CN117564404B - Automatic welding method of large-scale reinforcing mesh based on AI vision - Google Patents
Automatic welding method of large-scale reinforcing mesh based on AI vision Download PDFInfo
- Publication number
- CN117564404B CN117564404B CN202311587756.6A CN202311587756A CN117564404B CN 117564404 B CN117564404 B CN 117564404B CN 202311587756 A CN202311587756 A CN 202311587756A CN 117564404 B CN117564404 B CN 117564404B
- Authority
- CN
- China
- Prior art keywords
- reinforcing mesh
- welding
- model
- connecting section
- reinforcing
- 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
Links
- 238000003466 welding Methods 0.000 title claims abstract description 183
- 230000003014 reinforcing effect Effects 0.000 title claims abstract description 170
- 238000000034 method Methods 0.000 title claims abstract description 52
- 229910001294 Reinforcing steel Inorganic materials 0.000 claims abstract description 18
- 229910000831 Steel Inorganic materials 0.000 claims description 27
- 239000010959 steel Substances 0.000 claims description 27
- 230000002787 reinforcement Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- B23K9/00—Arc welding or cutting
- B23K9/0026—Arc welding or cutting specially adapted for particular articles or work
-
- 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
- B23K9/00—Arc welding or cutting
- B23K9/12—Automatic feeding or moving of electrodes or work for spot or seam welding or cutting
-
- 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
- B23K9/00—Arc welding or cutting
- B23K9/32—Accessories
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
- Manipulator (AREA)
Abstract
The invention discloses an automatic welding method of a large-scale reinforcing mesh based on AI vision, which comprises a working platform and an industrial personal computer, wherein the working platform comprises a guide rail and a stand moving along the guide rail, a support arm is rotatably arranged on the stand, a robot is arranged on the support arm in a sliding manner, a welding gun and a second vision device are arranged on the robot, a first vision device is arranged on the support arm, the working platform further comprises an operation platform arranged below the robot, and the automatic welding method further comprises the following steps: establishing a three-dimensional template, paving a reinforcing mesh, performing primary positioning, performing fine positioning, turning over, performing secondary primary positioning and performing fine positioning. Compared with the prior art, the invention completes the preliminary positioning of the reinforcing mesh through the first vision device, and then improves the positioning precision of the reinforcing mesh through the second vision device, thereby meeting the requirement of robot welding. The welding speed of the reinforcing mesh is high, and the efficiency is high. Particularly, when welding large-scale reinforcing steel bar meshes, the welding speed is far higher than that of a robot for welding by adopting manual teaching.
Description
Technical Field
The invention relates to the technical field of reinforcement mesh welding, in particular to an automatic welding method of a large-sized reinforcement mesh based on AI vision.
Background
In the construction industry, a large number of reinforcing mesh structural prefabricated members are widely used. The prior prefabricated member of the reinforcing mesh structure is generally bound or welded by manual work on cross intersections in the reinforcing mesh, but the manual welding has limitations, such as unstable welding quality, low construction efficiency, high welding cost, incapability of working under extreme conditions of high temperature, high pressure and the like. At present, the mechanical automatic welding technology is widely applied to various fields of automobiles, aerospace, industrial manufacturing and the like, but generally needs to rely on high-precision workpiece limiting and is matched with path teaching of a plurality of mechanical arm welding guns to meet the welding process requirements. However, the steel bars themselves are bent, the bent steel bars also have errors due to the characteristics of the elastic molds, the spliced steel bar meshes are necessarily irregular, gaps among the steel bars are uneven, height differences exist among the steel bars, the occurrence of arc starting, arc interruption and collision can be caused, and finally automatic mechanical welding failure is caused.
Disclosure of Invention
The invention provides an automatic welding method of a large reinforcing steel bar net based on AI vision, which is used for solving the problems that the large reinforcing steel bar net is irregular, the gap is large and automatic welding is difficult.
The invention provides an automatic welding method of a large reinforcing mesh based on AI vision, which comprises a working platform and an industrial personal computer, wherein the working platform comprises a guide rail and a machine base moving along the guide rail, a support arm is rotatably arranged on the machine base, a robot is arranged on the support arm in a sliding manner, a welding gun and a second vision device are arranged on the robot, a first vision device is arranged on the support arm, the working platform further comprises an operation table arranged below the robot, and the automatic welding method further comprises the following steps:
Establishing a three-dimensional template: establishing a 3D model template of a working platform, wherein the 3D model template comprises: the three-dimensional (3D) model template comprises a first reinforcing mesh model and a second reinforcing mesh model which are pre-established on the operation table, wherein the second reinforcing mesh model is formed by overturning the first reinforcing mesh model by 180 degrees, the first reinforcing mesh model and the second reinforcing mesh model both comprise the coordinate positions of a plurality of connecting sections, the industrial personal computer sorts the connecting sections of the first reinforcing mesh model and the second reinforcing mesh model respectively, the connecting sections comprise welding seams, the lengths of the welding seams are smaller than those of the connecting sections, and the connecting sections and the welding seams are in one-to-one correspondence;
Paving a reinforcing steel bar net: paving a plurality of steel bars on an operation table to form a steel bar net, and fixing adjacent steel bars through a clamp on the operation table;
Primary positioning: the machine base moves along the guide rail to drive the support arm to move from one end of the reinforcing mesh to the other end, and the support arm continuously shoots the reinforcing mesh and generates a first physical 3D model in the moving process; comparing the connecting section of the first reinforcing mesh model with the connecting section of the first physical 3D model to obtain the offset of the connecting section of the first physical 3D model in the first reinforcing mesh model;
Fine positioning: according to the offset and the 3D model template, the robot moves to the first connecting section; the second vision device acquires images of the first connecting section to obtain a 3D model of the first connecting section, the industrial personal computer obtains position coordinates of a welding line A in the first connecting section through the 3D model of the first connecting section, and then the starting point position of the welding line A is adjusted through a preset gap value; the welding gun starts an arc on one steel bar at the starting point of the welding line A, then moves to a middle position D of the two steel bars in swinging, and then moves along the extending direction of the steel bars in swinging by taking the position D as the starting point to finish the welding of the first connecting section;
Repeating the fine positioning step, and finishing welding of the residual connecting sections by the robot;
turning over: loosening the clamp, and turning over the reinforcing mesh by 180 degrees to enable the reverse surface of the reinforcing mesh to face upwards;
Primary positioning for the second time: the machine base moves along the guide rail to drive the support arm to move from one end of the reinforcing mesh to the other end, and the support arm continuously photographs the reinforcing mesh and generates a second physical 3D model in the moving process; comparing the connecting section of the second reinforcing mesh model with the connecting section of the second physical 3D model to obtain the offset of the connecting section of the second physical 3D model in the second reinforcing mesh model;
And finishing the welding of the reverse side of the reinforcing mesh through a fine positioning step.
Preferably, the specific step of adjusting the starting point position of the welding line A through a preset clearance value is as follows; if the gap of the starting point of the welding line A is smaller than the preset value, the starting point of the welding line A is the current position; if the gap of the starting point of the welding line A is larger than the preset value, the welding line A moves Lmm from the starting point position to the narrower direction, if the gap of the starting point of the welding line A after the movement is smaller than the preset value, the starting point of the welding line A is the current position, otherwise, the process is repeated until the gap of the starting point of the welding line A is smaller than the preset value.
Preferably, in the step of striking an arc on one of the steel bars at the start of the weld a, the welding gun: and obtaining a gap Wmm of the starting point of the welding seam A through the 3D model of the first connecting section, and enabling a welding gun positioned at the middle position of the starting point of the welding seam A to be shifted by half of the Wmm and then to be shifted Hmm, wherein a welding wire on the welding gun is contacted with one steel bar, and H is the thread depth of the steel bar thread.
Preferably, in the process of fine positioning, the welding gun adjusts the posture of the welding gun according to the coordinate positions of the two reinforcing steel bars in the 3D model of the first connecting section, so that the welding gun is always perpendicular to the plane where the two reinforcing steel bars are located.
Preferably, in the process of fine positioning, if the gap of the welding line is small, the travelling speed of the welding gun is high, and the wire feeding speed is slow, and if the gap of the welding line is large, the travelling speed of the welding gun is slow, and the wire feeding speed is fast.
Preferably, in the fine positioning step: the industrial personal computer calculates the space position information of the connecting section of the first reinforcing mesh model according to the offset and the 3D model template, and then the robot moves to the first connecting section according to the space position information of the connecting section of the first reinforcing mesh model; or the industrial personal computer calculates the space position information of the connecting section of the second reinforcing mesh model according to the offset and the 3D model template, and then the robot moves to the first connecting section according to the space position information of the connecting section of the second reinforcing mesh model.
Preferably, the two operation tables are respectively positioned at two sides of the guide rail, and when the robot welds the reinforcing mesh on one operation table, the other operation table lays or overturns the reinforcing mesh.
Preferably, in the step of first initial positioning: in the moving process of the support arm, the first vision device performs image acquisition on the operation table while performing image acquisition on the reinforcing mesh, and the first vision device processes the acquired image to obtain a first physical 3D model on the operation table model.
Preferably, the reinforcing mesh comprises a plurality of second reinforcing bars and a plurality of first reinforcing bars which are in straight lines, and one or two ends of the second reinforcing bars are in a bent shape.
Preferably, in the turning step: the support arm is rotated to prevent the support arm from staying above the operation table, and the reinforcing mesh is turned 180 degrees through the lifting appliance.
Compared with the prior art, the first vision device continuously shoots from beginning to end along the reinforcing mesh to obtain the coordinate position of the reinforcing mesh, and the reinforcing mesh is low in accuracy, but high in speed and efficiency. Then, through the coordinate position of the obtained reinforcing mesh, the welding wire moves to the vicinity of each connecting section, a 3D model of each connecting section is obtained through photographing by a second vision device, then, through the 3D model of the connecting section, the starting point position of a welding line is adjusted, a welding gun is shifted to enable the welding wire of the welding gun to be in contact with the reinforcing steel bars, the welding of the connecting sections is completed through setting two fluctuation points, and in the welding process, the posture of the welding gun is adjusted to enable the welding gun to be always perpendicular to the plane where the two reinforcing steel bars are located. Thereby ensure that can strike an arc smoothly, constantly arc in welding process, guarantee welded dry elongation parameter's stability, guarantee the effect in welding the solution pond, ensure that welding process is carried out smoothly.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a top view of the present invention;
FIG. 2 is a front view of the present invention;
FIG. 3 is a left side view of the present invention;
FIG. 4 is a schematic view of the structure of the invention for adjusting the posture of the welding gun;
FIG. 5 is a schematic view of the structure of the invention for adjusting the weld start;
FIG. 6 is a schematic view of a travel path of a welding gun according to the present invention.
Reference numerals:
100. the device comprises a working platform, a guide rail, a machine base, a support arm, a robot, an operating platform, a clamp and a reinforcing mesh.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-3, this embodiment provides a welding method for a bent cap reinforcing mesh, including a working platform 100 and an industrial personal computer, where the working platform 100 includes a guide rail 1 and a machine base 2 moving along the guide rail 1, a support arm 3 is rotatably provided on the machine base 2, a robot 4 is slidably provided on the support arm 3, a welding gun 8 and a second vision device are provided on the robot 4, a first vision device is provided on the support arm 3, the working platform 100 further includes an operation table 5 disposed below the robot 4, and a plurality of clamps 6 are provided on the operation table 5, and further includes the following steps:
Establishing a three-dimensional template: establishing a 3D model template of the working platform 100, the 3D model template comprising: the method comprises the steps that the coordinate position of a robot 4, the coordinate position of an operating platform 5, the coordinate position of a guide rail 1, the coordinate position of a machine base 2, the coordinate position of a support arm 3 and the coordinate position of a first vision device are arranged, a 3D model template comprises a first reinforcing mesh model and a second reinforcing mesh model which are pre-established on the operating platform 5, the second reinforcing mesh model is formed by overturning the first reinforcing mesh model by 180 degrees, the first reinforcing mesh model and the second reinforcing mesh model comprise the coordinate positions of a plurality of connecting sections 200, and an industrial personal computer sorts the connecting sections 200 of the first reinforcing mesh model and the connecting sections 200 of the second reinforcing mesh model respectively; the connecting sections 200 comprise welding seams 300, the length of the welding seams 300 is smaller than that of the connecting sections 200, the connecting sections 200 and the welding seams 300 are in one-to-one correspondence, each connecting section 200 comprises one welding seam 300, and the position of the connecting section 200 is equal to the position of the welding seam 300. After the first face (front face) of the mesh reinforcement 7 is welded, the other face (back face) needs to be welded by turning over, so that two models of the mesh reinforcement 7 need to be built on the operation table 5. The connecting section 200 is a portion where the two reinforcing bars 71 in the reinforcing mesh 7 are folded, and a place where the two reinforcing bars 71 in the connecting section 200 are contacted is not contacted but has a smaller gap. (marked in the figure)
Laying a reinforcing mesh 7: a plurality of reinforcing bars 71 are paved on an operation table 5 to form a reinforcing bar net 7, and adjacent reinforcing bars 71 are fixed through a clamp 6 on the operation table 5; the reinforcing mesh 7 is formed by splicing the reinforcing steel bars 71, and many errors, such as the non-straightness of the reinforcing steel bars 71 and the elastic modulus of the reinforcing steel bars 71, occur in the splicing process, and all the errors can cause the difference between the spliced reinforcing mesh 7 and the reinforcing mesh 7 in the 3D model template, and the differences can cause unsuccessful arcing, arc breakage, change in the dry elongation and the like in the welding process, so that the automatic welding of the reinforcing mesh 7 is affected.
Primary positioning: the machine base 2 moves to the end point of the guide rail 1 along the starting point of the guide rail 1, so that the support arm 3 is driven to move from one end of the reinforcing mesh 7 to the other end, and in the moving process of the support arm 3, the first vision device continuously photographs the reinforcing mesh 7 and generates a first physical 3D model; in this process, the height position of the support arm 3 is determined, that is, the height position of the first vision device is determined, the first vision device performs image acquisition on the reinforcing mesh 7 and also performs image acquisition on the operation table 5, the first vision device processes the acquired image to obtain a first physical 3D model on the operation table 5 model, the first physical 3D model comprises the model of the reinforcing mesh 7 and the model of the operation table 5, the coordinate position of the operation table 5 is determined, when the connection section 200 of the first reinforcing mesh model and the connection section 200 of the first physical 3D model are compared, the operation table 5 can be used as a common reference point, and after the operation table 5 of the 3D model template and the operation table 5 of the first physical 3D model are overlapped, the offset of the connection section 200 of the first physical 3D model in the first reinforcing mesh model is obtained; by this offset, the coordinate position of the connecting section 200 of the reinforcing mesh 7 can then be obtained. In this step, the coordinate position of the connecting section 200 of the reinforcing mesh 7 (physical object) is obtained by moving the first vision device to perform image acquisition, which is fast and efficient. However, in order to photograph the entire reinforcing mesh 7 in the width direction, the position of the first vision device is set to be high, resulting in insufficient photographing accuracy, and thus the obtained coordinate position of the connecting section 200 of the reinforcing mesh is subject to a certain error, which is difficult to satisfy the welding requirement of the robot 4.
Fine positioning: according to the offset and the 3D model template, robot 4 moves to the first connection section 200; the second vision device acquires images of the first connecting section 200 to obtain a 3D model of the first connecting section 200, the industrial personal computer obtains position coordinates of the welding line 300A in the first connecting section 200 through the 3D model of the first connecting section 200, and then the starting point position of the welding line 300A is adjusted through a preset gap value; referring to fig. 6, the welding gun 8 starts an arc at point C on one of the reinforcing bars 71 at the start point of the weld 300A, then proceeds to the intermediate position D of both reinforcing bars 71 in the swing, and then proceeds to point E in the extending direction of the reinforcing bars 71 in the swing with the point D as the start point to complete the welding of the first connecting segment 200. In this step, the industrial personal computer obtains the position coordinates of the weld 300A in the first connection section 200, and obtains the position coordinates of the weld 300A, so that the difference between the real object of the reinforcing mesh 7 and the reinforcing mesh 7 in the 3D model template is solved, but the gap at the starting point of the weld 300A may not be arc-started or welded if the gap is too large, so that the starting point position of the weld 300A needs to be adjusted through the preset gap value, so as to ensure that the gap at the starting point of the weld 300A meets the arc-starting requirement of the welding gun 8, avoid the conditions of arc-starting failure and welding failure, and ensure that the welding procedure can be smoothly executed. Secondly, the welding gun 8 is made to strike an arc on one of the reinforcing bars 71 at the starting point of the weld 300A, which is a first striking point, the welding wire 9 of the welding gun 8 is in contact with the reinforcing bars 71 in the first striking (ensuring smooth striking), then travels to the intermediate position D of the two reinforcing bars 71 in the swing, the position D is a second striking point, then travels in the extending direction of the reinforcing bars 71 in the swing with the position D as the starting point to finish the welding of the first connecting section 200, and the welded metal strip from the first striking point to the position D ensures that the welding wire 9 of the welding gun 8 is in contact with the metal strip in the second striking (ensuring smooth striking). The arrangement of two arcing points ensures the arc starting of the electric welding energy percentage, and ensures that the welding procedure can be smoothly executed.
Repeating the fine positioning step, and welding the remaining connecting sections 200 by the robot 4; for example, robot 4 moves to the second connection segment 200 according to the offset and the 3D model template; the second vision device acquires images of the second connecting section 200 to obtain a 3D model of the second connecting section 200, the 3D model industrial personal computer of the second connecting section 200 is used for obtaining position coordinates of a welding line 300B in the second connecting section 200, and then the position of the welding line 300 is obtained by a method of adjusting the starting point position of the welding line 300B through a preset gap value; the welding gun 8 is struck on one of the reinforcing bars 71 at the start point of the weld 300B, then travels to the intermediate position D of the two reinforcing bars 71 in the swing, and then travels in the extending direction of the reinforcing bars 71 in the swing with the D as the start point to complete the welding of the second connecting section 200.
Turning over: loosening the clamp 6, and turning over the reinforcing mesh 7 by 180 degrees to enable the reverse surface of the reinforcing mesh 7 to face upwards;
Primary positioning for the second time: the machine base 2 moves along the guide rail 1 to drive the support arm 3 to move from one end of the reinforcing mesh 7 to the other end, and the support arm 3 continuously photographs the reinforcing mesh 7 by the first vision device and generates a second physical 3D model in the moving process; comparing the connecting section 200 of the second reinforcing mesh model with the connecting section 200 of the second physical 3D model to obtain the offset of the connecting section 200 of the second physical 3D model in the second reinforcing mesh model;
The welding of the reverse side of the reinforcing mesh 7 is completed through the fine positioning step.
The specific steps of adjusting the starting point position of the welding line 300A through a preset clearance value are as follows; if the gap at the beginning of weld 300A is less than a preset value, e.g., the gap at the beginning of weld 300A is less than 10mm, then weld 300A need not be offset; referring to fig. 5, if the gap of the starting point O of the weld 300A is greater than 10mm, the weld 300A is moved from the starting point O to the narrower direction by 2mm to P (the weld 300A is extended to both ends at the O point, there must be one end being narrow and the other end being wide otherwise the reinforcing mesh 7 needs to be newly fastened), it is judged whether the gap of the starting point P of the moved weld 300A is greater than 10mm, if it is less than 10mm, the starting point of the weld 300A is P, otherwise the above procedure is repeated until the gap of the starting point of the weld 300A is less than 10mm.
Wherein, in the step of striking an arc on one of the reinforcing bars 71 at the start point of the weld 300A, the welding gun 8: the gap wm of the starting point of the weld 300A is obtained by the 3D model of the first connecting section 200, for example, the gap of the starting point of the weld 300A is 10mm, the welding gun 8 located at the middle position of the starting point of the weld 300A is shifted by 5mm and then shifted Hmm, and the welding wire 9 on the welding gun 8 is in contact with one of the reinforcing bars 71. Two steel bars 71 are provided in one connecting section 200, and the welding wire 9 on the welding gun 8 is generally in contact with the steel bars 71 on the inner side of the reinforcing mesh 7. The lowest point judged after the second vision device scans is the middle position of the starting point of the welding line 300A, but errors exist in the splicing process of the reinforcing mesh 7, and arc starting from the middle position of the starting point of the welding line 300A is easy to fail. To ensure successful arcing, an offset is required to initiate the arc at a conventional intermediate location to ensure that the wire 9 is in contact with the rebar 71 and thus has a stable arc initiation point. The gap between the bars 71 is dynamic, so that the gap error of the bars 71 is eliminated by shifting by 5mm, but the bars 71 are threaded, and the thread depth H is generally set to 5mm, so that shifting by 5mm is required to bring the welding wire 9 into contact with the bars 71 inside the mesh 7.
Wherein, in the fine positioning step: the industrial personal computer calculates the space position information of the connecting section 200 of the first reinforcing mesh model according to the offset and the 3D model template, and then the robot 4 moves to the first connecting section 200 according to the space position information of the connecting section 200 of the first reinforcing mesh model; or the industrial personal computer calculates the space position information of the connecting section 200 of the second reinforcing mesh model according to the offset and the 3D model template, and then the robot 4 moves to the first connecting section 200 according to the space position information of the connecting section 200 of the second reinforcing mesh model.
In the process of fine positioning, referring to fig. 4, the welding gun 8 adjusts the posture of the welding gun 8 according to the coordinate positions of the two reinforcing bars 71 in the 3D model of the first connecting section 200, so that the welding gun 8 is always perpendicular to the plane where the two reinforcing bars 71 are located. After the reinforcement mesh 7 is spliced, the condition that the height between the reinforcement bars 71 is fluctuated exists, and if the height difference between the reinforcement bars exceeds a certain range, the welding gun 8 can collide with the gun on the higher reinforcement bar 71, so that the welding is interrupted. The second vision device obtains the 3D model of each connecting section 200 through three-dimensional modeling, the 3D model not only can give an accurate welding seam 300 track, but also can give the coordinate position of the reinforcing steel bars 71, at the moment, the welding gun 8 can be guided to make an angle offset in the z direction through an algorithm, the welding gun 8 is always perpendicular to the plane where the two reinforcing steel bars 71 are located, the gun is prevented from being touched, the distance between the tail end of the welding gun 8 and the two reinforcing steel bars 71 is ensured to be consistent, the stability of the dry extension length parameters of welding is ensured, and the effect of a welding solution pool is ensured.
Wherein, in the process of fine positioning, the advancing speed and wire feeding speed of the welding gun 8 are adjusted according to the size of the gap of the welding seam 300. If the gap of the welding seam 300 is small, the running speed of the welding gun 8 is high, the wire feeding speed is low, and if the gap of the welding seam 300 is large, the running speed of the welding gun 8 is low, the wire feeding speed is high, and consistent continuous arc and filling amount are ensured in the step. The wire feeding speed can be adjusted by the current, the higher the current is, the faster the wire feeding speed is, and the lower the current is, the slower the wire feeding speed is.
The swing of the welding gun 8 is a fixed value, and is not automatically adjusted according to the width of the welding seam 300, and the setting is beneficial to ensuring the stability of the dry extension parameter of welding and ensuring the effect of a welding pool. The welding arc is continuously broken and the filling amount is ensured and then the advancing speed and the wire feeding speed of the welding gun 8 are adjusted.
As another embodiment of the present invention: the two operation tables 5 are respectively positioned at two sides of the guide rail 1, when the robot 4 welds the reinforcing mesh 7 on one operation table 5, the support arm 3 rotates above the operation table 5, the other operation table 5 lays or overturns the reinforcing mesh 7, and at the moment, the interference of the support arm 3 and the robot 4 is avoided, so that the working procedures are convenient to carry out. The arrangement of the rotary support arm 3 is beneficial to improving the welding efficiency of the robot 4 and is also convenient for laying and overturning the reinforcing mesh 7.
The reinforcing mesh 7 includes a plurality of first reinforcing bars 71 and a plurality of second reinforcing bars 71 in a straight line, one or both ends of the second reinforcing bars 71 are curved, and errors always exist after the second reinforcing bars 71 are manufactured due to the elastic modulus of the reinforcing bars 71, which results in that the laid reinforcing mesh 7 is inconsistent with the first reinforcing mesh model.
In the turning step: the support arm 3 is rotated so that the support arm 3 does not stay above the operation table 5, the reinforcing mesh 7 is turned 180 degrees by the lifting tool so that the back surface of the reinforcing mesh 7 faces upwards, and the reinforcing steel 71 can be lifted onto the operation table 5 by the lifting tool.
In the turning step: one side of the carrier is lapped over the operation table 5, then the reinforcing mesh 7 is turned over onto the carrier by the hanger, and then the carrier is moved over the operation table 5. Specifically, be fixed with a plurality of location side's pipe on the operation panel 5, the carrier includes a plurality of crossbeams (the crossbeam is also the side's pipe), the one end of crossbeam inserts the location side intraductal, the hoist is with reinforcing bar net 7 upset to the carrier on, the crossbeam is along location side's steel forward removal until spaning on operation panel 5, reinforcing bar net 7 places on operation panel 5 through the crossbeam this moment, the location side's pipe is equipped with the chamfer, make things convenient for reinforcing bar net 7 to cross location side's steel, the height of crossbeam is greater than the height of anchor clamps 6, in order to avoid anchor clamps 6 to influence reinforcing bar net 7.
In the invention, the first vision device continuously shoots along the reinforcing mesh 7 from beginning to end to obtain the coordinate position of the reinforcing mesh 7, and the accuracy of the reinforcing mesh 7 is low, but the speed of obtaining the position of the reinforcing mesh 7 is high and the efficiency is high. Then, the obtained coordinate positions of the reinforcing mesh 7 are moved to the vicinity of each connecting section 200, a 3D model of each connecting section 200 is obtained through photographing by a second vision device, then, the starting point positions of welding seams 300 are adjusted through the 3D models of the connecting sections 200, a welding gun 8 is shifted to enable welding wires 9 of the welding gun 8 to be in contact with reinforcing steel bars 71, and the posture of the welding gun 8 is adjusted to enable the welding gun 8 to be always perpendicular to the plane where the two reinforcing steel bars 71 are located. Thereby ensure that can strike an arc smoothly, constantly arc in welding process, guarantee welded dry elongation parameter's stability, guarantee the effect in welding the solution pond, ensure that welding process is carried out smoothly.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. The automatic welding method for the large-scale reinforcing mesh based on AI vision is characterized by comprising a working platform and an industrial personal computer, wherein the working platform comprises a guide rail and a machine base moving along the guide rail, a support arm is rotatably arranged on the machine base, a robot is slidably arranged on the support arm, a welding gun and a second vision device are arranged on the robot, a first vision device is arranged on the support arm, the working platform further comprises an operation table arranged below the robot, and the automatic welding method further comprises the following steps:
Establishing a three-dimensional template: establishing a 3D model template of a working platform, wherein the 3D model template comprises: the three-dimensional (3D) model template comprises a first reinforcing mesh model and a second reinforcing mesh model which are pre-established on the operation table, wherein the second reinforcing mesh model is formed by overturning the first reinforcing mesh model by 180 degrees, the first reinforcing mesh model and the second reinforcing mesh model both comprise the coordinate positions of a plurality of connecting sections, the industrial personal computer sorts the connecting sections of the first reinforcing mesh model and the second reinforcing mesh model respectively, the connecting sections comprise welding seams, the lengths of the welding seams are smaller than those of the connecting sections, and the connecting sections and the welding seams are in one-to-one correspondence;
Paving a reinforcing steel bar net: paving a plurality of steel bars on an operation table to form a steel bar net, and fixing adjacent steel bars through a clamp on the operation table;
Primary positioning: the machine base moves along the guide rail to drive the support arm to move from one end of the reinforcing mesh to the other end, and the support arm continuously shoots the reinforcing mesh and generates a first physical 3D model in the moving process; comparing the connecting section of the first reinforcing mesh model with the connecting section of the first physical 3D model to obtain the offset of the connecting section of the first physical 3D model in the first reinforcing mesh model;
Fine positioning: according to the offset and the 3D model template, the robot moves to the first connecting section; the second vision device acquires images of the first connecting section to obtain a 3D model of the first connecting section, the industrial personal computer obtains position coordinates of a welding line A in the first connecting section through the 3D model of the first connecting section, and then the starting point position of the welding line A is adjusted through a preset gap value; the welding gun starts an arc on one steel bar at the starting point of the welding line A, then moves to a middle position D of the two steel bars in swinging, and then moves along the extending direction of the steel bars in swinging by taking the position D as the starting point to finish the welding of the first connecting section;
Repeating the fine positioning step, and finishing welding of the residual connecting sections by the robot;
turning over: loosening the clamp, and turning over the reinforcing mesh by 180 degrees to enable the reverse surface of the reinforcing mesh to face upwards;
Primary positioning for the second time: the machine base moves along the guide rail to drive the support arm to move from one end of the reinforcing mesh to the other end, and the support arm continuously photographs the reinforcing mesh and generates a second physical 3D model in the moving process; comparing the connecting section of the second reinforcing mesh model with the connecting section of the second physical 3D model to obtain the offset of the connecting section of the second physical 3D model in the second reinforcing mesh model;
Welding the reverse side of the reinforcing mesh through a fine positioning step;
The specific steps of adjusting the starting point position of the welding line A through a preset clearance value are as follows; if the gap of the starting point of the welding line A is smaller than the preset value, the starting point of the welding line A is the current position; if the gap of the starting point of the welding line A is larger than a preset value, the welding line A moves Lmm from the starting point position to a narrower direction, if the gap of the starting point of the welding line A after the movement is smaller than the preset value, the starting point of the welding line A is the current position, otherwise, the process is repeated until the gap of the starting point of the welding line A is smaller than the preset value;
In the step of striking an arc on one steel bar at the starting point of the weld joint A, the welding gun comprises the following steps: obtaining a gap Wmm of the starting point of the weld A by the 3D model of the first connecting section, and shifting a welding gun at the middle position of the starting point of the weld A After the welding wire is shifted Hmm, the welding wire on the welding gun is contacted with a steel bar, wherein H is the thread depth of the steel bar thread;
The two operation tables are respectively positioned at two sides of the guide rail, and when the robot welds the reinforcing mesh on one operation table, the other operation table lays or overturns the reinforcing mesh.
2. The AI vision-based automatic welding method for large-scale reinforcing mesh according to claim 1, wherein in the process of fine positioning, the welding gun adjusts the posture of the welding gun according to the coordinate positions of two reinforcing bars in the 3D model of the first connecting section, so that the welding gun is always perpendicular to the plane in which the two reinforcing bars are located.
3. The AI vision-based automatic welding method for large-scale reinforcing mesh according to claim 1, wherein in the process of fine positioning, if the gap of the welding seam is small, the traveling speed of the welding gun is high, the wire feeding speed is low, and if the gap of the welding seam is large, the traveling speed of the welding gun is low, and the wire feeding speed is high.
4. The AI vision-based automatic welding method of a large-sized reinforcing mesh according to claim 1, wherein in the fine positioning step: the industrial personal computer calculates the space position information of the connecting section of the first reinforcing mesh model according to the offset and the 3D model template, and then the robot moves to the first connecting section according to the space position information of the connecting section of the first reinforcing mesh model; or the industrial personal computer calculates the space position information of the connecting section of the second reinforcing mesh model according to the offset and the 3D model template, and then the robot moves to the first connecting section according to the space position information of the connecting section of the second reinforcing mesh model.
5. The AI-vision-based automatic welding method of large-scale reinforcing mesh according to claim 1, wherein in the step of first preliminary positioning: in the moving process of the support arm, the first vision device performs image acquisition on the operation table while performing image acquisition on the reinforcing mesh, and the first vision device processes the acquired image to obtain a first physical 3D model on the operation table model.
6. The AI vision-based automatic welding method for a large-sized reinforcing mesh according to claim 1, wherein the reinforcing mesh comprises a plurality of second reinforcing bars and a plurality of first reinforcing bars in a straight line, and one or both ends of the second reinforcing bars are curved.
7. The automatic welding method of large-scale reinforcing mesh based on AI vision according to claim 1, wherein in the turning step: the support arm is rotated to prevent the support arm from staying above the operation table, and the reinforcing mesh is turned 180 degrees through the lifting appliance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311587756.6A CN117564404B (en) | 2023-11-27 | 2023-11-27 | Automatic welding method of large-scale reinforcing mesh based on AI vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311587756.6A CN117564404B (en) | 2023-11-27 | 2023-11-27 | Automatic welding method of large-scale reinforcing mesh based on AI vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117564404A CN117564404A (en) | 2024-02-20 |
| CN117564404B true CN117564404B (en) | 2024-06-14 |
Family
ID=89891455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311587756.6A Active CN117564404B (en) | 2023-11-27 | 2023-11-27 | Automatic welding method of large-scale reinforcing mesh based on AI vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117564404B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280456A (en) * | 2018-01-17 | 2018-07-13 | 湘潭大学 | A kind of recognition methods for boiler inner wall intersection welding seam |
| CN109530852A (en) * | 2018-12-26 | 2019-03-29 | 江苏新时代造船有限公司 | The welding procedure of part is found by a kind of group of boat segmental |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110605457B (en) * | 2018-06-15 | 2024-04-12 | 上海振华重工电气有限公司 | Robot automatic welding device for single-sided welding and double-sided forming of unequal-gap workpieces |
| CN110605463B (en) * | 2018-06-15 | 2021-05-18 | 上海振华重工电气有限公司 | Automatic robot welding device for submerged arc welding of spatial arc path |
| CN110524580B (en) * | 2019-09-16 | 2023-06-02 | 西安中科光电精密工程有限公司 | Welding robot vision assembly and measuring method thereof |
| CN111390915B (en) * | 2020-04-17 | 2022-07-15 | 上海智殷自动化科技有限公司 | Automatic weld path identification method based on AI |
| CN112122840B (en) * | 2020-09-23 | 2022-03-08 | 西安知象光电科技有限公司 | Visual positioning welding system and welding method based on robot welding |
| CN113334018A (en) * | 2021-06-18 | 2021-09-03 | 中建三局第二建设工程有限责任公司 | Visual guide robot automatic welding pipeline intersecting line device and method |
| CN113385869B (en) * | 2021-07-26 | 2022-05-17 | 武汉理工大学 | Robot welding equipment for large square lattice component based on machine vision and welding seam positioning method |
| CN114714029B (en) * | 2022-04-22 | 2023-09-12 | 奇瑞新能源汽车股份有限公司 | Automatic arc welding method and device for aluminum alloy |
| CN114749848A (en) * | 2022-05-31 | 2022-07-15 | 深圳了然视觉科技有限公司 | Steel bar welding automatic system based on 3D vision guide |
-
2023
- 2023-11-27 CN CN202311587756.6A patent/CN117564404B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280456A (en) * | 2018-01-17 | 2018-07-13 | 湘潭大学 | A kind of recognition methods for boiler inner wall intersection welding seam |
| CN109530852A (en) * | 2018-12-26 | 2019-03-29 | 江苏新时代造船有限公司 | The welding procedure of part is found by a kind of group of boat segmental |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117564404A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110153534B (en) | Multilayer and multi-path robot welding path planning method and system suitable for welding deformation | |
| CN111496428B (en) | Multilayer multi-pass welding bead planning method based on straight welding seam contour recognition and welding workstation | |
| JP5823278B2 (en) | Weld bead shaping device and shaping method thereof | |
| WO2015186795A1 (en) | Welding parameter derivation device | |
| CN110091039B (en) | Multilayer and multichannel welding path planning method and system for single-side V-shaped groove | |
| CN101274386B (en) | One side welding device and one side welding method | |
| CN110052692B (en) | V-groove robot welding path planning method and system | |
| JP7111666B2 (en) | Welding control method for portable welding robot, welding control device, portable welding robot, and welding system | |
| JP2002336994A (en) | Transport apparatus and welding equipment | |
| TW202202258A (en) | Control method for portable welding robot, welding control device, portable welding robot, and welding system | |
| CN113118675B (en) | Robot welding system task allocation and path planning method based on mobile platform | |
| CN110340485A (en) | A kind of molten product method of oriented energy five axis of deposition of cantilever design | |
| CN110076420B (en) | Thick plate robot dynamic welding path planning method and system considering angular deformation | |
| CN117564404B (en) | Automatic welding method of large-scale reinforcing mesh based on AI vision | |
| CN113664431A (en) | Steel structural part welding arm capable of adjusting posture in real time and adjusting method | |
| CN116921908A (en) | Welding method and welding equipment for rotating member | |
| CN105750776B (en) | The square and rectangular pipe Prewelding machine of JCO units | |
| CN114713944B (en) | Railway wagon end wall part welding method | |
| CN115837676A (en) | Track planning method for trackless transit platform | |
| JP2007090390A (en) | Welding method of rippled web beam | |
| CN113681133B (en) | Intelligent welding method of redundant degree of freedom robot with vision | |
| CN114981031A (en) | Gas-shielded arc welding method and method for manufacturing steel pipe | |
| CN105436661A (en) | Swinging arc welding method and arc welding robot | |
| JP5149526B2 (en) | Single-side welding equipment | |
| JP2005254378A (en) | Working device using articulated robot and 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 |