KR101717582B1 - Submerged arc welding machine capable of weld-line trace and image processing method for weld-line trace of submerged arc welding machine - Google Patents

Abstract

The present invention relates to a welding robot capable of tracking a weld line, and more particularly, to a welding robot for performing a welding operation and a welding robot provided on one side of the welding robot for processing an image obtained by irradiating a laser to a welding member to be welded, The laser vision system according to claim 1, wherein the laser vision system comprises a laser vision system, and the image vision system includes an image filter installed in front of the laser vision system so as to acquire three- . According to the present invention, there is an advantage that, even in the case of jumper welding using cut wires, the weld line can be traced from the three divided images acquired in the laser vision system.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to a welding method and a welding method for welding a welding wire,

The present invention relates to a jam welding using cut wires, and more particularly, to a jam welding system capable of tracking a welding line when welding is performed by spraying flux and cut wire on a surface to be improved, and image processing ≪ / RTI >

The SAW is characterized by the fact that the arc generated between the welding member to be welded and the filler material takes place inside the flux sprayed to the welding site, so that the arc is rarely exposed to the outside. The range of the welding current is different. In the field of heavy industry, it is mainly applied to butt welding of the abacus by using high current. In the case of welding thickness less than 20mm, I is improved, and when it is more than that, it is processed as Y improvement or X improvement, . The welding procedure is to weld the entire surface with two electrodes (DC + AC) or three electrodes (DC + AC + AC).

FIG. 1 is a schematic view of a prior art welding system in which a carriage 11, a wire 12, a welding torch (not shown) for moving along a predetermined rail 2 for welding a welding member 1 to be welded And a hopper tank 14 for storing a flux to be sprayed for protecting the molten metal when the welding is performed with the welding torch 13. The welding robot 10 and the welding robot 10, And a laser vision system 20 for measuring the geometrical shape of the welding member 1 by processing an image obtained by irradiating the welding member 1 with a laser.

In general, when the laser vision system 20 is used for tracking a weld line, the laser beam image irradiated on the improvement surface is obtained by measuring the geometry information of the joint while the improvement surface is in a clean state or the welding is performed. In the submerged arc welding using the cut wire, it is impossible to directly measure the improvement surface by using the laser vision system 20 by applying the cut wire to the improvement surface.

This will be described in detail as follows.

In the case of a general arc welding, the cut wire is not sprayed on the improvement surface but only the flux is sprayed. In this case, as shown in Fig. 2, the welding member 1 is measured by the laser vision system 20, and the corner portion where the line is bent is measured in the measured image as shown in Fig. 3, do.

However, in the case of the submerged welding using the cut wire to increase the amount of welding at the time of welding, the cut wire is sprayed on the improvement surface together with the flux. In this case, when the welding member 1 is measured by the laser vision system 20 as shown in Fig. 4, there is a problem that it is difficult to measure the shape of the improvement by spraying the cut wire on the improvement surface. That is, as shown in FIG. 5, since the edge portion of the line can not be measured in the measured image, there is a problem that it is difficult to find the point necessary for the weld line tracing.

SUMMARY OF THE INVENTION Accordingly, the present invention has been made to solve the above-mentioned problems occurring in the prior art, and it is an object of the present invention to provide a jam welding system capable of tracking a weld line even in a state where a cut wire is sprayed on an improvement surface, .

According to an aspect of the present invention, there is provided a welding robot for welding a workpiece, comprising: a welding robot for performing a welding operation; and a welding robot for welding a workpiece to be welded, And a laser vision system for measuring a geometric shape of a welding member by processing the laser beam, wherein the laser vision system comprises a laser vision system for acquiring three- A front image filter installed; A binarization processor for binarizing the three divided images acquired by the laser vision system; A closure / open operation unit for performing closure and open operation, which are morphology operations, on the binarized image processed by the binarization unit; And a point extracting unit for extracting a point at which the connecting line and the intermediate image match each other by obtaining the center of gravity of the top and bottom images from the closed and open computed images in the closed / open computation unit, And a glass part formed at both ends of the band-pass filter part so as to acquire the same image as the image acquired through the camera, in order to acquire the same image as the image acquired by the camera .

delete

According to another aspect of the present invention, there is provided an image processing method for tracking a weld line of a submerged arc welding system, the method comprising: a welding robot for performing a welding operation; And a laser vision system for measuring the geometrical shape of the welding member by processing the image obtained by irradiating the cut wire to the improvement surface. A step of installing an image filter in front of the laser vision system and acquiring three divided images along a traveling direction of the welding system through a laser vision system; Binarizing the acquired three-divided image; Performing a closing and opening operation on the processed binarized image to obtain the center of gravity of the top and bottom images from the obtained image, respectively, and extracting a point where the connected line and the center image meet, and using the extracted point as a weld line tracking point, The image filter has a bandpass filter section so that the middle part can acquire the same image as the image acquired by the laser vision system itself and is provided with a bandpass filter section so as to acquire the same image .

delete

According to the present invention, there is an advantage that, even in the case of jumbo welding using a cut wire on the improvement surface, the weld line can be traced from the three divided images acquired in the laser vision system.

1 is a schematic view of a conventional submerged arc welding system.
Fig. 2 is a conceptual diagram of the measurement of a laser vision system in the case of jumbo welding without cut wires. Fig.
Fig. 3 is a measurement image of a laser vision system in case of a jam welding without using a cut wire.
Fig. 4 is a schematic diagram of the measurement of a laser vision system in a jam welding using a cut wire. Fig.
Fig. 5 is a measurement image of a laser vision system in a jam welding using a cut wire.
FIG. 6 is a view showing the construction of a jam welding system capable of tracking a weld line according to the present invention. FIG.
FIG. 7 is a conceptual view of the image filter of FIG. 6;
8 is an image measured in a laser vision system according to the present invention.
9 is an image after the binarization processing of Fig.
10 is an image after the morphology closing and opening operation processing of Fig.
11 is a flow chart of an image processing method for tracking a weld line of a jam welding system according to the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 6 is a view showing a welding line system capable of tracking a weld line according to the present invention, FIG. 7 is a conceptual view of the image filter of FIG. 6, FIG. 8 is an image measured in the laser vision system according to the present invention, 10 is an image after the morphological closing and open computation processing in Fig.

As shown in the figure, the welding line tracking system according to the present invention includes a welding robot (110) for performing a welding operation so that the welding line can be traced even in the case of the damper welding using the cut wire on the improvement surface, In addition to the laser vision system 120 which is installed on one side of the welding robot 110 and measures the geometrical shape of the welding member by processing an image obtained by irradiating the welding member to be welded with a laser, A binarization processing unit 140 and a closing / opening operation unit (not shown) installed in front of the laser vision system 120 so as to acquire images divided into three according to the traveling direction of the welding system, 150).

The image filter 130 includes a bandpass filter 131 formed in a band shape at an intermediate portion and glass portions 132 and 133 formed at both ends.

That is, the image filter 130 is a band-pass filter unit 131 having a center wavelength of about 660 nm, for example, so that an image identical to the image acquired by the laser vision system 120 itself can be acquired And the glass parts 132 and 133 are provided so that both end portions can acquire the same image as a camera image, that is, an image acquired through a general camera.

Accordingly, by applying the image filter 130 in front of the laser vision system 120, the image measured in the laser vision system 120 is divided into three regions as shown in FIG.

The binarization processing unit 140 performs binarization processing on an image segmented into three regions acquired by the laser vision system 120. As a result of the binarization process, as shown in Fig. 9, one line is obtained by binarizing only the image of the middle portion, and when the cut wire is sprayed on the improvement surface of the image of the upper and lower ends, .

The closure / open computation unit 150 performs a closure / opening operation, which is a known morphology operation, in order to extract a weld line from the binarized image processed by the binarization processing unit 140, . In the case of a morphology closing and opening operation, noise reduction is performed. As a result, as shown in Fig. 10, the uneven image becomes a uniform image.

For reference, the morphology operation is an image processing technique used for transforming the shape of a specific object existing in an image, and is also used for expressing or describing the shape of an object. Morphology operations are mainly used for binary image processing, and can be extended to gray scale images.

On the other hand, in the point extracting unit (not shown), the center of gravity of the upper and lower images is obtained from the closed and opened images of the closed / open calculation unit 150, It can be used as a tracking point.

11 is a flowchart of an image processing method for tracking a weld line of a jam welding system according to the present invention.

The image processing method of the present invention includes a welding robot for performing a welding operation and a laser vision detecting unit for detecting a geometric shape of the welding member by processing an image obtained by irradiating a laser to a welding member to be welded, System is a method of image processing for tracking a weld line in a case where a welding operation is performed by spraying a flux and a cut wire on an improvement surface.

Referring to FIG. 11, an image filter is installed in front of the laser vision system, and a three-divided image is acquired through the laser vision system along the traveling direction of the welding system (S110). As shown in Fig. 7, the image filter is a band-pass filter unit so that the same image as the image acquired by the laser vision system itself can be acquired. It may be a glass part so that an image can be obtained.

By using the image filter in front of the laser vision system, the image measured in the laser vision system is divided into three regions as shown in FIG.

Subsequently, the obtained three-divided image is binarized (S120). As a result of the binarization process, as shown in Fig. 9, one line is obtained only by binarization of the image in the middle portion, and an uneven image is obtained due to the influence of the cut wire when the cut wire is sprayed on the images of the upper and lower ends.

Finally, in order to extract the weld line from the processed binarized image, a binarization image of the upper and lower ends is sequentially subjected to a closure and an open operation, which are morphology operations (S130). As a result of the closing and opening operation, as shown in Fig. 10, the uneven image becomes a uniform image.

From the obtained image, the center of gravity of the top and bottom images can be obtained, and the point where the connected line and the center image meet can be extracted and used as the weld line tracking point.

For reference, in the case of arc welding, since the position accuracy required for welding line tracking is not generally large and the melting point is large, the welding line tracking error can be applied even if the tracing performance is somewhat deteriorated. When applied, it occurs within a range that does not cause deterioration of welding quality.

While the present invention has been described in connection with certain exemplary embodiments thereof with reference to the accompanying drawings, it is to be understood that the invention is not limited to the specific embodiments thereof, And various modifications, alterations, and changes may be made without departing from the scope of the present invention.

Therefore, the embodiments disclosed in the present invention and the accompanying drawings are intended to illustrate and not to limit the technical spirit of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments and the accompanying drawings . The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

100: jam welding system 110: welding robot
120: Laser vision system 130: Image filter
131: band-pass filter unit 132, 133:
140: binarization processing unit 150: closed / open operation unit

Claims (5)

A welding robot 110 for performing a welding operation and a laser vision system for measuring a geometrical shape of a welding member by processing an image obtained by irradiating a welding member to be welded on one side of the welding robot 110 120), characterized in that:
An image filter 130 installed in front of the laser vision system 120 so as to acquire three-divided images along the traveling direction of the welding system through the laser vision system 120;
A binarization processing unit (140) for binarizing the three divided images acquired by the laser vision system (120);
A closure / open operation unit 150 for performing a closure operation and an open operation, which are morphology operations, on the binarized image processed by the binarization processing unit 140;
And a point extracting unit for extracting a center point of each of the top and bottom images from the closed and open computed images in the closure /
The image filter 130 includes a band-pass filter 131 formed in a band shape at an intermediate portion so as to acquire the same image as the image acquired by the laser vision system itself, (133, 132) formed at both ends of the welded joints. delete delete And a laser vision system for measuring a geometric shape of the welding member by processing an image obtained by irradiating a laser to a welding member provided on one side of the welding robot for performing a welding operation, A method of image processing for tracking a weld line in a case where a cut wire is sprayed on an improvement surface to perform a welding operation,
Installing an image filter in front of the laser vision system and acquiring a three-divided image along a traveling direction of the welding system through a laser vision system;
Binarizing the acquired three-divided image;
The processed binarized image is subjected to closure and opening operations, which are morphology operations, and the center of gravity of the top and bottom images is obtained from the obtained image, and a point at which the connected line and the center image meet is used as a seam line tracking point and,
The image filter is a band-pass filter unit so that the middle part can acquire the same image as the image acquired by the laser vision system itself. The image filter is made into a glass part so that the image of the both ends can be acquired by the camera Image Processing Method for Seam Lining Tracking of a Submerged Arc Welding System. delete

Images