Automatic Welding Method for Large-Scale Steel Reinforcement Mesh Based on AI Vision

Abstract

An object of the present invention is to provide an automatic welding method for large-scale steel bar meshes based on AI vision. 【Solution means】 It includes a work platform and an industrial computer. The work platform includes a guide rail and a pedestal that moves along the guide rail. A support arm is rotatably provided on the pedestal, a robot is slidably provided on the support arm, a welding torch and a second vision device are provided on the robot, a first vision device is provided on the support arm, and the work platform further includes an operation table provided under the robot. It also includes a three-dimensional template construction step, a steel bar mesh laying step, a first rough positioning step, a precise positioning step, a turning-over step, and a second rough positioning step and a precise positioning step. Compared with the prior art, the present invention completes the rough positioning of the steel bar mesh through the first vision device, then improves the positioning accuracy of the steel bar mesh through the second vision device, meets the requirements of robot welding, has a high welding speed and high efficiency for the steel bar mesh. Especially when welding large-scale steel bar meshes, the welding speed is significantly faster than that of a welding robot using manual teaching.

Description

Technical Field

[0001] The present invention relates to the technical field of steel mesh welding, and in particular, to an automatic welding method for large steel meshes based on AI vision.

Background Art

[0002] In the construction industry, a large number of ready-made products with steel mesh structures are widely used. Currently, for ready-made products with steel mesh structures, it is common to bind or weld the intersections of the steel meshes manually. However, manual welding has limitations such as unstable welding quality, low construction efficiency, high welding cost, and inability to work under extreme conditions such as high temperature and high pressure. Currently, mechanized automatic welding technology is widely used in various fields such as automobiles, aerospace, and industrial manufacturing. Usually, to meet the requirements of the welding process, it depends on high-precision position limitation of the workpieces and needs to be combined with multiple path teach-ins of the robot welding torch. However, the steel bars themselves are bent, and errors also occur in the bent steel bars due to the characteristics of the elastic modulus. The joined steel bar meshes are inevitably irregular, the gaps between the steel bars are uneven, and there are also steps between the steel bars. These prevent arc starting, cause arc interruption during the process, lead to collisions, and ultimately result in the failure of automatic welding by machines.

Summary of the Invention

Problems to be Solved by the Invention

[0003] The present invention provides an automatic welding method for large steel meshes based on AI vision to solve the problems of irregularity of large steel meshes, large gaps, and difficulty in automatic welding.

Means for Solving the Problems

[0004] The present invention provides an automatic welding method for large steel bar meshes based on AI vision, comprising a working platform and an industrial computer. The working platform comprises a guide rail and a pedestal moving along the guide rail. A support arm is rotatably provided on the pedestal, a robot is slidably provided on the support arm, a welding torch and a second vision device are provided on the robot, and a first vision device is provided on the support arm. The working platform further comprises an operation table provided under the robot, and also includes the following steps. Step of constructing a three-dimensional template: Construct a 3D model template of the working platform, which includes the coordinate positions of the robot, the operation table, the guide rail, the pedestal, the support arm and the first vision device, the first steel bar mesh model and the second steel bar mesh model pre-constructed on the operation table. The second steel bar mesh model is obtained by inverting the first steel bar mesh model by 180 degrees. Both the first steel bar mesh model and the second steel bar mesh model include the coordinate positions of a plurality of joint sections. The industrial computer rearranges the joint sections of the first steel bar mesh model and the joint sections of the second steel bar mesh model respectively. The joint section is provided with a welding seam, the length of the welding seam is shorter than the length of the joint section, and the joint section and the welding seam are in one-to-one correspondence. Step of laying the steel bar mesh: Lay a plurality of steel bars on the operation table to form a steel bar mesh, and fix the space between adjacent steel bars with clips on the operation table. First rough positioning step: The pedestal moves along the guide rail to move the support arm from one end of the steel bar mesh to the other end. While the support arm is moving, the first vision device continuously shoots the steel bar mesh to generate a first physical 3D model, compares the joint section of the first steel bar mesh model with the joint section of the first physical 3D model, and obtains the offset amount of the joint section of the first physical 3D model in the first steel bar mesh model. Precision positioning step: Based on the offset amount and the 3D model template, the robot moves to the first joint section. The second vision device collects an image of the first joint section to obtain a 3D model of the first joint section. Through the 3D model of the first joint section, the industrial computer obtains the position coordinates of the weld seam A in the first joint section. Then, through a preset gap value, the starting position of the weld seam A is adjusted. The welding torch starts an arc on one steel bar at the starting point of the weld seam A, then moves to the middle position D between the two steel bars during the oscillation, and starts from D to complete the welding of the first joint section along the extending direction of the steel bar during the oscillation. Repeat the precision positioning step, and the robot completes the welding of the remaining joint sections. Turning-over step: Loosen the clip and invert the steel mesh 180 degrees so that the back side of the steel mesh faces upward. Second rough positioning step: The pedestal moves along the guide rail to move the support arm from one end of the steel mesh to the other end. While the support arm is moving, the first vision device continuously captures the steel mesh to generate a second physical 3D model. Compare the joint section of the second steel mesh model with the joint section of the second physical 3D model to obtain the offset amount of the joint section of the second physical 3D model in the second steel mesh model. Complete the welding on the back side of the steel mesh through the precision positioning step.

[0005] Preferably, the specific steps for adjusting the starting position of the weld seam A through a preset gap value are as follows: When the gap at the starting point of the weld seam A is smaller than the preset value, the starting point of the weld seam A remains at the current position. When the gap at the starting point of the weld seam A is larger than the preset value, the weld seam A moves Lmm in the narrow direction from the starting position. When the gap at the starting point of the weld seam A after the movement is smaller than the preset value, the starting point of the weld seam A remains at the current position. When it is larger than the preset value, repeat the above process until the gap at the starting point of the weld seam A is smaller than the preset value.

[0006] Preferably, in the step of starting an arc on one steel bar at the starting point of the weld seam A, the welding torch obtains the gap W mm at the starting point of the weld seam A through the 3D model of the first joint section, offsets the welding torch at the intermediate position of the starting point of the weld seam A by half of W mm, and further offsets it by H mm. Then, the welding wire on the welding torch contacts one steel bar, where H represents the depth of the thread of the steel bar.

[0007] Preferably, in the precise positioning process, the welding torch adjusts the posture of the welding torch according to the coordinate positions of the two steel bars in the 3D model of the first joint section so that the two steel bars are always perpendicular to the plane where they are located.

[0008] Preferably, in the precise positioning process, when the gap of the weld seam is small, the moving speed of the welding torch is fast and the wire feeding speed is slow. When the gap of the weld seam is large, the moving speed of the welding torch is slow and the wire feeding speed is fast.

[0009] Preferably, in the precise positioning step, the industrial computer calculates the spatial position information of the joint section of the first steel bar mesh model based on the offset amount and the 3D model template. Then, the robot moves to the first joint section based on the spatial position information of the joint section of the first steel bar mesh model. Or the industrial computer calculates the spatial position information of the joint section of the second steel bar mesh model based on the offset amount and the 3D model template. Then, the robot moves to the first joint section based on the spatial position information of the joint section of the second steel bar mesh model.

[0010] Preferably, there are two operation tables. The two operation tables are respectively located on both sides of the guide rail. When the robot is welding the steel bar mesh on one of the operation tables, the steel bar mesh is laid or inverted on the other operation table.

[0011] Preferably, in the first rough positioning step, while the support arm is moving, the first vision device collects an image of the steel mesh and also collects an image of the operation table, and processes the images collected by the first vision device to obtain a first physical 3D model on the operation table model.

[0012] Preferably, the steel mesh includes a plurality of second steel bars and a plurality of straight first steel bars, and one or both ends of the second steel bars are curved.

[0013] Preferably, in the turning-over step, the support arm is rotated so that the support arm does not stay on the operation table, and the steel mesh is inverted 180 degrees through the lifting tool.

Advantages of the Invention

[0014] Compared with the prior art, in the present invention, the first vision device takes continuous shots from the beginning to the end along the steel mesh to obtain the coordinate position of the steel mesh. Although the accuracy of the steel mesh is low, the speed of obtaining the position of the steel mesh is fast and the efficiency is high. Then, through the obtained coordinate position of the steel mesh, it moves to the vicinity of each joint section, takes a photo with the second vision device to obtain a 3D model of each joint section, and through the 3D model of the joint section, adjusts the starting position of the weld seam, offsets the welding torch so that the welding wire of the welding torch contacts the steel bar, and sets two undulation points to complete the welding of the joint section, and adjusts the posture of the welding torch so that the welding torch is always perpendicular to the plane where the two steel bars are located during the welding process. Thereby, the arc starting is smooth, the arc breakage does not occur during the welding process, the stability of the wire protruding length parameter of the welding is ensured, the effect of the welding molten pool is also ensured, and it is ensured that the welding process continues smoothly.

[0015] Hereinafter, to clearly explain the technical means within the embodiments of the present invention or the prior art, the accompanying drawings necessary for depicting the embodiments or the prior art will be briefly described. The accompanying drawings described below are only some embodiments of the present invention, and based on these accompanying drawings, other accompanying drawings can be obtained on the premise that those skilled in the art do not perform creative activities.

Brief Description of the Drawings

[0016]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Modes for Carrying Out the Invention

[0017] Hereinafter, to make the object, technical means, and advantages of the present invention clearer, while referring to the accompanying drawings of the present invention, the technical means of the present invention will be clearly and completely described. The embodiments to be described are some embodiments of the present invention, and it goes without saying that they are not all embodiments. Based on the embodiments in the present invention, all other implementations obtained by those skilled in the art on the premise of not performing creative activities all belong to the protection scope of the present invention.

[0018] Referring to FIGS. 1 to 3, the present embodiment provides an automatic welding method for large steel bar meshes based on AI vision, and includes a work platform 100 and an industrial computer. The work platform 100 includes a guide rail 1 and a pedestal 2 that moves along the guide rail 1. A support arm 3 is rotatably provided on the pedestal 2, a robot 4 is slidably provided on the support arm 3, a welding torch and a second vision device are provided on the robot 4, a first vision device is provided on the support arm 3, the work platform 100 further includes an operation table 5 provided under the robot 4, and a plurality of clips 6 are provided on the operation table 5. The following steps are also included.

[0019] Step of constructing a three-dimensional template: Construct a 3D model template of the work platform 100. The 3D model template includes the coordinate positions of the robot 4, the coordinate position of the operation table 5, the coordinate position of the guide rail 1, the coordinate position of the pedestal 2, the coordinate position of the support arm 3, and the coordinate position of the first vision device, the first steel bar mesh model and the second steel bar mesh model pre-constructed on the operation table 5. The second steel bar mesh model is obtained by inverting the first steel bar mesh model by 180 degrees. Both the first steel bar mesh model and the second steel bar mesh model include the coordinate positions of a plurality of joint sections 200. The industrial computer rearranges the joint sections 200 of the first steel bar mesh model and the joint sections 200 of the second steel bar mesh model respectively. The joint section 200 includes a weld seam 300. The length of the weld seam 300 is shorter than the length of the joint section 200. The joint section 200 and the weld seam 300 are in one-to-one correspondence. Each of the joint sections 200 includes a weld seam 300. Positioning the joint section 200 is equivalent to positioning the weld seam 300. Since it is necessary to weld the other side (back side) after welding one side (front side) of the steel bar mesh 7, it is necessary to construct two steel bar mesh 7 models on the operation table 5. The joint section 200 is a part where two steel bars 71 in the steel bar mesh 7 are closed. There are parts where the two steel bars 71 in the joint section 200 are in contact and parts where they are not in contact, but the gap is relatively small (as shown in the figure).

[0020] Laying steps of the steel mesh 7: Lay a plurality of steel bars 71 on the operation table 5 to form the steel mesh 7, and fix the space between adjacent steel bars 71 with clips 6 on the operation table 5. The steel mesh 7 needs to be joined together with the steel bars 71. During the joining process, many errors occur, such as the straightness of the steel bars 71 themselves and the characteristics of the elastic modulus of the steel bars 71. These errors cause differences between the joined steel mesh 7 and the steel mesh 7 in the 3D model template. These differences may affect the automatic welding of the steel mesh 7 by causing failures in arc starting, arc interruption during the welding process, changes in the wire protruding length, etc.

[0021] The first rough positioning step: The pedestal 2 moves along the starting point of the guide rail 1 to the end point of the guide rail 1 to move the support arm 3 from one end of the steel mesh 7 to the other end. While the support arm 3 is moving, the first vision device continuously captures the steel mesh 7 to generate a first physical 3D model. During this process, the height position of the support arm 3, that is, the height position of the first vision device, is determined. The first vision device collects the image of the steel mesh 7 and also collects the image of the operation table 5. The image collected by the first vision device is processed to obtain the first physical 3D model on the operation table 5 model. The first physical 3D model includes the model of the steel mesh 7 and the model of the operation table 5. The operation table 5 remains unchanged throughout, and the coordinate position of the operation table 5 is determined. When comparing the joint section 200 of the first steel mesh model and the joint section 200 of the first physical 3D model, after overlapping the operation table 5 of the 3D model template and the operation table 5 of the first physical 3D model with the operation table 5 as the common reference point, the offset amount of the joint section 200 of the first physical 3D model in the first steel mesh model is obtained. Then, through this offset amount, the coordinate position of the joint section 200 of the steel mesh 7 is obtained. In this step, the coordinate position of the joint section 200 of the steel mesh 7 (physical object) is obtained by moving the first vision device to collect and process images, with high speed and efficiency. However, in order to capture all of the steel mesh 7 in the width direction, the first vision device is installed high, resulting in insufficient shooting accuracy. As a result, there is a certain error in the coordinate position of the joint section 200 of the obtained steel mesh, making it difficult to meet the welding needs of the robot 4.

[0022] Precision positioning step: Based on the offset amount and the 3D model template, the robot 4 moves to the first joint section 200. The second vision device collects an image of the first joint section 200 to obtain a 3D model of the first joint section 200. Through the 3D model of the first joint section 200, the industrial computer obtains the position coordinates of the weld seam 300A in the first joint section 200. Then, through a preset gap value, the starting position of the weld seam 300A is adjusted. Referring to FIG. 6, the welding torch 8 starts an arc at point C on one steel bar 71 at the starting point of the weld seam 300A, then moves to the middle position D between the two steel bars 71 during oscillation, and then moves from D as the starting point to point E along the extending direction of the steel bar 71 during oscillation to complete the welding of the first joint section 200. In this step, the industrial computer obtains the position coordinates of the weld seam 300A in the first joint section 200. By obtaining the position coordinates of the weld seam 300A, the difference between the actual steel mesh 7 and the steel mesh 7 in the 3D model template is eliminated. However, if the gap at the starting point of the weld seam 300A is too large, there may be a situation where the arc cannot start and welding cannot be performed. Therefore, the starting position of the weld seam 300A is adjusted through a preset gap value to ensure that the gap at the starting point of the weld seam 300A meets the arc-starting requirements of the welding torch 8, so that the arc cannot start and welding cannot occur, and to ensure that the welding process can proceed smoothly. Next, the welding torch 8 starts an arc on one steel bar 71 at the starting point of the weld seam 300A, which is the first arc-starting point. The welding wire 9 of the welding torch 8 during the first arc start contacts the steel bar 71 (ensuring a smooth arc start), then moves to the middle position D between the two steel bars 71 during oscillation. D is the second arc-starting point, and then moves along the extending direction of the steel bar 71 from D as the starting point during oscillation to complete the welding of the first joint section 200. The welding wire 9 of the welding torch 8 during the second arc start contacts the metal strip reliably (ensuring a smooth arc start) due to the welded metal strip from the first arc-starting point to D.By providing two arc starting points, electric welding enables 100% arc starting and ensures that the welding process proceeds smoothly.

[0023] The robot 4 repeats the precise positioning step to complete the welding of the remaining joint section 200. For example, according to the offset amount and the 3D model template, the robot 4 moves to the second joint section 200. The second vision device collects an image of the second joint section 200 to obtain a 3D model of the second joint section 200. Through the 3D model of the second joint section 200, the industrial computer obtains the position coordinates of the weld seam 300B within the second joint section 200. Then, through the method of adjusting the starting point position of the weld seam 300B according to the preset gap value, the position of the weld seam 300 is obtained. The welding torch 8 starts an arc on one steel bar 71 at the starting point of the weld seam 300B, then moves to the middle position D between the two steel bars 71 during oscillation, and starting from D, moves along the extending direction of the steel bar 71 during oscillation to complete the welding of the second joint section 200.

[0024] Turning - over step: Loosen the clip 6, and invert the steel - bar mesh 7 by 180 degrees so that the back side of the steel - bar mesh 7 faces upward. Second rough - positioning step: The pedestal 2 moves along the guide rail 1 to move the support arm 3 from one end of the steel - bar mesh 7 to the other end. While the support arm 3 is moving, the first vision device takes consecutive pictures of the steel - bar mesh 7 to generate a second physical 3D model. Compare the joint section 200 of the second steel - bar mesh model with the joint section 200 of the second physical 3D model to obtain the offset amount of the joint section 200 of the second physical 3D model in the second steel - bar mesh model. Complete the welding on the back side of the steel - bar mesh 7 through the precise positioning step.

[0025] The specific steps to adjust the starting position of the weld seam 300A through a preset gap value are as follows: When the gap at the starting point of the weld seam 300A is smaller than the preset value, for example, when the gap at the starting point of the weld seam 300A is less than 10 mm, there is no need to offset the weld seam 300A. Referring to Fig. 5, when the gap at the starting point O of the weld seam 300A is greater than 10 mm, the weld seam 300A moves 2 mm in the narrow direction from the starting point O to reach P (when the weld seam 300A extends at both ends at the starting point O, one end must be narrow and the other end must be wide. Otherwise, it is necessary to refix the steel mesh 7), and then determine whether the gap at the starting point P of the weld seam 300A after movement is greater than 10 mm. If it is less than 10 mm, the starting point of the weld seam 300A is P. If it is greater than 10 mm, repeat the above process until the gap at the starting point of the weld seam 300A is less than 10 mm.

[0026] In the step of starting an arc on one steel bar at the starting point of the welding joint 300A, the gap Wmm at the starting point of the welding joint 300A is obtained through the 3D model of the first joint section 200. For example, the gap at the starting point of the welding joint 300A is 10 mm. The welding torch 8 at the middle position of the starting point of the welding joint 300A is offset by 5 mm, and after further offset by Hmm, the welding wire 9 on the welding torch 8 contacts one steel bar 71. There are two steel bars 71 within one joint section 200, and the welding wire 9 of the welding torch 8 usually contacts the inner steel bar 71 of the steel bar mesh 7. The lowest point determined after scanning by the second vision device is at the middle position of the starting point of the welding joint 300A, but there are errors during the process of connecting the steel bar meshes 7. When starting an arc from the middle position of the starting point of the welding joint 300A, it is easy to fail. To ensure the successful start of the arc, it is necessary to offset the conventional arc start at the middle position so that the welding wire 9 surely contacts the steel bar 71 and has a stable arc start point. Since the value of the gap between the steel bars 71 is dynamic, first offset by 5 mm to eliminate the gap error of the steel bar 71. However, there are threads on the steel bar 71, and generally the height H of the thread is set to 5 mm. Therefore, further offset by 5 mm to make the welding wire 9 contact the inner steel bar 71 of the steel bar mesh 7.

[0027] In the precise positioning step, the industrial computer calculates the spatial position information of the joint section 200 of the first steel bar mesh model based on the offset amount and the 3D model template. Then, the robot 4 moves to the first joint section 200 based on the spatial position information of the joint section 200 of the first steel bar mesh model. Or the industrial computer calculates the spatial position information of the joint section 200 of the second steel bar mesh model based on the offset amount and the 3D model template. Then, the robot 4 moves to the first joint section 200 based on the spatial position information of the joint section 200 of the second steel bar mesh model.

[0028] In the precise positioning process, referring to FIG. 4, the welding torch 8 adjusts its posture according to the coordinate positions of the two steel bars 71 in the 3D model of the first joint section 200 so as to always be perpendicular to the plane where the two steel bars 71 are located. After the reinforcement mesh 7 is joined, a height variation occurs between the steel bars 71. When the height difference between the two exceeds a certain range, the welding torch 8 hits the higher steel bar 71, causing the welding to be interrupted. The second vision device obtains the 3D model of each joint section 200 through 3D modeling. The 3D model not only provides the accurate welding seam 300 trajectory but also the coordinate positions of the steel bars 71. At this time, through the algorithm, the welding gun 8 is guided to perform an angular offset in the z direction so that the welding torch 8 is always perpendicular to the plane where the two steel bars 71 are located, realizing that it does not hit, and ensuring that the distance between the end of the welding torch 8 and the two steel bars 71 is consistent, guaranteeing the stability of the wire protruding length parameter of the welding and also guaranteeing the effect of the welding molten pool.

[0029] In the precise positioning process, the moving speed of the welding torch 8 and the wire feeding speed are adjusted according to the size of the gap of the welding seam 300. When the gap of the welding seam 300 is small, the moving speed of the welding torch 8 is fast and the wire feeding speed is slow. When the gap of the welding seam 300 is large, the moving speed of the welding torch 8 is slow and the wire feeding speed is fast. In this step, it is ensured that arc interruption does not occur and the filling amount is consistent. The wire feeding speed can be adjusted by the magnitude of the current. The larger the current, the faster the wire feeding speed, and the smaller the current, the slower the wire feeding speed.

[0030] The amplitude of the welding torch 8 is set to a fixed value instead of being automatically adjusted according to the width of the welding seam 300. This setting ensures the stability of the wire protruding length parameter of the welding and also guarantees the effect of the welding molten pool. The prevention of arc interruption and the guarantee of the filling amount in welding are adjusted by the moving speed of the welding torch 8 and the wire feeding speed.

[0031] As another embodiment of the present invention, there are two operation tables 5, and the two operation tables 5 are respectively located on both sides of the guide rail 1. When the robot 4 is welding the steel mesh 7 on one operation table 5, the support arm 3 rotates above the operation table 5, and the steel mesh 7 is laid or inverted on the other operation table 5. At this time, there is no interference between the support arm 39 and the robot 4, and these processes can proceed smoothly. By rotating the support arm 3, it helps to improve the welding efficiency of the robot 4 and facilitates the laying and inversion of the steel mesh 7.

[0032] The steel mesh 7 includes a plurality of straight first steel bars 71 and a plurality of second steel bars 71. One end or both ends of the second steel bar 71 are curved. Due to the characteristics of the elastic modulus of the steel bar 71, errors always occur after the manufacture of the second steel bar 71, so that the laid steel mesh 7 does not match the first steel mesh model.

[0033] In the turning - over step, the support arm 3 is rotated so that the support arm 3 does not stay on the operation table 5, and the steel mesh 7 is inverted 180 degrees through the lifting tool, so that the back surface of the steel mesh 7 faces upward, and it is natural that the steel bar 71 can be carried onto the operation table 5 by the lifting tool.

[0034] In the turning - over step, one side of the mounting table is joined onto the operation table 5, and then the steel mesh 7 is inverted onto the mounting table through the lifting tool, and then the mounting table is moved onto the operation table 5. Specifically, a plurality of positioning angle pipes are fixed on the operation table 5. The mounting table is provided with a plurality of cross - bars (the cross - bars are also angle pipes). One end of the cross - bar is inserted into the positioning angle pipe. The lifting tool inverts the steel mesh 7 onto the mounting table, and the cross - bar advances along the positioning angle pipe until it spans the operation table 5. At this time, the steel mesh 7 is placed on the operation table 5 through the cross - bar. The positioning angle pipe is chamfered so that the steel mesh 7 can easily pass through the positioning angle pipe. The height of the cross - bar is greater than the height of the clip 6 so that the clip 6 does not affect the steel mesh 7.

[0035] In the present invention, the first vision device takes continuous shots from the beginning to the end along the steel mesh 7 to obtain the coordinate positions of the steel mesh 7. Although the accuracy of the steel mesh 7 is low, the speed of obtaining the position of the steel mesh 7 is fast and the efficiency is high. Then, through the obtained coordinate positions of the steel mesh 7, it moves to the vicinity of each joint section 200, takes a photo with the second vision device to obtain a 3D model of each joint section 200, and through the 3D model of the joint section 200, adjusts the starting position of the weld seam 300, offsets the welding torch 8 to make the welding wire 9 of the welding torch 8 contact the steel bar 71, and adjusts the posture of the welding torch 8 so that the welding torch 8 is always perpendicular to the plane where the two steel bars 71 are located. Thereby, the arc starting is smooth, the arc breakage does not occur during the welding process, the stability of the wire protruding length parameter of the welding is ensured, the effect of the welding molten pool is also ensured, and it is ensured that the welding process continues smoothly.

[0036] Finally, it should be noted that the above embodiments are only for clarifying the technical means of the present invention and are not for limiting and interpreting the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that the technical means described in each of the foregoing embodiments can be modified or a part of the technical features can be replaced with equivalents. Such modifications or replacements do not deviate from the essence of the corresponding technical means from the spirit and scope of the technical means of each embodiment of the present invention.

Explanation of Reference Numerals

[0037] 100 Working platform 1 Guide rail 2 Pedestal 3 Support arm 4 Robot 5 Operation table 6 Clip 7 Steel mesh

Claims

1. A method for automatic welding of large rebar meshes based on AI vision, comprising: a work platform; and an industrial computer, the work platform comprising a guide rail and a pedestal that moves along the guide rail; a support arm rotatably mounted on the pedestal; a robot slidably mounted on the support arm; a welding torch and a second visual device mounted on the robot; a first visual device mounted on the support arm; and the work platform further comprising an operation table mounted under the robot; 3D template construction step: construct a 3D model template of the working platform, the 3D model template includes the coordinate position of the robot, the coordinate position of the operation table, the coordinate position of the guide rail, the coordinate position of the base, the coordinate position of the support arm and the coordinate position of the first visual device, a first rebar mesh model and a second rebar mesh model pre-constructed on the operation table, the second rebar mesh model is a 180° inversion of the first rebar mesh model, the first rebar mesh model and the second rebar mesh model both include coordinate positions of a plurality of joint sections, the industrial computer respectively rearranges the joint sections of the first rebar mesh model and the joint sections of the second rebar mesh model, the joint sections have weld seams, the length of the weld seams is shorter than the length of the joint sections, and the joint sections and the weld seams correspond one-to-one; A reinforcing bar mesh laying step: laying a plurality of reinforcing bars on the operation table to form the reinforcing bar mesh, and fixing adjacent reinforcing bars with clips on the operation table; First rough positioning step: the base moves along the guide rail to move the support arm from one end of the reinforcing steel mesh to the other end, and while the support arm is moving, the first vision device takes continuous images of the reinforcing steel mesh to generate a first actual 3D model, compares the joint section of the first reinforcing steel mesh model with the joint section of the first actual 3D model, and obtains an offset amount of the joint section of the first reinforcing steel mesh model in the first actual 3D model; Precision positioning step: according to the offset amount and the 3D model template, the robot moves to the first joint section, the second vision device collects images of the first joint section to obtain a 3D model of the first joint section, the industrial computer obtains the position coordinate of the weld seam A in the first joint section through the 3D model of the first joint section, and then adjusts the start position of the weld seam A through a preset gap value, the welding torch starts an arc on one of the steel bars at the start of the weld seam A, and then moves to a middle position D between the two steel bars during swinging, and completes the welding of the first joint section along the extension direction of the steel bars during swinging from D as the starting point; Repeating the fine positioning step, the robot completes welding of the remaining joint sections; Flip step: loosen the clips and flip the rebar mesh 180 degrees so that the back side of the rebar mesh faces up; A second rough positioning step: the base moves along the guide rail to move the support arm from one end of the reinforcing steel mesh to the other end, and while the support arm is moving, the first vision device takes continuous images of the reinforcing steel mesh to generate a second actual 3D model, compares the joint section of the second reinforcing steel mesh model with the joint section of the second actual 3D model, and obtains an offset amount of the joint section of the second reinforcing steel mesh model in the second actual 3D model; The welding of the back side of the reinforcing steel mesh is completed through the precision positioning step. A method for automatic welding of large rebar meshes based on AI vision, comprising the steps of:

2. The specific step of adjusting the start position of the weld seam A through the preset gap value is as follows: if the gap at the start point of the weld seam A is smaller than a preset value, the start point of the weld seam A becomes a current position; if the gap at the start point of the weld seam A is larger than the preset value, the weld seam A moves L mm in a narrower direction from the start position; if the gap at the start point of the weld seam A after the movement is smaller than the preset value, the start point of the weld seam A becomes a current position; if the gap at the start point of the weld seam A is larger than the preset value, the above process is repeated until the gap at the start point of the weld seam A becomes smaller than the preset value.

3. 2. The method for automatic welding of large reinforcing steel meshes based on AI vision according to claim 1, wherein in the step of starting an arc on one of the steel bars at the start of the weld seam A, a gap W mm at the start of the weld seam A is obtained through the 3D model of the first joint section, and the welding torch at the middle position of the start of the weld seam A is offset by half W mm, and then further offset by H mm, after which the welding wire on the welding torch contacts the one of the steel bars, where H represents the height of the thread of the steel bar.

4. The method for automatic welding of large reinforcing steel meshes based on AI vision as described in claim 1, characterized in that in the precision positioning process, the welding torch adjusts the posture of the welding torch according to the coordinate positions of the two steel bars in the 3D model of the first joint section so that the two steel bars are always perpendicular to a plane.

5. The automatic welding method for large reinforcing steel mesh based on AI vision as claimed in claim 4, characterized in that in the precision positioning process, when the gap of the weld seam is small, the moving speed of the welding torch is fast and the feeding speed of the wire is slow, and when the gap of the weld seam is large, the moving speed of the welding torch is slow and the feeding speed of the wire is fast.

6. 2. The method for automatic welding of large reinforcing steel meshes based on AI vision according to claim 1, wherein in the precision positioning step, the industrial computer calculates spatial position information of the joint section of the first reinforcing steel mesh model based on the offset amount and the 3D model template, and then the robot moves to the first joint section based on the spatial position information of the joint section of the first reinforcing steel mesh model, or the industrial computer calculates spatial position information of the joint section of the second reinforcing steel mesh model based on the offset amount and the 3D model template, and then the robot moves to the first joint section based on the spatial position information of the joint section of the second reinforcing steel mesh model.

7. The automatic welding method for large reinforcing steel mesh based on AI vision as described in claim 1, characterized in that there are two operation tables, the two operation tables are located on both sides of the guide rail, and when the robot is welding the reinforcing steel mesh on one operation table, the other operation table lays or flips over the reinforcing steel mesh.

8. 2. The method for automatic welding of large reinforcing steel meshes based on AI vision according to claim 1, characterized in that in the first rough positioning step, while the support arm is moving, the first vision device collects images of the reinforcing steel mesh and also collects images of the operation table, and processes the images collected by the first vision device to obtain the first real 3D model on the model of the operation table.

9. The automatic welding method for large reinforcing steel mesh based on AI vision described in claim 1, characterized in that the reinforcing steel mesh comprises a plurality of second steel bars and a plurality of straight first steel bars, and one or both ends of the second steel bars are curved.

10. The automatic welding method for large reinforcing steel mesh based on AI vision as described in claim 7, characterized in that in the flipping step, the support arm is rotated so that the support arm does not remain on the operation table, and the reinforcing steel mesh is flipped 180 degrees through a hanging device.

Images