CN113894481B - Welding pose adjusting method and device for complex space curve welding seam - Google Patents
Welding pose adjusting method and device for complex space curve welding seam Download PDFInfo
- Publication number
- CN113894481B CN113894481B CN202111056501.8A CN202111056501A CN113894481B CN 113894481 B CN113894481 B CN 113894481B CN 202111056501 A CN202111056501 A CN 202111056501A CN 113894481 B CN113894481 B CN 113894481B
- Authority
- CN
- China
- Prior art keywords
- welding
- weld
- space curve
- complex space
- coordinates
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003466 welding Methods 0.000 title claims abstract description 383
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 26
- 239000013598 vector Substances 0.000 claims description 46
- 238000000605 extraction Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000013459 approach Methods 0.000 description 6
- 230000000977 initiatory effect Effects 0.000 description 6
- 238000002360 preparation method Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- XKRFYHLGVUSROY-UHFFFAOYSA-N Argon Chemical compound [Ar] XKRFYHLGVUSROY-UHFFFAOYSA-N 0.000 description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 229910052786 argon Inorganic materials 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
- B23K37/02—Carriages for supporting the welding or cutting element
- B23K37/0252—Steering means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Laser Beam Processing (AREA)
- Manipulator (AREA)
Abstract
The embodiment of the application discloses a welding pose adjusting method and device for a complex space curve welding seam. The method comprises the following steps: extracting weld feature point coordinates of a complex space curve weld image based on a self-updating template matching algorithm; calculating the current expected welding point coordinates according to the welding point characteristic point coordinates, and calculating the welding point deviation in the complex space curve welding point tracking process according to the current expected welding point coordinates so as to adjust the welding position in real time according to the welding point deviation; and establishing a discrete posture model of the complex space curve weld according to the weld characteristic point coordinates, so that the welding posture is adjusted in real time according to the discrete posture model. According to the embodiment of the application, the real-time adjustment of the welding position and the gesture of the complex space curve welding seam can be realized, and the welding quality and the welding stability are ensured.
Description
Technical Field
The application relates to the technical field of welding, in particular to a welding pose adjusting method and device for a complex space curve welding seam.
Background
With the development of computer vision, automatic control theory and artificial intelligence technology, robot welding has been rapidly developed. After the welding seam image is acquired by the robot welding based on the structural light sensor through the structural light vision sensor, the identification of the welding seam and the extraction of characteristic points of the welding seam are finished through an image processing algorithm, and then a control algorithm is designed based on the coordinate information of the characteristic points of the welding seam, so that the automatic tracking of the welding seam is realized.
Because the laser stripe advances the welding gun for a certain distance, how to overcome visual advance and accurately acquire real-time welding deviation in the welding process is a problem to be solved for the weld tracking of space curve welding lines. Meanwhile, the welding posture is also an important factor influencing the welding seam forming and welding quality, and in order to ensure the welding quality, the real-time adjustment of the welding posture of the welding robot is very necessary in the welding process of the complex space curve welding seam.
Disclosure of Invention
Because the existing method has the problems, the embodiment of the application provides a welding pose adjusting method and device for a complex space curve welding seam.
Specifically, the embodiment of the application provides the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for adjusting a welding pose of a complex space curve weld, including:
And 104, establishing a discrete posture model of the complex space curve weld joint according to the weld joint feature point coordinates, so that the welding posture is adjusted in real time according to the discrete posture model.
Optionally, extracting weld feature point coordinates of the complex space curve weld image based on a self-updating template matching algorithm includes:
Optionally, after extracting the weld feature point coordinates of the complex space curve weld image, the method further includes:
converting the two-dimensional coordinates of each weld characteristic point under the laser weld tracking sensor coordinate system into three-dimensional coordinates under the welding robot base coordinate system according to the coordinate change relation between the laser weld tracking sensor coordinate system and the welding robot base coordinate system;
Acquiring a weld initial point coordinate in the complex space curve weld image according to the change of the laser stripe shape in the complex space curve weld image, and converting the weld initial point coordinate into a welding robot base coordinate system;
comparing the initial point coordinates of the welding seam under the welding robot base coordinate system with initial point coordinates in a teaching track formed by the welding seam characteristic point coordinates to obtain welding seam initial point coordinate deviation;
and adjusting the position of the center point of the welding gun according to the coordinate deviation of the initial point of the welding seam, thereby realizing the automatic alignment of the welding gun and the initial point of the welding seam.
Optionally, calculating a current expected welding point coordinate according to the welding line feature point coordinate, and calculating a welding line deviation in the complex space curve welding line tracking process according to the current expected welding point coordinate, so as to adjust the welding position in real time according to the welding line deviation, including:
based on a sliding queue method, three-dimensional coordinate data of weld characteristic points contained in a current queue are obtained;
based on a preset times of B-spline fitting method, fitting three-dimensional coordinate data of weld characteristic points contained in the current queue into a smooth curve;
Acquiring coordinates of a current welding gun center point under a welding robot base coordinate system and three-dimensional coordinates of a welding seam characteristic point on a smooth curve;
calculating the current expected welding point coordinates according to the coordinates of the current welding gun center point under the welding robot base coordinate system and the three-dimensional coordinates of the welding line characteristic points on the smooth curve;
and calculating the weld deviation in the complex space curve weld tracking process according to the current expected weld point coordinates, so that the position of the center point of the welding gun is adjusted in real time according to the weld deviation.
Optionally, establishing a discrete gesture model of the complex space curve weld according to the weld characteristic point coordinates, so that the welding gun gesture is adjusted according to the discrete gesture model, including:
obtaining a direction vector, a proximity vector and a normal vector at each weld characteristic point, and establishing a discrete attitude model of the complex space curve weld according to the direction vector, the proximity vector and the normal vector at each weld characteristic point;
and calculating the current welding posture deviation of the welding robot according to the discrete posture model of the complex space curve welding seam so as to adjust the current welding posture of the welding robot in real time according to the current welding posture deviation of the welding robot.
Optionally, the coordinate change relationship between the coordinate system of the laser welding seam tracking sensor and the welding robot base coordinate system is as follows:
P′ b ＝T 6 T m P′ c
wherein P' b T is the homogeneous form of three-dimensional coordinates of weld joint characteristic points under a welding robot base coordinate system 6 For the robot pose transformation matrix, T m For a matrix of rotational and translational relationships between the camera and robot tool coordinate systems, P' c Is a homogeneous form of three-dimensional coordinates of the weld feature points in a camera coordinate system.
Optionally, the extracting, based on a template matching algorithm, weld feature point coordinates of the complex space curve weld image includes:
calculating the sum of gray level differences between the matching template and the region of interest according to the following formula, and taking the central point of the matching template image at the position with the minimum deviation as the characteristic point of the complex space curve welding seam; the formula is:
where T (x ', y') represents the pixel gray value of the (x ', y') coordinate on the matching template, I (x, y) represents the pixel gray value of the (x, y) coordinate in the region of interest, R (x, y) represents the sum of gray value squared differences between the matching template at the (x, y) coordinate of the region of interest and the pixels of the region of interest, and the smaller the value of R (x, y) is, the higher the degree of matching is.
In a second aspect, an embodiment of the present application provides a welding pose adjustment device for a complex space curve welding seam, including:
the acquisition module is used for acquiring images of the complex space curve weld joint through the laser weld joint tracking sensor;
the extraction module is used for extracting weld feature point coordinates of the complex space curve weld image based on a self-updating template matching algorithm;
the first processing module is used for calculating the current expected welding point coordinates according to the welding line characteristic point coordinates, and calculating the welding line deviation in the complex space curve welding line tracking process according to the current expected welding point coordinates so as to adjust the welding position in real time according to the welding line deviation;
and the second processing module is used for establishing a discrete gesture model of the complex space curve weld according to the weld characteristic point coordinates so as to adjust the welding gesture in real time according to the discrete gesture model.
In a third aspect, an embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method for adjusting welding pose of a complex space curve weld seam according to the first aspect when the processor executes the program.
In a fourth aspect, embodiments of the present application also provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for welding pose adjustment of a complex space curve weld according to the first aspect described above.
According to the technical scheme, the embodiment of the application firstly collects the image of the complex space curve welding seam, and extracts the welding seam characteristic point coordinates of the welding seam image by using a self-updating template matching algorithm. When welding position adjustment is performed: and calculating the current expected welding point coordinates according to the welding point characteristic point coordinates, and calculating the welding point deviation in the complex space curve welding point tracking process according to the current expected welding point coordinates so as to adjust the welding position in real time according to the welding point deviation. When welding posture adjustment is performed: and establishing a discrete posture model of the complex space curve weld according to the weld characteristic point coordinates, so that the welding posture is adjusted in real time according to the discrete posture model. Therefore, the embodiment of the application can realize real-time adjustment of the welding position and the gesture of the complex space curve welding seam, and ensures the welding quality and the welding stability.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings that are necessary for the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention and that other drawings can be obtained from these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a step flow diagram of a method for adjusting welding pose of a complex space curve weld provided by an embodiment of the present application;
FIG. 2 is a flowchart of steps of a method for extracting weld feature points based on self-updating template matching according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a laser weld tracking sensor provided in an embodiment of the present application;
FIG. 4 is a complex space curve weld image acquired by a laser weld tracking sensor provided by an embodiment of the present application;
FIG. 5 is a schematic diagram of a visual model of a laser weld tracking sensor provided in an embodiment of the present application;
FIG. 6 is a flowchart for acquiring a first weld image feature point according to an embodiment of the present application;
FIG. 7 is a flowchart for obtaining weld image feature point coordinates provided by an embodiment of the present application;
FIG. 8 is a flow chart of weld initiation point detection provided by an embodiment of the present application;
FIG. 9 is a flow chart of V-shaped weld initiation point detection provided by an embodiment of the present application;
FIG. 10 is a flow chart of lap weld initiation point detection provided by an embodiment of the present application;
FIG. 11 is a flow chart for detecting the initial point of a fillet weld provided in an embodiment of the present application;
FIG. 12 is a schematic diagram of a sliding data queuing algorithm provided by an embodiment of the present application;
FIG. 13 is a schematic diagram of a complex space curve weld error provided by an embodiment of the present application;
FIG. 14 is a schematic view of feature points and feature vectors of a V-shaped weld provided in an embodiment of the present application;
FIG. 15 is a schematic view of a complex space curve weld pose model provided by an embodiment of the present application;
FIG. 16 is a block diagram of a complex space curve real-time weld tracking and weld pose adjustment system provided by embodiments of the present application;
FIG. 17 is a schematic structural view of a welding pose adjusting device for a complex space curve weld provided in an embodiment of the present application;
fig. 18 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
As shown in fig. 1, a welding pose adjustment method for a complex space curve welding seam provided in an embodiment of the present application includes:
in this step, it should be noted that there are two common feature point extraction methods, one is to obtain the weld feature point based on the geometric feature of the laser stripe, and the other is to obtain the weld feature point based on the template matching. For the feature point extraction method based on geometric features, there are the following disadvantages: first, the adaptability is not strong. For different types of welds, a specific image processing algorithm is required, and thus the algorithm has no versatility. Secondly, the parameters are not dynamically adjusted. In image processing of the same weld type, parameters in the processing algorithm also need to be manually adjusted due to the difference of the sizes and angles of the weld grooves. And also has relatively poor robustness. In the process of using Gas Metal Arc Welding (GMAW), there are a lot of arc light and splash interference, and in some cases, the extraction of the weld characteristic points based on geometric features is easily interfered by welding noise, so that the weld characteristic points cannot be accurately obtained. In conclusion, the geometrical feature point-based weld feature point extraction method has the defects of poor flexibility, poor robustness and the like. The method for acquiring the characteristic points of the welding seam based on template matching is to take a known template and a region with the same size in the original image for comparison. From the upper left corner, the next pixel is shifted gradually, and the next line of pixels is shifted until all positions are compared, and the block with the smallest difference is the position to be found. Calculating the error between the matching template and the original image typically uses a square difference matching method, the formula is as follows:
Where T (x ', y') represents the pixel gray value of the (x ', y') coordinate on the template, I (x, y) represents the pixel gray value of the (x, y) coordinate on the original image, R (x, y) represents the sum of the gray value squared differences between the template and the original image pixels at the (x, y) coordinate of the original image, and the smaller the value of R (x, y) is, the higher the degree of matching is.
However, this method has the following disadvantages: first, the calculation amount of template matching is large. The template matching needs to calculate almost every pixel on the original image, and a large amount of multiplication and addition are involved in the middle, so that the time is more, and the real-time performance of the system is affected. Second, template matching is not well adapted to rotational deformation of the image. For complex space welding seams, the images of different positions of the same welding seam have larger difference and relative rotation, and the condition that the characteristic points are extracted by using a set of templates can have larger errors or inaccurate extraction exists. Therefore, aiming at some defects of the existing weld characteristic point extraction method, the embodiment of the application provides a self-updating template matching algorithm based on the region of interest, and the method has stronger robustness and better instantaneity for extracting the weld characteristic points of the complex space curve as shown in fig. 2. The self-updating template matching algorithm based on the region of interest is divided into two steps, wherein the first step is to search a first welding seam characteristic point by using the template matching algorithm based on the region of interest (ROI), and the second step is to acquire the welding seam characteristic point of the welding seam image of the next frame by using the template matching algorithm based on the self-updating, and the second step is continuously repeated. In the first image processing, a flow of searching for weld feature points using an ROI-based template matching method is shown in fig. 6, where a specific flow illustrated by taking V-shaped weld feature point extraction as an example is as follows: first a region of interest of the original image is calculated. Since the template matching calculation amount is large for the whole image, and the calculation amount can be greatly reduced by performing the template matching in the region of interest. As can be seen from fig. 6 (1) of the acquired original image, the laser stripes are approximately parallel to the horizontal axis of the image, and the gray values of the pixels at the laser stripes are significantly higher than the gray values of the other pixels in the image, so that the region of interest of the image can be obtained by summing the gray values of the pixels in each row. The sum formula of the gray values of each row of pixels is as follows:
Wherein J is v (i) Is the sum of the gray values of the pixels of the i-th row of the image, w and h are the width and height of the image, respectively.
As shown in fig. 6 (2), the region of interest of the image can be obtained by:
in the formula, [ x ] min ,x max ]Is the smallest and largest columns of the region of interest in the original image, [ y ] min ,y max ]Is the smallest and largest line of the region of interest in the original image, v c Is J in formula (6) v (i) Number of lines corresponding to maximum value, [ Deltay ] h ,Δy l ]The number of rows, Δy, extending up and down, respectively h +Δy l Is the number of lines of the region of interest.
In this step, as shown in fig. 3, the laser seam tracking sensor provided in the embodiment of the present application mainly includes an industrial camera, a sensor protection housing, a filter lens, a linear array laser, and the like. Wherein: the laser plane generated by the linear array laser is projected onto a workpiece to form laser stripes, the industrial camera and the filter lens are coaxially arranged on the inner wall of the sensor shell to collect a welding line image, the dimming lens is arranged in a drawer type structure to ensure that the calibration of the industrial camera is realized by extracting the dimming lens in a non-welding process, the system protection shell protects the sensor from the interference of splashing and high temperature, and the system protection shell is connected with a sixth axis of the robot through a mounting bracket. The acquired symmetrical V-shaped weld, lap joint weld and corner joint weld images are shown in fig. 4 by using the laser weld tracking sensor provided by the embodiment of the invention, wherein white lines in the weld images are laser stripes and splash light, and the white lines are black except the laser stripes and the splash light under the action of the filter lens.
In the step, firstly, according to the characteristics of the V-shaped welding seam, a matching template of the V-shaped welding seam is generated, and the characteristics of the V-shaped welding seam are obtainedThe characteristic point is located at the center of the template, the template consists of two bright point straight lines intersecting at the center, and the rest positions of the template are all black. The resulting V-shaped weld pattern is shown in fig. 6 (3). And then template matching is carried out in the region of interest to obtain weld characteristic points. According to the formula (5), template matching is performed by using the template of the V-shaped welding seam shown in fig. 6 (3) and the searched image shown in fig. 6 (2), and the sum of gray level variances between the template and the searched image is obtained. As shown in fig. 6 (4), the center point of the template image where the deviation is minimum is set as the characteristic point of the V-shaped weld. By template matching based on the region of interest, the first characteristic point F of the V-shaped weld can be obtained P1 (x 1 ,y 1 )。
In this step, it should be noted that, for a complex space curve weld, the weld may vary to some extent at different locations, including dimensional variations and angular variations. If the same V-shaped template is adopted, low matching precision and even matching errors are easy to cause, so on the basis of matching the template based on the region of interest, the application provides a matching algorithm of a self-updating template, the principle of the algorithm is shown in fig. 7, and the characteristic point extraction flow of the self-updating template matching algorithm on the V-shaped weld joint is as follows:
As shown in fig. 7 (2), V-shaped weld feature points F are extracted in the region of interest by the ROI-based template matching method through the generated V-shaped weld template p1 (x 1 ,y 1 ). Then on the original image, in coordinates (x 1 ,y 1 ) The side length is T for the center w The square image of the pixel serves as a new template. As shown in fig. 7 (3), the new template obtained by clipping is filtered and binarized, and then the image of the laser stripe center outline is extracted for template matching of the next frame image. To speed up the template matching, smaller searched images need to be used. Because the acquisition frame rate of the camera is above 20Hz, the difference between every two welding seam images is small, and the positions of the welding seam characteristic points in the images do not differ too much on the same welding seam track. Thus, the weld characteristic point F extracted from the previous frame is on the newly acquired image p1 (x 1 ,y 1 ) Centered, the extraction width is S w The pixel and the height are S h The area of the pixel is shown in fig. 7 (5) as a new searched image.
Then, the obtained image is used as a new matching template, the new matching template image traverses the searched image, the shape matching is carried out on the points on the central outline of the template image and the points on the searched image corresponding to the points, the position with the highest matching degree is obtained, and the central point of the template image is the obtained weld characteristic point coordinate as shown in fig. 7 (6).
In the step, the template and the searched image are repeatedly and dynamically updated, and the bottom characteristic point and the two edge characteristic points of the V-shaped welding seam are continuously obtained, so that the welding seam characteristic points of the welding seam image of the complex space curve are extracted.
in the step, firstly, based on a preset times of B-spline fitting method, fitting three-dimensional coordinate data of weld characteristic points contained in the current queue into a smooth curve; then acquiring the coordinates of the current welding gun center point under a welding robot base coordinate system and the three-dimensional coordinates of the welding seam characteristic points on the smooth curve; and finally, calculating the current expected welding point coordinates according to the coordinates of the current welding gun central point under the welding robot base coordinate system and the three-dimensional coordinates of the welding line characteristic points on the smooth curve, and calculating the welding line deviation in the complex space curve welding line tracking process according to the current expected welding point coordinates so as to adjust the welding gun central point position in real time according to the welding line deviation.
Step 104: and establishing a discrete posture model of the complex space curve weld according to the weld characteristic point coordinates, so that the welding posture is adjusted in real time according to the discrete posture model.
In the step, firstly, a direction vector, a proximity vector and a normal vector at each weld characteristic point are obtained, and a discrete attitude model of a complex space curve weld is established according to the direction vector, the proximity vector and the normal vector at each weld characteristic point; and then calculating the current welding posture deviation of the welding robot according to the discrete posture model of the complex space curve welding seam so as to adjust the current welding posture of the welding robot in real time according to the current welding posture deviation of the welding robot.
According to the technical scheme, the embodiment of the application firstly collects the image of the complex space curve welding seam, and extracts the welding seam characteristic point coordinates of the welding seam image by using a self-updating template matching algorithm. When welding position adjustment is performed: and calculating the current expected welding point coordinates according to the welding point characteristic point coordinates, and calculating the welding point deviation in the complex space curve welding point tracking process according to the current expected welding point coordinates so as to adjust the welding position in real time according to the welding point deviation. When welding posture adjustment is performed: and establishing a discrete posture model of the complex space curve weld according to the weld characteristic point coordinates, so that the welding posture is adjusted in real time according to the discrete posture model. Therefore, the embodiment of the application can realize real-time adjustment of the welding position and the gesture of the complex space curve welding seam, and ensures the welding quality and the welding stability.
Based on the foregoing embodiment, in this embodiment, extracting weld feature point coordinates of a complex space curve weld image based on a self-updating template matching algorithm includes:
Based on the foregoing embodiment, in this embodiment, after extracting the weld feature point coordinates of the complex space curve weld image, the method further includes:
converting the two-dimensional coordinates of each weld characteristic point under the laser weld tracking sensor coordinate system into three-dimensional coordinates under the welding robot base coordinate system according to the coordinate change relation between the laser weld tracking sensor coordinate system and the welding robot base coordinate system;
Acquiring a weld initial point coordinate in the complex space curve weld image according to the change of the laser stripe shape in the complex space curve weld image, and converting the weld initial point coordinate into a welding robot base coordinate system;
comparing the initial point coordinates of the welding seam under the welding robot base coordinate system with initial point coordinates in a teaching track formed by the welding seam characteristic point coordinates to obtain welding seam initial point coordinate deviation;
and adjusting the position of the center point of the welding gun according to the coordinate deviation of the initial point of the welding seam, thereby realizing the automatic alignment of the welding gun and the initial point of the welding seam.
In this embodiment, it should be noted that, the structured light visual projection imaging model is shown in fig. 5, where n is 1 、Π 2 、Π 3 The device comprises a camera imaging plane, a workpiece curved surface and a laser plane. In order to simplify the model, the imaging model of the camera is simplified into a small-hole imaging model without considering distortion of a lens, and the image coordinates p of the characteristic points of the welding seam f And its three-dimensional coordinates P in camera coordinate system c The relationship between them can be expressed as:
wherein (u, v) is the image coordinates of the weld feature points, (u) 0 ,v 0 ) Is the image coordinates of the center of the optical axis, (k) x ,k y ) Is the magnification factor in the horizontal and vertical axes, (x) c ,y c ,z c ) Is the three-dimensional coordinates of the characteristic points of the welding seam under the coordinate system of the camera, M c Is a matrix of parameters within the camera.
The equation for the structured light plane in the camera coordinate system is assumed to be:
z c ＝ax c +by c +c (2)
where a, b, c are coefficients that can be obtained by scaling the structured light plane.
Due to the laser stripe characteristic point P c Is located on the laser plane, so P c Point coordinates (x) c ,y c ,z c ) And (3) the equation (2) is satisfied. Combining the camera imaging model (1) and the positional relation model (2) of the laser relative to the camera, the three-dimensional coordinates of the laser fringe feature point image under the camera coordinate system can be obtained by the laser fringe feature point image coordinates, as shown in a formula (3):
in the seam tracking system, a laser seam tracking sensor is generally positioned on a robot hand to form a hand-eye system. Through hand-eye calibration, a rotation and translation relation matrix T between a camera coordinate system and a robot tool coordinate system can be obtained m . By network communication with the robot controller, the pose coordinates (x t ,y t ,z t ,Rx t ,Ry t ,Rz t ) Further calculating to obtain a robot pose transformation matrix T 6 According to formula (3) and calculated T m ,T 6 Matrix, homogeneous form P 'of three-dimensional coordinates of weld joint characteristic points under robot base coordinate system' b Can be obtained by the following formula:
P′ b ＝T 6 T m P′ c (4)
wherein T is 6 Can be read and calculated from the robot controller in real time, T m Can be obtained by hand-eye calibration, P' c Is a video cameraThree-dimensional coordinates P in a coordinate system c Is a homogeneous version of (c).
So far, according to the structured light visual model, three-dimensional coordinates of the welding seam characteristic points under a robot base coordinate system can be obtained through internal parameter calculation of a camera, structured light plane parameter calibration, robot TCP calibration, robot and hand-eye calibration of a laser, and the coordinates can be used for initial point guidance of the welding seam, welding seam tracking, automatic adjustment of welding gun posture and the like.
In this embodiment, it is noted that, in the welding process of the robot, it is difficult to ensure consistency of the positions of the workpieces, so that it is important for the robot to identify and guide the initial points of the weld joints, which is also a precondition for performing automatic weld joint tracking. The initial point detection flow of the welding seam is shown in fig. 8, the mechanical hand-held laser welding seam tracking sensor gradually moves to the initial point position of the welding seam, and the positions of laser stripes sequentially pass through a laser line 1, a laser line 2, a laser line 3 and a laser line 4. When the laser stripe is positioned on the laser line 1, the detection of the initial point of the welding line is started, the shape of the laser stripe is a straight line before the laser stripe approaches the initial point of the welding line, when the laser stripe reaches the initial point of the welding line, the laser stripe becomes the shape of the profile of the welding line, and the coordinates of the initial point of the welding line are obtained according to the change of the shape of the laser stripe. Next, an initial point detection algorithm for V-groove welds, lap welds, and fillet welds provided by the present application is described.
1. And detecting the initial point of the V-shaped welding seam. As shown in fig. 9, the V-shaped bead initial point detection is divided into three stages, namely an initial stage, an approach stage, and an arrival stage. As shown in fig. 9 (1), in the initial stage, only one laser line passes through the region of interest of the weld image. As shown in fig. 9 (2), when the mechanical hand-held laser weld tracking sensor is moved toward the V-shaped workpiece, the laser line becomes three parts including the laser line 1 and the laser line 2 on the workpiece and the laser line 3 on the indexer. The mechanical hand-held laser weld tracking sensor continues to move forward as shown in fig. 9 (3), with all laser lines on the workpiece. The detection of the V-groove weld initiation point is shown in algorithm 1 and equation (8), where Mr is defined as the line with the highest laser stripe brightness.
Algorithm 1:
2. and detecting the initial point of the lap joint. As shown in fig. 10, the lap seam initial point detection is divided into three stages, namely an initial stage, an approach stage, and an arrival stage. In fig. 10 (1), only one laser line passes through the weld image region of interest. In fig. 10 (2), when the mechanical hand-held laser weld tracking sensor is moved toward the overlapping workpiece, the laser line becomes two parts, the laser line 1 on the workpiece and the laser line 2 on the indexer. As shown in fig. 10 (3), the mechanical hand-held laser weld tracking sensor continues to move forward with both laser lines on the workpiece.
The detection of the lap weld initiation point is shown in algorithm 2 and equation (9).
Wherein, (P) x1 ，P y1 ) And (P) x2 ,P y2 ) Respectively point P 1 Sum point P 2 Pixel coordinates, H th1 ，H th2 And H th3 Is an error discrimination threshold.
Algorithm 2:
3. the initial point detection of the fillet weld is divided into three stages, i.e., an initial stage, an approach stage, and an arrival stage, as shown in fig. 11. In fig. 11 (1), there is only one laser line in the region of the weld image ROI. In FIG. 11 (2), the sensor is oriented at an angle when the laser weld is mechanically heldWhen the workpiece is moved, the laser line is changed into three parts, namely a laser line 1 and a laser line 2 on the workpiece and a laser line 3 on a positioner. As shown in fig. 11 (3), when the mechanical hand-held laser seam tracking sensor continues to move forward, the number of highlight points of the bottom laser line 3 gradually decreases, and the number of highlight points of the two inclined lines 1 and 2 continuously increases. Finally, the laser line 3 disappears and the laser line 1 and the laser line 2 are connected together. The present application briefly describes the detection of the fillet weld starting point as shown in algorithm 3 and equation (10). Wherein T is fi Defined as the threshold value of the second order difference value, D l And D r The two-level differential values calculated from the left and right sides of the laser line center profile are respectively calculated.
Algorithm 3:
wherein, (P) x1 ，P y1 ) And (P) x2 ，P y2 ) Respectively the jump points P 1 And trip point P 2 Pixel coordinates, N x And N y Respectively point P 1 Sum point P 2 The error in the abscissa and ordinate directions discriminates the threshold value.
In this embodiment, the initial point image coordinates of multiple weld seam types can be obtained by the weld seam initial point detection algorithm provided by the application. The three-dimensional coordinates of the weld characteristic points in the robot base coordinate system can be obtained by the formula (3) and the formula (4). After the three-dimensional coordinates of the initial point of the welding seam under the robot base coordinate system are obtained, the coordinates are compared with the coordinates of the initial point of the welding seam in the teaching track, and the deviation of the coordinates and the coordinates is obtained to be the deviation of the initial point of the welding seam. The upper computer sends the initial point deviation to the robot controller through the Ethernet, and after the robot controller receives the deviation, the robot is controlled to compensate the welding seam initial point deviation under the base coordinate system, so that automatic alignment of the welding gun and the welding seam initial point is realized. In practical applications, there are cases where the deviation of the initial point position is too large, and the one-time correction of the deviation may cause the robot to shake drastically or exceed the maximum speed. Therefore, the present application compensates for the weld initiation point deviation multiple times. Optionally, the offset compensation period of the initial point of the welding seam is 40ms, 1/10 of the initial offset is compensated each time, and the total time consumption of automatic alignment of the initial point of the welding seam is 400ms.
Based on the foregoing embodiment, in this embodiment, according to the weld feature point coordinates, a current expected weld point coordinate is calculated, and according to the current expected weld point coordinate, a weld deviation in a complex space curve weld tracking process is calculated, so that a welding position is adjusted in real time according to the weld deviation, including:
based on a sliding queue method, three-dimensional coordinate data of weld characteristic points contained in a current queue are obtained;
based on a preset times of B-spline fitting method, fitting three-dimensional coordinate data of weld characteristic points contained in the current queue into a smooth curve;
acquiring coordinates of a current welding gun center point under a welding robot base coordinate system and three-dimensional coordinates of a welding seam characteristic point on a smooth curve;
calculating the current expected welding point coordinates according to the coordinates of the current welding gun center point under the welding robot base coordinate system and the three-dimensional coordinates of the welding line characteristic points on the smooth curve;
and calculating the weld deviation in the complex space curve weld tracking process according to the current expected weld point coordinates, so that the position of the center point of the welding gun is adjusted in real time according to the weld deviation.
In this embodiment, the weld tracking is started after the automatic alignment of the welding gun and the initial point of the weld is completed. Because the space curve weld joint has larger curvature, and a section of advanced distance is always reserved between the weld joint tracking sensor and the welding gun, how to calculate accurate welding errors according to the acquired weld joint data and correct the errors in real time is an important problem. The embodiment of the application provides a sliding data team based on cubic B spline fittingThe method can effectively calculate the welding deviation in the space curve weld joint tracking process. Specifically, a schematic diagram of the sliding data queue algorithm is shown in fig. 12. During welding, FP 1 ～FP n Is a characteristic point of a welding seam, wherein FP 1 For the weld start point, FP n Is the weld end point. During the weld tracking process, when the welding gun is aligned with the initial weld point, the laser stripe is projected to point FP k And (3) upper part. k may be determined by the following formula:
k＝L*F c /v (11)
wherein L is the distance of the welding seam scanned before the welding gun reaches the starting point of the welding seam, F c And the acquisition frequency of the characteristic points of the welding seam is v, and the welding speed of the robot is v.
In the present embodiment, it is assumed that the welding gun is at T 1 And (3) aligning the moment with the initial point of the welding seam, and storing the coordinates of the k characteristic points of the welding seam in the FP, which is called as a preparation queue. If the next weld feature extraction fails or deviates too much, the FP and the data in the ready queue will not be updated. If the next weld feature point is successfully extracted, the point is saved to the FP and the data in the ready queue will slide forward on the FP. And repeating the process, continuously sliding the preparation queue on the FP, and calculating and correcting the weld joint deviation in real time. At T n-k+1 At that point, the weld end point is detected, at which time the FP and the weld data of the ready queue are no longer updated. And automatically updating the weld position data in the preparation queue by a sliding data queue method. Only processing the weld data in the preparation queue improves the calculation efficiency of the welding deviation in the weld tracking process.
In this embodiment, three B-spline fits are required to be made to the data in the ready queue. Because the weld position data in the preparation queue are discrete points, in order to improve the calculation accuracy of the welding error of the tracking system, the weld position data points are fitted by adopting cubic B-spline. Determining a cubic B spline curve by using four discrete points, and assuming that four welding points are P respectively 1 (x 1 ，y 1 ,z 1 ),P 2 (x 2 ,y 2 ,z 2 )、P 3 (x 3 ,y 3 ,z 3 )、P 4 (x 4 ,y 4 ,z 4 ) The parametric expression for the cubic b-spline is:
wherein, t is more than or equal to 0 and less than or equal to 1, and the component form of the cubic b spline is as shown in a formula (13):
wherein:
for k weld data in the ready queue, a cubic B-spline was used for fitting. First, one data point is added at each end of the weld data, i.e., k+2 data are fitted. At this time, k+2 discrete points are counted as P i (i=1, 2, …, k+2), from point P 1 、P 2 、P 3 And P 4 Fitting a first cubic B-spline curve from point P 2 、P 3 、P 4 And P 5 Fitting a second cubic B-spline curve, and so on, the kth-1 cubic B-spline curve is formed by P k-1 、P k 、P k+1 And P k+2 Fitting. Finally, discrete weld points in the position preparation queue are fitted to a smooth curve.
As can be seen from fig. 13, P t (t x ，t y ，t z ) Seating of a Tool Center Point (TCP) in a robot-based coordinate systemMark, P i (x i ，y i ，z i ) And acquiring coordinates of the weld characteristic points under a robot base coordinate system for the laser weld tracking sensor. P (P) e (p x ，p y ，p z ) Is the desired weld point coordinates. Welding deviation E (E) x ，e y ，e z ) Is P t And P e Welding errors between the two. Assuming that the robot welds in the y-axis direction, the weld bias is from the x-axis and z-axis directions. First, calculate the deviation of the data point in the ready queue in the y-direction, find the y-axis coordinate t from TCP y Recent y i . Obtaining point P by three times of B spline fitting i Coefficient a of (2) 0 、a 1 、a 2 、a 3 、b 0 、b 1 、b 2 、b 3 C 0 、c 1 、c 2 、c 3 . Point P i Y-axis coordinate y of (2) i Substitution of y (t) =b 0 +b 1 t+b 2 t 2 +b 3 t 3 The parameter t (0.ltoreq.t.ltoreq.1) can be obtained, and the desired weld position is calculated as follows:
p x ＝x(t)＝a 0 +a 1 t+a 2 t 2 +a 3 t 3 (17)
p z ＝z(t)＝c 0 +c 1 t+c 2 t 2 +c 3 t 3 (18)
therefore, the welding deviation in the x-axis direction is:
Δ x ＝p x -t x (19)
the welding bias in the z-axis direction is:
Δ z ＝p z -t z (20)
similarly, if the robot welds along the x-axis, the weld bias in the z-direction is the same as equation (20), and the weld bias in the y-axis direction is:
Δ y ＝p y -t y (21)
and finally, the industrial computer sends the welding deviation to the robot controller through the Ethernet, and the robot controller controls the welding gun to shift in the directions of the x axis, the y axis and the z axis under the robot coordinate system, so that real-time weld tracking is realized.
Based on the foregoing embodiment, in this embodiment, establishing a discrete posture model of the complex space curve weld according to the weld feature point coordinates, so that the welding gun posture is adjusted according to the discrete posture model, includes:
obtaining a direction vector, a proximity vector and a normal vector at each weld characteristic point, and establishing a discrete attitude model of the complex space curve weld according to the direction vector, the proximity vector and the normal vector at each weld characteristic point;
and calculating the current welding posture deviation of the welding robot according to the discrete posture model of the complex space curve welding seam so as to adjust the current welding posture of the welding robot in real time according to the current welding posture deviation of the welding robot.
In this embodiment, it should be noted that, since the shape, angle and size of the complex space curve weld are always changed, the posture of the welding gun is also an important factor affecting the weld formation and welding quality, and in order to ensure the welding quality, real-time adjustment of the welding posture of the welding robot is necessary during the welding process of the complex space curve weld. As shown in fig. 14, the space curve weld characteristic point of the V-groove includes both side edge points p1, p3 and a bottom center point p2. And establishing a discrete posture model of the space curve welding seam according to the welding seam characteristic point sampling data of the space curve welding seam, and controlling the local posture of the welding gun in real time. The discrete model of the weld is a series of discrete coordinate points of the characteristic points of the weld under a robot coordinate system, as shown in fig. 15, and the establishment flow of the weld posture model is as follows:
1. Obtaining a direction vector o (i) at a weld characteristic point: o (i) represents the tangential direction of the weld of the space curve at the ith sampling point, and can be obtained by obtaining the first derivative of the weld curve at the ith sampling point:
where i, j, k are unit vectors of x-axis, y-axis, and z-axis, respectively, in the robot base coordinate system.
2. Obtaining a proximity vector a (i): a (i) represents a normal vector of the space curve weld joint perpendicular to the weld joint at the ith sampling point, and can be calculated by the following formula:
wherein, the symbol represents the dot product operator of two vectors, and the vector b (i) is the vector v of the space curve welding seam at the ith sampling point 1 Vector v 3 Unit vector of bisector, as shown in fig. 13, vector v 1 Is the characteristic point p 1 And p is as follows 2 A determined direction vector; vector v 3 Is the characteristic point p 2 And p is as follows 3 The expression of the determined direction vector, b (i), is as follows:
3. obtaining a normal vector n (i): the vector product operation can be obtained by the direction vector o (i) and the approach vector a (i):
n(i)＝o(i)×a(i) (25)
therefore, the direction vector, the approach vector and the normal vector at the weld feature point can be obtained through the above 1, 2 and 3, and the rotation matrix R of the desired pose of the weld can be represented by the above three vectors:
the euler angles of the expected x-axis, y-axis and z-axis directions under the robot base coordinate system can be calculated by rotating the matrix R, and the calculation flow is shown in an algorithm 4.
Algorithm 4:
in this embodiment, it can be understood that the rotation matrix R can be converted into euler angles of X, Y, Z in three directions by the algorithm 4
θ, φ. And after the welding seam pose model is obtained, the pose of the welding gun is overlapped with the expected pose of the welding seam, so that the optimal pose welding can be realized. The current pose (x, y, z, R) of the robot can be read from the robot controller x ,R y ,R z ) Wherein R is x ，R y ，R z Euler angles of the robot in the X-axis, Y-axis and Z-axis directions are respectively shown. Therefore, the welding attitude deviation in the X-axis direction, the Y-axis direction, and the Z-axis direction in real time is: />
ΔR y ＝R y -θ (28)
ΔR z ＝R z -φ (29)
After the welding posture adjustment quantity is calculated according to formulas (27), (28) and (29), the posture deviation is sent to a robot controller for real-time welding posture adjustment through network communication, so that the robot can maintain the optimal welding posture to finish welding work, and the welding quality is ensured.
As shown in fig. 16, the device used in the method for tracking and adjusting welding posture of a complex space curve welding seam according to the embodiment of the application mainly comprises a laser vision sensor, a welding robot, an industrial computer and a welding device, wherein the industrial robot is a MOTOMAN-MA1440 six-degree-of-freedom welding robot, and the repeated positioning accuracy is +/-0.08 mm. The DX200 controller controls the movements of the robot and interacts with the industrial computer via ethernet. Based on an 8GB RAM and an industrial control host with a main frequency of 2.3GHz, extracting characteristic points of a complex space curve welding seam, and acquiring and completing automatic correction of welding deviation and automatic adjustment of welding posture. The welding equipment mainly comprises an argon/carbon dioxide shielding gas, a MOTOWELD-RD500 welding machine and an automatic wire feeder. As a real-time system, the processing period of the self-updating template matching algorithm is 9ms, the industrial personal computer sends a pose adjustment value to the robot controller once every 30ms, and the robot control period is 40ms.
Based on the same inventive concept, another embodiment of the present invention provides a welding pose adjusting device for a complex space curve welding seam, as shown in fig. 17, the device includes:
the acquisition module 1 is used for acquiring images of the complex space curve weld joint through the laser weld joint tracking sensor;
the extraction module 2 is used for extracting weld feature point coordinates of the complex space curve weld image based on a self-updating template matching algorithm;
the first processing module 3 is used for calculating the current expected welding point coordinates according to the welding line characteristic point coordinates, and calculating the welding line deviation in the complex space curve welding line tracking process according to the current expected welding point coordinates so as to adjust the welding position in real time according to the welding line deviation;
and the second processing module 4 is used for establishing a discrete gesture model of the complex space curve weld according to the weld characteristic point coordinates so as to adjust the welding gesture in real time according to the discrete gesture model.
The welding pose adjusting device for the complex space curve welding seam can be used for executing the method embodiment, and the principle and the technical effect of the welding pose adjusting device are similar and are not repeated here. Based on the same inventive concept, still another embodiment of the present invention provides an electronic device, referring to a schematic structural diagram of the electronic device shown in fig. 18, which specifically includes the following contents: a processor 1801, a memory 1802, a communication interface 1803, and a communication bus 1804;
Wherein the processor 1801, the memory 1802, and the communication interface 1803 perform communication with each other through the communication bus 1804; the communication interface 1803 is used for implementing information transmission between devices;
the processor 1801 is configured to invoke a computer program in the memory 1802, where the processor executes the computer program to implement all the steps of the welding pose adjustment method for a complex space curve welding seam.
Based on the same inventive concept, a further embodiment of the present invention provides a non-transitory computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements all the steps of the above-described welding pose adjustment method for a complex space curve weld.
Further, the logic instructions in the memory described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment of the invention. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the method for welding pose adjustment of a complex space curve weld seam according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The welding pose adjusting method of the complex space curve welding seam is characterized by comprising the following steps of:
step 101, acquiring images of a complex space curve weld joint through a laser weld joint tracking sensor;
step 102, extracting weld feature point coordinates of a complex space curve weld image based on a self-updating template matching algorithm;
step 103, calculating the current expected welding point coordinates according to the welding point characteristic point coordinates, and calculating the welding point deviation in the complex space curve welding line tracking process according to the current expected welding point coordinates so as to adjust the welding position in real time according to the welding point deviation;
104, establishing a discrete posture model of the complex space curve weld according to the weld characteristic point coordinates so as to adjust the welding posture in real time according to the discrete posture model;
The extracting the weld feature point coordinates of the complex space curve weld image based on the self-updating template matching algorithm comprises the following steps:
step 201, calculating pixel gray values of a complex space curve weld image, and determining an interested region of the weld image;
step 202, generating a matching template corresponding to the weld image according to the characteristics of the weld image, and extracting weld characteristic point coordinates of the weld image based on a template matching algorithm;
step 203, updating the matching template according to the currently extracted weld feature point coordinates, and determining the interested region of the weld image of the next frame, so that the next weld feature point coordinates are extracted according to the updated matching template;
step 204, repeatedly executing step 203 to extract weld feature point coordinates of the whole complex space curve weld image;
after extracting the weld characteristic point coordinates of the complex space curve weld image, the method further comprises the following steps:
converting the two-dimensional coordinates of each weld characteristic point under the laser weld tracking sensor coordinate system into three-dimensional coordinates under the welding robot base coordinate system according to the coordinate change relation between the laser weld tracking sensor coordinate system and the welding robot base coordinate system;
Acquiring a weld initial point coordinate in the complex space curve weld image according to the change of the laser stripe shape in the complex space curve weld image, and converting the weld initial point coordinate into a welding robot base coordinate system;
comparing the initial point coordinates of the welding seam under the welding robot base coordinate system with initial point coordinates in a teaching track formed by the welding seam characteristic point coordinates to obtain welding seam initial point coordinate deviation;
and adjusting the position of the center point of the welding gun according to the coordinate deviation of the initial point of the welding seam, thereby realizing the automatic alignment of the welding gun and the initial point of the welding seam.
2. The welding pose adjustment method of a complex space curve weld according to claim 1, wherein calculating a current expected welding point coordinate according to the weld feature point coordinate, and calculating a weld deviation in a complex space curve weld tracking process according to the current expected welding point coordinate, so as to adjust a welding position in real time according to the weld deviation, comprises:
based on a sliding queue method, three-dimensional coordinate data of weld characteristic points contained in a current queue are obtained;
based on a preset times of B-spline fitting method, fitting three-dimensional coordinate data of weld characteristic points contained in the current queue into a smooth curve;
Acquiring coordinates of a current welding gun center point under a welding robot base coordinate system and three-dimensional coordinates of a welding seam characteristic point on a smooth curve;
calculating the current expected welding point coordinates according to the coordinates of the current welding gun center point under the welding robot base coordinate system and the three-dimensional coordinates of the welding line characteristic points on the smooth curve;
and calculating the weld deviation in the complex space curve weld tracking process according to the current expected weld point coordinates, so that the position of the center point of the welding gun is adjusted in real time according to the weld deviation.
3. The method for adjusting the welding pose of a complex space curve weld according to claim 1, wherein establishing a discrete pose model of the complex space curve weld according to the weld feature point coordinates so that the welding gun pose is adjusted according to the discrete pose model comprises:
obtaining a direction vector, a proximity vector and a normal vector at each weld characteristic point, and establishing a discrete attitude model of the complex space curve weld according to the direction vector, the proximity vector and the normal vector at each weld characteristic point;
and calculating the current welding posture deviation of the welding robot according to the discrete posture model of the complex space curve welding seam so as to adjust the current welding posture of the welding robot in real time according to the current welding posture deviation of the welding robot.
4. The welding pose adjustment method of the complex space curve weld joint according to claim 1, wherein the coordinate change relation between the laser weld joint tracking sensor coordinate system and the welding robot base coordinate system is:
P’ b ＝T 6 T m P’ c
wherein P' b T is the homogeneous form of three-dimensional coordinates of weld joint characteristic points under a welding robot base coordinate system 6 For the robot pose transformation matrix, T m For a matrix of rotational and translational relationships between the camera and robot tool coordinate systems, P' c Is a homogeneous form of three-dimensional coordinates of the weld feature points in a camera coordinate system.
5. The method for adjusting welding pose of a complex space curve welding seam according to claim 1, wherein the extracting welding seam feature point coordinates of the complex space curve welding seam image based on a template matching algorithm comprises:
calculating the sum of gray level differences between the matching template and the region of interest according to the following formula, and taking the central point of the matching template image at the position with the minimum deviation as the characteristic point of the complex space curve welding seam; the formula is:
wherein T (x, y) represents the pixel gray value of the (x, y) coordinate on the matching template, I (x, y) represents the pixel gray value of the (x, y) coordinate in the region of interest, R (x, y) represents the sum of gray value squared differences between the matching template at the (x, y) coordinate of the region of interest and the pixels of the region of interest, and the smaller the value of R (x, y) is, the higher the matching degree is.
6. The utility model provides a welding position appearance adjusting device of complicated space curve welding seam which characterized in that includes:
the acquisition module is used for acquiring images of the complex space curve weld joint through the laser weld joint tracking sensor;
the extraction module is used for extracting weld feature point coordinates of the complex space curve weld image based on a self-updating template matching algorithm;
the first processing module is used for calculating the current expected welding point coordinates according to the welding line characteristic point coordinates, and calculating the welding line deviation in the complex space curve welding line tracking process according to the current expected welding point coordinates so as to adjust the welding position in real time according to the welding line deviation;
the second processing module is used for establishing a discrete gesture model of the complex space curve weld according to the weld characteristic point coordinates so as to adjust the welding gesture in real time according to the discrete gesture model;
the extraction module is specifically configured to:
calculating pixel gray values of the complex space curve weld joint images, and determining an interested region of the weld joint images;
generating a matching template corresponding to the weld image according to the characteristics of the weld image, and extracting weld characteristic point coordinates of the weld image based on a template matching algorithm;
Updating the matching template according to the currently extracted weld feature point coordinates, and determining an interested region of a weld image of the next frame so as to extract the next weld feature point coordinates according to the updated matching template;
repeatedly executing the steps of updating the matching template according to the currently extracted weld feature point coordinates and determining the interested region of the weld image of the next frame so as to extract the next weld feature point coordinates according to the updated matching template, thereby realizing the extraction of the weld feature point coordinates of the weld image of the whole complex space curve;
the automatic alignment module is used for converting the two-dimensional coordinates of each weld characteristic point under the coordinate system of the laser weld tracking sensor into the three-dimensional coordinates under the coordinate system of the welding robot base according to the coordinate change relation between the coordinate system of the laser weld tracking sensor and the coordinate system of the welding robot base; acquiring a weld initial point coordinate in the complex space curve weld image according to the change of the laser stripe shape in the complex space curve weld image, and converting the weld initial point coordinate into a welding robot base coordinate system; comparing the initial point coordinates of the welding seam under the welding robot base coordinate system with initial point coordinates in a teaching track formed by the welding seam characteristic point coordinates to obtain welding seam initial point coordinate deviation; and adjusting the position of the center point of the welding gun according to the coordinate deviation of the initial point of the welding seam, thereby realizing the automatic alignment of the welding gun and the initial point of the welding seam.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, implements the steps of the method for welding pose adjustment of complex space curve welds according to any of claims 1 to 5.
8. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the welding pose adjustment method of a complex space curve weld according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111056501.8A CN113894481B (en) | 2021-09-09 | 2021-09-09 | Welding pose adjusting method and device for complex space curve welding seam |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111056501.8A CN113894481B (en) | 2021-09-09 | 2021-09-09 | Welding pose adjusting method and device for complex space curve welding seam |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113894481A CN113894481A (en) | 2022-01-07 |
| CN113894481B true CN113894481B (en) | 2023-05-09 |
Family
ID=79028001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111056501.8A Active CN113894481B (en) | 2021-09-09 | 2021-09-09 | Welding pose adjusting method and device for complex space curve welding seam |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113894481B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114289857B (en) * | 2022-01-25 | 2023-07-07 | 江西理工大学 | Method for autonomously correcting travelling path of stirring head of friction stir welding equipment |
| CN115805358B (en) * | 2023-02-01 | 2023-06-23 | 南通华泰信息科技有限公司 | Information integration system based on fuzzy control |
| CN115870678B (en) * | 2023-03-02 | 2023-08-18 | 成都熊谷加世电器有限公司 | Posture adjusting system and method of internal welding machine, internal welding machine and storage medium |
| CN115890053B (en) * | 2023-03-02 | 2023-08-18 | 成都熊谷加世电器有限公司 | Internal welding machine alignment method and device, internal welding machine and storage medium |
| CN116704017B (en) * | 2023-08-09 | 2023-11-14 | 烟台大学 | Mechanical arm pose detection method based on visual mixing |
| CN117300301B (en) * | 2023-11-30 | 2024-02-13 | 太原科技大学 | Welding robot weld joint tracking system and method based on monocular line laser |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1782659B (en) * | 2004-12-02 | 2010-04-14 | 中国科学院自动化研究所 | Welding seam tracking sight sensor based on laser structure light |
| CN103008881A (en) * | 2012-12-05 | 2013-04-03 | 中国电子科技集团公司第四十五研究所 | Seam tracking method based on template matching |
| CN103418950A (en) * | 2013-07-03 | 2013-12-04 | 江南大学 | Automatic posture adjusting method for industrial welding robot in seam tracking process |
| CN104091323A (en) * | 2014-05-23 | 2014-10-08 | 湘潭大学 | Weld tracking feature signal extracting method based on MP-NBFE method |
| CN106312397B (en) * | 2016-10-12 | 2018-04-13 | 华南理工大学 | A kind of the welding track automatic tracking system and method for laser vision guiding |
| CN107798330B (en) * | 2017-11-10 | 2021-07-20 | 上海电力学院 | Weld image feature information extraction method |
| CN109272544B (en) * | 2018-10-22 | 2020-09-08 | 湖北文理学院 | Structured light three-dimensional measurement model of pipeline all-position welding line and image processing method |
| CN109623825B (en) * | 2018-12-30 | 2021-11-16 | 深圳市越疆科技有限公司 | Movement track planning method, device, equipment and storage medium |
| CN110211182B (en) * | 2019-05-31 | 2023-03-31 | 东北大学 | Liquid crystal backlight visual positioning method based on gray scale matching and target contour |
| CN110480128A (en) * | 2019-08-28 | 2019-11-22 | 华南理工大学 | A kind of real-time welding seam tracking method of six degree of freedom welding robot line laser |
| CN111299761B (en) * | 2020-02-28 | 2021-09-21 | 华南理工大学 | Real-time attitude estimation method of welding seam tracking system |
| CN111745266A (en) * | 2020-06-09 | 2020-10-09 | 宝冠科技(苏州)有限公司 | Corrugated board welding track generation method and system based on 3D vision position finding |
| CN112508971B (en) * | 2020-12-21 | 2023-08-22 | 华南理工大学 | Weld joint positioning method, system and storage medium based on simulation structure light stripe |
| CN113319411A (en) * | 2021-03-04 | 2021-08-31 | 湖南大学 | Visual positioning method and system and computing equipment |
| CN113042862A (en) * | 2021-03-12 | 2021-06-29 | 湖北文理学院 | Welding deviation detection system and detection method based on active and passive visual combination |
-
2021
- 2021-09-09 CN CN202111056501.8A patent/CN113894481B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113894481A (en) | 2022-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113894481B (en) | Welding pose adjusting method and device for complex space curve welding seam | |
| Tsai et al. | Machine vision based path planning for a robotic golf club head welding system | |
| CN113798634B (en) | Method, system and equipment for teaching spatial circular weld and tracking weld | |
| CN106181162B (en) | A kind of real-time weld joint tracking detection method based on machine vision | |
| Chen et al. | The autonomous detection and guiding of start welding position for arc welding robot | |
| JP6348093B2 (en) | Image processing apparatus and method for detecting image of detection object from input data | |
| CN108637435A (en) | A kind of three-dimensional seam tracking system and method for view-based access control model and arc voltage sensing | |
| CN112620926B (en) | Welding spot tracking method and device and storage medium | |
| US20110282492A1 (en) | Method of controlling a robotic tool | |
| CN109658456A (en) | Tank body inside fillet laser visual vision positioning method | |
| WO2014161603A1 (en) | A robot system and method for calibration | |
| CN108907526A (en) | A kind of weld image characteristic recognition method with high robust | |
| Ryberg et al. | Stereo vision for path correction in off-line programmed robot welding | |
| US11565422B2 (en) | Controller of robot apparatus for adjusting position of member supported by robot | |
| Zhou et al. | Autonomous acquisition of seam coordinates for arc welding robot based on visual servoing | |
| Ma et al. | Efficient and accurate start point guiding and seam tracking method for curve weld based on structure light | |
| CN114571160B (en) | Off-line curved surface weld extraction and attitude estimation method | |
| CN114654465A (en) | Welding seam tracking and extracting method based on line laser structure optical vision sensing | |
| CN116833645A (en) | Weld autonomous identification and welding method and system based on mobile robot | |
| CN116542914A (en) | Weld joint extraction and fitting method based on 3D point cloud | |
| CN114926531A (en) | Binocular vision based method and system for autonomously positioning welding line of workpiece under large visual field | |
| CN112643718B (en) | Image processing apparatus, control method therefor, and storage medium storing control program therefor | |
| JP7321953B2 (en) | Automatic welding system, welding method, learning device, method for generating learned model, learned model, estimation device, estimation method, and program | |
| CN114043488A (en) | Teaching automatic deviation rectifying method of multi-optical-knife vision-assisted robot detection system | |
| JP6285765B2 (en) | Information processing apparatus and information processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |