CN106181162A - A kind of real-time weld joint tracking detecting system based on machine vision and method - Google Patents

A kind of real-time weld joint tracking detecting system based on machine vision and method Download PDF

Info

Publication number
CN106181162A
CN106181162A CN201610672098.4A CN201610672098A CN106181162A CN 106181162 A CN106181162 A CN 106181162A CN 201610672098 A CN201610672098 A CN 201610672098A CN 106181162 A CN106181162 A CN 106181162A
Authority
CN
China
Prior art keywords
image
welding
video camera
ccd video
real
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
Application number
CN201610672098.4A
Other languages
Chinese (zh)
Other versions
CN106181162B (en
Inventor
刘新华
王润泽
王勇
郝敬宾
司垒
徐荣鑫
高鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China University of Mining and Technology CUMT
Original Assignee
China University of Mining and Technology CUMT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China University of Mining and Technology CUMT filed Critical China University of Mining and Technology CUMT
Priority to CN201610672098.4A priority Critical patent/CN106181162B/en
Publication of CN106181162A publication Critical patent/CN106181162A/en
Application granted granted Critical
Publication of CN106181162B publication Critical patent/CN106181162B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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

Landscapes

  • Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Image Analysis (AREA)
  • Manipulator (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a kind of real-time weld joint tracking detecting system based on machine vision, it includes: it includes: control the industrial computer of equipment as the system core；The image acquisition units being made up of light source controller, LED light source, image pick-up card and ccd video camera；And the motion control unit being made up of robot controller, welding robot；Present invention additionally comprises the detection of a kind of real-time weld joint tracking based on machine vision, the step such as including image acquisition → image procossing → data process → motor control；The present invention uses the method that real-time online detects, it is not necessary to manually carry out unnecessary operation, comparison correction at the expectation seam track generated by groove image with actual welds track；And in the case of Site Welding environment and manual teaching environment, off-line programing simulated environment have different, it is possible to carry out real-time weld joint tracking, overcome all kinds of interference of welding scene, it is ensured that the accuracy of welding effect and reliability.

Description

A kind of real-time weld joint tracking detecting system based on machine vision and method
Technical field
The present invention relates to a kind of real-time weld joint tracking detecting system based on machine vision and method, belong to machine vision and Technical field of mechanical automation.
Background technology
Welding plays the most most important role the most in the industrial production, and along with robot and vision-based detection process The development of technology, the automatization level of solder technology improves day by day, and weld joint tracking detection method also develops into meter from manual detection Calculation machine Intelligent Measurement.
Existing welding robot belongs to on-site manual teaching type or off-line programing type, welding robot in both approaches mostly The welding parameter of people and path of welding are all to plan before producing, and make the welding robot can be high-precision in work space Degree ground repeats programming movement.
And the weld seam path of planning is contrasted by traditional weld joint tracking detection method with the actual weld seam path produced Error correction, it is achieved the tracking of weld seam.Such welding seam tracking method can ensure that the high accuracy fortune of welding robot in planning region Row and weld joint tracking, but path planning can only be tracked, the adaptability to changes for emergency case is poor.
During actual welding, the interference of welding scene is more, and the shape of weldment can be along with the change of production environment The collision etc. of burst in the high temperature that change, such as molten bath produce, relatively low assembly precision, welding process, all can be to welding production Cause corresponding impact；When Site Welding environment and manual teaching environment, off-line programing simulated environment have the situation of different Under, the effect that conventional weld is followed the tracks of is the most undesirable, this restrict the further development of existing THE WELD SEAM TRACKING TECHNOLOGY.
Summary of the invention
The problem existed for above-mentioned prior art, the present invention provides a kind of real-time weld joint tracking based on machine vision to examine Examining system and method, it has high accuracy and adaptivity, it is possible to carries out real-time weld joint tracking, overcome all kinds of of welding scene Interference, thus ensure accuracy and the reliability of welding effect.
To achieve these goals, the technical solution used in the present invention is: a kind of real-time weld seam based on machine vision with Track detecting system, it includes:
The industrial computer of equipment is controlled as the system core；
The image acquisition units being made up of light source controller, LED light source, image pick-up card and ccd video camera；
And the motion control unit being made up of robot controller, welding robot；
Described Industrial Control Computer is responsible for image, the process of data and calculating；Described light-source controller controls LED light source Mobile with the movement of welding gun, make light source cover at weld seam and groove to be welded, it is ensured that the daylighting degree of image acquisition region；
Described ccd video camera includes ccd video camera one, ccd video camera two；Ccd video camera one, ccd video camera two are respectively It is arranged on the both sides of welding robot welding gun, mobile with the movement of welding gun；And ccd video camera one is to be welded towards welding gun front end At groove, welding position below the positive Butt welding gun of ccd video camera two.
A kind of real-time weld joint tracking detection method based on machine vision, uses above-mentioned system, comprises the following steps:
1) image acquisition: before welding starts, light-source controller controls LED light source is irradiated to groove in the way of front illumination And commissure, ccd video camera gathers the image in groove region to be welded at the beginning, and after time t, ccd video camera two starts to gather weldering Connecing the weld image of part, two initial pictures are according to being all transferred in industrial computer；
Wherein t is the delay shot by ccd video camera two after groove a region is photographed the welding of a region by ccd video camera one Time；
2) image procossing: obtain groove by image filtering, image segmentation, Morphological scale-space and edge detection process method Edge image with welded seam area partial enlargement；
3) data process: process the edge image of groove region partial enlargement, judge groove class according to algorithm for pattern recognition Type, calculates planned expectation seam track, processes the weld image of welding portion, the weld seam rail that calculating equipment actually generates Mark, filtered after obtain two smooth Weld pipe mill tracks, two seam tracks are contrasted and calculate tracking correction amount；
4) motor control: industrial computer carries out real-time deviation correcting according to correction amount, controls the motion of welding robot with further Welding, thus realize the accurate tracking of weld seam.
Described step 2) image procossing detailed process as follows:
(1) use gaussian filtering method that initial pictures is carried out denoising；
Digital picture can (x, y), x, y represent pixel coordinate, f (x, y) table respectively to be expressed as form f of two-dimensional array The gray scale of diagram picture；
fs(x, y)=G (and x, y) * f (x, y)
fs(x y) represents the digital picture after gaussian filtering；
(2) use maximum variance between clusters that image carries out image segmentation:
Use a threshold value that whole data are divided into two classes, if the variance between two classes is maximum, then this threshold Value is exactly optimal threshold value；
σ 2 ( T * ) = max T ∈ G σ 2 ( T )
I.e. select to make σ2(Tb) maximum T*As optimal segmenting threshold；
(3) use dilation erosion algorithm that image carries out Morphological scale-space:
First with structural element, to f, (x, y) carries out dilation operation, then with structural element, result is carried out erosion operation；Profit Can eliminate, with dilation erosion algorithm, the hole that target object is unnecessary, connect close object, fill up tiny on contour line simultaneously Indent wedge angle with the border of smooth object；
(4) Canny edge detection algorithm is used to enter image line rim detection:
Calculate gradient magnitude and the direction of filtering image,
▿ f = g r a n d ( f ) = [ g x g y ] = [ ∂ f ∂ x ∂ f ∂ y ]
Gradient amplitude:
Gradient direction:
Again gradient magnitude is carried out non-maxima suppression, if M (x, value y) less than pixel any two neighborhood it One, then make gN(x, y)=0；Otherwise, g is madeN(x, y)=M (x, y).gN(x y) represents the image after carrying out non-maximum suppression；
Finally use dual threshold algorithm process decision chart as marginal point: to set a threshold value upper bound THWith threshold value lower bound TL, in image Pixel then think necessarily border (g if greater than the threshold value upper boundN(x, y) >=TH), then think the most not less than threshold value lower bound It is border (gN(x, y)≤TL), between the two be then considered candidate item.
Compared with existing welding seam tracking method, the method and system that the present invention uses has the following advantages and effect:
1. the present invention uses the method that real-time online detects, it is not necessary to manually carry out unnecessary operation, after welding starts Welding robot can fully automatically carry out weld joint tracking detection；
2. the present invention utilizes groove image to generate expectation seam track, strong to the adaptivity of Site Welding environment, when existing In the case of field welding surroundings has different with manual teaching environment, off-line programing simulated environment, it is possible to carry out real-time weld seam Follow the tracks of, overcome all kinds of interference of welding scene, it is ensured that the accuracy of welding effect and reliability.
Accompanying drawing explanation
Fig. 1 is the solution of the present invention general principles schematic diagram.
Fig. 2 is the system principle schematic diagram of the present invention.
Detailed description of the invention
The invention will be further described below in conjunction with the accompanying drawings.
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under not making creative work premise Embodiment, broadly falls into the scope of protection of the invention.
If Fig. 2 is a kind of real-time weld joint tracking detecting system based on machine vision, it includes:
The industrial computer of equipment is controlled as the system core；
The image acquisition units being made up of light source controller, LED light source, image pick-up card and ccd video camera；
And the motion control unit being made up of robot controller, welding robot；
Described Industrial Control Computer is responsible for image, the process of data and calculating；Described light-source controller controls LED light source Mobile with the movement of welding gun, make light source cover at weld seam and groove to be welded, it is ensured that the daylighting degree of image acquisition region；
Described ccd video camera includes ccd video camera one, ccd video camera two；Ccd video camera one, ccd video camera two are respectively It is arranged on the both sides of welding robot welding gun, mobile with the movement of welding gun；And ccd video camera one is to be welded towards welding gun front end At groove, welding position below the positive Butt welding gun of ccd video camera two.
Being illustrated in figure 1 a kind of real-time weld joint tracking detection method based on machine vision, it uses above-mentioned system, bag Include following steps:
1) image acquisition: before welding starts, light-source controller controls LED light source is irradiated to groove in the way of front illumination And commissure, ccd video camera gathers the image in groove region to be welded at the beginning, and after time t, ccd video camera two starts to gather weldering Connecing the weld image of part, two initial pictures are according to being all transferred in industrial computer；
Wherein t is the delay shot by ccd video camera two after groove a region is photographed the welding of a region by ccd video camera one Time；
2) image procossing: obtain groove by image filtering, image segmentation, Morphological scale-space and edge detection process method Edge image with welded seam area partial enlargement；
3) data process: process the edge image of groove region partial enlargement, judge groove class according to algorithm for pattern recognition Type, calculates planned expectation seam track, processes the weld image of welding portion, the weld seam rail that calculating equipment actually generates Mark, filtered after obtain two smooth Weld pipe mill tracks, two seam tracks are contrasted and calculate tracking correction amount；
4) motor control: industrial computer carries out real-time deviation correcting according to correction amount, controls the motion of welding robot with further Welding, thus realize the accurate tracking of weld seam.
In such scheme, step 1), 2), 3) all two different regions are detected and are processed: groove district to be welded Territory and welded seam region.
Groove region to be welded is with the root face at groove as application, by root face and remainder gray feature value Difference, extract the morphological characteristic of groove part root face, it is judged that groove type also calculates expectation Weld pipe mill track；Welding weldering Seam region, with weld seam as application, calculates actual welds centrode by the marginal information of weld seam.
In such scheme, if step 1) do not collect root face information, i.e. welding object square groove, then in step 3) Data Data process, with the set of object both sides to be welded breach central point for expectation Weld pipe mill track.
In such scheme, t is that groove a region is photographed after a region is welded by ccd video camera two by ccd video camera one The time delay of shooting, relevant with the welding procedure of welding equipment, speed of welding, computer disposal speed etc., it is ensured that to be contrasted Expectation, actual welds track be the same area, the seam track that is mutually matched.
Wherein, step 2) image procossing be broadly divided into image filtering, image segmentation, Morphological scale-space and rim detection 4 Part, detailed process is as follows:
(1) use gaussian filtering method that initial pictures is carried out denoising；
Digital picture can (x, y), x, y represent pixel coordinate, f (x, y) table respectively to be expressed as form f of two-dimensional array The gray scale of diagram picture；
fs(x, y)=G (and x, y) * f (x, y)
fs(x y) represents the digital picture after gaussian filtering；
(2) use maximum variance between clusters that image carries out image segmentation:
Use a threshold value that whole data are divided into two classes, if the variance between two classes is maximum, then this threshold Value is exactly optimal threshold value；
σ 2 ( T * ) = max T ∈ G σ 2 ( T )
I.e. select to make σ2(Tb) maximum T*As optimal segmenting threshold；
(3) use dilation erosion algorithm that image carries out Morphological scale-space:
First with structural element, to f, (x, y) carries out dilation operation, then with structural element, result is carried out erosion operation；Profit Can eliminate, with dilation erosion algorithm, the hole that target object is unnecessary, connect close object, fill up tiny on contour line simultaneously Indent wedge angle with the border of smooth object；
(4) Canny edge detection algorithm is used to enter image line rim detection:
Calculate gradient magnitude and the direction of filtering image,
▿ f = g r a n d ( f ) = [ g x g y ] = [ ∂ f ∂ x ∂ f ∂ y ]
Gradient amplitude:
Gradient direction:
Again gradient magnitude is carried out non-maxima suppression, if M(x, value y) less than pixel any two neighborhood it One, then make gN(x, y)=0；Otherwise, g is madeN(x, y)=M (x, y).gN(x y) represents the image after carrying out non-maximum suppression；
Finally use dual threshold algorithm process decision chart as marginal point: to set a threshold value upper bound THWith threshold value lower bound TL, in image Pixel then think necessarily border (g if greater than the threshold value upper boundN(x, y) >=TH), then think the most not less than threshold value lower bound It is border (gN(x, y) >=TL), between the two be then considered candidate item.
In such scheme, step 3) judge groove type by algorithm for pattern recognition, further according to the welding of different grooves Feature, integrating step 2) the groove image that obtains calculates expectation seam track；Expect that seam track and actual welds track are through excellent Compare after changing smoothing processing, its departure, bias direction and tolerance speed are carried out Optimal calculation.
Compared with existing welding seam tracking method, the method and system that the present invention uses has the following advantages and effect:
1. the present invention uses the method that real-time online detects, it is not necessary to manually carry out unnecessary operation, after welding starts Welding robot can fully automatically carry out weld joint tracking detection；
2. the present invention utilizes groove image to generate expectation seam track, strong to the adaptivity of Site Welding environment, when existing In the case of field welding surroundings has different with manual teaching environment, off-line programing simulated environment, it is possible to carry out real-time weld seam Follow the tracks of, overcome all kinds of interference of welding scene, it is ensured that the accuracy of welding effect and reliability.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie In the case of the spirit or essential attributes of the present invention, it is possible to realize the present invention in other specific forms.Therefore, no matter From the point of view of which point, all should regard embodiment as exemplary, and be nonrestrictive, the scope of the present invention is by appended power Profit requires rather than described above limits, it is intended that all by fall in the implication of equivalency and scope of claim Change is included in the present invention.Should not be considered as limiting involved claim by any reference in claim.
The above, only presently preferred embodiments of the present invention, not in order to limit the present invention, every skill according to the present invention Any trickle amendment, equivalent and the improvement that above example is made by art essence, should be included in technical solution of the present invention Protection domain within.

Claims (3)

1. a real-time weld joint tracking detecting system based on machine vision, it is characterised in that it includes:
The industrial computer of equipment is controlled as the system core；
The image acquisition units being made up of light source controller, LED light source, image pick-up card and ccd video camera；
And the motion control unit being made up of robot controller, welding robot；
Described Industrial Control Computer is responsible for image, the process of data and calculating；Described light-source controller controls LED light source is with weldering The movement of rifle and move, make light source cover at weld seam and groove to be welded, it is ensured that the daylighting degree of image acquisition region；
Described ccd video camera includes ccd video camera one, ccd video camera two；Ccd video camera one, ccd video camera two are respectively mounted In the both sides of welding robot welding gun, mobile with the movement of welding gun；And ccd video camera one is towards welding gun front end groove to be welded Place, welding position below the positive Butt welding gun of ccd video camera two.
2. a real-time weld joint tracking detection method based on machine vision, it is characterised in that use as claimed in claim 1 System, comprises the following steps:
1) image acquisition: before welding starts, light-source controller controls LED light source is irradiated to groove and weldering in the way of front illumination At seam, ccd video camera gathers the image in groove region to be welded at the beginning, and after time t, ccd video camera two starts to gather weld part The weld image divided, two initial pictures are according to being all transferred in industrial computer；
When wherein t is the delay shot by ccd video camera two after groove a region is photographed the welding of a region by ccd video camera one Between；
2) image procossing: obtain groove and weldering by image filtering, image segmentation, Morphological scale-space and edge detection process method The edge image of seam region partial enlargement；
3) data process: process the edge image of groove region partial enlargement, judge groove type according to algorithm for pattern recognition, meter Calculate planned expectation seam track；Process the weld image of welding portion, the seam track that calculating equipment actually generates, warp Obtain two smooth Weld pipe mill tracks after filtering, two seam tracks are contrasted and calculate tracking correction amount；
4) motor control: industrial computer carries out real-time deviation correcting according to correction amount, controls motion and the further weldering of welding robot Connect, thus realize the accurate tracking of weld seam.
A kind of real-time weld joint tracking detection method based on machine vision the most according to claim 2, it is characterised in that institute The step 2 stated) image procossing detailed process as follows:
(1) use gaussian filtering method that initial pictures is carried out denoising；
Digital picture can (x, y), x, y represent pixel coordinate respectively, and (x y) represents figure to f to be expressed as form f of two-dimensional array The gray scale of picture；
fs(x, y)=G (and x, y) * f (x, y)
fs(x y) represents the digital picture after gaussian filtering；
(2) use maximum variance between clusters that image carries out image segmentation:
Use a threshold value that whole data are divided into two classes, if the variance between two classes is maximum, then this threshold value is just It it is optimal threshold value；
σ 2 ( T * ) = max T ∈ G σ 2 ( T )
I.e. select to make σ2(Tb) maximum T*As optimal segmenting threshold；
(3) use dilation erosion algorithm that image carries out Morphological scale-space:
First with structural element, to f, (x, y) carries out dilation operation, then with structural element, result is carried out erosion operation；Utilize swollen Swollen erosion algorithm can eliminate the hole that target object is unnecessary, connects close object, fills up tiny interior on contour line simultaneously Recessed wedge angle is with the border of smooth object；
(4) Canny edge detection algorithm is used to enter image line rim detection:
Calculate gradient magnitude and the direction of filtering image,
▿ f = g r a n d ( f ) = [ g x g y ] = [ ∂ f ∂ x ∂ f ∂ y ]
Gradient amplitude:
Gradient direction:
Again gradient magnitude is carried out non-maxima suppression, if M (x, value y) is less than one of any two neighborhood of pixel, Then make gN(x, y)=0；Otherwise, g is madeN(x, y)=M (x, y)；gN(x y) represents the image after carrying out non-maximum suppression；
Finally use dual threshold algorithm process decision chart as marginal point: to set a threshold value upper bound THWith threshold value lower bound TL, picture in image Vegetarian refreshments then thinks necessarily border (g if greater than the threshold value upper boundN(x, y) >=TH), then thinking inevitable less than threshold value lower bound is not limit Boundary (gN(x, y)≤TL), between the two be then considered candidate item.
CN201610672098.4A 2016-08-12 2016-08-12 A kind of real-time weld joint tracking detection method based on machine vision Active CN106181162B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610672098.4A CN106181162B (en) 2016-08-12 2016-08-12 A kind of real-time weld joint tracking detection method based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610672098.4A CN106181162B (en) 2016-08-12 2016-08-12 A kind of real-time weld joint tracking detection method based on machine vision

Publications (2)

Publication Number Publication Date
CN106181162A true CN106181162A (en) 2016-12-07
CN106181162B CN106181162B (en) 2018-10-23

Family

ID=57522633

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610672098.4A Active CN106181162B (en) 2016-08-12 2016-08-12 A kind of real-time weld joint tracking detection method based on machine vision

Country Status (1)

Country Link
CN (1) CN106181162B (en)

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106851062A (en) * 2017-02-04 2017-06-13 同济大学 A kind of weld seam recognition device based on machine vision
CN106945047A (en) * 2017-04-27 2017-07-14 上海新朋联众汽车零部件有限公司 Welding robot error compensation control system and its control method
CN107803606A (en) * 2017-10-13 2018-03-16 上海交通大学 A kind of detection method for quality of welding line and device based on overall process mark
CN108127286A (en) * 2018-01-11 2018-06-08 上海振华重工(集团)股份有限公司 A kind of abnormity Chong Bang plates robot automatic welding method
CN108247179A (en) * 2017-12-15 2018-07-06 太原科技大学 I shape grooves CO based on crater image2Weld deviation detecting method and device
CN108907526A (en) * 2018-08-04 2018-11-30 苏州佩恩机器人有限公司 A kind of weld image characteristic recognition method with high robust
CN109365960A (en) * 2018-12-07 2019-02-22 北京博清科技有限公司 Welding tracking identifies equipment and welding system
CN109483018A (en) * 2018-11-06 2019-03-19 湖北书豪智能科技有限公司 The active vision bootstrap technique of weld seam in automatic welding of pipelines
CN109877496A (en) * 2019-03-30 2019-06-14 哈尔滨理工大学 A kind of weld and HAZ detection system based on image sensing technology
CN110315172A (en) * 2019-08-08 2019-10-11 江苏汇博机器人技术股份有限公司 A kind of robot welding line tracking system for real training
CN110461524A (en) * 2017-02-27 2019-11-15 通用电气技术有限公司 System and method for manufacturing the boiler tube of the synchronous rotary with pipe relevant to automatic welding
CN110548988A (en) * 2019-09-23 2019-12-10 航天工程装备（苏州）有限公司 Automatic welding seam track recognition device and method based on visual technology
CN111097664A (en) * 2019-12-20 2020-05-05 广西柳州联耕科技有限公司 Real-time deviation rectifying method based on robot gluing
CN112238304A (en) * 2019-07-18 2021-01-19 山东淄博环宇桥梁模板有限公司 Method for automatically welding small-batch customized special-shaped bridge steel templates by mechanical arm based on image visual recognition of welding seams
CN112692470A (en) * 2020-11-27 2021-04-23 中船海洋动力部件有限公司 Robot off-line adaptive programming processing system and method based on visual sensing
CN114211168A (en) * 2022-02-21 2022-03-22 江苏天健智能装备制造有限公司 Method for correcting plane welding seam track based on image subtraction
CN114289857A (en) * 2022-01-25 2022-04-08 江西理工大学 Method for automatically correcting travel path of stirring head of friction stir welding equipment
CN114749849A (en) * 2022-06-01 2022-07-15 江苏徐工工程机械研究院有限公司 Welding control method, device and system
CN114769962A (en) * 2022-05-07 2022-07-22 广州东焊智能装备有限公司 Welding seam recognition and tracking system of mobile welding robot based on visual sensing
CN115570310A (en) * 2022-10-27 2023-01-06 华南理工大学 Dynamic reconstruction method, device, system, equipment and storage medium for welding line point cloud

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101219498A (en) * 2007-01-10 2008-07-16 李云峰 Welding line auto-tracking and controlling device of video frequency image sensor TIG weld
CN101961819A (en) * 2009-07-22 2011-02-02 中国科学院沈阳自动化研究所 Device for realizing laser welding and seam tracking and control method thereof
CN103008881A (en) * 2012-12-05 2013-04-03 中国电子科技集团公司第四十五研究所 Seam tracking method based on template matching
US20140027415A1 (en) * 2012-07-26 2014-01-30 General Electric Company Adaptive control hybrid welding system and methods of controlling
CN103934571A (en) * 2014-04-11 2014-07-23 上海交通大学 Thick plate robot welding system and multilayer multiple-pass weld real-time tracking and planning method
CN105798430A (en) * 2016-05-27 2016-07-27 廊坊智通机器人系统有限公司 Laser visual monitoring system for real-time welding line tracking
CN105817743A (en) * 2016-05-27 2016-08-03 天津智通机器人有限公司 Double-vision automatic weld joint tracking device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101219498A (en) * 2007-01-10 2008-07-16 李云峰 Welding line auto-tracking and controlling device of video frequency image sensor TIG weld
CN101961819A (en) * 2009-07-22 2011-02-02 中国科学院沈阳自动化研究所 Device for realizing laser welding and seam tracking and control method thereof
US20140027415A1 (en) * 2012-07-26 2014-01-30 General Electric Company Adaptive control hybrid welding system and methods of controlling
CN103008881A (en) * 2012-12-05 2013-04-03 中国电子科技集团公司第四十五研究所 Seam tracking method based on template matching
CN103934571A (en) * 2014-04-11 2014-07-23 上海交通大学 Thick plate robot welding system and multilayer multiple-pass weld real-time tracking and planning method
CN105798430A (en) * 2016-05-27 2016-07-27 廊坊智通机器人系统有限公司 Laser visual monitoring system for real-time welding line tracking
CN105817743A (en) * 2016-05-27 2016-08-03 天津智通机器人有限公司 Double-vision automatic weld joint tracking device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
潘东等: "基于机器视觉的焊接跟踪技术的应用研究", 《机械制造》 *

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106851062A (en) * 2017-02-04 2017-06-13 同济大学 A kind of weld seam recognition device based on machine vision
CN110461524A (en) * 2017-02-27 2019-11-15 通用电气技术有限公司 System and method for manufacturing the boiler tube of the synchronous rotary with pipe relevant to automatic welding
CN106945047A (en) * 2017-04-27 2017-07-14 上海新朋联众汽车零部件有限公司 Welding robot error compensation control system and its control method
CN107803606A (en) * 2017-10-13 2018-03-16 上海交通大学 A kind of detection method for quality of welding line and device based on overall process mark
CN108247179A (en) * 2017-12-15 2018-07-06 太原科技大学 I shape grooves CO based on crater image2Weld deviation detecting method and device
CN108127286A (en) * 2018-01-11 2018-06-08 上海振华重工(集团)股份有限公司 A kind of abnormity Chong Bang plates robot automatic welding method
CN108127286B (en) * 2018-01-11 2019-08-09 上海振华重工(集团)股份有限公司 A kind of abnormity Chong Bang plate robot automatic welding method
CN108907526A (en) * 2018-08-04 2018-11-30 苏州佩恩机器人有限公司 A kind of weld image characteristic recognition method with high robust
CN109483018A (en) * 2018-11-06 2019-03-19 湖北书豪智能科技有限公司 The active vision bootstrap technique of weld seam in automatic welding of pipelines
CN109365960A (en) * 2018-12-07 2019-02-22 北京博清科技有限公司 Welding tracking identifies equipment and welding system
CN109365960B (en) * 2018-12-07 2024-07-26 北京博清科技有限公司 Welding tracking and identifying equipment and welding system
CN109877496A (en) * 2019-03-30 2019-06-14 哈尔滨理工大学 A kind of weld and HAZ detection system based on image sensing technology
CN112238304A (en) * 2019-07-18 2021-01-19 山东淄博环宇桥梁模板有限公司 Method for automatically welding small-batch customized special-shaped bridge steel templates by mechanical arm based on image visual recognition of welding seams
CN112238304B (en) * 2019-07-18 2023-01-06 山东淄博环宇桥梁模板有限公司 Method for automatically welding small-batch customized special-shaped bridge steel templates by mechanical arm based on image visual recognition of welding seams
CN110315172B (en) * 2019-08-08 2021-06-25 江苏汇博机器人技术股份有限公司 Robot welding seam tracking system for practical training
CN110315172A (en) * 2019-08-08 2019-10-11 江苏汇博机器人技术股份有限公司 A kind of robot welding line tracking system for real training
CN110548988A (en) * 2019-09-23 2019-12-10 航天工程装备（苏州）有限公司 Automatic welding seam track recognition device and method based on visual technology
CN111097664B (en) * 2019-12-20 2021-05-25 广西柳州联耕科技有限公司 Real-time deviation rectifying method based on robot gluing
CN111097664A (en) * 2019-12-20 2020-05-05 广西柳州联耕科技有限公司 Real-time deviation rectifying method based on robot gluing
CN112692470A (en) * 2020-11-27 2021-04-23 中船海洋动力部件有限公司 Robot off-line adaptive programming processing system and method based on visual sensing
CN114289857A (en) * 2022-01-25 2022-04-08 江西理工大学 Method for automatically correcting travel path of stirring head of friction stir welding equipment
CN114211168A (en) * 2022-02-21 2022-03-22 江苏天健智能装备制造有限公司 Method for correcting plane welding seam track based on image subtraction
CN114769962A (en) * 2022-05-07 2022-07-22 广州东焊智能装备有限公司 Welding seam recognition and tracking system of mobile welding robot based on visual sensing
CN114769962B (en) * 2022-05-07 2024-01-30 广州东焊智能装备有限公司 Weld joint recognition tracking system of mobile welding robot based on visual sense
CN114749849A (en) * 2022-06-01 2022-07-15 江苏徐工工程机械研究院有限公司 Welding control method, device and system
CN114749849B (en) * 2022-06-01 2023-09-01 江苏徐工工程机械研究院有限公司 Welding control method, device and system
CN115570310A (en) * 2022-10-27 2023-01-06 华南理工大学 Dynamic reconstruction method, device, system, equipment and storage medium for welding line point cloud
CN115570310B (en) * 2022-10-27 2024-08-09 华南理工大学 Weld joint point cloud dynamic reconstruction method, device, system, equipment and storage medium

Also Published As

Publication number Publication date
CN106181162B (en) 2018-10-23

Similar Documents

Publication Publication Date Title
CN106181162A (en) A kind of real-time weld joint tracking detecting system based on machine vision and method
Lei et al. A review of vision-aided robotic welding
Xu et al. Visual sensing technologies in robotic welding: Recent research developments and future interests
CN107824940A (en) Welding seam traking system and method based on laser structure light
CN206263418U (en) A kind of real-time seam tracking system of six degree of freedom welding robot line laser
CN103759648B (en) A kind of complicated angle welding method for detecting position based on Binocular stereo vision with laser
Gu et al. Autonomous seam acquisition and tracking system for multi-pass welding based on vision sensor
CN109604777A (en) Welding seam traking system and method based on laser structure light
CN105571502A (en) Measuring method of weld gap in friction-stir welding
CN108032011B (en) Initial point guiding device and method are stitched based on laser structure flush weld
CN109483018A (en) The active vision bootstrap technique of weld seam in automatic welding of pipelines
CN108344693B (en) Automatic welding-oriented visual measurement method for misalignment of sheet welding seam
CN113269762B (en) Screen defect detection method, system and computer storage medium
CN108907526A (en) A kind of weld image characteristic recognition method with high robust
CN110503638B (en) Spiral adhesive quality online detection method
Fan et al. Seam feature point acquisition based on efficient convolution operator and particle filter in GMAW
CN104325268A (en) Industrial robot three-dimensional space independent assembly method based on intelligent learning
CN105157603A (en) Line laser sensor and method for calculating three-dimensional coordinate data of line laser sensor
CN114140439A (en) Laser welding seam feature point identification method and device based on deep learning
CN106493495A (en) High-accuracy machine vision alignment system
CN115070298A (en) Efficient double-wire welding path generation system and path generation method
Liu et al. Seam tracking system based on laser vision and CGAN for robotic multi-layer and multi-pass MAG welding
Lin et al. Intelligent seam tracking of an ultranarrow gap during K-TIG welding: a hybrid CNN and adaptive ROI operation algorithm
Ye et al. Weld seam tracking based on laser imaging binary image preprocessing
CN114842144A (en) Binocular vision three-dimensional reconstruction method and system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant