Method and system for welding robot to search for weld start and end points

Abstract

The present invention discloses a method and system for searching the starting and ending points of a weld by a welding robot, and belongs to the technical field of welding robots. The method includes: obtaining point cloud data of a weld; identifying the geometric features of the weld in the point cloud data, and determining the position of the center line of the weld by using the geometric features; scanning the center line of the weld to obtain the characteristic points of the center line of the weld, storing the characteristic points of the center line of the weld in an array, and performing mean filtering on the characteristic points in the array to obtain the filtered characteristic points; judging the filtered characteristic points according to a preset stable recognition condition to obtain the preliminary starting point and preliminary end point of the weld; within a preset range A of the preliminary starting point of the weld, using a distance threshold, screening the characteristic points within the preset range A to obtain the final starting point of the weld, and within a preset range B of the preliminary end point of the weld, using a distance threshold, screening the characteristic points within the preset range B to obtain the final end point of the weld.

Description

Technical Field

[0001] The invention relates to the technical field of welding robots, and in particular to a method and a system for a welding robot to search for a weld start and end point. Background Art

[0002] In modern manufacturing industry, welding is one of the important processing technologies and is widely used in the fields of automobiles, ships, construction, etc. Robot welding is widely used with laser sensing system to achieve high-precision welding. However, the traditional laser sensing weld search method has the following problems: Fixed scanning position: The robot with the sensor moves to a fixed position to perform laser scanning to find the weld. If the weld moves, the weld may not be scanned, resulting in failure.

[0003] Error-prone: Electric welding spots in the weld may cause errors when the laser scans the weld spots.

[0004] Inaccurate position: The absolute position method may not be able to search for the start and end points of the weld.

[0005] Therefore, in order to improve the accuracy of the welding robot's search for welds, a new method for searching welds is urgently needed. Summary of the invention

[0006] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method and system for a welding robot to search for the starting and ending points of a weld, accurately identify the starting and ending points of a weld, and not easily make mistakes when encountering spot welding points. The welding robot can dynamically adjust the path without manual intervention, thus solving the problems of low efficiency and easy alarm errors of fixed-point welds.

[0007] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In one aspect, the present invention provides a method for a welding robot to search for a weld start and end point, comprising: Get the point cloud data of the weld; Identifying geometric features of the weld in the point cloud data, and determining the position of the weld centerline using the geometric features; Scanning the weld centerline to obtain characteristic points of the weld centerline, storing the characteristic points of the weld centerline in an array, and performing mean filtering on the characteristic points of the weld centerline in the array to obtain filtered characteristic points; According to the preset stable recognition conditions, the filtered characteristic points are judged to obtain the preliminary starting point and preliminary end point of the weld; Within the preset range A of the initial starting point of the weld, a distance threshold is used to screen the feature points within the preset range A to obtain the final starting point of the weld. Within the preset range B of the initial end point of the weld, a distance threshold is used to screen the feature points within the preset range B to obtain the final end point of the weld.

[0008] Optionally, according to a preset stable recognition condition, the filtered feature points are judged to obtain the starting point and the end point of the weld, including: If the filtered feature points appear from nothing or exist continuously, the first filtered feature point is the initial starting point of the weld; If the filtered feature points disappear or do not exist continuously, the last filtered feature point is the preliminary end point of the weld.

[0009] Optionally, the steps of obtaining the final starting point and the final end point of the weld include: The preliminary starting points within the preset range A are screened from front to back. If the distance between the two feature points in the Y-axis direction and the distance in the Z-axis direction are both less than the distance threshold, the feature point at the previous position is taken as the final starting point and the screening is stopped; otherwise, the screening is continued; The preliminary end points within the preset range B are screened from back to front. If the distance between the two feature points in the Y-axis direction and the distance in the Z-axis direction are both less than the distance threshold, the feature end point at the latter position is taken as the final end point and the screening is stopped; otherwise, the screening is continued.

[0010] Optionally, the distance threshold is expressed as:

[0011] ;

[0012] ;

[0013] In the formula, It represents the average value of the sum of the differences of the characteristic points of the two weld center lines in the Y-axis coordinates; It represents the average value of the difference between the characteristic points of the two weld center lines in the Z-axis coordinates; The total number of characteristic points representing the characteristic points of the center lines of the two welds; Indicates The Y-axis coordinate of the characteristic point of the weld centerline; Indicates The Y-axis coordinates of the characteristic points of the two weld center lines; Indicates The Z-axis coordinate of the characteristic point of the weld centerline; Indicates The Z-axis coordinate of the characteristic point of the weld centerline.

[0014] Optionally, also include:

[0015] According to the calibration relationship between the welding robot's welding gun TCP point and the laser sensor installed on the welding robot's welding gun, a calibration matrix is ​​obtained;

[0016] The calibration matrix is ​​used to convert the starting point or the end point of the weld into a coordinate point of the welding robot; wherein the final starting point and the final end point of the weld are obtained by using a laser sensor.

[0017] Optionally, the calibration relationship between the welding robot's welding gun TCP point and the laser sensor installed on the welding robot's welding gun is expressed as:

[0018] ;

[0019] In the formula, Indicates the coordinates of the welding gun TCP point; represents the calibration matrix; Represents the point coordinates in the laser sensor coordinate system.

[0020] Optionally, the calibration matrix is ​​expressed as:

[0021] ;

[0022] In the formula, , , Represents the coordinate system of the laser sensor; represents the first unit vector; represents the second unit vector; represents the third unit vector; Indicates the amount of translation.

[0023] In a second aspect, the present invention provides a system for a welding robot to search for a weld start and end point, comprising:

[0024] Data acquisition module, used to: obtain point cloud data of welds;

[0025] A centerline determination module is used to: identify the geometric features of the weld in the point cloud data, and determine the position of the weld centerline using the geometric features;

[0026] The interference filtering module is used to: scan the weld center line to obtain the characteristic points of the weld center line, store the characteristic points of the weld center line in an array, and perform mean filtering on the characteristic points in the array to obtain filtered characteristic points;

[0027] A preliminary determination module is used to determine the filtered feature points according to preset stable recognition conditions to obtain a preliminary start point and a preliminary end point of the weld;

[0028] The final judgment module is used to: within the preset range A of the initial starting point of the weld, use the distance threshold to screen the feature points within the preset range A to obtain the final starting point of the weld; within the preset range B of the initial end point of the weld, use the distance threshold to screen the feature points within the preset range B to obtain the final end point of the weld.

[0029] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for a welding robot to search for the starting and ending points of a weld as described in the first aspect.

[0030] In a fourth aspect, the present invention provides a computer device, comprising:

[0031] Memory, for storing computer instructions;

[0032] A processor is used to execute the computer instructions to implement the steps of the method for a welding robot to search for the start and end points of a weld as described in the first aspect.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention can realize accurate positioning of the weld position, can filter electric welding spots, is not prone to errors when encountering welding spots, accurately identifies the starting point and end point of the weld, and can convert the starting point and end point of the weld into coordinate points of the welding robot according to the calibration matrix between the welding gun TCP point of the welding robot and the sensor, so that the welding robot can dynamically adjust the path without manual intervention, is suitable for mass production, solves the problems of low efficiency and easy alarm errors of fixed-point welding, and has important industrial application value and broad market prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The figure shows a flow chart of a method for searching the starting and ending points of a weld by a welding robot according to the present invention in one embodiment. DETAILED DESCRIPTION

[0036] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0037] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0038] Example 1

[0039] like Figure 1 As shown, this embodiment introduces a method for a welding robot to search for the starting and ending points of a weld. Before searching, a laser sensor is first fixedly mounted on the welding gun of the welding robot arm, and a controller is respectively connected to the welding robot and the laser sensor. The welding robot moves to scan the weld to search for the starting and ending points of the weld, and can effectively filter out electric welding spots in the weld.

[0040] The method specifically comprises the following steps:

[0041] Step 1: The sensor in this embodiment is a laser sensor. The relationship between the welding robot's welding gun TCP point and the laser sensor installed on the welding robot's welding gun is calibrated, which is expressed as:

[0042] ;

[0043] In the formula, Indicates the coordinates of the welding gun TCP point; represents the calibration matrix; Represents the point coordinates in the laser sensor coordinate system.

[0044] Step 2: According to the calibration relationship between the welding robot's welding gun TCP point and the laser sensor installed on the welding robot's welding gun, the calibration matrix is ​​obtained, which is expressed as:

[0045] ;

[0046] In the formula, , , Represents the coordinate system of the laser sensor; represents the first unit vector; represents the second unit vector; represents the third unit vector; Indicates the amount of translation.

[0047] In this embodiment, the noap coordinates: n, o, a are all unit vectors described by the coordinates in the original xyz laser sensor's coordinate system. The three are orthogonal to form a new right-handed coordinate system to describe the changing relationship between the position coordinate system and the original xyz coordinate system at this time; p represents the translation amount between the coordinates.

[0048] Step 3: Obtain the point cloud data of the weld. In this embodiment, the point cloud data of the weld is two-dimensional point cloud data, which can be represented by the coordinates of multiple groups of points, where one group of points is represented as ( , ),in , are the ordinate and vertical coordinates of the point. These points represent the local information of the weld surface. By acquiring a large number of such points, a complete two-dimensional data set of the weld surface can be constructed.

[0049] Step 4: Use signal processing algorithms to identify the geometric features of the weld in the point cloud data, and use the geometric features of the weld in combination with edge detection and fitting algorithms to accurately determine the position of the weld centerline. The weld geometric features include width, depth, contour, etc. The weld centerline position is accurately located with an error of less than 0.5 mm.

[0050] Step 5: Set the parameters of the controller to control the welding robot to scan the weld center line, obtain the characteristic points of the weld center line, store the characteristic points of the weld center line in an array, analyze all the characteristic points in the array, that is, calculate the average value of the sum of the difference values ​​of the characteristic points of the two weld center lines in the array under the Y and Z axis coordinates, which is the distance threshold, expressed as:

[0051] ;

[0052] In the formula, It represents the average value of the sum of the differences of the characteristic points of the two weld center lines in the Y-axis coordinates; The total number of characteristic points representing the characteristic points of the center lines of the two welds; Indicates The Y-axis coordinate of the characteristic point of the weld centerline; Indicates The Y-axis coordinates of the characteristic points of the two weld center lines can be calculated in the same way. , expressed as:

[0053] ;

[0054] It represents the average value of the difference between the characteristic points of the two weld center lines in the Z-axis coordinates; Indicates The Z-axis coordinate of the characteristic point of the weld centerline; Indicates The Z-axis coordinate of the characteristic point of the weld centerline.

[0055] Step 6: Perform mean filtering on the feature points of the weld centerline in the array to obtain filtered feature points.

[0056] Step 7: According to the preset stable recognition conditions, the filtered feature points are judged to obtain the preliminary starting point and preliminary end point of the weld, specifically:

[0057] If the filtered feature points appear from nothing or exist continuously, the first filtered feature point is the initial starting point of the weld;

[0058] If the filtered feature points disappear or do not exist continuously, the last filtered feature point is the preliminary end point of the weld.

[0059] In a specific embodiment, from not being able to identify the weld feature point to being able to identify the weld feature point, the first feature point is the initial starting point of the weld, and from being able to identify the weld feature point to not being able to identify the weld feature point, the last feature point is the initial end point of the weld.

[0060] In another specific embodiment, when encountering an electric welding spot, there may be no weld features. Therefore, when n weld feature points are continuously and stably identified, the first feature point is determined as the weld starting point, and when n weld feature points cannot be continuously and stably identified, the last feature point is determined as the weld end point. This method can be used to filter electric welding spots and prevent misjudgment.

[0061] Step 8: Within the preset range A of the initial starting point of the weld, a distance threshold is used to screen the feature points within the preset range A to obtain the final starting point of the weld. Within the preset range B of the initial end point of the weld, a distance threshold is used to screen the feature points within the preset range B to obtain the final end point of the weld. Specifically:

[0062] The preliminary starting points within the preset range A are screened from front to back. If the distance between the two feature points in the Y-axis direction and the distance in the Z-axis direction are both less than the distance threshold, the feature point at the previous position is taken as the final starting point and the screening is stopped; otherwise, the screening is continued;

[0063] The preliminary end points within the preset range B are screened from back to front. If the distance between the two feature points in the Y-axis direction and the distance in the Z-axis direction are both less than the distance threshold, the feature end point at the latter position is taken as the final end point and the screening is stopped; otherwise, the screening is continued.

[0064] Step 9: Use the calibration matrix to convert the starting point or end point of the weld into the coordinate point of the welding robot, and then send it to the welding robot; wherein the final starting point and final end point of the weld are obtained by using the laser sensor. By using the calibration matrix between the welding robot's welding gun TCP point and the laser sensor installed on the welding robot's welding gun, the welding robot can dynamically adjust the path without manual intervention, which is suitable for mass production and solves the problem of low efficiency and easy alarm errors of fixed-point welding.

[0065] In actual welding applications, the welding is completed using the searched final starting point and final end point of the weld. Except for the final starting point and final end point of the weld, traditional fixed position scanning is still used.

[0066] When this embodiment is used, it can realize accurate positioning of the weld position, can filter electric welding spots, is not prone to errors when encountering welding spots, and can accurately identify the starting point and end point of the weld, which has important industrial application value and broad market prospects.

[0067] Example 2

[0068] This embodiment introduces a system for a welding robot to search for the start and end points of a weld, including:

[0069] Data acquisition module, used to: obtain point cloud data of welds;

[0070] A centerline determination module is used to: identify the geometric features of the weld in the point cloud data, and determine the position of the weld centerline using the geometric features;

[0071] The interference filtering module is used to: scan the weld center line to obtain the characteristic points of the weld center line, store the characteristic points of the weld center line in an array, and perform mean filtering on the characteristic points in the array to obtain filtered characteristic points;

[0072] A preliminary determination module is used to determine the filtered feature points according to preset stable recognition conditions to obtain a preliminary starting point and a preliminary end point of the weld;

[0073] The final judgment module is used to: within the preset range A of the initial starting point of the weld, use the distance threshold to screen the feature points within the preset range A to obtain the final starting point of the weld; within the preset range B of the initial end point of the weld, use the distance threshold to screen the feature points within the preset range B to obtain the final end point of the weld.

[0074] Example 3

[0075] This embodiment introduces a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for a welding robot to search for the start and end points of a weld described in Embodiment 1 are implemented.

[0076] Example 4

[0077] This embodiment introduces a computer device, including:

[0078] Memory, for storing computer instructions;

[0079] The processor is used to execute the computer instructions to implement the steps of the method for the welding robot to search for the starting and ending points of the weld as described in Example 1.

[0080] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0081] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. 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.

[0082] 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 comprising 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.

[0083] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0084] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A method for a welding robot to search for the start and end points of a weld, characterized in that: include: Get the point cloud data of the weld; Identifying geometric features of the weld in the point cloud data, and determining the position of the weld centerline using the geometric features; Scanning the weld centerline to obtain characteristic points of the weld centerline, storing the characteristic points of the weld centerline in an array, and performing mean filtering on the characteristic points of the weld centerline in the array to obtain filtered characteristic points; According to the preset stable recognition conditions, the filtered characteristic points are judged to obtain the preliminary starting point and preliminary end point of the weld; Within the preset range A of the initial starting point of the weld, a distance threshold is used to screen the feature points within the preset range A to obtain the final starting point of the weld. Within the preset range B of the initial end point of the weld, a distance threshold is used to screen the feature points within the preset range B to obtain the final end point of the weld.

2. The method for searching the starting and ending points of a weld by a welding robot according to claim 1, characterized in that: According to the preset stable recognition conditions, the filtered feature points are judged to obtain the starting point and the end point of the weld, including: If the filtered feature points appear from nothing or exist continuously, the first filtered feature point is the initial starting point of the weld; If the filtered feature points disappear or do not exist continuously, the last filtered feature point is the preliminary end point of the weld.

3. The method for searching the starting and ending points of a weld by a welding robot according to claim 1, characterized in that: The steps of obtaining the final starting point and the final end point of the weld include: The feature points within the preset range A are screened from front to back. If the distance between two feature points in the Y-axis direction and the distance in the Z-axis direction are both less than the distance threshold, the feature point at the previous position is taken as the final starting point and the screening is stopped; otherwise, the screening is continued; The preliminary end points within the preset range B are screened from back to front. If the distance between the two feature points in the Y-axis direction and the distance in the Z-axis direction are both less than the distance threshold, the feature end point at the latter position is taken as the final end point and the screening is stopped; otherwise, the screening is continued.

4. The method for searching the starting and ending points of a weld by a welding robot according to claim 1 or 3, characterized in that: The distance threshold is expressed as: ； ； In the formula, It represents the average value of the sum of the differences of the characteristic points of the center lines of the two welds in the Y-axis coordinates; It represents the average value of the difference between the characteristic points of the two weld center lines in the Z-axis coordinates; The total number of characteristic points representing the characteristic points of the center lines of the two welds; Indicates The Y-axis coordinate of the characteristic point of the weld centerline; Indicates The Y-axis coordinates of the characteristic points of the two weld center lines; Indicates The Z-axis coordinate of the characteristic point of the weld centerline; Indicates The Z-axis coordinate of the characteristic point of the weld centerline.

5. The method for searching the starting and ending points of a weld by a welding robot according to claim 1, characterized in that: Also includes: According to the calibration relationship between the welding robot's welding gun TCP point and the laser sensor installed on the welding robot's welding gun, a calibration matrix is ​​obtained; The calibration matrix is ​​used to convert the starting point or the end point of the weld into a coordinate point of the welding robot; wherein the final starting point and the final end point of the weld are obtained by using a laser sensor.

6. The method for searching the starting and ending points of a weld by a welding robot according to claim 5, characterized in that: The calibration relationship between the welding robot's welding gun TCP point and the laser sensor installed on the welding robot's welding gun is expressed as: ； In the formula, Indicates the coordinates of the welding gun TCP point; represents the calibration matrix; Represents the point coordinates in the laser sensor coordinate system.

7. The method for searching the starting and ending points of a weld by a welding robot according to claim 5, characterized in that: The calibration matrix is ​​expressed as: ； In the formula, , , Represents the coordinate system of the laser sensor; represents the first unit vector; represents the second unit vector; represents the third unit vector; Indicates the amount of translation.

8. A system for a welding robot to search for the start and end points of a weld, characterized in that: include: Data acquisition module, used to: obtain point cloud data of welds; A centerline determination module is used to: identify the geometric features of the weld in the point cloud data, and determine the position of the weld centerline using the geometric features; The interference filtering module is used to: scan the weld center line to obtain the characteristic points of the weld center line, store the characteristic points of the weld center line in an array, and perform mean filtering on the characteristic points in the array to obtain filtered characteristic points; A preliminary determination module is used to determine the filtered feature points according to preset stable recognition conditions to obtain a preliminary starting point and a preliminary end point of the weld; The final judgment module is used to: within the preset range A of the initial starting point of the weld, use the distance threshold to screen the feature points within the preset range A to obtain the final starting point of the weld; within the preset range B of the initial end point of the weld, use the distance threshold to screen the feature points within the preset range B to obtain the final end point of the weld.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for a welding robot to search for the start and end points of a weld described in any one of claims 1 to 7 are implemented.

10. A computer device, characterized in that: include: Memory, for storing computer instructions; A processor is used to execute the computer instructions to implement the steps of the method for a welding robot to search for the start and end points of a weld according to any one of claims 1 to 7.

Images