CN112067623B - Method and system for detecting appearance quality of welding seam of steel structural member - Google Patents
Method and system for detecting appearance quality of welding seam of steel structural member Download PDFInfo
- Publication number
- CN112067623B CN112067623B CN202010976707.1A CN202010976707A CN112067623B CN 112067623 B CN112067623 B CN 112067623B CN 202010976707 A CN202010976707 A CN 202010976707A CN 112067623 B CN112067623 B CN 112067623B
- Authority
- CN
- China
- Prior art keywords
- welding
- weld joint
- weld
- judging
- vision sensor
- 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.)
- Active
Links
- 238000003466 welding Methods 0.000 title claims abstract description 144
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 47
- 239000010959 steel Substances 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000007547 defect Effects 0.000 claims abstract description 73
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 230000000007 visual effect Effects 0.000 claims abstract description 8
- 239000000463 material Substances 0.000 claims description 9
- 238000005507 spraying Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 239000003550 marker Substances 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 claims description 2
- 238000011160 research Methods 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/888—Marking defects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Laser Beam Processing (AREA)
Abstract
The invention discloses a method and a system for detecting appearance quality of a welding seam of a steel structural member. The system comprises an arc welding robot, a welding gun is arranged on the arc welding robot, the welding gun is connected with a wire feeder and a welding power supply, a laser vision sensor is arranged on a part, deviating from arc light emission, of the welding gun, and the arc welding robot, the wire feeder, the welding power supply and the laser vision sensor are connected with a control system. The laser vision sensor includes a structured light source that emits blue laser light and a CCD camera that receives only the blue laser light. Under the drive of an arc welding robot, the welding gun and the laser vision sensor synchronously move together, so that the laser vision sensor immediately acquires images of welding seams after the welding gun finishes welding. The invention can realize automatic detection of the appearance quality of the welding seam generated by welding the steel structural members, and solves various defects caused by detecting the appearance quality of the welding seam in a visual observation mode of detection personnel.
Description
Technical Field
The invention relates to a method and a system for detecting appearance quality of a welding line of a steel structure member, and belongs to the field of detection of appearance quality of welding lines of steel structure members.
Background
The steel structure industry is an emerging industry which is green, environment-friendly and sustainable at present. In recent years, the steel consumption of the steel structure in China exceeds 7000 ten thousand tons, and the steel structure is the first steel structure in the world. With the rapid and high-quality development of the steel structure industry, china puts higher demands on the quality and detection of welding seams of steel structure members.
At present, the quality detection of the welding seam of the steel structure member in China mainly relates to two aspects of internal quality detection and appearance quality detection, wherein the appearance quality detection of the welding seam is still finished in a visual observation mode of detection personnel, and the manual mode has high requirements on skills required to be mastered by the detection personnel and high labor intensity, and is difficult to adapt to the future automatic and intelligent detection requirements of the steel structure industry. In addition, steel structural member welding often involves multi-layer multi-pass welding, and if a bottoming weld or a transition weld produces an appearance defect but is not found and handled in time, the subsequent process is highly likely to form a weld internal defect, resulting in a great reduction in the load carrying capacity of the welded site. Moreover, the welding operation time of the steel structural member is long, the labor intensity of the detection personnel is high due to the visual observation mode, and the detection timeliness and accuracy are not guaranteed.
In recent years, researchers at home and abroad gradually apply the visual sensing technology to the aspect of appearance acquisition of the welding seam and develop more researches, but the researches mainly relate to how to determine a subsequent welding starting point and a welding path through the appearance outline of a previous welding seam, and do not relate to the research of identifying and judging the appearance defects of the welding seam.
Disclosure of Invention
The invention aims to provide a method for detecting the appearance quality of a welding line of a steel structure member and a system for detecting the appearance quality of the welding line of the steel structure member for implementing the method, which can realize automatic detection of the appearance quality of the welding line generated by welding the steel structure member and solve various defects caused by detecting the appearance quality of the welding line in a visual observation mode of a detector.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
The method for detecting the appearance quality of the welding line of the steel structural member is characterized by comprising the following steps:
1) Setting an acquisition interval at intervals along the length direction of the weld joint, and carrying out image acquisition on the weld joint to be detected once;
2) The following processing is performed on each acquired image:
2-1) into a two-dimensional image with the width direction of the weld joint as the horizontal axis and the height direction of the weld joint as the vertical axis, wherein: defining the surface of the base material where the welding line is positioned as a reference surface;
2-2) obtaining a weld appearance contour from the two-dimensional image;
2-3) performing smooth filtering treatment on the appearance outline of the welding seam;
2-4) extracting a weld joint body from the weld joint appearance outline after the smooth filtering treatment;
2-5) judging whether the undercut defect exists or not:
2-5-1) searching the lowest point outside each side of the weld joint body, and calculating the size of the edge valley depth, wherein the distance between the lowest point outside each side of the weld joint body and the reference plane is defined as the edge valley depth;
2-5-2) judging the edge valley depth: if the depth of the edge valley is larger than the set undercut threshold, judging that undercut defects occur; otherwise, judging that no undercut defect exists;
2-6) judging whether the air holes or crack defects exist or not:
2-6-1) fitting to obtain an ideal weld joint body without defects;
2-6-2) searching for a point with a height smaller than that of the ideal weld joint body and the largest distance from the ideal weld joint body on the weld joint body extracted in 2-4) as a peak valley: if no peak valley is found, judging that no air hole and no crack defect exist, and entering 2-7); otherwise, enter 2-6-3);
2-6-3) searching maximum height values of each side from peak valley to two sides, taking points corresponding to the maximum height values found at each side of the peak valley as peak tops, and calculating the distance between two peak tops and the distance between two peak top connecting lines and the peak valley, wherein the distance between two peak tops is defined as peak top distance, and the distance between two peak top connecting lines and the peak valley is defined as body valley depth;
2-6-4) judging peak top spacing and body valley depth: if the peak top distance is larger than a set distance threshold value or the body valley depth is larger than a set valley depth threshold value, judging that air holes or crack defects occur, and entering 3); otherwise, judging that no air holes and crack defects exist, and entering 2-7);
2-7) judging whether the defect of residual height exists or not:
2-7-1) calculating the maximum height value of the weld joint body, and defining the point corresponding to the maximum height value of the weld joint body as the highest point of the body;
2-7-2) judging the highest point of the body: if the height value of the highest point of the body is larger than the set height threshold value, judging that the residual height defect occurs; otherwise, judging that the defect of no residual height exists;
3) And (5) finishing detection of the appearance quality of the weld joint to be detected, and ending.
A steel structure member weld appearance quality detection system for implementing the steel structure member weld appearance quality detection method is characterized in that: the steel structural member welding seam appearance quality detecting system comprises an arc welding robot, wherein a welding gun is arranged on the arc welding robot, the welding gun is connected with a wire feeder and a welding power supply, a laser vision sensor is arranged at a position, deviating from arc light emission, on the welding gun, and the arc welding robot, the wire feeder, the welding power supply and the laser vision sensor are connected with a control system, wherein: the laser vision sensor comprises a structural light source for emitting blue laser and a CCD camera for receiving only the blue laser; under the drive of an arc welding robot, the welding gun and the laser vision sensor synchronously move together, so that the laser vision sensor immediately acquires images of welding seams after the welding gun finishes welding.
The invention has the advantages that:
the invention realizes the automatic detection of the appearance quality of the welding seam generated by welding the steel structural members, solves various defects caused by the visual observation mode of detecting the appearance quality of the welding seam by detection personnel, is not influenced by the skill level of the detection personnel, has accurate and reliable judging result of the appearance quality of the welding seam, greatly reduces the labor intensity of the detection personnel and has high detection efficiency.
Drawings
FIG. 1 is a schematic illustration of the length, width and height direction definitions of a weld.
FIG. 2 is a schematic representation of a two-dimensional image with undercut defects.
Fig. 3 is a schematic of a two-dimensional image with a pinhole or crack defect.
FIG. 4 is a schematic of a two-dimensional image with residual high defects.
FIG. 5 is a schematic diagram of the composition of the weld appearance quality detection system of the steel structural member of the present invention.
Detailed Description
As shown in fig. 1 to 5, the method for detecting the appearance quality of the welding seam of the steel structural member comprises the following steps:
1) Along the length direction of the weld joint, the image acquisition is carried out on the weld joint 20 to be detected once at each interval set acquisition interval, for example, the image is acquired once at each interval of 20 mu m (set acquisition interval);
2) The following processing is performed on each acquired image:
2-1) into a two-dimensional image with the width direction of the weld joint as the horizontal axis and the height direction of the weld joint as the vertical axis, wherein: the length direction of the weld is defined as the X direction, the width direction of the weld is defined as the Y direction, and the height direction of the weld is defined as the Z direction, as shown in fig. 1, the base material surface 10 where the weld is located is defined as a reference surface, that is, the base material surface 10 where the weld 20 is located is taken as the zero point of the vertical axis, and the zero point of the horizontal axis can be set arbitrarily without limitation, for example, a certain position of the weld 20 is taken as the zero point of the horizontal axis;
2-2) obtaining a weld appearance contour from the two-dimensional image;
2-3) adopting a well-known filtering algorithm to carry out smooth filtering treatment on the appearance outline of the welding seam;
2-4) extracting a weld joint body 22 from the weld joint appearance outline after the smoothing filter treatment;
2-5) judging whether there is an undercut defect or not, as understood with reference to fig. 2:
2-5-1) searching the lowest point outside each side of the weld joint body 22, and calculating the size of the edge valley depth, wherein the distance between the lowest point outside each side of the weld joint body 22 and the reference surface is defined as the edge valley depth;
2-5-2) judging the edge valley depth according to the current national standard GB50661 'steel structure welding Specification' in the steel structure industry: if the edge valley depth is larger than the set undercut threshold, judging that the undercut defect occurs at the weld joint 20 to be tested; otherwise, if the edge Gu Shen is less than or equal to the set undercut threshold, determining or regarding that the weld 20 to be measured has no undercut defect;
2-6) with reference to FIG. 3, a determination is made as to whether there are pinholes or crack defects:
2-6-1) fitting to obtain an ideal weld body 22' without any defects based on the weld height data to be measured;
2-6-2) finding a point on the weld body 22 extracted in 2-4) having a height smaller than the ideal weld body 22 'and having the largest distance from the ideal weld body 22' as a peak-valley: if no peak valley is found, namely, the weld joint body 22 extracted in 2-4) is very consistent with the ideal weld joint body 22', judging that the weld joint 20 to be tested has no air holes and crack defects, and entering 2-7); otherwise, if the peak valley is found, entering 2-6-3);
2-6-3) searching the maximum height value of each side from the peak valley of the weld joint body 22 to two sides, taking the point corresponding to the maximum height value found at each side of the peak valley as a peak top (such as peak top 1 and peak top 2 shown in fig. 3), and calculating the distance between two peak tops and the distance between two peak top connecting lines and the peak valley, wherein the distance between two peak tops is defined as the peak top distance, and the distance between two peak top connecting lines and the peak valley is defined as the body valley depth;
2-6-4) judging peak top spacing and body valley depth according to the current national standard GB50661 steel structure welding Specification in the steel structure industry: if the peak top distance is larger than the set distance threshold value or the body valley depth is larger than the set valley depth threshold value, judging that the weld joint 20 to be tested has air holes or crack defects at the position, and entering 3); otherwise, if the peak top distance is smaller than or equal to the set distance threshold value and the body valley depth is smaller than or equal to the set valley depth threshold value, judging or considering that the weld joint 20 to be tested has no air holes and crack defects, and entering 2-7);
2-7) with reference to FIG. 4, a determination is made as to whether there are residual high defects:
2-7-1) calculating the maximum height value of the weld joint body 22 based on the height data of the weld joint 20 to be measured, and defining the point corresponding to the maximum height value of the weld joint body 22 as the body highest point;
2-7-2) judging the highest point of the body according to the current national standard GB50661 'steel structure welding Specification' of the steel structure industry: if the height value of the highest point of the body is larger than the set height threshold value, judging that the residual height defect exists in the weld joint 20 to be tested; otherwise, if the height value of the highest point of the body is smaller than or equal to the set height threshold value, judging or considering that the weld joint 20 to be tested has no residual height defect;
3) And (5) finishing the detection of the appearance quality of the weld joint 20 to be detected, and ending.
In the present invention, the welded seam welded on the surface 10 of the base material is generally in a straight strip shape or a straight line shape, and of course, the welded seam may have a certain bending degree, but the welded seam has a longitudinal direction of the welded seam no matter whether the welded seam is bent or not, that is, the method of the present invention is not limited by the bending shape of the welded seam.
In step 1), by means of optical triangulation (a well-known method), the blue laser is emitted to the surface of the weld 20 to be measured by the laser vision sensor 40 which emits the blue laser and only receives the blue laser, that is, the structural light source 41 in the laser vision sensor 40 emits the blue laser to the surface of the weld 20 to be measured, so that the blue laser is received by the CCD camera 42 in the laser vision sensor 40 after being reflected by the surface of the weld 20 to be measured, thereby completing one image acquisition. In other words, the laser vision sensor 40 can filter out only light components between the red light wavelength and the infrared light wavelength by light having a wavelength of 405 nm. In practical implementation, the laser vision sensor 40 moves along the length direction of the weld joint, and when the set collection interval reaches the collection point every time the laser vision sensor 40 moves, the structural light source 41 for emitting blue laser and the CCD camera 42 for receiving only blue laser in the laser vision sensor 40 are located above the weld joint 20 to be tested and are arranged in an axisymmetric manner relative to the collection point on the weld joint 20 to be tested, that is, the structural light source 41 for emitting blue laser in the laser vision sensor 40, the CCD camera 42 for receiving only blue laser in the laser vision sensor 40 and the collection point are in an inverted isosceles triangle, please refer to fig. 5.
In practical implementation, based on the setting that the laser vision sensor 40 itself can capture light points (collection points) with different angles at different distances by the CCD camera 42, the distance between the laser vision sensor 40 and the collection point on the surface of the weld 20 to be measured below the laser vision sensor can be calculated through the known distance between the CCD camera 42 and the structured light source 41, so that the acquisition of the height data of the weld to be measured is completed immediately in the process of image acquisition.
In step 2-2), a portion of the reference surface (base material surface 10) where the weld is not welded is identified from the two-dimensional image based on the obtained height data of the weld to be measured, thereby removing the portion of the weld which is not welded to obtain a weld appearance profile 21.
For example, as shown in fig. 2, if the weld 20 to be measured has only undercut defects, the obtained weld appearance contour 21 is composed of the contour formed by the weld body 22 and the undercut defects 31 on both sides thereof, and if the weld 20 to be measured has only air hole defects, the obtained weld appearance contour 21 is the weld body 22 with air hole defects.
In practical design, the steps 2-4) specifically include: selecting a weld appearance contour portion higher than a reference surface (base material surface 10) as a weld body 22 based on the to-be-measured weld height data in the two-dimensional image, i.e., selecting a portion of the weld appearance contour 21 having a height greater than 0 as the weld body 22 in the two-dimensional image, wherein: the curvature of the two edge points where the two sides of the weld body 22 intersect the reference surface is greater than a predetermined threshold, in other words, the curvature of the two edge points where the two sides of the weld body 22 intersect the reference surface is much greater than the curvature of the other portions of the weld body 22 where there is no defect.
In actual implementation, for each two-dimensional image continuously collected along the length direction of the weld joint and judged to have the air holes or the crack defects by the steps 2-6-4), the part of all the two-dimensional images judged to have the air holes or the crack defects is subjected to communication area treatment, and then the following judgment is carried out: if the length of the communicated area is greater than the set air hole threshold value, judging that the weld joint 20 to be tested has crack defects; otherwise, if the length of the communicated area is smaller than or equal to the set air hole threshold value, the defect of air holes (pits) at the position of the weld joint 20 to be detected is judged.
After step 3), it may further comprise: the defects are identified by a code-spraying marker in the vicinity of the defects of the weld 20 to be measured.
The invention also provides a steel structural member welding seam appearance quality detection system for implementing the steel structural member welding seam appearance quality detection method, specifically, as shown in fig. 5, the steel structural member welding seam appearance quality detection system comprises an arc welding robot 50, wherein a welding gun 80 is arranged on the arc welding robot 50 through a clamp, the welding gun 80 is connected with a wire feeder 90 and a welding power supply 100, namely, a wire feeding outlet of the wire feeder 90 is connected with a wire feeding inlet of the welding gun 80, an electric power outlet of the welding power supply 100 is connected with an electric power inlet of the welding gun 80, a laser vision sensor 40 is arranged on a part, which is far away from arc light emission, of the welding gun 80, and signal ports of the arc welding robot 50, the wire feeder 90, the welding power supply 100 and the laser vision sensor 40 are respectively connected with corresponding control ports of a control system 60, wherein: the laser vision sensor 40 includes a structured light source 41 emitting blue laser light and a CCD camera 42 receiving only the blue laser light; the welding gun 80 and the laser vision sensor 40 move synchronously under the drive of the arc welding robot 50, so that the laser vision sensor 40 can acquire images of the welded weld joint 20 immediately after the welding gun 80 completes welding.
In practical designs, a code-spraying marker (not shown) may be mounted beside the laser vision sensor 40, and the code-spraying marker and the laser vision sensor 40 move synchronously together, so that when the defect of the weld 20 is determined, the mark is printed immediately, and the defect is identified.
As shown in fig. 5, the control system 60 is also connected to an industrial personal computer 70.
In the present invention, the arc welding robot 50, the welding gun 80, the wire feeder 90, the welding power source 100, the laser vision sensor 40, and the code-spraying marker are existing devices in the art.
In the present invention, the control system 60 is a well known system in the art, and mainly functions to: controlling the image acquisition of the laser vision sensor 40, processing and analyzing the image fed back by the laser vision sensor 40, controlling the movement of the arc welding robot 50, controlling the wire feeding and power supply of the welding gun 80, receiving the instruction sent by the industrial personal computer 70, uploading data to the industrial personal computer 70, and the like.
In use, the arc welding robot 50 drives the welding gun 80 and the laser vision sensor 40 to move along a preset welding path (i.e., the length direction of the weld joint) under the control of the control system 60, and the welding gun 80 performs welding operation on the surface 10 of the base material during the movement. When the welding gun 80 completes the welding operation at a certain position on the surface 10 of the base material and the control system 60 determines that the position is the acquisition point, the laser vision sensor 40 immediately performs image acquisition on the welding seam 20 at the position under the control of the control system 60, and then feeds back the acquired image to the control system 60, so that the control system 60 detects the appearance quality of the welding seam. If the defect is detected at the position, marking is performed nearby the defect by a code spraying and marking device, otherwise, if the defect is not detected at the position, the welding gun 80 continues to move, and the processes of welding, image acquisition and appearance quality detection are repeated until the welding operation is not performed.
The invention has the following advantages:
1. the size of the appearance defects of the welding seam of the steel structural member is small, and is usually in the order of a few millimeters, so that the effect of arc light and heat emitted by a welding gun (or welding arc) can influence the acquisition accuracy of the appearance of the welding seam in the welding process. In view of the fact that the steel structural member is in a red-hot state in the welding process, most of the radiated light is light components ranging from red wavelength to infrared wavelength, the invention adopts the laser vision sensor which can emit blue laser and only receive the blue laser, and only filters out the light components ranging from red wavelength to infrared wavelength through the light with the wavelength of 405nm, so that interference to visual acquisition and weld appearance defect detection caused by the light radiated by a welding gun (the light components ranging from red wavelength to infrared wavelength) in the welding process is avoided.
2. The invention carries out smooth filtering treatment on the image after the image is acquired on the welding seam, thereby effectively eliminating the surface ripple of the welding seam (commonly called the welding seam scale pattern, which belongs to the normal contour and shape of the qualified welding seam) and avoiding the false judgment of the appearance quality of the welding seam caused by the surface ripple of the welding seam.
3. The invention can realize the accurate determination of main defects of the weld joint, namely undercut, air holes, cracks and residual height defects.
4. The invention combines the appearance quality requirement of the butt welding seam and the specification of the out-of-standard defect in the current national standard GB50661 'steel structure welding specification' in the steel structure industry, effectively avoids the missed judgment and the misjudgment of the appearance defect of the butt welding seam, and greatly improves the detection accuracy.
The foregoing is a description of the preferred embodiments of the present invention and the technical principles applied thereto, and it will be apparent to those skilled in the art that any modifications, equivalent changes, simple substitutions and the like based on the technical scheme of the present invention can be made without departing from the spirit and scope of the present invention.
Claims (5)
1. The method for detecting the appearance quality of the welding line of the steel structural member is characterized by comprising the following steps:
1) Image acquisition is carried out on the weld joint to be detected at each interval set acquisition interval along the length direction of the weld joint, wherein: by means of an optical triangulation method, blue laser is emitted to the surface of a weld joint to be detected through a laser vision sensor which emits blue laser and only receives the blue laser, so that the blue laser is received by a CCD camera of the laser vision sensor after being reflected by the surface of the weld joint to be detected, and one-time image acquisition is completed; immediately acquiring an image of the welded weld after the welding gun finishes welding, wherein the laser vision sensor can avoid interference of light radiated by the welding gun in the welding process to visual acquisition and weld appearance defect detection;
2) The following processing is performed on each acquired image:
2-1) into a two-dimensional image with the width direction of the weld joint as the horizontal axis and the height direction of the weld joint as the vertical axis, wherein: defining the surface of the base material where the welding line is positioned as a reference surface;
2-2) obtaining a weld appearance profile from the two-dimensional image, wherein: based on the obtained height data of the weld to be detected, identifying the part of the welding seam which is not welded on the reference surface from the two-dimensional image, thereby removing the part of the welding seam which is not welded and obtaining the appearance outline of the welding seam;
2-3) performing smooth filtering treatment on the appearance outline of the welding seam;
2-4) extracting a weld joint body from the weld joint appearance outline after the smoothing filter treatment, wherein: selecting a welding seam appearance outline part higher than the reference surface as a welding seam body based on the welding seam height data to be detected in the two-dimensional image, wherein the curvature of two edge points at which two sides of the welding seam body intersect with the reference surface is larger than a preset threshold value;
2-5) judging whether the undercut defect exists or not:
2-5-1) searching the lowest point outside each side of the weld joint body, and calculating the size of the edge valley depth, wherein the distance between the lowest point outside each side of the weld joint body and the reference plane is defined as the edge valley depth;
2-5-2) judging the edge valley depth: if the depth of the edge valley is larger than the set undercut threshold, judging that undercut defects occur; otherwise, judging that no undercut defect exists;
2-6) judging whether the air holes or crack defects exist or not:
2-6-1) fitting to obtain an ideal weld joint body without defects;
2-6-2) searching for a point with a height smaller than that of the ideal weld joint body and the largest distance from the ideal weld joint body on the weld joint body extracted in 2-4) as a peak valley: if no peak valley is found, judging that no air hole and no crack defect exist, and entering 2-7); otherwise, enter 2-6-3);
2-6-3) searching maximum height values of each side from peak valley to two sides, taking points corresponding to the maximum height values found at each side of the peak valley as peak tops, and calculating the distance between two peak tops and the distance between two peak top connecting lines and the peak valley, wherein the distance between two peak tops is defined as peak top distance, and the distance between two peak top connecting lines and the peak valley is defined as body valley depth;
2-6-4) judging peak top spacing and body valley depth: if the peak top distance is larger than a set distance threshold value or the body valley depth is larger than a set valley depth threshold value, judging that air holes or crack defects occur, and entering 3); otherwise, judging that no air holes and crack defects exist, and entering 2-7);
2-7) judging whether the defect of residual height exists or not:
2-7-1) calculating the maximum height value of the weld joint body, and defining the point corresponding to the maximum height value of the weld joint body as the highest point of the body;
2-7-2) judging the highest point of the body: if the height value of the highest point of the body is larger than the set height threshold value, judging that the residual height defect occurs; otherwise, judging that the defect of no residual height exists;
3) Finishing detection of appearance quality of the weld joint to be detected, wherein:
continuously acquiring two-dimensional images which are continuously acquired along the length direction of the welding seam and are judged to be in existence of the air holes or the crack defects in the step 2-6-4), carrying out communication area treatment on the parts which are judged to be in existence of the air holes or the crack defects in all the two-dimensional images, and then judging: if the length of the communicated area is greater than the set air hole threshold value, judging that crack defects occur; otherwise, judging that the air hole defect occurs;
if the defect is detected, marking is carried out nearby the defect by a code spraying marking device.
2. The steel structural member weld appearance quality detection method according to claim 1, characterized in that:
after said step 3), further comprising: and marking the defects nearby the defects of the weld to be detected by using a code spraying marker.
3. A steel structural member weld joint appearance quality detection system that implements the steel structural member weld joint appearance quality detection method of claim 1 or 2, characterized in that: the steel structural member welding seam appearance quality detecting system comprises an arc welding robot, wherein a welding gun is arranged on the arc welding robot, the welding gun is connected with a wire feeder and a welding power supply, a laser vision sensor is arranged at a position, deviating from arc light emission, on the welding gun, and the arc welding robot, the wire feeder, the welding power supply and the laser vision sensor are connected with a control system, wherein: the laser vision sensor comprises a structural light source for emitting blue laser and a CCD camera for receiving only the blue laser; under the drive of an arc welding robot, the welding gun and the laser vision sensor synchronously move together, so that the laser vision sensor immediately acquires images of welding seams after the welding gun finishes welding.
4. A steel structural member weld appearance quality detection system according to claim 3, wherein:
and a code spraying and marking device is arranged beside the laser vision sensor.
5. A steel structural member weld appearance quality detection system according to claim 3, wherein:
The control system is connected with the industrial personal computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010976707.1A CN112067623B (en) | 2020-09-16 | 2020-09-16 | Method and system for detecting appearance quality of welding seam of steel structural member |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010976707.1A CN112067623B (en) | 2020-09-16 | 2020-09-16 | Method and system for detecting appearance quality of welding seam of steel structural member |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112067623A CN112067623A (en) | 2020-12-11 |
| CN112067623B true CN112067623B (en) | 2024-05-24 |
Family
ID=73696977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010976707.1A Active CN112067623B (en) | 2020-09-16 | 2020-09-16 | Method and system for detecting appearance quality of welding seam of steel structural member |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112067623B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610814B (en) * | 2021-08-10 | 2022-11-18 | 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 |
| CN115070251B (en) * | 2022-06-21 | 2024-01-05 | 苏州大学 | Friction stir welding surface welding quality detection method |
| US11878364B2 (en) | 2022-06-27 | 2024-01-23 | Soochow University | Method for detecting surface welding quality of friction stir welding |
| CN115338556A (en) * | 2022-08-03 | 2022-11-15 | 湖南科技大学 | Weld joint quality detection method for thick-wall welding workpiece and computer equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103542819A (en) * | 2012-07-17 | 2014-01-29 | 宝山钢铁股份有限公司 | Detection and quality judgment method for strip steel weld surface appearance |
| JP2014092391A (en) * | 2012-11-01 | 2014-05-19 | Yokogawa Bridge Holdings Corp | Welding flaw outer appearance inspection system and welding flaw outer appearance inspection method |
| JP2017148841A (en) * | 2016-02-24 | 2017-08-31 | 株式会社東芝 | Welding processing system and welding failure detection method |
| CN107824940A (en) * | 2017-12-07 | 2018-03-23 | 淮安信息职业技术学院 | Welding seam traking system and method based on laser structure light |
| CN109239081A (en) * | 2018-09-18 | 2019-01-18 | 广东省特种设备检测研究院珠海检测院 | Weldquality parameter detection method based on structure light and visual imaging |
| 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 |
| WO2020129617A1 (en) * | 2018-12-19 | 2020-06-25 | パナソニックＩｐマネジメント株式会社 | Visual inspection device, method for improving accuracy of determination for existence/nonexistence of shape failure of welding portion and kind thereof using same, welding system, and work welding method using same |
-
2020
- 2020-09-16 CN CN202010976707.1A patent/CN112067623B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103542819A (en) * | 2012-07-17 | 2014-01-29 | 宝山钢铁股份有限公司 | Detection and quality judgment method for strip steel weld surface appearance |
| JP2014092391A (en) * | 2012-11-01 | 2014-05-19 | Yokogawa Bridge Holdings Corp | Welding flaw outer appearance inspection system and welding flaw outer appearance inspection method |
| JP2017148841A (en) * | 2016-02-24 | 2017-08-31 | 株式会社東芝 | Welding processing system and welding failure detection method |
| CN107824940A (en) * | 2017-12-07 | 2018-03-23 | 淮安信息职业技术学院 | Welding seam traking system and method based on laser structure light |
| CN109239081A (en) * | 2018-09-18 | 2019-01-18 | 广东省特种设备检测研究院珠海检测院 | Weldquality parameter detection method based on structure light and visual imaging |
| WO2020129617A1 (en) * | 2018-12-19 | 2020-06-25 | パナソニックＩｐマネジメント株式会社 | Visual inspection device, method for improving accuracy of determination for existence/nonexistence of shape failure of welding portion and kind thereof using same, welding system, and work welding method using same |
| 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 |
Non-Patent Citations (3)
| Title |
|---|
| 侯勇主编.《焊条电弧焊》.机械工业出版社,2018,(第1版),第26-31页. * |
| 唐红元编著.《既有建筑结构检测鉴定与加固》.西南交通大学出版社,2017,(第1版),第43-45页. * |
| 崔吉、崔建国主编.《工业视觉实用教程》.上海交通大学出版社,2018,(第1版),第14-15页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112067623A (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112067623B (en) | Method and system for detecting appearance quality of welding seam of steel structural member | |
| CN105458462B (en) | A kind of trapezoidal weld seam multi-parameter synchronizing visual detecting and tracking method of Varied clearance | |
| CN110530877B (en) | Welding appearance quality detection robot and detection method thereof | |
| CN102699534B (en) | Scanning type laser vision sensing-based narrow-gap deep-groove automatic laser multilayer welding method for thick plate | |
| CN104764750B (en) | Elevator balanced compensated chain automatic detection device for quality and method based on machine vision | |
| CN111738985B (en) | Visual detection method and system for weld joint contour | |
| CN102455171B (en) | Method for detecting geometric shape of back of tailor-welding weld and implementing device thereof | |
| KR100695945B1 (en) | The system for tracking the position of welding line and the position tracking method thereof | |
| CN102303190A (en) | Method for visually tracking plane abut-jointed weld beam by linear laser | |
| CN103464383A (en) | Industrial robot sorting system and method | |
| CN109693140B (en) | Intelligent flexible production line and working method thereof | |
| CN108802178B (en) | Quality detection equipment and quality detection method for steel rail welded joint | |
| CN106378514B (en) | The non-homogeneous subtle more weld seam vision detection systems of stainless steel and method based on machine vision | |
| CN112304954A (en) | Part surface defect detection method based on line laser scanning and machine vision | |
| CN109949362A (en) | A kind of material visible detection method | |
| CN203508417U (en) | Sorting system of industrial robot | |
| CN107803606A (en) | A kind of detection method for quality of welding line and device based on overall process mark | |
| CN113160162B (en) | Hole recognition method and device applied to workpiece and hole processing equipment | |
| CN114043045B (en) | Round hole automatic plug welding method and device based on laser vision | |
| KR101264935B1 (en) | welding position detecting method by camera images | |
| CN116908107A (en) | Paint surface flaw detection system based on machine vision | |
| CN101995218A (en) | Image type screw thread template automatic detection instrument | |
| CN106780655B (en) | Manual decision method and system for automatic welding path | |
| CN107202797A (en) | Contactless Continuous Hot Dip Galvanizing Line strip steel weld joint detecting system and its method | |
| CN115014205B (en) | Visual detection method and detection system for tower tray and automatic welding guiding system thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |