Portable welding robot and welding method thereof

Abstract

The invention relates to the technical field of welding robots, in particular to a portable welding robot and a welding method.The portable welding robot comprises a welding module, an adjusting module, a moving module and a binocular vision module.The moving module can solve the problem that an existing welding robot is difficult to transfer; meanwhile, aiming at the welding problem of structural parts such as a box beam, a frame and a carriage, a binocular vision module is adopted to realize welding seam positioning, so that the problem of high layering of welding seams is solved, and automatic welding of the structural parts such as the box beam, the frame and the carriage is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of welding robots, and particularly relates to a portable welding robot and a welding method thereof. Background Art

[0002] Products such as box girders, vehicle frames, and carriages have long weld seams and the welds are stratified in the height direction. When using a robot workstation to weld this type of product, the welding range is limited, and an additional large-scale indexing mechanism needs to be designed to move the workpiece to complete the welding. For the existing automated welding application scenarios of large parts such as box girders, vehicle frames, and carriages, most of them use robot workstations or special welding machines for construction.

[0003] For a robot workstation, it uses the form of a ground rail + robot to complete the welding of a single long straight weld. After the welding is completed, an external mechanism is used to complete the flipping of the workpiece. After moving to a suitable position, the welding of the subsequent welds is carried out. For a special welding machine, it is generally divided into two types: rail type and trackless type. When using a rail type special welding machine, the track is laid first. After the track is correctly positioned, the special welding machine is used to complete the welding. When using a trackless special welding machine, generally, welding and fine-tuning are carried out simultaneously, and the welding wire and welding torch are always kept in the correct trajectory and posture. The existing arc welding robots will encounter problems such as difficult movement and limited welding range when dealing with the welding operations of products such as box girders, vehicle frames, and carriages with long weld seams and the welds being stratified in the height direction.

[0004] In summary, there is an urgent need for a portable welding robot and a welding method thereof to solve the problems in the prior art. Summary of the Invention

[0005] The purpose of the present invention is to provide a portable welding robot and a welding method thereof, and the specific technical solutions are as follows:

[0006] A portable welding robot includes a welding module, an adjustment module, a moving module, and a binocular vision module;

[0007] The welding module includes a welding torch and a robotic arm. The welding torch is arranged on the robotic arm, and the robotic arm is adjustably connected to the adjustment module;

[0008] The adjustment module is fixedly arranged on the moving module and is used to adjust the position of the robotic arm;

[0009] The moving module is used to drive the portable welding robot to move;

[0010] The binocular vision module is arranged on the adjustment module. The binocular vision module includes a control center, a first rotating mechanism, and a second rotating mechanism respectively connected to the control center. The rotating surfaces of the first rotating mechanism and the second rotating mechanism are perpendicular to each other;

[0011] A first vision sensor is provided on the first rotating mechanism, and a second vision sensor is provided on the second rotating mechanism. The first rotating mechanism is used to enable the first vision sensor to perform rotational sampling, and the second rotating mechanism is used to enable the second vision sensor to perform rotational sampling;

[0012] The control center is connected to the adjustment module and the welding module. The first vision sensor and the second vision sensor are connected to the control center. The control center receives sampling data, and the adjustment module and the welding module complete weld seam positioning through the control center and control the robotic arm to complete the welding operation.

[0013] Optionally, the welding module further includes a welding power source provided on the moving module.

[0014] Optionally, the welding module further includes a wire installation bracket and a wire feeder provided on the adjustment module.

[0015] Optionally, the adjustment module includes a first adjustment mechanism and a second adjustment mechanism. The second adjustment mechanism is adjustably provided on the first adjustment mechanism along the vertical direction, and the welding module is adjustably provided on the second adjustment mechanism along the horizontal direction.

[0016] Optionally, the first adjustment mechanism further includes a lifting motor provided on the moving module for driving the second adjustment mechanism to lift;

[0017] The second adjustment mechanism further includes an adjustment motor provided on the first adjustment mechanism for driving the robotic arm to adjust its position along the horizontal direction.

[0018] Optionally, the first vision sensor includes a first rotating motor and a line laser sensor. The first rotating motor is used to drive the line laser sensor to rotate along a first rotating plane; the second vision sensor includes a second rotating motor and a 3D camera. The second rotating motor is used to drive the 3D camera to rotate along a second rotating plane. The first rotating plane is a horizontal plane, and the second rotating plane is a vertical plane.

[0019] Optionally, the moving module includes a handle, universal wheels, and a moving chassis. The universal wheels and the moving chassis are both provided at the lower part of the handle, and the adjustment module is installed on the moving chassis.

[0020] Optionally, the moving chassis includes a plurality of mounting plates and reinforcing ribs for connecting the mounting plates. Universal balls and directional wheels are provided below the mounting plates and the reinforcing ribs.

[0021] In addition, the present invention also includes a welding method using the portable welding robot as described above, including the following steps:

[0022] Use the mobile module to move the portable welding robot to the welding position;

[0023] Use the adjustment module and the binocular vision module to locate the weld seam;

[0024] Drive the welding module to perform cyclic welding on the weld seam to complete the welding operation.

[0025] Optionally, use the adjustment module and the binocular vision module to locate the weld seam. The weld seam positioning includes the positioning of the starting point of the weld seam and the recognition of the weld seam trajectory. The process of weld seam positioning is as follows:

[0026] Positioning of the starting point of the weld seam: Drive the first vision sensor to scan up and down through the first rotating mechanism to determine the vertical distance between the first vision sensor and the welding workpiece and the straight-line distance between the first vision sensor and the weld seam. Use trigonometric functions to calculate the starting height of the welding torch relative to the weld seam, and use the vertical distance to achieve the positioning of the welding torch in the horizontal direction to complete the positioning of the starting point of the weld seam;

[0027] Recognition of the weld seam trajectory: Use the first vision sensor to scan the weld seam position to obtain multiple weld seam scanning stripes. The intersection points of the weld seam scanning stripes are the weld seam feature points. Use the second vision sensor to take pictures of the weld seam feature points to obtain a weld seam image; Preprocess the weld seam image to remove the interference of impurities on the welding workpiece; Digitalize the weld seam image; Extract the center line of the weld seam scanning stripes in the weld seam image and calculate the intersection coordinates of all center lines: Construct the weld seam trajectory based on the intersection coordinates.

[0028] Applying the technical solution of the present invention has the following beneficial effects:

[0029] The method of the present invention provides a portable welding robot and its welding method. The present invention optimizes the design of the mobile chassis structure of the portable welding robot, which is beneficial for the welding robot to be transported to the welding position, and realizes the adjustment of the welding manipulator through the adjustment module, improving the flexibility of the welding robot. The portable welding robot disclosed in the present invention is provided with a binocular vision module to realize weld seam positioning and improve the accuracy of welding through welding trajectory tracking.

[0030] In addition to the purposes, features and advantages described above, the present invention has other purposes, features and advantages. The following will refer to the drawings for a further detailed description of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 It is a schematic structural diagram of the portable welding robot in the preferred embodiment of the present invention;

[0033] Figure 2 It is a schematic structural diagram of the adjustment module in the preferred embodiment of the present invention;

[0034] Figure 3 It is a schematic structural diagram of the moving module in the preferred embodiment of the present invention;

[0035] Figure 4 It is a schematic structural diagram of the binocular vision module in the preferred embodiment of the present invention;

[0036] Among them, 1 - welding torch, 2 - welding power source, 3 - robotic arm, 4 - binocular vision module, 5 - second adjustment mechanism, 6 - wire installation bracket, 7 - first adjustment mechanism, 8 - wire feeder, 9 - handle, 10 - control cabinet, 11 - mounting base plate, 12 - wire feeder mounting plate, 13 - robotic arm mounting plate, 14 - first vision sensor, 15 - second vision sensor, 16 - robotic arm adjustment plate, 17 - lifting motor mounting plate, 18 - adjustment plate stiffener, 19 - first adjustment mechanism adapter plate, 20 - universal ball, 21 - first stiffener, 22 - first adjustment mechanism mounting plate, 23 - cable placement plate, 24 - handrail, 25 - gear shift regulating valve, 26 - welding power source mounting plate, 27 - shock-absorbing spring, 28 - universal wheel, 29 - control cabinet mounting plate, 30 - second stiffener, 31 - directional wheel, 32 - line laser sensor, 33 - first motor reducer, 34 - first rotating motor, 35 - 3D camera, 36 - second motor reducer, 37 - second rotating motor, 38 - first rotating surface, 39 - second rotating surface. Detailed implementation manners

[0037] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific implementation manners. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0038] As Figure 1 、 Figure 2 、 Figure 3 and Figure 4 shown, this embodiment provides a portable welding robot, including a welding module, an adjustment module, a moving module, and a binocular vision module 4.

[0039] In this embodiment, the welding module includes a welding torch 1, a welding power source 2, and a robotic arm 3. The welding torch 1 is disposed on the robotic arm 3, and the robotic arm 3 is adjustably connected to the adjustment module. It should be noted that the robotic arm 3 in this embodiment includes a six-axis actuator, and the welding torch 1 is installed at the end of the six-axis actuator. The welding power source 2 is disposed on the moving module.

[0040] Specifically, the welding module further includes a wire mounting bracket 6 and a wire feeder 8 disposed on the adjustment module.

[0041] In this embodiment, the adjustment module is fixedly disposed on the moving module and is used to adjust the position of the robotic arm 3. In this embodiment, the adjustment module includes a first adjustment mechanism 7 and a second adjustment mechanism 5. The second adjustment mechanism 5 is adjustably disposed on the first adjustment mechanism 7 along the vertical direction, and the robotic arm 3 in the welding module is adjustably disposed on the second adjustment mechanism 5 along the horizontal direction.

[0042] Further, the first adjustment mechanism 7 further includes a lifting motor disposed on the moving module for driving the second adjustment mechanism to lift. The second adjustment mechanism further includes an adjustment motor disposed on the first adjustment mechanism for driving the robotic arm to adjust its position along the horizontal direction. An installation base plate 11 is provided below the first adjustment mechanism 7, and the first adjustment mechanism 7 is disposed on the moving module through the installation base plate.

[0043] Further, the second adjustment mechanism 5 further includes a robotic arm adjustment plate 16 which is adjustably disposed along the horizontal direction, and the robotic arm 3 is disposed on the robotic arm adjustment plate 16.

[0044] In this embodiment, the moving module is used to drive the portable welding robot to move. In this embodiment, the moving module includes a handle 9, universal wheels 28, and a moving chassis. The universal wheels 28 and the moving chassis are both disposed at the lower part of the handle 9. An armrest 24 is provided at the upper part of the handle 9, and the adjustment module is installed on the moving chassis. In this embodiment, a shock-absorbing spring 27 is provided between the handle 9 and the universal wheels 28.

[0045] Further, a gear position adjustment valve 25 is installed on the armrest 24 for switching the rising gear position and the falling gear position of the second adjustment mechanism 5.

[0046] Specifically, the moving chassis includes a plurality of mounting plates and reinforcing ribs for connecting the mounting plates. Universal balls 20 and directional wheels 31 are provided below the mounting plates and the reinforcing ribs. The mounting plates include a first adjustment mechanism mounting plate 22, a cable placement plate 23, a welding power source mounting plate 26, and a control cabinet mounting plate 29.

[0047] The first adjustment mechanism mounting plate 22 is used to mount the first adjustment mechanism.

[0048] The cable placement plate 23 is used to place the relay cable, communication cable and welding torch cable of the welding robot.

[0049] The welding power supply mounting plate 26 is used to mount the welding power supply, and the welding power supply is connected to the welding torch 1 through the welding torch cable.

[0050] The control cabinet mounting plate 29 is used to mount the control cabinet 10. The control center is arranged in the control cabinet 10, and the control center is connected to the adjustment module, the binocular vision module 4 and the welding module through the relay cable and the communication cable.

[0051] Further, the reinforcing ribs include a first reinforcing rib 21 and a second reinforcing rib 30. The first reinforcing rib 21 is used to connect different mounting plates, and the second reinforcing rib 30 is used to fix the cable placement plate 23. In this embodiment, a universal ball 20 is provided below each first reinforcing rib 21.

[0052] Further, a wire feeder mounting plate 12, a lifting motor mounting plate 17, an adjustment plate reinforcing rib 18 and a first adjustment mechanism adapter plate 19 are provided on the first adjustment mechanism 7. The wire feeder mounting plate 12 is used to mount the wire feeder 8, the lifting motor mounting plate 17 is used to mount the lifting motor, the adjustment plate reinforcing rib 18 is arranged between the first adjustment mechanism adapter plate 19 and the second adjustment mechanism 5, and the first adjustment mechanism adapter plate 19 is used to mount the second adjustment mechanism 5. The first adjustment mechanism adapter plate 19 is arranged on the first adjustment mechanism 7 in an adjustable manner along the vertical direction;

[0053] Further, a robotic arm mounting plate 13 is provided on the second adjustment mechanism 5, and the robotic arm 3 is connected to the robotic arm adjustment plate 16 through the robotic arm mounting plate 13.

[0054] The binocular vision module 4 is arranged on the adjustment module. The binocular vision module 4 includes a control center and a first rotating mechanism and a second rotating mechanism respectively connected to the control center. The rotating surfaces of the first rotating mechanism and the second rotating mechanism are arranged perpendicular to each other;

[0055] A first vision sensor 14 is provided on the first rotating mechanism, and a second vision sensor 15 is provided on the second rotating mechanism. The first rotating mechanism is used to realize the rotational sampling of the first vision sensor 14, and the second rotating mechanism is used to realize the rotational sampling of the second vision sensor 15;

[0056] The control center is connected to the adjustment module and the welding module. The first vision sensor and the second vision sensor are connected to the control center. The control center receives the sampling data. The adjustment module and the welding module complete the weld seam positioning through the control center and control the robotic arm to complete the welding operation.

[0057] In this embodiment, the first vision sensor includes a first rotating motor 34 and a line laser sensor 32. The first rotating motor 34 is connected to a first motor reducer 33. The first rotating motor is used to drive the line laser sensor 32 to rotate along a first rotation plane 38. The second vision sensor includes a second rotating motor 37 and a 3D camera 35. The second rotating motor is connected to a second motor reducer 36 and is used to drive the 3D camera to rotate along a second rotation plane 39. The first rotation plane 38 is a horizontal plane ( Figure 4 the XOY plane in Figure 4 ), and the second rotation plane 39 is a vertical plane (

[0058] In addition, the present invention also includes a welding method using the portable welding robot as described above, which includes the following steps:

[0059] Use the moving module to move the portable welding robot to the welding position; in this step, an external device can be borrowed to first move the portable welding robot to a rough position, and then fine-tune it through the moving module.

[0060] Use the adjustment module and the binocular vision module to perform weld seam positioning.

[0061] Drive the welding module to perform cyclic welding on the weld seam. The cyclic welding specifically repeats the weld seam positioning, and then performs multiple weldings on the weld seam. After all the weld seams are welded, the welding operation is completed.

[0062] Optionally, use the adjustment module and the binocular vision module to perform weld seam positioning. The weld seam positioning includes the positioning of the weld seam starting point and the recognition of the weld seam trajectory. The process of weld seam positioning is as follows:

[0063] Positioning of the weld seam starting point: Drive the first vision sensor to perform up and down scanning through the first rotating mechanism, determine the vertical distance between the first vision sensor and the welding workpiece and the linear distance between the first vision sensor and the weld seam, calculate the starting height of the welding torch relative to the weld seam using trigonometric functions, and use the vertical distance to achieve the positioning of the welding torch in the horizontal direction to complete the positioning of the weld seam starting point.

[0064] Weld seam trajectory recognition: Use the first vision sensor to scan the weld seam position to obtain multiple weld seam scanning stripes. The intersection points of the weld seam scanning stripes are the weld seam feature points. Use the second vision sensor to take pictures of the weld seam feature points to obtain a weld seam image; preprocess the weld seam image to remove the interference of impurities on the welded workpiece; digitalize the weld seam image; extract the center line of the weld seam scanning stripes in the weld seam image, and calculate the intersection coordinates of all center lines: construct the weld seam trajectory based on the intersection coordinates. It should be noted that in this embodiment, a line laser sensor 32 is used, and the weld seam scanning stripes are laser stripes.

[0065] In this embodiment, the convolution idea is adopted to enhance the image sampling quality and remove the interference of oil stains and rust in the image. Let (x, y) be a point in the sampled image, and l be the filter template. Apply a grid of size m×n to filter the weld seam image, and the expression is as follows:

[0066]

[0067] Among them, l(x, y) represents the processing result of the Gaussian filter, w(s, t) is the filter coefficient, and f(x + s, y + t) represents the pixel value. In the grid of size m×n, m = 2a + 1, n = 2b + 1, and both a and b are adjustment factors and take integer values. In this embodiment, the disturbances are excluded by adjusting the values of a and b according to the size of the interference image.

[0068] Furthermore, in order to make the edges of the weld seam image clear and stable, and at the same time reduce the noise interference (oil stains) in the image, bilateral filtering is used for filtering. The bilateral filtering formula is as follows:

[0069]

[0070] Among them, g(i, j) represents the processing result of the bilateral filtering model; (i, j) and (k, l) are the re-numbered image points of the point (x, y) after being processed by the Gaussian filter; ω(i, j, k, l) is the weighting coefficient, which is the product of the spatial domain filter d(i, j, k, l) and the range domain filter r(i, j, k, l). The calculation methods of the spatial domain filter d(i, j, k, l) and the range domain filter r(i, j, k, l) are as follows:

[0071]

[0072] Among them, exp represents the exponential function; represents the variance of the spatial domain Gaussian function, and this variance determines the influence range of the spatial proximity factor; represents the variance of the gray domain Gaussian function, and this variance determines the influence range of the brightness similarity factor; ||f(i, j)-f(k, l)|| 2It represents the gray - level difference of pixel values between pixel point (i, j) and pixel point (k, l).

[0073] Further, the calculation method of the weighting coefficient ω(i, j, k, l) can be obtained as follows:

[0074]

[0075] Further, in order to perform image threshold segmentation on the weld scan stripe area near the weld feature point to extract the weld scan stripe from the gray - converted image, the following steps are adopted in this embodiment:

[0076] 1) Gray - scale image preparation: First, convert the original image containing the weld feature point into a gray - scale image because the weld scan stripe usually has a relatively obvious contrast in the gray - scale image.

[0077] 2) Threshold setting: Next, set a suitable threshold T. This threshold should be determined according to the brightness difference between the weld scan stripe and the background so as to accurately separate the weld scan stripe.

[0078] 3) Threshold segmentation: Perform threshold segmentation operation on the gray - scale image. For each pixel in the image, if its gray - level value is lower than the threshold T, set the value of this pixel to 0 (representing black or background); if its gray - level value is higher than or equal to the threshold T, set the value of this pixel to 255 (representing white or weld scan stripe).

[0079] 4) Extract the weld scan stripe: Through the above - mentioned threshold segmentation operation, the weld scan stripe will be separated from the background to form a binary image. In this binary image, the weld scan stripe appears as a white area while the background appears as a black area.

[0080] 5) Subsequent processing: According to specific requirements, the extracted weld scan stripe can be further processed and analyzed, such as morphological operations, edge detection, etc., to obtain more accurate weld feature point information. It should be noted that this step is an optional item, that is, whether to perform subsequent processing is determined according to actual needs.

[0081] Through the above steps, this embodiment extracts the weld scan stripe near the weld feature point from the gray - scale image, providing basic data for subsequent analysis and processing. At the same time, by adjusting the threshold T, this embodiment can adapt to different lighting conditions and the brightness of the weld scan stripe, improving the accuracy and robustness of the segmentation.

[0082] The segmented image g(x, y) is given by the following formula:

[0083]

[0084] Due to the influence of splashes, burrs, and pits on the workpiece itself, the image after threshold segmentation will affect the extraction of the image after grayscale conversion. Therefore, morphological operations of the image are used to eliminate the interference of image information caused by the defects of the workpiece itself.

[0085] Image dilation: Suppose A and B are subsets in the set Z, which is expressed as the dilation of B with respect to A, and the specific definition is as follows:

[0086]

[0087] For pits, morphological dilation is used to fill the holes at the edges of the weld scan stripes.

[0088] Morphological erosion: A⊙B is expressed as the erosion of B with respect to A, and the specific definition is as follows:

[0089]

[0090] For splashes and burrs, morphological erosion can be used to remove the isolated parts outside the weld scan stripes.

[0091] In image processing, dilation and erosion are two basic morphological operations, which have a significant impact on the weld scan stripe area in the image. The dilation operation will make the weld scan stripe area larger, while the erosion operation will make it smaller. Based on these two basic operations, this embodiment can obtain the comprehensive application of the expansion operation and the reduction operation to further realize more complex processing of the image.

[0092] Opening Operation is a process of first eroding and then dilating. Its main function is to eliminate the smaller connected domains in the image, while retaining the larger connected domains and smoothing the boundaries of the weld scan stripes. Through the opening operation, this embodiment can effectively remove the noise and small details in the image, while maintaining the main structure and shape of the weld scan stripes.

[0093] Closing Operation is a process of first dilating and then eroding. Its function is to remove the small holes inside the weld scan stripes and smooth its contour. The closing operation is particularly useful when dealing with weld scan stripes with holes or breaks, because it can fill these holes and make the weld scan stripes look more continuous and complete.

[0094] Extension Operation refers to first performing an erosion operation on image A using the structuring element B, and then performing a dilation operation. The extension operation of B with respect to A is to first erode and then dilate A with B. The specific definition is

[0095]

[0096] The shrinking operation of B on A is to dilate A by B first and then erode it. The specific definition is as follows:

[0097]

[0098] In this embodiment, the extraction of the center line of the weld scan stripe after photographing is obtained by the skeleton extraction method. The steps are as follows:

[0099] First, the geometric center method is used to identify the pixel points of the upper and lower edges of the object in the image. Then, for each column of pixels, calculate the vertical center position of the upper and lower edge pixels in this column, that is, the geometric center of this column of pixels. This center position can be obtained by taking the average value of the row numbers of the upper and lower edge pixels.

[0100] Once the geometric center of each column is determined, the coordinates of these center points can be connected in the order of columns to form a center line running through the image, and this center line represents the central axis of the weld scan stripe.

[0101] In the above way, the geometric center method can effectively extract the center line of the weld scan stripe in the weld image, which can be expressed by the following formula:

[0102]

[0103] Among them, x 1 , x 2 respectively represent the pixel coordinates in the u-axis direction of the pixel coordinate system. According to the calculation formula, the pixel coordinate x 0 of the center line on the u-axis is obtained, and then each column is added, and all pixel points form the center line of the weld scan stripe.

[0104] Construct the weld track: After obtaining the center line of the weld scan stripe, perform a linear fitting on the curved center line to further obtain the accurate intersection coordinates of the two center lines, and the weld track is obtained after fitting the intersection coordinates.

[0105] It should be noted that the device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] The above is only the preferred embodiment of the present invention and is not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A portable welding robot, characterized in that: It includes a welding module, an adjustment module, a moving module and a binocular vision module (4); The welding module comprises a welding gun (1) and a mechanical arm (3), wherein the welding gun (1) is arranged on the mechanical arm (3), and the mechanical arm (3) is adjustably connected to the adjustment module; The adjustment module is fixedly arranged on the moving module and is used to adjust the position of the mechanical arm (3); The moving module is used to drive the portable welding robot to move; The binocular vision module (4) is arranged on the adjustment module, and comprises a control center and a first rotating mechanism and a second rotating mechanism respectively connected to the control center, wherein the rotating planes of the first rotating mechanism and the second rotating mechanism are arranged perpendicular to each other; The first rotating mechanism is provided with a first visual sensor (14), and the second rotating mechanism is provided with a second visual sensor (15); the first rotating mechanism is used to enable the first visual sensor (14) to perform rotation sampling, and the second rotating mechanism is used to enable the second visual sensor (15) to perform rotation sampling; The control center is connected to the regulating module and the welding module, the first visual sensor (14) and the second visual sensor (15) are connected to the control center, the control center receives sampling data, and the regulating module and the welding module complete the weld positioning through the control center and control the robot arm (3) to complete the welding operation.

2. The portable welding robot according to claim 1, characterized in that: The welding module also includes a welding power source (2) arranged on the moving module.

3. The portable welding robot according to claim 1, characterized in that: The welding module also includes a welding wire mounting bracket (6) and a wire feeder (8) arranged on the adjustment module.

4. The portable welding robot according to claim 1, characterized in that: The adjustment module comprises a first adjustment mechanism (7) and a second adjustment mechanism (5), wherein the second adjustment mechanism (5) is adjustably arranged on the first adjustment mechanism (7) along a vertical direction, and the welding module is adjustably arranged on the second adjustment mechanism (5) along a horizontal direction.

5. The portable welding robot according to claim 1, characterized in that: The first adjusting mechanism (7) further comprises a lifting motor, which is arranged on the moving module and is used to drive the second adjusting mechanism (5) to move up and down; The second adjustment mechanism (5) further comprises an adjustment motor, which is arranged on the first adjustment mechanism (7) and is used to drive the mechanical arm (3) to adjust its position along the horizontal direction.

6. The portable welding robot according to claim 5, characterized in that: The first visual sensor (14) comprises a first rotating motor (34) and a line laser sensor (32), wherein the first rotating motor (34) is used to drive the line laser sensor (32) to rotate along a first rotating plane (38); the second visual sensor (15) comprises a second rotating motor (37) and a 3D camera (35), wherein the second rotating motor is used to drive the 3D camera to rotate along a second rotating plane (39), wherein the first rotating plane (38) is a horizontal plane and the second rotating plane (39) is a vertical plane.

7. The portable welding robot according to claim 1, characterized in that: The mobile module comprises a handle (9), a universal wheel (28) and a mobile chassis. The universal wheel (28) and the mobile chassis are both arranged at the lower part of the handle (9), and the adjustment module is installed on the mobile chassis.

8. The portable welding robot according to claim 7, characterized in that: The mobile chassis comprises a plurality of mounting plates and reinforcing ribs for connecting the mounting plates, and a universal ball (20) and a directional wheel (31) are arranged below the mounting plates and the reinforcing ribs.

9. A welding method using the portable welding robot according to any one of claims 1 to 8, characterized in that: The steps include: Use the mobile module to move the portable welding robot to the welding position; Using the adjustment module and the binocular vision module (4) to locate the weld; The welding module is driven to perform cyclic welding on the weld to complete the welding operation.

10. The welding method according to claim 9, characterized in that: The adjustment module and the binocular vision module are used to locate the weld. The weld positioning includes the positioning of the weld starting point and the recognition of the weld trajectory. The process of weld positioning is as follows: Positioning the starting point of the weld: driving the first visual sensor (14) to scan up and down through the first rotating mechanism, determining the vertical distance between the first visual sensor (14) and the welding workpiece and the linear distance between the first visual sensor (14) and the weld, using trigonometric functions to calculate the starting height of the welding gun relative to the weld, using the vertical distance to position the welding gun (1) in the horizontal direction, and completing the positioning of the starting point of the weld; Weld seam trajectory recognition: using a first visual sensor (14) to scan the weld seam position to obtain a plurality of weld seam scanning stripes, the intersection of the weld seam scanning stripes is a weld seam feature point, using a second visual sensor (15) to take a picture of the weld seam feature point to obtain a weld seam image; pre-processing the weld seam image to remove interference from impurities on the welding workpiece; The weld image is digitized; the center lines of the weld scanning stripes in the weld image are extracted, and the intersection coordinates of all the center lines are calculated; and the weld trajectory is constructed based on the intersection coordinates.

Images