CN112935473B - Automatic welding machine based on machine vision and control method thereof - Google Patents
Automatic welding machine based on machine vision and control method thereof Download PDFInfo
- Publication number
- CN112935473B CN112935473B CN202110151456.8A CN202110151456A CN112935473B CN 112935473 B CN112935473 B CN 112935473B CN 202110151456 A CN202110151456 A CN 202110151456A CN 112935473 B CN112935473 B CN 112935473B
- Authority
- CN
- China
- Prior art keywords
- welding
- image
- welding seam
- control module
- module
- 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
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
- B23K9/00—Arc welding or cutting
- B23K9/095—Monitoring or automatic control of welding parameters
- B23K9/0953—Monitoring or automatic control of welding parameters using computing means
Abstract
The invention discloses an automatic welding machine based on machine vision, which comprises a welding current control module, a welding current detection module and a welding current detection module, wherein the welding current control module is used for controlling welding current; the welding speed control module is used for controlling the welding speed; the welding gun height control module is used for controlling the length of a welding arc; the welding seam image acquisition module is used for shooting a welding seam image; the welding seam image storage module is used for pre-storing a standard welding seam image and storing the image shot by the welding seam image acquisition module; the welding seam image analysis module is used for analyzing the welding seam image shot by the welding seam image acquisition module; and the welding machine control module is in communication connection with the welding current control module, the welding speed control module and the welding gun height control module and is used for controlling the welding parameters according to the analysis result of the welding seam image analysis module. The invention can improve the defects of the prior art and improve the speed of detecting the quality of the welding seam.
Description
Technical Field
The invention relates to the technical field of automatic welding, in particular to an automatic welding machine based on machine vision and a control method thereof.
Background
Automatic welding is a welding technique that has developed fast in recent years, and it can effectively replace manual welding in some fields, practices thrift the manpower, improves work efficiency. By introducing the machine vision technology into the field of automatic welding, the automatic welding equipment can automatically check the welding quality. However, the existing machine vision technology needs to perform complex operation processing on the welding seam image when detecting the welding seam, so that the consumed time is long, and the real-time performance of welding quality monitoring is poor.
Disclosure of Invention
The invention aims to provide an automatic welding machine based on machine vision and a control method thereof, which can solve the defects of the prior art and improve the speed of detecting the quality of a welding seam.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows.
An automatic welding machine based on machine vision comprises,
the welding current control module is used for controlling welding current;
the welding speed control module is used for controlling the welding speed;
the welding gun height control module is used for controlling the length of a welding arc;
the welding seam image acquisition module is used for shooting a welding seam image;
the welding seam image storage module is used for prestoring a standard welding seam image and storing the image shot by the welding seam image acquisition module;
the welding seam image analysis module is used for analyzing the welding seam image shot by the welding seam image acquisition module;
and the welding machine control module is in communication connection with the welding current control module, the welding speed control module and the welding gun height control module and is used for controlling the welding parameters according to the analysis result of the welding seam image analysis module.
The control method of the automatic welding machine based on the machine vision comprises the following steps:
A. the welding seam image acquisition module acquires a welding seam image in real time and sends the welding seam image to the welding seam image storage module for storage;
B. b, performing feature analysis on the weld image acquired in real time in the step A by a weld image analysis module, and then comparing the weld image with a historical weld image and a standard weld image stored by a weld image storage module to obtain a comparison result;
C. and C, the welding machine control module sends control commands to the welding current control module, the welding speed control module and the welding gun height control module according to the comparison result obtained in the step B, and controls welding parameters.
Preferably, in the step a, the welding seam image acquisition module acquires 10% to 15% of overlapping portions of two adjacent welding seam images.
Preferably, in the step B, the characteristic analysis of the weld image includes the steps of,
b11, acquiring width data of the welding seam and image blocks with the gray scale exceeding the preset conditions in the welding seam area;
b12, calculating the average weld depth of the image area acquired in the step B1;
and B13, correcting the image characteristics acquired in the step according to the overlapped part of the two adjacent welding seam images.
Preferably, in step B11, the preset gradation condition is,
the average gray scale is within a preset average gray scale range, and the gray scale value of each pixel is within a preset pixel gray scale range.
Preferably, in step B12, the average weld depth D of the image region acquired in step B1 is calculated by,
where n is the number of random sampling points of the image region, k i Is the gray-to-depth transform coefficient of the ith sample point, delta i Is the correction factor, g, for the ith sample point i Is the gray scale of the ith sampling point; delta when the sampling point is outside the image block with the gray scale exceeding the preset condition i Is 1, when the sampling point is in the image block with the gray scale exceeding the preset condition, delta i The calculation method of (a) is that,
wherein
J is the total number of sampling points in the image block.
Preferably, the step B of comparing the historical weld image and the standard weld image stored in the weld image storage module includes the steps of,
b21, comparing the real-time weld joint image with the historical weld joint image, and obtaining a plurality of image deviation sets according to the time sequence; marking the regions of which the corresponding region deviation changes exceed a set deviation threshold in the adjacent image deviation set;
and B22, when the real-time weld image is compared with the standard weld image, preferentially comparing the marked areas in the step B21, if the comparison shows that the nonlinearity of the real-time weld image is larger than a set nonlinearity threshold value, taking the result as a comparison result, and finishing the comparison, otherwise, comparing other areas of the real-time weld image with the standard weld image to form a comparison deviation set, and taking the comparison deviation set as the comparison result.
The beneficial effect that adopts above-mentioned technical scheme to bring lies in: according to the method, the capture accuracy of the weld abnormal features is improved by improving the processing and comparing method of the weld image, the image processing process is simplified on the premise of ensuring the detection sensitivity of the weld abnormal region, and therefore the real-time performance of weld quality detection is improved.
Drawings
FIG. 1 is a schematic diagram of one embodiment of the present invention.
Detailed Description
Referring to fig. 1, one embodiment of the present invention includes,
the welding current control module 1 is used for controlling welding current;
the welding speed control module 2 is used for controlling the welding speed;
the welding gun height control module 3 is used for controlling the length of a welding arc;
the welding seam image acquisition module 4 is used for shooting a welding seam image;
the welding seam image storage module 5 is used for prestoring a standard welding seam image and storing the image shot by the welding seam image acquisition module 4;
the welding seam image analysis module 6 is used for analyzing the welding seam image shot by the welding seam image acquisition module 4;
and the welding machine control module 7 is in communication connection with the welding current control module 1, the welding speed control module 2 and the welding gun height control module 3 and is used for controlling welding parameters according to the analysis result of the welding seam image analysis module 6.
The control method of the automatic welding machine based on the machine vision comprises the following steps:
A. the welding seam image acquisition module 4 acquires the welding seam image in real time and sends the welding seam image to the welding seam image storage module 5 for storage;
B. the welding seam image analysis module 6 is used for carrying out feature analysis on the welding seam image obtained in real time in the step A and then comparing the welding seam image with the historical welding seam image and the standard welding seam image stored in the welding seam image storage module 5 to obtain a comparison result;
C. and C, the welding machine control module 7 sends control commands to the welding current control module 1, the welding speed control module 2 and the welding gun height control module 3 according to the comparison result obtained in the step B, and controls welding parameters.
In the step A, 10% -15% of overlapping parts exist on two adjacent welding seam images acquired by the welding seam image acquisition module 4.
In the step B, the characteristic analysis of the welding seam image comprises the following steps,
b11, acquiring width data of the welding seam and image blocks with the gray scale exceeding the preset conditions in the welding seam area;
b12, calculating the average weld depth of the image area acquired in the step B1;
and B13, correcting the image characteristics acquired in the step according to the overlapped part of the two adjacent welding seam images.
In step B11, the preset gradation condition is,
the average gray scale is within a preset average gray scale range, and the gray scale value of each pixel is within a preset pixel gray scale range.
In step B12, the average weld depth D of the image region acquired in step B1 is calculated by,
wherein n is the number of random sampling points of the image area, k i Is the gray-to-depth transform coefficient of the ith sample point, delta i Is the correction factor, g, for the ith sample point i The gray scale of the ith sampling point is shown; when the sampling point is out of the image block with the gray scale exceeding the preset condition, delta i Is 1, when the sampling point is in the image block with the gray scale exceeding the preset condition, delta i The calculation method of (a) is that,
wherein
J is the total number of sampling points in the image block.
In the step B, the comparison with the historical weld image and the standard weld image stored in the weld image storage module 5 comprises the following steps,
b21, comparing the real-time weld joint image with the historical weld joint image, and obtaining a plurality of image deviation sets according to the time sequence; marking the regions of which the corresponding region deviation changes exceed a set deviation threshold in the adjacent image deviation set;
and B22, when the real-time weld image is compared with the standard weld image, preferentially comparing the marked areas in the step B21, if the comparison shows that the nonlinearity of the real-time weld image is larger than a set nonlinearity threshold value, taking the result as a comparison result, and finishing the comparison, otherwise, comparing other areas of the real-time weld image with the standard weld image to form a comparison deviation set, and taking the comparison deviation set as the comparison result.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, are merely for convenience of description of the present invention, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (4)
1. A control method of an automatic welding machine based on machine vision is realized based on the automatic welding machine based on machine vision, and is characterized in that: an automatic welding machine based on machine vision includes,
the welding current control module (1) is used for controlling welding current;
the welding speed control module (2) is used for controlling the welding speed;
the welding gun height control module (3) is used for controlling the length of a welding arc;
the welding seam image acquisition module (4) is used for shooting a welding seam image;
the welding seam image storage module (5) is used for pre-storing a standard welding seam image and storing an image shot by the welding seam image acquisition module (4);
the welding seam image analysis module (6) is used for analyzing the welding seam image shot by the welding seam image acquisition module (4);
the welding machine control module (7) is in communication connection with the welding current control module (1), the welding speed control module (2) and the welding gun height control module (3) and is used for controlling welding parameters according to the analysis result of the welding seam image analysis module (6);
the control method comprises the following steps:
A. the welding seam image acquisition module (4) acquires the welding seam image in real time and sends the welding seam image to the welding seam image storage module (5) for storage;
B. the welding seam image analysis module (6) performs characteristic analysis on the welding seam image acquired in real time in the step A, and then compares the welding seam image with the historical welding seam image and the standard welding seam image stored in the welding seam image storage module (5) to obtain a comparison result;
C. the welding machine control module (7) sends control commands to the welding current control module (1), the welding speed control module (2) and the welding gun height control module (3) according to the comparison result obtained in the step B, and controls welding parameters;
in the step B, the characteristic analysis of the welding seam image comprises the following steps,
b11, acquiring width data of the welding seam and image blocks with the gray scale exceeding the preset conditions in the welding seam area;
b12, calculating the average weld depth of the image area acquired in the step B1;
b13, correcting the image characteristics obtained in the above steps according to the overlapped part of two adjacent welding seam images;
in the step B, the comparison with the historical welding seam image and the standard welding seam image stored by the welding seam image storage module (5) comprises the following steps,
b21, comparing the real-time weld joint image with the historical weld joint image, and obtaining a plurality of image deviation sets according to the time sequence; marking the regions of which the corresponding region deviation changes exceed a set deviation threshold in the adjacent image deviation set;
and B22, when the real-time weld image is compared with the standard weld image, preferentially comparing the marked areas in the step B21, if the comparison shows that the nonlinearity of the real-time weld image is larger than a set nonlinearity threshold value, taking the result as a comparison result, and finishing the comparison, otherwise, comparing other areas of the real-time weld image with the standard weld image to form a comparison deviation set, and taking the comparison deviation set as the comparison result.
2. The control method for an automatic welder based on machine vision according to claim 1, characterized in that: in the step A, 10-15% of overlapping parts exist on two adjacent welding seam images acquired by the welding seam image acquisition module (4).
3. The control method for the automatic welder based on the machine vision as claimed in claim 1, characterized in that: in step B11, the preset gradation condition is,
the average gray scale is within a preset average gray scale range, and the gray scale value of each pixel is within a preset pixel gray scale range.
4. The control method for the automatic welder based on the machine vision as claimed in claim 1, characterized in that: in step B12, the average weld depth D of the image region acquired in step B1 is calculated by,
where n is the number of random sampling points of the image region, k i Is the gray-to-depth transform coefficient of the ith sample point, delta i Is the correction factor, g, for the ith sample point i Is the gray scale of the ith sampling point; when the sampling point is out of the image block with the gray scale exceeding the preset condition, delta i Is 1, when the sampling point is in the image block with the gray scale exceeding the preset condition, delta i The calculation method of (a) is that,
wherein
J is the total number of sampling points in the image block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110151456.8A CN112935473B (en) | 2021-02-03 | 2021-02-03 | Automatic welding machine based on machine vision and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110151456.8A CN112935473B (en) | 2021-02-03 | 2021-02-03 | Automatic welding machine based on machine vision and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112935473A CN112935473A (en) | 2021-06-11 |
| CN112935473B true CN112935473B (en) | 2022-09-16 |
Family
ID=76243514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110151456.8A Active CN112935473B (en) | 2021-02-03 | 2021-02-03 | Automatic welding machine based on machine vision and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112935473B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114799600B (en) * | 2022-05-13 | 2024-03-15 | 中车工业研究院有限公司 | Method, equipment, system, medium and product for controlling melting width |
| CN115229397B (en) * | 2022-09-22 | 2022-12-20 | 江苏友邦精工实业有限公司 | Combined welding device for automobile frame |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625759B (en) * | 2009-07-30 | 2011-10-12 | 重庆医科大学 | Image quality evaluation method |
| US8569655B2 (en) * | 2009-10-13 | 2013-10-29 | Lincoln Global, Inc. | Welding helmet with integral user interface |
| CN109514043B (en) * | 2018-12-13 | 2020-11-24 | 南昌市龙诚电器设备有限公司 | Effective welding control system of welding robot |
| CN109967829B (en) * | 2019-04-17 | 2020-08-18 | 北华航天工业学院 | Welding machine control system and control method thereof |
| CN112258521B (en) * | 2020-10-16 | 2022-06-07 | 江苏方天电力技术有限公司 | Three-dimensional reconstruction method for pipeline weld joint based on single elliptical imaging radiograph |
-
2021
- 2021-02-03 CN CN202110151456.8A patent/CN112935473B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112935473A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112935473B (en) | Automatic welding machine based on machine vision and control method thereof | |
| CN108637435B (en) | Three-dimensional weld tracking system and method based on vision and arc pressure sensing | |
| CN115115644B (en) | Vehicle welding defect detection method based on artificial intelligence | |
| CN103134809A (en) | Welded line defect detection method | |
| CN114821114A (en) | Groove cutting robot image processing method based on visual system | |
| CN116423005B (en) | Tin soldering process optimization method and system for improving welding precision | |
| CN107610103B (en) | Steel pipe spiral arc welding seam region extraction method based on X-ray imaging | |
| CN112419298B (en) | Bolt node plate rust detection method, device, equipment and storage medium | |
| CN107423709A (en) | A kind of object detection method for merging visible ray and far infrared | |
| CN113781446A (en) | Method and device for detecting greasy dirt on glass fiber surface, storage medium and electronic equipment | |
| CN109967829B (en) | Welding machine control system and control method thereof | |
| CN108492306A (en) | A kind of X-type Angular Point Extracting Method based on image outline | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN115880296B (en) | Machine vision-based prefabricated part quality detection method and device | |
| CN110852990A (en) | Rubber tree oblique cutter mark detection method based on image processing | |
| CN114932292A (en) | Narrow-gap passive visual weld joint tracking method and system | |
| CN113643352A (en) | Natural icing on-line monitoring running wire image icing degree evaluation method | |
| CN110276296B (en) | Structured light weld joint identification method based on image processing | |
| CN114037832A (en) | Method and system for extracting typical region in satellite remote sensing image | |
| CN113870220A (en) | Conductor galloping on-line monitoring method and device based on rectangular image detection | |
| CN115731254A (en) | Method for solving size of image based on sub-pixel | |
| CN111917157A (en) | Automatic charging method, system, equipment and storage medium for inspection robot | |
| CN115990896B (en) | Welding robot control system based on image recognition | |
| CN116834023B (en) | Nailing robot control system | |
| CN117079100B (en) | Weld defect recognition system based on deep learning |
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 |