CN109822216A - Welding bead track and posture real-time tracking detection method, electronic equipment and medium - Google Patents
Welding bead track and posture real-time tracking detection method, electronic equipment and medium Download PDFInfo
- Publication number
- CN109822216A CN109822216A CN201910037379.6A CN201910037379A CN109822216A CN 109822216 A CN109822216 A CN 109822216A CN 201910037379 A CN201910037379 A CN 201910037379A CN 109822216 A CN109822216 A CN 109822216A
- Authority
- CN
- China
- Prior art keywords
- image
- gray scale
- coordinate system
- threshold
- forming component
- 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.)
- Granted
Links
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
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/20—Bonding
- B23K26/21—Bonding by welding
-
- 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
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/70—Auxiliary operations or equipment
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Laser Beam Processing (AREA)
Abstract
The embodiment of the present invention provides a kind of welding bead track and posture real-time tracking detection method, electronic equipment and medium, belongs to welding automation field.This method is using homogenous diffused light source irradiation workpiece surface areola groove near zone to be welded synchronous with multi-thread laser light source, and the time for exposure by adjusting image-forming component obtains the suitable original image of gray scale；Gray scale frequency histogram by calculating the analysis original image determines two threshold values；Binaryzation is carried out to original image respectively with two threshold values, and extracts groove region and laser projection region；Based on the groove region and laser projection region, the normal vector of the three-dimensional position and the workpiece surface to be welded that obtain groove center is calculated.The embodiment of the present invention is using double light source synchronous irradiation workpiece surfaces and obtains the unsaturated image of gray scale, can adapt to the special occasions such as high-speed welding, remote detection, and image processing method speed is fast, can satisfy the requirement of welding real-time tracking.
Description
Technical field
The present embodiments relate to welding automation field, more particularly, to a kind of welding bead track and posture in real time with
Track detection method, electronic equipment and medium.
Background technique
Important meaning is all had for automatically tracking in teaching automatic before welding and weldering in the automatic detection of welding field, weld seam
Justice, and vision-based detection becomes the important way that weld seam detects automatically because being capable of providing the information abundant about weld seam.
Weld seam detection common structure light method at present, this method pass through the change of structure light on project structured light to groove
Shape obtains the location information of groove, however when groove gap is minimum, the deformation of structure light in the picture is difficult to differentiate, and the party
Method can only detect the three-dimensional coordinate of groove, it is difficult to detect the posture of workpiece surface, therefore can not guide welding gun tune in welding process
Whole posture.
Chinese patent literature (publication number CN103954216A) discloses a kind of strong mirror-reflection work based on spherical surface light source
Laser array and spherical surface light source are alternately lighted and are incident upon workpiece surface by the narrower groove detection device of part and method, the sensor
On, and image when with image-forming component sync pulse jamming difference light source igniting, image when being lighted by laser array obtain laser
Array subpoint nearby workpiece surface pose, then pass through spherical surface light source igniting when brightness uniformity image obtain groove two
Information is tieed up, the two is combined into the three-dimensional pose to determine groove.However, there are two o'clock deficiencies for this method: first is that image-forming component is adopted
There are the time differences for the image of image and spherical surface light source igniting that the laser array of collection is lighted, in high-speed welding or workpiece surface to be welded
When pose variation is violent, the detection error as caused by the time difference is obvious；Second is that image when this method requirement spherical surface light source igniting
Gray scale is close to being saturated, quick and precisely to extract the center of groove, and in the application of groove real-time tracking, detection device
It is often connected with welding torch, in some occasions for needing to weld at a distance, such as the laser welding under certain occasions, welding torch is difficult to connect
Nearly workpiece needs more powerful spherical surface light source to make image grayscale close to saturation, and to get over large volume general for the power of light source
Also can be bigger, cause the volume of detection device entirety to increase.
Summary of the invention
The embodiment of the present invention provides a kind of welding bead track and posture real-time tracking detection method, electronic equipment and medium, with
It solves of the existing technology existing when being measured in real time areola groove to be difficult to adapt to high-speed welding, remote detection etc.
The problem of occasion.
In a first aspect, the embodiment of the present invention provides a kind of welding bead track and posture real-time tracking detection method, comprising:
Using homogenous diffused light source irradiation workpiece surface areola groove near zone to be welded synchronous with multi-thread laser light source, and
Time for exposure by adjusting image-forming component obtains the suitable original image of gray scale；
The gray scale frequency histogram of the original image is calculated and analyzed, determines the first threshold for extracting groove region
With the second threshold for extracting laser projection region；
It is utilized respectively the first threshold and second threshold and binaryzation is carried out to the original image, and to by binaryzation
The original image of processing carries out the reservation of morphological operation and connected domain, obtains groove region and laser projection region；
Based on the groove region and laser projection region, the three-dimensional position for obtaining groove center and described to welder is calculated
The normal vector on part surface.
Second aspect, the embodiment of the present invention provides a kind of electronic equipment, including memory, processor and is stored in memory
Computer program that is upper and can running on a processor, is realized when the processor executes described program as first aspect provides
Welding bead track and the step of posture real-time tracking detection method.
The third aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium, are stored thereon with calculating
Machine program realizes welding bead track and posture real-time tracking as provided by first aspect when the computer program is executed by processor
The step of detection method.
Welding bead track provided in an embodiment of the present invention and posture real-time tracking detection method, electronic equipment and medium, can
The occasions such as high-speed welding, remote detection suitable for areola groove, have widened the application scenarios of areola groove detection method, and
Image processing method speed is fast, can satisfy the requirement of welding real-time tracking.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the principle schematic diagram of the detection device of the detection method proposed using the embodiment of the present invention；
Fig. 2 is schematic diagram of the multi-thread laser light source projects on workpiece surface to be welded；
Fig. 3 is the flow diagram of welding bead track provided in an embodiment of the present invention and posture real-time tracking detection method；
Fig. 4 is the schematic diagram of the original image of image-forming component acquisition；
Fig. 5 is the gray scale frequency histogram of the original image of image-forming component acquisition.
Fig. 6 is the entity structure schematic diagram of electronic equipment provided in an embodiment of the present invention；
Description of symbols: 1- control unit；2- welding gun；3- sensor outer housing；4- image-forming component；The multi-thread laser light of 5-
Source；6- filter element；7- homogenous diffused light source；8- workpiece to be welded；81- groove.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the structure using welding bead track provided in an embodiment of the present invention and posture real-time tracking detection side detection device
Schematic illustration, comprising: control unit 1, sensor outer housing 3, and be fixed in sensor outer housing 3 image-forming component 4, filter
Element 6, multi-thread laser light source 5 and homogenous diffused light source 7.Wherein, control unit 1 is connected with image-forming component 4 by control line；
Multi-thread laser light source 5 can issue at least two laser line projections on the surface of workpiece 8 to be welded, as shown in Fig. 2, being multi-thread laser light
Source 5 is incident upon the schematic diagram on workpiece surface to be welded；The diffused light that homogenous diffused light source 7 can issue brightness uniformity is incident upon to be welded
The surface of workpiece 8；The reflected light on 8 surface of workpiece to be welded enters image-forming component 4 after filter element 6 and is imaged.
In welding process, welding gun needs to be aligned welding bead, while welding gun needs to keep certain posture with workpiece surface to be welded
Therefore relationship (for example welding gun axis is vertical with workpiece surface), carries out welding track and posture real with guaranteeing welding quality
When tracing detection target be real-time tracking detection groove central three-dimensional position and workpiece surface normal vector, groove central three-dimensional
The normal information of position and workpiece surface can adjust for the welding gun pose in welding process and welding condition adjusting provides
Reference frame.
Fig. 3 is the flow diagram of welding bead track provided in an embodiment of the present invention and posture real-time tracking detection method, packet
It includes:
It is step 100, attached using homogenous diffused light source irradiation synchronous with multi-thread laser light source workpiece surface areola groove to be welded
Near field, and the time for exposure by adjusting image-forming component obtains the suitable original image of gray scale；
The areola groove of workpiece surface to be welded is the minimum groove of refers to the gap, is usually no more than 0.1mm.
The embodiment of the present invention uses homogenous diffused light source irradiation workpiece surface areola to be welded slope synchronous with multi-thread laser light source
Mouth near zone avoids so as to calculate the three-dimensional position of groove and the normal vector of workpiece surface according to same frame image
The detection error as caused by time difference when existing method is calculated using two field pictures, and the gray scale of image need not approach and satisfy
With reduce the requirement to homogenous diffused light source lighting brightness.
The time for exposure of image-forming component is adjusted, obtains the suitable original image of gray scale, wherein gray scale properly refers into pixel
The gray scale for the image that part obtains meets pre-set tonal range.
Specifically, multi-thread laser light source 5 and homogenous diffused light source 7 are lighted simultaneously, and it is attached to irradiate 8 surface groove 81 of workpiece to be welded
Close region, control unit 1 control the original image I that image-forming component 4 shoots the region, as shown in figure 4, a in figure indicates slope
Mouthful, b indicates two laser rays, and the small cube and ellipse in figure show workpiece surface trace.Control unit 1 calculates original later
The average gray r of image IaveIf rave∈[rmin,rmax] then enter in next step, otherwise control unit 1 adjusts image-forming component 4
Time for exposure obtains original image I again, until rave∈[rmin,rmax], wherein [rmin,rmax] it is a preset gray scale
Range is in order to keep the gray scale on 8 surface of workpiece to be welded in original image I moderate, convenient for extracting groove area in subsequent step herein
Domain and laser projection region.For example, when the average gray of original image I is 128, it is believed that the gray scale of the original image is suitable
In.
Image-forming component three is established before step 100 in order to realize that butt welding road track and posture carry out real-time tracking detection
It ties up rectangular coordinate system { C }, wherein the origin of { C } is the optical center of image-forming component 4, the z-axis direction of { C } and 4 light of image-forming component
Axis direction is identical；Pixel two-dimensional coordinate system { P } is established on the image that image-forming component 4 acquires；
Image-forming component 4 is demarcated, the image-forming component three-dimensional cartesian coordinate system { C } is obtained and the pixel two dimension is sat
The transformational relation of corresponding points between mark system { P }；
Multi-thread laser light source 5 is demarcated, obtains the multi-thread each optical plane of laser light source in the image-forming component
Equation in three-dimensional cartesian coordinate system { C }.
Step 200, the gray scale frequency histogram for calculating and analyzing the original image are determined for extracting groove region
First threshold and second threshold for extracting laser projection region；
After obtaining the satisfactory original image I of average gray, its gray scale frequency histogram p (r) is calculated.
Gray scale frequency histogram by analyzing the original image determine first threshold for extracting groove region and
For extracting the second threshold in laser projection region, specifically include:
It calculates according to the following formula and extracts first threshold t used in groove regionlow:
tlow=max r,
Wherein, r is the gray value in gray scale frequency histogram, and p (i) is the frequency that gray value i occurs, and a is set in advance for one
Fixed value, 0 < a < 1.
Since the gray scale of laser rays in original image I is much higher than other regions, high gray scale in gray scale frequency histogram
Area can have a peak, as shown in figure 5, can be sharp by extracting using the corresponding gray value of the low ebb in front of peak as threshold value
Light view field.
Specifically, first gray scale frequency histogram p (r) is smoothed to remove random fluctuation therein, is put down
Gray scale frequency histogram p after cunnings(r) after, p is founds(r) the maximum minimum point of gray scale in, by the minimum point pair
The gray scale answered is as the second threshold t for extracting laser projection regionhigh。
It should be noted that the low gray area of gray scale frequency histogram may since groove 81 may be more narrower
There is no low ebbs, therefore can not be determined with similar method and extract threshold value t used in groove regionlow。
The gray scale frequency histogram can be smoothed using gaussian filtering method or the mean filter.
Step 300 is utilized respectively the first threshold and second threshold to original image progress binaryzation, and to warp
The original image for crossing binary conversion treatment carries out the reservation of morphological operation and connected domain, obtains groove region and laser projection
Region；
Specifically, the first threshold and second threshold are utilized respectively, binaryzation is carried out to the original image, can obtained
Two binary images, to using first threshold carry out binarization operation acquisition binary image progress morphology be connected to
The reservation in domain obtains groove region；Morphology is carried out to the binary image for carrying out binarization operation acquisition using second threshold
With the reservation of connected domain, laser projection region is obtained.
Step 300 the following steps are included:
Utilize the first threshold tlowBinary conversion treatment is carried out to the original image I, retains gray scale in original image I
Less than or equal to the first threshold tlowPoint, obtain the first binary image Ilow；
Due to noise etc., the first binary image IlowMesoslope mouth region domain there may be small gap and hole, because
This is to the first binary image IlowA morphology closed operation is carried out, gap therein and cave fillings are made.
Due to 8 surface of workpiece to be welded, there may be the low echo areas in part, as shown in figure 4, in original image I gray scale compared with
It is low, it is retained in after binary conversion treatment, and these low general areas in echo area are smaller or shape is thin unlike groove 81
It is long, therefore connected domain extraction is carried out again, enough big and elongate form the connected domains of Retention area.
That is the connected domain of Retention area and circularity rate the first preset condition of satisfaction, the first preset condition specifically:
Wherein, A represents the area of connected domain, Amin1Represent the first area threshold of preset connected domain, RcThe company of representative
The circularity rate in logical domain, Rcmax1Represent the first circularity rate threshold value of preset connected domain；
Wherein, the circularity rate R of connected domaincIs defined as:
Wherein, P represents the perimeter of connected domain.
By the first binary image IlowIn the connected domain that retains as groove region, be based on the groove region
Obtain coordinate of the groove center in the pixel two-dimensional coordinate system { P }.
The specific steps for obtaining coordinate of the groove center in the pixel two-dimensional coordinate system can be with are as follows: in the first binaryzation
Image IlowIn take an intermediate column, find two intersection points of this column with the connected domain retained, the midpoint of two intersection points regarded
For groove center, the coordinate of the intersection point is obtained, that is, obtains coordinate of the groove center in pixel two-dimensional coordinate system { P }.If even
Logical domain be it is discontinuous, then to connected domain carry out straight line fitting after, take the first binary image IlowAn intermediate column, by this
Column and the intersection point of the connected domain after fitting are considered as groove center, and then get groove center in pixel two-dimensional coordinate system { P }
Coordinate.
Utilize the second threshold thighBinary conversion treatment is carried out to the original image I, retains gray scale in original image I
More than or equal to the second threshold thighPoint, obtain the second binary image Ihigh；
Due to laser speckle etc., in original image I there is a large amount of small low gray areas, two-value in laser projection region
Become small gap and hole after change, therefore to IhighA morphology closed operation is carried out, is eliminated in laser projection region
Minim gap and hole.
Due to 8 surface of workpiece to be welded, there may be part high-reflection regions, and gray scale is higher in original image I, through binaryzation
I is retained in after processinghighIn, and the general area in these high-reflection regions is smaller or shape is thin unlike laser projection region
It is long, therefore connected domain extraction is carried out again, the enough elongated connected domains of the enough big and shapes of Retention area,
That is the connected domain of Retention area and circularity rate the second preset condition of satisfaction, the second preset condition specifically:
Wherein, A represents the area of connected domain, Amin2Represent the second area threshold value of preset connected domain, RcThe company of representative
The circularity rate in logical domain, Rcmax2Represent the second circularity rate threshold value of preset connected domain.RcIt is defined as described above.
By the second binary image IhighIn the connected domain that retains as laser projection region, wherein laser is thrown
Shadow zone domain refers to the workpiece surface region where multi-thread laser projection.
The series of points on laser projection line is obtained in the pixel two-dimensional coordinate system { P } based on the laser projection region
In coordinate.
Step 400 is based on the groove region and laser projection region, calculates the three-dimensional position for obtaining groove center and institute
State the normal vector of workpiece surface to be welded.
Specifically, series of points is in the pixel two-dimensional coordinate system on the laser projection line obtained according to step 300
Coordinate in { P }, in conjunction with the image-forming component three-dimensional cartesian coordinate system { C } and pixel two-dimensional coordinate system for demarcating acquisition before
The transformational relation of corresponding points and each optical plane of multi-thread laser light source are sat at image-forming component three-dimensional right angle between { P }
Equation in mark system { C } calculates on the laser projection line series of points in the image-forming component three-dimensional cartesian coordinate system { C }
Coordinate；
By the surface region of the workpiece to be welded 8 where multi-stripe laser projection line depending on being a flat surface W, it is based on the laser projection
Coordinate of the series of points in the image-forming component three-dimensional cartesian coordinate system { C } on line, where fitting multi-thread laser projection
Equation of the workpiece planarization W in the image-forming component three-dimensional cartesian coordinate system { C }.
Least square method can be used in approximating method.
And the normal vector of the workpiece planarization W is obtained according to the equation calculation.
According to where coordinate of the groove center in the pixel two-dimensional coordinate system { P }, the multi-thread laser projection
Equation, the image-forming component three-dimensional cartesian coordinate system of the workpiece planarization W in the image-forming component three-dimensional cartesian coordinate system { C }
The transformational relation of corresponding points between { C } and pixel two-dimensional coordinate system { P } calculates and obtains groove center in the three-dimensional rectangular coordinate
It is the coordinate in { C }.
According to the normal vector of groove central three-dimensional position and workpiece surface, can in welding process the adjustment of welding gun pose and
Welding condition, which is adjusted, provides reference frame.
Welding bead track provided in an embodiment of the present invention and posture real-time tracking detection method, detect groove three-dimensional coordinate and
The pose of workpiece surface can be suitable for the occasions such as high-speed welding, the remote detection of areola groove, widen the inspection of areola groove
The application scenarios of survey method, and image processing method speed is fast, can satisfy the requirement of welding real-time tracking.
Fig. 6 is the entity structure schematic diagram of electronic equipment provided in an embodiment of the present invention, as shown in fig. 6, the electronic equipment
It may include: processor (processor) 610,620, memory communication interface (Communications Interface)
(memory) 630 and communication bus 640, wherein processor 610, communication interface 620, memory 630 pass through communication bus 640
Complete mutual communication.Processor 610 can call the meter that is stored on memory 630 and can run on processor 610
Calculation machine program to execute welding bead track provided by above-mentioned each method embodiment and posture real-time tracking detection method, such as is wrapped
It includes: using homogenous diffused light source irradiation workpiece surface areola groove near zone to be welded synchronous with multi-thread laser light source, and passing through
The time for exposure for adjusting image-forming component obtains the suitable original image of gray scale；Calculate and analyze the gray scale frequency of the original image
Histogram determines the second threshold for extracting the first threshold in groove region and for extracting laser projection region；Benefit respectively
Binaryzation is carried out to the original image with the first threshold and second threshold, and to by the described original of binary conversion treatment
Image carries out the reservation of morphological operation and connected domain, obtains groove region and laser projection region；Based on the groove region
With laser projection region, the normal vector of the three-dimensional position and the workpiece surface to be welded that obtain groove center is calculated.
In addition, the logical order in above-mentioned memory 630 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
The technical solution of the inventive embodiments substantially part of the part that contributes to existing technology or the technical solution in other words
It can be expressed in the form of software products, which is stored in a storage medium, including some instructions
With so that computer equipment (can be personal computer, server or the network equipment an etc.) execution present invention is each
The all or part of the steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk
Etc. the various media that can store program code.
The embodiment of the present invention also provides a kind of non-transient computer readable storage medium, is stored thereon with computer program,
The computer program realizes the welding bead track that above-mentioned each method embodiment provides and the inspection of posture real-time tracking when being executed by processor
Survey method, for example, attached using homogenous diffused light source irradiation workpiece surface areola groove to be welded synchronous with multi-thread laser light source
Near field, and the time for exposure by adjusting image-forming component obtains the suitable original image of gray scale；It calculates and analyzes described original
The gray scale frequency histogram of image determines the first threshold for extracting groove region and for extracting laser projection region
Two threshold values；It is utilized respectively the first threshold and second threshold and binaryzation is carried out to the original image, and to by binaryzation
The original image of processing carries out the reservation of morphological operation and connected domain, obtains groove region and laser projection region；Base
In the groove region and laser projection region, the method for the three-dimensional position and the workpiece surface to be welded that obtain groove center is calculated
Vector.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of welding bead track and posture real-time tracking detection method characterized by comprising
Using homogenous diffused light source irradiation workpiece surface areola groove near zone to be welded synchronous with multi-thread laser light source, and pass through
The time for exposure for adjusting image-forming component obtains the suitable original image of gray scale；
The gray scale frequency histogram of the original image is calculated and analyzed, determines first threshold and use for extracting groove region
In the second threshold for extracting laser projection region；
It is utilized respectively the first threshold and second threshold and binaryzation is carried out to the original image, and to by binary conversion treatment
The original image carry out the reservation of morphological operation and connected domain, obtain groove region and laser projection region；
Based on the groove region and laser projection region, the three-dimensional position and the workpiece table to be welded for obtaining groove center are calculated
The normal vector in face.
2. the method according to claim 1, wherein described same using homogenous diffused light source and multi-thread laser light source
Step irradiates workpiece surface areola groove near zone to be welded, and the acquisition of the time for exposure by adjusting image-forming component gray scale is suitable
Before the step of original image, further includes:
Image-forming component three-dimensional cartesian coordinate system is established, establishes pixel two-dimensional coordinate system on the image of image-forming component acquisition；
Image-forming component is demarcated, is obtained between the image-forming component three-dimensional cartesian coordinate system and the pixel two-dimensional coordinate system
The transformational relation of corresponding points；
Multi-thread laser light source is demarcated, obtains the multi-thread each optical plane of laser light source in the image-forming component three-dimensional straight
Equation in angular coordinate system.
3. the method according to claim 1, wherein the time for exposure by adjusting image-forming component obtains ash
The step of spending suitable original image, specifically:
Calculate the average gray of the image of the workpiece surface areola groove near zone to be welded of image-forming component shooting；
If the average gray adjusts the time for exposure of the image-forming component not in preset tonal range, until to be welded
The average gray of the image of workpiece surface areola groove near zone meets the preset tonal range.
4. the method according to claim 1, wherein the gray scale frequency calculated and analyze the original image
The step of histogram, the determining second threshold for extracting the first threshold in groove region and for extracting laser projection region,
Specifically:
Calculate the gray scale frequency histogram of the original image；
The first threshold t is calculated according to the following formulalow:
tlow=max r,
Wherein, r is the gray value in gray scale frequency histogram, and p (i) is the frequency that gray value i occurs, and a is one preset
Value, 0 < a < 1；
The gray scale frequency histogram of the original image is smoothed, it is straight to obtain the gray scale frequency after smoothing processing
Side figure ps(r), p is obtaineds(r) the maximum minimum point of gray scale in, using the gray scale of the minimum point as second threshold
Value thigh。
5. according to the method described in claim 2, it is characterized in that, described be utilized respectively the first threshold and second threshold pair
The original image carries out binaryzation, and carries out morphological operation and connected domain to the original image Jing Guo binary conversion treatment
Reservation, obtain groove region and the step of laser projection region, specifically:
Binary conversion treatment is carried out to the original image using the first threshold, retains gray scale and is less than or equal to the first threshold
Point, obtain the first binary image；
Morphology closed operation is carried out to first binary image, then carries out the extraction of connected domain, it is default to retain satisfaction first
The connected domain of condition is based on the groove area using the connected domain retained in first binary image as groove region
Domain obtains coordinate of the groove center in the pixel two-dimensional coordinate system；
Binary conversion treatment is carried out to the original image using the second threshold, retains gray scale and is more than or equal to the second threshold
Point, obtain the second binary image；
Morphology closed operation is carried out to second binary image, then carries out the extraction of connected domain, it is default to retain satisfaction second
The connected domain of condition is swashed using the connected domain retained in second binary image as laser projection region based on described
Light view field obtains coordinate of the series of points in the pixel two-dimensional coordinate system on laser projection line.
6. according to the method described in claim 5, it is characterized in that, it is described be based on the groove region and laser projection region,
The step of calculating the normal vector of the three-dimensional position and the workpiece surface to be welded that obtain groove center, specifically:
It is three-dimensional according to coordinate, the image-forming component of the series of points on the laser projection line in the pixel two-dimensional coordinate system
The transformational relation of corresponding points and each optical plane of multi-thread laser light source between rectangular coordinate system and pixel two-dimensional coordinate system
Equation in the image-forming component three-dimensional cartesian coordinate system calculates on the laser projection line series of points described into pixel
Coordinate in part three-dimensional cartesian coordinate system；
Based on coordinate of the series of points in the image-forming component three-dimensional cartesian coordinate system on the laser projection line, fit more
Equation of the workpiece planarization in the image-forming component three-dimensional cartesian coordinate system where line laser projection, and according to the equation meter
Calculate the normal vector for obtaining the workpiece planarization；
It is flat in the coordinate in the pixel two-dimensional coordinate system, the workpiece where the multi-thread laser projection according to the groove center
Equation, the image-forming component three-dimensional cartesian coordinate system and pixel two dimension of the face in the image-forming component three-dimensional cartesian coordinate system are sat
The transformational relation of corresponding points between mark system, calculates the coordinate for obtaining groove center in the three-dimensional cartesian coordinate system.
7. according to the method described in claim 4, it is characterized in that, described be smoothed the gray scale frequency histogram
The step of, specifically:
The gray scale frequency histogram is smoothed using gaussian filtering method or the mean filter.
8. according to the method described in claim 5, it is characterized in that, first preset condition specifically:
Wherein, A represents the area of connected domain, Amin1Represent the first area threshold of preset connected domain, RcRepresent connected domain
Circularity rate, Rcmax1Represent the first circularity rate threshold value of preset connected domain；
Wherein, RcIs defined as:
Wherein, P represents the perimeter of connected domain；
Correspondingly, second preset condition are as follows:
Wherein, A represents the area of connected domain, Amin2Represent the second area threshold value of preset connected domain, RcRepresent connected domain
Circularity rate, Rcmax2Represent the second circularity rate threshold value of preset connected domain.
9. a kind of electronic equipment characterized by comprising
At least one processor；And
At least one processor being connect with the processor communication, in which:
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough execute method as described in any of the claims 1 to 8.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute method as described in any of the claims 1 to 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910037379.6A CN109822216B (en) | 2019-01-15 | 2019-01-15 | Welding bead track and posture real-time tracking detection method, electronic equipment and medium |
| PCT/CN2020/071096 WO2020147639A1 (en) | 2019-01-15 | 2020-01-09 | Method for real-time tracking and detection of weld bead trajectory and attitude, electronic device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910037379.6A CN109822216B (en) | 2019-01-15 | 2019-01-15 | Welding bead track and posture real-time tracking detection method, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109822216A true CN109822216A (en) | 2019-05-31 |
| CN109822216B CN109822216B (en) | 2020-03-17 |
Family
ID=66861078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910037379.6A Active CN109822216B (en) | 2019-01-15 | 2019-01-15 | Welding bead track and posture real-time tracking detection method, electronic equipment and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109822216B (en) |
| WO (1) | WO2020147639A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179255A (en) * | 2019-12-30 | 2020-05-19 | 南京衍构科技有限公司 | Feature recognition method in automatic preparation process of membrane water-cooled wall |
| WO2020147639A1 (en) * | 2019-01-15 | 2020-07-23 | 清华大学 | Method for real-time tracking and detection of weld bead trajectory and attitude, electronic device and medium |
| US20220063018A1 (en) * | 2020-08-27 | 2022-03-03 | Dm3D Technology, Llc | Vision-based rotary part offset correction for weld toolpathing |
| CN114345841A (en) * | 2021-12-31 | 2022-04-15 | 苏州德威尔卡光电技术有限公司 | Control method in laser cleaning process and laser cleaning control system |
| CN114749849A (en) * | 2022-06-01 | 2022-07-15 | 江苏徐工工程机械研究院有限公司 | Welding control method, device and system |
| CN115055806A (en) * | 2022-08-11 | 2022-09-16 | 先富斯技术（武汉）有限公司 | Welding track tracking method and device based on visual tracking |
| CN115988866A (en) * | 2023-03-21 | 2023-04-18 | 深圳市利和兴股份有限公司 | NFC LAMI processing control method and system based on machine vision |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782526B (en) * | 2022-06-22 | 2022-09-02 | 季华实验室 | Welding seam track calculation method and device of H-shaped steel, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6033874A (en) * | 1983-08-03 | 1985-02-21 | Mitsubishi Heavy Ind Ltd | Robot for arc welding |
| US5481085A (en) * | 1994-09-09 | 1996-01-02 | University Of Kentucky Research Foundation | Apparatus and method for measuring 3-D weld pool shape |
| CN103954216A (en) * | 2014-05-13 | 2014-07-30 | 清华大学 | Strong specular reflection workpiece thin and narrow groove detection device and method based on spherical surface light sources |
| CN106952281A (en) * | 2017-05-15 | 2017-07-14 | 上海交通大学 | A kind of method that weld profile feature recognition and its welding bead are planned in real time |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102780845A (en) * | 2012-06-14 | 2012-11-14 | 清华大学 | Light source alternate strobe synchronous camera shooting method and vision detection system |
| CN104950800B (en) * | 2015-06-12 | 2017-08-08 | 广东省自动化研究所 | A kind of localization method for seeking track localization process system |
| CN109822216B (en) * | 2019-01-15 | 2020-03-17 | 清华大学 | Welding bead track and posture real-time tracking detection method, electronic equipment and medium |
-
2019
- 2019-01-15 CN CN201910037379.6A patent/CN109822216B/en active Active
-
2020
- 2020-01-09 WO PCT/CN2020/071096 patent/WO2020147639A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6033874A (en) * | 1983-08-03 | 1985-02-21 | Mitsubishi Heavy Ind Ltd | Robot for arc welding |
| US5481085A (en) * | 1994-09-09 | 1996-01-02 | University Of Kentucky Research Foundation | Apparatus and method for measuring 3-D weld pool shape |
| CN103954216A (en) * | 2014-05-13 | 2014-07-30 | 清华大学 | Strong specular reflection workpiece thin and narrow groove detection device and method based on spherical surface light sources |
| CN106952281A (en) * | 2017-05-15 | 2017-07-14 | 上海交通大学 | A kind of method that weld profile feature recognition and its welding bead are planned in real time |
Non-Patent Citations (1)
| Title |
|---|
| 邹怡蓉等: "基于图像色彩信息的焊缝识别算法", 《焊接学报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020147639A1 (en) * | 2019-01-15 | 2020-07-23 | 清华大学 | Method for real-time tracking and detection of weld bead trajectory and attitude, electronic device and medium |
| CN111179255A (en) * | 2019-12-30 | 2020-05-19 | 南京衍构科技有限公司 | Feature recognition method in automatic preparation process of membrane water-cooled wall |
| US20220063018A1 (en) * | 2020-08-27 | 2022-03-03 | Dm3D Technology, Llc | Vision-based rotary part offset correction for weld toolpathing |
| CN114345841A (en) * | 2021-12-31 | 2022-04-15 | 苏州德威尔卡光电技术有限公司 | Control method in laser cleaning process and laser cleaning control system |
| CN114345841B (en) * | 2021-12-31 | 2022-10-04 | 苏州德威尔卡光电技术有限公司 | Control method in laser cleaning process and laser cleaning control system |
| CN114749849A (en) * | 2022-06-01 | 2022-07-15 | 江苏徐工工程机械研究院有限公司 | Welding control method, device and system |
| CN114749849B (en) * | 2022-06-01 | 2023-09-01 | 江苏徐工工程机械研究院有限公司 | Welding control method, device and system |
| CN115055806A (en) * | 2022-08-11 | 2022-09-16 | 先富斯技术（武汉）有限公司 | Welding track tracking method and device based on visual tracking |
| CN115055806B (en) * | 2022-08-11 | 2022-11-18 | 先富斯技术（武汉）有限公司 | Welding track tracking method and device based on visual tracking |
| CN115988866A (en) * | 2023-03-21 | 2023-04-18 | 深圳市利和兴股份有限公司 | NFC LAMI processing control method and system based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020147639A1 (en) | 2020-07-23 |
| CN109822216B (en) | 2020-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109822216A (en) | Welding bead track and posture real-time tracking detection method, electronic equipment and medium | |
| CN108332658B (en) | A kind of welding bead pose real-time detection method for complex-curved welding | |
| JP2012045610A (en) | Apparatus and method for determining shape of end of bead | |
| JP2017514193A (en) | 3D image analysis apparatus for determining a line-of-sight direction | |
| CN109702293B (en) | Welding penetration quality real-time control method based on visual detection | |
| CN106735749B (en) | A kind of laser assisted weld seam Intelligent tracing system | |
| CN105138965A (en) | Near-to-eye sight tracking method and system thereof | |
| CN106773495B (en) | The automatic focusing method and system of projector with multiple lamp light source | |
| US10630890B2 (en) | Three-dimensional measurement method and three-dimensional measurement device using the same | |
| CN104636760A (en) | Positioning method for welding seam | |
| US20200074615A1 (en) | System and Method for Evaluating Displays of Electronic Devices | |
| CN102155920B (en) | Welding seam measuring method based on micro field depth | |
| CN109857255A (en) | A kind of display parameter regulation method, device and wear display equipment | |
| CN108381034A (en) | A kind of laser auto focusing obstacle eliminating system and control method | |
| CN112025090A (en) | Online detection method and detection device for laser deep penetration welding defects | |
| US20240231485A1 (en) | Eyeball tracking method and virtual reality device | |
| CN114998441B (en) | Adaptive adjustment method and device for tripod head lamp of unmanned aerial vehicle, electronic equipment and storage medium | |
| CN103954216A (en) | Strong specular reflection workpiece thin and narrow groove detection device and method based on spherical surface light sources | |
| CN110519580A (en) | A kind of projector automatic focusing method, device, equipment and readable storage medium storing program for executing | |
| WO2017101292A1 (en) | Autofocusing method, device and system | |
| CN204545670U (en) | A kind of narrow gap weld seam follows the tracks of laser sensor | |
| TW201541057A (en) | Method of capturing images | |
| CN103528540A (en) | Prism-based single-camera stereoscopic vision imaging device applied to sensing of welding pool | |
| CN107368817A (en) | Face identification method and device | |
| CN108620714B (en) | Welding deviation detection system based on GMAW (gas metal arc welding) molten pool profile characteristics and detection method 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 |