CN109604830A - A kind of accurate seam tracking system of active laser vision guide robotic laser welding - Google Patents
A kind of accurate seam tracking system of active laser vision guide robotic laser welding Download PDFInfo
- Publication number
- CN109604830A CN109604830A CN201810825163.1A CN201810825163A CN109604830A CN 109604830 A CN109604830 A CN 109604830A CN 201810825163 A CN201810825163 A CN 201810825163A CN 109604830 A CN109604830 A CN 109604830A
- Authority
- CN
- China
- Prior art keywords
- laser
- robot
- weld
- welding
- image
- 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
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
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/346—Working by laser beam, e.g. welding, cutting or boring in combination with welding or cutting covered by groups B23K5/00 - B23K25/00, e.g. in combination with resistance welding
- B23K26/348—Working by laser beam, e.g. welding, cutting or boring in combination with welding or cutting covered by groups B23K5/00 - B23K25/00, e.g. in combination with resistance welding in combination with arc heating, e.g. TIG [tungsten inert gas], MIG [metal inert gas] or plasma welding
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Plasma & Fusion (AREA)
- Manipulator (AREA)
- Laser Beam Processing (AREA)
Abstract
The invention discloses a kind of active laser vision guide robotic lasers to weld accurate seam tracking system, it include: laser-composite welding robot, active laser vision system, laser light source, image processing system and control system, the active laser vision system and laser light source are set in laser-composite welding robot, described image processing system is set in control system, and the laser-composite welding robot, active laser vision system, positioning cross slide unit, laser light source, image processing system are connect with control system；Electric arc arc light and interference of splashing, which cause seam tracking system to lead to the problem of excessive picture noise finally, when aiming to solve the problem that existing laser-arc hybrid welding in industry influences welding quality, welding precision and efficiency, by welding seam with robot arm end add location control its by be accurately positioned cross slid platform realization combine, to meet quick, accurate, steady weld seam intelligent-tracking.
Description
Technical field
The invention belongs to technical field of laser welding, in particular to a kind of active laser vision guide robotic laser weldering
Connect accurate seam tracking system and its tracking.
Background technique
Laser welding is applied increasingly extensive in the industrial production, and laser welding process limitation becomes increasingly conspicuous, main to show
Are as follows: laser weld energy utilization rate bottom, throat thickness increase lead to that the production cost increases；Laser welding fills the welding of workpiece
It is weak with required precision height, groove bridging ability；Since metal vaporizes strongly, laser welded seam is also easy to produce undercut, recess and stomata and lacks
It falls into, and is difficult to eliminate by experimental parameter adjusting；The cooling velocity of Laser Welding is excessive, and weld seam easily forms brittlement phase, connector
Plasticity and toughness it is lower.Therefore, Laser-Arc Hybrid Welding is in widespread attention, and laser welding and arc welding are combined
To realize that high-quality high-efficiency welding produces.Compared with conventional arc weldering and laser welding, Laser-Arc Hybrid Welding has big welding
The advantages that fusion penetration, high technology stability, high welding efficiency, stronger welded gaps bridging capability and small welding deformation, Neng Gou great
Amplitude improves welding efficiency and welding quality.However, the welding method combines the two kinds of welderings of laser welding and conventional arc welding
Method is connect, the factor for influencing welding process is more, and welding procedure is relatively complicated, the appearance of weld and weld seam of welding point
Quality is closely related, and good appearance of weld could have excellent joint mechanical property, and it is especially heavy to efficiently control appearance of weld
It wants.
Laser-arc hybrid welding in industry robot has industrial robot automation and flexibility degree is high, flexibility and steady
The advantages that qualitative good, movement is quick accurate, automatic welding is important, and there are two types of implementations: one is be based on manual teaching
The control mode of reproduction or off-line programing, another kind is the control mode based on soldering joint automatic tracking technology.Manual teaching playback
Or off-line programing needs weld seam in space tracking once it is determined that cannot change, when there are mismachining tolerances, clamping for welding workpiece
After there are location error, welding when workpiece thermal deformation can occur, these factors may make seam track occur it is a degree of
Variation, actual seam track is deviateed in the robot welding track for causing teaching programming to obtain, to influence welding quality.And
Seam tracking system passes through sensor real-time detection weld bead feature points (discrete point that characteristic point is weld seam actual path)
Position controls robot according to the three-dimensional coordinate of characteristic point and carries out automatically tracking welding, with higher flexibility and wider array of
Application range is able to achieve the automatic welding with high level.Optical visual formula sensor, utilizes CCD CMOS sensitive chip
Directly weld seam is imaged, the information such as shape, the position of weld seam, active optical visual sensor are then obtained from image
It being illuminated using local location of the special secondary light source to target, illuminated position forms high-brightness region in the picture,
Reduce feature extraction difficulty.But it is susceptible to the interference of arc light and splashing, measurement point is smaller at a distance from pad, arc
Light and splashing noise are stronger, these factors, which all have vision system, to be interfered, and increase the difficulty of seam tracking system.Cause
This, improves vision system robustness, effectively extraction weld bead feature points, resists a degree of arc light splashing and interference of splashing, figure
As noise, to improve the measuring precision, frequency and anti-interference ability, becomes optimization, improves seam tracking system urgently
Problem to be solved.
Secondly, when be carried out in such a way that robot is combined with laser-arc hybrid welding in industry head seam tracking system design,
When realizing with operation, on condition that robot TCP point is accurately demarcated along weld bead feature points, if operator generates artificial dredge
Leakage causes the process to generate deviation, it will subsequent weld joint tracking precision to be influenced, so as to cause laser-arc hybrid welding in industry matter
Amount decline；Meanwhile the repetitive positioning accuracy of robot is generally between ± 0.03mm~± 0.06mm, however due to robot
The reasons such as the deviation of mechanical part itself, the resolution of each control unit, the position coordinates of robot TCP point might not ten
Divide accurately, laser facula carries out weld job under the guidance of this TCP point, it is also possible to lead to the decline of welding quality.
Summary of the invention
Goal of the invention: in order to overcome the above deficiency, the object of the present invention is to provide a kind of active laser vision guide machines
The accurate seam tracking system of people's laser welding, structure is simple, and design rationally, is readily produced, and intelligence degree is high, system is steady
Strong property is strong, reduces manual labor amount, improves work efficiency, it is ensured that welding quality.
Technical solution: to achieve the goals above, the present invention provides a kind of active laser vision guide robotic lasers
Weld accurate seam tracking system, comprising: laser-composite welding robot, active laser vision system, laser light source, image
Processing system and control system, the active laser vision system and laser light source are set to laser-composite welding robot
On, described image processing system be set to control system in, the laser-composite welding robot, active laser vision system,
Laser light source, image processing system are connect with control system；
In the laser-composite welding robot be equipped with industrial robot, laser compound welding tip, wire feeder and
For pinpoint positioning cross slide unit and the source of welding current, the positioning cross slide unit is set to the leading portion of industrial robot, and
It connect with slide unit driving motor, and the laser compound welding tip is installed on positioning cross slide unit, and the wire feeder is set to
The side of laser compound welding tip, the source of welding current to laser-composite welding robot provide welding current, arc voltage,
The Parameters Integrated Survey Methods such as wire feed rate are adjusted.
Heretofore described positioning cross slide unit is equipped with horizontal slide unit and longitudinal slide unit, the horizontal slide unit and longitudinal direction
Slide unit uses staggered form design, and bottom plate is equipped in the horizontal slide unit and longitudinal slide unit, and the two sides of the bottom plate are equipped with straight
Line guide rail, top are equipped with driving mechanism, and the linear guide is equipped with sliding block, and the driving mechanism is connect with control system.
Bearing block and screw rod are equipped in heretofore described driving mechanism, one end of the bearing block is equipped with servo motor,
And be located in front of servo motor on the bearing block and be additionally provided with feed screw nut's support, the screw rod is installed on bearing block simultaneously
It is fixed by feed screw nut's support, and the screw rod is connect with servo motor.
Heretofore described industrial robot uses six-shaft industrial robot, is provided with pedestal, robotic arm and driving machine
Structure, is equipped with lower arm and forearm in the mechanical arm, and the pedestal is equipped with the mounting base for installing lower arm, under the lower arm
Portion and mounting base use movable connection, and the forearm is installed on the top of lower arm, and the two uses movable connection, described
Positioning cross slide unit is set to the forearm of industrial robot.
Laser vision sensor and industrial camera are equipped in heretofore described active laser vision system.
Vision controller, robot controller, cross slid platform controller and control are equipped in heretofore described control system
Device processed, the vision controller are connect with active laser vision system, and the robot controller is connect with industrial robot,
The cross slid platform controller is connect with positioning cross slide unit；
The first central processing unit, the first internal storage unit, visual sensor interface are equipped in the vision controller
And first communication interface, the both ends of the visual sensor interface are deposited with inside active laser vision system and first respectively
Storage unit connection, first internal storage unit, visual sensor interface and the first communication interface with the first centre
Manage unit connection；
It is connect in the robot controller equipped with the second central processing unit, the second internal storage unit, the second communication
Mouth, driver, motion control card, input/output interface, the input/output interface are connect with the second internal storage unit,
The output end of the driver is connect with the input terminal of the motor of driving mechanical arm, and the output end and mechanical arm of the motor connect
It connects, the motion control is stuck in the connection of the encoder in mechanical arm, and second internal storage unit, drives the second communication interface
Dynamic device, motion control card, robot input/output interface are connect with the second central processing unit, and the robot controls
System is connect by the second communication interface with the first communication interface in vision control system；
Third communication interface, third central processing unit, third storage inside list are equipped in the cross slid platform controller
In member, servo-driver, sliding block control module and slide unit input/output interface, the third communication interface and vision controller
The connection of the first communication interface, the output end of the servo-driver connect with slide unit driving motor, the sliding block control module
It is connect with the input terminal of the encoder of positioning cross slide unit, the in the slide unit input/output interface and robot controller
Two communication interfaces are bi-directionally connected, the third communication interface, third internal storage unit, servo-driver, sliding block control module
It is connect with third central processing unit with slide unit input/output interface；
The vision controller, robot controller, cross slid platform controller are connect with controller.
Heretofore described active laser vision guide robotic laser welds the work side of accurate seam tracking system
Method, specific working method are as follows:
1): first by laser vision sensor by identifying project structured light to face of weld in the course of work
The relevant laser stripe band of weld profile information；
2): and then industrial camera obtains the image of the laser stripe band generated in previous step, and transfers data to figure
As processing system, characteristics of weld seam information is extracted by the data extraction module of image processing system, from the center of laser stripe band
After line detects position while welding, it may be assumed that extracted without the detection of deformation laser stripe baseline and weld bead feature points；
3): and then intelligent-tracking is carried out to weld seam again, specific welding is controlled according to the result of tracking, is being welded
It can find that industrial robot path is accurate or inaccurate two kinds of situations during seam tracking；
4): when confirmation industrial robot path is accurate during previous step tracking, specific working method is such as
Under:
A), robot controller issues HOME signals, and positioning cross slide unit is restored to intermediate initial position；
B), cross slid platform controller issues HOME signals in place；
C), industrial robot reaches program initial bit, and then industrial robot starts initial search point；
D), the starting point of robot controller searching machine people tool ends end TCPTCP point；
E), register queue is then established, laser vision sensor position sequence corresponding with weld bead feature points is recorded；
F), then judge whether robot tool end TCP is located at initial weld bead feature points, if it is not, so it will
Return step b) is to the starting point for c) searching robot tool end TCP again；If it is then robot tool end TCP is located at weldering
Path initial position signal is stitched, then robot controller starts to weld operational order；
G), then robot controller starts weld joint tracking operational order；
H), continue to establish register and line up, record laser vision sensor position sequence corresponding with weld bead feature points；
I), robot tool end TCP carries out weld bead feature points tracking operation；
J), whether robot tool end TCP is located at last bit weld bead feature points, if it is not, so it wants return step f)
Line up to establish to register g) is re-started；If it is then robot tool end TCP is located at path of welding most end end position
Signal；
K), robot controller terminates to weld operational order；
5): in above-mentioned steps 3) it can find that industrial robot path is inaccurate during weld joint tracking, there are deviations
When, need the deviation to weld seam feature point trajectory to compensate, so that robot tool end TCP is special along more accurate weld seam
The path operation generated of sign point, while positioning cross slide unit also being needed, to being accurately positioned, to realize three-dimensional weldering to Y-direction and Z
Seam tracking, until completing laser welding operation.
Heretofore described active laser vision guide robotic laser welds the work side of accurate seam tracking system
Method, wherein the data extraction module of step 3) image processing system extracts characteristics of weld seam information, from the center line of laser stripe band
Detect that the specific method of position while welding is as follows:
Described image processing system is to active laser vision weld joint image procossing and Detecting Welding Seam algorithm, nothing
Need additional narrow-band filter；Specific working method includes two parts: (1) without deformation laser stripe baseline detection；(2) weld seam
Feature point extraction；
1) without the detection of deformation laser stripe baseline, specific step is as follows:
Step 1: image preprocessing
A, mean filter processing is carried out to laser stripe image acquired in industrial camera；The mean filter method is as follows
Shown in formula:
Wherein, maximum value it is expected for laser stripe width, be the image intensity of the i-th row jth column pixel, be after filtering i-th
The end value of row jth column.
B, HSV color space will be converted to from rgb color space through processing image again, i.e., be accurately extracted from image again
Laser blue light color sets the threshold value in tri- channels HSV, and carries out mask process to image, and the setting of three kinds of threshold values is so that low
The low contrast laser stripe that quality laser generates can obtain subsequent processing；
M=M1∩M2∩M3
Wherein, M1, M2, M3, respectively H, S, the exposure mask threshold value of V triple channel, i, j are respectively pixel position No., for most
Obtained exposure mask intersection area eventually；
C, former RGB image is converted to gray level image, method again through gray proces are as follows:
Grey=0.299*R+0.587*G+0.114*B
By the R in the RGB (R, G, B) of script, G, B are replaced with Grey, formed new color RGB (Grey, Grey,
Grey), the single channel grayscale image that can form replacement RGB (R, G, B), is applied to the single channel gray scale through exposure mask intersection
Figure；
D, median filtering then is carried out to image again, removes the spiced salt, speckle noise, it may be assumed that median filtering contains surprise with one
The sliding window of several points sorts the pixel in neighborhood by gray level, and taking median is output pixel；
Subsequent further image processing process is used for once the resulting image of processing by above-mentioned steps；
Step 2: laser stripe profile detection
A, the method detected by laser peak extracts the contour edge pixel of characterization laser stripe band, it may be assumed that neck swashs
Striations is vertical, and the intensity threshold that the horizontal every row pixel of setting is accepted or rejected obtains intensity peak point, forms laser stripe band basis；
Noise filtering is carried out to the image pixel intensities peak point that horizontal direction is formed again；Acquired image pixel intensities peak point is fitted,
Return obtains laser stripe baseline position；
B, weld bead feature points are extracted
By taking the baseline that vertical laser stripe band is obtained as an example, it is known that on baseline, the deformed region along baseline can be considered
Position containing weld bead feature points: the step of extracting these weld bead feature points from laser stripe band image can be summarized as: one,
Determine vertical direction ROI；Two, the mark and selection in crosspoint；Three, the ROI of horizontal direction is determined；Four, the horizontal peak of weld seam is detected
Value point；
Around the laser baseline previously obtained, the image through filtering is cut according to following method, it may be determined that vertical
With horizontal direction ROI；
Vertical ROI is obtained by following formula,
ROI (i, c)=I (i, j)
Wherein
Wherein, LW is desired laser stripe bandwidth, and N is the line number of image.I (i, j) is the figure of the i-th row jth column
As intensity, ROI (i, c) is the area-of-interest of image, and p is by the column mark of the laser lines detected in original image；
Therefrom, the upper end characteristic point and lower bottom end characteristic point of extracted laser line segment deformed region are obtained；
Horizontal ROI is obtained by following formula,
ROI (c, j)=I ' (i, j)
Wherein, Ytop≤i≤Ybottom；min(Xtop,Xbottom)≤j≤M
In formula, Ytop, Xtop, Ybottom, XbottomUpper end point and lower bottom are concentrated for the joint in image I (i, j)
The y-axis of endpoint and the coordinate value of x-axis, M are the column number of image I (i, j)；
Therefrom, it can get the weld seam horizontal peak characteristic point of extracted laser line segment deformed region, obtain the horizontal peak of weld seam
The method of value tag point is as follows:
Step 1: removal noise spot extracts the profile point in horizontal ROI on laser band, that is, extracted laser stripe belt wheel
The characteristic point of wide deformed region；
Step 2: being divided into top and twoth area of lower part for the profile of laser stripe band in ROI, according to following constraint condition, divides
Part not except the Internal periphery of top and the bottom region supplements the discontinuous point in laser stripe profile deformed area continuous；
-LW≤Pci≤LW
Wherein, LW is the width of desired laser stripe band, PciBy supplement discontinuous point column mark；
Step 3: profile point on top and the bottom laser stripe band in above-mentioned complete ROI is formed with the discontinuous point supplemented
Point set carries out linear fit respectively, and resulting two straight-line intersections can be identified as weld seam characteristic point peak load.
Heretofore described active laser vision guide robotic laser welds the work side of accurate seam tracking system
Method there are when deviation, needs wherein can find that industrial robot path is inaccurate during weld joint tracking when in step 5)
The deviation of weld seam feature point trajectory is compensated, specific tracking is as follows:
1), robot controller issues HOME signals, and positioning cross slide unit is restored to intermediate initial position；
2), cross slid platform controller issues HOME signals in place；
3), industrial robot reaches program initial bit, and then industrial robot starts initial search point；
4), the starting point of robot controller searching machine people tool ends end TCP；
5) register queue, is then established, laser vision sensor position sequence corresponding with weld bead feature points is recorded；
6), then judge whether robot tool end TCP is located at initial weld bead feature points, if it is not, so it will
Return step 4) to 5) searching robot tool end TCP starting point again；If it is then robot tool end TCP is located at weld seam
Path initial position signal；
7), robot controller judges whether industrial robot carries out empty run and run；
8) industrial robot as the result is shown, obtained in step 7) runs operation if not in sky, then robot control
Device processed will order it to continue to establish register and line up, and record laser vision sensor position sequence corresponding with weld bead feature points；
9), record corresponds to TCP point Y-direction, the Z-direction correction value of the position sequence；
10), robot tool end TCP is located at path of welding least significant end position signal；
11), robot controller terminates to weld operational order；
12) industrial robot as the result is shown, obtained in step 7) runs operation if it is in sky, then robot control
Device processed will order it to establish register queue and record visual sensor position sequence corresponding with weld bead feature points；
13), record corresponds to TCP point Y-direction, the Z-direction correction value of the position sequence；
14), robot controller judges whether industrial robot completes W empty race, if the result display of monitoring is not complete
At then it will repeat step a) to h)；
15) if the industrial robot as the result is shown, monitored in previous step completes W empty race, W will be calculated
Secondary empty race gained weld bead feature points optimal estimation and corresponding laser vision sensor position sequence and Y-direction, Z-direction correction value；
16), then robot controller order industrial robot starts welding operation；
17) after, industrial robot receives welding operational order, start welding operation；
18), robot controller starts weld joint tracking operational order；
19), robot tool end TCP carries out tracking operation referring to optimal estimation weld bead feature points；
20), then whether robot controller confirmation robot tool end TCP is located at last bit weld bead feature points, if not
It is, then it wants return step 19) line up to establish to 20) re-starting the first register；If it is then robot tool
End TCP is located at path of welding least significant end position signal；
20), robot controller terminates to weld operational order.
Above-mentioned technical proposal can be seen that the invention has the following beneficial effects:
1, a kind of active laser vision guide robotic laser of the present invention welds accurate seam tracking system, purport
When solving existing laser-arc hybrid welding in industry, electric arc arc light and interference of splashing cause seam tracking system to generate excessive image
Noise finally influences the problem of welding quality, welding precision and efficiency, solves artificial calibration and robot itself component, control
Robot TCP point caused by the deviation that algorithm processed generates is to weld seam feature point tracking fault problem, by welding seam and machine
Device people's mechanical arm tail end adds location control, and it is combined by being accurately positioned cross slid platform realization, realizes that robot TCP point can
It advances by ground along weld bead feature points, to meet quick, accurate, steady weld seam intelligent-tracking.
2, heretofore described without the detection of deformation laser stripe baseline and characteristics of weld seam point extracting method, effectively extract
Weld bead feature points resist a degree of arc light splashing and splash interference, picture noise, to improve the measuring precision, frequency
Rate and anti-interference ability become optimization, improve seam tracking system urgent problem to be solved.
3, right there are when deviation when can find that industrial robot path is inaccurate during weld joint tracking in the present invention
The realization for the mode that the deviation of the characteristics of weld seam locus of points compensates allows it to realize accurate weld joint tracking, it is ensured that machine is artificial
Tool end TCP advances along reliable weld bead feature points, dynamically accurately compensates to deviation, further improves its weldering
The accuracy for stitching tracking improves the quality of its welding.
4, total in image processing process in the present invention, image preprocessing uses mean filter, and laser blue light is adjacent to periphery
Domain pixel expanding so that the high-intensitive saturated pixel at laser stripe center is more smooth, while inhibiting the height of image background
Intensity noise.
Detailed description of the invention
Fig. 1 is laser of the present invention-composite welding robot structural schematic diagram；
Fig. 2 is spot welds feature extraction schematic diagram in the present invention；
Fig. 3 is the flow chart of weld beam shape and weld bead feature points detection, extraction process in the present invention；
Fig. 4 is the main control structure of robotic laser composite welding seam tracking system of active laser vision guidance；
Fig. 5 is the variance analysis schematic diagram that laser vision sensor deviates seam track during robot teaching；
The weld seam that Fig. 6 causes the vision system deviateed to extract, estimate by robot tool end TCP due to artificial origin
Feature point trajectory variance analysis；
Fig. 7 is relative pose network diagram in the present invention；
Fig. 8 is control strategy schematic diagram；
Fig. 9 is register queue in the present invention；
Figure 10 is workflow schematic diagram of the invention；
Figure 11 is the structural schematic diagram of positioning cross slide unit in the present invention.
Specific embodiment
In the following with reference to the drawings and specific embodiments, the present invention is furture elucidated.
Embodiment
A kind of active laser vision guide robotic laser as shown in the figure welds accurate seam tracking system, comprising: swashs
Light-composite welding robot 1, active laser vision system 2, laser light source 3, image processing system 4 and control system 5, it is described
Active laser vision system 2 and laser light source 2 are set in laser-composite welding robot 1, and described image processing system 4 is set
In control system 2, the laser-composite welding robot 1, active laser vision system 2, laser light source, image procossing system
System 2 is connect with control system 4；
Industrial robot 11, laser compound welding tip 12, wire feeder are equipped in the laser-composite welding robot 1
13 and be used for pinpoint positioning cross slide unit 14 and the source of welding current, the positioning cross slide unit 14 be set to industrial machine
The leading portion of people 11, and it connect with slide unit driving motor, the laser compound welding tip 12 is installed on positioning cross slide unit 14
On, the wire feeder 13 is set to the side of laser compound welding tip 12, and the source of welding current is to laser-composite welding machine
People 1 provides the Parameters Integrated Survey Methods such as welding current, arc voltage, wire feed rate and adjusts.
Positioning cross slide unit described in the present embodiment 14 is equipped with horizontal slide unit 141 and longitudinal slide unit 142, the transverse direction
Slide unit 141 and longitudinal slide unit 142 use staggered form design, and are equipped with bottom in the horizontal slide unit 141 and longitudinal slide unit 142
Plate 143, the two sides of the bottom plate 143 are equipped with linear guide 144, and top is equipped with driving mechanism 145, in the linear guide 144
Equipped with sliding block 146, the driving mechanism 145 is connect with control system 5.
Bearing block 1451 and screw rod 1452 are equipped in driving mechanism 145 described in the present embodiment, the bearing block 1451
One end is equipped with servo motor 1453, and the front on the bearing block 1451 positioned at servo motor 1453 is additionally provided with feed screw nut
Support 1454, the screw rod 1452 is installed on bearing block 1451 and is fixed by feed screw nut's support 1454, and the screw rod
1452 connect with servo motor 1453.
Industrial robot 11 described in the present embodiment uses six-shaft industrial robot, is provided with pedestal 111, robotic arm
With driving mechanism 112, lower arm 113 and forearm 114 are equipped in the mechanical arm, the pedestal 111 is equipped with for installing lower arm
113 mounting base 115,113 lower part of lower arm and mounting base 115 use movable connection, and the forearm 114 is installed on down
The top of arm 113, and the two uses movable connection, the positioning cross slide unit 14 is set to the forearm of industrial robot 11
114。
Laser vision sensor and industrial camera are equipped in active laser vision system described in the present embodiment 2.
Vision controller, robot controller, cross slid platform controller are equipped in control system 4 described in the present embodiment
And controller, the vision controller are connect with active laser vision system 2, the robot controller and industrial robot
11 connections, the cross slid platform controller are connect with positioning cross slide unit 14；
The first central processing unit, the first internal storage unit, visual sensor interface are equipped in the vision controller
And first communication interface, the both ends of the visual sensor interface are deposited with inside active laser vision system 2 and first respectively
Storage unit connection, first internal storage unit, visual sensor interface and the first communication interface with the first centre
Manage unit connection；
It is connect in the robot controller equipped with the second central processing unit, the second internal storage unit, the second communication
Mouth, driver, motion control card, input/output interface, the input/output interface are connect with the second internal storage unit,
The output end of the driver is connect with the input terminal of the motor of driving mechanical arm, and the output end and mechanical arm of the motor connect
It connects, the motion control is stuck in the connection of the encoder in mechanical arm, and second internal storage unit, drives the second communication interface
Dynamic device, motion control card, robot input/output interface are connect with the second central processing unit, and the robot controls
System is connect by the second communication interface with the first communication interface in vision control system；
Third communication interface, third central processing unit, third storage inside list are equipped in the cross slid platform controller
In member, servo-driver, sliding block control module and slide unit input/output interface, the third communication interface and vision controller
The connection of the first communication interface, the output end of the servo-driver connect with slide unit driving motor, the sliding block control module
It is connect with the input terminal of the encoder of positioning cross slide unit 14, in the slide unit input/output interface and robot controller
Second communication interface is bi-directionally connected, and the third communication interface, third internal storage unit, servo-driver, sliding block control mould
Block and slide unit input/output interface are connect with third central processing unit；
The vision controller, robot controller, cross slid platform controller are connect with controller.
Embodiment 2
A kind of active laser vision guide robotic laser as shown in the figure welds accurate seam tracking system, comprising: swashs
Light-composite welding robot 1, active laser vision system 2, laser light source 3, image processing system 4 and control system 5, it is described
Active laser vision system 2 and laser light source 2 are set in laser-composite welding robot 1, and described image processing system 4 is set
In control system 2, the laser-composite welding robot 1, active laser vision system 2, laser light source, image procossing system
System 2 is connect with control system 4；
Industrial robot 11, laser compound welding tip 12, wire feeder are equipped in the laser-composite welding robot 1
13 and be used for pinpoint positioning cross slide unit 14 and the source of welding current, the positioning cross slide unit 14 be set to industrial machine
The leading portion of people 11, and it connect with slide unit driving motor, the laser compound welding tip 12 is installed on positioning cross slide unit 14
On, the wire feeder 13 is set to the side of laser compound welding tip 12, and the source of welding current is to laser-composite welding machine
People 1 provides the Parameters Integrated Survey Methods such as welding current, arc voltage, wire feed rate and adjusts.
Positioning cross slide unit described in the present embodiment 14 is equipped with horizontal slide unit 141 and longitudinal slide unit 142, the transverse direction
Slide unit 141 and longitudinal slide unit 142 use staggered form design, and are equipped with bottom in the horizontal slide unit 141 and longitudinal slide unit 142
Plate 143, the two sides of the bottom plate 143 are equipped with linear guide 144, and top is equipped with driving mechanism 145, in the linear guide 144
Equipped with sliding block 146, the driving mechanism 145 is connect with control system 5.
Bearing block 1451 and screw rod 1452 are equipped in driving mechanism 145 described in the present embodiment, the bearing block 1451
One end is equipped with servo motor 1453, and the front on the bearing block 1451 positioned at servo motor 1453 is additionally provided with feed screw nut
Support 1454, the screw rod 1452 is installed on bearing block 1451 and is fixed by feed screw nut's support 1454, and the screw rod
1452 connect with servo motor 1453.
Industrial robot 11 described in the present embodiment uses six-shaft industrial robot, is provided with pedestal 111, robotic arm
With driving mechanism 112, lower arm 113 and forearm 114 are equipped in the mechanical arm, the pedestal 111 is equipped with for installing lower arm
113 mounting base 115,113 lower part of lower arm and mounting base 115 use movable connection, and the forearm 114 is installed on down
The top of arm 113, and the two uses movable connection, the positioning cross slide unit 14 is set to the forearm of industrial robot 11
114。
Laser vision sensor and industrial camera are equipped in active laser vision system described in the present embodiment 2.
Vision controller, robot controller, cross slid platform controller are equipped in control system 4 described in the present embodiment
And controller, the vision controller are connect with active laser vision system 2, the robot controller and industrial robot
11 connections, the cross slid platform controller are connect with positioning cross slide unit 14；
The first central processing unit, the first internal storage unit, visual sensor interface are equipped in the vision controller
And first communication interface, the both ends of the visual sensor interface are deposited with inside active laser vision system 2 and first respectively
Storage unit connection, first internal storage unit, visual sensor interface and the first communication interface with the first centre
Manage unit connection；
It is connect in the robot controller equipped with the second central processing unit, the second internal storage unit, the second communication
Mouth, driver, motion control card, input/output interface, the input/output interface are connect with the second internal storage unit,
The output end of the driver is connect with the input terminal of the motor of driving mechanical arm, and the output end and mechanical arm of the motor connect
It connects, the motion control is stuck in the connection of the encoder in mechanical arm, and second internal storage unit, drives the second communication interface
Dynamic device, motion control card, robot input/output interface are connect with the second central processing unit, and the robot controls
System is connect by the second communication interface with the first communication interface in vision control system；
Third communication interface, third central processing unit, third storage inside list are equipped in the cross slid platform controller
In member, servo-driver, sliding block control module and slide unit input/output interface, the third communication interface and vision controller
The connection of the first communication interface, the output end of the servo-driver connect with slide unit driving motor, the sliding block control module
It is connect with the input terminal of the encoder of positioning cross slide unit 14, in the slide unit input/output interface and robot controller
Second communication interface is bi-directionally connected, and the third communication interface, third internal storage unit, servo-driver, sliding block control mould
Block and slide unit input/output interface are connect with third central processing unit；
The vision controller, robot controller, cross slid platform controller are connect with controller.
Active laser vision guide robotic laser described in the present embodiment welds the work of accurate seam tracking system
Method, specific working method are as follows:
1): first by laser vision sensor by identifying project structured light to face of weld in the course of work
The relevant laser stripe band 6 of weld profile information；
2): and then industrial camera obtains the image of the laser stripe band 6 generated in previous step, and transfers data to
Image processing system 4 extracts characteristics of weld seam information by the data extraction module of image processing system 4, from laser stripe band 6
Center line detecting to position while welding after, it may be assumed that carry out without deformation laser stripe baseline detection and weld bead feature points extract；
3): and then intelligent-tracking is carried out to weld seam again, specific welding is controlled according to the result of tracking, is being welded
It can find that 11 path of industrial robot is accurate or inaccurate two kinds of situations during seam tracking；
4): when confirmation 11 path of industrial robot is accurate during previous step tracking, specific working method is such as
Under:
A), robot controller issues HOME signals, and positioning cross slide unit 14 is restored to intermediate initial position；
B), cross slid platform controller issues HOME signals in place；
C), industrial robot 11 reaches program initial bit, and then industrial robot 11 starts initial search point；
D), the starting point of robot controller searching machine people tool ends end TCPTCP point 7；
E), register queue is then established, laser vision sensor position sequence corresponding with weld bead feature points is recorded；
F), then judge whether robot tool end TCP7 is located at initial weld bead feature points, if it is not, so it will
Return step b to c is wanted to search the starting point of robot tool end TCP7 again；If it is then robot tool end TCP7 is located at
Weld seam path initial position signal, then robot controller starts to weld operational order；
G), then robot controller starts weld joint tracking operational order；
H), continue to establish register and line up, record laser vision sensor position sequence corresponding with weld bead feature points；
I), robot tool end TCP7 carries out weld bead feature points tracking operation；
J), whether robot tool end TCP7 is located at last bit weld bead feature points, if it is not, so it wants return step f
Register is re-started to g to line up to establish；If it is then robot tool end TCP7 is located at path of welding most end end position
Signal；
K), robot controller terminates to weld operational order；
5): can find that 11 path of industrial robot is inaccurate during above-mentioned steps 3 are in weld joint tracking, there are deviations
When, need the deviation to weld seam feature point trajectory to compensate, so that robot tool end TCP7 is special along more accurate weld seam
The a path generated operation of sign point, at the same also need positioning cross slide unit 14 to Y to and Z-direction be accurately positioned, realize three-dimensional
Weld joint tracking, until completing laser welding operation.
The robotic laser of active laser vision guide described in the present embodiment welds the work side of accurate seam tracking system
Method, wherein the data extraction module of step 3 image processing system 4 extracts characteristics of weld seam information, from the center line of laser stripe band
Detect that the specific method of position while welding is as follows:
Described image processing system 4 is to active laser vision weld joint image procossing and Detecting Welding Seam algorithm, nothing
Need additional narrow-band filter；Specific working method includes two parts: (1) without deformation laser stripe baseline detection；(2) weld seam
Feature point extraction；
1) without the detection of deformation laser stripe baseline, specific step is as follows:
Step 1: image preprocessing
A, mean filter processing is carried out to laser stripe image acquired in industrial camera；The mean filter method is as follows
Shown in formula:
Wherein, maximum value it is expected for laser stripe width, be the image intensity of the i-th row jth column pixel, be after filtering i-th
The end value of row jth column.
B, HSV color space will be converted to from rgb color space through processing image again, i.e., be accurately extracted from image again
Laser blue light color sets the threshold value in tri- channels HSV, and carries out mask process to image, and the setting of three kinds of threshold values is so that low
The low contrast laser stripe that quality laser generates can obtain subsequent processing；
M=M1∩M2∩M3
Wherein, M1, M2, M3, respectively H, S, the exposure mask threshold value of V triple channel, i, j are respectively pixel position No., for most
Obtained exposure mask intersection area eventually；
C, former RGB image is converted to gray level image, method again through gray proces are as follows:
Grey=0.299*R+0.587*G+0.114*B
By the R in the RGB (R, G, B) of script, G, B are replaced with Grey, formed new color RGB (Grey, Grey,
Grey), the single channel grayscale image that can form replacement RGB (R, G, B), is applied to the single channel gray scale through exposure mask intersection
Figure；
D, median filtering then is carried out to image again, removes the spiced salt, speckle noise, it may be assumed that median filtering contains surprise with one
The sliding window of several points sorts the pixel in neighborhood by gray level, and taking median is output pixel；
Subsequent further image processing process is used for once the resulting image of processing by above-mentioned steps；
Step 2: laser stripe profile detection
A, the method detected by laser peak extracts the contour edge pixel of characterization laser stripe band, it may be assumed that neck swashs
Striations is vertical, and the intensity threshold that the horizontal every row pixel of setting is accepted or rejected obtains intensity peak point, forms 6 base of laser stripe band
Plinth；Noise filtering is carried out to the image pixel intensities peak point that horizontal direction is formed again；Acquired image pixel intensities peak point is intended
It closes, return obtains laser stripe baseline position；
B, weld bead feature points are extracted
By taking the baseline that vertical laser stripe band 6 is obtained as an example, it is known that on baseline, the deformed region along baseline is visual
It can be summarized as the position containing weld bead feature points: the step of extracting these weld bead feature points from 6 image of laser stripe band:
One, vertical direction ROI is determined；Two, the mark and selection in crosspoint；Three, the ROI of horizontal direction is determined；Four, weld seam water is detected
Flat peak point；
Around the laser baseline previously obtained, the image through filtering is cut according to following method, it may be determined that vertical
With horizontal direction ROI；
Vertical ROI is obtained by following formula,
ROI (i, c)=I (i, j)
Wherein
Wherein, LW is desired 6 width of laser stripe band, and N is the line number of image.I (i, j) is the i-th row jth column
Image intensity, ROI (i, c) are the area-of-interest of image, and p is by the column mark of the laser lines detected in original image；
Therefrom, the upper end characteristic point and lower bottom end characteristic point of extracted laser line segment deformed region are obtained；
Horizontal ROI is obtained by following formula,
ROI (c, j)=I ' (i, j)
Wherein, Ytop≤i≤Ybottom；min(Xtop,Xbottom)≤j≤M
In formula, Ytop, Xtop, Ybottom, XbottomUpper end point and lower bottom are concentrated for the joint in image I (i, j)
The y-axis of endpoint and the coordinate value of x-axis, M are the column number of image I (i, j)；
Therefrom, it can get the weld seam horizontal peak characteristic point of extracted laser line segment deformed region, obtain the horizontal peak of weld seam
The method of value tag point is as follows:
Step 1: removal noise spot extracts the profile point in horizontal ROI on laser band, that is, extracted laser stripe belt wheel
The characteristic point of wide deformed region；
Step 2: being divided into top and twoth area of lower part for the profile of laser stripe band 6 in ROI, according to following constraint condition,
Part except the Internal periphery of top and the bottom region respectively supplements the discontinuous point in laser stripe profile deformed area continuous；
-LW≤Pci≤LW
Wherein, LW is the width of desired laser stripe band, PciBy supplement discontinuous point column mark；
Step 3: profile point on top and the bottom laser stripe band 6 in above-mentioned complete ROI is formed with the discontinuous point supplemented
Point set carry out linear fit respectively, resulting two straight-line intersections can be identified as weld seam characteristic point peak load.
Active laser vision guide robotic laser described in the present embodiment welds the work of accurate seam tracking system
Method in step 5, can find that 11 path of industrial robot is inaccurate during weld joint tracking, there are when deviation, need
The deviation of weld seam feature point trajectory is compensated, specific tracking is as follows:
1), robot controller issues HOME signals, and positioning cross slide unit 14 is restored to intermediate initial position；
2), cross slid platform controller issues HOME signals in place；
3), industrial robot 11 reaches program initial bit, and then industrial robot 11 starts initial search point；
4), the starting point of robot controller searching machine people tool ends end TCP7；
5) register queue, is then established, laser vision sensor position sequence corresponding with weld bead feature points is recorded；
6), then judge whether robot tool end TCP7 is located at initial weld bead feature points, if it is not, so it will
Return step 4 to 5 is wanted to search robot tool end TCP7 starting point again；If it is then robot tool end TCP7 is located at weldering
Stitch path initial position signal；
7), robot controller judges whether industrial robot 11 carries out empty run and run；
8) industrial robot as the result is shown 11, obtained in step 7 runs operation if not in sky, then robot
Controller will order it to continue to establish register to line up one, record laser vision sensor corresponding with weld bead feature points position
Sequence；
9), record corresponds to TCP point Y-direction, the Z-direction correction value of the position sequence；
10), robot tool end TCP is located at path of welding least significant end position signal；
11), robot controller terminates to weld operational order；
12) industrial robot as the result is shown 11, obtained in step 7 runs operation if it is in sky, then robot control
Device processed will order it to establish register queue two and record visual sensor position sequence corresponding with weld bead feature points；
13), record corresponds to TCP point Y-direction, the Z-direction correction value of the position sequence；
14), robot controller judges whether industrial robot 11 completes W empty race, if the result display of monitoring is not
It completes, then it will repeat step a to h；
15) if the industrial robot as the result is shown 11, monitored in previous step completes W empty race, will calculate
W empty race gained weld bead feature points optimal estimation and corresponding laser vision sensor position sequence and Y-direction, Z-direction correction
Value；
16), then robot controller order industrial robot 11 starts welding operation；
17) after, industrial robot 11 receives welding operational order, start welding operation；
18), robot controller starts weld joint tracking operational order；
19), robot tool end TCP carries out tracking operation referring to optimal estimation weld bead feature points；
20), then whether robot controller confirmation robot tool end TCP is located at last bit weld bead feature points, if not
It is to line up to establish then it wants return step 19 to 20 to re-start the first register；If it is then robot tool end
TCP is located at path of welding least significant end position signal；
21), robot controller terminates to weld operational order.
During operator's artificial teaching, although ensuring that robot tool end TCP point is in weld seam as far as possible always
Center line, it can be difficult to avoiding the occurrence of the case where visual sensor deviates seam track during robot teaching.Such as Fig. 5
It is shown:
In Fig. 5, during artificial teaching, the small size deviation of travel path generation of visual sensor, and robot tool
TCP point is held more strictly to advance along axis of a weld, therefore, the weld bead feature points rail for causing vision system to extract, estimating
There is deviation in mark, it will influences tracking accuracy and accuracy.
In Fig. 6, during artificial teaching, robot tool end TCP7 may cause to deviate weld seam due to artificial origin
Path, this also leads to, and vision system extracts, deviation occurs in the characteristics of weld seam locus of points estimated, on this basis it is subsequent into
Robot tool end TCP7 will likely be made to deviate weld seam path therewith when row weld joint tracking, welding is caused to fail.
To solve the above-mentioned problems, the deviation of the characteristics of weld seam locus of points caused by above-mentioned two situations need to be compensated,
So that robot tool end TCP point efficiently accomplishes laser welding along the path operation generated of more accurate weld bead feature points
Operation.Although robot has the characteristics that repetitive positioning accuracy is high, it makes tool ends end TCP point in high-speed motion situation
Accurately reach the ability of target weld bead feature points spatial position, existing defects down.Therefore, it is also desirable to increase in robot end
The accurate-positioning control device of Y-direction and Z-direction as shown in Figure 4, with ensure can quickly, accurately carry out three-dimensional weld joint tracking.
In order to be compensated to above-mentioned deviation, on condition that robot carry out weld joint tracking need to have it is more accurate and reliable
Characteristics of weld seam point sequence track generated.
(1) it can be used as to obtain referring to desired characteristics of weld seam point sequence, robot shown with regard to the weld seam first
Religion programming, and ensure that robot tool end TCP point is maintained on axis of a weld and run, it obtains with normal weld service speed
More reliable robot tool end TCP locus of points program when operation.
(2) on the basis of ensuring that visual sensor pose is fixed correct, weld bead feature points sequential extraction procedures and vision are carried out
For sensor along the determination (the two forms one-to-one relationship) of bead direction position point sequence, the latter is denoted as Xsd={ Xsd1,
Xsd2,L,Xsd(l+1), while recorder people's tool ends end TCP point is along the position X of bead directiontd={ Xtd0,Xtd2,L,Xtdl,
In this case, and without the tracking of the position compensation of robot tool end TCP point and subsequent weld characteristic point it operates.
Robot carries out W above-mentioned empty run and operates, and in visual sensor location point, weld bead feature points are relative to machine
The coordinate sequence of people's basis coordinates system can be denoted as
On this basis, optimal estimation is carried out to the corresponding weld bead feature points coordinate value of visual sensor location point, rejected
The biggish weld bead feature points coordinate value of deviation can get " robot sky runs the characteristics of weld seam locus of points " shown in Figure 10, in this, as
Robot tool end TCP point is denoted as into the desired reference value of line trace
It enables and corresponds to Xsd'sDeposit relationship shown in Fig. 7
Resulting weld bead feature points coordinate after running with reference to sky, robot tool end TCP point draw the mistake for getting rid of deviation point
It leads, deviation caused by compensation deviates, to correctly advance along axis of a weld.
(3) according to above-mentioned steps, according to sky run gained weld bead feature points position be desired robot tool end TCP from
The control strategy of motion tracking is as shown in Figure 8.
According to control strategy shown in Fig. 8, form two queues, i.e., with the one-to-one visual sensing of weld bead feature points
The queue of device location point and robot tool end TCP point are during tracking along bead direction location point queue:
Wherein, queue one includes weld bead feature points P1, P2Until Pk+1, repeatedly resulting after empty race to refer to weld bead feature pointsUntilWith visual sensor along the position X of bead directions1, Xs2To Xs(k+1)And position when sky race
Xsd1, Xsd2To Xsd(k+1)It corresponds.
Queue two includes position X of the TCP point in robot tool end along bead directiont0, Xt1Until Xtk, perpendicular to weld seam side
To lateral Y-direction need to finely tune and reach the correction amount of accurate positioninExtremelyPerpendicular to weld seam side
To lateral Z-direction need to finely tune and reach the correction amount of accurate positionin ExtremelyAccording to aforementioned mechanical arm
Control strategy will be adjacent in mechanical arm tool ends end TCP point either by cradle head or space coordinate move mode
Carry out interpolation between ordinal position point, and at up to each tracked weld bead feature points position when carries out the correction of Y-direction and Z-direction,
Deviation can be eliminated on tri- directions in X, Y, Z to reach, to ensure robot tool end TCP point through three-dimensional weld joint tracking
After reach expected pose.
Claims (9)
1. a kind of active laser vision guide robotic laser welds accurate seam tracking system, it is characterised in that: include: sharp
Light-composite welding robot (1), active laser vision system (2), laser light source (3), image processing system (4) and control system
It unites (5), the active laser vision system (2) and laser light source (3) are set in laser-composite welding robot (1), described
Image processing system (4) is set in control system (5), the laser-composite welding robot (1), active laser vision system
(2), laser light source, image processing system (2) are connect with control system (5)；
Industrial robot (11), laser compound welding tip (12), wire-feed motor are equipped in the laser-composite welding robot (1)
Structure (13) and be used for pinpoint positioning cross slide unit (14) and the source of welding current, the positioning cross slide unit (14) be set to work
The leading portion of industry robot (11), and it connect with slide unit driving motor, the laser compound welding tip (12) is installed on positioning ten
On word slide unit (14), the wire feeder (13) is set to the side of laser compound welding tip (12), and the source of welding current is to laser-
Composite welding robot (1) provides welding current, arc voltage, wire feed rate Parameters Integrated Survey Method and adjusts.
2. active laser vision guide robotic laser according to claim 1 welds accurate seam tracking system, special
Sign is: the positioning cross slide unit (14) is equipped with horizontal slide unit (141) and longitudinal slide unit (142), the horizontal slide unit
(141) and longitudinal slide unit (142) uses staggered form design, and is equipped in the horizontal slide unit (141) and longitudinal slide unit (142)
The two sides of bottom plate (143), the bottom plate (143) are equipped with linear guide (144), and top is equipped with driving mechanism (145), the straight line
Guide rail (144) is equipped with sliding block (146), and the driving mechanism (145) connect with control system (5).
3. active laser vision guide robotic laser according to claim 2 welds accurate seam tracking system, special
Sign is: bearing block (1451) and screw rod (1452), one end of the bearing block (1451) are equipped in the driving mechanism (145)
It is located in front of servo motor (1453) equipped with servo motor (1453), and on the bearing block (1451) and is additionally provided with feed screw nut
Support (1454), the screw rod (1452) are installed on bearing block (1451) and are fixed by feed screw nut's support (1454), and
The screw rod (1452) connect with servo motor (1453).
4. active laser vision guide robotic laser according to claim 1 welds accurate seam tracking system, special
Sign is: the industrial robot (11) uses six-shaft industrial robot, is provided with pedestal (111), robotic arm and driving machine
Structure (112) is equipped with lower arm (113) and forearm (114) in the mechanical arm, and the pedestal (111) is equipped with for installing lower arm
(113) mounting base (115), lower arm (113) lower part and mounting base (115) use movable connection, the forearm (114)
It is installed on the top of lower arm (113), and the two uses movable connection, the positioning cross slide unit (14) is set to industrial robot
(11) forearm (114).
5. active laser vision guide robotic laser according to claim 1 welds accurate seam tracking system, special
Sign is: laser vision sensor and industrial camera are equipped in the active laser vision system (2).
6. active laser vision guide robotic laser according to claim 1 welds accurate seam tracking system, special
Sign is: vision controller, robot controller, cross slid platform controller and controller, institute are equipped in the control system (4)
It states vision controller to connect with active laser vision system (2), the robot controller is connect with industrial robot (11), institute
Cross slid platform controller is stated to connect with positioning cross slide unit (14)；
In the vision controller be equipped with the first central processing unit, the first internal storage unit, visual sensor interface and
First communication interface, the both ends of the visual sensor interface respectively with active laser vision system (2) and the first storage inside
Unit connection, first internal storage unit, visual sensor interface and the first communication interface with the first central processing
Unit connection；
The second central processing unit, the second internal storage unit, the second communication interface, driving are equipped in the robot controller
Device, motion control card, input/output interface, the input/output interface are connect with the second internal storage unit, the driving
The output end of device is connect with the input terminal of the motor of driving mechanical arm, and the output end of the motor is connect with mechanical arm, the fortune
It is dynamic to control the encoder connection being stuck in mechanical arm, second internal storage unit, the second communication interface, driver, movement
Control card, robot input/output interface are connect with the second central processing unit, and the robot control system passes through the
Two communication interfaces are connect with the first communication interface in vision control system；
It is equipped with third communication interface in the cross slid platform controller, third central processing unit, third internal storage unit, watches
Take driver, sliding block control module and slide unit input/output interface, the third communication interface and first in vision controller
Communication interface connection, the output end of the servo-driver are connect with slide unit driving motor, the sliding block control module and positioning
The input terminal of the encoder of cross slid platform (14) connects, second in the slide unit input/output interface and robot controller
Communication interface is bi-directionally connected, the third communication interface, third internal storage unit, servo-driver, sliding block control module and
Slide unit input/output interface is connect with third central processing unit；
The vision controller, robot controller, cross slid platform controller are connect with controller.
7. active laser vision guide robotic laser according to any one of claims 1 to 6 welds accurate weld joint tracking
The working method of system, it is characterised in that: specific working method is as follows:
1): first by laser vision sensor by identifying weld seam for project structured light to face of weld in the course of work
The relevant laser stripe band (6) of profile information；
2): and then industrial camera obtains the image of the laser stripe band (6) generated in previous step, and transfers data to image
Processing system (4) extracts characteristics of weld seam information by the data extraction module of image processing system (4), from laser stripe band (6)
Center line detecting to position while welding after, it may be assumed that carry out without deformation laser stripe baseline detection and weld bead feature points extract；
3): and then intelligent-tracking is carried out to weld seam again, specific welding is controlled according to the result of tracking, in weld joint tracking
It can find that industrial robot (11) path is accurate or inaccurate two kinds of situations in the process；
4): when confirmation industrial robot (11) path is accurate during previous step tracking, specific working method is as follows:
A), robot controller issues HOME signals, and positioning cross slide unit (14) are restored to intermediate initial position；
B), cross slid platform controller issues HOME signals in place；
C), industrial robot (11) reaches program initial bit, and then industrial robot (11) starts initial search point；
D), the starting point of robot controller searching machine people tool ends end TCPTCP point (7)；
E), register queue is then established, laser vision sensor position sequence corresponding with weld bead feature points is recorded；
F), then judge whether robot tool end TCP (7) is located at initial weld bead feature points, if it is not, so it will be returned
Step b) is returned to the starting point for c) searching robot tool end TCP (7) again；If it is then robot tool end TCP (7) position
In weld seam path initial position signal, then robot controller starts to weld operational order；
G), then robot controller starts weld joint tracking operational order；
H), continue to establish register and line up, record laser vision sensor position sequence corresponding with weld bead feature points；
I), robot tool end TCP (7) carries out weld bead feature points tracking operation；
J), whether robot tool end TCP (7) is located at last bit weld bead feature points, if it is not, so it wants return step f) extremely
G) register is re-started to line up to establish；If it is then robot tool end TCP (7) is located at path of welding most end end position
Signal；
K), robot controller terminates to weld operational order；
5) it: in above-mentioned steps 3) can find that industrial robot (11) path is inaccurate during weld joint tracking, there are when deviation,
The deviation to weld seam feature point trajectory is needed to compensate, so that robot tool end TCP (7) is along more accurate characteristics of weld seam
Point path operation generated, while positioning cross slide unit (14) also being needed to be accurately positioned Y-direction and Z-direction, it realizes three-dimensional
Weld joint tracking, until completing laser welding operation.
8. the work that active laser vision guide robotic laser according to claim 7 welds accurate seam tracking system
Method, it is characterised in that: the data extraction module of step 3) image processing system (4) extracts characteristics of weld seam information, from laser strip
The center line detecting of line band is as follows to the specific method of position while welding:
Described image processing system (4) is not necessarily to active laser vision weld joint image procossing and Detecting Welding Seam algorithm
Additional narrow-band filter；Specific working method includes two parts: (1) without deformation laser stripe baseline detection；(2) characteristics of weld seam
Point extracts；
1) without the detection of deformation laser stripe baseline, specific step is as follows:
Step 1: image preprocessing
A, mean filter processing is carried out to laser stripe image acquired in industrial camera；The mean filter method such as following formula institute
Show:
Wherein, maximum value it is expected for laser stripe width, be the image intensity of the i-th row jth column pixel, for the i-th row jth after filtering
The end value of column；
B, HSV color space will be converted to from rgb color space through processing image again, i.e., accurately extracts laser indigo plant from image again
Photochromic coloured silk sets the threshold value in tri- channels HSV, and carries out mask process to image, and the setting of three kinds of threshold values is so that low quality swashs
The low contrast laser stripe that light generates can obtain subsequent processing；
M=M1∩M2∩M3
Wherein, M1, M2, M3, respectively H, S, the exposure mask threshold value of V triple channel, i, j are respectively pixel position No., finally to be obtained
Exposure mask intersection area；
C, former RGB image is converted to gray level image, method again through gray proces are as follows:
Grey=0.299*R+0.587*G+0.114*B
By the R in the RGB (R, G, B) of script, G, B are replaced with Grey, form new color RGB (Grey, Grey, Grey), i.e.,
The single channel grayscale image that replacement RGB (R, G, B) can be formed, is applied to the single channel grayscale image through exposure mask intersection；
D, median filtering then is carried out to image again, removes the spiced salt, speckle noise, it may be assumed that median filtering contains odd point with one
Sliding window, by the pixel in neighborhood by gray level sort, take median be output pixel；
Subsequent further image processing process is used for once the resulting image of processing by above-mentioned steps；
Step 2: laser stripe profile detection
A, the method detected by laser peak extracts the contour edge pixel of characterization laser stripe band, it may be assumed that neck laser stripe
Vertically, the intensity threshold that the horizontal every row pixel of setting is accepted or rejected, obtains intensity peak point, forms laser stripe band (6) basis；It is right again
The image pixel intensities peak point that horizontal direction is formed carries out noise filtering；Acquired image pixel intensities peak point is fitted, is returned
Obtain laser stripe baseline position；
B, weld bead feature points are extracted
By taking the baseline that vertical laser stripe band (6) is obtained as an example, it is known that on baseline, can be considered and contain along the deformed region of baseline
Have the position of weld bead feature points: the step of extracting these weld bead feature points from laser stripe band (6) image can be summarized as: one,
Determine vertical direction ROI；Two, the mark and selection in crosspoint；Three, the ROI of horizontal direction is determined；Four, the horizontal peak of weld seam is detected
Value point；
Around the laser baseline previously obtained, the image through filtering is cut according to following method, it may be determined that vertically and water
Square to ROI；
Vertical ROI is obtained by following formula,
ROI (i, c)=I (i, j)
Wherein
Wherein, LW is desired laser stripe band (6) width, and N is the line number of image, and I (i, j) is the image of the i-th row jth column
Intensity, ROI (i, c) are the area-of-interest of image, and p is by the column mark of the laser lines detected in original image；
Therefrom, the upper end characteristic point and lower bottom end characteristic point of extracted laser line segment deformed region are obtained；
Horizontal ROI is obtained by following formula,
ROI (c, j)=I ' (i, j)
Wherein, Ytop≤i≤Ybottom；min(Xtop,Xbottom)≤j≤M
In formula, Ytop, Xtop, Ybottom, XbottomUpper end point and lower bottom endpoint are concentrated for the joint in image I (i, j)
Y-axis and x-axis coordinate value, M be image I (i, j) column number；
Therefrom, it can get the weld seam horizontal peak characteristic point of extracted laser line segment deformed region, it is special to obtain weld seam horizontal peak
The method for levying point is as follows:
Step 1: removal noise spot extracts the profile point in horizontal ROI on laser band, that is, extracted laser stripe belt profile becomes
The characteristic point in shape region；
Step 2: being divided into top and twoth area of lower part for the profile of laser stripe band (6) in ROI, according to following constraint condition, respectively
Part except the Internal periphery of top and the bottom region supplements the discontinuous point in laser stripe profile deformed area continuous；
-LW≤Pci≤LW
Wherein, LW is the width of desired laser stripe band, PciBy supplement discontinuous point column mark；
Step 3: to the point of profile point on top and the bottom laser stripe band (6) in above-mentioned complete ROI and the discontinuous point composition supplemented
Collection carries out linear fit respectively, and resulting two straight-line intersections can be identified as weld seam characteristic point peak load.
9. the work that active laser vision guide robotic laser according to claim 7 welds accurate seam tracking system
Method, it is characterised in that: in step 5), can find that industrial robot (11) path is inaccurate during weld joint tracking, deposit
In deviation, the deviation to weld seam feature point trajectory is needed to compensate, specific tracking is as follows:
1), robot controller issues HOME signals, and positioning cross slide unit (14) are restored to intermediate initial position；
2), cross slid platform controller issues HOME signals in place；
3), industrial robot (11) reaches program initial bit, and then industrial robot (11) starts initial search point；
4), the starting point of robot controller searching machine people tool ends end TCP (7)；
5) register queue, is then established, laser vision sensor position sequence corresponding with weld bead feature points is recorded；
6), then judge whether robot tool end TCP (7) is located at initial weld bead feature points, if it is not, so it will be returned
Step 4) is returned to 5) searching robot tool end TCP (7) starting point again；If it is then robot tool end TCP (7) is located at
Weld seam path initial position signal；
7), robot controller judges whether industrial robot (11) carries out empty run and run；
8) industrial robot as the result is shown (11), obtained in step 7) runs operation if not in sky, then robot control
Device processed will order it to continue to establish register and line up, and record laser vision sensor position sequence corresponding with weld bead feature points；
9), record corresponds to TCP point Y-direction, the Z-direction correction value of the position sequence；
10), robot tool end TCP is located at path of welding least significant end position signal；
11), robot controller terminates to weld operational order；
12) industrial robot as the result is shown (11), obtained in step 7) runs operation if it is in sky, then robot controls
Device will order it to establish register queue and record visual sensor position sequence corresponding with weld bead feature points；
13), record corresponds to TCP point Y-direction, the Z-direction correction value of the position sequence；
14), robot controller judges whether industrial robot (11) completes W empty race, if the result display of monitoring is not complete
At then it will repeat step a) to h)；
15) if the industrial robot as the result is shown (11), monitored in previous step completes W empty race, will calculate W times
Sky runs gained weld bead feature points optimal estimation and corresponding laser vision sensor position sequence and Y-direction, Z-direction correction value；
16), then robot controller order industrial robot (11) starts welding operation；
17) after, industrial robot (11) receives welding operational order, start welding operation；
18), robot controller starts weld joint tracking operational order；
19), robot tool end TCP carries out tracking operation referring to optimal estimation weld bead feature points；
20), then whether robot controller confirmation robot tool end TCP is located at last bit weld bead feature points, if it is not, that
It wants return step 19) line up to establish to 20) re-starting the first register；If it is then TCP, robot tool end
In path of welding least significant end position signal；
20), robot controller terminates to weld operational order.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810825163.1A CN109604830B (en) | 2018-07-25 | 2018-07-25 | Accurate welding seam tracking system for laser welding of active laser vision guiding robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810825163.1A CN109604830B (en) | 2018-07-25 | 2018-07-25 | Accurate welding seam tracking system for laser welding of active laser vision guiding robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109604830A true CN109604830A (en) | 2019-04-12 |
| CN109604830B CN109604830B (en) | 2021-04-23 |
Family
ID=66001969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810825163.1A Active CN109604830B (en) | 2018-07-25 | 2018-07-25 | Accurate welding seam tracking system for laser welding of active laser vision guiding robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109604830B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109926694A (en) * | 2019-04-22 | 2019-06-25 | 大连智汇达科技有限公司 | A kind of welding robot |
| CN110443260A (en) * | 2019-08-05 | 2019-11-12 | 广东博智林机器人有限公司 | Groove localization method between a kind of building wall board |
| WO2020020113A1 (en) * | 2018-07-25 | 2020-01-30 | 同高先进制造科技（太仓）有限公司 | Active laser vision weld tracking system and weld position detecting method |
| CN110860791A (en) * | 2019-12-25 | 2020-03-06 | 汤忠武 | Laser seam-searching visual guidance welding system and welding method |
| CN111055054A (en) * | 2020-01-13 | 2020-04-24 | 北京博清科技有限公司 | Welding seam identification method and device, welding robot and storage medium |
| CN111861993A (en) * | 2020-06-15 | 2020-10-30 | 渤海造船厂集团有限公司 | Method for quickly finding and accurately positioning welding line by laser vision point cloud system |
| CN111940954A (en) * | 2020-08-14 | 2020-11-17 | 南京水木自动化科技有限公司 | High-reliability arc light interference-resistant welding polymorphic data intelligent agent and processing method |
| CN112080738A (en) * | 2020-07-16 | 2020-12-15 | 宁夏莫克仪表科技有限公司 | Processing method and processing device for laser cladding of wear-resistant thermocouple sleeve |
| CN112894223A (en) * | 2021-01-16 | 2021-06-04 | 佛山市广凡机器人有限公司 | Automatic welding robot of diversified type that turns to |
| CN112935649A (en) * | 2021-01-23 | 2021-06-11 | 佛山市广凡机器人有限公司 | All-directional steering type welding robot and use method thereof |
| CN113119122A (en) * | 2021-04-10 | 2021-07-16 | 西北工业大学 | Hybrid off-line programming method of robot welding system |
| CN113199175A (en) * | 2021-04-15 | 2021-08-03 | 深圳中集智能科技有限公司 | Auxiliary welding device of crawling welding robot, control method and welding method thereof |
| CN113369686A (en) * | 2021-06-11 | 2021-09-10 | 杭州国辰机器人科技有限公司 | Intelligent welding system and method based on two-dimensional code visual teaching technology |
| CN113400300A (en) * | 2021-05-24 | 2021-09-17 | 陶建明 | Servo system for robot tail end and control method thereof |
| CN114523203A (en) * | 2022-03-13 | 2022-05-24 | 扬州沃盛车业制造有限公司 | Intelligent laser welding method and system |
| CN115383262A (en) * | 2022-08-12 | 2022-11-25 | 华南理工大学 | Automatic tracking method and system for welding seam track under laser vision guidance |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08166813A (en) * | 1994-12-14 | 1996-06-25 | Fanuc Ltd | Tracking control method for robot accompanied by weaving operation |
| CN101623867A (en) * | 2008-07-11 | 2010-01-13 | 中国科学院沈阳自动化研究所 | Equipment and method for enabling robot to track specified path with high precision |
| CN104985289A (en) * | 2015-07-31 | 2015-10-21 | 华南理工大学 | Laser sensor-based welding seam automatic tracking test device and test method thereof |
| CN105328304A (en) * | 2015-12-09 | 2016-02-17 | 山东中清智能科技有限公司 | Welding seam starting point automatic position searching method based on statistics |
| CN106392267A (en) * | 2016-11-28 | 2017-02-15 | 华南理工大学 | Line laser real-time welding seam tracking method for six-freedom-degree welding robot |
| CN107424144A (en) * | 2017-04-26 | 2017-12-01 | 哈尔滨理工大学 | Weld joint tracking image processing algorithm based on laser vision |
-
2018
- 2018-07-25 CN CN201810825163.1A patent/CN109604830B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08166813A (en) * | 1994-12-14 | 1996-06-25 | Fanuc Ltd | Tracking control method for robot accompanied by weaving operation |
| CN101623867A (en) * | 2008-07-11 | 2010-01-13 | 中国科学院沈阳自动化研究所 | Equipment and method for enabling robot to track specified path with high precision |
| CN104985289A (en) * | 2015-07-31 | 2015-10-21 | 华南理工大学 | Laser sensor-based welding seam automatic tracking test device and test method thereof |
| CN105328304A (en) * | 2015-12-09 | 2016-02-17 | 山东中清智能科技有限公司 | Welding seam starting point automatic position searching method based on statistics |
| CN106392267A (en) * | 2016-11-28 | 2017-02-15 | 华南理工大学 | Line laser real-time welding seam tracking method for six-freedom-degree welding robot |
| CN107424144A (en) * | 2017-04-26 | 2017-12-01 | 哈尔滨理工大学 | Weld joint tracking image processing algorithm based on laser vision |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020020113A1 (en) * | 2018-07-25 | 2020-01-30 | 同高先进制造科技（太仓）有限公司 | Active laser vision weld tracking system and weld position detecting method |
| CN109926694A (en) * | 2019-04-22 | 2019-06-25 | 大连智汇达科技有限公司 | A kind of welding robot |
| CN110443260A (en) * | 2019-08-05 | 2019-11-12 | 广东博智林机器人有限公司 | Groove localization method between a kind of building wall board |
| CN110443260B (en) * | 2019-08-05 | 2022-02-22 | 广东博智林机器人有限公司 | Positioning method for grooves between building wallboards |
| CN110860791B (en) * | 2019-12-25 | 2021-06-08 | 株洲光谷激光加工技术有限公司 | Laser seam-searching visual guidance welding system and welding method |
| CN110860791A (en) * | 2019-12-25 | 2020-03-06 | 汤忠武 | Laser seam-searching visual guidance welding system and welding method |
| CN111055054A (en) * | 2020-01-13 | 2020-04-24 | 北京博清科技有限公司 | Welding seam identification method and device, welding robot and storage medium |
| CN111055054B (en) * | 2020-01-13 | 2021-11-16 | 北京博清科技有限公司 | Welding seam identification method and device, welding robot and storage medium |
| CN111861993A (en) * | 2020-06-15 | 2020-10-30 | 渤海造船厂集团有限公司 | Method for quickly finding and accurately positioning welding line by laser vision point cloud system |
| CN111861993B (en) * | 2020-06-15 | 2023-06-06 | 渤海造船厂集团有限公司 | Quick searching and accurate weld positioning method for laser vision point cloud system |
| CN112080738A (en) * | 2020-07-16 | 2020-12-15 | 宁夏莫克仪表科技有限公司 | Processing method and processing device for laser cladding of wear-resistant thermocouple sleeve |
| CN111940954A (en) * | 2020-08-14 | 2020-11-17 | 南京水木自动化科技有限公司 | High-reliability arc light interference-resistant welding polymorphic data intelligent agent and processing method |
| CN112894223A (en) * | 2021-01-16 | 2021-06-04 | 佛山市广凡机器人有限公司 | Automatic welding robot of diversified type that turns to |
| CN112935649A (en) * | 2021-01-23 | 2021-06-11 | 佛山市广凡机器人有限公司 | All-directional steering type welding robot and use method thereof |
| CN113119122B (en) * | 2021-04-10 | 2022-11-22 | 西北工业大学 | Hybrid off-line programming method of robot welding system |
| CN113119122A (en) * | 2021-04-10 | 2021-07-16 | 西北工业大学 | Hybrid off-line programming method of robot welding system |
| CN113199175A (en) * | 2021-04-15 | 2021-08-03 | 深圳中集智能科技有限公司 | Auxiliary welding device of crawling welding robot, control method and welding method thereof |
| CN113400300A (en) * | 2021-05-24 | 2021-09-17 | 陶建明 | Servo system for robot tail end and control method thereof |
| CN113400300B (en) * | 2021-05-24 | 2024-05-03 | 陶建明 | Servo system for robot tail end and control method thereof |
| CN113369686A (en) * | 2021-06-11 | 2021-09-10 | 杭州国辰机器人科技有限公司 | Intelligent welding system and method based on two-dimensional code visual teaching technology |
| CN114523203A (en) * | 2022-03-13 | 2022-05-24 | 扬州沃盛车业制造有限公司 | Intelligent laser welding method and system |
| CN115383262A (en) * | 2022-08-12 | 2022-11-25 | 华南理工大学 | Automatic tracking method and system for welding seam track under laser vision guidance |
| CN115383262B (en) * | 2022-08-12 | 2023-06-16 | 华南理工大学 | Automatic tracking method and system for weld joint track under laser vision guidance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109604830B (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109604830A (en) | A kind of accurate seam tracking system of active laser vision guide robotic laser welding | |
| CN109226967A (en) | A kind of steady seam tracking system of active laser vision for Laser-Arc Hybrid Welding | |
| CN210046133U (en) | Welding seam visual tracking system based on laser structured light | |
| CN108817613A (en) | A kind of arc welding robot weld seam deviation-rectifying system and method | |
| CN104588838B (en) | A kind of automatic tracing control of welding gun on-line amending system and control method thereof | |
| CN111014879B (en) | Automatic welding method for corrugated plate of robot based on laser weld seam tracking | |
| CN107414253A (en) | Weld Seam Tracking Control device and control method based on cross laser | |
| CN102699534B (en) | Scanning type laser vision sensing-based narrow-gap deep-groove automatic laser multilayer welding method for thick plate | |
| CN103480991B (en) | Thin steel plate narrow welding joint online visual inspection and control device | |
| CN112059363A (en) | Unmanned wall climbing welding robot based on vision measurement and welding method thereof | |
| CN110919134A (en) | Tube plate positioning welding method | |
| CN111229548A (en) | Automatic tracking dispensing system based on assembly line | |
| JP2015212012A (en) | Method of controlling robot tool | |
| CN111299078A (en) | Automatic tracking dispensing method based on assembly line | |
| CN110064819A (en) | The extraction of cylinder longitudinal seam characteristic area, welding seam tracking method and system based on structure light | |
| CA2554031A1 (en) | Method for automatically applying and controlling a structure applicable on a substrate and device for carrying out said method | |
| CN103203526A (en) | Laser visual tracking system | |
| CN104057202A (en) | System and method for remotely monitoring automatic welding of mobile robot based on FPGA | |
| CN102284769A (en) | System and method for initial welding position identification of robot based on monocular vision sensing | |
| CN105414821A (en) | Welding robot welding seam automatic tracking system | |
| CN207077080U (en) | Weld Seam Tracking Control device based on cross laser | |
| CN115070298A (en) | Efficient double-wire welding path generation system and path generation method | |
| CN212329961U (en) | Unmanned wall welding robot that climbs based on vision measurement | |
| CN109834373A (en) | A kind of view-based access control model and the automation submerged arc soldering equipment of laser tracking | |
| CN111398271A (en) | Detection optimization system and method for laser near-net-shape defect |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211229 Address after: 215400 No.16, North Ring Road, taicanggang Economic Development Zone, Taicang City, Suzhou City, Jiangsu Province Patentee after: Parnova Intelligent Technology (Suzhou) Co.,Ltd. Address before: 215400 No.10, North Ring Road, taicanggang Economic Development Zone, Taicang City, Suzhou City, Jiangsu Province Patentee before: TONGGAO ADVANCED MANUFACTURING TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |