JP7165924B2 - Welding condition setting support device - Google Patents

Description

TECHNICAL FIELD The present invention relates to an apparatus for assisting setting of welding conditions when performing arc welding by applying a voltage between a work and an electrode to generate an arc between the work and the electrode.

In Patent Document 1, a plurality of input images are acquired by photographing the arc with a video camera during arc welding, the luminance distribution on a predetermined detection line in the image is captured for each input image, and based on the luminance distribution on the detection line A technique for specifying the number of spatters generated during arc welding by detecting spatters that have passed through is disclosed.

JP 2009-28775 A

However, in Patent Document 1, spatters passing through the detection line are detected based on a plurality of input images, so if the imaging speed of the video camera is too slow, the accuracy of the number of specified spatters deteriorates. Therefore, a video camera with a high shooting speed is required, increasing equipment costs.

The present invention has been made in view of the above points, and an object of the present invention is to reduce equipment costs.

In one aspect of the present invention, a device for supporting setting of welding conditions when performing arc welding by applying a voltage between the work and the electrode to generate an arc between the work and the electrode includes the arc A spatter detection process for detecting spatter composed of a plurality of consecutive pixels whose pixel value indicating brightness exceeds a predetermined threshold in an input image obtained by photographing the work during welding, excluding a predetermined mask area. and a spatter number identification process for identifying the number of spatters detected by the spatter detection process.

According to this aspect, since spatter can be detected using only one input image, a high-speed video camera is not required, and equipment costs can be reduced.

Also, since the number of spatters larger than a predetermined size corresponding to the threshold value is identified, the welding conditions are adjusted so as to reduce the number of spatters larger than the predetermined size by referring to the identified number of spatters. Easy to set. Therefore, it becomes easy to reduce spatters larger than a predetermined size.

In addition, by using the area where the arc light and the welding jig are reflected in the input image as the mask area, it is possible to suppress erroneous detection of spatter as spatter, so that the number of spatter can be specified more accurately. be possible.

According to the welding condition setting support device according to the present invention, since spatter can be detected using only one input image, a video camera with a high imaging speed is not required, and equipment costs can be reduced.

Also, since the number of spatters larger than a predetermined size corresponding to the threshold value is identified, the welding conditions are adjusted so as to reduce the number of spatters larger than the predetermined size by referring to the identified number of spatters. Easy to set. Therefore, it becomes easy to reduce spatters larger than a predetermined size.

In addition, by using the area where the arc light and the welding jig are reflected in the input image as the mask area, it is possible to suppress erroneous detection of spatter as spatter, so that the number of spatter can be specified more accurately. be possible.

1 is a diagram showing a schematic configuration of a welding system provided with a computer as a welding condition setting support device according to an embodiment of the present invention; FIG. FIG. 4 is an explanatory diagram showing spatter generated during arc welding; 5 is a flow chart showing a procedure for setting welding conditions using a computer as a welding condition setting support device according to an embodiment of the present invention; 5 is a flowchart showing the procedure of mask processing; FIG. 4 is an explanatory diagram illustrating a grayscale image of a superimposed image; FIG. 4 is an explanatory diagram illustrating a binarized image of a grayscale image of a superimposed image; FIG. 10 is an explanatory diagram showing a method of extending a white portion of a binarized image; FIG. 4 is an explanatory diagram illustrating an example of a mask image; FIG. 4 is an explanatory diagram illustrating detected spatters; FIG. 10 is an explanatory diagram illustrating an example of a processed image;

BEST MODE FOR CARRYING OUT THE INVENTION An embodiment of the present invention will be described below with reference to the drawings. The following description of preferred embodiments is merely exemplary in nature and is in no way intended to limit the invention, its applicability or its uses.

FIG. 1 shows a welding system 100. As shown in FIG. This welding system 100 includes a welding robot 110, a video camera 120, a memory card 130 accommodated in the video camera 120, a computer 140 as a welding condition setting support device according to the embodiment of the present invention, and the computer 140. and a card reader 150 connected to the

Welding robot 110, as also shown in FIG. By applying a voltage between the work 170 and the welding wire 160, an arc A is generated between the workpiece 170 and the welding wire 160 to perform arc welding. During arc welding, the portion to be welded of the workpiece 170 is melted to form a molten pool 171, and the spatter SP scatters from the molten pool 171. The tip of the welding torch 111 is provided with an ejection hole (not shown) for ejecting shield gas.

The video camera 120 is installed at a position where the entire scattering area of the spatter SP including the entire work 170 can be photographed via an ND (Neutral Density) filter (not shown), and the photographed moving image is saved in the memory card 130 . Note that the frame rate (imaging speed) of the video camera 120 is set to 60 fps. Also, the focus, aperture, and shutter speed of the electronic shutter of the video camera 120 are fixed.

The computer 140 includes a computer main body 141 and a display 142 as a display section. The computer main body 141 includes a storage section 141a and an image processing section 141b.

The storage unit 141a of the computer main body 141 stores a learned model generated by supervised learning using a plurality of images containing the spatter SP and a plurality of images not containing the spatter SP as training data. . Deep learning, for example, is used as a supervised learning method for generating a trained model. Note that the storage unit 141a further stores moving images captured by the video camera 120 and still images obtained by dividing the moving images.

The image processing unit 141b of the computer main body 141 reads the moving image stored in the memory card 130 inserted in the card reader 150, and stores it in the storage unit 141a. Further, the image processing unit 141b divides the moving image stored in the storage unit 141a into still images (frames) and stores the still images in the storage unit 141a as input images. Further, the image processing unit 141b determines a mask area based on a plurality of input images stored in the storage unit 141a, detects spatter SP from the area of the input image excluding the mask area, and determines the number of detected spatter SP. are identified (mask area determination processing, spatter detection processing, spatter number identification processing). The detection of the spatter SP is performed using the trained model stored in the storage unit 141a. Further, the image processing unit 141b generates a processed image I (see FIG. 10) by performing predetermined processing on the input image (image generation processing). Details of the method of determining the mask area, the method of detecting the spatter SP, the method of specifying the number of the spatter SP, and the method of generating the processed image I will be described later.

The display 142 displays the processed image I generated by the image processing section 141 b of the computer main body 141 .

A procedure for setting welding conditions for the welding system 100 will be described below with reference to FIG.

First, in ( S<b>101 ), the user causes the video camera 120 to shoot and save the shot video in the memory card 130 while the welding robot 110 is performing arc welding. As a result, a moving image of the entire spatter SP scattering region including the entire work 170 during arc welding is saved in the memory card 130 .

Next, in ( S<b>102 ), the user removes the memory card 130 from the video camera 120 and inserts it into the card reader 150 to transfer the moving image saved in the memory card 130 from the card reader 150 to the computer main body 141 . Then, the image processing unit 141b of the computer main body 141 receives the moving image transferred from the card reader 150 and stores it in the storage unit 141a.

Next, in (S103), the user causes the image processing unit 141b of the computer main body 141 to divide the moving image during arc welding stored in the storage unit 141a into a plurality of still images (frames), and converts the still images into input images. is stored in the storage unit 141a.

Then, in (S104), the image processing unit 141b performs the following mask processing.

FIG. 4 shows the procedure of mask processing performed in (S104).

In (S104), first, in (S201), the image processing unit 141b converts all input images (frames) stored in the storage unit 141a into grayscale images. It should be noted that the pixel value of the grayscale image indicates the brightness by 8 bits, the pixel value indicating black is 0, and the pixel value indicating white is 255.

Next, in (S202), the image processing unit 141b generates a superimposed image based on the grayscale images of all the input images obtained in (S201). The pixel value of each pixel of the superimposed image is the average of the pixel values of all the grayscale images obtained in (S201). FIG. 5 illustrates the superimposed image obtained in (S202).

Next, in (S203), the image processing unit 141b converts the superimposed image generated in (S202) into a binarized image. Specifically, the pixel values of the pixels whose pixel values in the superimposed image are equal to or less than a predetermined reference value are converted to a value (0) indicating black, and the pixel values of the pixels whose pixel values in the superimposed image exceed a predetermined reference value are converted into , to a value (255) indicating white. FIG. 6 illustrates the binarized image obtained in (S203).

In (S204), the image processing unit 141b generates a mask image by expanding the white portion of the binarized image obtained in (S203). Specifically, as shown in FIG. 7, processing is performed to convert black pixels contained in a 7×7 area RE centering on the white pixel WP of the binarized image obtained in (S203) into white pixels. FIG. 8 illustrates the mask image obtained in (S204). As a result, the area of white pixels in the mask image is determined as the mask area.

Then, in (S205), the image processing unit 141b performs a process of subtracting the pixel value of each pixel of the mask image from the pixel value of each pixel for each input image stored in the storage unit 141a. is stored in the storage unit 141a as an image after mask processing. In the image after mask processing, the mask area determined in (S204) becomes black pixels. This completes the mask processing.

After the mask processing is completed, in (S105), the image processing unit 141b selects the masked image that has not undergone the processes (S105) to (S111) among the masked images saved in the storage unit 141a. to a grayscale image.

Next, in (S106), the image processing unit 141b sets the pixel values of pixels whose pixel values are equal to or less than a predetermined threshold value Gs to a value (0) indicating black in the grayscale image obtained in (S105). A conversion process is applied to obtain a spatter detection target image IM. As a result, a pixel whose pixel value indicating brightness exceeds a predetermined threshold value Gs is specified as a non-black pixel (specific pixel). Then, for example, as shown in FIG. 9, a region composed of a plurality of consecutive pixels is detected as spatter SP from non-black pixels (specific pixels) included in the spatter detection target image IM. In FIG. 9, PB indicates black pixels and PW indicates pixels other than black. The detection of the spatter SP here is performed using the learned model stored in the storage unit 141a. Then, a first spatter list ListGs that identifies all the detected spatters SP is created.

Next, in (S107), the image processing unit 141b converts the pixel values of pixels whose pixel values are equal to or less than a predetermined threshold value Gm (first threshold value) to black in the grayscale image obtained in (S105). A process for converting to the indicated value (0) is performed, and a region composed of a plurality of continuous pixels is detected as spatter SP from pixels other than black (specific pixels) in the processed image. The detection of the spatter SP here is also performed using the learned model stored in the storage unit 141a. Note that the threshold Gm is set to a value larger than the threshold Gs. Then, a second spatter list ListGm that identifies all the detected spatters SP is created.

Next, in (S108), the image processing unit 141b converts the pixel values of pixels whose pixel values are equal to or lower than a predetermined threshold value Gl (second threshold value) to black in the grayscale image obtained in (S105). A process for converting to the indicated value (0) is performed, and a region composed of a plurality of continuous pixels is detected as spatter SP from pixels other than black (specific pixels) in the processed image. The detection of the spatter SP here is also performed using the learned model stored in the storage unit 141a. Note that the threshold Gl is set to a value greater than the threshold Gm. Then, a third spatter list ListGl that identifies all the detected spatters SP is created. In the first to third spatter lists ListGs, ListGm, and ListGl, the spatters SP are specified by coordinates.

Here, as the size of the spatter SP increases, the brightness of the spatter SP also increases. Therefore, the spatter SP specified in (S106) to (S108) is larger than the size corresponding to each of the thresholds Gs, Gm, and Gl. It becomes the number of spatter SP.

In addition, since the masked area determined in (S204) is a black pixel in the masked image, the detection of the spatter SP in (S106) to (S108) is based on the input image excluding the masked area. will be done for

Next, in (S109), the image processing unit 141b specifies a small spatter SP excluding the spatter SP specified by the second spatter list ListGm from the spatter SP specified by the first spatter list ListGs. Create a list SmallS. Further, the image processing unit 141b identifies the number of spatters SP identified by the small spatter list SmallS as the spatter count S of the small spatters SP.

Subsequently, in (S110), the image processing unit 141b specifies medium spatter SP excluding spatter SP specified by the third spatter list ListGl from the spatter SP specified by the second spatter list ListGm. Create a list MiddleS. In addition, the image processing unit 141b identifies the number of spatters SP identified in the middle spatter list MiddleS as the spatter count M of medium-sized spatters SP.

Subsequently, in (S111), the image processing unit 141b sets the third spatter list ListGl as a large spatter list LargeS as it is, and sets the number of spatters SP specified by the large spatter list LargeS as the number of large spatters SP. It is specified as the number of spatters L.

Next, in (S112), the image processing unit 141b determines whether or not the post-masking image (frame) that has not undergone the processing of (S105) to (S111) remains in the storage unit 141a. Then, if it remains, the process returns to (S105), and if not, the process proceeds to (S113).

In (S113), the image processing unit 141b specifies the total number of spatters S, M, and L as the total number of spatters T. FIG. Further, the image processing unit 141b adds a display of the frame number and the total number of spatters T to the upper left corner of each input image, and displays the spatters SP specified by the small spatter list SmallS as blue rectangles. Processing to surround the shape frame F1, surround the spatter SP specified by the middle spatter list MiddleS with a yellow rectangular frame F2, and surround the spatter SP specified by the large spatter list LargeS with a red rectangular frame F3. to generate a processed image I illustrated in FIG. In FIG. 10, a blue frame F1 is indicated by a double line, a yellow frame F2 is indicated by a solid line, and a red frame F3 is indicated by a broken line. Further, in FIG. 10, A' indicates a region in which the light of the arc A itself and the workpiece 170, the welding jig, and the fume illuminated by the light of the arc A are reflected. Since the area A' is made a mask area by masking, it is possible to suppress erroneous detection of objects other than the spatter SP as the spatter SP, and to more accurately specify the number of the spatter SP. In addition, in (S201) to (S204), since the mask area is determined based on a plurality of input images of the work 170 taken during arc welding, objects that are likely to be erroneously detected as spatter SP, such as the work 170 and welding jigs, can be detected. Even if the relative position with respect to the video camera 120 is not fixed, it is possible to more reliably prevent objects other than the spatter SP from being erroneously detected as the spatter SP.

At (S114), the display 142 displays the processed image I generated at (S113). By referring to the total number of spatters T displayed on the display 142, the user determines whether the welding conditions, such as the voltage value applied between the workpiece 170 and the welding wire 160, are appropriate. When the user determines that the welding conditions are inappropriate, the user changes the welding conditions so as to reduce the number of large spatters SP, and executes the processes (S101) to (S114) again. Also, at this time, the spatter SP is displayed on the display 142 with frames F1, F2, and F3 having colors corresponding to the size thereof. The reliability of the number of spatters T displayed at 142 can be determined.

Therefore, according to the present embodiment, in (S105) to (S111), the image processing unit 141b specifies the number of spatters SP using only one input image (image after mask processing). The processing can be simplified compared to the case of specifying the number of spatters SP using a plurality of input images as in the above. Also, the number of spatters SP can be specified using only one input image, and a video camera with a high imaging speed is not required as the video camera 120, so equipment costs can be reduced.

In general, even if small spatters SP adhere to the work 170, the spatters SP can be easily removed with a metal brush or the like. However, the number of man-hours required for removal increases.

According to the present embodiment, in (S106) to (S108), the image processing unit 141b detects the spatter SP by combining a plurality of images in which the spatter SP is captured and a plurality of images in which the sputter SP is not captured. is used as the training model generated by supervised learning with . It is difficult to detect, for example, a part of the spatter SP that is not the spatter SP. Therefore, the possibility of erroneous detection can be reduced.

In general, the larger the spatter SP, the heavier the spatter SP, and the lower the moving speed. Therefore, the larger the spatter SP, the shorter the trajectory of the spatter SP reflected in one input image. Therefore, even when the imaging range is narrowed, large spatters SP are more likely to fall within the imaging range than small spatters SP, and large spatters SP are less likely to be missed in detection.

In the present embodiment, the image processing unit 141b once converts the post-masking image into a grayscale image in (S105). A pixel whose pixel value indicating brightness exceeds a predetermined threshold may be specified as a specific pixel.

In addition, in this embodiment, in (S106) to (S108), the spatter SP is detected using the learned model. may Alternatively, all regions in which pixels other than black are continuous in a number equal to or more than the first number and equal to or less than the second number (>the first number) may be detected as the spatter SP. In this case, since a region in which non-black pixels are consecutive in excess of the second number is not detected as spatter SP, it is possible to prevent spatter SP from being erroneously detected as spatter SP.

Further, in the present embodiment, the processed image I is obtained by adding frames F1, F2, and F3 to the detected spatter SP in the input image. A processed image I may be used.

Also, in the present embodiment, the image processing unit 141b of the computer main body 141 receives the moving image including the input image from the card reader 150, but it may be received from another information transmission device.

Moreover, in the present embodiment, the present invention is applied to arc welding using the welding robot 110, but the present invention can also be applied when the welding torch is operated manually.

Moreover, in the present embodiment, the present invention is applied when the voltage applied between the work 170 and the welding wire 160 is not a pulse voltage. It can also be applied when the voltage applied is a pulse voltage.

Further, in this embodiment, in (S105) to (S108), the spatter SP is detected using the post-masking image. However, by once detecting the spatter SP from the input image and omitting the spatter SP located in the mask area from the list of the detected spatter SP, the sputter SP is detected for the area in the input image from which the mask area is omitted. may

Further, in the present embodiment, the input image is processed to display only the frame number and the total number of spatters T to obtain the processed image I. However, in addition to the frame number and the total number of spatters T, A processed image I may be obtained by processing to give the indications of M and L. FIG.

The welding condition setting support device of the present invention can reduce equipment costs, facilitate reduction of spatters larger than a predetermined size, and suppress erroneous detection of spatters that are not spatters. It is useful as a device for supporting the setting of welding conditions when arc welding is performed by applying a voltage between the work and the electrode to generate an arc between the work and the electrode.

140 computer (welding condition setting support device)
141a storage unit
141b image processing unit 142 display (display unit)
160 welding wire (electrode)
170 Work A Arc SP Sputter I Processing images F1, F2, F3 Frames (marks)

Claims (4)

A device for supporting the setting of welding conditions when performing arc welding by generating an arc between the work and the electrode by applying a voltage between the work and the electrode,
Spatter detection is performed to detect spatter composed of a plurality of continuous pixels whose pixel values indicating brightness exceed a predetermined threshold in an area excluding a predetermined mask area in an input image obtained by photographing the workpiece during arc welding. a detection process; a spatter number specifying process for specifying the number of spatters detected by the spatter detection process ; and a mask area determination for determining the mask area based on a plurality of input images taken of the workpiece during the arc welding. A welding condition setting support device comprising an image processing unit that executes processing . A device for supporting the setting of welding conditions when performing arc welding by generating an arc between the work and the electrode by applying a voltage between the work and the electrode,
Spatter detection is performed to detect spatter composed of a plurality of continuous pixels whose pixel values indicating brightness exceed a predetermined threshold in an area excluding a predetermined mask area in an input image obtained by photographing the workpiece during arc welding. an image processing unit that performs a detection process and a spatter number identification process that identifies the number of spatters detected by the spatter detection process;
The image processing unit sets the predetermined threshold to a first threshold and a second threshold larger than the first threshold, and executes the spatter detection process,
In the spatter number specifying process, out of the spatters detected by the spatter detection process in which the predetermined threshold is set to the first threshold, the spatter detected by the spatter detection process in which the predetermined threshold is set to the second threshold is detected. and the number of spatters detected by a spatter detection process in which the predetermined threshold is set to the second threshold, and the number of spatters detected by the second threshold is specified. . A device for supporting the setting of welding conditions when performing arc welding by generating an arc between the work and the electrode by applying a voltage between the work and the electrode,
Spatter detection is performed to detect spatter composed of a plurality of continuous pixels whose pixel values indicating brightness exceed a predetermined threshold in an area excluding a predetermined mask area in an input image obtained by photographing the workpiece during arc welding. an image processing unit that executes a detection process and a spatter number specifying process that specifies the number of spatters detected by the spatter detection process;
a display unit for displaying the number of spatters specified by the spatter number specifying process of the image processing unit;andA welding condition setting support device comprising: In the welding condition setting support device according to claim 3 ,
The image processing unit further performs an image generation process for generating a processed image in which the spatters detected by the spatter detection process are marked on the input image, and
The welding condition setting support device, wherein the display unit displays the processed image generated by the image generation process.

Images