CN209550915U - A kind of on-line measuring device of the Laser Welding hump defect based on image procossing - Google Patents

A kind of on-line measuring device of the Laser Welding hump defect based on image procossing Download PDF

Info

Publication number
CN209550915U
CN209550915U CN201821450222.3U CN201821450222U CN209550915U CN 209550915 U CN209550915 U CN 209550915U CN 201821450222 U CN201821450222 U CN 201821450222U CN 209550915 U CN209550915 U CN 209550915U
Authority
CN
China
Prior art keywords
axis
servo motor
laser
axis servo
fixture
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.)
Expired - Fee Related
Application number
CN201821450222.3U
Other languages
Chinese (zh)
Inventor
丁树权
游德勇
许礼彬
潘雅灵
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.)
Guangdong University of Technology
Original Assignee
Guangdong University of Technology
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 Guangdong University of Technology filed Critical Guangdong University of Technology
Priority to CN201821450222.3U priority Critical patent/CN209550915U/en
Application granted granted Critical
Publication of CN209550915U publication Critical patent/CN209550915U/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Laser Beam Processing (AREA)

Abstract

The on-line measuring device for the Laser Welding hump defect based on image procossing that the utility model discloses a kind of, described device include the structures such as laser 17, optical fiber, laser focusing head 1, bracket 14, workpiece 2, fixture jacking block 3, fixture bolt 4, cushion block 5, clamp bottom board 6, Y-axis servo motor 7, Y-axis sliding rail 8;Reliable basis of the utility model testing result as adjusting process parameter fast and accurately can be judged and be effectively eliminated to hump defect;Algorithm adaptability is good, and portable strong, flexibility and independence degree are higher, and higher to defect recognition precision, equipment is simple, have broad application prospects.

Description

A kind of on-line measuring device of the Laser Welding hump defect based on image procossing
Technical field
The utility model relates to Laser Welding Quality on-line checking field more particularly to a kind of laser based on image procossing Weld the on-line measuring device of hump defect.
Background technique
Welding is manufacturing fundamental technology.Compared with other welding techniques, laser welding is small with heat input, welds Seam depth-to-width ratio is big, speed of welding is fast, flexible, high degree of automation, is not necessarily to the remarkable advantages such as vacuum environment, has been widely applied In industries such as nuclear energy, shipbuilding industry, aerospace, national defence weapon, auto manufacturing and rolling stock manufactures, it is considered to be 21 century One of advanced interconnection technique most with prospects.Especially in high power laser welding, since laser power density is high, energy The behaviors such as air pressure, molten bath flowing have more complexity in the more, metallic vapour of amount input, hole, are easy to generation welding defect, wherein As one of common deficiency, the aperture bottom that laser beam heat is concentrically formed in welding process fails to continue opening hump, causes Metal liquid forms hump in the accumulation at aperture back, extreme influence the smooth beauty of weldquality and weld seam back, Since technological parameter each in welding process has complicated coupled relation, the producing cause of current such defect fails to obtain very It good parsing and avoids.
In the context of detection of laser welding defect, a kind of retrieval discovery: patent " laser welding defect based on spectral information Inline diagnosis method " (specific quantitative criteria 201710361486.5) application number: is established based on spectral information to judge The presence or absence of defect, shortcoming are that this method fails to play detection and inhibitory effect well for hump defect.Patent " a method of inhibit myriawatt grade laser welding upper surface defect " (application number: 201510039722.2) devise metal Grain transportation system can supply the loss of material when part splashing generates, reduce the generation of Welding bead subsidence, but for hump defect Elimination fail to have effect.Related patents are had no in terms of the detection and inhibition of the hump defect of laser welding workpiece at present.
Therefore we are dedicated to developing on-line measuring device and the side of a kind of Laser Welding hump defect based on image procossing Method can carry out on-line checking to workpiece back situation in welding process and effectively eliminate hump defect to solve the above problems.
Utility model content
The purpose of this utility model is that proposing a kind of on-line checking dress of Laser Welding hump defect based on image procossing It sets and method, on-line checking can be carried out to workpiece back situation in welding process, hump defect can be effectively eliminated.
Technical solution adopted by the utility model: the on-line checking of the Laser Welding hump defect based on image procossing Device includes three axis slide units, fixture module, control module, laser, optical fiber, laser focusing head, bracket, device bottom plate;Three axis Clamp bottom board is installed above slide unit, fixture module is installed on clamp bottom board, is gone back on the bracket installed above three axis slide units Laser focusing head is installed, is connected by optical fiber with laser, installs optical filter before high speed camera additional.
The three axis slide units include X-axis slide rail, X-axis servo motor, Y-axis sliding rail, Y axis servo motor, Z axis slide rail; Specific connection is that X-axis slide rail is equipped on device bottom plate, and the end of X-axis slide rail is equipped with X-axis servo motor, X-axis slide rail Y axis sliding rail is installed, the end of Y-axis sliding rail is equipped with Y-axis servo motor, is equipped with fixture on the sliding block of Y-axis sliding rail on sliding block Bottom plate, also vertically-mounted on device bottom plate to have Z axis slide rail, the end of Z axis slide rail is equipped with Z axis servo motor, the cunning of Z axis slide rail Bracket is installed on block.
The fixture module includes clamp bottom board, cushion block, workpiece, fixture jacking block, fixture bolt;Specific connection is to press from both sides Have and two cushion blocks are installed on bottom plate, places workpiece on cushion block, fixture jacking block workpiece pressing is simultaneously locked by fixture bolt.
The control module includes, X-axis servo motor, Y-axis servo motor, Z axis servo motor, motion control unit, Laser, cooling system, high speed camera, industrial personal computer, monitor;Specific connection is X-axis servo motor, Y-axis servo motor, Z Axis servo motor is connected with motion control unit respectively, industrial personal computer 19 respectively with motion control unit, laser, cooling system, High speed camera connection, industrial personal computer are also connect with monitor.
Specifically, adjustment mode is divided into two kinds, the first is to inhibit hump by adjusting speed of welding, and second is logical Adjustment defocusing amount is crossed to inhibit hump.
The workflow of the first is: clamping, and starting sliding rail welding, high speed camera is to side surface of workpiece timing acquiring figure Picture is passed back in industrial personal computer in real time and is handled according to the algorithmic procedure of the utility model by piece, and the adjustment of processing result is joined Number S is compared with standard value, and Real-time Feedback changes the rotation of X-axis servo motor to motion control unit if being more than threshold value Speed, to change the slide block movement speed of X-axis slide rail, so as to adjust speed of welding.
Second of workflow is clamping, starting sliding rail welding, high speed camera to side surface of workpiece timing acquiring picture, Picture is passed back in real time in industrial personal computer and is handled according to the algorithmic procedure of the utility model, by the adjusting parameter S of processing result It is compared with standard value, Real-time Feedback makes Z axis servo motor generate certain angle position to motion control unit if being more than threshold value It moves, the sliding block in Z axis slide rail is made to move down certain distance, drive laser focusing head to move down certain distance by bracket, To make laser spot move down.
The utility model has the beneficial effects that
1. the quantitative criteria for establishing hump carries out on-line checking and assessment, testing result to workpiece hump in welding process As the reliable basis of adjusting process parameter, hump defect fast and accurately can be judged and be effectively eliminated.
2. algorithm adaptability is good, portable strong, flexibility and independence degree are higher, and testing result is reliable.
3. equipment is simple, slightly improving existing equipment can be realized, be had broad application prospects.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the hump on-line measuring device of the utility model;
Fig. 2 is the right view of the hump on-line measuring device of the utility model;
Fig. 3 is the structural block diagram of the hump on-line measuring device of the utility model;
Fig. 4 is the realization step block diagram of the image processing algorithm of the hump online test method of the utility model;
Fig. 5 is the schematic diagram that the relevant hump defect of the utility model generates.
Label declaration: 1. laser focusing heads, 2. workpiece, 3. fixture jacking blocks, 4. fixture bolts, 5. cushion blocks, 6. fixture bottoms Plate, 7.Y axis servo motor, 8.Y axis sliding rail, 9.X axis sliding rail, 10.X axis servo motor, 11. device bottom plates, 12. high-speed cameras Head, 13.Z axis sliding rail, 14. brackets, 15.Z axis servo motor, 16. motion control units, 17. lasers, 18. cooling systems, 19. industrial personal computer, 20. monitors.
Specific embodiment
Below in conjunction with the attached drawing in utility model embodiment, the technical scheme in the embodiment of the utility model is carried out clear Chu is fully described by, it is clear that the described embodiments are only a part of the embodiments of the utility model, rather than whole realities Apply example.Based on the embodiments of the present invention, those of ordinary skill in the art institute without creative efforts The every other embodiment obtained, fall within the protection scope of the utility model.
As shown in Figure 1, 2, 3, the on-line measuring device of the Laser Welding hump defect based on image procossing includes three axis Slide unit, fixture module, control module, laser 17, optical fiber (not shown), laser focusing head 1, bracket 14, device bottom plate 11; Clamp bottom board 6 is installed above three axis slide units, fixture module, the bracket installed above three axis slide units are installed on clamp bottom board It is also equipped with laser focusing head 1 on 14, is connected by optical fiber with laser 17, installs optical filter additional before high speed camera 12, with drop Low light intensity, high speed camera 12 generate position and its rear to molten bath open back hump in welding and shoot.
The three axis slide units include that X-axis slide rail 9, X-axis servo motor 10, Y-axis sliding rail 8, Y-axis servo motor 7, Z axis are sliding Rail 13;Specific connection is that X-axis slide rail 9 is equipped on device bottom plate 11, and the end of X-axis slide rail 9 is equipped with X-axis servo motor 10, Y-axis sliding rail 8 is installed, the end of Y-axis sliding rail 8 is equipped with Y-axis servo motor 7, the cunning of Y-axis sliding rail 8 on the sliding block of X-axis slide rail 9 Clamp bottom board 6 is installed, also vertically-mounted on device bottom plate 11 to have Z axis slide rail 13, the end of Z axis slide rail 13 is equipped with Z on block Axis servo motor 15 is equipped with bracket 14 on the sliding block of Z axis slide rail 13.
The fixture module includes clamp bottom board 6, cushion block 5, workpiece 2, fixture jacking block 3, fixture bolt 4;Specific connection It is that two cushion blocks 5 are installed on clamp bottom board 6, places workpiece 2 on cushion block 5, cushion block 5 is set so that high speed camera 12 is to workpiece 2 Back welding situation is shot;3 workpiece pressing 2 of fixture jacking block is simultaneously locked by fixture bolt 4.
The control module includes X-axis servo motor 10, Y-axis servo motor 7, Z axis servo motor 15, motion control Unit 16, laser 17, cooling system 18, high speed camera 12, industrial personal computer 19, monitor 20;Specific connection is X-axis servo Motor 10, Y axis servo motor 7, Z axis servo motor 15 are connected with motion control unit 16 respectively, control X-axis slide rail 9, Y respectively Axis sliding rail 8,13 movement velocity of Z axis slide rail, to control movement velocity and the direction of workpiece 2;Industrial personal computer 19 is controlled with movement respectively Unit 16 processed, laser 17, cooling system 18, high speed camera 12 connect, and industrial personal computer 19 is also connect with monitor 20, for grasping Author input welding condition and image acquisition parameter, the progress for monitoring welding region, control welding progress and stopping, rule The danger that operator operates and observes close to welding region is kept away.
Laser 17 uses Nd:YAG solid state laser, CO2Appointing in laser, disc type laser device or semiconductor laser It anticipates one kind.
As shown in figure 4, steps are as follows for the realization of image processing algorithm:
S11, picture pretreatment, including extracted region and binaryzation.Picture when to a laser welding extracts interested Region.
S12, corrosion treatment.In bianry image, problem set is two-dimensional integer space Z2Element.As Z2In collection A and B is closed, indicates corrosion of the B to A is defined as:
Wherein B is a structural elements (in this case, it is the square structure members that a size is 5 × 5);A is to be corroded pair As.The noise in binaryzation picture can be effectively removed using corrosion, and (hump, flies at steam in the region of diminution each section Splash) size, the area size for reducing each section, which can shield non-humped area for next step, provide convenience.S13, non-hump zone Domain shielding.Due to the often generation of accompanied splash and metallic vapour in laser welding, influence is caused for the detection of hump, Therefore need to shield these non-humped areas, interested humped area is left, the length including bounding box for extracting hump is facilitated The attributes such as wide and hump area.
S14, expansion process.Expansion process is carried out after carrying out shielding processing to non-hump zone, then to remaining hump zone, It is similar with S2, indicate expansion of the B to A is defined as:
Wherein B is that (in this case, it is the disc structure members that a size is 4 × 4 for a structural elements;A is inflated object,For the reflection of set B, it is defined as follows:
I.e. if B is the set for describing the pixel of objects in images,It is that (x, y) coordinate is substituted by (- x ,-y) in B Point set.
Contraction refinement is brought it about due to being corroded in second step humped area, expansion can be such that it has been restored to originally Shape.
S15, subregion mark.Label is carried out for each obtained humped area of S4, region is found by eight connectivity, that is, works as There is a pixel in lower or so or upper left, upper right, lower-left, the one of direction in bottom right to one pixel on it, then two pixels It is labeled as the same area.
S16, zone attribute is obtained.To each subregion, its bounding box and area are obtained.Bounding box, which is one, may include The minimum rectangle of the humped area is indicated by a four-dimensional vector [x, y, length, width], has respectively represented bounding box X coordinate, y-coordinate, length and width, and this frame is shown on picture.
S17, data processing.The attribute of obtained hump subregion is handled, its length-width ratio Ratio=is obtained Length/Width constitutes a bivector [Ratio, Area] with area, utilizes formula: w1Ratio+w2Area=S is obtained Adjusting parameter S is obtained, wherein w1、w2The respectively weight coefficient of length-width ratio and area.
S18, data transmission.If adjusting parameter S is more than predetermined threshold, motion control unit 16 is transmitted a signal to, is subtracted The speed of service of small X-axis servo motor 10, adjustment the result is that adjusting parameter S reduces (indicate hump generate trend be suppressed), When the speed of service that adjusting parameter S is decreased in predetermined threshold, and motion control unit 16 maintains X-axis servo motor 10 current.
Non- humped area can be obtained by a large amount of experimental data.The foundation of non-humped area has the following steps:
S131, experimental data are the image data shot by high speed camera 12, sample frequency 5000fps, to acquisition Each picture, mark out non-hump zone and hump zone.Due to molten bath bottom trace be move downward and edge do not advise Definition then be steam and and splash, and motion profile is determined along the edge moved toward welding opposite direction on the downside of welding plate is round and smooth Justice is hump, is based on such standard, to a picture, if the pixel is non-hump zone, is labeled as 0, is otherwise labeled as 1, all data are all marked into completion.The mark picture of one non-humped area.
One S132, creation non-humped area, size is consistent in the extracted area-of-interest of original image, if marking In picture, a pixel is marked as 0, then the corresponding pixel in non-humped area created also sets 0.
S133, for each picture in labeled data, step S132 is carried out, until having traversed all mark figures Piece obtains one and includes the two-part image in humped area and non-humped area.
S134, obtained non-humped area are a logic matrix actually, and non-humped area pixel is 0.It will corrode in S12 Treated picture and non-humped area dot product are 0 that is, in matrix, and corresponding picture pixels then set 0.
Before welding, manually workpiece 2 is stepped up on fixture, clicks start button on monitor 20, X-axis slide rail 9, Y-axis sliding rail 8, Z axis slide rail 13 control laser focusing head 1 and are welded to workpiece 2 presetting region, and high speed camera 12 is right Picture is passed back industrial personal computer 19 in real time and handled, by processing result real-time delivery to motion control by weld seam side timing acquiring picture Unit 16.
Specifically, adjustment mode is divided into two kinds, the first is to inhibit hump by adjusting speed of welding, and second is logical Adjustment defocusing amount is crossed to inhibit hump.
The workflow of the first is: clamping, and starting sliding rail welding, high speed camera 12 is to 2 side timing acquiring of workpiece Picture is passed back in industrial personal computer 19 in real time and is handled according to the algorithmic procedure of the utility model by picture, by the tune of processing result Whole parameter S is compared with standard value, and Real-time Feedback changes X-axis servo motor to motion control unit 16 if being more than threshold value 10 rotation speed, to change the slide block movement speed of X-axis slide rail 9, so as to adjust speed of welding.
Second of workflow is clamping, and starting sliding rail welding, high speed camera 12 is to 2 side timing acquiring figure of workpiece Picture is passed back in industrial personal computer 19 in real time and is handled according to the algorithmic procedure of the utility model by piece, by the adjustment of processing result Parameter S is compared with standard value, and Real-time Feedback produces Z axis servo motor 15 to motion control unit 16 if being more than threshold value Raw certain angular displacement, makes the sliding block in Z axis slide rail 13 move down certain distance, by bracket 14 drive laser focusing head 1 to Under move a certain distance, so that laser spot be made to move down.
The generation of the adjusting parameter S control hump defined using the utility model is illustrated.According to many experiments number According to, when the possibility identified be hump region length-width ratio and area reach certain threshold value when, that is, can be identified as hump generation And the interference of other noises is excluded, adjusting parameter S is defined accordingly, when S reaches the threshold value set in industrial personal computer 19, is just passed Defeated signal is to motion control unit 16, and method of adjustment later is divided into two kinds, and first method is the fortune to X-axis servo motor 10 The progress of scanning frequency degree is reduced with certain gain acceleration, and sealing wire input energy increases, and maintains the opening state at keyhole back, To inhibit metallic solution in the bulk deposition (as shown in Figure 5) at back, that is, the generation of hump is inhibited, as adjusting parameter S It is decreased in the threshold value of setting, the speed of service that motion control unit 16 maintains X-axis servo motor 10 current;Second method is So that Z axis servo motor 15 is generated certain angular displacement, the sliding block in Z axis slide rail 13 is made to move down certain distance, passes through bracket 14 Laser focusing head 1 is driven to move down certain distance, so that laser spot be made to move down, energy moving down inside keyhole can The opening state at keyhole back is maintained to inhibit to inhibit metallic solution in the bulk deposition (as shown in Figure 5) at back The generation of hump, when adjusting parameter S is decreased in the threshold value of setting, motion control unit 16 is maintained in current Z axis slide rail 13 The position of sliding block.
The above is preferred embodiments of the present invention, it is noted that for the ordinary skill of the art For personnel, without departing from the principle of this utility model, several improvements and modifications can also be made, these are improved and profit Decorations are also considered as the protection scope of the utility model.

Claims (4)

1. a kind of on-line measuring device of the Laser Welding hump defect based on image procossing, it is characterised in that: described device includes Three axis slide units, fixture module, control module, laser (17), optical fiber, laser focusing head (1), bracket (14), device bottom plate (11);It is equipped with above three axis slide units clamp bottom board (6), fixture module is installed on clamp bottom board, is pacified above three axis slide units It is also equipped with laser focusing head (1) on the bracket (14) of dress, is connected by optical fiber with laser (17), before high speed camera (12) Install optical filter additional.
2. the on-line measuring device of the Laser Welding hump defect according to claim 1 based on image procossing, feature exist In: the three axis slide units include X-axis slide rail (9), X-axis servo motor (10), Y-axis sliding rail (8), Y-axis servo motor (7), Z Axis sliding rail (13);Specific connection is to be equipped on device bottom plate (11) X-axis slide rail (9), and the end of X-axis slide rail (9) is equipped with X Axis servo motor (10) is equipped with Y-axis sliding rail (8) on the sliding block of X-axis slide rail (9), and the end of Y-axis sliding rail (8) is equipped with Y-axis and watches It takes motor (7), is equipped on the sliding block of Y-axis sliding rail (8) clamp bottom board (6), it is also vertically-mounted on device bottom plate (11) to have Z axis sliding Rail (13), the end of Z axis slide rail (13) are equipped with Z axis servo motor (15), are equipped with bracket on the sliding block of Z axis slide rail (13) (14)。
3. the on-line measuring device of the Laser Welding hump defect according to claim 1 based on image procossing, feature exist In: the fixture module includes clamp bottom board (6), cushion block (5), workpiece (2), fixture jacking block (3), fixture bolt (4);Tool Body connection is that two cushion blocks (5) are installed on clamp bottom board (6), places workpiece (2) on cushion block (5), fixture jacking block (3) compresses work Part (2) is simultaneously locked by fixture bolt (4).
4. the on-line measuring device of the Laser Welding hump defect according to claim 1 based on image procossing, feature exist In: the control module includes X-axis servo motor (10), Y-axis servo motor (7), Z axis servo motor (15), motion control Unit (16), laser (17), cooling system (18), high speed camera (12), industrial personal computer (19), monitor (20);Specifically connect Connecing is, X-axis servo motor (10), Y-axis servo motor (7), Z axis servo motor (15) respectively with motion control unit (16) phase Even, industrial personal computer (19) connects with motion control unit (16), laser (17), cooling system (18), high speed camera (12) respectively It connects, industrial personal computer (19) is also connect with monitor (20).
CN201821450222.3U 2018-09-05 2018-09-05 A kind of on-line measuring device of the Laser Welding hump defect based on image procossing Expired - Fee Related CN209550915U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201821450222.3U CN209550915U (en) 2018-09-05 2018-09-05 A kind of on-line measuring device of the Laser Welding hump defect based on image procossing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201821450222.3U CN209550915U (en) 2018-09-05 2018-09-05 A kind of on-line measuring device of the Laser Welding hump defect based on image procossing

Publications (1)

Publication Number Publication Date
CN209550915U true CN209550915U (en) 2019-10-29

Family

ID=68297665

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201821450222.3U Expired - Fee Related CN209550915U (en) 2018-09-05 2018-09-05 A kind of on-line measuring device of the Laser Welding hump defect based on image procossing

Country Status (1)

Country Link
CN (1) CN209550915U (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109108518A (en) * 2018-09-05 2019-01-01 广东工业大学 A kind of online test method and device of Laser Welding hump defect

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109108518A (en) * 2018-09-05 2019-01-01 广东工业大学 A kind of online test method and device of Laser Welding hump defect

Similar Documents

Publication Publication Date Title
Rout et al. Advances in weld seam tracking techniques for robotic welding: A review
Shen et al. Real-time seam tracking technology of welding robot with visual sensing
Xu et al. Visual sensing technologies in robotic welding: Recent research developments and future interests
US20200269340A1 (en) Active Laser Vision Robust Weld Tracking System and Weld Position Detection Method
Xu et al. Application of sensing technology in intelligent robotic arc welding: A review
CN109108518A (en) A kind of online test method and device of Laser Welding hump defect
US5533146A (en) Weld bead quality determining apparatus
Fan et al. Visual sensing and penetration control in aluminum alloy pulsed GTA welding
CN103231162A (en) Device and method for visual detection of welding quality of robot
Zhang et al. Narrow-seam identification and deviation detection in keyhole deep-penetration TIG welding
Xu et al. Real‐time image capturing and processing of seam and pool during robotic welding process
Mohd Shah et al. Autonomous detection and identification of weld seam path shape position
CN209550915U (en) A kind of on-line measuring device of the Laser Welding hump defect based on image procossing
Wang et al. Groove-center detection in gas metal arc welding using a template-matching method
Yu et al. Vision-based deviation extraction for three-dimensional control in robotic welding with steel sheet
Wu et al. Research on robust laser vision feature extraction method for fillet welds with different reflective materials under uncertain interference
JP2005014027A (en) Weld zone image processing method, welding management system, feedback system for welding machine, and butt line detection system
Lin et al. Intelligent seam tracking of an ultranarrow gap during K-TIG welding: a hybrid CNN and adaptive ROI operation algorithm
Hong et al. Real-time quality monitoring of ultrathin sheets edge welding based on microvision sensing and SOCIFS-SVM
Hong et al. Filter-PCA-based process monitoring and defect identification during climbing helium arc welding process using DE-SVM
Yang et al. Automatic extraction and identification of narrow butt joint based on ANFIS before GMAW
Guo et al. Progress, challenges and trends on vision sensing technologies in automatic/intelligent robotic welding: State-of-the-art review
Zhang et al. A study on seam tracking in robotic GMA welding process
Soares et al. Computer vision system for weld bead geometric analysis
WO2023280679A1 (en) Automatic seam detection for a welding process

Legal Events

Date Code Title Description
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20191029

Termination date: 20200905