Welding seam positioning method, medium and equipment

Abstract

The invention relates to a welding seam positioning method, a medium and equipment, and the method comprises the steps: obtaining a to-be-welded workpiece surface image, obtaining workpiece contour point clouds, obtaining the curvature of each workpiece contour point cloud, judging whether the curvature is greater than a set curvature threshold value, if yes, keeping the curvature, if not, removing the curvature, obtaining an initial welding seam point, and carrying out the clustering and straight-through filtering of the initial welding seam point, and a plurality of welding seam area point clouds are obtained, linear equations are fitted for all the welding seam area point clouds, and end points of points in all the linear equations are obtained and serve as final welding seam points. The problems that in the prior art, the welding efficiency is low, the welding precision is insufficient, and the welding quality is insufficient when a workpiece displaces or deforms are solved.

Description

Technical Field

[0001] The invention relates to the technical field of automated welding, and in particular to a weld positioning method, medium and equipment. Background Art

[0002] In the field of boiler manufacturing, membrane wall tube screen is a key piping structure that enhances boiler performance by improving heat exchange efficiency and providing reliable thermal protection. In the traditional membrane wall tube screen manufacturing process, the welding workload is huge, especially the need to weld flat steel between light tubes. Each flat steel requires four welds, which is not only inefficient but also requires high manual spot welding. Although the introduction of MPM (Membrane Panel Machine) membrane wall automatic welding equipment has improved welding efficiency to a certain extent, there are still some shortcomings. The main problem is that the MPM equipment requires manual adjustment of the welding gun position to ensure precise alignment between the flat steel and the pipe, and the welding gun position is fixed, which cannot adapt to the slight deformation or displacement of the pipe during the welding process, resulting in unsatisfactory welding results.

[0003] Therefore, how to improve it is a technical problem that needs to be solved urgently in this field. Summary of the invention

[0004] Based on this, the purpose of this application is to provide a weld positioning method, medium and equipment to solve at least one technical problem mentioned in the above background technology.

[0005] In a first aspect, the present application provides a weld positioning method, comprising:

[0006] Acquire the surface image of the workpiece to be welded and obtain the workpiece contour point cloud;

[0007] Obtain the curvature of each workpiece contour point cloud and determine whether it is greater than the set curvature threshold. If so, retain it; if not, remove it to obtain the initial weld point.

[0008] Clustering and straight-through filtering are performed on the initial weld points to obtain several weld area point clouds;

[0009] Fit the straight line equation to the point cloud of each weld area, and obtain the endpoints of the points inside the straight line equation as the current weld point.

[0010] Furthermore, the specific steps of obtaining the initial weld point include:

[0011] Acquire several adjacent point clouds of each workpiece contour point cloud, fit the curve, and construct the curve equation corresponding to each workpiece contour point cloud;

[0012] Obtain the curvature of the contour point cloud of each workpiece according to the curve equation, and determine whether it is greater than the preset curvature threshold. If so, retain the corresponding point cloud; if not,剔除 the corresponding point cloud to obtain the initial weld points.

[0013] Further, the steps of obtaining the curvature of the contour point cloud of each workpiece according to the curve equation include:

[0014] z i = ax i 2 + bx i + c 2 - 1

[0015] where z i is the curve equation corresponding to the i-th point in the contour point cloud of the workpiece, 0 < i ≤ N, N is the number of points in the contour point cloud of the workpiece, a, b, and c are coefficients, and x i is the coordinate of the i-th point in the contour point cloud of the workpiece on the x-axis.

[0016]

[0017] where k i is the curvature corresponding to the i-th point in the contour point cloud of the workpiece, and z i is the curve equation corresponding to the i-th point in the contour point cloud of the workpiece, 0 < i ≤ N, N is the number of points in the contour point cloud of the workpiece.

[0018] Further, the steps of clustering and passing through filtering on the initial weld points to obtain several weld region point clouds include:

[0019] Obtain the z-axis coordinates of all the initial weld points and arrange them in the set order;

[0020] Obtain the first set number of initial weld points, calculate the average value of their z-axis coordinates to determine the first filtering range;

[0021] Perform passing through filtering on the initial weld points according to the first filtering range to obtain updated weld points;

[0022] Cluster the updated weld points to obtain several point cloud clusters, and obtain the coordinate extreme values of the points in each point cloud cluster to determine the second filtering range corresponding to each point cloud cluster;

[0023] Perform passing through filtering on each corresponding point cloud cluster according to the second filtering range to obtain several weld region point clouds.

[0024] Further, the steps of obtaining the current weld points include:

[0025] S41: Set a straight line model, and respectively select several points from each weld region point cloud to fit and determine the parameters of the straight line model to obtain several current straight line equations;

[0026] S42: determining the current inner point according to the distance between each point in the point cloud of each weld area and the current straight line equation, and counting the number of the current inner points;

[0027] S43: Determine whether the iteration end condition is met, if so, execute step S44, if not, return to step S41;

[0028] S44: taking the point cloud corresponding to the maximum current number of inner points as the actual inner points, and performing straight line fitting to obtain the final straight line equation corresponding to the point cloud of each weld area;

[0029] S45: Projecting the actual inner point to the corresponding final straight line equation to obtain the endpoint of the actual inner point, which is the current weld point corresponding to the point cloud of each weld area.

[0030] Furthermore, it also includes:

[0031] Determine whether the distance between the current weld point and the reference point is greater than the distance threshold. If so, take the reference point as the final weld point; if not, take the current weld point as the final weld point, and update the reference point based on the current weld point and / or the previous weld point.

[0032] Further, the step of updating the reference point includes:

[0033] Take the current weld point as the new reference point;

[0034] Alternatively, a weight may be set for each weld point according to the chronological order, and a new reference point may be calculated according to the weight based on the current weld point and a number of previous weld points.

[0035] In a second aspect, the present application provides a weld automatic welding method, comprising:

[0036] P1: Control the workpiece to be welded to move in the set direction;

[0037] P2: Obtain the final weld point on the surface of the workpiece to be welded by any of the above methods;

[0038] P3: Weld the workpiece to be welded according to the final welding point;

[0039] P4: Determine whether welding is completed. If so, end welding. If not, return to step P1.

[0040] In a third aspect, the present application further provides a computer storage medium storing an executable program code; the executable program code is used to execute the weld positioning method described in any one of the first aspect or the weld automatic welding method described in any one of the second aspect.

[0041] In a fourth aspect, the present application also provides a terminal device comprising a memory and a processor; the memory stores a program code that can be executed by the processor; the program code is used to execute the weld positioning method described in any one of the first aspect or the weld automatic welding method described in any one of the second aspect.

[0042] The present invention provides a weld positioning method, medium and device, which obtains the surface image of the workpiece to be welded, obtains the workpiece contour point cloud, then obtains the curvature of each point cloud, and determines whether it is greater than the set curvature threshold. If so, it is retained, if not, it is eliminated, and the initial weld point is obtained to improve the welding accuracy and efficiency. The initial weld point is then clustered and through-filtered to obtain a number of weld area point clouds, and finally the straight line equation is fitted to each weld area point cloud, and the endpoints of the points in each straight line equation are obtained as the final weld point. The weld points on the workpiece surface are obtained by scanning the workpiece to be welded in real time, so as to avoid the reduction of welding accuracy due to deformation displacement or other influences of the workpiece during the welding process, and improve the welding quality. The existing technology solves the problems of low welding efficiency, insufficient welding accuracy, and insufficient welding quality when the workpiece is displaced or deformed. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flow chart of a weld positioning method according to an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of a measurement system according to an embodiment of the present invention;

[0045] Figure 3 A schematic diagram of a workpiece contour point cloud according to an embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram of a boiler membrane wall tube structure according to an embodiment of the present invention;

[0047] Figure 5 A schematic diagram of a current weld point corresponding to a weld area point cloud according to an embodiment of the present invention;

[0048] Figure 6 This is a schematic diagram of a contour point cloud in an embodiment of the present invention when a small part is missing at the weld;

[0049] Figure 7 The figure is a flow chart of the automatic welding method of a weld according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] It should be noted that if the embodiments of the present invention involve directional indications, such as up, down, left, right, front, back, etc., then the directional indication is only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly. In addition, if the embodiments of the present invention involve descriptions of "first, second", "S1, S2", "step one, step two", etc., then such descriptions are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of indicated technical features or indicating the execution order of the method, etc. Those skilled in the art can understand that anything that does not violate the gist of the invention under the technical concept of the invention should be included in the protection scope of the present invention.

[0052] like Figure 1 As shown, the present invention provides a weld positioning method, which can be optionally used for positioning the fillet weld of the membrane wall tube panel of a boiler:

[0053] S1: Acquire the surface image of the workpiece to be welded and obtain the workpiece contour point cloud;

[0054] Specifically, it is optional but not limited to scanning the surface of the workpiece to be welded by an acquisition device, acquiring workpiece surface image data, obtaining workpiece surface point cloud, analyzing the workpiece surface point cloud, and obtaining workpiece contour point cloud; the acquisition device is optional but not limited to a laser three-dimensional contour measurement system, a 3D line scan camera, a 3D structured light camera, a TOF camera, a laser scanner, a multi-view stereo vision system, a grating projection measuring instrument, and other commonly used scanning devices that can be used to obtain three-dimensional data of the object surface.

[0055] For example, Figure 2 As shown, a measurement system is optionally provided. First, the workpiece is transported to a set direction by a conveying device in the MPM device, and then a laser 3D profile measurement system is installed in the transport direction of the workpiece. When the workpiece is transported to the scanning range of the laser 3D profile measurement system, the laser 3D profile measurement system takes a picture of the workpiece to obtain the workpiece surface image data and obtain the workpiece surface point cloud, so as to analyze the workpiece surface point cloud and obtain the following Figure 3 The workpiece contour point cloud is shown.

[0056] S2: Obtain the curvature of each workpiece contour point cloud, and determine whether it is greater than the set curvature threshold. If so, retain it; if not, eliminate it to obtain the initial weld points.

[0057] Specifically, since the curvature of the point cloud near the weld is relatively high, the set curvature threshold can be selected but not limited to this. Obtain the curvature of each point in the workpiece contour point cloud and determine whether it is greater than the curvature threshold. If it is greater, it is a high-curvature point, that is, the initial weld point, and the corresponding point cloud needs to be retained. If it is not greater, it means that the corresponding point cloud does not belong to the weld point and needs to be eliminated. After screening all the point clouds, the initial weld points can be obtained.

[0058] Preferably, the specific steps for obtaining the initial weld points may include:

[0059] S21: Obtain several adjacent point clouds of each workpiece contour point cloud, fit a curve, and construct the curve equation corresponding to each workpiece contour point cloud.

[0060] Exemplarily, according to the workpiece contour point cloud located in the XOZ plane in the coordinate system of the acquisition device obtained in step S1, the Y coordinate of each point cloud is 0. Taking any point P i (x i ,z i ) in the workpiece contour point cloud as an example, taking this point as the center, obtain a total of 5 points before and after (x i-2 ,z i-2 ), (x i-1 ,z i-1 ), (x i ,z i ), (x i+1 ,z i+2 ), (x i+2 ,z i+2 ). Use a quadratic polynomial to fit a curve z = f(x) for these 5 points. This curve can be optionally expressed as Equation 2-1:

[0061] z i = ax i 2 + bx i + c 2-1

[0062] where z i is the curve equation corresponding to the i-th point in the workpiece contour point cloud, 0 < i ≤ N, N is the number of points in the workpiece contour point cloud, a, b, and c are coefficients, and x i is the coordinate of the i-th point in the workpiece contour point cloud on the x-axis. It is preferred to use the least squares method to fit the polynomial to obtain the coefficients a, b, and c.

[0063] Preferably, if the selected point cloud is located at both ends of the workpiece contour point cloud and it is impossible to take this point as the center when obtaining the four adjacent points of this point cloud, only the four adjacent points need to be selected.

[0064] S22: Obtain the curvature of each workpiece contour point cloud according to the curve equation, and determine whether it is greater than the preset curvature threshold. If so, retain the corresponding point cloud; if not, eliminate the corresponding point cloud to obtain the initial weld points.

[0065] Specifically, it is optional but not limited to set the curvature threshold, calculate the curvature of each point cloud according to the curve equation corresponding to each point cloud obtained in step S21, and then determine whether the curvature of each point cloud is greater than the preset curvature threshold. If so, it means that this point cloud meets the requirements and the corresponding point cloud needs to be retained; if not, it means that this point cloud is not a weld point and the corresponding point cloud needs to be eliminated to obtain the initial weld points.

[0066] Exemplarily, the curvature of each point cloud can be calculated according to the curvature calculation formula 2-2:

[0067]

[0068] where k i is the curvature corresponding to the i-th point in the workpiece contour point cloud, and z i is the curve equation corresponding to the i-th point in the workpiece contour point cloud, 0 < i ≤ N, and N is the number of points in the workpiece contour point cloud.

[0069] Preferably, when obtaining the workpiece contour point cloud in step S1, due to factors such as environmental influence or process conditions interference, there are still several interference points in the initial weld points obtained in step S2, which need to be eliminated. Therefore, after step S2, it further includes:

[0070] S3: Cluster and perform straight-through filtering on the initial weld points to obtain several weld area point clouds;

[0071] Specifically, it is optional but not limited to cluster all the initial weld points obtained in step S2 according to the distance between each point cloud, so as to obtain several point cloud clusters, and perform straight-through filtering on each point cloud cluster according to the set filtering range, then several corresponding weld area point clouds can be obtained.

[0072] Preferably, the step of clustering and performing straight-through filtering on the initial weld points to obtain several weld area point clouds may include:

[0073] S31: Obtain the z-axis coordinates of all the initial weld points and arrange them according to the set order;

[0074] S32: Obtain the first set number of initial weld points, calculate the average value of their z-axis coordinates to determine the first filtering range;

[0075] Preferably, the setting order and the setting quantity are arbitrarily set by those skilled in the art.

[0076] For example, the coordinates of all initial weld points on the z-axis can be obtained, and the initial weld points are arranged in ascending order according to the size of the corresponding coordinates, and the average coordinate value z of the first five initial weld points on the z-axis is obtained. ave , thereby determining the first filtering range [z ave -3,z ave +3].

[0077] S33: performing through filtering on the initial weld point according to the first filtering range to obtain an updated weld point;

[0078] Specifically, the initial weld point may be subjected to through-filtering according to the first filtering range to remove noise and background points at the weld point where the problem occurred, and obtain an updated weld point.

[0079] S34: clustering the updated weld points to obtain a plurality of point cloud clusters, and obtaining the coordinate extreme value of the point cloud in each point cloud cluster to determine the second filtering range corresponding to each point cloud cluster;

[0080] S35: performing through filtering on each corresponding point cloud cluster according to the second filtering range to obtain a plurality of weld area point clouds.

[0081] For example, a distance coefficient threshold d can be optionally set, and points whose distance to adjacent points is less than d are divided into a cluster to obtain several point cloud clusters. Then, the maximum extreme value x of each point cloud cluster on the x-axis is calculated. max and the minimum extreme value x min , and the minimum extreme value z on the z-axis min , x min , thereby determining the second filtering range [x min -3,x max +3] and [z min -3,z min +3], and finally, each point cloud cluster is subjected to through-filtering according to the second filtering range corresponding to each point cloud cluster, so as to obtain the weld area point cloud corresponding to each point cloud cluster.

[0082] For example, Figure 4 Taking the boiler membrane wall tube containing three steel pipes as an example, each steel pipe is connected with flat steel. All the identified initial weld points can be clustered according to the distance coefficient threshold d. The minimum number of points in a class is 2, and two point cloud clusters can be obtained. It is worth noting that the distance coefficient threshold needs to be greater than the length of the flat steel and less than the diameter of the steel pipe.

[0083] S4: Fitting a straight line equation to the point cloud of each weld area, and obtaining the endpoints of the points within each straight line equation as the current weld point.

[0084] Specifically, it is optional but not limited to fitting a straight line to each weld area point cloud to obtain the straight line equation corresponding to each weld area point cloud, and setting a distance threshold to obtain the inner point of each straight line equation as the current weld point of the corresponding weld area.

[0085] Preferably, the step of fitting a straight line equation to each weld area point cloud and obtaining the endpoints of each point in the straight line equation as the current weld point may optionally include but is not limited to:

[0086] S41: setting a straight line model, selecting a number of points from the point cloud of each weld area, fitting and determining the parameters of the straight line model, and obtaining a number of current straight line equations;

[0087] Specifically, it is optional but not limited to setting the straight line model to y=mx+b, where m is the slope of the straight line, b is the intercept of the straight line, x and y are the coordinates of the points on the straight line, and any two points are selected from the point cloud of each weld area and substituted into the straight line model to obtain the equation coefficients of the straight line model corresponding to the point cloud of each weld area.

[0088] Preferably, the straight line model can also be expressed as Among them, A, B and C are the components of the direction vector of the straight line, (a, b, c) and (x, y, z) are the coordinates of any two known points on the straight line; it is worth noting that the equations that need to be satisfied by the straight line model and the parameters used are for example explanation and are not limited to this.

[0089] S42: determining the current inner point according to the distance between each point in the point cloud of each weld area and the current straight line equation, and counting the number of the current inner points;

[0090] Specifically, it is optional but not limited to using the existing distance calculation formula to calculate the distance from each point in the point cloud of each weld area to the corresponding current straight line equation, count all points whose distance is less than a preset distance threshold as points within the straight line, and count the number of points within the straight line to execute subsequent steps.

[0091] S43: Determine whether the iteration end condition is met, if so, execute step S44, if not, return to step S41;

[0092] S44: taking the point cloud corresponding to the maximum current number of inner points as the actual inner points, and performing straight line fitting to obtain the final straight line equation corresponding to the point cloud of each weld area;

[0093] Specifically, it is optional but not limited to setting a threshold of the number of iterations as the condition for ending the iteration, and determining whether the current inner point of the straight line equation obtained in step S42 is accurate. If the number of iterations is reached, it can be considered that the parameters of the straight line equation are accurate enough, and the current inner point with the largest number corresponding to each straight line equation is taken as the actual inner point, and a straight line fitting is performed on the actual inner points corresponding to each straight line equation to obtain the final straight line equation corresponding to each weld area point cloud. If the number of iterations is not reached, it means that the parameters of the straight line equation are not accurate, and it is necessary to randomly select any point in the point cloud of each weld area to refit the straight line equation, and iterate continuously until the condition for ending the iteration is met.

[0094] S45: Projecting the actual inner point to the corresponding final straight line equation to obtain the endpoint of the actual inner point, which is the current weld point corresponding to the point cloud of each weld area.

[0095] Specifically, the current weld points corresponding to each weld area point cloud include a left weld endpoint and a right weld endpoint. It is optional but not limited to projecting the actual inner points in each weld area point cloud to the corresponding final straight line equation to obtain the projection points corresponding to each weld area point cloud, which are the weld area projection points, and obtaining the left coordinate extreme value and the right coordinate extreme value of each weld area projection point on the x-axis, that is, the projection point of the left weld endpoint and the projection point of the right weld endpoint. The point clouds corresponding to the two projection points in the weld area point cloud are the left weld endpoint and the right weld endpoint, and the result is as follows: Figure 5 The current weld point is shown.

[0096] In this embodiment, a weld positioning method of the present invention is provided, by acquiring the surface image of the workpiece to be welded, obtaining the workpiece contour point cloud, then obtaining the curvature of each workpiece contour point cloud, and judging whether it is greater than the set curvature threshold, if so, retaining it, if not, eliminating it, obtaining the initial weld point, improving the welding accuracy and efficiency, and then clustering and through filtering the initial weld point to obtain a number of weld area point clouds, and finally fitting the straight line equation of each weld area point cloud, and obtaining the endpoints of the points in each straight line equation as the final weld point, by real-time scanning the workpiece to be welded, obtaining the welding points on the workpiece surface, avoiding the reduction of welding accuracy due to deformation displacement or other influences of the workpiece during the welding process, and improving the welding quality. The low welding efficiency and insufficient welding accuracy of the prior art, as well as the insufficient welding quality when the workpiece is displaced or deformed, are solved.

[0097] Preferably, during actual welding, due to the small gap between the flat steel and the steel pipe, the laser emitted by the laser 3D profile measurement system is easily affected by the welding arc, resulting in the inability to be received by the sensor, resulting in a small part of the contour point cloud weld being easily missing, such as Figure 6As shown in the figure, in this case, the above algorithm may mistakenly identify the edge point of the flat steel instead of the actual weld point. Therefore, the steps to obtain the final weld point also include:

[0098] S5: Determine whether the distance between the current weld point and the reference point is greater than a distance threshold. If so, use the reference point as the final weld point; if not, use the current weld point as the final weld point, and update the reference point based on the current weld point and / or the previous weld point.

[0099] Specifically, it is optional but not limited to setting a distance threshold and the coordinates of the initial reference point, including a left reference point corresponding to the left weld endpoint in each weld area point cloud and a right reference point corresponding to the right weld endpoint. When the workpiece to be welded moves to the scanning range of the acquisition device, the acquisition device acquires each weld area point cloud on the workpiece to be welded within a fixed acquisition range, so that each weld area point cloud is approximately in the same position in the acquisition device coordinate system. Then, a technician in this field sets the coordinates of the initial reference point, and determines whether the distance between the weld endpoint and the reference point in each weld area point cloud is greater than the distance threshold based on the weld area point clouds acquired in sequence by the acquisition device. If not, the weld endpoint in the current weld area point cloud is used as the reference point. If so, the reference point is used as the weld endpoint in the current weld area point cloud. The process is repeated until the acquisition of all weld area point clouds on the workpiece to be welded is completed.

[0100] Preferably, since only the distance between the current weld point and the reference point is judged to determine the final weld point, it is too dependent on the accuracy of a few weld points and has low robustness. It is optional to consider the influence of historical weld points to reduce errors caused by accidental factors and improve the stability of the welding process. Therefore, step S5 also includes:

[0101] S51: setting a weight for each weld point according to the time sequence, and calculating a new reference point according to the weight based on the current weld point and a number of previous weld points.

[0102] Specifically, it is optional but not limited to sorting the coordinates of all the final weld points and the current weld points that have been obtained in chronological order, then setting a weight for each weld point according to the specific order, and then obtaining the coordinates of a set number of weld points, calculating their weighted average, and using the weighted average as the new reference point.

[0103] For example, let the coordinates of the current weld point be point A(2,3), the final weld point closest to the current weld point in time be point B(4,5), and the final weld point second closest to the current weld point in time be point C(6,1). It is optional to assign weights to each final weld point according to the time sequence, such as weight W A =0.5 point B(4,5), weight W B =0.3 point C(6,1), weight WC =0.2, thus calculating the weighted average of the three weld points according to the coordinates of each weld point and the corresponding weight:

[0104] P=A×W A +B×W B +C×W C

[0105] Where P is the weighted average coordinate, i.e. the coordinate of the reference point, A, B and C are the weld points, and W A , W B and W C is the weight corresponding to each weld point.

[0106] like Figure 7 As shown, the present invention also provides a weld automatic welding method, which can be optionally used for boiler membrane wall tube panel corner weld automatic welding:

[0107] P1: Control the workpiece to be welded to move in the set direction;

[0108] Specifically, it is optional but not limited to placing the workpiece to be welded at a set position on a conveying device, and then driving the workpiece to be welded to move in a set direction through the conveying device; the conveying device includes MPM equipment, conveyor belts and other equipment that can move the workpiece to be welded.

[0109] P2: Obtain the final weld point on the surface of the workpiece to be welded by any of the above methods;

[0110] P3: Weld the workpiece to be welded according to the final welding point;

[0111] Specifically, it is optional but not limited to obtaining a plurality of weld points on the surface of the workpiece to be welded according to the weld positioning method, and then controlling the welding equipment to weld the surface of the workpiece to be welded according to the coordinates of all the weld points obtained.

[0112] P4: Determine whether welding is completed. If so, end welding. If not, return to step P1.

[0113] Specifically, it is optional but not limited to obtaining all welding points in step P2 and the welding progress of the welding equipment in step P3, and determining whether all welding points have been welded. If there are welding points that have not been welded, return to step P1 so that the workpiece to be welded continues to move in the set direction, so as to control the welding equipment to continue welding the workpiece to be welded. If all identified welding points of the workpiece to be welded have been welded, the welding can be terminated.

[0114] On the other hand, the present invention also provides a computer storage medium storing executable program code; the executable program code is used to execute any of the above-mentioned weld positioning methods or weld automatic welding methods.

[0115] On the other hand, the present invention also provides a terminal device, including a memory and a processor; the memory stores a program code that can be executed by the processor; the program code is used to execute any of the above-mentioned weld positioning methods or weld automatic welding methods.

[0116] Exemplarily, the program code may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the program code in the terminal device.

[0117] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the terminal device may also include an input / output device, a network access device, a bus, etc.

[0118] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0119] The memory may be an internal storage unit of the terminal device, such as a hard disk or a memory. The memory may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device. Further, the memory may also include both an internal storage unit of the terminal device and an external storage device. The memory is used to store the program code and other programs and data required by the terminal device. The memory may also be used to temporarily store data that has been output or is to be output.

[0120] The above-mentioned computer storage medium and terminal device are created based on the above-mentioned weld positioning method or weld automatic welding method. Their technical functions and beneficial effects are no longer repeated here. The various technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the various technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A weld positioning method, characterized in that: include: Acquire the surface image of the workpiece to be welded and obtain the workpiece contour point cloud; Obtain the curvature of each workpiece contour point cloud and determine whether it is greater than the set curvature threshold. If so, retain it; if not, remove it to obtain the initial weld point. Clustering and straight-through filtering are performed on the initial weld points to obtain several weld area point clouds; Fit the straight line equation to the point cloud of each weld area, and obtain the endpoints of the points inside the straight line equation as the current weld point.

2. The method according to claim 1, characterized in that The specific steps to obtain the initial weld point include: Acquire several adjacent point clouds of each workpiece contour point cloud, fit the curve, and construct the curve equation corresponding to each workpiece contour point cloud; The curvature of each workpiece contour point cloud is obtained according to the curve equation, and it is determined whether it is greater than the preset curvature threshold. If so, the corresponding point cloud is retained, if not, the corresponding point cloud is removed to obtain the initial weld point.

3. The method according to claim 2, characterized in that The steps of obtaining the curvature of each workpiece contour point cloud according to the curve equation include: z i =ax i 2 +bx i +c 2-1 Among them, z i is the curve equation corresponding to the i-th point in the workpiece contour point cloud, where 0 < i ≤ N, N is the number of points in the workpiece contour point cloud, a, b, and c are coefficients, and x i is the coordinate of the i-th point in the workpiece contour point cloud on the x-axis; where k i is the curvature corresponding to the i-th point in the workpiece contour point cloud, and z i is the curve equation corresponding to the i-th point in the workpiece contour point cloud, where 0 < i ≤ N and N is the number of points in the workpiece contour point cloud.

4. The method according to claim 1, characterized in that: The steps of clustering and through-filtering the initial weld points to obtain several weld area point clouds include: Get the z-axis coordinates of all initial weld points and arrange them according to the set order; Obtain a pre-set number of initial weld points, and calculate the average value of their z-axis coordinates to determine a first filtering range; Performing through filtering on the initial weld point according to the first filtering range to obtain an updated weld point; Clustering the updated weld points to obtain a number of point cloud clusters, and obtaining the coordinate extreme values ​​of the point clouds in each point cloud cluster to determine the second filtering range corresponding to each point cloud cluster; According to the second filtering range, each corresponding point cloud cluster is through-filtered to obtain a number of weld area point clouds.

5. The method according to claim 1, characterized in that The steps to obtain the current weld point include: S41: setting a straight line model, selecting a number of points from the point cloud of each weld area, fitting and determining the parameters of the straight line model, and obtaining a number of current straight line equations; S42: determining the current inner point according to the distance between each point in the point cloud of each weld area and the current straight line equation, and counting the number of the current inner points; S43: Determine whether the iteration end condition is met, if so, execute step S44, if not, return to step S41; S44: taking the point cloud corresponding to the maximum current number of inner points as the actual inner points, and performing straight line fitting to obtain the final straight line equation corresponding to the point cloud of each weld area; S45: Projecting the actual inner point to the corresponding final straight line equation to obtain the endpoint of the actual inner point, which is the current weld point corresponding to the point cloud of each weld area.

6. The method according to any one of claims 1 to 5, characterized in that: Also includes: Determine whether the distance between the current weld point and the reference point is greater than the distance threshold. If so, take the reference point as the final weld point; if not, take the current weld point as the final weld point, and update the reference point based on the current weld point and / or the previous weld point.

7. The method according to claim 6, characterized in that The steps to update the reference point include: Take the current weld point as the new reference point; Alternatively, a weight may be set for each weld point according to the chronological order, and a new reference point may be calculated according to the weight based on the current weld point and a number of previous weld points.

8. A weld seam automatic welding method, characterized in that: include: P1: Control the workpiece to be welded to move in the set direction; P2: The final weld point on the surface of the workpiece to be welded is obtained by using the weld positioning method described in any one of claims 1 to 7; P3: Weld the workpiece to be welded according to the final welding point; P4: Determine whether welding is completed. If so, end welding. If not, return to step P1.

9. A computer storage medium, characterized in that An executable program code is stored; the executable program code is used to execute the weld positioning method described in any one of claims 1 to 7 or the weld automatic welding method described in claim 8.

10. A terminal device, characterized in that: It comprises a memory and a processor; the memory stores a program code executable by the processor; the program code is used to execute the weld positioning method described in any one of claims 1 to 7 or the weld automatic welding method described in claim 8.

Images