CN114749848A - Steel bar welding automatic system based on 3D vision guide - Google Patents
Steel bar welding automatic system based on 3D vision guide Download PDFInfo
- Publication number
- CN114749848A CN114749848A CN202210609490.XA CN202210609490A CN114749848A CN 114749848 A CN114749848 A CN 114749848A CN 202210609490 A CN202210609490 A CN 202210609490A CN 114749848 A CN114749848 A CN 114749848A
- Authority
- CN
- China
- Prior art keywords
- welding
- point
- mechanical arm
- point cloud
- steel bars
- 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 152
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 49
- 239000010959 steel Substances 0.000 title claims abstract description 49
- 230000000007 visual effect Effects 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000003014 reinforcing effect Effects 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 229910001294 Reinforcing steel Inorganic materials 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000011800 void material Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 2
- 238000005452 bending Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000010276 construction Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction 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
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Robotics (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a steel bar welding automatic system based on 3D visual guidance, wherein the hardware of the automatic system comprises a visual module, a welding mechanical arm and a working platform, wherein the visual module comprises a 3D camera and an industrial personal computer; the welding mechanical arm consists of a mechanical arm and a welding gun, and the two mechanical arms are inversely arranged on the portal frame; the system can evaluate the offset of the intersection point position of the steel bars to be welded relative to the standard position in the space three-dimensional coordinate, can transmit the offset to corresponding mechanical welding equipment, guides the welding equipment to realize accurate welding, and simultaneously utilizes a visual evaluation system to evaluate the welding quality. The welding method can solve the problem of automatic welding failure caused by bending, deformation and poor placing consistency of the reinforcing mesh, and the welding point is positioned through the visual algorithm to calculate the welding track, so that the welding teaching of a mechanical arm is reduced, the welding automation based on visual guidance is realized, and the welding efficiency of the reinforcing mesh is improved.
Description
Technical Field
The invention belongs to the technical field of welding, and particularly relates to a steel bar welding automatic system based on 3D visual guidance.
Background
In the construction industry, a large number of reinforcing mesh structural preforms are widely used. The prior prefabricated member of the reinforcing mesh structure is generally bound or welded by manpower at the cross point in the reinforcing mesh, but the manual welding has limitations, such as unstable welding quality, low construction efficiency, high welding cost, incapability of working under extreme conditions of high temperature, high pressure and the like. At present, a mechanical automatic welding technology is widely applied to various fields of automobiles, aerospace, industrial manufacturing and the like, but generally high-precision workpiece limiting is required, and the path teaching of a mechanical arm welding gun is matched for multiple times to meet the welding process requirement, however, when the conditions of bending, distortion, deformation, inconsistent placing positions and the like exist in a steel bar structure, the abnormity of welding missing, collision and the like can occur, and finally, the automatic mechanical welding fails; meanwhile, in the case of a complex welding scene, the manual teaching steps are complicated, and the welding efficiency is low.
Disclosure of Invention
The invention aims to: in order to solve the above-mentioned problem of proposing, provide a steel bar welding automation system based on 3D vision guide.
The technical scheme adopted by the invention is as follows: the utility model provides a steel bar welding automation system based on 3D vision guide, automation system's hardware composition includes vision module, welding arm, work platform, wherein: the vision module consists of a 3D camera and an industrial personal computer; the welding mechanical arm consists of a mechanical arm and a welding gun, wherein the two mechanical arms are inversely arranged on the portal frame; the operation platform consists of an operation plane, a portal frame and a portal frame moving track; the automatic system for welding the steel bars based on the 3D visual guidance comprises the following steps when in operation:
s1, when hand-eye calibration of a common calibration plate is carried out, the calibration plate is placed in the center of a welding effective area, the teaching device is controlled to move, the mechanical arm carries the 3D camera to move to different positions to shoot the calibration plate, hand-eye calibration is carried out, and a hand-eye calibration result is calculated;
s2, when 3D vision-based calibration is carried out, a 3D camera is used for shooting areas to be welded of the steel bars, an industrial personal computer directly returns all welding points to be welded, then a demonstrator controls a welding gun to move to each welding point step by step, and the industrial personal computer calculates a hand-eye calibration result by recording mechanical arm coordinates of an algorithm output point and a welding gun to a welding position;
s3, moving the portal frame to preset positions A, B, C, D, N, and presetting mechanical arm photographing positions R1, R2 and R3 … Rn to cover welding points as much as possible when the portal frame is fixed at a certain point;
s4, moving the portal frame to the position A, and moving the mechanical arm to the photographing position R1; the mechanical arm sends a signal to the 3D camera to start shooting, collects the 3D point cloud of the steel bar to be welded and transmits the 3D point cloud to the industrial personal computer
S5, analyzing the to-be-welded point by the visual software of the industrial personal computer according to the 3D point cloud through an algorithm;
s6, the welding mechanical arm receives the welding track and executes welding; after all welding is finished, the mechanical arm moves to a photographing position R1;
and S7, after welding is finished, welding quality detection is carried out. Evaluating the quality of a steel weld from multiple dimensions, including image level and point cloud level
And S8, positioning the welding ROI area of the acquired image data, extracting the image data characteristics, sending the image data characteristics into a trained deep learning network model for reasoning, analyzing the difference between abnormal welding data and normal data, and outputting a confidence coefficient X.
And S9, performing feature extraction on the point cloud data, including counting the point cloud distribution density at the welding junction, analyzing whether a large-area cavity exists or not, and calculating the smoothness degree of the point cloud. And outputting the welding quality confidence coefficient Y.
S10, overlapping the image confidence X and the point cloud confidence Y with different weights, wherein the image confidence X and the point cloud confidence Y are finally output in a fusion mode; and enabling the cooperation result of the two to be consistent with the preset target, and outputting the corresponding OK/NG information.
In a preferred embodiment.
In a preferred embodiment, in step S1, the hand-eye calibration is performed by using coordinate values and corresponding images at different positions of the robot arm using the vision software on the industrial personal computer.
In a preferred embodiment, in step S3, after covering as many welding points as possible, the main welding process is started.
In a preferred embodiment, in step S4, the 3D camera has a wide field of view and a fast imaging speed, and coordinates of up to 8-64 intersections of the reinforcing steel bars can be obtained by a single photograph.
In a preferred embodiment, in step S4, the to-be-welded point is analyzed through an algorithm; the specific process is as follows:
s51, firstly, preprocessing the collected point cloud data, including down-sampling, outlier filtering, straight-through filtering and the like, so as to effectively reduce the number of point clouds and facilitate the subsequent point cloud calculation;
s52, projecting the obtained point cloud data to the xoy plane to obtain a projection graph, so that the three-dimensional point cloud data is mapped to the two-dimensional image data, and the subsequent intersection point positioning difficulty is further simplified;
s53, preprocessing the two-dimensional image data obtained in the last step, wherein the preprocessing comprises morphological processing, merging of connected domains, and reinforcing the image characteristics of the intersection points of the reinforcing steel bars, so that the subsequent intersection point detection is facilitated;
s54, performing cross intersection detection on the preprocessed steel bar intersection image, firstly, using the corner detection to preliminarily position the cross intersection, and then, using four end points of the cross intersection, namely the upper end point, the lower end point, the left end point and the right end point to accurately position the intersection center of the steel bar;
s55, mapping the intersection point position of the steel bars on the two-dimensional image to obtain the intersection point position of the steel bars on the space; thereby obtaining a 3D coordinate point of the point to be welded;
and S56, converting the hand-eye calibration result into a 3D coordinate point under a mechanical arm coordinate system, generating a welding path planning track and sending the welding path planning track to the welding mechanical arm.
In a preferred embodiment, in step S6, the 3D camera is started to capture a 3D point cloud of the welded steel bars, and the 3D point cloud data is transmitted to the industrial personal computer.
In a preferred embodiment, in step S9, artificial feature extraction is also performed on the point cloud data.
In a preferred embodiment, in step S9, it is further determined whether there is a large area of void, whether there is a point cloud distribution density at the welding boundary, the smoothness of the point cloud, and the output welding quality confidence Y.
In a preferred embodiment, in step S9, a detection model is obtained through network training, and the detection model is used to output a confidence of the welding quality.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. according to the invention, the system can evaluate the offset of the intersection point position of the steel bar to be welded relative to the standard position in the three-dimensional space coordinate, and can transmit the offset to corresponding mechanical welding equipment to guide the welding equipment to realize accurate welding, and meanwhile, a visual evaluation system is utilized to evaluate the welding quality.
2. According to the welding method and the welding device, the problem of automatic welding failure caused by bending, deformation and poor placing consistency of the reinforcing mesh can be solved, the welding points are positioned through a visual algorithm, and the welding track is calculated, so that the welding teaching of a mechanical arm is reduced, the welding automation based on visual guidance is realized, and the welding efficiency of the reinforcing mesh is improved.
Drawings
FIG. 1 is a schematic diagram of a work platform according to the present invention;
FIG. 2 is a front elevation view of the work platform of the present invention;
fig. 3 is a left side view of the work platform of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
With reference to figure 1 of the drawings,
the utility model provides a steel bar welding automation system based on 3D vision guide, automation system's hardware composition includes vision module, welding arm, work platform, wherein: the vision module consists of a 3D camera and an industrial personal computer; the welding mechanical arm consists of a mechanical arm and a welding gun, wherein the two mechanical arms are inversely arranged on the portal frame; the operation platform consists of an operation plane, a portal frame and a portal frame moving track; the automatic system for welding the steel bars based on the 3D visual guidance comprises the following steps when in operation:
s1, when the hand-eye calibration of a common calibration plate is carried out, the calibration plate is placed in the center of a welding effective area, the demonstrator is controlled to move, the mechanical arm carries the 3D camera to move to different positions to shoot the calibration plate, the hand-eye calibration is carried out, and the hand-eye calibration result is calculated;
s2, when calibration based on 3D vision is carried out, a 3D camera is used for shooting areas to be welded of the reinforcing steel bars, an industrial personal computer directly returns all welding points to be welded, then a demonstrator controls a welding gun to move to each welding point step by step, and the industrial personal computer calculates a hand-eye calibration result by recording an algorithm output point and mechanical arm coordinates of the welding gun to a welding position;
s3, moving the portal frame to preset positions A, B, C, D, N, and presetting mechanical arm photographing positions R1, R2 and R3 … Rn to cover welding points as much as possible when the portal frame is fixed at a certain point;
s4, moving the portal frame to the position A, and moving the mechanical arm to the photographing position R1; the mechanical arm sends a signal to the 3D camera to start shooting, collects the 3D point cloud of the steel bar to be welded and transmits the 3D point cloud to the industrial personal computer
S5, analyzing the to-be-welded point by the visual software of the industrial personal computer according to the 3D point cloud through an algorithm;
s6, the welding mechanical arm receives the welding track and executes welding; after all welding is finished, the mechanical arm moves to a photographing position R1;
s7, detecting the welding quality after welding; evaluating the quality of a steel weld from multiple dimensions, including image level and point cloud level
S8, positioning a welding ROI area of the acquired image data, extracting image data characteristics, sending the image data characteristics into a trained deep learning network model for reasoning, analyzing the difference between abnormal welding data and normal data, and outputting a confidence coefficient X;
s9, extracting the characteristics of the point cloud data, including counting the point cloud distribution density at the welding junction, analyzing whether a large-area cavity exists or not, and calculating the smoothness of the point cloud; outputting a welding quality confidence coefficient Y;
s10, superposing different weights on the image confidence X and the point cloud confidence Y which are finally output in a fusion manner; and enabling the cooperation result of the two to be consistent with the preset target, and outputting corresponding OK/NG information.
In step S1, the vision software on the industrial personal computer is used to calibrate the hand and eye by using the coordinate values and the corresponding images at different positions of the robot arm.
In step S3, after covering as many welding points as possible, the normal welding process is started.
In the step S4, the 3D camera has a wide field of view and a fast imaging speed, and coordinates of as many as 8 to 64 steel bar intersections can be obtained by a single photographing.
In the step S4, the welding point to be welded is analyzed through an algorithm; the specific process is as follows:
s51, firstly, preprocessing the collected point cloud data, including down-sampling, outlier filtering, straight-through filtering and the like, so as to effectively reduce the number of point clouds and facilitate the subsequent point cloud calculation;
s52, projecting the obtained point cloud data to the xoy plane to obtain a projection graph, so that the three-dimensional point cloud data is mapped to the two-dimensional image data, and the subsequent intersection point positioning difficulty is further simplified;
s53, preprocessing the two-dimensional image data obtained in the last step, wherein the preprocessing comprises morphological processing, merging of connected domains, and reinforcing the image characteristics of the intersection points of the reinforcing steel bars, so that the subsequent intersection point detection is facilitated;
s54, performing cross intersection detection on the preprocessed steel bar intersection image, firstly, using the corner detection to preliminarily position the cross intersection, and then, using four end points of the cross intersection, namely the upper end point, the lower end point, the left end point and the right end point to accurately position the intersection center of the steel bar;
s55, mapping the intersection point position of the steel bars on the two-dimensional image to obtain the intersection point position of the steel bars on the space; thereby obtaining a 3D coordinate point of a to-be-welded point;
and S56, converting the hand-eye calibration result into a 3D coordinate point under a mechanical arm coordinate system, generating a welding path planning track and sending the welding path planning track to the welding mechanical arm.
In the step S6, a 3D camera is started to shoot 3D point cloud of the welded steel bars, and the 3D point cloud data are transmitted to an industrial personal computer.
In step S9, artificial feature extraction is also performed on the point cloud data.
In step S9, it is also determined whether there is a large area of void, the smoothness of the point cloud, and the output welding quality confidence Y in the point cloud distribution density at the welding junction.
In step S9, a detection model is obtained through network training, and the detection model is used to output the welding quality confidence X.
The system can evaluate the offset of the intersection point position of the steel bars to be welded relative to the standard position in the space three-dimensional coordinate, can transmit the offset to corresponding mechanical welding equipment, guides the welding equipment to realize accurate welding, and simultaneously utilizes the visual evaluation system to evaluate the welding quality.
The invention can solve the problem of automatic welding failure caused by bending, deformation and poor placing consistency of the reinforcing mesh. The welding points are positioned through a visual algorithm, and the welding track is calculated, so that the welding teaching of a mechanical arm is reduced, the welding automation based on visual guidance is realized, and the welding efficiency of the reinforcing mesh is improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. The utility model provides a steel bar welding automation system based on 3D vision guide which characterized in that: the hardware of the automation system comprises a visual module, a welding mechanical arm and a working platform, wherein: the vision module consists of a 3D camera and an industrial personal computer; the welding mechanical arm consists of a mechanical arm and a welding gun, wherein the two mechanical arms are inversely arranged on the portal frame; the operation platform consists of an operation plane, a portal frame and a portal frame moving track; the automatic system for welding the steel bars based on the 3D visual guidance comprises the following steps when in operation:
s1, when the hand-eye calibration of a common calibration plate is carried out, the calibration plate is placed in the center of a welding effective area, the demonstrator is controlled to move, the mechanical arm carries the 3D camera to move to different positions to shoot the calibration plate, the hand-eye calibration is carried out, and the hand-eye calibration result is calculated;
s2, when 3D vision-based calibration is carried out, a 3D camera is used for shooting areas to be welded of the steel bars, an industrial personal computer directly returns all welding points to be welded, then a demonstrator controls a welding gun to move to each welding point step by step, and the industrial personal computer calculates a hand-eye calibration result by recording mechanical arm coordinates of an algorithm output point and a welding gun to a welding position;
s3, moving the portal frame to preset positions A, B, C, D, N, and presetting mechanical arm photographing positions R1, R2 and R3 … Rn to cover welding points as much as possible when the portal frame is fixed at a certain point;
s4, moving the portal frame to the position A, and moving the mechanical arm to the photographing position R1; the mechanical arm sends a signal to the 3D camera to start shooting, collects the 3D point cloud of the steel bar to be welded and transmits the 3D point cloud to the industrial personal computer
S5, analyzing the to-be-welded point by the visual software of the industrial personal computer according to the 3D point cloud through an algorithm;
s6, the welding mechanical arm receives the welding track and executes welding; after all welding is finished, the mechanical arm moves to a photographing position R1;
s7, after welding, detecting the welding quality; evaluating the quality of a steel weld from multiple dimensions, including an image level and a point cloud level
S8, positioning a welding ROI area of the acquired image data, extracting image data characteristics, sending the image data characteristics into a trained deep learning network model for reasoning, analyzing the difference between abnormal welding data and normal data, and outputting a confidence coefficient X;
s9, extracting the characteristics of the point cloud data, including counting the point cloud distribution density of the welding junction, analyzing whether a large-area cavity exists or not, and calculating the smoothness of the point cloud; outputting a welding quality confidence coefficient Y;
s10, superposing different weights on the image confidence X and the point cloud confidence Y which are finally output in a fusion manner; and enabling the cooperation result of the two to be consistent with the preset target, and outputting corresponding OK/NG information.
2. The automated system for welding of steel bars based on 3D visual guidance of claim 1, wherein: in the step S1, the hand-eye calibration is performed by using the coordinate values of the different positions of the mechanical arm and the corresponding images using the vision software on the industrial personal computer.
3. The automatic system for steel bar welding based on 3D visual guidance as claimed in claim 1, wherein: in step S3, after covering as many welding points as possible, the normal welding process is started.
4. The automated system for welding of steel bars based on 3D visual guidance of claim 1, wherein: in the step S4, the 3D camera has a wide field of view and a fast imaging speed, and coordinates of as many as 8 to 64 steel bar intersections can be obtained by a single photographing.
5. The automated system for welding of steel bars based on 3D visual guidance of claim 1, wherein: in the step S4, the welding point to be welded is analyzed through an algorithm; the specific process is as follows:
s51, firstly, preprocessing the acquired point cloud data, including downsampling, outlier filtering, direct filtering and the like, so as to effectively reduce the number of point clouds and facilitate the calculation of the subsequent point clouds;
s52, projecting the obtained point cloud data to the xoy plane to obtain a projection diagram, so that the three-dimensional point cloud data is mapped to the two-dimensional image data, and the subsequent intersection point positioning difficulty is further simplified;
s53, preprocessing the two-dimensional image data obtained in the last step, wherein the preprocessing comprises morphological processing, merging of connected domains, and reinforcing the image characteristics of the intersection points of the reinforcing steel bars, so that the subsequent intersection point detection is facilitated;
s54, performing cross intersection point detection on the preprocessed steel bar intersection point image, firstly performing angular point detection to preliminarily position the steel bar intersection point, and then accurately positioning the intersection point center of the steel bar by using four end point values of the upper, lower, left and right sides of the intersection point;
s55, mapping the intersection point position of the steel bars on the two-dimensional image to obtain the intersection point position of the steel bars on the space; thereby obtaining a 3D coordinate point of a to-be-welded point;
and S56, converting the hand-eye calibration result into a 3D coordinate point under a mechanical arm coordinate system, generating a welding path planning track and sending the welding path planning track to the welding mechanical arm.
6. The automated system for welding of steel bars based on 3D visual guidance of claim 1, wherein: and in the step S6, starting a 3D camera to shoot and collect 3D point cloud of the welded steel bars, and transmitting the 3D point cloud data to an industrial personal computer.
7. The automated system for welding of steel bars based on 3D visual guidance of claim 1, wherein: in step S9, artificial feature extraction is also performed on the point cloud data.
8. The automated system for welding of steel bars based on 3D visual guidance of claim 1, wherein: in step S9, the distribution density of the point cloud at the welding junction, whether there is a large area of void, the smoothness of the point cloud, and the output welding quality confidence Y are also determined.
9. The automated system for welding of steel bars based on 3D visual guidance of claim 1, wherein: in step S9, a detection model is obtained through network training, and the detection model is used to output the welding quality confidence X.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210609490.XA CN114749848A (en) | 2022-05-31 | 2022-05-31 | Steel bar welding automatic system based on 3D vision guide |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210609490.XA CN114749848A (en) | 2022-05-31 | 2022-05-31 | Steel bar welding automatic system based on 3D vision guide |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114749848A true CN114749848A (en) | 2022-07-15 |
Family
ID=82336590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210609490.XA Pending CN114749848A (en) | 2022-05-31 | 2022-05-31 | Steel bar welding automatic system based on 3D vision guide |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114749848A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116225030A (en) * | 2023-05-09 | 2023-06-06 | 中铁九局集团有限公司 | Walking control system and method of steel bar binding robot |
| CN117564404A (en) * | 2023-11-27 | 2024-02-20 | 中国建筑第五工程局有限公司 | Automatic welding method of large-scale reinforcing mesh based on AI vision |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108568624A (en) * | 2018-03-29 | 2018-09-25 | 东风贝洱热系统有限公司 | A kind of mechanical arm welding system and welding method based on image procossing |
| WO2020233273A1 (en) * | 2019-05-17 | 2020-11-26 | 南京禹智智能科技有限公司 | High-precision automatic welding robot and welding method thereof |
| CN112122840A (en) * | 2020-09-23 | 2020-12-25 | 西安知象光电科技有限公司 | Visual positioning welding system and welding method based on robot welding |
| CN112958959A (en) * | 2021-02-08 | 2021-06-15 | 西安知象光电科技有限公司 | Automatic welding and detection method based on three-dimensional vision |
| CN113478483A (en) * | 2021-07-02 | 2021-10-08 | 普瑞特机械制造股份有限公司 | Mobile robot welding method and system based on stainless steel storage tank |
| CN113634958A (en) * | 2021-09-27 | 2021-11-12 | 西安知象光电科技有限公司 | Three-dimensional vision-based automatic welding system and method for large structural part |
| CN114434059A (en) * | 2022-04-08 | 2022-05-06 | 西安知象光电科技有限公司 | Automatic welding system and method for large structural part with combined robot and three-dimensional vision |
-
2022
- 2022-05-31 CN CN202210609490.XA patent/CN114749848A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108568624A (en) * | 2018-03-29 | 2018-09-25 | 东风贝洱热系统有限公司 | A kind of mechanical arm welding system and welding method based on image procossing |
| WO2020233273A1 (en) * | 2019-05-17 | 2020-11-26 | 南京禹智智能科技有限公司 | High-precision automatic welding robot and welding method thereof |
| CN112122840A (en) * | 2020-09-23 | 2020-12-25 | 西安知象光电科技有限公司 | Visual positioning welding system and welding method based on robot welding |
| CN112958959A (en) * | 2021-02-08 | 2021-06-15 | 西安知象光电科技有限公司 | Automatic welding and detection method based on three-dimensional vision |
| CN113478483A (en) * | 2021-07-02 | 2021-10-08 | 普瑞特机械制造股份有限公司 | Mobile robot welding method and system based on stainless steel storage tank |
| CN113634958A (en) * | 2021-09-27 | 2021-11-12 | 西安知象光电科技有限公司 | Three-dimensional vision-based automatic welding system and method for large structural part |
| CN114434059A (en) * | 2022-04-08 | 2022-05-06 | 西安知象光电科技有限公司 | Automatic welding system and method for large structural part with combined robot and three-dimensional vision |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116225030A (en) * | 2023-05-09 | 2023-06-06 | 中铁九局集团有限公司 | Walking control system and method of steel bar binding robot |
| CN117564404A (en) * | 2023-11-27 | 2024-02-20 | 中国建筑第五工程局有限公司 | Automatic welding method of large-scale reinforcing mesh based on AI vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112122840B (en) | Visual positioning welding system and welding method based on robot welding | |
| Zhu et al. | Online camera-lidar calibration with sensor semantic information | |
| CN114749848A (en) | Steel bar welding automatic system based on 3D vision guide | |
| CN107214703B (en) | Robot self-calibration method based on vision-assisted positioning | |
| CN112476434A (en) | Visual 3D pick-and-place method and system based on cooperative robot | |
| CN111192307B (en) | Self-adaptive deviation rectifying method based on laser cutting of three-dimensional part | |
| CN106041937A (en) | Control method of manipulator grabbing control system based on binocular stereoscopic vision | |
| CN109470149B (en) | Method and device for measuring position and posture of pipeline | |
| CN113276106A (en) | Climbing robot space positioning method and space positioning system | |
| CN114474041A (en) | Welding automation intelligent guiding method and system based on cooperative robot | |
| CN114473309A (en) | Welding position identification method for automatic welding system and automatic welding system | |
| CN115131268A (en) | Automatic welding system based on image feature extraction and three-dimensional model matching | |
| CN116465315B (en) | Automatic screen quality detection method and system | |
| TW202302301A (en) | Automated calibration system and method for the relation between a profile scanner coordinate frame and a robot arm coordinate frame | |
| CN114581368B (en) | Bar welding method and device based on binocular vision | |
| CN115619738A (en) | Detection method for module side seam welding after welding | |
| CN112508933B (en) | Flexible mechanical arm movement obstacle avoidance method based on complex space obstacle positioning | |
| CN113269729B (en) | Assembly body multi-view detection method and system based on depth image contrast | |
| CN116465335A (en) | Automatic thickness measurement method and system based on point cloud matching | |
| CN115464651A (en) | Six groups of robot object grasping system | |
| CN114842144A (en) | Binocular vision three-dimensional reconstruction method and system | |
| Zou et al. | Laser-based precise measurement of tailor welded blanks: a case study | |
| CN114708318B (en) | Unknown surface curvature measurement method based on depth camera | |
| CN117522830A (en) | Point cloud scanning system for detecting boiler corrosion | |
| CN118003340B (en) | Visual mechanical arm material grabbing control method and 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 |