CN111390915A - Automatic weld joint path identification method based on AI - Google Patents
Automatic weld joint path identification method based on AI Download PDFInfo
- Publication number
- CN111390915A CN111390915A CN202010308035.7A CN202010308035A CN111390915A CN 111390915 A CN111390915 A CN 111390915A CN 202010308035 A CN202010308035 A CN 202010308035A CN 111390915 A CN111390915 A CN 111390915A
- Authority
- CN
- China
- Prior art keywords
- welding
- workpiece
- seam
- robot
- welding seam
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/005—Manipulators for mechanical processing tasks
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
The invention relates to an automatic welding seam path recognition method based on AI, which comprises the steps of importing three-dimensional model data of a workpiece to be welded into a welding robot controller, wherein the imported three-dimensional model data of the workpiece comprises the integral structure of the workpiece to be welded and the position information of a welding seam in the workpiece; compared with the traditional automatic welding technology, the application of the method can reduce a large amount of programming teaching time and improve the production efficiency; welding paths can be generated rapidly for different workpieces, and the links of designing complex tools are reduced; the method can well avoid the problem of processing errors of workpieces or position deviation of discharging; the method can be applied to different welding types such as fillet welding, vertical welding, lap welding and the like, and can also realize automatic adjustment of different types of welding modes.
Description
Technical Field
The invention relates to the field of robot welding, in particular to an automatic welding seam path identification method based on AI.
Background
At present, when a welding robot is used for welding, the whole robot motion and welding seam welding track need to be taught manually, so that when the structure of a welding workpiece or the shape and position of a welding seam change greatly, manual teaching consumes a large amount of labor cost and time cost; due to the existence of machining errors, workpieces and welding seams with the same structure have certain differences, and welding quality may be affected by using the original manually taught track. Meanwhile, the traditional welding robot lacks welding seam parameter detection equipment, so that welding parameters can not be adjusted according to different welding seams, and the welding quality can not be effectively guaranteed. In recent years, deep learning has been a rapidly advancing result in the fields of image recognition, stereoscopic vision, and the like. The traditional welding robot needs to adopt the latest AI technology to improve the labor productivity and improve the welding quality.
Disclosure of Invention
According to the technical problem, the invention provides an automatic welding seam path identification method based on AI, which comprises the following specific operation flows:
the method comprises the steps of firstly, importing three-dimensional model data of a workpiece to be welded into a welding robot controller, wherein the imported three-dimensional model data of the workpiece comprise the integral structure of the workpiece to be welded and position information of a welding seam in the workpiece;
secondly, mounting a workpiece to be welded on a welding tool table, and integrally photographing the workpiece through a three-dimensional camera fixed above the working table to detect whether the position and the placing posture of the workpiece to be welded on the working table are correct or not and manually confirm the safety and the readiness of all equipment on site;
thirdly, the automatic programming controller of the welding robot generates a motion track of the welding robot for completing the whole welding process of the workpiece in an off-line mode according to the three-dimensional model data of the equipment, the welding seam position information and the model of the welding robot; the path planning software and the collision detection software are used for carrying out preliminary robot track planning, and reinforcement learning is used for further optimizing the track, so that the automatic planning of a single track in a welding workpiece can be realized;
moving the welding robot to the position above the welding seam according to the generated track, further detecting and positioning the welding seam through a binocular camera arranged at the tail end of a welding robot tool, and adjusting the welding track of the current welding seam according to the obtained welding seam result; due to the existence of tolerance of the welding workpiece, certain errors can exist in the actual motion process of the motion trail automatically generated according to the model of the welding workpiece; therefore, in the specific welding process, when the welding line moves to the general position, the welding line is automatically detected and positioned, a binocular stereo camera is used, the technical scheme of combining a deep neural network and a traditional vision method is adopted, the welding line is automatically detected and positioned, and the positioning precision can reach within 4 mm;
fifthly, scanning the current welding seam by the laser scanner in an off-line mode according to the adjusted welding track, acquiring the accurate position of the welding seam and welding seam characteristic information, and transmitting the welding seam characteristic information to the robot automatic programming controller; if the welding robot is ensured to weld accurately, the positioning accuracy of the welding seam needs to be within 1mm, and the positioning accuracy of the three-dimensional camera is within 4mm, so that a laser scanner needs to be used for scanning the detected welding seam off line, more accurate positioning of the welding seam is completed, the positioning accuracy can be within 1mm, and the requirement of the welding robot on the welding accuracy is met;
and sixthly, the robot automatic programming controller selects the existing welding process packet in the automatic programming controller according to the welding material characteristics and the welding seam characteristics to obtain welding speed, current and voltage welding parameters, stores the typical welding type, the workpiece and the welding seam type and the corresponding welding parameters in the form of the welding process packet, and selects a specific welding process packet to weld after the welding type, the workpiece and the welding seam type are input or obtained through the sensor. With the increasing of welding data, the welding parameters can be generated in real time by adopting a technical scheme of reinforcement learning.
The motion track refers to the position and posture information of the welding gun; in addition, in the motion trajectory, factors of collision detection and welding efficiency need to be comprehensively considered.
The obtained welding line information includes welding line width and groove angle.
The invention has the beneficial effects that: compared with the traditional automatic welding technology, the application of the method can reduce a large amount of programming teaching time and improve the production efficiency; welding paths can be generated rapidly for different workpieces, and the links of designing complex tools are reduced; the method can well avoid the problem of processing errors of workpieces or position deviation of discharging; the method can be applied to different welding types such as fillet welding, vertical welding, lap welding and the like, and can also realize automatic adjustment of different types of welding modes. According to the invention, by adding the laser visual seam tracking system and the stereoscopic vision automatic teaching system, the complicated process of teaching paths can be reduced in the automatic welding production, the welding paths can be accurately found when different workpieces or workpieces have processing errors, the welding seams can be quickly and accurately found for welding operation when workpiece positions are inconsistent in the tooling fixture or the blanking process, the complicated tooling design links can be reduced, and the welding seams can be automatically identified for welding operation by using the artificial intelligence technology of deep reinforcement learning. The invention reduces the programming teaching process of the welding robot or the special machine, saves the programming time of workers, and can increase the product percent of pass and reduce the product rejection rate of workpieces with processing errors or discharging position errors. According to different welding types, the method can automatically debug the welding types, reduce teaching processes, quickly generate welding paths according to different workpieces, and improve production efficiency. For complex workpieces, the difficulty of designing the tool can be reduced.
Drawings
FIG. 1 is a schematic flow chart of the overall scheme of the present invention.
Detailed Description
The invention will be further explained with reference to fig. 1:
example 1
The specific operation method when the invention is used is as follows:
1. importing three-dimensional model data of a workpiece to be welded into a welding robot controller, wherein the imported three-dimensional model data of the workpiece comprises the integral structure of the workpiece to be welded and the position information of a welding seam in the workpiece;
2. the welding tool table is used for installing a workpiece to be welded to the welding tool table, the workpiece is integrally photographed through a three-dimensional camera fixed above the working table, whether the position and the placing posture of the workpiece to be welded on the working table are correct or not is detected, and the safety of all equipment needs to be confirmed on site manually.
3. The automatic programming controller of the welding robot generates a motion track of the welding robot for completing the whole welding process of the workpiece in an off-line manner according to the three-dimensional model data of the equipment, the welding seam position information and the model of the welding robot; the motion trail refers to the position and posture information of the welding gun; in addition, in the motion trajectory, factors such as collision detection and welding efficiency need to be comprehensively considered. And performing preliminary robot track planning by using path planning software and collision detection software, and further optimizing the track by using reinforcement learning, so that automatic planning of a single track in a welding workpiece can be realized.
4. And the welding robot moves to the upper part of the welding seam according to the generated track, the welding seam is further detected and positioned through a binocular camera arranged at the tail end of the welding robot tool, and the welding track of the current welding seam is adjusted according to the obtained welding seam result. Due to the existence of tolerance of the welding workpiece, certain errors can exist in the actual motion process of the motion trail automatically generated according to the model of the welding workpiece. Therefore, there is a need for automatic detection and positioning of welds when moved to the general position of the weld during a particular welding process. A binocular stereo camera is used, a technical scheme of combining a deep neural network with a traditional vision method is adopted, automatic detection and positioning are carried out on a welding seam, and the positioning precision can reach within 4 mm.
5. The laser scanner scans the current welding seam in an off-line mode according to the adjusted welding track, obtains the accurate position of the welding seam and welding seam characteristic information (mainly including the width of the welding seam, the angle of a groove and the like), and transmits the welding seam characteristic information to the robot automatic programming controller. If guarantee the accurate welding of welding robot, the positioning accuracy of welding seam need reach within 1mm, and the above-mentioned positioning accuracy who uses stereo camera is within 4mm, consequently need use laser scanner to carry out the off-line scanning to the welding seam that detects, accomplish the more accurate location of welding seam, positioning accuracy can be within 1mm, satisfy welding robot welding accuracy demand, and simultaneously, laser scanner can also scan some physical characteristics that obtain the welding seam, like the welding seam width, groove angle etc., welding process provides more data support afterwards.
6. The robot automatic programming controller selects the existing welding process package in the automatic programming controller according to the welding material characteristics (welding material, welding material thickness and the like) and the welding seam characteristics (welding seam type, welding seam width and the like) to obtain welding parameters (such as welding speed, current, voltage and the like). And storing typical welding types, workpieces, welding seam types and corresponding welding parameters in a welding process package form, and selecting a specific welding process package for welding after the welding types, the workpieces and the welding seam types are input or acquired through the sensors. With the increasing of welding data, the welding parameters can be generated in real time by adopting a technical scheme of reinforcement learning.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications can be made without departing from the principle of the present invention, and these modifications should also be construed as the protection scope of the present invention.
Claims (3)
1. An automatic welding seam path identification method based on AI comprises the following specific operation procedures:
the method comprises the steps of firstly, importing three-dimensional model data of a workpiece to be welded into a welding robot controller, wherein the imported three-dimensional model data of the workpiece comprise the integral structure of the workpiece to be welded and position information of a welding seam in the workpiece;
secondly, mounting a workpiece to be welded on a welding tool table, and integrally photographing the workpiece through a three-dimensional camera fixed above the working table to detect whether the position and the placing posture of the workpiece to be welded on the working table are correct or not and manually confirm the safety and the readiness of all equipment on site;
thirdly, the automatic programming controller of the welding robot generates a motion track of the welding robot for completing the whole welding process of the workpiece in an off-line mode according to the three-dimensional model data of the equipment, the welding seam position information and the model of the welding robot; the path planning software and the collision detection software are used for carrying out preliminary robot track planning, and reinforcement learning is used for further optimizing the track, so that the automatic planning of a single track in a welding workpiece can be realized;
moving the welding robot to the position above the welding seam according to the generated track, further detecting and positioning the welding seam through a binocular camera arranged at the tail end of a welding robot tool, and adjusting the welding track of the current welding seam according to the obtained welding seam result; due to the existence of tolerance of the welding workpiece, certain errors can exist in the actual motion process of the motion trail automatically generated according to the model of the welding workpiece; therefore, in the specific welding process, when the welding line moves to the general position, the welding line is automatically detected and positioned, a binocular stereo camera is used, the technical scheme of combining a deep neural network and a traditional vision method is adopted, the welding line is automatically detected and positioned, and the positioning precision can reach within 4 mm;
fifthly, scanning the current welding seam by the laser scanner in an off-line mode according to the adjusted welding track, acquiring the accurate position of the welding seam and welding seam characteristic information, and transmitting the welding seam characteristic information to the robot automatic programming controller; if the welding robot is ensured to weld accurately, the positioning accuracy of the welding seam needs to be within 1mm, and the positioning accuracy of the three-dimensional camera is within 4mm, so that a laser scanner needs to be used for scanning the detected welding seam off line, more accurate positioning of the welding seam is completed, the positioning accuracy can be within 1mm, and the requirement of the welding robot on the welding accuracy is met;
and sixthly, the robot automatic programming controller selects the existing welding process packet in the automatic programming controller according to the welding material characteristics and the welding seam characteristics to obtain welding speed, current and voltage welding parameters, stores the typical welding type, the workpiece and the welding seam type and the corresponding welding parameters in the form of the welding process packet, and selects a specific welding process packet to weld after the welding type, the workpiece and the welding seam type are input or obtained through the sensor. With the increasing of welding data, the welding parameters can be generated in real time by adopting a technical scheme of reinforcement learning.
2. The AI-based automatic weld path recognition method according to claim 1, wherein the movement trajectory refers to position and attitude information of a welding gun; in addition, in the motion trajectory, factors of collision detection and welding efficiency need to be comprehensively considered.
3. The AI-based automatic weld path identification method according to claim 1, wherein the acquired weld information is weld width, groove angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010308035.7A CN111390915B (en) | 2020-04-17 | 2020-04-17 | Automatic weld path identification method based on AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010308035.7A CN111390915B (en) | 2020-04-17 | 2020-04-17 | Automatic weld path identification method based on AI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111390915A true CN111390915A (en) | 2020-07-10 |
| CN111390915B CN111390915B (en) | 2022-07-15 |
Family
ID=71417601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010308035.7A Active CN111390915B (en) | 2020-04-17 | 2020-04-17 | Automatic weld path identification method based on AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111390915B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111872920A (en) * | 2020-07-22 | 2020-11-03 | 成都卡诺普自动化控制技术有限公司 | Offline teaching-free laser positioning method and system |
| CN112464405A (en) * | 2020-11-26 | 2021-03-09 | 江南造船(集团)有限责任公司 | Weld joint expression method based on three-dimensional model |
| CN112453648A (en) * | 2020-11-17 | 2021-03-09 | 上海智殷自动化科技有限公司 | Off-line programming laser welding seam tracking system based on 3D vision |
| CN112621030A (en) * | 2020-12-07 | 2021-04-09 | 重庆顺泰铁塔制造有限公司 | Method for generating welding track of power transmission tower node |
| CN112959329A (en) * | 2021-04-06 | 2021-06-15 | 南京航空航天大学 | Intelligent control welding system based on vision measurement |
| CN113177914A (en) * | 2021-04-15 | 2021-07-27 | 青岛理工大学 | Robot welding method and system based on semantic feature clustering |
| CN113369761A (en) * | 2021-07-09 | 2021-09-10 | 北京石油化工学院 | Method and system for guiding robot welding seam positioning based on vision |
| CN114119611A (en) * | 2022-01-25 | 2022-03-01 | 季华实验室 | Weld parameter identification method and device, electronic equipment and storage medium |
| CN114789442A (en) * | 2022-04-24 | 2022-07-26 | 重庆创御智能装备有限公司 | Self-adaptive path planning algorithm for welding robot |
| CN114851195A (en) * | 2022-04-24 | 2022-08-05 | 重庆创御智能装备有限公司 | Control method of visual welding process system |
| CN115351448A (en) * | 2022-08-10 | 2022-11-18 | 北斗启明（北京）节能科技服务有限公司 | Novel visual automatic welding technology |
| 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 (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104384765A (en) * | 2014-10-14 | 2015-03-04 | 江苏湃锐自动化科技有限公司 | Automatic welding method based on three-dimensional model and machine vision and welding device based on three-dimensional model and machine vision |
| DE102014223203A1 (en) * | 2014-11-13 | 2016-05-19 | Kuka Roboter Gmbh | Method for pendulum welding |
| EP3434424A1 (en) * | 2017-07-27 | 2019-01-30 | Convergent Information Technologies GmbH | Efficient programming of robots for processing of workpieces with various variants |
| CN109903279A (en) * | 2019-02-25 | 2019-06-18 | 北京深度奇点科技有限公司 | The automatic teaching method and device of weld seam motion profile |
| CN110039523A (en) * | 2019-05-20 | 2019-07-23 | 北京无远弗届科技有限公司 | A kind of industrial robot vision's servo-system, servo method and device |
| CN110102855A (en) * | 2019-05-15 | 2019-08-09 | 上海振华重工(集团)股份有限公司 | A kind of robot automtion welding system, device and method |
| CN110102886A (en) * | 2019-04-03 | 2019-08-09 | 安徽工布智造工业科技有限公司 | A kind of Intelligent welding system applied to metal structure |
| CN110434516A (en) * | 2019-08-28 | 2019-11-12 | 浙江大学城市学院 | A kind of Intelligent welding robot system and welding method |
| CN110524581A (en) * | 2019-09-16 | 2019-12-03 | 西安中科光电精密工程有限公司 | A kind of flexible welding robot system and its welding method |
-
2020
- 2020-04-17 CN CN202010308035.7A patent/CN111390915B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104384765A (en) * | 2014-10-14 | 2015-03-04 | 江苏湃锐自动化科技有限公司 | Automatic welding method based on three-dimensional model and machine vision and welding device based on three-dimensional model and machine vision |
| DE102014223203A1 (en) * | 2014-11-13 | 2016-05-19 | Kuka Roboter Gmbh | Method for pendulum welding |
| EP3434424A1 (en) * | 2017-07-27 | 2019-01-30 | Convergent Information Technologies GmbH | Efficient programming of robots for processing of workpieces with various variants |
| CN109903279A (en) * | 2019-02-25 | 2019-06-18 | 北京深度奇点科技有限公司 | The automatic teaching method and device of weld seam motion profile |
| CN110102886A (en) * | 2019-04-03 | 2019-08-09 | 安徽工布智造工业科技有限公司 | A kind of Intelligent welding system applied to metal structure |
| CN110102855A (en) * | 2019-05-15 | 2019-08-09 | 上海振华重工(集团)股份有限公司 | A kind of robot automtion welding system, device and method |
| CN110039523A (en) * | 2019-05-20 | 2019-07-23 | 北京无远弗届科技有限公司 | A kind of industrial robot vision's servo-system, servo method and device |
| CN110434516A (en) * | 2019-08-28 | 2019-11-12 | 浙江大学城市学院 | A kind of Intelligent welding robot system and welding method |
| CN110524581A (en) * | 2019-09-16 | 2019-12-03 | 西安中科光电精密工程有限公司 | A kind of flexible welding robot system and its welding method |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111872920A (en) * | 2020-07-22 | 2020-11-03 | 成都卡诺普自动化控制技术有限公司 | Offline teaching-free laser positioning method and system |
| CN112453648A (en) * | 2020-11-17 | 2021-03-09 | 上海智殷自动化科技有限公司 | Off-line programming laser welding seam tracking system based on 3D vision |
| CN112464405B (en) * | 2020-11-26 | 2022-11-15 | 江南造船(集团)有限责任公司 | Three-dimensional model-based weld joint expression method |
| CN112464405A (en) * | 2020-11-26 | 2021-03-09 | 江南造船(集团)有限责任公司 | Weld joint expression method based on three-dimensional model |
| CN112621030A (en) * | 2020-12-07 | 2021-04-09 | 重庆顺泰铁塔制造有限公司 | Method for generating welding track of power transmission tower node |
| CN112959329A (en) * | 2021-04-06 | 2021-06-15 | 南京航空航天大学 | Intelligent control welding system based on vision measurement |
| CN112959329B (en) * | 2021-04-06 | 2022-03-11 | 南京航空航天大学 | Intelligent control welding system based on vision measurement |
| CN113177914A (en) * | 2021-04-15 | 2021-07-27 | 青岛理工大学 | Robot welding method and system based on semantic feature clustering |
| CN113177914B (en) * | 2021-04-15 | 2023-02-17 | 青岛理工大学 | Robot welding method and system based on semantic feature clustering |
| CN113369761A (en) * | 2021-07-09 | 2021-09-10 | 北京石油化工学院 | Method and system for guiding robot welding seam positioning based on vision |
| CN113369761B (en) * | 2021-07-09 | 2023-07-21 | 北京石油化工学院 | Method and system for positioning welding seam based on vision guiding robot |
| CN114119611A (en) * | 2022-01-25 | 2022-03-01 | 季华实验室 | Weld parameter identification method and device, electronic equipment and storage medium |
| CN114119611B (en) * | 2022-01-25 | 2022-04-01 | 季华实验室 | Weld parameter identification method and device, electronic equipment and storage medium |
| WO2023142229A1 (en) * | 2022-01-25 | 2023-08-03 | 季华实验室 | Weld joint parameter identification method and apparatus, and electronic device and storage medium |
| CN114789442A (en) * | 2022-04-24 | 2022-07-26 | 重庆创御智能装备有限公司 | Self-adaptive path planning algorithm for welding robot |
| CN114851195A (en) * | 2022-04-24 | 2022-08-05 | 重庆创御智能装备有限公司 | Control method of visual welding process system |
| CN115351448A (en) * | 2022-08-10 | 2022-11-18 | 北斗启明（北京）节能科技服务有限公司 | Novel visual automatic welding technology |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111390915B (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111390915B (en) | Automatic weld path identification method based on AI | |
| CN111014879B (en) | Automatic welding method for corrugated plate of robot based on laser weld seam tracking | |
| US8706300B2 (en) | Method of controlling a robotic tool | |
| EP3119552B1 (en) | Method of welding components along a welding joint using two robots | |
| EP1123769A2 (en) | Robot welding | |
| CN109514133A (en) | A kind of autonomous teaching method of welding robot 3D curved welding seam based on line-structured light perception | |
| CN102211245A (en) | Spot welding system and dressing determination method | |
| JP2021035708A (en) | Production system | |
| CN112917038A (en) | Control method for automatic welding | |
| CN112958959A (en) | Automatic welding and detection method based on three-dimensional vision | |
| CN115255555A (en) | Welding process | |
| JP3191563B2 (en) | Automatic correction method for offline teaching data | |
| CN110508906A (en) | A kind of method that robotic laser displacement sensor seeks position | |
| CN114986050A (en) | Welding robot system based on ROS system and working method | |
| CN107199423B (en) | Non-programming teaching-free intelligent welding robot | |
| CN109986255B (en) | Hybrid vision servo parallel robot and operation method | |
| CN111992895A (en) | Intelligent marking system and method | |
| CN110919238B (en) | Automatic welding method and welding device | |
| CN108465905A (en) | Dual robot active light source intelligence centering double sides double arc connects method and apparatus | |
| CN113195142B (en) | Automatic welding system, method for manufacturing elevator car chamber member, and automatic welding method | |
| CN110695494B (en) | Corrugated plate external shaft tracking system and method thereof | |
| CN208575361U (en) | A kind of complexity Zhong Zuli robot compression arc MAG welder | |
| CN115041887A (en) | Contour measuring and recognizing system for robot welding workpiece | |
| WO2022091767A1 (en) | Image processing method, image processing device, robot mounted-type conveyance device, and system | |
| JP7093881B1 (en) | System and automatic guided vehicle |
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 |