CN115338556A - Weld joint quality detection method for thick-wall welding workpiece and computer equipment - Google Patents
Weld joint quality detection method for thick-wall welding workpiece and computer equipment Download PDFInfo
- Publication number
- CN115338556A CN115338556A CN202210929891.3A CN202210929891A CN115338556A CN 115338556 A CN115338556 A CN 115338556A CN 202210929891 A CN202210929891 A CN 202210929891A CN 115338556 A CN115338556 A CN 115338556A
- Authority
- CN
- China
- Prior art keywords
- weld
- curve
- welding
- line
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003466 welding Methods 0.000 title claims abstract description 204
- 238000001514 detection method Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000006243 chemical reaction Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000002787 reinforcement Effects 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 239000011324 bead Substances 0.000 description 6
- 238000007689 inspection Methods 0.000 description 4
- 238000013441 quality evaluation Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004021 metal welding Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/12—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to investigating the properties, e.g. the weldability, of materials
- B23K31/125—Weld quality monitoring
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to a method and equipment for detecting the quality of a welding seam of a thick-wall welding workpiece. The weld joint quality detection method comprises the following steps: carrying out image processing on a metallographic picture of a welding seam section to obtain the outer contour of an inner welding seam and the outer contour of an outer welding seam; drawing an inner welding line curve and an outer welding line curve according to the first outline information and the second outline information; acquiring a first center line, a first horizontal line and a second horizontal line according to the first contour information; acquiring a second center line, a third horizontal line and a fourth horizontal line according to the second contour information; calculating a center deviation value, a misalignment value, a residual height value of an inner welding line and a residual height value of an outer welding line according to the first center line, the second center line, the first horizontal line, the second horizontal line, the third horizontal line and the fourth horizontal line; and judging whether the welding seam quality of the thick-wall welding workpiece is qualified or not according to the center deviation value, the edge error value, the inner welding seam surplus height value and the outer welding seam surplus height value. The welding seam quality detection method can improve the detection efficiency and the detection precision of the welding seam quality detection.
Description
Technical Field
The invention relates to the technical field of welding manufacturing, in particular to a weld joint quality detection method and computer equipment for thick-wall welding workpieces.
Background
In the field of metal welding, for welding of thick-walled workpieces, in consideration of the fact that the wall thickness ratio of the workpieces is relatively thick, two welding grooves are usually machined on the inner side and the outer side of a joint part in order to guarantee the quality of the welded workpieces, and the welding quality is improved by adopting an inner-outer welding mode. However, such welding also causes problems such as the presence or absence of misalignment and displacement of the inner bead and the outer bead, and these problems directly affect the quality of the workpiece. At present, a method of manual observation and judgment is generally adopted for detecting the quality of a welded seam after welding, wherein the most commonly used method of detecting the welded seam is to acquire the cross-sectional shape of the welded seam in a manual mode and judge the quality of the welded seam in a manual line drawing mode.
Disclosure of Invention
Therefore, it is necessary to provide a weld joint quality detection method and a computer device for a thick-wall workpiece, which can improve the weld joint detection accuracy, in order to solve the problem of low detection accuracy in the conventional weld joint detection method for the thick-wall workpiece.
A weld quality detection method for thick-wall welding workpieces comprises the following steps:
obtaining a metallographic picture of a weld joint section of a thick-wall welding workpiece;
carrying out image processing on the metallographic picture of the welding seam section to obtain the outer contour of the inner welding seam and the outer contour of the outer welding seam;
acquiring first contour information according to the outer contour of the inner welding seam, acquiring second contour information according to the outer contour of the outer welding seam, and drawing an inner welding seam curve and an outer welding seam curve according to the first contour information and the second contour information;
respectively storing the inner welding line curve and the outer welding line curve in a first mask and a second mask which have the same size, and performing logic and operation on image pixels in the first mask and the second mask to obtain a first intersection point coordinate of the inner welding line curve and a second intersection point coordinate of the outer welding line curve;
acquiring coordinates of four extreme points of the inner weld curve according to the first contour information, and drawing a first center line, a first horizontal line and a second horizontal line according to the coordinates of the four extreme points of the inner weld curve; the intersection point of the first central line and the first horizontal line is the same as the origin of the coordinate of the first intersection point, and the second horizontal line is a connecting line of the leftmost extreme point and the rightmost extreme point of the inner weld curve;
acquiring coordinates of four extreme points of the outer weld curve according to the second contour information, and drawing a second central line, a third horizontal line and a fourth horizontal line according to the coordinates of the four extreme points of the outer weld curve; the intersection point of the second center line and the third horizontal line is the origin of the second intersection point coordinate, and the fourth horizontal line is the connecting line of the leftmost extreme point and the rightmost extreme point of the outer weld curve;
calculating a center deviation value according to the first center line and the second center line, calculating a misalignment value according to the first horizontal line and the third horizontal line, calculating a residual height value of an inner welding line according to an inner welding line curve and the second horizontal line, and calculating a residual height value of an outer welding line according to an outer welding line curve and the fourth horizontal line;
and judging whether the welding seam quality of the thick-wall welding workpiece is qualified or not according to the center deviation value, the misalignment value, the inner welding seam allowance value and the outer welding seam allowance value.
In one embodiment, the step of performing image processing on the metallographic picture of the welding seam section to obtain the outer contour of the inner welding seam and the outer contour of the outer welding seam comprises the following steps:
preprocessing a metallographic picture of a welding seam section to obtain a smooth image;
using a watershed algorithm to perform segmentation and color filling on the smooth image to obtain a segmentation filling image;
extracting a target area of the weld filling image by using an HSV color space conversion method to obtain an inner weld area and an outer weld area;
and (3) performing curve completion and interference elimination on the contour curve of the inner welding seam region and the contour curve of the outer welding seam region through morphological opening and closing operation, and acquiring the outer contour of the inner welding seam and the outer contour of the outer welding seam by using a canny edge detection method.
In one embodiment, the step of preprocessing the metallographic picture of the weld section to obtain a smooth image comprises: and (4) carrying out image preprocessing on the metallographic picture of the welding seam section by using Gaussian filtering to obtain a filtered smooth image.
In one embodiment, the step of performing target region extraction on the weld filling image by using an HSV color space conversion method to obtain an inner weld region and an outer weld region includes:
performing color conversion on the welding seam filling image by using an HSV color space conversion algorithm;
extracting a target area according to the H value, the S value and the V value of the color in the inner weld area after color conversion to obtain the inner weld area;
and extracting a target area according to the H value, the S value and the V value of the color in the outer welding seam area after color conversion to obtain the outer welding seam area.
In one embodiment, the step of obtaining first contour information according to an outer contour of an inner weld, obtaining second contour information according to an outer contour of an outer weld, and drawing an inner weld curve and an outer weld curve according to the first contour information and the second contour information includes:
detecting the outer contour of the inner welding seam and the outer contour of the outer welding seam respectively by using a findContours function to obtain first contour information and second contour information;
and drawing an inner welding line curve and an outer welding line curve according to the first outline information and the second outline information by using a drawContours function.
In one embodiment, after the step of detecting the outer contour of the inner weld and the outer contour of the inner weld respectively by using findContours function to obtain the first contour information and the second contour information, the method further includes:
and storing the first contour information and the second contour information in a preset first storage unit and a preset second storage unit respectively.
In one embodiment, the step of calculating the inner weld reinforcement value according to the inner weld curve and the second horizontal line, and calculating the outer weld reinforcement value according to the outer weld curve and the fourth horizontal line includes:
according to the formula
Calculating the height value of the inner weld curve; wherein, y1 avg Is the height value of the inner weld curve, y1 max Is the highest extreme point coordinate of the inner weld curve, y1 min The coordinate of the lowest extreme point of the inner weld curve is obtained;
according to the formula
Calculating the height value of the outer welding line curve; wherein, y2 avg Height value of outer weld curve, y2 max Is the highest extreme point coordinate of the outer weld curve, y2 min The lowest extreme point coordinate of the outer welding line curve is obtained;
if y1 avg Greater than y2 avg Then, the coordinate y1 of the highest extreme point of the inner weld curve max Subtracting the second horizontal line to obtain the residual height value of the inner welding line, and obtaining the minimum extreme point coordinate y2 of the outer welding line curve min Subtracting the fourth horizontal line to obtain the residual height value of the outer welding seam;
if y1 avg Less than y2 avg Then, the coordinate y1 of the lowest extreme point of the inner weld curve min Subtracting the second horizontal line to obtain the residual height value of the inner welding line, and obtaining the maximum extreme point coordinate y2 of the outer welding line curve max And the fourth horizontal line is subtracted to obtain the residual height value of the outer welding seam.
In one embodiment, the welding seam detection items of the wall thickness welding workpiece comprise a center deviation value smaller than or equal to a first preset value, a misalignment value smaller than or equal to a second preset value, an inner welding seam surplus height value within a first preset range, and an outer welding seam surplus height value within a second preset range;
according to central deviation value, wrong limit value, interior welding seam surplus height value and the step that outer welding seam surplus height value judges whether the welding seam quality of thick wall welding work piece is qualified, include: if the four welding detection items are simultaneously met, the welding seam of the thick-wall welding workpiece is qualified; and if any one of the four welding detection items does not accord with the preset welding detection item, the welding seam of the thick-wall welding workpiece is unqualified.
In one embodiment, the first preset value is 3 mm; the second preset value is 1.6 mm; the first preset range is 0 mm to 3.5 mm; the second predetermined range is 0 mm to 3.0 mm.
A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the computer program, when executed by the processor, implements the steps of the weld quality detection method as described above.
According to the method and the computer equipment for detecting the weld quality of the wall-thickness welded workpiece, the steps in the method are executed, so that the outer contour of the inner weld and the outer contour of the outer weld can be extracted from the metallographic picture of the section of the weld, and the data processing is carried out on the outer contour of the inner weld and the outer contour of the outer weld, so that a complete and less-interference inner weld curve and an outer weld curve can be obtained, and the accuracy of the weld quality detection result can be improved; further, data operation is carried out on coordinate pixels of the inner weld curve and the outer weld curve to respectively find out intersection point coordinates and four extreme point coordinates of the two weld curves, and quality evaluation parameters such as a center deviation value, a wrong edge value, an inner weld residual height value and an outer weld residual height value are calculated in an auxiliary line drawing mode according to the intersection point coordinates and the extreme point coordinates, so that the accuracy of a detection quality result is further improved. Therefore, the weld joint quality detection method for the thick-wall welding workpiece can improve the weld joint detection efficiency and the detection accuracy of the thick-wall welding workpiece.
Drawings
Various additional advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like parts are designated by like reference numerals throughout the drawings. In the drawings:
FIG. 1 is a diagram of an application environment of a weld quality detection method for thick-walled welding workpieces according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a weld quality detection method for thick-walled welding workpieces according to an embodiment of the invention;
FIG. 3 is a drawing of weld signature lines in an embodiment of the present invention.
FIG. 4 is a schematic flowchart of step S200 in the weld quality inspection method for thick-walled welded workpieces shown in FIG. 2;
FIG. 5 is a flowchart illustrating step S230 of step S200 shown in FIG. 3;
fig. 6 is a flowchart illustrating step S300 of the weld quality inspection method for thick-walled welded workpieces shown in fig. 2.
The reference numerals in the detailed description illustrate: 10. an inner weld curve; 20. an outer weld curve; 30. a first centerline; 40. a second centerline; 50. a first horizontal line; 60. a second horizontal line; 70. a third horizontal line; 80. a fourth horizontal line; 91. an inner weld area; 92. an outer weld zone.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully hereinafter with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
When an element is referred to as being "on" another element, it can be directly on the other element or intervening elements may also be present, unless otherwise specified. It will also be understood that when an element is referred to as being "between" two elements, it can be the only one between the two elements, or one or more intervening elements may also be present.
Where the terms "comprising," "having," and "including" are used herein, another component may be added unless a specific limiting term is used, such as "only," "consisting of 8230; \8230composition," etc. Unless mentioned to the contrary, terms in the singular may include the plural and are not to be construed as being one in number.
The weld quality detection method for the thick-wall welding workpiece can be applied to the application environment shown in FIG. 1. Fig. 1 is a diagram of an application environment of a weld quality detection method for thick-walled welding workpieces, which includes a server 104 and a terminal 102 in one embodiment. The server 104 may detect the quality of the weld, and send the detection result to the terminal 102; the terminal 102 may receive the detection result sent by the server 104 and return feedback information. Wherein the server 104 may communicate with the terminal 102 via a network. The server 104 may be implemented by an independent server or a server cluster composed of a plurality of servers, and the terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and the like, which is not limited in this embodiment of the present application.
In the prior art, appearance inspection is often performed on welding of thick-wall welding workpieces manually, but the manual inspection mode efficiency and accuracy are low. Therefore, the problems of low welding seam detection efficiency and low detection accuracy exist at present.
Based on the method and the equipment, the welding seam quality of the thick-wall workpiece can be automatically detected, and the welding seam quality detection efficiency and the detection result accuracy are improved. Fig. 2 is a schematic flowchart of a weld quality detection method for a thick-wall weld workpiece according to an embodiment of the present application.
Referring to fig. 2 and 3, the method for detecting the quality of the weld seam of the thick-wall welding workpiece in the preferred embodiment of the invention is used for detecting the appearance quality of the weld seam of the thick-wall welding workpiece. Among them, the thick-wall welding workpiece is a pipe welding member or a plate welding member, etc., which requires a relatively high welding requirement and requires double-side welding. The weld quality detection method for thick-walled welded workpieces includes steps S100 to S800.
And S100, obtaining a metallographic picture of a welding seam section of the thick-wall welding workpiece.
The metallographic picture of the section of the welding seam can be an existing image or a newly acquired image.
And S200, carrying out image processing on the metallographic picture of the welding seam section to obtain the outer contour of the inner welding seam and the outer contour of the outer welding seam.
Specifically, the weld section metallographic picture is input into the image processing software, so that the weld section metallographic picture can be accurately subjected to data processing, and the inner weld outline and the outer weld outline in the weld section metallographic picture can be quickly and accurately obtained.
Step S300, acquiring first contour information according to the outer contour of the inner welding seam, acquiring second contour information according to the outer contour of the outer welding seam, and drawing an inner welding seam curve 10 and an outer welding seam curve 20 according to the first contour information and the second contour information. Specifically, the first profile information comprises each pixel coordinate, profile characteristic parameters and a profile number of the inner weld profile; the second profile information includes each pixel coordinate of the outer weld profile, a profile characteristic parameter, and a profile number.
Step S400, the inner weld curve 10 and the outer weld curve 20 are respectively stored in a first mask and a second mask which have the same size, and the image pixels in the first mask and the second mask are subjected to logical AND operation to obtain a first intersection point coordinate of the inner weld curve 10 and a second intersection point coordinate of the outer weld curve 20.
Step S500, obtaining coordinates of four extreme points of the inner weld curve 10 according to the first contour information, and drawing a first center line 30, a first horizontal line 50, and a second horizontal line 60 according to the coordinates of the four extreme points of the inner weld curve 10.
The first intersection point and the first intersection point of the first center line 30 and the first horizontal line 50 have the same coordinates, and the second horizontal line 60 is a connection line between the leftmost extreme point and the rightmost extreme point of the inner weld curve 10. Wherein the first center line 30 is a vertical line passing through the first intersection coordinates, and the first horizontal line 50 is a horizontal line passing through the first intersection coordinates. In the weld of the welded workpiece, the leftmost extreme point and the rightmost extreme point generally occur at the surface of the welded workpiece, so the second horizontal line 60 is the horizontal line of the inner weld at the inner surface of the thick-walled welded workpiece.
Step S600, obtaining coordinates of four extreme points of the outer weld curve 20 according to the second contour information, and drawing a second center line 40, a third horizontal line 70, and a fourth horizontal line 80 according to the coordinates of the four extreme points of the outer weld curve 20.
The intersection point of the second center line 40 and the third horizontal line 70 is the origin of the second intersection coordinate, and the fourth horizontal line 80 is the connection line between the leftmost extreme point and the rightmost extreme point of the outer weld curve 20. Similarly to step S50, the second center line 40 and the third horizontal line 70 are a vertical line passing through the second center coordinate and a horizontal line passing through the second center coordinate, respectively; a fourth horizontal line 80 is the horizontal line of the outer weld at the outer surface of the thick-walled welded workpiece. The first center line 30, the second center line 40, the first horizontal line 50, the second horizontal line 60, the third horizontal line 70, and the fourth horizontal line 80 are auxiliary lines drawn in the data-processed image to assist in acquisition of subsequent quality evaluation parameters.
Step S700, a center deviation value is calculated according to the first center line 30 and the second center line 40, a misalignment value is calculated according to the first horizontal line 50 and the third horizontal line 70, a reinforcement value of the inner weld is calculated according to the inner weld curve 10 and the second horizontal line 60, and a reinforcement value of the outer weld is calculated according to the outer weld curve 20 and the fourth horizontal line 80. And the center deviation value, the misalignment value, the residual height value of the inner welding seam and the residual height value of the outer welding seam are welding seam quality evaluation parameters.
And step S800, judging whether the welding seam quality of the thick-wall welding workpiece is qualified or not according to the center deviation value, the misalignment value, the inner welding seam allowance value and the outer welding seam allowance value.
Specifically, the welding seam quality detection items of the thick-wall welding workpiece comprise that a center deviation value is smaller than or equal to a first preset value, a misalignment value is smaller than or equal to a second preset value, an inner welding seam surplus height value is within a first preset range, and an outer welding seam surplus height value is within a second preset range. The step of step S800 includes: if the center deviation value is smaller than or equal to a first preset value, the misalignment value is smaller than or equal to a second preset value, the inner welding seam surplus height value is within a first preset range, and the outer welding seam surplus height value is within a second preset range, the welding seam quality is qualified; and if the center deviation value is larger than a first preset value, and/or the misalignment value is larger than a second preset value, and/or the inner welding seam surplus height value exceeds a first preset range, and/or the outer welding seam surplus height value exceeds a second preset range, indicating that the welding seam quality is unqualified.
More specifically, the first preset value is 3 mm; the second preset value is 1.6 mm; the first predetermined range is 0 mm to 3.5 mm; the second predetermined range is 0 mm to 3.0 mm. If the center deviation value is larger than 3 mm, the dislocation of the inner and outer welding seams is large, and the welding firmness can be reduced; if the misalignment value is larger than 1.6 mm, the distance between the inner welding seam and the outer welding seam in the wall thickness direction of the thick-wall workpiece is larger, and the condition of no penetration welding is likely to exist; if the residual height value of the inner weld and the residual height value of the outer weld are less than 0, the situation that full welding cannot be performed is likely to occur, if the residual height value of the inner weld is greater than 3.5 mm and the residual height value of the outer weld is greater than 3.0 mm, the residual heights of the inner weld and the inner weld are too high, stress of a weld bead is likely to be concentrated, and if the stress is too high, the weld bead is likely to tear, corrode and the like. Therefore, only when all the four detection items are qualified, the weld quality of the thick-wall welding workpiece can be qualified.
By executing the steps S100 to S800, the weld seam of the thick-wall welded workpiece can be automatically detected, and the detection efficiency of the weld seam detection method for the thick-wall welded workpiece is higher than that of the conventional manual drawn line detection method. Moreover, by performing the steps S200 and S300, the complete inner weld curve 10 and the outer weld curve 20 with less interference can be obtained, which contributes to the improvement of the accuracy of the weld quality detection result. Further, by performing steps S400 to S600, the accurate first center line 30, second center line 40, first horizontal line 50, second horizontal line 60, third horizontal line 70 and fourth horizontal line 80 can be automatically drawn as an auxiliary line for acquiring the seam quality evaluation parameter, and then by performing steps S700 and S800, the seam quality detection result of the thick-walled welding workpiece can be accurately obtained. Therefore, the welding seam quality detection method for the thick-wall welding workpiece can improve the detection efficiency and the detection result accuracy of the welding seam detection of the thick-wall welding workpiece.
Referring also to fig. 4, in some implementations, step S200 includes steps S210 to S240.
And step S210, preprocessing the metallographic picture of the welding seam section to obtain a smooth image.
Specifically, in step S210, image preprocessing is performed on the metallographic picture of the welding seam section by gaussian filtering to obtain a filtered smooth image. Therefore, preprocessing operation is carried out on the metallographic picture of the welding seam section through Gaussian filtering to obtain a smooth image with high image quality.
And S220, segmenting and filling colors in the smooth image by using a watershed algorithm to obtain a segmented filled image.
Specifically, a mouse is used for selecting a target region to fill a segmentation feature region and a background by a watershed algorithm, the smooth image is used as an input image, and gradient operation is performed on the input image to obtain a segmentation filling image, so that subsequent extraction of the outer contour of the inner welding seam and the outer contour of the outer welding seam is facilitated. Wherein different feature areas in the segmentation fill image are filled with different colors.
Step S230, performing target area extraction on the weld filling image by using an HSV color space conversion method to obtain an inner weld area 91 and an outer weld area 92. Referring to fig. 5, specifically, step S230 includes steps S231 to S233:
step S231, color conversion is performed on the weld filling image using an HSV color space conversion algorithm.
Step S232, performing target area extraction according to the H value, S value, and V value of the color in the inner weld area 91 after the color conversion to obtain the inner weld area 91.
Step S233, performing target region extraction according to the H, S, and V values of the color in the outer weld region 92 after the color conversion to obtain the outer weld region 92.
Thus, by executing steps S231 to S233, automatic extraction of the inner bead region 91 and the outer bead region 92 can be realized, and the accuracy is high.
Step S240, performing curve completion and interference elimination on the contour curve of the inner weld region 91 and the contour curve of the outer weld region 92 through morphological opening and closing operations, and obtaining the outer contour of the inner weld and the outer contour of the outer weld by using canny edge detection.
Therefore, in step S240, the contour curve of the inner weld region 91 and the contour curve of the outer weld region 92 are respectively completed through morphological opening and closing operations, and the interference of a small object is eliminated, and then the canny edge detection is performed to obtain a complete and less-interference inner weld outline and outer weld outline.
Therefore, by executing the steps S210 to S240 to perform operation and data processing on the metallographic picture of the weld section, the outer contour of the inner weld and the outer contour of the inner weld are automatically obtained clearly, completely and with less interference, which is beneficial to further improving the accuracy of the weld quality detection result of the thick-wall welded workpiece.
Referring to fig. 6, in some embodiments, step S300 includes step S310 and step S320.
Step S310, the findContours function is used for detecting the outer contour of the inner welding seam and the outer contour of the inner welding seam respectively so as to obtain first contour information and second contour information.
In step S320, draw the inner weld curve 10 and the outer weld curve 20 according to the first profile information and the second profile information respectively using a drawContours function. Specifically, in the process of executing step S320, the non-contour curve is reduced by the contour length condition, so as to further improve the accuracy of the inner weld curve 10 and the outer weld curve 20.
The drawContours function can be used for automatically drawing the inner welding line curve 10 and the outer welding line curve 20, and the detection efficiency and the detection precision of welding line quality detection are further improved.
Specifically, the method further includes, between step S310 and step S320: and storing the first contour information and the second contour information in a preset first storage unit and a preset second storage unit respectively.
In some embodiments, step S700 includes the steps of:
according to the formula
Calculating the height value of the inner weld curve 10; wherein, y1 avg Height value, y1, of inner weld curve 10 max Is the highest extreme point coordinate, y1, of the inner weld curve 10 min The lowest extreme point coordinate of the inner weld curve 10.
According to the formula
Calculating 2 the height value of the outer weld curve 20; wherein, y2 avg Is the height value, y2, of the outer weld curve 20 max Is the highest extreme point coordinate, y2, of the outer weld curve 20 min The lowest extreme point coordinate of the outer weld curve 20.
If y1 avg Greater than y2 avg The coordinate y1 of the highest extreme point of the inner weld curve 10 max Subtracting the second horizontal line 60 to obtain the inner weld reinforcement value and the minimum extreme point coordinate y2 of the outer weld curve 20 min And the fourth horizontal line 80 to obtain the outer weld residual height value.
If y1 avg Less than y2 avg Then the coordinate y1 of the lowest extreme point of the inner weld curve 10 min Subtracted from the second horizontal line 60 to obtain the inner weldValue of seam allowance, maximum extreme point coordinate y2 to outer weld curve 20 max And the fourth horizontal line 80 to obtain the outer weld reinforcement value.
Thus, by comparing y1 avg And y2 avg The height of the inner weld curve 10 and the outer weld curve 20 is judged, and different height value calculation methods are selected according to different position relations between the inner weld curve 10 and the outer weld curve 20, so that accurate inner weld height values and outer weld height values are obtained.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent should be subject to the appended claims.
Claims (10)
1. A weld quality detection method for thick-walled welded workpieces is characterized by comprising the following steps:
obtaining a metallographic picture of a weld joint section of a thick-wall welding workpiece;
carrying out image processing on the metallographic picture of the welding seam section to obtain the outer contour of the inner welding seam and the outer contour of the outer welding seam;
acquiring first contour information according to the outer contour of the inner welding seam, acquiring second contour information according to the outer contour of the outer welding seam, and drawing an inner welding seam curve and an outer welding seam curve according to the first contour information and the second contour information;
respectively storing the inner welding line curve and the outer welding line curve in a first mask and a second mask which have the same size, and performing logic and operation on image pixels in the first mask and the second mask to obtain a first intersection point coordinate of the inner welding line curve and a second intersection point coordinate of the outer welding line curve;
acquiring coordinates of four extreme points of the inner weld curve according to the first contour information, and drawing a first center line, a first horizontal line and a second horizontal line according to the coordinates of the four extreme points of the inner weld curve; the intersection point of the first central line and the first horizontal line is the same as the origin of the coordinate of the first intersection point, and the second horizontal line is a connecting line of the leftmost extreme point and the rightmost extreme point of the inner weld curve;
acquiring coordinates of four extreme points of the outer weld curve according to the second contour information, and drawing a second central line, a third horizontal line and a fourth horizontal line according to the coordinates of the four extreme points of the outer weld curve; the intersection point of the second center line and the third horizontal line is the origin of the second intersection point coordinate, and the fourth horizontal line is the connecting line of the leftmost extreme point and the rightmost extreme point of the outer weld curve;
calculating a center deviation value according to the first center line and the second center line, calculating a misalignment value according to the first horizontal line and the third horizontal line, calculating a residual height value of an inner welding line according to an inner welding line curve and the second horizontal line, and calculating a residual height value of an outer welding line according to an outer welding line curve and the fourth horizontal line;
and judging whether the welding seam quality of the thick-wall welding workpiece is qualified or not according to the center deviation value, the misalignment value, the inner welding seam allowance value and the outer welding seam allowance value.
2. The weld quality detection method according to claim 1, wherein the step of performing image processing on the metallographic picture of the weld section to obtain the outer contour of the inner weld and the outer contour of the outer weld comprises the steps of:
preprocessing a metallographic picture of a welding seam section to obtain a smooth image;
using a watershed algorithm to perform segmentation and color filling on the smooth image to obtain a segmentation filling image;
extracting a target area of the weld filling image by using an HSV color space conversion method to obtain an inner weld area and an outer weld area;
and performing curve completion and interference elimination on the contour curve of the inner welding seam region and the contour curve of the outer welding seam region through morphological opening and closing operation, and acquiring the outer contour of the inner welding seam and the outer contour of the outer welding seam in a canny edge detection mode.
3. The weld joint quality detection method according to claim 2, wherein the step of preprocessing the metallographic picture of the section of the weld joint to obtain a smooth image comprises the steps of: and (3) carrying out image preprocessing on the metallographic picture of the section of the welding seam by using Gaussian filtering to obtain a filtered smooth image.
4. The weld quality detection method according to claim 2, wherein the step of performing target region extraction on the weld filling image by using an HSV color space conversion method to obtain an inner weld region and an outer weld region comprises:
performing color conversion on the weld filling image by using an HSV color space conversion algorithm;
extracting a target area according to the H value, the S value and the V value of the color in the inner weld area after color conversion to obtain the inner weld area;
and extracting a target area according to the H value, the S value and the V value of the color in the outer welding seam area after color conversion to obtain the outer welding seam area.
5. The weld quality detection method according to claim 1, wherein the step of obtaining first profile information according to an outer profile of the inner weld, obtaining second profile information according to an outer profile of the outer weld, and drawing an inner weld curve and an outer weld curve according to the first profile information and the second profile information includes:
detecting the outer contour of the inner welding seam and the outer contour of the outer welding seam respectively by using a findContours function to obtain first contour information and second contour information;
and drawing an inner welding line curve and an outer welding line curve according to the first outline information and the second outline information by using a drawContours function.
6. The weld quality detection method according to claim 5, wherein after the step of detecting the outer contour of the inner weld and the outer contour of the inner weld respectively using findContours functions to obtain the first contour information and the second contour information, the method further comprises:
and respectively storing the first contour information and the second contour information in a preset first storage unit and a preset second storage unit.
7. The weld quality detection method according to claim 1, wherein the step of calculating the residual height value of the inner weld according to the inner weld curve and the second horizontal line, and the step of calculating the residual height value of the outer weld according to the outer weld curve and the fourth horizontal line comprises:
according to the formula
Calculating the height value of the inner weld curve; wherein, y1 avg Height value of inner weld curve, y1 max Is the highest extreme point coordinate of the inner weld curve, y1 min The coordinate of the lowest extreme point of the inner weld curve is obtained;
according to the formula
Calculating the height value of the outer welding line curve; wherein, y2 avg Height value of the outer weld curve, y2 max Is the highest extreme point coordinate of the outer weld curve, y2 min The lowest extreme point coordinate of the outer welding line curve is obtained;
if y1 avg Greater than y2 avg Then the coordinate y1 of the highest extreme point of the inner weld curve max Subtracting the second horizontal line to obtain the residual height value of the inner welding line, and obtaining the minimum extreme point coordinate y2 of the outer welding line curve min Subtracting the fourth horizontal line to obtain the residual height value of the outer welding seam;
if y1 avg Less than y2 avg Inner weld curveLowest extreme point coordinate y1 of line min Subtracting the second horizontal line to obtain the residual height value of the inner welding line, and obtaining the maximum extreme point coordinate y2 of the outer welding line curve max And the fourth horizontal line is subtracted to obtain the residual height value of the outer welding seam.
8. The weld quality detection method according to claim 1, wherein the weld detection items of the wall thickness welding workpiece include that a center deviation value is less than or equal to a first preset value, a misalignment value is less than or equal to a second preset value, an inner weld reinforcement value is within a first preset range, and an outer weld reinforcement value is within a second preset range;
according to central deviation value, wrong limit value, interior welding seam surplus height value and the step that outer welding seam surplus height value judges whether the welding seam quality of thick wall welding work piece is qualified, include: if the four welding detection items are simultaneously met, the welding seam of the thick-wall welding workpiece is qualified; and if any item in the four welding detection items does not accord with the welding detection item, the welding seam of the thick-wall welding workpiece is unqualified.
9. The weld quality detection method according to claim 8, wherein the first preset value is 3 mm; the second preset value is 1.6 mm; the first preset range is 0 mm to 3.5 mm; the second predetermined range is 0 mm to 3.0 mm.
10. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the computer program when executed by the processor implements the steps of the weld quality detection method of any one of claims 1 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210929891.3A CN115338556A (en) | 2022-08-03 | 2022-08-03 | Weld joint quality detection method for thick-wall welding workpiece and computer equipment |
| CN202310948113.3A CN117260055A (en) | 2022-08-03 | 2023-07-31 | Weld quality detection method and computer equipment for thick-wall welded workpiece |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210929891.3A CN115338556A (en) | 2022-08-03 | 2022-08-03 | Weld joint quality detection method for thick-wall welding workpiece and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115338556A true CN115338556A (en) | 2022-11-15 |
Family
ID=83950043
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210929891.3A Pending CN115338556A (en) | 2022-08-03 | 2022-08-03 | Weld joint quality detection method for thick-wall welding workpiece and computer equipment |
| CN202310948113.3A Pending CN117260055A (en) | 2022-08-03 | 2023-07-31 | Weld quality detection method and computer equipment for thick-wall welded workpiece |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310948113.3A Pending CN117260055A (en) | 2022-08-03 | 2023-07-31 | Weld quality detection method and computer equipment for thick-wall welded workpiece |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN115338556A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050147289A1 (en) * | 2002-04-30 | 2005-07-07 | Jfe Steel Coroporation | Method and instrument for measuring bead cutting shape of electric welded tube |
| JP2005319507A (en) * | 2004-05-11 | 2005-11-17 | Oshima Shipbuilding Co Ltd | Multiple electrodes one side submerged arc welding method |
| CN105931227A (en) * | 2016-04-14 | 2016-09-07 | 北京工业大学 | Weld surface defect feature extraction method based on image gray scale B sweeping curve |
| CN111103291A (en) * | 2019-12-20 | 2020-05-05 | 广西柳州联耕科技有限公司 | Image recognition and quality intelligent evaluation system based on product weld joint characteristics |
| CN111438460A (en) * | 2020-04-18 | 2020-07-24 | 南昌大学 | Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method |
| CN112067623A (en) * | 2020-09-16 | 2020-12-11 | 中国京冶工程技术有限公司 | Method and system for detecting appearance quality of weld joint of steel structural member |
| CN112465851A (en) * | 2020-09-27 | 2021-03-09 | 华南理工大学 | Parameter detection method based on surface contour curve of surface weld of pressure vessel |
| CN112453751A (en) * | 2020-11-27 | 2021-03-09 | 上海交通大学 | Pipeline all-position welding back surface online monitoring method based on visual sensing |
| CN113441815A (en) * | 2021-08-31 | 2021-09-28 | 南京南暄励和信息技术研发有限公司 | Electric arc additive manufacturing layer width and residual height cooperative control method based on deep learning |
| CN113610814A (en) * | 2021-08-10 | 2021-11-05 | 广东利元亨智能装备股份有限公司 | Weld quality detection method and device, electronic equipment and storage medium |
| CN114260630A (en) * | 2022-01-20 | 2022-04-01 | 中广核工程有限公司 | Welding system and welding control method |
-
2022
- 2022-08-03 CN CN202210929891.3A patent/CN115338556A/en active Pending
-
2023
- 2023-07-31 CN CN202310948113.3A patent/CN117260055A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050147289A1 (en) * | 2002-04-30 | 2005-07-07 | Jfe Steel Coroporation | Method and instrument for measuring bead cutting shape of electric welded tube |
| JP2005319507A (en) * | 2004-05-11 | 2005-11-17 | Oshima Shipbuilding Co Ltd | Multiple electrodes one side submerged arc welding method |
| CN105931227A (en) * | 2016-04-14 | 2016-09-07 | 北京工业大学 | Weld surface defect feature extraction method based on image gray scale B sweeping curve |
| CN111103291A (en) * | 2019-12-20 | 2020-05-05 | 广西柳州联耕科技有限公司 | Image recognition and quality intelligent evaluation system based on product weld joint characteristics |
| CN111438460A (en) * | 2020-04-18 | 2020-07-24 | 南昌大学 | Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method |
| CN112067623A (en) * | 2020-09-16 | 2020-12-11 | 中国京冶工程技术有限公司 | Method and system for detecting appearance quality of weld joint of steel structural member |
| CN112465851A (en) * | 2020-09-27 | 2021-03-09 | 华南理工大学 | Parameter detection method based on surface contour curve of surface weld of pressure vessel |
| CN112453751A (en) * | 2020-11-27 | 2021-03-09 | 上海交通大学 | Pipeline all-position welding back surface online monitoring method based on visual sensing |
| CN113610814A (en) * | 2021-08-10 | 2021-11-05 | 广东利元亨智能装备股份有限公司 | Weld quality detection method and device, electronic equipment and storage medium |
| CN113441815A (en) * | 2021-08-31 | 2021-09-28 | 南京南暄励和信息技术研发有限公司 | Electric arc additive manufacturing layer width and residual height cooperative control method based on deep learning |
| CN114260630A (en) * | 2022-01-20 | 2022-04-01 | 中广核工程有限公司 | Welding system and welding control method |
Non-Patent Citations (1)
| Title |
|---|
| 吴禹胜: "埋弧焊钢管焊缝过渡角复型测量方法研究", 《焊管》, pages 65 - 68 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117260055A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111462054B (en) | Dispensing quality detection method | |
| Shah et al. | Butt welding joints recognition and location identification by using local thresholding | |
| CN111462110A (en) | Welding seam quality detection method, device and system and electronic equipment | |
| CN108629343B (en) | License plate positioning method and system based on edge detection and improved Harris corner detection | |
| CN109977954B (en) | Identification and positioning method and system for electric automobile charging interface | |
| CN111127402A (en) | Visual detection method for welding quality of robot | |
| CN113658132A (en) | Computer vision-based structural part weld joint detection method | |
| CN112419297A (en) | Bolt looseness detection method, device, equipment and storage medium | |
| KR102073468B1 (en) | System and method for scoring color candidate poses against a color image in a vision system | |
| CN113077437B (en) | Workpiece quality detection method and system | |
| CN116740072B (en) | Road surface defect detection method and system based on machine vision | |
| CN115690108A (en) | Aluminum alloy rod production quality evaluation method based on image processing | |
| CN111832659A (en) | Laser marking system and method based on feature point extraction algorithm detection | |
| CN115018846A (en) | AI intelligent camera-based multi-target crack defect detection method and device | |
| CN115457063A (en) | Method, device and equipment for extracting edge of circular hole of PCB (printed Circuit Board) and storage medium | |
| CN114283132A (en) | Defect detection method, device, equipment and storage medium | |
| JP2011243139A (en) | Image processing device, image processing method and compute program | |
| CN110060239B (en) | Defect detection method for bottle opening of bottle | |
| CN117058411B (en) | Method, device, medium and equipment for identifying edge appearance flaws of battery | |
| CN115338556A (en) | Weld joint quality detection method for thick-wall welding workpiece and computer equipment | |
| CN112069924A (en) | Lane line detection method, lane line detection device and computer-readable storage medium | |
| WO2000028309A1 (en) | Method for inspecting inferiority in shape | |
| CN111754467A (en) | Hough transform-based parking space detection method and device, computer equipment and storage medium | |
| CN114219802B (en) | Skin connecting hole position detection method based on image processing | |
| CN111563883B (en) | Screen vision positioning method, positioning equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20221115 |