CN109702293B - Welding penetration quality real-time control method based on visual detection - Google Patents
Welding penetration quality real-time control method based on visual detection Download PDFInfo
- Publication number
- CN109702293B CN109702293B CN201910057453.0A CN201910057453A CN109702293B CN 109702293 B CN109702293 B CN 109702293B CN 201910057453 A CN201910057453 A CN 201910057453A CN 109702293 B CN109702293 B CN 109702293B
- Authority
- CN
- China
- Prior art keywords
- molten pool
- welding
- center
- weld bead
- area
- 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 119
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000035515 penetration Effects 0.000 title claims abstract description 33
- 230000000007 visual effect Effects 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 title claims abstract description 12
- 239000011324 bead Substances 0.000 claims abstract description 50
- 230000005855 radiation Effects 0.000 claims abstract description 17
- 230000000149 penetrating effect Effects 0.000 claims abstract description 12
- 238000005286 illumination Methods 0.000 claims description 16
- 238000011179 visual inspection Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000003287 optical effect Effects 0.000 claims description 4
- 230000003628 erosive effect Effects 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a welding penetration quality real-time control method based on visual detection, which comprises the following steps: continuously acquiring back images of the weld bead by using a visual sensor with an infrared high-pass filter in the welding process; acquiring thermal radiation light of a molten pool and arc light information transmitted through a weld bead groove gap through a previous frame image; determining the area of the center of the back of the molten pool according to the heat radiation light information, and calculating the position of the center line of the weld bead according to the arc light information penetrating through the gap of the weld bead groove; starting a parallel light illuminating source when the next frame of image is collected, and calculating the central position of the back of the molten pool and the characteristic width of the back of the molten pool by combining the obtained area of the center of the back of the molten pool according to the light and shadow characteristics formed by the molten pool and the back of the welding line; calculating the position offset between the center of the back of the molten pool and the center line of the weld bead; and adjusting welding parameters according to the characteristic width and the position offset of the back of the molten pool to control penetration, and repeating the process until welding is finished, thereby realizing closed-loop control on the welding penetration quality.
Description
Technical Field
The invention relates to a welding penetration quality real-time control method based on visual detection, and belongs to the technical field of welding automation.
Background
The welding automation replaces the traditional manual work with automation equipment, overcomes the defects of manual welding, improves the labor production efficiency, and has important significance for ensuring the stability of the welding process and the quality of welding seams. Weld penetration quality control is one of the technical problems facing weld automation. In the actual welding process, various uncertain factors such as assembly gaps of welding workpieces, heat dissipation condition changes, workpiece misalignment and the like cause inconsistent weld penetration quality, and cause local incomplete penetration, welding leakage or misalignment of the weld. In order to overcome the influence of uncertain factors in operating conditions on welding quality and improve the reliability of automatic welding, a welding system can realize the function of detecting penetration quality in the welding process in real time, so that the control on the welding penetration quality is further achieved by adjusting welding parameters in real time.
The search of the prior art documents shows that the detection means of the penetration quality in the welding process has various measures, such as adopting arc pressure to sense the vibration information of a molten pool, adopting ultrasonic waves to detect the position of a solid-liquid interface of the molten pool, adopting an acoustic signal of the welding process to reflect the penetration state and the like. Visual detection in various detection means has very wide application prospect in welding due to the advantages of non-contact, electromagnetic interference resistance and rich information. The visual inspection of the penetration quality is divided into visual inspection of the front side of the molten pool and visual inspection of the back side of the molten pool. The Chinese invention patent CN106624266B introduces a penetration quality detection method, which obtains the front information of a molten pool through a visual sensor, and calculates the welding seam deviation and the penetration state by adopting a neural network model in combination with the welding current information. On one hand, the method needs a large amount of experimental data to train a practical neural network model, so that the fusion penetration state is correctly reflected according to the front information of the molten pool, and when the working conditions such as the thickness and the arc length of a welding workpiece change, the model needs to be retrained; on the other hand, the image acquired at the front of the molten pool is disturbed by strong arc light, so the signal-to-noise ratio is low and the image characteristics are unstable. In the thesis published in the intelligent manufacturing, "intelligent control research on the back width of TIG welding seam of aluminum alloy" the welding penetration quality detection is performed by a method of irradiating the back of the welding seam with structured light, acquiring information of the structured light by using a visual sensor, and identifying the back width of the welding seam. The width of the back of the welding seam obtained by the method is the width of the back of the welding seam in the solidified area, a time delay link is introduced into a welding quality closed-loop control system, the whole outline shape of a molten pool and the welding seam cannot be obtained, the centering condition of the welding seam cannot be obtained, and the reflected penetration information is less.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a welding penetration quality real-time control method based on visual detection. The invention carries out visual sensing on the thermal radiation of a molten pool on the back of a welding workpiece and the arc light penetrating through the weld bead groove gap, and combines with the light and shadow characteristics of the molten pool and the back of a weld bead constructed by adopting parallel light to obtain the characteristic width of the back of the molten pool and the position offset of the center of the back of the molten pool relative to the central line of the weld bead, thereby adjusting the welding current and the pose of a welding gun relative to the weld bead in real time and realizing the control of the penetration quality. The invention is suitable for backing welding and single-layer welding under the conditions that welding workpieces are in tight butt joint and the backs have no liners.
The invention is realized by the following technical scheme:
a welding penetration quality real-time control method based on visual detection comprises the following steps:
(1) placing a visual sensor with an infrared high-pass filter and a parallel light illumination light source on the back of a welding workpiece, starting welding, and acquiring a welding bead back image by the visual sensor;
(2) acquiring heat radiation light information of a molten pool and arc light information penetrating through a weld bead groove gap when an odd frame image is collected, determining the area of the center of the back of the molten pool according to the heat radiation light information, and calculating the position of a weld bead center line according to the arc light information penetrating through the weld bead groove gap; starting a parallel light illuminating source when the even frame image is collected, extracting the back profiles of the molten pool and the welding seam according to the light and shadow characteristics formed by the bulges on the back of the molten pool and the welding seam, and calculating the central position of the back of the molten pool and the characteristic width of the back of the molten pool by combining the area of the center of the back of the molten pool obtained by the odd frame image;
(3) calculating the position offset between the center of the back of the molten pool and the center line of the weld bead, adjusting the welding current according to the characteristic width of the back of the molten pool, and adjusting the relative pose of the welding gun and the weld bead according to the position offset; and (6) returning to the step (2) until the welding is finished.
In the step (1), the step of placing the vision sensor with the infrared high-pass filter and the parallel light illumination light source on the back of the welding workpiece specifically comprises the following steps: the vision field of the vision sensor is aligned with the back area of the welding workpiece right below the welding gun, the wave band of the parallel light illuminating source is in the pass band of the infrared high-pass filter, the illuminating area is a shooting area of the vision sensor, and the position relation of the illuminating source, the vision sensor and the welding workpiece meets the optical reflection law, namely the parallel light emitted by the illuminating source can enter the light path of the vision sensor through the reflection energy of the welding workpiece.
Preferably, in the step (2), the determining the region where the center of the back of the molten pool is located according to the thermal radiation light information includes: in the odd frame image, the back of the molten pool is represented as a region with higher brightness due to heat radiation light, the region is extracted by image threshold segmentation, the position of the centroid of the region is calculated, the neighborhood of the centroid is used as the region where the center of the back of the molten pool is located, and the size of the neighborhood is determined according to experiments.
Preferably, in the step (2), the step of calculating the position of the center line of the weld bead based on the information of the arc transmitted through the weld bead groove gap includes: in the odd frame image, the arc light penetrating through the weld bead groove gap is represented as a long and narrow highlight area, the highlight area is extracted by threshold segmentation, morphological erosion and thinning are carried out on the highlight area, the center line of the highlight area is calculated by linear Hough transform, and the center line is taken as the weld bead center line.
Preferably, in the step (2), the back profiles of the weld pool and the weld bead are extracted according to light and shadow features formed by projections on the back of the weld pool and the weld bead, and the specific method is as follows: in the even frame image, the reflected parallel light illuminating rays of the molten pool and the lower convex surface of the back surface of the welding seam are mostly prevented from entering the visual sensor and are shown as a darker area in the image, other areas of the back surface of the welding workpiece reflect most illuminating rays into the visual sensor, the surface in the image is a high-brightness area, the molten pool and the welding seam area are extracted from the image by threshold segmentation, pixels of the area are traversed, the outline of the area is obtained, and the outline is used as the back surface outline of the molten pool and the welding seam.
Preferably, in the step (2), the step of calculating the position of the center of the back of the molten pool and the characteristic width of the back of the molten pool by combining the region where the center of the back of the molten pool is located, which is obtained by the odd-numbered frame image, includes: fitting the back profiles of the molten pool and the welding seam by using a semiellipse equation, enumerating the center of a semiellipse in the region of the back center of the molten pool, solving the parameters of a major semi-axis and a minor semi-axis of the semiellipse by using a least square method, selecting the semiellipse with the minimum error square sum as the fitting result of the back profiles of the molten pool and the welding seam, taking the center of the semiellipse as the back center of the molten pool, and taking the maximum width of the semiellipse as the characteristic width of the back of the molten pool.
Preferably, in the step (3), the calculating of the position offset between the center of the back surface of the molten pool and the center line of the weld bead includes: calculating the distance between the center of the back surface of the molten pool and the center line of the weld bead by a mode of calculating the distance from a point to a straight line, and taking the distance as the position offset.
The invention carries out time-sharing multiplexing on the visual sensor, integrates image information obtained by heat radiation, arc light and an active illumination light source of the molten pool, directly obtains the characteristic width of the back of the molten pool and the position offset between the center of the back of the molten pool and the center line of a weld bead, and adjusts welding parameters in real time to control the penetration quality. The method utilizes the thermal radiation information of the molten pool to quickly position the position of the back of the molten pool in the image, skillfully utilizes the arc light penetrating through the gap of the welding bead groove to determine the position of the center line of the welding bead, and utilizes the parallel light illuminating source to construct the light and shadow condition on the back of the welding workpiece, so that the contour characteristics of the molten pool and the welding bead in the obtained image are obvious, the image processing difficulty is obviously reduced, the image processing speed is improved, and the requirement of real-time control is met.
Drawings
FIG. 1 is a flow chart of a method for real-time control of weld penetration quality based on visual inspection according to the present disclosure;
FIG. 2 is a schematic view of an apparatus for visual sensing of the backside of a welded workpiece as employed in an embodiment of the present invention;
FIG. 3 is a diagram illustrating an odd frame image obtained by a vision sensor according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating an even frame of image captured by a vision sensor according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a position offset δ and a molten pool back side characteristic width w obtained after image processing according to an embodiment of the present invention;
reference numerals:
1-a welding gun; 2-welding the workpiece;
21-welding a welding bead; 3-an infrared high-pass filter;
4-a vision sensor; 5-parallel light illumination source.
Detailed Description
The invention is further described below with reference to the figures and examples.
Fig. 1 is a flowchart of a welding penetration quality real-time control method based on visual inspection, which includes the following steps:
(1) placing a visual sensor with an infrared high-pass filter and a parallel light illumination light source on the back of a welding workpiece, starting welding, and acquiring a welding bead back image by the visual sensor;
(2) acquiring heat radiation light information of a molten pool and arc light information penetrating through a weld bead groove gap when an odd frame image is collected, determining the area of the center of the back of the molten pool according to the heat radiation light information, and calculating the position of a weld bead center line according to the arc light information penetrating through the weld bead groove gap; starting a parallel light illuminating source when the even frame image is collected, extracting the back profiles of the molten pool and the welding seam according to the light and shadow characteristics formed by the bulges on the back of the molten pool and the welding seam, and calculating the central position of the back of the molten pool and the characteristic width of the back of the molten pool by combining the area of the center of the back of the molten pool obtained by the odd frame image;
(3) calculating the position offset between the center of the back of the molten pool and the center line of the weld bead, adjusting the welding current according to the characteristic width of the back of the molten pool, and adjusting the relative pose of the welding gun and the weld bead according to the position offset; and (6) returning to the step (2) until the welding is finished.
In the step (1), the visual field of the vision sensor is aligned to the back area of the welding workpiece right below the welding gun, in this embodiment, a high-pass filter with a cut-off wavelength of 808nm is used, the wave band of the parallel light illumination source is within the pass band of the infrared high-pass filter, the illumination area is a visual sensor shooting area, the positional relationship among the illumination source, the visual sensor and the welding workpiece satisfies the optical reflection law, that is, the parallel light emitted by the illumination source can enter the optical path of the visual sensor through the reflection energy of the welding workpiece, as shown in fig. 2, the included angles α and β between the parallel light illumination source 5 and the visual sensor 4 and the axis of the welding gun 1 are equal, and the axes of the three are in the same plane, and in addition, in order to facilitate image.
In this embodiment, the visual sensor is 300 pixels wide and 400 pixels high. For convenience of description, a rectangular coordinate system is established in the image acquired by the vision sensor, taking the pixel as a length unit, the upper left corner of the image as an origin, and the width and height directions of the image are respectively an X axis and a Y axis.
In the step (2), the obtained odd frame image is as shown in fig. 3, and since the parallel light illumination source 5 is in an off state at this time, the image obtained by the vision sensor 4 is an image of arc light transmitted through heat radiation of a molten pool and a weld bead groove gap. The back of the molten pool in the image is represented as an irregular area with higher brightness due to heat radiation light, the irregular area with higher brightness can be determined by adopting image threshold segmentation and simply screening an image connected domain from two aspects of area and perimeter, and the position (x) of the centroid A of the irregular area is calculated0,y0) A neighborhood D
D:{(x,y)|x∈[x0-Δx,x0+Δx]},|y∈[y0-Δy,y0+Δy]
The area in which the center of the molten pool backside is located, where Δ x and Δ y are preset values, represents the fluctuation range of the center of the molten pool backside, and is determined through experiments, where Δ x is Δ y is 15 in this embodiment.
In the step (2), in the obtained odd frame image, the arc passing through the weld bead groove gap appears as a long and narrow highlight region, and the position of the arc represents the position of the weld bead groove gap. Therefore, the highlight region is extracted by threshold segmentation, morphological erosion and refinement are performed on the highlight region, the center line of the highlight region is calculated by linear hough transform, and the center line is taken as the weld bead center line L, as shown in fig. 2.
In the step (2), the obtained even frame image is shown in fig. 4, because the parallel light illumination light source is in an on state at this time, most of the reflected parallel light illumination light rays cannot enter the visual sensor due to the convex lower surface of the back of the weld pool and the weld bead, and are represented as a region with darker brightness in the image, while most of the illumination light rays are reflected into the visual sensor by other regions of the back of the welding workpiece, the surface is a highlight region in the image, the weld pool and the weld pool region are extracted from the image by using threshold segmentation, pixels of the region are traversed, the contour of the region is obtained, and the contour is used as the contour of the back of the weld pool and the weld bead, as shown by a dotted line in fig. 4. The method utilizes the convex-down property of the back of the molten pool and the welding seam, and uses parallel light to construct a light and shadow condition, thereby enhancing the image characteristics of the back of the molten pool and the welding seam.
Using semi-elliptic equations
Fitting the back profile of the weld pool and the weld bead, wherein (x'0,y′0) The center of the semiellipse and the central position B of the back of the molten pool to be determined are provided, and a and B are parameters to be solved of the semiellipse. Enumerating (x 'in neighborhood D of A above'0,y′0) Obtaining semiellipse parameters a and b by using least square method, selecting semiellipse with minimum error square sum as fitting result of weld pool and back profile of weld seam, and obtaining (x'0,y′0) As shown in fig. 5, the molten pool back side characteristic width w is 2a as the molten pool back side center position B.
The position deviation δ between the weld bead center line position L and the molten pool back surface center position B obtained as described above is calculated by finding the point-to-straight line distance, as shown in fig. 5.
And (3) adjusting the welding current according to the characteristic width w of the back of the molten pool, and adjusting the relative pose of the welding gun and the welding bead according to the position offset delta, wherein the control method can be PID (proportion integration differentiation) control widely applied in the industry, fuzzy control and the like.
It should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and are not meant to limit the scope of the present invention. Therefore, although the present invention has been described in detail with reference to the above embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the present invention.
Claims (7)
1. A welding penetration quality real-time control method based on visual detection is characterized by comprising the following steps:
(1) placing a visual sensor with an infrared high-pass filter and a parallel light illumination light source on the back of a welding workpiece, starting welding, and acquiring a welding bead back image by the visual sensor;
(2) acquiring heat radiation light information of a molten pool and arc light information penetrating through a weld bead groove gap when an odd frame image is collected, determining the area of the center of the back of the molten pool according to the heat radiation light information, and calculating the position of a weld bead center line according to the arc light information penetrating through the weld bead groove gap; starting a parallel light illuminating source when the even frame image is collected, extracting the back profiles of the molten pool and the welding seam according to the light and shadow characteristics formed by the bulges on the back of the molten pool and the welding seam, and calculating the central position of the back of the molten pool and the characteristic width of the back of the molten pool by combining the area of the center of the back of the molten pool obtained by the odd frame image;
(3) calculating the position offset between the center of the back of the molten pool and the center line of the weld bead, adjusting the welding current according to the characteristic width of the back of the molten pool, and adjusting the relative pose of the welding gun and the weld bead according to the position offset; and (6) returning to the step (2) until the welding is finished.
2. The method for real-time control of the weld penetration quality based on the visual inspection as claimed in claim 1, wherein the placement of the visual sensor with the infrared high-pass filter and the parallel light illumination light source on the back of the welded workpiece specifically comprises:
the vision field of the vision sensor is aligned with the back area of the welding workpiece right below the welding gun, the wave band of the parallel light illuminating source is in the pass band of the infrared high-pass filter, the illuminating area is a shooting area of the vision sensor, and the position relation of the illuminating source, the vision sensor and the welding workpiece meets the optical reflection law, namely the parallel light emitted by the illuminating source can enter the light path of the vision sensor through the reflection energy of the welding workpiece.
3. The method for controlling the welding penetration quality in real time based on the visual inspection according to the claim 1, wherein the area where the center of the back of the molten pool is located is determined according to the thermal radiation light information, and the method comprises the following specific steps:
in the odd frame image, the back of the molten pool is represented as a region with higher brightness due to heat radiation light, the region is extracted by image threshold segmentation, the position of the centroid of the region is calculated, the neighborhood of the centroid is used as the region where the center of the back of the molten pool is located, and the size of the neighborhood is determined according to experiments.
4. The method for controlling the welding penetration quality in real time based on the visual inspection as claimed in claim 1, wherein the method for calculating the position of the center line of the welding bead according to the information of the arc light penetrating through the gap of the groove of the welding bead comprises the following steps:
in the odd frame image, the arc light penetrating through the weld bead groove gap is represented as a long and narrow highlight area, the highlight area is extracted by threshold segmentation, morphological erosion and thinning are carried out on the highlight area, the center line of the highlight area is calculated by linear Hough transform, and the center line is taken as the weld bead center line.
5. The real-time control method for the weld penetration quality based on the visual inspection as claimed in claim 1, wherein the back profiles of the weld pool and the weld bead are extracted according to the light and shadow characteristics formed by the projections on the back of the weld pool and the weld bead, and the specific method is as follows:
in the even frame image, the reflected parallel light illuminating rays of the molten pool and the lower convex surface of the back surface of the welding seam are mostly prevented from entering the visual sensor and are shown as a darker area in the image, other areas of the back surface of the welding workpiece reflect most illuminating rays into the visual sensor, the surface in the image is a high-brightness area, the molten pool and the welding seam area are extracted from the image by threshold segmentation, pixels of the area are traversed, the outline of the area is obtained, and the outline is used as the back surface outline of the molten pool and the welding seam.
6. The method for controlling the welding penetration quality in real time based on the visual inspection according to claim 1, wherein the welding penetration quality real-time control method is characterized in that the central position of the back of the molten pool and the characteristic width of the back of the molten pool are calculated by combining the region where the center of the back of the molten pool is located, which is obtained by the odd frame images, and the method comprises the following steps:
fitting the back profiles of the molten pool and the welding seam by using a semiellipse equation, enumerating the center of a semiellipse in the region of the back center of the molten pool, solving the parameters of a major semi-axis and a minor semi-axis of the semiellipse by using a least square method, selecting the semiellipse with the minimum error square sum as the fitting result of the back profiles of the molten pool and the welding seam, taking the center of the semiellipse as the back center of the molten pool, and taking the maximum width of the semiellipse as the characteristic width of the back of the molten pool.
7. The method for controlling the weld penetration quality in real time based on the visual inspection as claimed in claim 1, wherein the method for calculating the position offset between the center of the back surface of the molten pool and the center line of the weld bead comprises the following steps:
calculating the distance between the center of the back surface of the molten pool and the center line of the weld bead by a mode of calculating the distance from a point to a straight line, and taking the distance as the position offset.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910057453.0A CN109702293B (en) | 2019-01-22 | 2019-01-22 | Welding penetration quality real-time control method based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910057453.0A CN109702293B (en) | 2019-01-22 | 2019-01-22 | Welding penetration quality real-time control method based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109702293A CN109702293A (en) | 2019-05-03 |
| CN109702293B true CN109702293B (en) | 2020-01-14 |
Family
ID=66261592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910057453.0A Active CN109702293B (en) | 2019-01-22 | 2019-01-22 | Welding penetration quality real-time control method based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109702293B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102021117714A1 (en) | 2021-07-08 | 2023-01-12 | Endress+Hauser SE+Co. KG | Automatic seam detection for a welding process |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490867B (en) * | 2019-08-22 | 2020-08-28 | 四川大学 | Metal additive manufacturing forming dimension real-time prediction method based on deep learning |
| KR102536439B1 (en) * | 2019-12-04 | 2023-05-26 | 도시바 미쓰비시덴키 산교시스템 가부시키가이샤 | Welding abnormal diagnosis device |
| CN112453751B (en) * | 2020-11-27 | 2022-07-15 | 上海交通大学 | Pipeline all-position welding back surface online monitoring method based on visual sensing |
| CN114612457A (en) * | 2022-03-21 | 2022-06-10 | 徐州华宝能源科技有限公司 | Automobile part laser welding adjusting method and system based on computer vision |
| CN115106621B (en) * | 2022-05-20 | 2023-05-23 | 华南理工大学 | Full-position robot deep-melting K-TIG welding system and control method |
| CN116106980B (en) * | 2023-04-13 | 2024-02-20 | 江苏时代新能源科技有限公司 | Gap detection device and gap detection method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07214316A (en) * | 1994-01-28 | 1995-08-15 | Mitsubishi Heavy Ind Ltd | One side automatic welding method and its device |
| JP2006192437A (en) * | 2005-01-11 | 2006-07-27 | Hitachi Ltd | Welding equipment |
| CN101885102A (en) * | 2010-06-29 | 2010-11-17 | 哈尔滨工业大学 | Back surface camera and welding gun follow-up control device and method applied to detection of reverse molten bath for aluminum alloy TIG welding |
| CN107127432A (en) * | 2017-06-22 | 2017-09-05 | 西南交通大学 | The aluminum alloy MIG welding Fusion Control System and method adjusted based on welder |
-
2019
- 2019-01-22 CN CN201910057453.0A patent/CN109702293B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07214316A (en) * | 1994-01-28 | 1995-08-15 | Mitsubishi Heavy Ind Ltd | One side automatic welding method and its device |
| JP2006192437A (en) * | 2005-01-11 | 2006-07-27 | Hitachi Ltd | Welding equipment |
| CN101885102A (en) * | 2010-06-29 | 2010-11-17 | 哈尔滨工业大学 | Back surface camera and welding gun follow-up control device and method applied to detection of reverse molten bath for aluminum alloy TIG welding |
| CN107127432A (en) * | 2017-06-22 | 2017-09-05 | 西南交通大学 | The aluminum alloy MIG welding Fusion Control System and method adjusted based on welder |
Non-Patent Citations (2)
| Title |
|---|
| 基于铝合金 GTAW 焊三光路视觉传感的熔池特征提取;章妍;《中国优秀硕士学位论文全文数据库 信息科技辑》;20150615(第6期);正文第6,55-57页 * |
| 铝合金TIG焊缝背面宽度的智能控制研究;田志杰等;《智能制造》;20161031(第10期);第47-50页 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102021117714A1 (en) | 2021-07-08 | 2023-01-12 | Endress+Hauser SE+Co. KG | Automatic seam detection for a welding process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109702293A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109702293B (en) | Welding penetration quality real-time control method based on visual detection | |
| Xu et al. | Visual sensing technologies in robotic welding: Recent research developments and future interests | |
| US20200269340A1 (en) | Active Laser Vision Robust Weld Tracking System and Weld Position Detection Method | |
| CN105458462B (en) | A kind of trapezoidal weld seam multi-parameter synchronizing visual detecting and tracking method of Varied clearance | |
| CN102814574B (en) | Narrow gap welding monitoring and welding line deviation detecting method based on infrared vision sensing | |
| WO2016107408A1 (en) | Infrared vision sensing detection method and device for narrow-gap weld seam deviation | |
| Zhang et al. | Narrow-seam identification and deviation detection in keyhole deep-penetration TIG welding | |
| CN106990112B (en) | Multi-layer multi-pass welding track detection device and method based on multi-visual information fusion | |
| WO1988000508A1 (en) | Method of detecting position data in arc welding | |
| CN108856978B (en) | Angle joint penetration control method based on near-infrared binocular vision recognition | |
| CN106378514B (en) | The non-homogeneous subtle more weld seam vision detection systems of stainless steel and method based on machine vision | |
| Liu et al. | Precise initial weld position identification of a fillet weld seam using laser vision technology | |
| CN110480127A (en) | A kind of seam tracking system and method based on structured light visual sensing | |
| CN113504239B (en) | Quality control data analysis method | |
| CN109822216A (en) | Welding bead track and posture real-time tracking detection method, electronic equipment and medium | |
| Lin et al. | Intelligent seam tracking of an ultranarrow gap during K-TIG welding: a hybrid CNN and adaptive ROI operation algorithm | |
| Wang et al. | Vision-based seam tracking in robotic welding: A review of recent research | |
| CN108620714B (en) | Welding deviation detection system based on GMAW (gas metal arc welding) molten pool profile characteristics and detection method thereof | |
| JPH06344167A (en) | Laser beam machine | |
| CN111397529A (en) | Complex surface shape detection method based on binocular vision structured light | |
| Zhang et al. | A study on seam tracking in robotic GMA welding process | |
| CN108788544B (en) | Welding seam initial point detection method based on structured light vision sensor | |
| CN116664508A (en) | Weld surface quality detection method and computer readable storage medium | |
| CN106141382A (en) | Bevel for welding marginal position visual sensing detection method | |
| Wang et al. | Quality inspection scheme for automotive laser braze joints |
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 |