CN210731420U - Automatic welding device based on machine vision and AI algorithm - Google Patents
Automatic welding device based on machine vision and AI algorithm Download PDFInfo
- Publication number
- CN210731420U CN210731420U CN201920757510.1U CN201920757510U CN210731420U CN 210731420 U CN210731420 U CN 210731420U CN 201920757510 U CN201920757510 U CN 201920757510U CN 210731420 U CN210731420 U CN 210731420U
- Authority
- CN
- China
- Prior art keywords
- welding
- algorithm
- robot
- machine vision
- welding device
- 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
Images
Abstract
The utility model discloses an automatic welder based on machine vision and AI algorithm, including the robot, the robot is provided with arm, welder and industry camera, and the arm is provided with the first cantilever of fixed welder and industry camera, and welder sets up in the end of first cantilever, and industry camera sets up in the radial outside of first cantilever. The utility model discloses an automatic welding device based on machine vision and AI algorithm can improve the precision of welding track, and then, ensures welding quality for automatic welding device is really high-efficient; moreover, the relative position of the welding gun and the industrial camera is fixed and easy to convert, and a user can conveniently control and debug.
Description
Technical Field
The utility model relates to a welding equipment field especially relates to an automatic welder based on machine vision and AI algorithm.
Background
In the prior art, automatic welding is an effective way for improving welding efficiency and reducing labor cost. Correspondingly, automatic welding device is also by extensive application, and common automatic welding device includes industrial robot, and the last welder that installs of industrial robot.
It is common, edit out the welding seam data according to the product drawing earlier, also, the movement track of welder tip during welding, then with the leading-in industrial robot of welding seam data, then, manual regulation welder, make welder tip be close to welding starting point on the product, record current industrial robot's coordinate, and set industrial robot starting point into with current coordinate, finally, industrial robot drives the welder action, welder begins the welding from the starting point, and move along the welding seam track, accomplish the welding.
However, the manufacturing and positioning of the product are deviated, which results in the reduction of welding quality.
SUMMERY OF THE UTILITY MODEL
The utility model discloses aim at solving above-mentioned technical problem, provide an automatic welder based on machine vision and AI algorithm, the manufacturing and the positioning error of automatic compensation product, accurate welding ensures welding quality.
The utility model discloses a realize through following technical scheme:
an aspect of the utility model is to provide an automatic welder based on machine vision and AI algorithm, including the robot, the robot is provided with arm, welder and industry camera, and the arm is provided with the first cantilever of fixed welder and industry camera, and welder sets up in the end of first cantilever, and industry camera sets up in the radial outside of first cantilever.
Beneficially, compared with the prior art, the utility model discloses an automatic welding device based on machine vision and AI algorithm can improve the precision of welding track, and then, ensures welding quality, makes automatic welding device really high-efficient; moreover, the relative position of the welding gun and the industrial camera is fixed and easy to convert, and a user can conveniently control and debug.
According to a second aspect of the present invention, an automatic welding device based on machine vision and AI algorithm, preferably,
according to the utility model discloses an automatic welder based on machine vision and AI algorithm of second aspect, it is preferred, still include the anchor clamps of fixed product, drive the first swivel mount of anchor clamps horizontal rotation adjustment.
Beneficially, through setting up first swivel mount for automatic welder can weld the different sides of product, overcomes the big and limited circumstances of robot welding scope of product size.
According to the utility model discloses an automatic welder based on machine vision and AI algorithm of second aspect, it is preferred, anchor clamps be the rectangle that the level set up, and the diagonal position of anchor clamps sets up the tight subassembly that presss from both sides of fixed product.
The clamp assembly for fixing the product is arranged at the diagonal position of the clamp, so that the shielding of the clamp assembly on a welding gun can be reduced, the debugging difficulty is reduced, the product switching is facilitated, the welding route is easy to optimize, and the influence of the interference of the welding gun route is avoided.
According to the utility model discloses an automatic welder based on machine vision and AI algorithm of second aspect, it is preferred, clamping component includes the briquetting, drives the rotatory revolving cylinder that goes up and down of briquetting.
Beneficially, utilize revolving cylinder, can avoid the briquetting to shelter from the product in upper and lower direction, the dismouting mode of extension product conveniently takes out the product from anchor clamps.
According to the utility model discloses an automatic welder based on machine vision and AI algorithm of second aspect, it is preferred, anchor clamps still include side profiling and side direction compressing tightly the piece.
Beneficially, through setting up side profiling and side direction and compressing tightly the piece, increase the restraint to the product, reduce the deformation of product for the product size after the welding finishes accords with the drawing requirement and the precision is high.
According to the utility model discloses an automatic welder based on machine vision and AI algorithm of second aspect, it is preferred, anchor clamps and first revolving stage are provided with two sets ofly, set up respectively in the relative both sides of robot.
The welding robot has the advantages that when the robot welds a product on one clamp, the robot can disassemble and assemble a product on the other clamp, so that the pause of the robot is reduced, and the welding efficiency is improved.
According to the utility model discloses an automatic welder based on machine vision and AI algorithm of second aspect, it is preferred, the robot is provided with the second swivel mount of connecting the arm, and the arm passes through the second swivel mount and connects ground, and the second swivel mount is used for driving the arm and rotates along the horizontal direction.
Beneficially, directly drive the arm through the second swivel mount and rotate for the robot can be quick begin the welding, need not detailed debugging again, shortens the debugging time.
Drawings
In order to more clearly illustrate the technical solution in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly described below.
It is clear that the described figures represent only some embodiments of the invention, not all embodiments, and that a person skilled in the art can also derive other designs and figures from these figures without inventive effort.
Fig. 1 is a schematic structural view of a welding device of the present invention;
fig. 2 is a flow chart of an automatic welding method of the welding device of the present invention;
fig. 3 is a calculation diagram of the calculation step and the scaling step in fig. 2.
Detailed Description
This section will describe in detail the embodiments of the present invention, preferred embodiments of the present invention are shown in the attached drawings, which are used to supplement the description of the text part of the specification with figures, so that one can intuitively and vividly understand each technical feature and the whole technical solution of the present invention, but they cannot be understood as the limitation of the protection scope of the present invention.
In the description of the present invention, it should be understood that the orientation or positional relationship indicated with respect to the orientation description, such as up, down, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, a plurality of means are one or more, a plurality of means are two or more, and the terms greater than, less than, exceeding, etc. are understood as not including the number, and the terms greater than, less than, within, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless there is an explicit limitation, the words such as setting, installation, connection, etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above words in combination with the specific contents of the technical solution.
As shown in fig. 1, in one aspect, there is provided an automatic welding apparatus based on machine vision and AI algorithm, structurally including a robot 10 and a fixing mechanism 20 fixing a product to be welded.
The robot 10 is provided with a robot arm, a welding gun 13 and an industrial camera 12.
Preferably, the mechanical arm has six degrees of freedom, can weld at a plurality of angles, avoids the interference collision of the welding gun 13 and the fixing mechanism 20 or products during welding, is suitable for more complicated products, and therefore reduces the use cost of users.
More specifically, the robot arm is provided with a first cantilever 11 that fixes a welding gun 13 and an industrial camera 12, the welding gun 13 is disposed at a distal end of the first cantilever 11, and the industrial camera 12 is disposed radially outside the first cantilever 11.
Because the welding gun 13 and the industrial camera 12 are both arranged on the first cantilever 11, the relative position of the welding gun 13 and the industrial camera 12 is determined by the difference of the installation positions, and the relative position of the welding gun 13 and the industrial camera 12 is fixed, so that calculation and conversion during subsequent welding are facilitated.
The industrial camera 12 is arranged on the first cantilever 11, so that the shielding of an object on a position to be welded can be avoided, the industrial camera 12 is convenient to be aligned to the position to be welded, the position of the position to be welded on a plane image shot by the industrial camera 12 is accurate, the difference is small, meanwhile, the complexity of an AI algorithm is reduced, and the calculation is convenient.
In addition, for the fixing of the product, the fixing mechanism 20 may include a clamp 22 for fixing the product, and a first rotary seat 21 for driving the clamp 22 to rotate horizontally for adjustment.
The first swivel mount 21 drives the clamp 22 to swivel so that different sides of the product face the robot arm, thereby extending the welding range of the robot arm and enabling the robot 10 to be used to weld larger and more complex products.
In some embodiments, the clamp 22 and the first rotary base 21 may be provided in two sets, respectively on opposite sides of the robot 10.
Therefore, when the robot 10 welds a product on one clamp 22, the robot can disassemble and assemble a product on the other clamp 22, so that the stop of the robot 10 is reduced, and the welding efficiency is improved.
Correspondingly, can make robot 10 is provided with the second swivel mount of connecting the arm, and the arm passes through the second swivel mount and connects ground, and the second swivel mount is used for driving the arm and rotates along the horizontal direction, and the second swivel mount is not drawn.
Correspondingly, the mechanical arm is directly driven to rotate through the second rotary seat, so that the robot 10 can quickly start welding without detailed debugging again, and the debugging time is shortened.
For the fixture 22 for fixing the product, the fixture 22 generally includes a base plate for placing the product, a positioning plate, and a clamping assembly 23 for pressing and fixing the product, and the fixture 22 assembly may be a manual quick-clamping tool, or an automatic tool such as an air cylinder.
In order to avoid the clamping assembly 23 from shielding and interfering, so that the welding gun 13 cannot be conveniently close to the position to be welded, the clamp 22 may be a horizontally arranged rectangle, and the assembly of the clamp 22 is arranged at the diagonal position of the clamp 22.
Because the welding gun 13 can be conveniently contacted with the product on both sides of the clamping assembly 23, the clamping assembly 23 cannot interfere or shield the welding.
And, the clamping component 23 of fixing the product is set up in the diagonal position of the clamp 22, can reduce the block of the clamping component to the welding torch 13, reduce and debug the difficulty, facilitate the product to switch over, moreover, it is apt to optimize the welding route, not influenced by the interference of welding torch 13 route.
In some embodiments, the clamping assembly 23 may include a press block, and a rotary cylinder for rotatably lifting and lowering the press block.
The utility model has the advantages of effectually, through utilizing revolving cylinder, can avoid the briquetting to shelter from the product in upper and lower direction, the dismouting mode of extension product conveniently takes out the product from anchor clamps.
In some embodiments, the clamp 22 may further include a side cam and a side hold down that is a hand snap tool or an air cylinder.
What easily reachs is, through setting up side profiling and side direction and compressing tightly the piece, increases the restraint to the product, reduces the deformation of product for the product size after the welding finishes accords with the drawing requirement and the precision is high.
As shown in fig. 2, on the other hand, the automatic welding apparatus of the present embodiment also applies an automatic welding method based on machine vision and AI algorithm.
The automatic welding method comprises the following core steps.
And a photographing step, wherein an industrial camera 12 is used for photographing the part to be welded of the product to obtain a plane image of the position to be welded.
And a calculating step, namely calculating the pixel position of the welding starting point on the plane image by using an AI algorithm according to the characteristics of the plane image.
As shown in fig. 3, on the image captured by the industrial camera 12, the structural feature of the product is projected as a plurality of straight line segments or circular arc segments having relative positions, and the AI algorithm selects a point on a certain straight line segment or circular arc segment as a welding start point based on the characteristics of these straight line segments and circular arc segments, and specifies the pixel position of the welding start point, which is a value of the start point of the welding gun 13 with respect to the center of the plane image, and can be set to a1 ═ x1, y1, which is approximate to the coordinate values of the position point in the XY plane coordinate system.
And a conversion step of converting the coordinate position of the welding starting point in the coordinate system of the robot 10 according to the relative position relationship between the industrial camera 12 and the welding gun 13.
Specifically, since the industrial camera 12 has a fixed mounting position a2 on the robot arm, and a2 is equal to (x2, y2, z2), a — a1+ a2 is equal to (x1+ x2, y1+ y2, z2) and since the end of the welding gun 13 has a fixed position difference B1 from the industrial camera 12 is equal to (△ x, △ y, △ z, △α), when the end of the welding gun 13 is to be located at the welding start point, the end of the welding gun 13 is equal to B1+ a (x1+ x2+ △ x, y1+ y2+ △ y, z2+ △ z, △α), and △α is a deflection angle between the end of the welding gun 13 and the industrial camera 12.
And a welding step, in which the welding gun 13 starts welding from the coordinate position of the welding starting point, and the welding track is executed according to the stored welding seam data.
The welding seam data can be a three-dimensional or two-dimensional track of a position to be welded of a product, and of course, can also contain welding energy data, such as voltage, current, welding speed and the like, so that the welding quality can be controlled more accurately.
That is, in order to better control the welding quality, the end of the welding gun 13 must not only weld according to the welding trajectory, but also control the welding energy in order to comprehensively control the welding process.
According to the welding method, the industrial camera 12 is used for shooting, so that a plane image of a position to be welded of a product can be obtained, the coordinates of a welding starting point are obtained through an AI algorithm, further, the welding starting point of the robot 10 can be corrected according to the actual condition of the product, the deviation generated by product manufacturing and positioning is compensated, the position of a welding line is accurate, the welding quality is improved, the defective rate of welding is reduced, and the production efficiency is improved.
In order to enable the industrial camera 12 to accurately shoot a planar image of the position to be welded, a rotation step can be arranged before the shooting step, and the rotation step horizontally rotates the product, so that the position to be welded of the product is opposite to the industrial camera 12, and accordingly, the conversion difficulty is also reduced.
In order to avoid deviation of the welding end point caused by simple welding according to the theoretical welding track, the calculating step may further include calculating a pixel position of the welding end point, and the converting step may further include converting a coordinate position of the welding end point in the coordinate system of the robot 10.
Furthermore, in order to avoid the deviation of the welding seam track caused by pure welding according to the theoretical welding track, the calculation step further comprises calculating the pixel position of an interpolation point between the welding starting point and the welding ending point, the conversion step further comprises converting to obtain the coordinate position of the interpolation point, and the compensation step is further included between the conversion step and the welding step, and compares the coordinate of the interpolation point with the welding seam data to correct the welding seam data.
In addition, the robot 10 can set a relative coordinate system with reference to a numerical control machine tool, and is particularly described by taking iron wire welding as an example, so that the application is convenient.
Specifically, according to the characteristics of the plane image, calculating to obtain a characteristic point taking the central end point of the iron wire as the characteristic, determining the coordinate value of the characteristic point in a plane image coordinate system, then, according to the relation between the plane image coordinate system and the robot 10 coordinate system, converting to obtain the coordinate value of the characteristic point in the robot 10 coordinate system, and establishing a workpiece coordinate system by using the coordinate value of the characteristic point in the robot 10 coordinate system as the origin, so that the robot 10 can drive the welding gun 13 to act according to the coordinates of the welding route on the workpiece coordinate system, and welding is completed.
Therefore, the obtained characteristic point is not limited to the welding start point, and may be other points as long as the theoretical welding route is satisfied to coincide with the actual welding capability.
The above embodiments are not limited to the technical solutions of the embodiments themselves, and the embodiments may be combined with each other into a new embodiment. The above embodiments are only used for illustrating the technical solutions of the present invention and are not limited thereto, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of the technical solutions of the present invention.
Claims (7)
1. The automatic welding device based on the machine vision and AI algorithm is characterized by comprising a robot (10), wherein the robot (10) is provided with a mechanical arm, a welding gun (13) and an industrial camera (12), the mechanical arm is provided with a first cantilever (11) for fixing the welding gun (13) and the industrial camera (12), the welding gun (13) is arranged at the tail end of the first cantilever (11), and the industrial camera (12) is arranged on the radial outer side of the first cantilever (11).
2. The automatic welding device based on machine vision and AI algorithm of claim 1, further comprising a fixture (22) for fixing the product, a first rotary seat (21) for driving the fixture (22) to rotate horizontally for adjustment, wherein the first rotary seat (21) is disposed at the bottom of the fixture (22).
3. The automatic welding device based on machine vision and AI algorithm of claim 2, characterized in that the clamp (22) is a horizontally arranged rectangle, and the diagonal position of the clamp (22) is provided with a clamping component (23) for fixing the product.
4. The automatic welding device based on machine vision and AI algorithm of claim 3, characterized in that the clamping assembly (23) comprises a press block, a rotating cylinder driving the press block to rotate and lift.
5. The automatic welding device based on machine vision and AI algorithm of claim 2, characterized in that the clamp (22) further comprises a lateral profile and a lateral hold-down.
6. The automatic welding device based on machine vision and AI algorithm of claim 2, characterized in that the fixture (22) and the first turret (21) are provided in two groups, one on each opposite side of the robot (10).
7. The automatic welding device based on machine vision and AI algorithm as claimed in claim 6, wherein the robot (10) is provided with a second swivel mount connected to a robot arm, the robot arm is connected to the ground through the second swivel mount, and the second swivel mount is used for driving the robot arm to rotate along the horizontal direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920757510.1U CN210731420U (en) | 2019-05-23 | 2019-05-23 | Automatic welding device based on machine vision and AI algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920757510.1U CN210731420U (en) | 2019-05-23 | 2019-05-23 | Automatic welding device based on machine vision and AI algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210731420U true CN210731420U (en) | 2020-06-12 |
Family
ID=71009969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920757510.1U Active CN210731420U (en) | 2019-05-23 | 2019-05-23 | Automatic welding device based on machine vision and AI algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210731420U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110142533A (en) * | 2019-05-23 | 2019-08-20 | 深圳市科瑞悦电气设备有限公司 | A kind of automatic soldering method and welder based on machine vision Yu AI algorithm |
-
2019
- 2019-05-23 CN CN201920757510.1U patent/CN210731420U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110142533A (en) * | 2019-05-23 | 2019-08-20 | 深圳市科瑞悦电气设备有限公司 | A kind of automatic soldering method and welder based on machine vision Yu AI algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7738996B2 (en) | Method for positioning a welding robot tool | |
| CN107262926B (en) | Automatic laser welding device with CCD detection function and welding method | |
| WO2018218607A1 (en) | Laser welding device and welding method therefor | |
| CN107042379B (en) | A kind of disk connecting rod automatic welder | |
| CN107953033A (en) | A kind of double-sided laser bonding machine and processing method for camshaft processing | |
| CN110722263A (en) | Battery cover plate welding system and method | |
| CN210731420U (en) | Automatic welding device based on machine vision and AI algorithm | |
| CN110076569A (en) | It is a kind of to weld and welding front and back processing integration apparatus and processing method | |
| CN102398136B (en) | Fixture for simultaneously welding multiple salient points of automobile parts | |
| CN112958928A (en) | Intelligent welding system and method | |
| CN210281030U (en) | Non-rotating shaft circular seam welding equipment | |
| CN110142533A (en) | A kind of automatic soldering method and welder based on machine vision Yu AI algorithm | |
| CN109454388A (en) | Girth welding system | |
| CN107414233B (en) | Harness welds intelligent robot and Intelligent welding system | |
| CN202271095U (en) | Clamp for welding multiple protruding points of automobile part simultaneously | |
| CN202388167U (en) | Clamp for welding plurality of convex points on automobile part simultaneously | |
| CN115837547A (en) | Automatic welding device based on three-axis movement | |
| CN106425178B (en) | A kind of complicated abnormal shape workpiece robot welding system and method | |
| CN212398476U (en) | Double-station friction stir welding equipment with upper machine head and lower machine head | |
| CN109986256A (en) | Device and method for the swash plate in welded tank case | |
| CN207013898U (en) | A kind of mechanical component of composite welding | |
| CN214350213U (en) | Fuel tank filler hole resistance welding integration equipment | |
| CN214444252U (en) | Rotary automatic welding device for rubber ball pump base | |
| CN218612117U (en) | Embedded automatic tin soldering machine without fixture positioning | |
| CN220739761U (en) | Argon arc welding rotary welding device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210803 Address after: 518000 B21, building 522, Bagualing Industrial Zone, baguasan Road, Hualin community, Yuanling street, Futian District, Shenzhen, Guangdong Province Patentee after: Shenzhen weizhizi Technology Co.,Ltd. Address before: 518000 factory building a, No. 19, Nanling Road, Shajing xiner, Bao'an District, Shenzhen, Guangdong Province Patentee before: SHENZHEN KRY ELECTRICAL EQUIPMENT Co.,Ltd. |
|
| TR01 | Transfer of patent right |