Nothing Special   »   [go: up one dir, main page]

CN114043045A - Round hole automatic plug welding method and device based on laser vision - Google Patents

Round hole automatic plug welding method and device based on laser vision Download PDF

Info

Publication number
CN114043045A
CN114043045A CN202111432473.5A CN202111432473A CN114043045A CN 114043045 A CN114043045 A CN 114043045A CN 202111432473 A CN202111432473 A CN 202111432473A CN 114043045 A CN114043045 A CN 114043045A
Authority
CN
China
Prior art keywords
welding
coordinate
coordinates
laser
seam
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111432473.5A
Other languages
Chinese (zh)
Other versions
CN114043045B (en
Inventor
郝盼
张彦超
马俊杰
石文静
张永泉
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.)
Suzhou Full Vision Intelligent Photoelectric Co ltd
Original Assignee
Suzhou Full Vision Intelligent Photoelectric Co ltd
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 Suzhou Full Vision Intelligent Photoelectric Co ltd filed Critical Suzhou Full Vision Intelligent Photoelectric Co ltd
Priority to CN202111432473.5A priority Critical patent/CN114043045B/en
Publication of CN114043045A publication Critical patent/CN114043045A/en
Application granted granted Critical
Publication of CN114043045B publication Critical patent/CN114043045B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K9/00Arc welding or cutting
    • B23K9/12Automatic feeding or moving of electrodes or work for spot or seam welding or cutting
    • B23K9/133Means for feeding electrodes, e.g. drums, rolls, motors
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K9/00Arc welding or cutting
    • B23K9/24Features related to electrodes
    • B23K9/28Supporting devices for electrodes
    • B23K9/287Supporting devices for electrode holders
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K9/00Arc welding or cutting
    • B23K9/32Accessories

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Plasma & Fusion (AREA)
  • Mechanical Engineering (AREA)
  • Laser Beam Processing (AREA)
  • Manipulator (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention relates to the technical field of welding, in particular to a round hole automatic plug welding method and a round hole automatic plug welding device based on laser vision, and the round hole automatic plug welding method comprises the following steps: the welding gun and the sensor are arranged on the mechanical arm; the sensor includes: the laser device is used for emitting line laser to irradiate on a welding workpiece and scan a circular welding hole in the welding workpiece, the camera is used for shooting a laser image of the welding workpiece and sending the laser image to the welding seam processor, and the welding seam processor is used for converting a two-dimensional coordinate of the laser image into a three-dimensional coordinate of a circular welding seam and sending the three-dimensional coordinate to the mechanical arm controller; the mechanical arm controller is used for controlling the mechanical arm to drive the welding gun and the sensor to act, calculating the circle center and the volume of a welding seam circle, and controlling the welding position and the welding time of the welding gun according to the circle center coordinate and the volume of the circular welding seam. The invention can improve the quality of welding seams and realize automatic welding.

Description

Round hole automatic plug welding method and device based on laser vision
Technical Field
The invention relates to the technical field of welding, in particular to a round hole automatic plug welding method and device based on laser vision.
Background
The circular hole plug welding is one welding process, which includes drilling one technological hole in steel plate and welding to fill the hole. It is often used for the connection between flat plates, where bolts or rivets are used. The size of the welding seam of the circular hole plug welding is mainly specified by a sinking angle and a filling depth of the welding seam, when an upper layer plate is thick, a common electric drill and the like are used for punching, a consumable electrode welding mode is used, two plates are melted through a welding hole to form a welding mode, and common manual arc welding and secondary arc welding are used.
At present, when plug welding is carried out by a welding device in the prior art, circular welding is difficult to position a plug welding hole effectively, so that accurate welding of circular hole plug welding is achieved, welding defects such as welding deviation and undercut are easy to generate, and the previous circular hole plug welding has overlarge heat input, so that the flatness is poor and the deformation is poor. The appearance is very difficult to see, is difficult to satisfy the requirement that the surface requirement is higher and higher on the existing market, and in addition the round hole welding operation gets up inconveniently, and is also high to welder technical skill requirement, hardly welds the pleasing to the eye welding seam appearance that has the uniformity. When the surface of the workpiece is rough, the accuracy of the algorithm is necessarily affected. The algorithm requires high imaging quality of the image and needs complicated image smoothing. The existing algorithm mainly aims at linear welding seams, calculates intersection points or sharp points as characteristic points, and is not suitable for identifying the characteristic points on an arc line.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a circular hole automatic plug welding method and device based on laser vision so as to improve the precision of circular hole plug welding, reduce the labor intensity of workers through an automatic method and improve the welding efficiency.
In order to solve the problems, the invention adopts the technical scheme that: a round hole automatic plug welding device based on laser vision comprises: the welding gun and the sensor are arranged on the mechanical arm;
the sensor includes: the laser device is used for emitting line laser to irradiate on a welding workpiece and scan a circular welding hole in the welding workpiece, the camera is used for shooting a laser image of the welding workpiece and sending the laser image to the welding seam processor, and the welding seam processor is used for converting a two-dimensional coordinate of the laser image into a three-dimensional coordinate of a circular welding seam and sending the three-dimensional coordinate to the mechanical arm controller;
the mechanical arm controller is used for controlling the mechanical arm to drive the welding gun and the sensor to act, calculating the circle center and the volume of a welding seam circle, and controlling the welding position and the welding time of the welding gun according to the circle center coordinate and the volume of the circular welding seam.
The circular hole automatic plug welding device based on laser vision further comprises a welding gun controller, and the welding gun controller is used for providing current and voltage for a welding gun.
In addition, the invention also provides a round hole automatic plug welding method based on laser vision, and the round hole automatic plug welding device based on laser vision comprises the following steps:
s1, manually inputting a start point coordinate and an end point coordinate;
s2, driving the welding gun and the sensor to move to the position of the start point coordinate by the mechanical arm and move forward in the end point direction;
s3, after passing through a round hole, calculating to obtain the welding seam circular coordinate and the circle center position through the laser image collected by the camera, and recording the current position;
s4, driving the welding gun to move to the position of the circle center through the mechanical arm, and carrying out wire feeding welding;
s5, after welding, driving the welding gun to move to the recorded position through the mechanical arm;
and S6, driving the welding gun to move forward to the terminal direction again through the mechanical arm, and repeating the steps S3-S5 until the welding gun moves to the terminal coordinate position, so that the welding is finished.
In step S3, the method for determining the weld circle coordinate specifically includes:
s301, extracting a current frame image acquired by a camera, and performing feature extraction on the image through a gray threshold to obtain feature points;
s302, fitting the extracted characteristic points into a straight line by a least square method, and taking a point close to an end point on the fitted straight line as a circular coordinate of the welding line;
and S303, repeating the operations of the steps S301 and S302 on each frame of image collected by the camera to obtain all coordinates on the weld circle.
In step S3, the method for determining the position of the circle center specifically includes:
s304, obtaining a matrix P of coordinates of the upper point of the circular hole weld joint under a camera coordinate systemcameraConverting the coordinates of the welding point under the camera coordinate system into the coordinates P under the robot coordinate systemrobotThe conversion formula is:
Figure BDA0003380790680000021
wherein,
Figure BDA0003380790680000022
calibrating a matrix for the hand and the eye;
s305, fitting a circle center coordinate (x) through the coordinates of the welding line points by using a least square methodc,yc)。
In the step S3, the hand-eye calibration matrix
Figure BDA0003380790680000023
The calculation formula of (2) is as follows:
Figure BDA0003380790680000024
wherein,
Figure BDA0003380790680000025
representing a phaseTransformation matrix of machine coordinate system to robot arm end coordinate system, PbaseCoordinates representing points on the calibration plate in the robot coordinate system, P1 cameraAnd 3D coordinates representing the corresponding points on the calibration plate obtained by the 3D camera.
The automatic plug welding method for the round hole based on the laser vision further comprises the step of obtaining a hand-eye calibration matrix.
In step S4, when wire feeding welding is performed, the welding time is:
Figure BDA0003380790680000026
wherein V represents the volume of the circular hole weld, d represents the diameter of the welding wire, and V represents the wire feeding speed.
The calculation formula of the volume of the circular hole welding seam is as follows:
V=πR2h;
wherein R represents the radius of the circular hole welding seam, and h represents the height of the circular hole welding seam;
the calculation formula of the radius of the circular hole welding seam is as follows:
Figure BDA0003380790680000031
wherein (x)c,yc) Represents the coordinates of the circle center of the circular hole weld joint, (x)i,yi) And the coordinates of the ith data point on the circular hole weld joint are shown, and N represents the number of coordinate points.
The method for determining the height of the circular hole weld joint comprises the following steps: and after converting the point coordinates on the welding seam circle and the point coordinates on the bottom surface of the welding seam circle into three-dimensional coordinates, fitting to obtain the three-dimensional coordinates of the circle center of the welding seam circle and the three-dimensional coordinates of the circle center of the bottom surface of the welding seam circle, and obtaining the height of the welding seam through the distance between the two coordinates.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention provides a round hole automatic plug welding method and a device based on laser vision, which adopt a sensor comprising a camera and a line laser as a guide to ensure high precision of welding line detection; the welding parameters of each welding line are constant, the quality of the welding line is less influenced by human factors, and the requirements on the operation technology of workers are reduced.
2. The six-axis robot system is adopted for accurate positioning, the welding effect is stable, and the whole process is more intelligent; the technology reduces the labor intensity of workers and improves the working environment.
3. The device has the advantages of simple structure, convenient operation and low cost, can meet the plug welding requirements of different circular holes, and can effectively improve the welding efficiency. The overall algorithm has small calculated amount, short running time, fast identification result acquisition, computer resource saving, low cost, high transportability and strong practicability.
Drawings
Fig. 1 is a schematic structural diagram of an external shape of a circular hole automatic plug welding device based on laser vision according to a first embodiment of the present invention;
fig. 2 is a block diagram of a circuit structure of a circular hole automatic plug welding device based on laser vision according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a circular hole automatic plug welding method based on laser vision according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram of a laser line extraction point according to a second embodiment of the present invention;
FIG. 5 is a schematic illustration of a laser image obtained in a second embodiment of the present invention;
FIG. 6 is a schematic diagram of points on the weld circle and points on the bottom surface of the weld obtained by fitting in the second embodiment of the present invention;
FIG. 7 is a schematic diagram of a height of a circular hole weld obtained in the second embodiment of the present invention;
FIG. 8 is a graph of welding current versus wire feed speed for different wire diameters in an embodiment of the present invention.
In the figure, 1 is a mechanical arm controller, 2 is a welding gun controller, 3 is a robot walking ground rail, 4 is a mechanical arm, 5 is a sensor, 6 is a welding workpiece, 7 is a robot mounting base, 8 is a laser observation plane, 9 is a robot mounting rail, 10 is a welding seam circle, 11 is a laser line, and 12 is a welding seam bottom surface.
Detailed description of the preferred embodiments
In order to make the technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to specific embodiments and accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
As shown in fig. 1 to 2, an embodiment of the present invention provides a circular hole automatic plug welding device based on laser vision, including: the welding gun and the sensor are arranged on the mechanical arm. The sensor includes: the laser device is used for emitting line laser to irradiate on a welding workpiece and scan a circular welding hole in the welding workpiece, the camera is used for shooting a laser image of the welding workpiece and sending the laser image to the welding seam processor, and the welding seam processor is used for converting a two-dimensional coordinate of the laser image into a three-dimensional coordinate of a circular welding seam and sending the three-dimensional coordinate to the mechanical arm controller; the mechanical arm controller is used for controlling the mechanical arm to drive the welding gun and the sensor to act, calculating the circle center and the volume of a welding seam circle, and controlling the welding position and the welding time of the welding gun according to the circle center coordinate and the volume of the circular welding seam.
Specifically, as shown in fig. 2, the circular hole automatic plug welding device based on laser vision of the embodiment further includes a welding gun controller, and the welding gun controller is used for supplying current and voltage to a welding gun.
Specifically, in this embodiment, the arm is six robots, and it can realize accurate location, and then improves welding quality.
Example two
As shown in fig. 3, a second embodiment of the present invention provides an automatic plug welding method for a circular hole based on laser vision, which uses an automatic plug welding device for a circular hole based on laser vision according to an embodiment, and includes the following steps:
and S1, manually inputting the coordinates of the starting point and the coordinates of the end point.
The robot enters a manual teaching mode, and a starting point coordinate and an end point coordinate are input.
And S2, driving the welding gun and the sensor to move to the position of the start point coordinate by the mechanical arm, and advancing towards the end point direction.
After the welding gun runs to the position of the starting point coordinate, the laser in the sensor emits laser, the camera shoots laser images, the mechanical arm drives the sensor to advance towards the end point direction, and the camera can shoot multi-frame images.
And S3, after passing through a round hole, calculating to obtain the welding seam circular coordinate and the circle center position through the laser image collected by the camera, and recording the current position.
In step S3, the method for determining the weld circle coordinate specifically includes:
s301, extracting a current frame image acquired by a camera, and performing feature extraction on the image through a gray threshold to obtain feature points;
s302, fitting the extracted characteristic points into a straight line by a least square method, and taking a point close to an end point on the fitted straight line as a circular coordinate of the welding line;
and S303, repeating the operations of the steps S301 and S302 on each frame of image collected by the camera to obtain all coordinates on the weld circle.
In this embodiment, a laser image captured by a camera in the sensor 5 is in a raw format, each frame is a raw image, an abscissa x, an ordinate y, and a gray value corresponding to each pixel of the image are stored in the raw image, a threshold is set, a point of the gray value greater than the threshold is a point on a laser line, and points extracted on the laser line are shown in fig. 4, where the point is an extracted point, and x is an end point of a fitted straight line close to a circular hole.
Specifically, a straight line y ═ ax + b is fitted to the extracted points by using a least square method, wherein x and y are horizontal axis coordinates, and a and b are fitting coefficients, namely, a data set of points on a series of laser lines is givenLet D { (x)1,y1),(x2,y2),(x3,y3),...,(xn,yn) H, so that the f (x) function fits D as closely as possible. The key to the principle and idea of the least squares fit function f (x) is that the sum of squared differences is minimal, i.e. the Q value is minimal:
Q=(ax1+b-y1)2+(ax2+b-y2)2+...+(axn+b-yn)2; (1)
Figure BDA0003380790680000051
because (x)1,y1),(x2,y2),(x3,y3),...,(xn,yn) All are known variables, the problem is transformed to solve for the minimum of Q ═ f (a, b), i.e. to solve for the point (a, b), making the value of f (a, b) extremely small, using the partial derivative to solve for the value of f (a, b) extremely small:
Figure BDA0003380790680000052
Figure BDA0003380790680000053
after the arrangement is simplified, the formula of the values a and b is as follows:
Figure BDA0003380790680000054
Figure BDA0003380790680000055
wherein,
Figure BDA0003380790680000056
is xi、yiThe arithmetic mean, i.e.:
Figure BDA0003380790680000057
Figure BDA0003380790680000058
and (3) bringing the a and the b into a fitting straight line y which is ax + b to obtain the fitting straight line, and selecting the end point on the fitting straight line close to the round hole as a point on the circular hole of the welding seam, as shown in fig. 4, wherein x is the end point of the fitting straight line close to the round hole. After the circle corresponding to the welding seam of the whole round hole is scanned, all points on the welding seam circle can be obtained by n pairs of laser lines in the multi-frame image.
Specifically, in this embodiment, a plurality of straight lines are obtained by fitting the laser lines on each frame of image for a plurality of times, and then the corresponding end points are obtained.
As shown in fig. 5, which is a laser image obtained from one frame image, the upper two "x" in the figure are points on the weld circle, and the lower two "x" are points on the circle of the weld bottom surface. As shown in fig. 6, in order to obtain a laser image by combining images of a plurality of frames, the "x" of the outer ring is a set of points on the bead circle, and the "x" of the inner ring indicates a set of points on the circle of the bead bottom surface.
In step S3, the method for determining the position of the circle center specifically includes:
s304, obtaining a matrix P of coordinates of the upper point of the circular hole weld joint under a camera coordinate systemcameraConverting the coordinates of the welding point under the camera coordinate system into the coordinates P under the robot coordinate systemrobotThe conversion formula is:
Figure BDA0003380790680000061
wherein,
Figure BDA0003380790680000062
calibrating a matrix for the hand and the eye; the hand-eye calibration matrix
Figure BDA0003380790680000063
The calculation formula of (2) is as follows:
Figure BDA0003380790680000064
wherein,
Figure BDA0003380790680000065
a transformation matrix, P, representing the robot end to base coordinate systembaseCoordinates representing points on the calibration plate in the robot coordinate system, P1 cameraAnd 3D coordinates representing the corresponding points on the calibration plate obtained by the 3D camera.
Because the camera is fixed at the tail end of the mechanical arm, the relation between a camera coordinate system and the tail end coordinate system of the mechanical arm is fixed at the moment, the transformation relation between the camera coordinate system and the base coordinate system changes constantly, and the quantity to be solved at the moment is a transformation matrix from the camera coordinate system camera to the tail end coordinate system end of the mechanical arm
Figure BDA0003380790680000066
From the relationship of the respective coordinate systems, the following coordinate system transformation equations can be listed:
Figure BDA0003380790680000067
wherein P isbaseRepresenting the coordinate from the point fixed on the welding plate at a certain position to the coordinate system of the robot base, and directly obtaining the corresponding 3D coordinate P by calculating the coordinate through a 3D camera arranged at the tail end of the mechanical arm1 cameraPlus a transformation matrix from the robot end to the base coordinate system
Figure BDA0003380790680000068
And a transformation matrix from the camera coordinate system to the robot end coordinate system
Figure BDA0003380790680000069
Then canTo find the coordinate P of the point on the calibration plate in the robot coordinate systembase. Conversion matrix from camera coordinate system to robot end coordinate system
Figure BDA00033807906800000610
The hand-eye calibration matrix is the hand-eye calibration matrix which needs to be obtained, so that the hand-eye calibration matrix shown in the formula (10) can be obtained.
S305, fitting a circle center coordinate (x) through the coordinates of the welding line points by using a least square methodc,yc)。
Specifically, in this embodiment, the weld seam actuator fits the coordinates of the center of the circle according to the coordinates of the identified points on the circular weld seam, and there are a series of weld seam circular coordinate data points { x }i、yiIn (x-x), the equation of a circle can be written as (x-x)c)2+(y-yc)=R2The least squares fit requires the sum of the squares of the distances to be minimal, i.e.: f ═ Σ ((x)i-xc)2+(yi-yc)2-R2)2And minimum. (x)i,yi) Coordinates of the ith data point on the round hole weld are shown.
Defining an auxiliary function:
g(x,y)=(x-xc)2+(y-yc)2-R2; (12)
the above equation can be expressed as: f ═ Σ g (x)i,yi)2According to the least square method, it is found that the following condition is satisfied when f takes an extremum.
Figure BDA0003380790680000071
Firstly, simplification:
Figure BDA0003380790680000072
the radius R cannot be 0, so that Σ g (x) must be presenti,yi) 0, leaving two of the formulaeA step of:
Figure BDA0003380790680000073
Figure BDA0003380790680000074
namely the following two equations:
Figure BDA0003380790680000075
here, it is assumed that:
Figure BDA0003380790680000081
the simple equation defines several parameters:
Figure BDA0003380790680000082
the above equation can be written as:
Figure BDA0003380790680000083
can solve ucAnd vcIt is used.
Figure BDA0003380790680000084
Then the position of the circle center is:
Figure BDA0003380790680000085
the weld radius R can be obtained by the simultaneous equation:
∑g(xi,yi)=0; (23)
∑((xi-xc)2+(yi-yc)2-R2)=0; (24)
obtaining:
Figure BDA0003380790680000086
wherein (x)c,yc) Represents the coordinates of the circle center of the circular hole weld joint, (x)i,yi) Coordinates of the ith data point on the circular hole weld joint are represented, and N represents the number of coordinate points
And S4, driving the welding gun to move to the position of the circle center through the mechanical arm, and carrying out wire feeding welding.
In step S4, when wire feeding welding is performed, the welding time is:
Figure BDA0003380790680000091
wherein V represents the volume of the circular hole weld, d represents the diameter of the welding wire, and V represents the wire feeding speed.
The calculation formula of the volume of the circular hole welding seam is as follows:
V=πR2h; (27)
wherein R represents the radius of the circular hole welding seam, h represents the height of the circular hole welding seam, and the circular hole welding seam is obtained by taking the center of the circular hole welding seam as a perpendicular line of the bottom surface. As shown in fig. 7, the center of the circular hole weld is taken, and a perpendicular line is made to the bottom surface of the weld, and the length of the perpendicular line is the height of the volume. Specifically, in this embodiment, after the two-dimensional coordinates of the end points in the multi-frame image shown in fig. 6 are obtained and converted into the three-dimensional coordinates through the hand-eye calibration matrix, the three-dimensional coordinates of the center of the weld circle and the three-dimensional coordinates of the center of the bottom surface of the weld circle can be obtained through fitting, and the height of the weld can be obtained through judgment according to the distance between the two coordinates. Furthermore, the weld height can also be directly acquired by other means, for example, by a 3D camera.
S5, after welding, driving the welding gun to move to the recorded position through the mechanical arm;
and S6, driving the welding gun to move forward to the terminal direction again through the mechanical arm, and repeating the steps S3-S5 until the welding gun moves to the terminal coordinate position, so that the welding is finished.
Specifically, in the present embodiment, there is no fixed correspondence between the wire feed speed and the welding current, and as shown in fig. 8, they are positively correlated, that is, the welding current is increased as the wire feed speed is increased. Through experimental measurement, the wire feeding speed and the welding current of the welding wire with the diameter of 1.2mm meet the formula: -0.5741x3+9.7568x2-13.8951x +185.43, wherein x is the wire feed speed in m/min, y is the welding current in a, and the formula of the welding voltage and the welding current is: welding voltage is welding current x 0.05+ 14.
In summary, the invention provides a round hole automatic plug welding method and device based on laser vision, which adopts a sensor comprising a camera and a line laser as a guide to ensure high precision of weld detection; the welding parameters of each welding line are constant, the quality of the welding line is less influenced by human factors, and the requirements on the operation technology of workers are reduced. In addition, the six-axis robot system is adopted for accurate positioning, the welding effect is stable, and the whole process is more intelligent; the technology reduces the labor intensity of workers and improves the working environment. The device has the advantages of simple structure, convenient operation and low cost, can meet the plug welding requirements of different circular holes, and can effectively improve the welding efficiency. The overall algorithm has small calculated amount, short running time, fast identification result acquisition, computer resource saving, low cost, high transportability and strong practicability.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. The utility model provides an automatic plug welding device of round hole based on laser vision which characterized in that includes: the welding gun and the sensor are arranged on the mechanical arm;
the sensor includes: the laser device is used for emitting line laser to irradiate on a welding workpiece and scan a circular welding hole in the welding workpiece, the camera is used for shooting a laser image of the welding workpiece and sending the laser image to the welding seam processor, and the welding seam processor is used for converting a two-dimensional coordinate of the laser image into a three-dimensional coordinate of a circular welding seam and sending the three-dimensional coordinate to the mechanical arm controller;
the mechanical arm controller is used for controlling the mechanical arm to drive the welding gun and the sensor to act, calculating the circle center and the volume of a welding seam circle, and controlling the welding position and the welding time of the welding gun according to the circle center coordinate and the volume of the circular welding seam.
2. The automatic round hole plug welding device based on the laser vision is characterized by further comprising a welding gun controller, wherein the welding gun controller is used for supplying current and voltage to a welding gun.
3. The round hole automatic plug welding method based on the laser vision adopts the round hole automatic plug welding device based on the laser vision according to claim 1, and is characterized by comprising the following steps of:
s1, manually inputting a start point coordinate and an end point coordinate;
s2, driving the welding gun and the sensor to move to the position of the start point coordinate by the mechanical arm and move forward in the end point direction;
s3, after passing through a round hole, calculating to obtain the welding seam circular coordinate and the circle center position through the laser image collected by the camera, and recording the current position;
s4, driving the welding gun to move to the position of the circle center through the mechanical arm, and carrying out wire feeding welding;
s5, after welding, driving the welding gun to move to the recorded position through the mechanical arm;
and S6, driving the welding gun to move forward to the terminal direction again through the mechanical arm, and repeating the steps S3-S5 until the welding gun moves to the terminal coordinate position, so that the welding is finished.
4. The circular hole automatic plug welding method based on laser vision according to claim 3, characterized in that in step S3, the method for determining the circular coordinates of the weld is specifically as follows:
s301, extracting a current frame image acquired by a camera, and performing feature extraction on the image through a gray threshold to obtain feature points;
s302, fitting the extracted characteristic points into a straight line by a least square method, and taking a point close to an end point on the fitted straight line as a circular coordinate of the welding line;
and S303, repeating the operations of the steps S301 and S302 on each frame of image collected by the camera to obtain all coordinates on the weld circle.
5. The method for automatically plug-welding the circular hole based on the laser vision as claimed in claim 3, wherein in the step S3, the method for determining the position of the circle center is specifically as follows:
s304, obtaining a matrix P of coordinates of the upper point of the circular hole weld joint under a camera coordinate systemcameraConverting the coordinates of the welding point under the camera coordinate system into the coordinates P under the robot coordinate systemrobotThe conversion formula is:
Figure FDA0003380790670000021
wherein,
Figure FDA0003380790670000022
calibrating a matrix for the hand and the eye;
and S305, fitting a circle center coordinate (xc, yc) by using a least square method through the weld point coordinate.
6. The automatic plug welding method for round holes based on laser vision according to claim 5, wherein in step S3, the hand-eye calibration matrix
Figure FDA0003380790670000023
The calculation formula of (2) is as follows:
Figure FDA0003380790670000024
wherein,
Figure FDA0003380790670000025
a transformation matrix, P, representing the coordinate system of the camera to the coordinate system of the end of the robot armbaseCoordinates representing points on the calibration plate in the robot coordinate system, P1 cameraAnd 3D coordinates representing the corresponding points on the calibration plate obtained by the 3D camera.
7. The automatic plug welding method for round holes based on the laser vision as claimed in claim 6, characterized by further comprising the step of obtaining a hand-eye calibration matrix.
8. The method for automatically plug-welding round holes based on laser vision according to claim 3, wherein in step S4, the welding time during wire feeding welding is:
Figure FDA0003380790670000026
wherein V represents the volume of the circular hole weld, d represents the diameter of the welding wire, and V represents the wire feeding speed.
9. The automatic plug welding method for the round hole based on the laser vision is characterized in that the calculation formula of the volume of the round hole welding seam is as follows:
V=πR2h;
wherein R represents the radius of the circular hole welding seam, and h represents the height of the circular hole welding seam;
the calculation formula of the radius of the circular hole welding seam is as follows:
Figure FDA0003380790670000027
wherein (x)c,yc) Represents the coordinates of the circle center of the circular hole weld joint, (x)i,yi) And the coordinates of the ith data point on the circular hole weld joint are shown, and N represents the number of coordinate points.
10. The round hole automatic plug welding method based on the laser vision is characterized in that the method for determining the height of the round hole weld seam is as follows: and after converting the point coordinates on the welding seam circle and the point coordinates on the bottom surface of the welding seam circle into three-dimensional coordinates, fitting to obtain the three-dimensional coordinates of the circle center of the welding seam circle and the three-dimensional coordinates of the circle center of the bottom surface of the welding seam circle, and obtaining the height of the welding seam through the distance between the two coordinates.
CN202111432473.5A 2021-11-29 2021-11-29 Round hole automatic plug welding method and device based on laser vision Active CN114043045B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111432473.5A CN114043045B (en) 2021-11-29 2021-11-29 Round hole automatic plug welding method and device based on laser vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111432473.5A CN114043045B (en) 2021-11-29 2021-11-29 Round hole automatic plug welding method and device based on laser vision

Publications (2)

Publication Number Publication Date
CN114043045A true CN114043045A (en) 2022-02-15
CN114043045B CN114043045B (en) 2023-04-11

Family

ID=80211522

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111432473.5A Active CN114043045B (en) 2021-11-29 2021-11-29 Round hole automatic plug welding method and device based on laser vision

Country Status (1)

Country Link
CN (1) CN114043045B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114571154A (en) * 2022-04-13 2022-06-03 天津科技大学 Tube plate welding method and device
CN115780984A (en) * 2023-01-31 2023-03-14 无锡市振华汽车部件股份有限公司 Multi-point positioning method and positioning assembly for projection welding machine
CN116175256A (en) * 2023-04-04 2023-05-30 杭州纳志机器人科技有限公司 Automatic positioning method for loading and unloading of trolley type robot

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20180115646A (en) * 2017-04-13 2018-10-23 재단법인 경북아이티융합 산업기술원 Bead recognition apparatus using vision camera and method thereof
CN109215000A (en) * 2018-08-03 2019-01-15 武汉工程大学 A kind of weld beam shape method and system
CN109658456A (en) * 2018-10-29 2019-04-19 中国化学工程第六建设有限公司 Tank body inside fillet laser visual vision positioning method
CN110508906A (en) * 2019-08-30 2019-11-29 上海发那科机器人有限公司 A kind of method that robotic laser displacement sensor seeks position
CN110576242A (en) * 2019-08-29 2019-12-17 成都长客新筑轨道交通装备有限公司 Numerical control welding method for gap automatic compensation filling
CN112917035A (en) * 2021-01-27 2021-06-08 安徽中科春谷激光产业技术研究院有限公司 Automatic assembly welding device and method for embedded part
CN112959329A (en) * 2021-04-06 2021-06-15 南京航空航天大学 Intelligent control welding system based on vision measurement
CN113160162A (en) * 2021-04-14 2021-07-23 深圳远荣智能制造股份有限公司 Hole recognition method and device applied to workpiece and hole processing equipment

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20180115646A (en) * 2017-04-13 2018-10-23 재단법인 경북아이티융합 산업기술원 Bead recognition apparatus using vision camera and method thereof
CN109215000A (en) * 2018-08-03 2019-01-15 武汉工程大学 A kind of weld beam shape method and system
CN109658456A (en) * 2018-10-29 2019-04-19 中国化学工程第六建设有限公司 Tank body inside fillet laser visual vision positioning method
CN110576242A (en) * 2019-08-29 2019-12-17 成都长客新筑轨道交通装备有限公司 Numerical control welding method for gap automatic compensation filling
CN110508906A (en) * 2019-08-30 2019-11-29 上海发那科机器人有限公司 A kind of method that robotic laser displacement sensor seeks position
CN112917035A (en) * 2021-01-27 2021-06-08 安徽中科春谷激光产业技术研究院有限公司 Automatic assembly welding device and method for embedded part
CN112959329A (en) * 2021-04-06 2021-06-15 南京航空航天大学 Intelligent control welding system based on vision measurement
CN113160162A (en) * 2021-04-14 2021-07-23 深圳远荣智能制造股份有限公司 Hole recognition method and device applied to workpiece and hole processing equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
修延飞等: "一种用于穿孔塞焊焊缝特征提取的视觉识别算法", 《焊接学报》 *
张国强: "坡口及焊缝表面三维轮廓的激光视觉表征", 《中国硕士论文全文数据库》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114571154A (en) * 2022-04-13 2022-06-03 天津科技大学 Tube plate welding method and device
CN114571154B (en) * 2022-04-13 2024-04-12 天津科技大学 Tube plate welding method and device
CN115780984A (en) * 2023-01-31 2023-03-14 无锡市振华汽车部件股份有限公司 Multi-point positioning method and positioning assembly for projection welding machine
CN116175256A (en) * 2023-04-04 2023-05-30 杭州纳志机器人科技有限公司 Automatic positioning method for loading and unloading of trolley type robot
CN116175256B (en) * 2023-04-04 2024-04-30 杭州纳志机器人科技有限公司 Automatic positioning method for loading and unloading of trolley type robot

Also Published As

Publication number Publication date
CN114043045B (en) 2023-04-11

Similar Documents

Publication Publication Date Title
CN114043045B (en) Round hole automatic plug welding method and device based on laser vision
CN111618396B (en) Multilayer multi-channel welding device and welding method based on visual characterization
CN110524580B (en) Welding robot vision assembly and measuring method thereof
CN112122840B (en) Visual positioning welding system and welding method based on robot welding
CN113333998B (en) Automatic welding system and method based on cooperative robot
CN110102855A (en) A kind of robot automtion welding system, device and method
CN108856978B (en) Angle joint penetration control method based on near-infrared binocular vision recognition
CN114012210B (en) Deposition quality judgment system and method in electric arc additive process
CN111192307A (en) Self-adaptive deviation rectifying method based on laser cutting of three-dimensional part
CN112958959A (en) Automatic welding and detection method based on three-dimensional vision
CN110449783B (en) Robot welding device and method for acquiring welding seam track
CN110681945A (en) Welding height control method and device for full-automatic tube plate welding
CN117047237B (en) Intelligent flexible welding system and method for special-shaped parts
CN113223071B (en) Workpiece weld joint positioning method based on point cloud reconstruction
CN111687515A (en) Intelligent welding guide system for large steel structure
CN207077080U (en) Weld Seam Tracking Control device based on cross laser
CN210677336U (en) Welding seam track automatic identification device based on vision technology
CN209632369U (en) A kind of welding system of ship group Vertical board support structure
CN113385869B (en) Robot welding equipment for large square lattice component based on machine vision and welding seam positioning method
CN109746603A (en) A kind of welding system of ship group Vertical board support structure
CN108857130A (en) A kind of ship universal structural member 3-D positioning method based on the processing of image framing bit
CN112355438A (en) Automatic robot welding process for container corrugated welding
CN109048148A (en) Based on binocular vision root face identification model and the adaptive welding method of robot
CN113664431A (en) Steel structural part welding arm capable of adjusting posture in real time and adjusting method
CN115533380B (en) Weld defect identification and automatic repair welding method

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