CN117655521A - Visual positioning guide laser welding method and system - Google Patents
Visual positioning guide laser welding method and system Download PDFInfo
- Publication number
- CN117655521A CN117655521A CN202311711064.8A CN202311711064A CN117655521A CN 117655521 A CN117655521 A CN 117655521A CN 202311711064 A CN202311711064 A CN 202311711064A CN 117655521 A CN117655521 A CN 117655521A
- Authority
- CN
- China
- Prior art keywords
- welding
- image
- point
- weld
- contour
- 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.)
- Pending
Links
- 238000003466 welding Methods 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000000007 visual effect Effects 0.000 title claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 206010044565 Tremor Diseases 0.000 abstract 1
- 230000008569 process Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000002679 ablation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
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
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/20—Bonding
- B23K26/21—Bonding by welding
Landscapes
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Engineering & Computer Science (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- Laser Beam Processing (AREA)
Abstract
The invention discloses a visual positioning guide laser welding method and a visual positioning guide laser welding system, comprising the steps of collecting a weld surface image of an object to be welded and processing the image to obtain a weld edge contour map; wiping the non-welding seam edge area to obtain contour images of the inner edge and the outer edge of the welding seam; extracting the coordinates of the centroid of the outline of the outer edge of the welding seam, and connecting the centroid C with the outer outline point P w Obtaining the intersection point P with the inner contour N Taking P w And P N Is the welding point P at the middle point C The method comprises the steps of carrying out a first treatment on the surface of the Traversing all outline points in turn according to the method to obtain a center point Set (P) of the welding line C ) And converts it into a set of physical coordinate points W ‑ Set(P C ) The method comprises the steps of carrying out a first treatment on the surface of the Performing curve fitting on the center point set by using a fitting algorithm to obtain a smooth weld curve; and controlling the welding head to weld according to the fitted path. The method acquires the inner and outer edge patterns of the welding seam to obtain the central path of the welding seam as a welding path, so that the welding precision is improved; simultaneously, a cubic B spline curve fitting algorithm is adopted to obtain a smoother welding path, and the tremble of a welding head is reducedAnd the welding quality is improved.
Description
Technical Field
The invention relates to the field of machine vision, in particular to a vision positioning guiding laser welding method and system.
Background
Laser welding is one of the important aspects of laser processing technology application, and is mainly applied to precision welding of tiny parts. The laser radiation heats the surface of the workpiece, the surface heat diffuses to the inside through heat conduction, and the workpiece is melted by controlling parameters such as the width, the energy, the power density, the repetition frequency and the like of the laser pulse, so that a specific molten pool is formed.
The weld generally has a certain width, and in the conventional welding process, it is difficult to ensure that the welding head is always kept at the center of the weld. When the welding head deviates from the center of the welding head, uneven heating of two sides of the welding seam can be caused, and the welding quality is affected. Meanwhile, in practical welding application, the shapes of the edges at two sides of the welding line may be irregular, and saw-tooth shapes exist or a plurality of undulating edges exist in a certain length, so that a plurality of center points exist in a short distance, frequent shaking of a welding head can occur in the welding process, namely the welding efficiency is influenced, and the welding quality is also influenced.
Disclosure of Invention
The invention provides a visual positioning guide laser welding method and a visual positioning guide laser welding system, which can reduce the moving distance of a welding head, thereby improving the welding efficiency and the welding quality.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a visual positioning guidance laser welding method, comprising the steps of:
s1, acquiring a weld surface image of an object to be welded by a camera, and processing the image to obtain a weld edge profile;
s2, manually erasing the non-welding seam edge area, and only leaving contour images of the inner edge and the outer edge of the welding seam;
s3, extracting a welding seam outer edge contour centroid C, and connecting the centroid C with an outer contour point P w Obtaining the intersection point P with the inner contour N Taking P w And P N Is the welding point P where the midpoint of (2) C ；
S4, traversing all the outer contour points in sequence according to the method of the step S3, and obtaining a center point Set (P) of the welding line C ) And converts it into a Set of physical coordinate points W-Set (P C )；
S5, performing curve fitting on the central point Set W-Set (PC) by using a fitting algorithm to obtain a smooth weld curve;
s6, controlling the welding head to weld according to the fitted path.
As a preferred embodiment of the foregoing, step S1 includes: firstly, controlling a high-definition CCD camera to move above an object to be welded, shooting a clear welding line image by adjusting a focal length, and carrying out pretreatment, graying and image enhancement on the image; dividing the processed image, and dividing the welding line image from the background; and performing edge detection operation on the segmented weld joint image, and extracting contour points to obtain a weld joint contour picture.
As a preferable aspect of the above solution, step S2 includes: the mouse is used for erasing other interference contours in the segmented weld joint images by adopting an 'rubber' function on the images, the principle is that the cursor moves on the images to acquire image pixel coordinates, and when the cursor moves to the interference contours, the pixels in a certain area with the cursor as the center are set to 0, so that the white contours are changed into black, and the interference contours are erased.
As a preferable aspect of the foregoing, steps S3 and S4 include: acquiring the coordinate of the centroid C of the outer contour of the welding seam, and connecting the centroid with an outer contour point P w The connection intersects the inner contour at point P N Taking P w And P of N The midpoint is taken as a welding point P C And traversing all outer contour points in the same way to obtain a welding center point Set (PC), wherein the coordinates of the point Set are image coordinates, the image coordinates are converted into physical coordinates, a conversion relation between an image coordinate system and the physical coordinate system is obtained by using a nine-point calibration method, and the physical coordinates W-Set (PC) of the welding center point are calculated through the corresponding conversion relation.
As a preferable aspect of the above, step S5 includes: and performing three times of B spline fitting on the discrete weld center point Set W-Set (PC) to obtain a smooth curve.
As a preferable aspect of the above solution, step S6 includes: and transmitting the fitted curve as a welding path to a motion controller, wherein the motion controller controls the welding head to move according to the welding path, so as to finish laser welding.
A vision positioning guidance laser welding system comprises a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to realize the method.
Due to the structure, the invention has the beneficial effects that:
the welding line edge is detected visually, the welding line center is extracted, and a welding path is determined; and simultaneously, a cubic B spline interpolation algorithm is adopted to fit the welding path, so that a smoother welding path is obtained. Through the improvement of the two points, the welding head is always positioned at the center of the welding seam in the welding process, frequent shaking of the welding head in the welding process is also guaranteed, and the moving distance of the welding head is reduced, so that the welding efficiency and the welding quality are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the description of the embodiments will be briefly described below.
FIG. 1 is a workflow diagram of the present invention;
FIG. 2 is a graph of image segmentation effect according to the present invention;
FIG. 3 is a weld edge detection chart of the present invention;
FIG. 4 is a graph of the effect of a cubic B-spline curve fit of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Please refer to fig. 1 to 4. The aim of the embodiment of the invention is that: detecting the center of the welding seam in a visual detection mode, and preliminarily determining a welding path; and simultaneously, performing curve fitting on the weld joint center by adopting a cubic B spline fitting algorithm to obtain a smooth welding path. And the welding precision and the welding quality are ensured. Specific:
as shown in fig. 1, the present embodiment provides a visual positioning guidance laser welding method, which includes the following steps:
s1, acquiring a weld surface image of an object to be welded by a camera, and processing the image to obtain a weld edge profile;
s2, manually erasing the non-welding seam edge area, and only leaving contour images of the inner edge and the outer edge of the welding seam;
s3, extracting a welding seam outer edge contour centroid C, and connecting the centroid C with an outer contour point P w Obtaining the intersection point P with the inner contour N Taking P w And P N Is the welding point P where the midpoint of (2) C ；
S4, traversing all the outer contour points in sequence according to the method of the step S3, and obtaining a center point Set (P) of the welding line C ) And converts it into a Set of physical coordinate points W-Set (P C )；
S5, performing curve fitting on the central point Set W-Set (PC) by using a fitting algorithm to obtain a smooth weld curve;
s6, controlling the welding head to weld according to the fitted path.
Wherein:
the step S1 comprises the following steps: firstly, controlling a high-definition CCD camera to move above an object to be welded, shooting a clear welding seam image by adjusting a focal length, and transmitting the acquired image to an image processing system, wherein the image processing system performs preprocessing, graying and image enhancement processing on the image so that the welding seam characteristics are more outstanding; the method comprises the steps of dividing a processed image, namely thresholding the processed image, wherein the general purpose of thresholding the image is to separate a target area and a background area from a gray level image, and the thresholding of the image generally comprises a fixed threshold value and an adaptive threshold value, but the ideal dividing effect is hardly achieved only by the fixed threshold value of equipment, and the embodiment adopts the adaptive threshold value method to divide so as to obtain a better weld image, as shown in fig. 2; and performing edge detection operation on the segmented weld joint image, and extracting contour points to obtain a weld joint contour picture.
The step S2 comprises the following steps: the mouse is used for erasing other interference contours in the segmented weld joint images by adopting an 'rubber' function on the images so as to avoid noise interference and reduce unnecessary calculation amount, and the principle is that a cursor moves on the images to acquire image pixel coordinates, and when the cursor moves to the interference contours, the pixels in a certain area with the cursor as the center are set to 0, so that the white contours are changed into black, and the interference contours are erased.
The steps S3 and S4 include: and determining a welding line center path according to the detected inner edge and the detected outer edge of the welding line, as shown in fig. 3. Acquiring the coordinate of the centroid C of the outer contour of the welding seam, and connecting the centroid with an outer contour point P w The connection intersects the inner contour at point P N Taking P w And P of N The midpoint is taken as a welding point P C And traversing all the outer contour points in the same way to obtain a welding center point Set (PC), wherein the coordinates of the point Set are image coordinates, and the image coordinates are required to be converted into physical coordinates. The method for converting the image coordinate system into the physical coordinate system comprises the following steps: the welding head reaches the position PR1 by controlling the movement mechanism, the laser is controlled to emit light, a spot ablation trace is left on the laser photographic paper, and 3X 3 spot points (PR 1, PR2 and … PR 9) are manufactured by the same method. The camera collects images of nine light spots, an image detection method is used for detecting image coordinates (PI 1, PI2, … PI 9) of the nine light spots, and a 'nine-point calibration' method is used for obtaining a conversion relation between an image coordinate system and a physical coordinate system. And calculating the physical coordinate W-Set (PC) of the center point of the welding line through the corresponding conversion relation. In the actual welding application, the shape of the edges at two sides of the welding seam may be irregular in the welding seam center path obtained in the step S4, and the edges with saw teeth or multiple undulations in a certain length are formed, so that multiple center points are formed in a short distance, frequent shaking of the welding head can occur in the welding process, namely the welding efficiency is affected, and the welding quality is also affected. Therefore, in order to ensure welding quality and efficiency, the weld center path needs to be optimized.
The step S5 comprises the following steps: three B-spline fits were performed on the discrete weld center point Set W-Set (PC) to obtain a smooth curve, as shown in FIG. 4.
The step S6 comprises the following steps: and transmitting the fitted curve as a welding path to a motion controller, wherein the motion controller controls the welding head to move according to the welding path, so as to finish laser welding.
The embodiment also provides a visual positioning guide laser welding system, which comprises a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to realize the method.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A visual positioning guiding laser welding method is characterized in that: the method comprises the following steps:
s1, acquiring a weld surface image of an object to be welded by a camera, and processing the image to obtain a weld edge profile;
s2, manually erasing the non-welding seam edge area, and only leaving contour images of the inner edge and the outer edge of the welding seam;
s3, extracting a welding seam outer edge contour centroid C, and connecting the centroid C with an outer contour point P w Obtaining the intersection point P with the inner contour N Taking P w And P N Is the welding point P where the midpoint of (2) C ；
S4, traversing all the outer contour points in sequence according to the method of the step S3, and obtaining a center point Set (P) of the welding line C ) And converts it into a Set of physical coordinate points W-Set (P C )；
S5, performing curve fitting on the central point Set W-Set (PC) by using a fitting algorithm to obtain a smooth weld curve;
s6, controlling the welding head to weld according to the fitted path.
2. The visual positioning guide laser welding method according to claim 1, wherein: the step S1 comprises the following steps: firstly, controlling a high-definition CCD camera to move above an object to be welded, shooting a clear welding line image by adjusting a focal length, and carrying out pretreatment, graying and image enhancement on the image; dividing the processed image, and dividing the welding line image from the background; and performing edge detection operation on the segmented weld joint image, and extracting contour points to obtain a weld joint contour picture.
3. The visual positioning guide laser welding method according to claim 1, wherein: the step S2 comprises the following steps: the mouse is used for erasing other interference contours in the segmented weld joint images by adopting an 'rubber' function on the images, the principle is that the cursor moves on the images to acquire image pixel coordinates, and when the cursor moves to the interference contours, the pixels in a certain area with the cursor as the center are set to 0, so that the white contours are changed into black, and the interference contours are erased.
4. The visual positioning guide laser welding method according to claim 1, wherein: the steps S3 and S4 include: acquiring the coordinate of the centroid C of the outer contour of the welding seam, and connecting the centroid with an outer contour point P w The connection intersects the inner contour at point P N Taking P w And P of N The midpoint is taken as a welding point P C And traversing all outer contour points in the same way to obtain a welding center point Set (PC), wherein the coordinates of the point Set are image coordinates, the image coordinates are converted into physical coordinates, a conversion relation between an image coordinate system and the physical coordinate system is obtained by using a nine-point calibration method, and the physical coordinates W-Set (PC) of the welding center point are calculated through the corresponding conversion relation.
5. The visual positioning guide laser welding method according to claim 1, wherein: the step S5 comprises the following steps: and performing three times of B spline fitting on the discrete weld center point Set W-Set (PC) to obtain a smooth curve.
6. The visual positioning guide laser welding method according to claim 1, wherein: the step S6 comprises the following steps: and transmitting the fitted curve as a welding path to a motion controller, wherein the motion controller controls the welding head to move according to the welding path, so as to finish laser welding.
7. A vision positioning guided laser welding system comprising a memory, a processor, and a computer program stored on the memory, characterized in that: a processor executing a computer program to implement the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311711064.8A CN117655521A (en) | 2023-12-13 | 2023-12-13 | Visual positioning guide laser welding method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311711064.8A CN117655521A (en) | 2023-12-13 | 2023-12-13 | Visual positioning guide laser welding method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117655521A true CN117655521A (en) | 2024-03-08 |
Family
ID=90082402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311711064.8A Pending CN117655521A (en) | 2023-12-13 | 2023-12-13 | Visual positioning guide laser welding method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117655521A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118656613A (en) * | 2024-07-08 | 2024-09-17 | 深圳亚太航空技术股份有限公司 | A quick-release connection device detection system and method |
| CN119035887A (en) * | 2024-10-11 | 2024-11-29 | 中国电建集团山东电力管道工程有限公司 | Visual guidance-based weld joint rapid identification method and system |
-
2023
- 2023-12-13 CN CN202311711064.8A patent/CN117655521A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118656613A (en) * | 2024-07-08 | 2024-09-17 | 深圳亚太航空技术股份有限公司 | A quick-release connection device detection system and method |
| CN119035887A (en) * | 2024-10-11 | 2024-11-29 | 中国电建集团山东电力管道工程有限公司 | Visual guidance-based weld joint rapid identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117655521A (en) | Visual positioning guide laser welding method and system | |
| CN109226967B (en) | Active laser vision steady weld joint tracking system for laser-arc hybrid welding | |
| CN108637435B (en) | Three-dimensional weld tracking system and method based on vision and arc pressure sensing | |
| CN210046133U (en) | Welding seam visual tracking system based on laser structured light | |
| CN113427168A (en) | Real-time welding seam tracking device and method for welding robot | |
| CN106181162B (en) | A kind of real-time weld joint tracking detection method based on machine vision | |
| Lü et al. | Feature extraction of welding seam image based on laser vision | |
| CN106825914B (en) | A kind of integrated laser welding gun with welding line tracking function | |
| CN111055054B (en) | Welding seam identification method and device, welding robot and storage medium | |
| CN113894481B (en) | Method and device for adjusting welding position and posture of complex space curve welding seam | |
| US20180147647A1 (en) | Adaptive control method and equipment of arc swing in narrow gap welding | |
| CN114769988A (en) | Welding control method and system, welding equipment and storage medium | |
| CN112750102A (en) | Welding spot positioning method and system based on image processing | |
| CN116833550A (en) | Laser control method and laser processing apparatus | |
| CN114211168A (en) | Method for correcting plane welding seam track based on image subtraction | |
| CN109671059A (en) | A kind of battery case image processing method and system based on OpenCV | |
| CN113909689B (en) | Pipeline welding groove feature extraction method of laser light bar | |
| CN118521528B (en) | A high-precision weld seam recognition and robot tracking path generation method | |
| Reddy et al. | A low-cost vision-based weld-line detection and measurement technique for robotic welding | |
| CN114932292B (en) | Narrow-gap passive vision weld joint tracking method and system | |
| CN115106644A (en) | Self-adaptive judgment method for welding seam starting point, welding method, welding equipment and medium | |
| CN111230883B (en) | Return method and device for crawling welding robot, robot and storage medium | |
| CN115971635A (en) | Friction stir welding control method and system based on visual sensing and machine tool | |
| CN114043080B (en) | Intelligent laser welding treatment method for stainless steel | |
| Zhang et al. | Adaptive control method for ship curved hybrid laser-arc welding through lightweight encoder-decoder architecture |
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 |