can be determined to be a circle with point F as the center and a preset length as the radius. Accordingly, point F is determined as a path point.

[0065] For the boundary point H, since the boundary circle with point F as the center and a preset length as the radius covers the boundary point H, the boundary point H does not belong to the uncovered boundary circle, and there is no need to determine the boundary circle corresponding to the boundary point H.

[0066] In step S160, the slag removal trajectory is determined according to the initial point and the path points.

[0067] like Figure 4 As shown, for example, after the initial point B, path point A, path point C, path point D, path point E and path point F are determined in step S130 and step S150, the slag removal trajectory can be determined, for example, Figure 4 The red lines connecting waypoint A, initial point B, waypoint C, waypoint D, waypoint E and waypoint F.

[0068] In step S170, the slag cleaning tool is controlled to move along the slag cleaning track, so as to clean the welding slag on the current weld. Here, the slag cleaning contour of the slag cleaning tool at least covers a circle with a preset length as a radius. The slag cleaning contour of the slag cleaning tool can be circular or other shapes.

[0069] For example, the slag cleaning tool, especially the center of the slag cleaning contour, can be automatically controlled to move along the red line connecting path point A, initial point B, path point C, path point D, path point E and path point F to perform slag cleaning.

[0070] In the above embodiment, an automated slag removal method is proposed, which removes the slag by visually extracting the slag area and planning the slag removal path. The proposed slag removal method has the following advantages:

[0071] First, the slag cleaning method of the above embodiment can be automatically executed by the machine, and the operator only needs to monitor and maintain the machine, which greatly reduces the labor intensity of the relevant personnel and improves the safety of the operation. Moreover, the automated execution of the slag cleaning method can achieve high consistency and repeatability of the slag cleaning process, which is conducive to ensuring the quality stability of each batch of welded products. Furthermore, it is also conducive to reducing the impact of manual operation time and human factors on welding quality, reducing the defective rate and rework cost, and reducing the cost of welding processing.

[0072] Second, the above embodiment obtains the welding slag image, identifies the welding slag pixel points, and then plans the slag cleaning path to automate the slag cleaning. Specifically, when planning the slag cleaning path, the initial point and the initial circle are first determined. For the uncovered boundary points, the boundary circle is determined so that the boundary points can be covered by the boundary circle. Since the boundary points are the points on the edge of the welding slag, the boundary points can be covered, which can ensure that the points inside the welding slag are also covered, which is conducive to ensuring that the welding slag can be comprehensively and effectively removed. Therefore, the above embodiment can accurately identify and plan the slag cleaning path, ensure the surface quality of the weld before welding, avoid welding defects such as inclusions, pores and unfusion caused by welding slag residue, thereby improving the overall mechanical properties and service life of the weld.

[0073] Third, in the above embodiment, boundary circles are determined only for uncovered boundary points, and there is no need to determine boundary circles for covered boundary points. Compared with the method of determining boundary circles for all boundary points, the above embodiment reduces the number of boundary circles and correspondingly reduces the number of path points, thereby forming a shorter slag removal path, which can achieve comprehensive removal of welding slag with a shorter slag removal path, and is conducive to improving the efficiency of slag removal.

[0074] Fourth, the above-mentioned embodiment determines the welding slag pixel points through visual processing and automatically plans the slag cleaning path. When the welding slag distribution is uncertain, the actual welding slag distribution can be determined according to the welding slag image obtained by visual processing, and then the slag cleaning path of the slag cleaning tool can be adjusted in real time. It has good versatility and flexibility, and is suitable for welding of workpieces of various shapes and sizes.

[0075] The determination of the initial circle is described below in conjunction with some embodiments.

[0076] In some embodiments, determining the initial circle includes determining a corresponding circle for each of the plurality of welding slag pixel points, and determining a corresponding circle that covers the largest number of welding slag pixel points among the plurality of welding slag pixel points as the initial circle. Here, the corresponding circle of a welding slag pixel point is a circle with the welding slag pixel point as the center and a preset length as the radius.

[0077] like Figure 4 As shown, the circle with point B as the center and the preset length as the radius is the corresponding circle that covers the largest number of welding slag pixels. Therefore, point B can be determined as the initial point, and the circle with point B as the center and the preset length as the radius can be determined as the initial circle.

[0078] In the above embodiment, the corresponding circle covering the largest number of welding slag pixels among the corresponding circles of the plurality of welding slag pixels is determined as the initial circle. Therefore, the initial circle can cover as many welding slag pixels as possible, which is beneficial to reducing the number of uncovered welding slag pixels, thereby helping to reduce the length of the slag cleaning path and improve the slag cleaning efficiency.

[0079] As some implementations, the initial circle may be determined using the following formula.

[0080] c1=argmax{q∈P∣||qp||≤r}

[0081] Where c1 is the center of the initial circle, i.e., the initial point. P represents the set of welding slag pixels, such as the set of all black pixels in the binary image, P = {(x i ,y i )|i=1,2,…,N}. (x i ,y i ) represents the coordinates of the ith welding slag pixel point, N is a natural number. q and p are both welding slag pixel points in the set P, and r is a preset length.

[0082] The meaning of the above formula is to select a point p in the point set P so that the circle with p as the center and a radius of a preset length r covers the largest number of welding slag pixel points q, and use point p as the center c1 of the initial circle.

[0083] The determination of the boundary circle is described below in conjunction with some embodiments.

[0084] In some embodiments, the boundary circle can just cover the boundary point, that is, the boundary point is located on the circumference of the boundary circle, which is helpful to reduce the length of the slag cleaning path as much as possible and improve the slag cleaning efficiency.

[0085] In some embodiments, when determining the boundary circle, the boundary circle corresponding to the boundary point is determined in the order of the distance from the boundary point to the initial point from far to near.

[0086] For example, the distance between boundary point I and initial point B is farther than the distance between boundary point H and initial point B. The boundary circle of boundary point I can be determined first, and then the boundary circle of boundary point H can be determined. After the boundary circle of boundary point I is determined, since the boundary circle of boundary point I has covered boundary point H, boundary point H does not belong to the uncovered boundary points, and therefore, there is no need to determine the boundary circle of boundary point H again.

[0087] Since the boundary circles of boundary points farther from the initial point may be able to cover some boundary points closer to the initial point, in the above embodiment, the boundary circles are determined in order of the distance from the boundary points to the initial point from far to near, which is beneficial to reducing the number of boundary circles generated in the process of boundary circle determination, thereby reducing the time required for slag cleaning path planning and improving slag cleaning efficiency.

[0088] In some embodiments, the center of the boundary circle may be determined using the following formula.

[0089]

[0090] Among them, c jis the center of the boundary circle, c1 is the center of the initial circle, r is the preset length, b i is the i-th uncovered boundary point.

[0091] The meaning of the above formula is that for each uncovered boundary point b i , by using the vector translation method, the circle with the center c1 of the initial circle as the center and the preset length r as the radius is translated so that the translated circle can just cover the boundary point b i , the circle after translation is the boundary circle.

[0092] In other words, by setting the center of the bounding circle c j The position of c j The circle with the center at r and the radius at r can just cover the boundary point b. i , and minimize the c j The additional coverage area brought by a circle with a center of r and a preset length r as the radius. Here, minimizing the additional coverage area can mean maximizing the overlap area between the boundary circle and the initial circle.

[0093] In some embodiments, the slag cleaning trajectory is determined based on the initial point and the path points, including connecting the initial point and the path points in sequence in a preset direction, such as from left to right or from right to left, to obtain the slag cleaning trajectory.

[0094] For example, Figure 4 As shown, if the preset direction is the left-right direction, that is, the slag cleaning tool is restricted to move along the left-right direction, the initial point B, path point A, path point C, path point D, path point E and path point F can be connected in sequence from left to right or from right to left, rather than from top to bottom or from bottom to top.

[0095] In actual scenarios, slag cleaning tools are often installed on robots, and the robots move on tracks, so the movement of slag cleaning tools is restricted by the movement direction of the robot on the track. Therefore, the initial point and path points can be connected in sequence according to the movement direction of the robot on the track, which is conducive to ensuring that the slag cleaning path and the movement direction of the robot on the track are consistent, thereby improving the slag cleaning efficiency.

[0096] In some embodiments, the slag cleaning tool is a circular slag cleaning brush, and the radius of the slag cleaning brush is greater than or equal to a preset length. Controlling the slag cleaning tool to move along the slag cleaning track includes: controlling the center of the slag cleaning brush to move along the slag cleaning track.

[0097] For example, if the radius of a circular slag cleaning brush is 10 mm, the preset length can be set to 10 mm or 9 mm, etc.

[0098] The following describes a method for planning a slag removal path in conjunction with a specific embodiment. The formula can be referred to in the previous description and will not be repeated here.

[0099] (1) The coordinates of the welding slag pixels are extracted according to the visually recognized welding slag position, and the set of welding slag pixels P is determined as follows: i ,y i )|i=1,2,…,N}.

[0100] (2) Determine the center of the initial circle: Select a point p from the set P of welding slag pixels, and calculate the number of covered points of a circle with p as the center and a radius of a preset length r, and select the point p with the largest number of covered points as the initial center c1.

[0101] c1=argmax{q∈P∣||qp||≤r}

[0102] (3) Determine the center of the boundary circle: For each uncovered boundary point b i , by adjusting the position of c1, find a new center c j , so that the new center can just cover this boundary point b i , and try to minimize the additional coverage area brought by the new center of the circle.

[0103]

[0104] Where c1 is the center of the starting point, b i is the current boundary point.

[0105] (4) Path planning: Repeat step 3 to determine the center position of the circle covering all welding slag areas, and connect the initial point and path points in sequence from left to right or from right to left to form a slag removal path.

[0106] In some embodiments, obtaining a slag image of the slag on the current weld bead includes obtaining a weld bead image of the current weld bead; and extracting the slag image according to the grayscale value of each pixel in the weld bead image.

[0107] In some embodiments, obtaining a slag image of the slag on the current weld bead includes obtaining a weld bead image of the current weld bead; and extracting the slag image according to the RGB value and grayscale value of each pixel in the weld bead image.

[0108] As some implementation methods, a welding slag image is extracted according to the RGB value and grayscale value of each pixel in the welding bead image, including: determining the RGB value and grayscale value of each pixel in the welding bead image; for each pixel in the welding bead image, calculating the first absolute value of the difference between the R value and the grayscale value, the second absolute value of the difference between the G value and the grayscale value, and the third absolute value of the difference between the B value and the grayscale value; calculating the color change value, the color change value is the sum of the first absolute value, the second absolute value and the third absolute value; and judging whether there is welding slag in the area corresponding to the pixel according to the color change value.

[0109] For example, the color change value may be determined using the following formula.

[0110] Δ=|r(x,y)-img(x,y)|+|g(x,y)-img(x,y)|+|b(x,y)-img(x,y)|

[0111] Among them, Δ is the color change value, r(x,y) represents the R value of the pixel with coordinates (x,y), g(x,y) represents the G value of the pixel with coordinates (x,y), b(x,y) represents the B value of the pixel with coordinates (x,y), and img(x,y) represents the grayscale value of the pixel with coordinates (x,y).

[0112] The R value, G value, and B value can reflect the components of the red, green, and blue channels of an image, and the gray value can reflect the brightness of an image. The R value, G value, B value, and gray value of black, white, or gray are close. The R value, G value, and B value of colors (such as red, blue, etc.) are generally not close, and at least one of R, G, and B is significantly different from the gray value. Therefore, the color change values ​​of black, white, and gray are all low, while the color change values ​​of color images are high. Colors can be distinguished from black, white, and gray using the color change value.

[0113] There are usually rusted parts in the weld bead, and the color of the rusted parts is usually yellow or brown, that is, colorful. It is not necessary to treat the rusted parts when cleaning the slag. In the related art, the rusted parts may be identified as welding slag when identifying welding slag.

[0114] In the above embodiment, the concept of color change value is proposed, and the color change value is defined as the sum of the first absolute value of the difference between the R value and the grayscale value, the second absolute value of the difference between the G value and the grayscale value, and the third absolute value of the difference between the B value and the grayscale value. This can effectively identify the colored rusted parts, making it easier to exclude the rusted parts when identifying the welding slag, thereby improving the accuracy of slag cleaning.

[0115] In some embodiments, judging whether welding slag exists in the area corresponding to the pixel point according to the color change value includes: judging whether welding slag exists in the area corresponding to the pixel point according to the weighted sum of the color change value and the gray value.

[0116] The weld image not only shows the welding slag, but also the workpiece used for welding. Considering that welding slag is generally black and the workpiece is generally gray, the grayscale values ​​of the two are quite different, and the welding slag and the workpiece can be distinguished by the grayscale value. Judging whether there is welding slag in the area corresponding to the pixel point based on the weighted sum of the color change value and the grayscale value is helpful to avoid the interference of the rusted part and the workpiece on the welding slag identification, so as to identify the welding slag more accurately.

[0117] For example, the welding slag can be determined based on the following formula.

[0118]

[0119] Among them, 255 represents white, 0 represents black, ω is the set color change coefficient, img(x,y)+ωΔ is the weighted sum of the color change value and the gray value, and thresh is the preset threshold. mask(x,y) is used to extract the image of the welding slag position using the threshold segmentation method.

[0120] In some embodiments, the color change coefficient ω may be set to 0.33, and the preset threshold thresh may be set to 80.

[0121] Using the mask(x,y) function, the pixels corresponding to the welding slag can be set to black, and the pixels corresponding to the workpiece and the rusted part can be set to white. In other words, the black area in the image obtained after threshold segmentation represents the welding slag area.

[0122] In the above embodiment, by comparing the weighted sum of the color change value and the gray value img(x,y)+ωΔ with the preset threshold value thresh, if the weighted sum of the pixel point is greater than the preset threshold value, the pixel point is considered to be non-welding slag (such as a workpiece or a rusted part); otherwise, the pixel point is considered to be welding slag. In addition, the color of the pixel point is set based on the result of the threshold segmentation, the welding slag is set to black, and the non-welding slag is set to white, which is convenient for the subsequent planning of the slag removal path.

[0123] Figure 5 is a schematic diagram of capturing images according to some embodiments of the present disclosure.

[0124] In some embodiments, obtaining a weld bead image of a current weld bead includes: obtaining a captured image and corresponding point cloud data, the captured image showing at least one weld bead; determining weld bead boundaries L1, L2...LN based on the corresponding point cloud data; determining a spacing D1, D2...Dn-1 of each weld bead based on a distance between two adjacent weld bead boundaries; and extracting a portion of the captured image corresponding to the weld bead with the largest spacing from the weld bead image as the weld bead image of the current weld bead.

[0125] like Figure 5As shown, at least 4 welds are shown in the captured image, L1, L2, L3, L4, and L5 are weld boundaries, P1, P2, P3, P4, and P5 are points on L1, L2, L3, L4, and L5, respectively, and P1, P2, P3, P4, and P5 are located at the same horizontal position. The spacing between L1 and L2 is the distance between P1 and P2, that is, D1. The spacing between L2 and L3 is the distance between P2 and P3, that is, D2. The spacing between L3 and L4 is the distance between P3 and P4, that is, D3. The spacing between L4 and L5 is the distance between P4 and P5, that is, D4.

[0126] The position index I with the maximum distance can be calculated using the following formula.

[0127] I=index(max{D1,D2,…,Dn-1})

[0128] Where: max{} is used to find the maximum distance, and index() is the function for extracting the index position.

[0129] Since D4 is the largest among D1, D2, D3 and D4, I=4 can be obtained from the above formula, so the partial captured image corresponding to the weld bead between L4 and L5 is determined as the weld bead image of the current weld bead.

[0130] Considering that in multi-pass welding (including multi-layer multi-pass welding), there are multiple welds at the same time, and the current weld will partially cover the previous weld, so the current weld is the widest. In the above embodiment, the weld with the largest spacing in the captured image is determined as the current weld, which is conducive to accurately identifying the current weld, and then completing the slag removal of the current weld in time, avoiding the impact on subsequent welding, and improving the welding quality.

[0131] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0132] Figure 6 is a schematic diagram of an automated welding and slag removal system according to some embodiments of the present disclosure. Figure 7 It is a schematic diagram of the structure of a slag cleaning device according to some embodiments of the present disclosure.

[0133] like Figure 6 As shown, the automatic welding and slag removal system includes a welding device 4, a slag removal device 5, a robot 2 and a controller (not shown in the figure). The automatic welding and slag removal system can be used to weld and remove slag from a workpiece 6 to be welded.

[0134] The welding device 4 is used to perform a welding operation on a workpiece 6 to form a weld seam on the workpiece 6, and the weld seam includes at least one weld bead. The welding device 4 may include, for example, a welding gun.

[0135] The slag removal device 5 includes a visual mechanism 53 and a slag removal tool 55. The visual mechanism 53 is configured to scan the weld to obtain a captured image and optional point cloud data, such as three-dimensional point cloud data. The slag removal tool 55 is used to remove the welding slag generated on the weld. The slag removal tool 55 may include a grinding tool, which may include a wire brush or a grinding wheel. The slag removal profile of the slag removal tool 55 at least covers a circle with a preset length as a radius.

[0136] The robot 2 is configured to be connectable to the welding device 4 or the slag removal device 5. The robot 2 includes, for example, a six-axis robot.

[0137] The controller is configured to: control the robot 2 to connect with the welding device 4 to perform welding of the current weld bead on the workpiece 6 to be welded; after the welding of the current weld bead is completed, control the robot 2 to switch to connect with the slag cleaning device 5; control the visual mechanism 53 to capture the weld bead image of the current weld bead to obtain the weld slag image of the weld slag on the current weld bead and determine the slag cleaning trajectory according to the method described in any one of the above embodiments; control the robot 2 to drive the slag cleaning tool 55 of the slag cleaning device 5 to move along the slag cleaning trajectory to clean the weld slag on the current weld bead.

[0138] like Figure 1 As described in the illustrated embodiments, the above embodiments have the advantages of reducing the labor intensity of relevant personnel, improving the safety of operations, enhancing the slag cleaning quality, improving the slag cleaning efficiency, high consistency and repeatability of the slag cleaning process, and good versatility and flexibility.

[0139] In addition, in the related art, in order to protect personal safety, when the slag cleaning work is completed manually, it is often necessary to stop the machine, which increases the processing time, reduces the overall welding efficiency, and increases the cost of welding processing. In the above embodiment, by automatically switching the welding device 4 and the slag cleaning device 5, welding and slag cleaning operations can be performed alternately without stopping the machine, which significantly reduces the waiting time between the welding process and the slag cleaning process, which is conducive to improving the overall welding efficiency.

[0140] In some embodiments, the robot 2 realizes the switching connection between the slag cleaning device 5 and the welding device 4 through a quick-change device 51 (e.g., a flange). The quick-change device 51 may, for example, include a flange mounted on the robot 2, a flange mounted on the welding device 4, and a flange mounted on the slag cleaning device 5. The use of a quick-change device to realize the rapid switching between the welding process and the slag cleaning process is conducive to reducing the waiting time between the welding and slag cleaning processes and improving the overall welding efficiency.

[0141] In addition, in the related art, welding and slag removal are performed at two different workstations. In the above embodiment, the robot 2 can complete welding and slag removal at the same workstation through the quick change device 51, which is beneficial to reduce the space required for welding and slag removal and save space costs.

[0142] In some embodiments, the automated welding and slag removal system may further include a bracket 3. The bracket 3 is used to store the welding device 4 and the slag removal device 5.

[0143] In some embodiments, the automated welding and slag removal system may further include a ground rail 1. The robot 2 is mounted on the ground rail 1 to enable the robot 2 to move laterally so as to cover the operating range of the workpiece 6 to be welded.

[0144] In some embodiments, the automated welding and slag removal system may further include a positioner 7 .

[0145] In some embodiments, Figure 7 As shown, the slag cleaning device 5 further includes a force control device 52, which is configured to adjust the pressure and angle of the slag cleaning tool 55, which is beneficial to improving the slag cleaning quality.

[0146] As some implementations, the force control device 52 is, for example, a flexible force control device. The flexible force control system can adjust the pressure and angle of the wire brush in real time according to the actual weld shape and slag thickness to ensure that the slag is removed thoroughly without damaging the weld.

[0147] In some embodiments, the controller is further configured to control the force control device 52 to adjust the pressure and angle of the slag cleaning tool 55 according to the slag cleaning trajectory while the robot 2 drives the slag cleaning tool 55 of the slag cleaning device 5 to move along the slag cleaning trajectory.

[0148] In some embodiments, the slag cleaning device 5 further includes a main shaft 54, and the main shaft 54 ​​is used to connect the slag cleaning tool 55 to realize the rotation of the slag cleaning tool.

[0149] In some embodiments, the controller is further configured to control the robot 2 to perform multi-layer and multi-pass welding on the workpiece 6 to be welded, wherein after the welding of the current weld pass is completed and before the welding of the next weld pass, the robot 2 is controlled to drive the slag cleaning tool 55 of the slag cleaning device 5 to move along the slag cleaning track to clean the welding slag on the current weld pass. In other words, slag cleaning is performed once each time a welding pass is completed.

[0150] Figure 8 It is a schematic flow chart of an automated welding and slag cleaning method according to some embodiments of the present disclosure. Figure 8 The method shown can be used Figure 6 The automated welding and slag removal system is realized.

[0151] Step S810: The robot 2 receives a welding instruction. The welding instruction is, for example, a multi-layer multi-pass welding instruction. In some embodiments, the welding instruction is issued by a controller and includes specific welding parameters and welding paths.

[0152] Step S820: The robot 2 performs welding of the current layer / current pass. At this time, the robot 2 is connected to the welding device 4 (such as a welding gun), and the robot 2 starts the welding device 4 to perform the welding operation of the current pass according to the predetermined welding path.

[0153] Step S830 : the robot 2 switches from being connected to the welding device 4 to being connected to the slag cleaning device 5 . For example, the robot 2 can be switched by the quick-change device 51 .

[0154] Step S840: Acquire a slag image of the welding slag on the current weld bead. As some implementation methods, the visual mechanism 53 of the slag cleaning device 5 can be used to collect the point cloud and image data of the weld, and process them to acquire the slag image of the welding slag on the current weld bead. For example, the robot 2 starts the visual mechanism 53, scans the weld, and acquires the point cloud and image data of the weld surface. The weld bead boundary is extracted based on the point cloud data, and the spacing of each weld bead is determined based on the distance between the boundaries of two adjacent weld beads; the partial captured image corresponding to the weld bead with the largest spacing is determined as the weld bead image of the current weld bead, and the threshold segmentation method introduced above is used to identify the welding slag in the current weld bead. The welding slag image is as follows: Figure 2 and 3 shown.

[0155] Step S850: Determine the slag removal trajectory. For example, Figure 4 The slag removal trajectory planning method shown determines the initial point and the path point, and then obtains the slag removal trajectory.

[0156] Step S860: Perform slag removal. After the slag removal planning is completed, the control robot 2 drives the slag removal tool 55 of the slag removal device 5 to move along the slag removal track to remove the welding slag on the current weld. In some embodiments, the force control device 52 can be used to adjust the pressure and angle of the slag removal tool 55.

[0157] Step S870: The controller determines whether the welding instruction is completed. For multi-layer multi-pass welding, it includes multi-layer welding, and each layer of welding includes multiple passes of welding. Therefore, the completion of the welding instruction of multi-layer multi-pass welding can refer to the completion of the welding of the last pass of the last layer. If the welding instruction is not completed, the robot 2 can switch from being connected to the slag cleaning device to being connected to the welding device, and continue to execute step S820 to weld the next weld pass.

[0158] If the welding task is completed, step S880 is executed to end the welding. At this time, the robot 2 can move the welding device 4 and the slag removal device 5 to a specific position, and return itself to a specific position (eg, an initial position) to wait for the next welding instruction.

[0159] The above-mentioned embodiment provides an automated welding and slag removal composite method, which can complete welding and slag removal efficiently and with high quality, and is particularly suitable for multi-layer and multi-pass welding and inter-layer slag removal scenarios of engineering machinery cranes and mining car frames.

[0160] The embodiment of the present disclosure also provides a slag cleaning device, including a module configured to execute the method described in any one of the above embodiments.

[0161] For example, the slag cleaning device includes an acquisition module, a first determination module, a second determination module, a third determination module, a fourth determination module, a fifth determination module and a control module.

[0162] The acquisition module is configured to acquire a slag image of the slag on the current weld bead.

[0163] The first determination module is configured to determine a plurality of welding slag pixel points of the welding slag in the welding slag image.

[0164] The second determination module is configured to determine an initial circle and determine the center of the initial circle as an initial point, wherein the initial circle has one of the plurality of welding slag pixel points as its center and a preset length as its radius.

[0165] The third determination module is configured to determine a boundary point, where the boundary point is a welding slag pixel point located at an edge of the welding slag among the multiple welding slag pixel points.

[0166] The fourth determination module is configured to determine, for each uncovered boundary point, a corresponding boundary circle and determine the center of the boundary circle as a path point, the boundary circle having the preset length as a radius and being able to cover the boundary point, the center of the boundary circle being on the same straight line as the boundary point and the initial point and being between the boundary point and the initial point.

[0167] The fifth determination module is configured to determine a slag removal trajectory according to the initial point and the path point.

[0168] The control module is configured to control the slag cleaning tool to move along the slag cleaning trajectory so as to clean the welding slag on the current weld bead, and the slag cleaning contour of the slag cleaning tool at least covers a circle with the preset length as the radius.

[0169] Fig. 9 It is a schematic diagram of the structure of an automated welding and slag cleaning device according to some embodiments of the present disclosure.

[0170] like Fig. 9As shown, the automated welding and slag removal device 900 includes a memory 910 and a processor 920 coupled to the memory 910 , and the processor 920 is configured to execute the method of any one of the aforementioned embodiments based on the instructions stored in the memory 910 .

[0171] The memory 910 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0172] The automated welding and slag removal device 900 may also include an input / output interface 930, a network interface 940, a storage interface 950, etc. The input / output interface 930, the network interface 940, the storage interface 950, and the memory 910 and the processor 920 may be connected, for example, via a bus 960. The input / output interface 930 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 940 provides a connection interface for various networked devices. The storage interface 950 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0173] The embodiments of the present disclosure further provide a computer-readable storage medium, comprising computer program instructions, which implement the method of any one of the above embodiments when executed by a processor.

[0174] The embodiment of the present disclosure further provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, any one of the above-mentioned methods is implemented.

[0175] So far, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0176] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0177] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present disclosure. It should be understood that the functions specified in one or more processes in the flowchart and / or one or more blocks in the block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions specified in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0178] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0179] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0180] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A slag cleaning method, include: Get the slag image of the slag on the current weld bead; Determine a plurality of welding slag pixel points of welding slag in the welding slag image; Determine an initial circle and determine the center of the initial circle as an initial point, wherein the initial circle has one of the plurality of welding slag pixel points as a center and a preset length as a radius; Determine a boundary point, where the boundary point is a welding slag pixel point located at the edge of the welding slag among the plurality of welding slag pixel points; For each uncovered boundary point, determine a corresponding boundary circle and determine the center of the boundary circle as a path point, the boundary circle has the preset length as a radius and can cover the boundary point, and the center of the boundary circle is located on the same straight line as the boundary point and the initial point and is located between the boundary point and the initial point; Determine a slag removal trajectory according to the initial point and the path point; as well as The slag cleaning tool is controlled to move along the slag cleaning track, so as to clean the welding slag on the current weld bead, and the slag cleaning contour of the slag cleaning tool at least covers a circle with the preset length as the radius.

2. The method according to claim 1, in, Determine the initial circle, including: Determine a corresponding circle for each welding slag pixel point among the plurality of welding slag pixel points, the corresponding circle being a circle with the welding slag pixel point as a center and the preset length as a radius; Among the corresponding circles of the plurality of welding slag pixel points, a corresponding circle that covers the largest number of welding slag pixel points is determined as the initial circle.

3. The method according to claim 1 or 2, in, Determining a slag removal trajectory according to the initial point and the path point includes: The initial point and the path points are connected in sequence according to a preset direction to obtain the slag removal trajectory.

4. The method according to any one of claims 1 to 3, in, The slag cleaning tool is a circular slag cleaning brush, and the radius of the slag cleaning brush is greater than or equal to the preset length; Controlling the slag cleaning tool to move along the slag cleaning track includes: controlling the center of the slag cleaning brush to move along the slag cleaning track.

5. The method according to any one of claims 1 to 4, in, Get the slag image of the slag on the current weld bead, including: Acquire a weld bead image of the current weld bead; and The welding slag image is extracted according to the gray value of each pixel in the weld bead image.

6. The method according to any one of claims 1 to 4, in, Get the slag image of the slag on the current weld bead, including: Acquire a weld bead image of the current weld bead; and The welding slag image is extracted according to the RGB value and the grayscale value of each pixel in the welding bead image.

7. The method according to claim 6, in, Extracting the welding slag image according to the RGB value and the gray value of each pixel point in the welding bead image includes: Determine the RGB value and grayscale value of each pixel in the weld bead image; For each pixel point in the weld bead image, a first absolute value of the difference between the R value and the grayscale value, a second absolute value of the difference between the G value and the grayscale value, and a third absolute value of the difference between the B value and the grayscale value are calculated; a color change value is calculated, where the color change value is the sum of the first absolute value, the second absolute value, and the third absolute value; and whether there is welding slag in the area corresponding to the pixel point is determined according to the color change value.

8. The method according to claim 7, in, Judging whether there is welding slag in the area corresponding to the pixel point according to the color change value includes: It is determined whether welding slag exists in the area corresponding to the pixel point according to the weighted sum of the color change value and the gray value.

9. The method according to any one of claims 5 to 8, in, Acquiring a weld bead image of the current weld bead, comprising: Acquire a captured image and corresponding point cloud data, wherein the captured image shows at least one weld bead; Determining a weld bead boundary based on the corresponding point cloud data; The spacing of each weld bead is determined according to the distance between the boundaries of two adjacent weld bead; A partial captured image corresponding to the weld bead with the largest spacing is extracted from the weld bead image as the weld bead image of the current weld bead.

10. A slag cleaning device, include: Memory; as well as A processor coupled to the memory, configured to execute the method according to any one of claims 1 to 9 based on instructions stored in the memory.

11. An automated welding and slag removal system, include: A welding device, used for performing a welding operation on a workpiece to be welded to form a weld on the workpiece to be welded, wherein the weld includes at least one weld bead; A slag cleaning device, comprising a visual mechanism and a slag cleaning tool, wherein the visual mechanism is used to scan the weld to obtain a photographic image, and the slag cleaning tool is used to remove the welding slag generated on the weld; A robot configured to be connectable to the welding device or the slag removal device; The controller is configured as: Controlling the robot to connect with the welding device to perform welding of a current weld bead on the workpiece to be welded; After the welding of the current weld is completed, controlling the robot to switch to connect with the slag cleaning device; Controlling the visual mechanism to capture a weld bead image of the current weld bead to obtain a weld slag image of the weld slag on the current weld bead and determining a slag removal trajectory according to any one of the methods of claims 1-9; The robot is controlled to drive the slag cleaning tool of the slag cleaning device to move along the slag cleaning track to clean the welding slag on the current weld bead, and the slag cleaning contour of the slag cleaning tool at least covers a circle with the preset length as the radius.

12. The system according to claim 11, in, The slag cleaning device further comprises a force control device, which is configured to adjust the pressure and angle of the slag cleaning tool.

13. The system according to claim 12, in, The controller is further configured to control the force control device to adjust the pressure and angle of the slag cleaning tool according to the slag cleaning trajectory while the robot drives the slag cleaning tool of the slag cleaning device to move along the slag cleaning trajectory.

14. A system according to any one of claims 11 to 13, in, The robot realizes the switching connection between the slag cleaning device and the welding device through the flange.

15. The system according to any one of claims 11 to 14, in, The controller is also configured to: The robot is controlled to perform multi-layer and multi-pass welding on the workpiece to be welded, wherein after the welding of the current weld pass is completed and before the welding of the next weld pass, the robot is controlled to drive the slag cleaning tool of the slag cleaning device to move along the slag cleaning track to clean the welding slag on the current weld pass.

Images