JPH0221206A - Detection of groove by image processing - Google Patents

Abstract

PURPOSE:To always certainly control a groove by a method wherein the imaging signal of a welded part is integrated and subsequently subjected to differentiation processing to detect a root gap and a shoulder from a peak value and, when the peak value is a predetermined value or less, a root gap width is calculated from a shoulder detected value. CONSTITUTION:The imaging signal of a gap part G by an imaging device 42 is supplied to an operational processing part 48 and the positions of two sets of shoulder parts and root gap parts are detected by an integrating means 50 and a differentiation means 52. In this case, when a judge means 55 judges that the differentiated value by the means 52 is a reference value or less, the operation of formula I, G=Go+L-Lo is operated on the basis of the detection result of the shoulder parts by an operation means 56 to determine the width of a gap G. Therefore, a root gap width is substantially detected with respect to a part impossible to detect a root gap such as a temporary welded part and a groove can be always controlled accurately. In the formula, Go is a reference root gap width, L is an actually measured shoulder width and Lo is a reference shoulder width.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a method of imaging a groove for automatic arc welding, for example, prior to a welding torch, and determining the root gap width from the image information.

[Prior Art] There is an arc welding method that controls penetration by detecting the root gap width and controlling the welding current. In this case, the root gap width was detected by detecting the position of the peak point of the image processing result of the groove, which was imaged in front of the torch using a COD camera or the like. For example, the inventors of the present invention have developed a groove detection device that performs integral and differential processing on the brightness of an image of the groove to detect information about the groove necessary to set welding conditions that maintain the welding arc in a predetermined state. Patent application 1986-
No. 89908 has already been filed.

FIG. 4 is an explanatory diagram showing the configuration of the groove detection device, FIG. 5 is a flowchart of the processing steps of the device, and FIG. 6 is a time chart of the processing steps.

In FIG. 4, initial settings are performed so that the base material 26, the groove surface 30, and the root gap width 28 are within the field of view of the imaging device 2 (see step SA in FIG. 5). Note that 24 is an air nozzle for removing fumes generated during welding.

The image signal from the imaging device 2 is manually input to the control unit 4 (see step SC).

This control section 4 is connected to a memory 6 and an arithmetic processing section 8, respectively. This arithmetic processing section 8 has an integrating means 10, a differentiating means 12, a detecting means 14, and an arithmetic means 16, respectively. Further, the detection means 14 is provided with a limiter 18 that suppresses large fluctuations due to erroneous detection.

In order to speed up and simplify information processing, the control unit 4 usually sets or sets only a small region as shown by the - dotted chain line in FIG. 6 (8) as a processing region for the image of the imaging device 2. The pixel data within these areas are read out from the memory 6 and subjected to subsequent signal processing. Further, each region is designed to track the positions of root gap ends GA, GB, shoulders KA, KB as welding progresses.

FIG. 6(C) shows the luminance data of each pixel at an appropriate X coordinate value. As shown in this figure, the brightness is generally high at the aperture surface 20 and low at the root gap. However, it is difficult to accurately detect the positions of the root gap ends GA, GB, and shoulders KA, KB due to the FA3 effect of optical noise.

Therefore, with respect to the luminance of such a pixel, positional integration is performed by the integrating means lO by adding the Y coordinate in the X direction (see step SC).

Positional integration in the X direction is performed for pixels within the specified area indicated by the dashed line in FIG. 6(A), and as a result, luminance integral data as shown in FIG. 6(D) is obtained. (In the figure, the broken line indicates the part where the integration process is not performed).

Next, for the integral data as described above, the differentiating means 12
Differentiation is performed by (see step SC). This differentiation is performed by finding the absolute value of the difference between the luminances (QA, QB) of the pixels located second to the left and right of the pixel for which the differential value is sought.

Differential value = l QA-QB Figure 6 (E) shows the differential data obtained in the above manner, and the peaks corresponding to the root gap GAGB, shoulders KA, and KB are clearly visible. .

Next, the detection means 14 detects the positions of the root gaps GA, GB, shoulders KA, KB and measures the root gap width with respect to the differential luminance obtained as described above (see step SC).

In other words, within the designated area shown in Figure 6 (^),
The position of the pixel with the maximum differential value is determined and detected as the position of the root gap GA, GB, shoulder KA, KB. The root gap width 28 is measured from the detected root gaps GA and GB.

Next, welding data such as a welding current command value and welding speed are calculated by the calculation means 16 from the measured gap width 28 using a predetermined conversion formula (see step SC). This welding data is stored in the -degree memory 6, and after a predetermined delay, is output from the control unit 4 to the welding control device 20 (see step SC) to control the welding current command value, welding speed, etc. of the welding torch 22. do.

The above operations are repeated, and when all welding is completed, the operation of the device is also completed (see step SC).

[Problems to be Solved by the Invention] However, with the detection method of the above-mentioned device, the root gap may not appear in the image due to light from the back side, or if the root gap is actually filled due to tacking at a welded part, etc. Similarly, since root gap information does not appear in the image, the gap width cannot be detected. In addition, even if it is not a special case like the above, if there is not much difference in brightness between the groove surface and the groove surface, noise due to humus or scratches on the groove surface may be mistaken for the gap width, which may cause malfunction. There was a possibility.

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to provide a groove detection method using images that allows reliable welding even in situations where it is difficult to detect the root gap position due to disappearance of the root gap end during welding.

[Means for Solving the Problem] The groove detection method using image processing according to the invention includes an integral step of performing an integral process on image information of a groove image captured by an imaging means; The method includes a differentiation process that performs differential processing on image information, and a detection process that obtains information about the groove dimensions from the differentiated image information, and a detection process that maintains the welding arc in a predetermined state with respect to the groove. A groove detection method using image processing to obtain information regarding the positions of the two root gap edges GA, GB and two shoulders KA, KB necessary for controlling welding conditions by limiting the corresponding two-dimensional detection areas. comprising a determination step of determining whether peak values corresponding to the two root gap ends GA and GB are greater than or equal to a predetermined value, and if the peak values are greater than or equal to the predetermined value in the determination step, each of the peak values Two root gap edges GA.

The root gap width is determined by determining the position of GB, and if it is less than a predetermined value in the determination step, the two root gap ends GA are indirectly divided by the positions of the shoulder KA and KB of the two grooves, This determines the width dimension between GB.

[Operation] In the wood invention, after the differentiation step, it is determined whether the peak value of the root gap of the groove is equal to or greater than a predetermined value, and if it is less than the predetermined value, the detected groove shoulder KA,
The estimated value of the gap width is indirectly determined by calculation from the position of KB.

The calculation method is to add A, KB to the shoulder of the detected groove.
The measured shoulder width measured from each position and the reference shoulder width of the groove shape that was stored in advance during initial setting. , the estimated root gap width G is calculated using the reference root gap width Go using the following calculation formula.

G=GO+t, -t,.

[Example] Fig. 1 is an explanatory diagram showing the configuration of a groove detection device according to the present detection method, Fig. 2 is a flowchart of the processing steps of the device, and Fig. 3 is a flowchart of the processing steps of the device.
The figure shows timer 1 of the tack welding process.

In FIG. 1, initial settings are performed so that the base material 66, the groove surface 70, and the root gap width G are included in the field of view of the imaging device 42, and at the same time, the reference shoulder width of the groove shape is set. , reference root gap width G. The values of basic data such as the following are manually input (see step Sa in FIG. 2). Note that 64 is an air nozzle for removing fumes generated during welding.

The image signal from the imaging device 42 is manually input to the control unit 44 (see step sb).

This control section 44 is connected to a memory 46 and an arithmetic processing section 48, respectively. This arithmetic processing section 48 includes the integrating means 5
0, differentiating means 52, detecting means 54, determining means 55, and calculating means 56, respectively. Further, the detection means 54 includes:
A limiter 58 is provided to suppress large fluctuations due to erroneous detection.

In order to speed up information processing and simplify i7H, the control unit 44 normally sets only a minute area as shown by the dashed line in FIG. 3 (8) as a processing area for the image of the imaging device 42. pixel data within these areas is read out from the memory 46 and subjected to subsequent signal processing.

In addition, as welding progresses in each area, the root gap edge GA,
The positions of GB, shoulder KA, and KB are tracked.

FIG. 3(C) shows the luminance data of each pixel in the Xa region including the welding portion 69 which is tack welded from the back side at the root gap portion.

As shown in this figure, the brightness at the root gap is low to some extent, but the brightness distribution within the groove is flat and unclear as a whole. Due to the influence of overall optical noise, not only the root gap edge GAGB but also the shoulder K
It is difficult to detect the positions of A and KB well.

Therefore, the positional integration of the luminance of the pixel is performed by the integrating means 50 by adding the Y coordinate in the X direction (see step Sc).

Position integration in the X direction is performed for pixels within the four designated areas indicated by the dashed-dotted lines in Figure 3 (A), and as a result, luminance integral data as shown in Figure 3 (D) is obtained. (In the figure, the broken line indicates the part where the integration process is not performed).

Next, for the integral data as described above, the differentiating means 52
Differentiation is performed by (see step Sc). This differentiation is performed by finding the absolute value of the luminance difference between the pixels (QA, QB) located second to the left and right of the pixel for which the differential value is sought.

Differential value=lQA-QB FIG. 3(E) shows the differential data obtained in the above manner. The root gap GA, GB, and shoulder KA are determined by the detection means 54 based on the differential luminance data obtained as described above.

The position of KB is detected and the root gap width is measured (
(see step Se), but as shown in the figure, the shoulder K
The peaks corresponding to A and KB are clearly visible, while the peaks corresponding to root gaps GA and GB are on the groove surface 7.
It can be seen that because there is not much difference in brightness from 0, it does not appear clearly. At this time, noise etc. occur and the root gap G
If it becomes higher than the peak corresponding to A, GB,
This noise may be applied to the root gap end, resulting in malfunction.

Therefore, a determination is made to determine whether or not the peaks corresponding to the detected root gaps GA and GB are equal to or greater than a predetermined value (see step Si).

If the value is greater than or equal to the predetermined value, the value detected by the detection means 54, that is, within the designated area shown in FIG.
The position of the pixel with the maximum differential value of ε) is determined by the root gap G
Detected as the position of A, GB, shoulder KA, KB,
The root gap width G is measured from the detected root gear amplifiers GA and GB, and the value is sent to the next calculation means 56.

If it is smaller than the predetermined value, the measured shoulder width calculated from the respective positions of the shoulders KA and KB of the groove detected by differentiation and the reference shoulder of the groove shape stored in advance at the time of initial setting are used. Width Lo, standard root gap width G. The estimated root gap width G is calculated using the following calculation formula +11 (see step Sc), and the value is sent to the next calculation means 56.

G=GO+L-LO・+11 By the way, the characteristics of the change in the magnitude of the welding current to maintain the penetration depth with respect to the change in the root cap width of the groove between the two members to be joined are the characteristics of the welding wire and shielding gas. Various penetration depths are determined in advance through experiments as relationships specific to the materials used. For example, if the welding current is I
, the root gap width is G, and the welding current when the root gap width is zero is Io, then within the welding speed range, 1 ” I o k G
... It has been confirmed that a linear change characteristic expressed by the linear form of (2) can be obtained, where k in the above equation is a constant uniquely determined by the material used, etc.

Similarly, the welding speed V is also determined in advance through experiments as shown in conversion formula (3) below.

V=K・Vr/(So+△5(G))...(3) However, K is the wire cross-sectional area, vf is the wire feeding speed, So is the appropriate welding cross-sectional area when the gap is 0, △S ( G) is the groove cross-sectional area increase number.

Therefore, the welding current command value, welding speed, etc. are calculated by the calculation means 56 from the measured and calculated gap width G using the conversion formulas (2) and (3) (see step Sc). This welding data is stored in the -degree memory 46, and after a predetermined delay, is sent from the control section 44 to the welding control device 6.
0 (see step 5g), and controls the welding current command value, welding speed, etc. of the welding torch 62.

The above operations are repeated, and when all welding is completed, the operation of the apparatus is also completed (see step Sh).

By performing the judgment process as described above, even if the root gap does not appear in the image data during the welding process due to temporary welding or light from the back side, it is possible to ensure the output of the root gap width, and it is possible to ensure penetration. Control can be carried out reliably.

Furthermore, differential value peaks smaller than a predetermined value are discarded, reducing malfunctions and greatly increasing reliability.

In addition, the groove of the back weld joint after front welding is already 1
Since the bottom of part 848 has melted, there may be no root gap. Even in such a case, the groove detection method using Sueyori image processing makes it possible to perform welding without requiring any other special 11S setting.

[Effects of the Invention] As explained above, the present invention has a determination process for determining the root gap of the groove, so that the root gap is not displayed in the image data during the welding process during tack bonding due to welding or light from the back side. It is possible to secure the output of the root gap width even if it is not the same, and to perform penetration control reliably. Furthermore, since data smaller than a predetermined value is discarded, malfunctions are reduced and reliability is greatly improved.

[Brief explanation of the drawing]

Figure 1 is an explanatory diagram showing the configuration of a groove detection device using the present detection method, Figure 2 is a flowchart of the processing steps of the device, and Figure 3 is a flowchart of the processing steps of the device.
The figure is a time chart of the processing process of the welding part for tack attachment.
FIG. 5 is an explanatory diagram showing the configuration of the groove detection device, FIG. 5 is a flowchart of the processing steps of the device, and FIG. 6 is a time chart of the processing steps. In the figure, 50 is an integrating means, 52 is a differentiating means, 54 is a detecting means, 55 is a determining means, and 56 is a calculating means. Patent attorney Tadashi Sato October 26, 1988

Claims (1)

[Claims] An integration step of performing an integral process on image information of a groove image captured by an imaging means; a differentiation step of performing a differentiation process on the integrated image information; two root gap ends GA necessary for controlling welding conditions to maintain the welding arc in a predetermined state with respect to the groove, In a groove detection method using image processing in which information regarding the positions of GB, two shoulders KA and KB is obtained by limiting two-dimensional detection areas corresponding to each, peaks corresponding to the two root gap edges GA and GB are obtained. It has a determination step of determining whether the value is greater than or equal to a predetermined value, and if the value is greater than or equal to the predetermined value in the determination step, the positions of the two root gap ends GA and GB are determined based on the respective peak values and the root gap is determined. If the width is determined and is less than a predetermined value in the determination step, the two root gap ends GA are calculated indirectly from the positions of the shoulders KA and KB of the two grooves,
A groove detection method using image processing to determine the width between GB.