CN115464263B - Laser welding seam automatic tracing method, detection method and device - Google Patents

Laser welding seam automatic tracing method, detection method and device

Info

Publication number
CN115464263B
CN115464263B CN202211155049.5A CN202211155049A CN115464263B CN 115464263 B CN115464263 B CN 115464263B CN 202211155049 A CN202211155049 A CN 202211155049A CN 115464263 B CN115464263 B CN 115464263B
Authority
CN
China
Prior art keywords
robot
coordinate system
laser
weld
line
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.)
Active
Application number
CN202211155049.5A
Other languages
Chinese (zh)
Other versions
CN115464263A (en
Inventor
李志强
赵福龙
柯学
左从进
王莉
刘欣
李超
马旭颐
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.)
AVIC Manufacturing Technology Institute
Original Assignee
AVIC Beijing Aeronautical Manufacturing Technology Research Institute
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 AVIC Beijing Aeronautical Manufacturing Technology Research Institute filed Critical AVIC Beijing Aeronautical Manufacturing Technology Research Institute
Priority to CN202211155049.5A priority Critical patent/CN115464263B/en
Publication of CN115464263A publication Critical patent/CN115464263A/en
Application granted granted Critical
Publication of CN115464263B publication Critical patent/CN115464263B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00—Working by laser beam, e.g. welding, cutting or boring
    • B23K26/20—Bonding
    • B23K26/21—Bonding by 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
    • B23K26/00—Working by laser beam, e.g. welding, cutting or boring
    • B23K26/70—Auxiliary operations or equipment
    • B23K26/702—Auxiliary equipment
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Plasma & Fusion (AREA)
  • Robotics (AREA)
  • Laser Beam Processing (AREA)

Abstract

The invention relates to an automatic tracking method of a laser welding seam, which comprises the steps of installing a focus tool, fixing a tool tip tool, determining a reference point of the focus tool and a fixed point of the tool tip tool, establishing a laser welding gun focus coordinate system by adopting a four-point method, establishing a robot base coordinate system by taking an installation base of a robot as a reference, determining a coordinate relation between the robot base coordinate system and the laser welding gun focus coordinate system according to a pose matrix of the robot base coordinate system, scanning the edges of a rib plate to obtain a surface profile image of a to-be-welded test piece, extracting welding seam characteristic points of two side edges of a laser belt from the obtained surface profile image of the to-be-welded test piece, fitting the welding seam characteristic points of two side edges into a first line segment and a second line segment respectively, and solving the intersection point of the first line segment and the second line segment to obtain a central track coordinate of the welding seam.

Description

Automatic tracking method, detection method and device for laser welding seam
Technical Field
The invention belongs to the technical field of automatic laser welding processing of complex space curved thin-wall structural parts, and particularly relates to an automatic tracking method, an automatic detection method and an automatic detection device for a laser welding seam.
Background
The welding method is characterized in that a T-shaped welding seam structure is generally adopted in aviation, automobile and other rib wall boards, the T-shaped welding seam is welded from the left side and the right side by adopting a double-beam laser welding mode, the development speed and the application popularization of laser welding in the industries are directly influenced by the laser welding quality and efficiency of the T-shaped welding seam structure, the robot double-beam laser welding is one of main production and processing modes of titanium alloy assemblies, riveting and spot welding cannot be used for meeting stealth and light weight requirements, the consistency of welding seams to be welded is poor due to workpiece thermoforming deformation, rib plate processing errors and clamping errors, an offline programming track cannot be directly used for welding, each welding seam needs manual teaching calibration, the consistency of manual teaching welding quality is poor, the efficiency is low, the welding seam is not suitable for the rapid development of new-generation aircraft in China, and the production quality and the efficiency of the titanium alloy assemblies of the aircraft in China are seriously influenced.
The aviation titanium alloy complex space curved surface thin-wall structural member is high in laser welding difficulty, firstly, a welding space is narrow, rib plates are crisscrossed vertically and horizontally, the space curved surface is complex in shape, a measuring device needs to be measured remotely and does not interfere with a tool and a workpiece, the precision of the measuring device is reduced along with the increase of the measuring range of the measuring device, the laser welding requirement precision is very high, the welding line quality reaches level I, the deviation of the center of the welding line is not more than +/-0.1 mm, therefore, the system requires that the measuring device is small and compact in size structure, and meanwhile, higher measuring precision is ensured, secondly, the titanium alloy wall plates are subjected to laser cleaning before being welded, reinforcing ribs are vertically assembled on a bottom plate, the effect similar to the vertical arrangement of two mirror surfaces is achieved, multiple reflections are easy to be generated during the measurement of a sensor, and the measuring precision is seriously affected.
The general structural light sensor is large in attenuation of measurement precision along with the increase of measurement vision and measurement distance, so that the process requirement cannot be met, and the structural laser sensor with a small vision cannot meet the welding accessibility and the measurement vision requirement of the T-shaped joint of the titanium alloy laser welding. In addition, the laser welding speed reaches 6-12 m/min, the dynamic tracking speed of the robot welding seam measuring system is low, the welding track is dynamically adjusted, the welding forming track quality is poor, and the process requirements cannot be met.
In the aspect of weld joint detection after welding, the requirement of the double-beam welding weld joint meets the standard of the navigation mark I grade weld joint, and mainly comprises the requirements of the internal quality, the mechanical property and the appearance of the weld joint, wherein the main detection means of the internal defects of the weld joint are X-ray flaw detection, common defects are cracks, incomplete welding, unfused, air holes, slag inclusion and the like, the mechanical property mainly adopts a tensile experiment method, the tensile strength and the shearing strength are required to meet the technical requirements, the appearance quality requirement is met, the weld joint is evenly transited, the arc starting and arc receiving positions have no defects of pits, weld tumors, undercut and the like, and the height difference of welding feet is less than or equal to 0.3mm. Appearance quality is an important evaluation standard of the quality of the double-beam welding process, currently, the defects of the surface are mainly checked by manual visual arrangement, and the height difference of the welding leg is measured by adopting a metallographic method. The metallographic method is low in efficiency and can not detect actually welded workpieces, and the metallographic test piece is manufactured by cutting the T-shaped welding seam when the height of the welding leg is measured.
Disclosure of Invention
The invention mainly aims at the problems and provides an automatic tracking method, an automatic detection method and an automatic detection device for a laser welding seam, which replace manual teaching, automatically complete welding seam welding and post-welding detection and greatly improve welding efficiency and quality stability.
In order to achieve the above purpose, the invention provides an automatic tracking method for a laser welding seam, which comprises the following steps:
Step 1, installing a focus tool at the tail end of a laser welding gun, determining a reference point of the focus tool, fixing a tool nose tool on a workbench, determining a fixed point of the tool nose tool, enabling the reference point to be just contacted with the fixed point by adopting a four-point method, and establishing a focus coordinate system of the laser welding gun through data of four position points;
Step 2, a robot base coordinate system is established by taking a mounting base of a line laser sensor mounted on a robot as a reference, and a coordinate relation between the robot base coordinate system and a laser welding gun focus coordinate system is determined according to a pose matrix of the robot base coordinate system;
step 3, the robot drives the line laser sensor to move along the position to be welded of the test piece to be welded, scans the edge of the rib plate to obtain the surface profile image of the test piece to be welded,
Step 4, extracting weld characteristic points of two side edges of a laser belt from the obtained surface profile image of the test piece to be welded, respectively making a first line segment and a second line segment for the weld characteristic points of the two side edges, and taking the first line segment and the second line segment as weld characteristics;
and 5, fitting the first line segment and the second line segment of the weld joint characteristic, and solving the intersection point to obtain the weld joint center track coordinate.
Further, in step 1, the calibration process for establishing the focal coordinate system of the laser welding gun is as follows:
Manually operating the robot to enable the laser welding gun to move from four different directions to a fixed point, recording four points P 1、P2、P3、P4, recording position and posture data (X, Y, Z, theta 1、θ2、θ3) of a flange at the tail end of the robot, enabling coordinates of the four tool center points to be equal in a world coordinate system, and completing calculation on an operation demonstrator to obtain a tool coordinate system TCP (X, Y, Z);
and (3) carrying out gesture calibration on the tool coordinate system, namely moving the tool coordinate system TCP to any fixed point for measurement, moving one point in the negative direction of the Y axis to the fixed point for measurement, then moving any point with the X of a negative value in the XY plane to the fixed point for measurement, recording data, and completing calculation calibration on an operation demonstrator.
Further, in step 2, the step of determining a coordinate relationship between the robot base coordinate system and the laser welding gun focal point coordinate system includes:
when the robot is in a certain pose, the pose matrix of the welding seam welding end effector relative to the robot base coordinate is T 1, the pose matrix from the line sensor coordinate system to the end flange is X 1, the pose of the world coordinate system under the robot base coordinate system is P 1＝T1X1M1, when the robot moves to another pose, the parameters are changed into T 2、X2、P2, because the line sensor is fixed on the end, X 1＝X2, and because the world coordinate system and the end coordinate system are static, P 1＝P2, the welding seam welding end effector has the following functions There is ax=xb,
Let A be an m n matrix, B be an n matrix, X be an m n matrix, it can be seen from the matrix direct product definition:
when A or B is an identity matrix, there are
If a and b are constant, there are,
vec(aA+bB)=a×vec(A)+b×vec(B)
Assume that
Ax=xb can be expressed as:
To determine the unique solution of the above equation, two sets of rotation axis non-parallel motions are required, and the simultaneous equations for these two sets of motions are:
And solving a feature vector v= [ v 1v2…v13 ] corresponding to the minimum singular value by using a least square method, wherein the relation matrix is as follows:
Further, the step 3 includes forming an included angle of about 45 degrees between the YZ plane of the laser welding gun and the vertical face of the rib plate, setting a plurality of points S 0、S1……、Sn、Sn+1 on the to-be-welded test piece, enabling the robot to drive the line laser sensor to scan along the sequence of S 0、S1……、Sn、Sn+1, sending a pulsation command to the line laser sensor at the point S 0 by the PLC, triggering data acquisition, sending line structure laser by the three-dimensional line structure laser vision system, and scanning the edge of the rib plate to obtain the surface profile image of the to-be-welded test piece.
In step 4, before the first line segment and the second line segment are respectively made on the weld feature points at the two side edges, filtering processing is further performed on the weld feature points.
Further, in step 5, the step of fitting the first line segment and the second line segment of the weld feature, and solving the intersection point to obtain the weld center track coordinate includes:
according to the known fitting function of the weld characteristic points, the square of the distances from all the weld characteristic points to the straight line is minimized, and the square sum of errors from the weld characteristic points to the straight line is calculated, namely:
Wherein k and b are equation coefficients, z i、xi is acquired coordinate data to be solved, and k and b are respectively derived to obtain:
Order the The method comprises the following steps:
Wherein A, B is a weld characteristic point in a first line segment, C, D is a weld characteristic point in a second line segment, z 1＝k1x+b1 and z 2＝k2x+b2 of the first line segment can be determined, an intersection point X A,ZA can be obtained by the two line segments, and an actual weld center track coordinate can be obtained by performing linear interpolation on all sampling points.
Further, after step 5, the method further comprises correcting the welding track based on the coordinates of the welding seam center track.
The invention provides a laser welding seam detection method for achieving the purpose, which comprises the steps of collecting laser welding seam fringe images after welding the surfaces of test pieces to be welded, preprocessing the laser welding seam fringe images, and extracting key points of the preprocessed laser welding seam fringe images, wherein the step of extracting the key points of the laser welding seam fringe images comprises the following steps:
Extracting a welding seam contour curve, dividing an interested region of the original data, and setting a welding seam detection starting point A and a welding seam detection end point D;
Traversing all welding line contour feature data points in the divided interested area, finding out the corresponding abscissa of the highest point E of the arc line in the laser two-dimensional coordinates, searching in the direction of the ordinate or the abscissa respectively by taking the point as a reference until a welding line key feature inflection point B and a welding line key feature inflection point C which are zero in distance from the bottom plate and the vertical plate are found out, and marking the coordinates of the point;
fitting line segments AB and CD by using a least square method, wherein an intersection point O of the two line segments is used as a welding seam center, calculating a welding leg height difference I OB-OC I, judging whether the welding leg height difference I OB-OC I is smaller than or equal to a preset value, and judging that the welding seam is unqualified when a threshold value is exceeded.
Further, the preprocessing step further comprises the steps of graying treatment, noise reduction, binarization, image enhancement and key region extraction of the graph.
The device comprises a robot moving device, a robot, a welding seam testing end effector, a working platform and a laser, wherein the robot moving device is arranged on two sides of the working platform and is installed on a sliding table of the robot moving device, the welding seam testing end effector is installed on an end flange of the robot, and the welding seam testing end effector at least comprises a line laser sensor, a wire feeding device, a laser welding gun and a CCD module which are integrated into a whole.
The technical scheme of the invention has the following advantages:
and emitting line structure laser through a three-dimensional line structure laser vision system, scanning the surface of the workpiece to be detected to obtain a surface profile image of the workpiece to be detected, processing the surface profile image by an image filter and a data acquisition card to obtain three-dimensional point cloud coordinates of the surface of the workpiece to be detected, automatically calculating and analyzing center coordinates of a welding seam of the workpiece to be welded by a system, scanning a welding path by a robot driving sensor, automatically calculating actual welding seam track coordinates by the system, obtaining tool coordinate positions of an end effector of the robot through matrix transformation, and automatically correcting the movement track of the robot. And scanning the welded seam by a sensor after welding, automatically identifying the welded seam, calculating the height of a welding leg, analyzing the common appearance quality and providing a basis for workpiece detection.
Drawings
FIG. 1 is a general block diagram of an apparatus for an automatic laser weld seam tracking method in accordance with the present disclosure.
FIG. 2 is a three-dimensional view of a weld testing end effector of the present disclosure.
FIG. 3 is an elevation view of a weld testing end effector of the present disclosure.
FIG. 4 is a side view of a weld testing end effector of the present disclosure.
Fig. 5 is a schematic diagram of a welding direction measurement according to the present disclosure.
FIG. 6 is a schematic diagram of a sensor measurement of the present disclosure.
FIG. 7 is a flow chart of a method for weld trace detection and post-weld topography detection according to the present disclosure.
Fig. 8 is a diagram of a torch focus TCP setup in accordance with the present disclosure.
Fig. 9 is a schematic diagram of a TCP calibration of a welding gun according to the present disclosure.
FIG. 10 is a schematic diagram of TCF calibration according to the present disclosure.
FIG. 11 is a sample scanning spot of a test piece according to the present disclosure.
FIG. 12 is a schematic cross-sectional view of a T-shaped weld of the present disclosure.
FIG. 13 is a schematic view of the morphology of a post-weld bead of the present disclosure.
In the figure, a moving device of a robot 001, a control cabinet of the robot, a dust removing cabinet 004, a robot 005, a wire feeder 006, a working platform 007, a water cooling machine 008, a laser, 009, a ribbed wallboard workpiece 010, a control console 100, a welding seam welding end effector 101, a line laser sensor 102, a sensor fixing seat 103, a wire feeder 104, a connecting flange 105, an adapter flange 106, a coaxial shielding gas sleeve, 107, a wire feeder 108, a wire feeder pipe 109, a laser welding gun 110, a base 111, a CCD module 112, a wire feeding fixing plate 200, a base plate 201, a vertical plate 202, a tool pressing plate I203 and a tool pressing plate II.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, unless explicitly stated or limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected, mechanically connected, electrically connected, directly connected, indirectly connected via an intervening medium, or in communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Referring to fig. 1, an assembly structure of an apparatus for an automatic tracking method for a laser welding seam according to a preferred embodiment of the application is shown.
Referring to fig. 1, fig. 1 is a schematic diagram of an assembly structure of a device for an automatic tracking method of a laser welding seam according to one embodiment of the present application.
In the embodiment shown in fig. 1, the assembly structure mainly comprises two sets of welding seam testing end effectors 100, two sets of robots 004 (being six-degree-of-freedom robots), two sets of robot moving devices 001, a robot control cabinet 002, a dust removing cabinet 003, a working platform 006, a laser 008, a water cooling machine 007, a control cabinet 010, measurement and control analysis software and the like (see fig. 1). The working platform 007 is arranged in the middle of the system, the working platform 006 is fixed with the ground foundation through expansion bolts and is used for installing welding tools and workpieces, two sets of robot moving devices 001 are symmetrically arranged at two sides of the working platform 007, two sets of robots 004 are respectively installed on sliding tables of the two sets of robot moving devices 001, the robot moving devices 001 serve as external shafts of the robots 004, the movement processing range of the robots 004 is expanded, two sets of welding seam welding end effectors 100 are respectively installed on end flanges of the robots 004, the left side and the right side are symmetrical, see, 2 and 3, two sets of laser welding guns 109 are respectively integrally installed on the two sets of welding seam welding end effectors 100, the two sets of lasers 008 are connected with the laser welding guns 109 through optical fibers and provide welding laser energy for the two sets of laser welding guns, each set of lasers 008 is provided with one set of water cooling machine 007, the water cooling machine 007 is placed beside the lasers 008, the lasers 008 and the water cooling machines 007 are arranged on the inner side of the system, and moving parts and static part ends are separately placed. The console 010 is placed outside the system, and is convenient for an operator to control.
Referring to fig. 1 to 4, the welding end effector 100 is composed of a wire laser sensor 101, a sensor holder 102, a wire feeder 103, a connection flange 104, an adapter flange 105, a coaxial shielding gas sleeve 106, a wire feeder 107, a wire feeder 108, a laser welding gun 109, a base 110, a CCD module 111, a wire feeder fixing plate 112, and the like.
The connection relation of the components of the welding seam measuring end effector 100 will be described in detail.
The flange 104 passes through screw connection with sensor fixing base 102, adapter flange 105 installs at flange 104 top, with robot 004 terminal flange butt joint, adapter flange 105 can be according to the design size of different robot interface, easy to assemble, base 110 passes through the screw and is connected fixedly with flange 104, laser welder 109 installs on base 110, coaxial shielding gas external member 106 is installed at laser welder 109 lower extreme, coaxial shielding gas external member 106 side has the air inlet, switch on shielding gas, provide the gas protection for the welding, improve part surface shaping quality.
The CCD module 111 is mounted on the top of the laser welding gun 109, the CCD module 11 is a high-definition camera, the welding line can be clearly seen through the inner lens group, and a filter lens is configured, so that the laser welding process can be monitored.
QBH interface 112 is installed in laser welder 109 side, connect the optic fibre, the laser 008 is connected to the optic fibre other end, sensor fixing base 102 installs on base 110, line laser sensor 101 installs on sensor fixing base 102, send a fixed plate 112 to install in base 110 side, wire feed device 103 installs on sending a fixed plate 112, wire feed device 103 one end is connected with wire feeder 005 through wire feed pipe 108, the other end is connected with wire feed head 107 through wire feed pipe 108, wire feed head 107 is fixed on coaxial gas protection sleeve 106, wire feed device 103 is the power device of wire feed system, can realize advancing and backing of welding wire, the wire reel is installed inside wire feed machine 005. The welding travel direction is the front of the wire laser sensor 101, the middle of the welding wire, and the rear of the laser gun 109 (as shown in fig. 5). The line laser sensor 101, the wire feeder 103 and the laser welding gun 109 are integrated together and are installed at the tail end of the flange of the robot 003 through flanges, the left side and the right side are symmetrically arranged, the system carries out welding seam position tracking firstly, and the welding track of the robot is automatically corrected.
The laser axis is parallel to the center of the welding gun, the center of the welding gun forms an included angle of about 45 degrees with the reinforcing rib (vertical plate) during measurement, the welding gun properly withdraws along the Z axis to avoid interference with the tool, and the welding gun stretches out along the Z axis during welding to enable the welding gun head to be positioned at a welding position, and the welding gun forms an included angle of 60 degrees with the reinforcing rib.
The welding seam tracking system based on the line laser sensor mainly comprises a PLC, an industrial personal computer, a data acquisition card, a motion controller, a robot system, a communication module and the like, wherein the PLC is connected with the robot system and the industrial personal computer through a Modbus-TCP for communication, the robot and the laser respectively perform I/O control with the PLC, and the main control console is connected with the left side and the right side measuring welding systems through EtherCat interfaces, so that the cooperative control of the double robot systems is realized.
The line structure laser vision system is composed of a laser driver, a line structure laser, an image sensor, an image filter, an image processor, a control logic board and the like (as shown in fig. 6). The method comprises the steps of emitting line structure laser through a three-dimensional line structure laser vision system, scanning the surface of a workpiece to be welded (namely a test piece to be welded), obtaining a surface profile image of the workpiece to be measured, processing the surface profile image through an image filter and a data acquisition card, obtaining three-dimensional point cloud coordinates of the surface of the workpiece to be measured, automatically calculating and analyzing welding seam center coordinates of the workpiece to be welded through a system, driving a sensor by a robot to scan a welding path, automatically calculating actual welding seam track coordinates through the system, obtaining tool coordinate pose of an end effector of the robot through matrix transformation, and automatically correcting the movement track of the robot. And scanning the welded seam by a sensor after welding, automatically identifying the welded seam, calculating the height of a welding leg, analyzing the common appearance quality and providing a basis for workpiece detection.
It will be appreciated by those skilled in the art that the assembly structure of the apparatus for a laser weld automatic tracking method shown in fig. 1-6 is not limiting of the apparatus, and that the apparatus may include more or less components than those shown, and that certain components may not necessarily be part of the apparatus, may be omitted entirely or combined as desired within the scope of not changing the essence of the invention.
The high-precision linear structure light sensor based on the customized large-view long-depth-of-field develops a laser welding T-shaped structure welding seam track automatic identification system, realizes autonomous programming of a welding seam path program of a double-beam laser welding process, replaces manual teaching, develops a post-welding seam morphology analysis system, forms a complete system unit with software and hardware, meets product quality requirements, and realizes automatic welding engineering application of the T-shaped welding seam of the titanium alloy wallboard.
As shown in fig. 7-9, the embodiment of the invention provides an automatic tracking method for a laser welding seam, which comprises the following steps:
Step 1, establishing a laser welding gun tool coordinate system, and calibrating for TCP (too l center po i nt, namely a tool center point);
a focus tool is arranged at the tail end of a laser welding gun, a reference point of the focus tool is determined, a tool nose tool is fixed on a workbench, a fixed point of the tool nose tool is determined, the reference point is just contacted with the fixed point by adopting a four-point method, and a focus coordinate system of the laser welding gun is established through data of four position points.
It will be appreciated that the focal length position of the laser torch is first determined, the tool coordinate system TCP is established at this position, the focal point tool is mounted on the end of the laser torch, and the focal point is located from the tip of the focal point to the center of the focusing mirror of the laser torch at the focal length of the torch (as shown in fig. 8).
And fixing the calibrated tool tip tool on a workbench, using the tip of the calibrated tool tip tool as a reference point, and calibrating a laser welding gun focus coordinate system TCP (too l center po i nt, namely a tool center point) by adopting a four-point method.
Defining a base coordinate system { B }, an end flange coordinate system { F } and a tool coordinate system { T }, and the pose relation from the end flange coordinate system { F } to the base coordinate system { B } can be used as a matrixThe representation is made of a combination of a first and a second color,
Wherein, the Is a rotation matrix of the end flange coordinate system { F } relative to the base coordinate system { B }, and comprises three position vectorsRespectively representing the directional cosine of the 3 unit principal vectors of F with respect to B,Is the position vector of the origin of F with respect to B,Can be obtained by the positive solution of robot kinematics.A transformation matrix representing T with respect to the base coordinates B,A transformation matrix representing the tool coordinates { T } relative to the end flange coordinates { F }, since the tool is mounted on the robot flangeIs a fixed value, the tool TCP calibration is a determinationIs used for the control of the temperature of the liquid crystal display device,And FPtcp.
The calibration process comprises (a) calibrating a tool center point position (TCP), and (b) calibrating a tool coordinate system posture (TCF).
As shown in fig. 9, the tool center point position (TCP) is calibrated by manually operating the robot to move the laser welding gun from four different directions to a fixed point, recording four points P 1、P2、P3、P4, and the robot end flange pose data (X, Y, Z, θ 1、θ2、θ3), wherein the four tool center points are equal in coordinates in the world coordinate system, and performing calculation on the operation demonstrator to obtain the tool coordinate system TCP (X, Y, Z).
Referring to fig. 10, tool coordinate system posture (TCF) calibration is performed by moving a tool coordinate system TCP to any one fixed point for measurement, moving a point in the negative Y-axis direction to the fixed point for measurement, then moving any point in the negative X-axis direction to the fixed point for measurement, recording data, and completing calculation calibration on an operation demonstrator.
Step2, calibrating coordinates of the line laser sensor;
and establishing a robot base coordinate system by taking a mounting base of the linear laser sensor mounted on the robot as a reference, and determining a coordinate relationship between the robot base coordinate system and the laser welding gun focus coordinate system according to a pose matrix of the robot base coordinate system.
Specifically, the coordinate calibration of the line laser sensor is mainly to determine the coordinate relationship between the coordinate system of the line laser sensor and the focus of the laser welding gun. When the robot is in a certain pose, the pose matrix of the welding seam welding end effector relative to the robot base coordinate is T 1, the pose matrix from the line sensor coordinate system to the end flange is X 1, the pose of the world coordinate system under the robot base coordinate system is P 1＝T1X1M1, when the robot moves to another pose, the parameters are changed into T 2、X2、P2, because the line sensor is fixed on the end, X 1＝X2, and because the world coordinate system and the end coordinate system are static, P 1＝P2, the welding seam welding end effector has the following functionsThere is ax=xb,
Let A be an m n matrix, B be an n matrix, X be an m n matrix, it can be seen from the matrix direct product definition:
when A or B is an identity matrix, there are
If a and b are constant, there are,
vec(aA+bB)=a×vec(A)+b×vec(B)
Assume that
Ax=xb can be expressed as:
To determine the unique solution of the above equation, two sets of rotation axis non-parallel motions are required, and the simultaneous equations for these two sets of motions are:
And solving a feature vector v= [ v 1 v2 … v13 ] corresponding to the minimum singular value by using a least square method, wherein the relation matrix is as follows:
Step 3, planning a scanning program;
And driving the line laser sensor to move along the to-be-welded position of the to-be-welded test piece by the robot, and scanning the edge of the rib plate to obtain a surface profile image of the to-be-welded test piece.
In this step, firstly, a robot measurement program is written in offline programming software, so that the YZ plane of a laser welding gun and the vertical face of a rib plate form an included angle of about 45 degrees (shown in fig. 11), a plurality of points S 0、S1……、Sn、Sn+1 are arranged on a test piece to be welded, so that the robot drives a line laser sensor to scan along the sequence of S 0、S1……、Sn、Sn+1, a pulse command is sent to the line laser sensor by a PLC at the point S 0 to trigger data acquisition, a three-dimensional line structure laser vision system sends line structure laser, the edge of the rib plate is scanned, a surface profile image of the test piece to be welded is obtained, and then three-dimensional point cloud coordinates of the surface of the test piece to be welded are obtained. The line laser sensor moves to a position S 1, the measurement instruction is stopped, the line laser sensor returns to the rib plate edge position information, the line laser sensor moves to a position S 2～Sn+1, the PLC sends out pulse measurement instructions to obtain three-dimensional point cloud coordinate information of each sampling point S i, each sampling point is stopped for 1-3 seconds, measurement precision loss caused by movement of the robot is reduced, the line laser sensor moves to a position S n, the PLC triggers the pulse measurement instructions, the line laser sensor moves to a position S n+1, the acquisition instruction is stopped, and the line laser sensor returns to the rib plate edge information.
Step 4, recognizing weld characteristics;
and extracting weld characteristic points of two side edges of the laser belt from the obtained surface profile image of the test piece to be welded, respectively making a first line segment and a second line segment for the weld characteristic points of the two side edges, and taking the first line segment and the second line segment as weld characteristics.
As shown in fig. 12, taking a T-shaped weld joint with a single side as an example, the vertical plate 201 is vertically placed on the bottom plate 200 under the action of the first tool pressing plate 202 and the second tool pressing plate 203, the tool features are eliminated, and the line segments AB and CD are taken as weld joint features.
Step 5:T, calculating the center coordinates of the welding line track;
Fitting the first line segment and the second line segment of the weld feature, and solving the intersection point to obtain the weld center track coordinate.
With continued reference to fig. 12, line segments AB, CD are fitted by a least square method, respectively, that is, the squares of the distances from all points to a straight line are minimized according to the already-point fitting function, and the sum of squares of the errors from the points to the straight line is calculated, that is:
Wherein k and b are equation coefficients, z i、xi is acquired coordinate data to be solved, and k and b are respectively derived to obtain:
Order the
The method comprises the following steps:
Wherein A, B is a weld characteristic point in a first line segment, C, D is a weld characteristic point in a second line segment, z 1＝k1x+b1 and z 2＝k2x+b2 of the first line segment can be determined, an intersection point X A,ZA can be obtained by the two line segments, and an actual weld center track coordinate can be obtained by performing linear interpolation on all sampling points.
Step 6, robot track correction;
On the basis of calibrating the welding track, the robot applies track correction data obtained by measurement and calculation on a tool coordinate system TCP, and invokes a track offset instruction to realize the correction of the welding track.
The Modbus-TCP communication function is mainly used for communication between welding seam locating software and a robot, the welding seam locating software sends data mainly comprising track correction XYZ coordinate offset, measurement, calculation completion zone bits and the like, the robot sends data comprising the robot in place and the current point number and the like, the correction data are sent and stored to a specific register of a robot system after each point is measured by adopting a distributed transmission method, and unified calling is carried out when a welding program is executed, so that the communication transmission bandwidth and speed are ensured not to influence the welding process.
Step 7, robot automatic welding;
according to the technological requirements, signal instructions such as light emitting, attenuation and wire emitting are added, a double-beam synchronous welding signal is added, a welding program is tried to be run, a laser and a wire feeder are disconnected for enabling, the spot track of a guiding laser welding gun is checked and verified, and the welding program is run to finish part welding.
After the steps 1-7 are completed, as the requirement of the double-beam welding seam meets the standard of the navigation mark grade I welding seam, the welding seam mainly comprises the internal quality, mechanical property and appearance requirement of the welding seam, the part is detected after welding, the main detection means of the internal defect of the welding seam is X-ray flaw detection at present, common defects are cracks, incomplete welding, incomplete fusion, air holes, slag inclusion and the like, the mechanical property mainly adopts a tensile experiment method, the tensile strength and the shearing strength are required to meet the technical requirement, the appearance quality requirement of the welding seam is uniform, the arc starting and arc receiving part has no defects such as pits, weld flash, undercut and the like, and the height difference of welding feet is less than or equal to 0.3mm. Appearance quality is an important evaluation standard of the quality of the double-beam welding process, currently, the surface defects are mainly checked by manual visual arrangement, and the height of the welding leg is measured by adopting a metallographic method. The metallographic method is low in efficiency and cannot detect welded workpieces, and the metallographic test piece is manufactured by cutting the T-shaped welding seam when the height of the welding leg is measured.
Therefore, the embodiment also provides a laser welding seam detection method, which is used for detecting the height difference of the welding leg of the T-shaped welding seam based on a laser vision method and carrying out on-line detection on common morphological defects. The method is quick, accurate and effective, improves the weld quality evaluation level, and comprises the following steps of 8-9, wherein the specific steps are as follows:
Step 8, scanning a welded seam after welding;
Before detection, the line laser sensor collects three-dimensional data of the surface of the test piece to be welded, and the three-dimensional data of the surface of the test piece to be welded is transmitted to the industrial personal computer through the Ethernet.
Step 9, weld quality analysis
After the quality online detection system software acquires the data of the line laser sensor, the data is subjected to image preprocessing, the filtered data is converted into a gray level image and a three-dimensional point cloud image, the 2D/3D image is displayed on a software interface, and the data of the output and the weld morphology can be displayed.
The preprocessing of the laser welding seam stripe image comprises the following modes, but is not limited to gray processing, noise reduction, binarization, image enhancement and key area extraction, wherein:
and (3) carrying out graying treatment on the original image by adopting a weighted average method so as to maintain the original image form and improve the measurement accuracy.
The filtering noise reduction is realized, the line laser sensor is affected by environmental disturbance, light and the like in the data image acquisition process, and image processing analysis is not facilitated, so that the filtering noise reduction is realized by adopting a proper filtering algorithm. And referring to a weld seam locating filtering method, performing Gaussian filtering by adopting a convolution template so as to eliminate the influence of noise.
Image binarization, the image binarization processing is used for reducing the image data quantity and improving the operation efficiency. The maximum space method is adopted to carry out binarization processing, D 1 gray scale ranges [0, g ], the proportion of the image is m 0, the average gray scale value p 0,D2 gray scale ranges [ g+1, H ], the proportion of the image is m 1, the average gray scale value p 1, the total average gray scale value of the image is p, s is the variance of D 1 and D 2, the number of pixels with gray scale value smaller than g is K 0, the number of pixels with gray scale value larger than g is K 1, and the method comprises the following steps:
s=m0m1(p0-p1)2
The maximum inter-class variance method is based on a threshold value g corresponding to the maximum value s in the gray level distribution of the image, the weld joint image subjected to noise reduction treatment is subjected to binarization treatment, the threshold value is automatically obtained, the edge information of the original image is reserved, and the number of broken parts is small.
When the original image is corroded, the target image-text is gradually contracted, and partial areas are blurred, so that the image is possibly distorted, the image is enhanced, the image is subjected to closed operation, the effective part of the image is enhanced, and the extraction of key areas is facilitated.
And extracting the key areas of the image, selecting the effective line segments AB and CD of the image, reducing the operation times and improving the efficiency.
After the key points of the weld image are extracted and the weld laser image is obtained, the key points in the image are further extracted to detect and judge the appearance quality of the weld, and the key points are extracted as shown in fig. 13, and the method comprises the following steps:
Extracting a welding seam contour curve, dividing an interested region of the original data, and setting a welding seam detection starting point A and a welding seam detection end point D;
Traversing all welding line contour feature data points in the divided interested area, finding out the corresponding abscissa of the highest point E of the arc line in the laser two-dimensional coordinates, searching in the direction of the ordinate or the abscissa respectively by taking the point as a reference until a welding line key feature inflection point B and a welding line key feature inflection point C which are zero in distance from the bottom plate and the vertical plate are found out, and marking the coordinates of the point;
Fitting line segments AB and CD by using a least square method, taking an intersection point O of the two line segments as a welding seam center, calculating a welding leg height difference I OB-OC I, judging whether the welding leg height difference I OB-OC I is smaller than or equal to a preset value of 0.3mm, and when the threshold value is exceeded, judging that the welding seam is unqualified, and carrying out reworking treatment. And (5) carrying out the next process after the product is qualified.
And in the same way, the high points and pits on the curve BEC can be judged, a threshold value is set, and if the threshold value is exceeded, the judgment is failed.
In the description and claims of the present application, the words "comprise/comprising" and the words "have/include" and variations thereof are used to specify the presence of stated features, values, steps, or components, but do not preclude the presence or addition of one or more other features, values, steps, components, or groups thereof.
Some features of the invention, which are, for clarity of illustration, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, some features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable combination in different embodiments.
The foregoing description of the preferred embodiment of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.

Claims (7)

1.一种激光焊接焊缝自动寻迹方法，其特征在于，包括以下步骤：1. A laser welding seam automatic tracking method, characterized by comprising the following steps: 步骤1：在激光焊枪末端安装焦点工具，确定所述焦点工具的参考点，在工作台上固定刀尖工具，确定所述刀尖工具的固定点，采用四点法，使所述参考点与所述固定点刚好接触，通过四个位置点的数据，建立激光焊枪焦点坐标系；Step 1: Install a focus tool at the end of the laser welding gun, determine the reference point of the focus tool, fix the tool tip on the workbench, determine the fixed point of the tool tip, use the four-point method to make the reference point just touch the fixed point, and establish the laser welding gun focus coordinate system based on the data of the four position points; 步骤2：以线激光传感器安装在机器人的安装基座为基准，建立机器人基坐标系，根据所述机器人基坐标系的位姿矩阵，确定所述机器人基坐标系与所述激光焊枪焦点坐标系之间的坐标关系；Step 2: With the line laser sensor installed on the robot's mounting base as a reference, establish a robot base coordinate system, and determine the coordinate relationship between the robot base coordinate system and the laser welding gun focus coordinate system according to the pose matrix of the robot base coordinate system; 步骤3：由机器人带动所述线激光传感器沿着待焊试件的待焊位置移动，扫描筋板边缘，得到待焊试件表面轮廓图像；Step 3: The robot drives the line laser sensor to move along the welding position of the welded specimen, scans the edge of the rib plate, and obtains a surface contour image of the welded specimen; 步骤4：从得到的所述待焊试件表面轮廓图像中，提取激光带两侧边缘的焊缝特征点，对两侧边缘的所述焊缝特征点分别作线段一和线段二，以所作的线段一和线段二为焊缝特征；Step 4: Extracting weld feature points on both sides of the laser band from the obtained surface contour image of the welded specimen, and creating line segments 1 and 2 for the weld feature points on both sides of the laser band, respectively, with the created line segments 1 and 2 being weld features; 步骤5：对所述焊缝特征的线段一和线段二进行拟合，求解其交点即为焊缝中心轨迹坐标；Step 5: Fit the line segment 1 and the line segment 2 of the weld feature, and solve their intersection point to obtain the coordinates of the weld center trajectory; 步骤2中，确定所述机器人基坐标系与所述激光焊枪焦点坐标系之间的坐标关系的步骤包括：In step 2, the step of determining the coordinate relationship between the robot base coordinate system and the laser welding gun focus coordinate system includes: 机器人处于某一位姿时，焊缝测焊末端执行器相对于所述机器人基坐标的位姿矩阵为T1，线传感器坐标系到末端法兰位姿矩阵为X1，世界坐标系在机器人基坐标系下的位姿为P1＝T1X1M1，机器人运动到另一个位姿时，上述参数变为T2、X2、P2，由于线传感器固定在末端上，所以X1＝X2，又由于世界坐标系和末端坐标系是静止的，所以P1＝P2，令，，则有AX＝XB，When the robot is in a certain posture, the posture matrix of the weld seam measurement end effector relative to the robot base coordinate is T 1 , the posture matrix from the line sensor coordinate system to the end flange is X 1 , and the posture of the world coordinate system in the robot base coordinate system is P 1 = T 1 X 1 M 1 . When the robot moves to another posture, the above parameters become T 2 , X 2 , and P 2 . Since the line sensor is fixed on the end, X 1 = X 2 . Since the world coordinate system and the end coordinate system are stationary, P 1 = P 2 . Let , , then AX＝XB, 设A是m×n的矩阵，B是n×n的矩阵，X是m×n的矩阵，由矩阵直积定义可知:Assume A is an m×n matrix, B is an n×n matrix, and X is an m×n matrix. From the definition of matrix direct product, we know that: 当A或B是单位矩阵时，有When A or B is the identity matrix, we have 设a和b为常数，则有，Let a and b be constants, then we have, vec(aA+bB)＝a×vec(A)+b×vec(B)vec(aA+bB)=a×vec(A)+b×vec(B) 假设Assumptions 则AX＝XB可以表示为:Then AX=XB can be expressed as: 要确定上式的唯一解，需要两组旋转轴不平行的运动，这两组运动得到的联立方程为:To determine the unique solution of the above equation, two sets of motions with non-parallel rotation axes are required. The simultaneous equations obtained from these two sets of motions are: 用最小二乘法求解出最小奇异值对应的特征向量v＝[v1 v2 … v13]，则关系矩阵为:Use the least squares method to solve the eigenvector v = [v 1 v 2 … v 13 ] corresponding to the minimum singular value, then the relationship matrix is: 。 . 2.如权利要求1所述的一种激光焊接焊缝自动寻迹方法，其特征在于，步骤1中，所述建立激光焊枪焦点坐标系的标定过程为：2. The laser welding seam automatic tracking method according to claim 1, wherein in step 1, the calibration process for establishing the laser welding gun focus coordinate system is: 工具中心点位置标定：手动操作机器人使激光焊枪从四个不同方向移动到固定点处，记录四个点P1、P2、P3、P4，机器人末端法兰位姿数据(X,Y,Z,θ1、θ2、θ3)，四次工具中心点在世界坐标系中坐标相等，在操作示教器上完成计算，得到工具坐标系TCP(X，Y，Z)；Tool center point position calibration: Manually operate the robot to move the laser welding gun from four different directions to a fixed point, record the four points P1 , P2 , P3 , and P4 , and the robot end flange pose data (X, Y, Z, θ1 , θ2 , θ3 ). The coordinates of the four tool center points in the world coordinate system are equal. Complete the calculation on the teaching pendant to obtain the tool coordinate system TCP (X, Y, Z); 工具坐标系姿态标定：将工具坐标系TCP移动到任意一个固定点进行测量，将Y轴负方向的一点移动到固定点进行测量，然后XY平面内X为负值的任意一点移动到固定点进行测量，记录数据，在操作示教器上完成计算标定。Tool coordinate system posture calibration: Move the tool coordinate system TCP to any fixed point for measurement, move a point in the negative direction of the Y axis to the fixed point for measurement, then move any point in the XY plane with a negative X value to the fixed point for measurement, record the data, and complete the calculation calibration on the teaching pendant. 3.如权利要求1所述的一种激光焊接焊缝自动寻迹方法，其特征在于，所述步骤3的步骤包括，使激光焊枪YZ平面与筋板立面成约45度夹角，在待焊试件上设置若干点S0、S1……、Sn、Sn+1，使机器人带动线激光传感器沿着S0、S1 ……、Sn、Sn+1的顺序进行扫描，在S0点处由PLC给线激光传感器发出脉动指令，触发数据采集，三维线结构激光视觉系统发出线结构激光，扫描筋板边缘，得到待焊试件表面轮廓图像。3. A laser welding seam automatic tracing method according to claim 1, characterized in that the step 3 includes making the YZ plane of the laser welding gun form an angle of approximately 45 degrees with the vertical surface of the rib plate, setting a plurality of points S0 , S1 ..., Sn , Sn +1 on the specimen to be welded, and causing the robot to drive the line laser sensor to scan along the order of S0 , S1 ..., Sn , Sn +1 . At point S0 , the PLC sends a pulsating instruction to the line laser sensor to trigger data acquisition, and the three-dimensional line structure laser vision system emits a line structure laser to scan the edge of the rib plate to obtain a surface contour image of the specimen to be welded. 4.如权利要求1所述的一种激光焊接焊缝自动寻迹方法，其特征在于，步骤4中，在对两侧边缘的所述焊缝特征点分别作线段一和线段二之前，还包括对所述焊缝特征点作滤波处理。4. A laser welding weld automatic tracing method as described in claim 1, characterized in that in step 4, before making line segment 1 and line segment 2 for the weld feature points on both side edges respectively, it also includes filtering processing on the weld feature points. 5.如权利要求1所述的一种激光焊接焊缝自动寻迹方法，其特征在于，在步骤5中，对所述焊缝特征的线段一和线段二进行拟合，求解其交点即为焊缝中心轨迹坐标的步骤包括：5. The method for automatically tracing a laser welding seam according to claim 1, wherein in step 5, fitting the first and second line segments of the weld feature and solving the intersection thereof as the coordinates of the weld center trajectory comprises: 根据已知的所述焊缝特征点拟合函数，使所有焊缝特征点到直线的距离的平方最小，求焊缝特征点到直线的误差平方和，即：According to the known fitting function of the weld feature points, the square of the distance from all weld feature points to the straight line is minimized, and the sum of the squares of the errors from the weld feature points to the straight line is calculated, that is: 式中，k、b为方程系数，待求解，zi、xi为采集到的坐标数据，分别对k、b求导，可得：Where k and b are the coefficients of the equation to be solved, z i and xi are the collected coordinate data, and by taking the derivative of k and b respectively, we can get: 令，make , 得到：get: 式中，A、B为线段一中的焊缝特征点，C、D为线段二中的焊缝特征点，可确定线段一：z1＝k1x+b1和线段二：z2＝k2x+b2，两条线段可求得交点XA，ZA；对所有的采样点进行线性插值，即可得到实际的焊缝中心轨迹坐标。Where A and B are the weld feature points in line segment one, and C and D are the weld feature points in line segment two. Line segment one: z 1 = k 1 x + b 1 and line segment two: z 2 = k 2 x + b 2 can be determined, and the intersection points X A and Z A of the two line segments can be obtained. Linear interpolation is performed on all sampling points to obtain the actual weld center trajectory coordinates. 6.如权利要求1所述的一种激光焊接焊缝自动寻迹方法，其特征在于，在步骤5之后，还包括在焊缝中心轨迹坐标的基础上对焊接轨迹进行修正。6. The method for automatically tracking a laser welding seam according to claim 1, characterized in that after step 5, the method further comprises correcting the welding trajectory based on the coordinates of the weld center trajectory. 7.一种用于权利要求1-6任一项所述的一种激光焊接焊缝自动寻迹方法的装置，其特征在于，所述装置包括：机器人运动装置、机器人、焊缝测焊末端执行器、工作平台、激光器；所述工作平台的两侧设有机器人运动装置，所述机器人安装在所述机器人运动装置的滑台上；所述机器人的末端法兰上安装有所述焊缝测焊末端执行器；其中，所述焊缝测焊末端执行器至少包括集成于一体的线激光传感器、送丝装置、激光焊枪以及CCD模块。7. A device for the automatic tracing method of laser welding welds according to any one of claims 1 to 6, characterized in that the device comprises: a robot motion device, a robot, a weld seam detection end effector, a work platform, and a laser; robot motion devices are provided on both sides of the work platform, and the robot is mounted on a slide of the robot motion device; the weld seam detection end effector is mounted on the end flange of the robot; wherein the weld seam detection end effector comprises at least an integrated line laser sensor, a wire feeding device, a laser welding gun, and a CCD module.
CN202211155049.5A 2022-09-21 2022-09-21 Laser welding seam automatic tracing method, detection method and device Active CN115464263B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211155049.5A CN115464263B (en) 2022-09-21 2022-09-21 Laser welding seam automatic tracing method, detection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211155049.5A CN115464263B (en) 2022-09-21 2022-09-21 Laser welding seam automatic tracing method, detection method and device

Publications (2)

Publication Number Publication Date
CN115464263A CN115464263A (en) 2022-12-13
CN115464263B true CN115464263B (en) 2025-10-03

Family

ID=84335819

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211155049.5A Active CN115464263B (en) 2022-09-21 2022-09-21 Laser welding seam automatic tracing method, detection method and device

Country Status (1)

Country Link
CN (1) CN115464263B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116329824A (en) * 2023-04-24 2023-06-27 仝人智能科技(江苏)有限公司 Hoisting type intelligent welding robot and welding method thereof
CN116423049B (en) * 2023-06-12 2023-09-08 广州市易鸿智能装备有限公司 Repair welding position determining method and device
CN116503397B (en) * 2023-06-26 2023-09-01 山东天通汽车科技股份有限公司 In-vehicle transmission belt defect detection method based on image data
CN117206752A (en) * 2023-09-08 2023-12-12 上海闪熔科技有限公司 A device, method, medium and equipment for assisting robot automatic welding
CN117483917A (en) * 2023-10-19 2024-02-02 浙大宁波理工学院 Automatic tracking welding method based on weld seam visual recognition
CN117781869A (en) * 2023-12-25 2024-03-29 智云流形科技(江阴)有限公司 Calibration methods, devices and equipment
CN117464652B (en) * 2023-12-26 2024-03-19 济南二机床集团有限公司 Workpiece carrying parallel-serial mechanical arm and track control method of parallel-serial mechanical arm
CN118710724B (en) * 2024-08-28 2024-10-29 中国建筑第五工程局有限公司 An AI visual weld position automatic search method

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112561854A (en) * 2020-11-11 2021-03-26 深圳大学 Welding seam detection method based on line structure light point cloud

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1058139A (en) * 1996-08-20 1998-03-03 Mitsubishi Heavy Ind Ltd Method for welding intersection part of tube
CN110681950A (en) * 2019-08-29 2020-01-14 北京航空航天大学 Robot seam tracking system and control method based on structured light sensor
CN112862794A (en) * 2021-02-20 2021-05-28 河北工业大学 Fillet weld appearance detection method based on structured light
CN113954085A (en) * 2021-09-08 2022-01-21 重庆大学 Intelligent positioning and control method of welding robot based on binocular vision and linear laser sensing data fusion

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112561854A (en) * 2020-11-11 2021-03-26 深圳大学 Welding seam detection method based on line structure light point cloud

Also Published As

Publication number Publication date
CN115464263A (en) 2022-12-13

Similar Documents

Publication Publication Date Title
CN115464263B (en) Laser welding seam automatic tracing method, detection method and device
CN110530877B (en) Welding appearance quality detection robot and detection method thereof
CN112122840B (en) Visual positioning welding system and welding method based on robot welding
CN110524582B (en) Flexible assembly welding robot workstation
CN116175035B (en) Intelligent welding method for steel structure high-altitude welding robot based on deep learning
CN107414253B (en) Welding seam tracking control device and method based on cross laser
CN111014879B (en) Automatic welding method for corrugated plate of robot based on laser weld seam tracking
Huang et al. Development of a real-time laser-based machine vision system to monitor and control welding processes
Nele et al. An image acquisition system for real-time seam tracking
CN114515924A (en) Tower foot workpiece automatic welding system and method based on weld joint identification
CN115112018B (en) A three-coordinate machine intelligent composite joint inspection system and method based on stereo vision
CN211825860U (en) Automatic flaw detection device guided by vision
CN103231162A (en) Device and method for visual detection of welding quality of robot
CN117047237B (en) Intelligent flexible welding system and method for special-shaped parts
CN106735749B (en) A Laser-Assisted Weld Seam Intelligent Tracking System
CN117564441A (en) Friction stir welding seam quality monitoring system and method based on machine vision
CN108344693B (en) A visual measurement method of thin-plate weld misalignment for automatic welding
CN104400217A (en) Full-automatic laser welding method and full-automatic laser welding device
CN114633021A (en) Laser welding method and device for real-time vision acquisition
Geng et al. A method of welding path planning of steel mesh based on point cloud for welding robot
Shen et al. Measurement and evaluation of laser-scanned 3D profiles in wire arc hybrid manufacturing processes
Caggiano et al. 3D digital reconfiguration of an automated welding system for a railway manufacturing application
CN114309930B (en) Symmetrical double-station spray pipe laser welding equipment
CN114782378A (en) Method for constructing robot intelligent welding database for welding process of various components
CN210775253U (en) A welding shape quality inspection robot

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