CN111242979B - Method for recognizing and tracking splashing of three-dimensional space in laser welding process - Google Patents
Method for recognizing and tracking splashing of three-dimensional space in laser welding process Download PDFInfo
- Publication number
- CN111242979B CN111242979B CN202010048245.7A CN202010048245A CN111242979B CN 111242979 B CN111242979 B CN 111242979B CN 202010048245 A CN202010048245 A CN 202010048245A CN 111242979 B CN111242979 B CN 111242979B
- Authority
- CN
- China
- Prior art keywords
- splash
- dimensional space
- tracking
- motion
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003466 welding Methods 0.000 title claims abstract description 35
- 230000008569 process Effects 0.000 title claims abstract description 26
- 238000012545 processing Methods 0.000 claims description 32
- 239000000284 extract Substances 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 abstract description 2
- 239000002184 metal Substances 0.000 description 18
- 230000005855 radiation Effects 0.000 description 8
- 230000000877 morphologic effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002269 spontaneous effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method for recognizing and tracking three-dimensional space splash in a laser welding process, which relates to the field of laser welding and comprises the following steps: the method comprises the steps of acquiring a splash three-dimensional image, extracting splash three-dimensional space features, and positioning and tracking a splash flight track. According to the invention, the splash identification and extraction success rate is improved through an image enhancement technology, the splash is subjected to three-dimensional positioning by correlating images obtained by synchronizing the XOZ plane and the YOZ plane, and further the splash movement track is tracked by correlating splash positions at different moments, so that the splash movement characteristics are obtained.
Description
Technical Field
The invention relates to the field of laser welding, in particular to a method for recognizing and tracking three-dimensional space splashing in a laser welding process.
Background
In laser welding, molten metal in a molten pool is impacted by a high-velocity metal vapor stream and is separated from droplets, i.e., splatters, formed in the molten pool. The generation of spatter is on the one hand an unstable behaviour of the weld pool during laser welding and on the other hand also adversely affects the surface quality of the laser welded seam. Therefore, the splash generated in the laser welding process is identified and the motion characteristics are extracted from the high-speed photographic image, and the method has important application in online monitoring of the laser welding process, welding stability research and weld surface quality improvement.
In the prior art, there have been reports of extracting the splash shape and position during laser welding. Such as: the L.Nicolosi et al at university of Telston, selected to directly binarize the image, the image obtained by this method would binarize the spontaneous radiation light generated by the keyhole and plume and the thermal radiation light generated by the splash at the same time, and it would not be possible to distinguish. After the image is directly binarized by Sun Yan et al of Guangzhou university of industry, an image of the metal plume is obtained through an on operation of firstly corroding and then expanding, and then the image of the metal plume is removed from the binarized image, so that an image of splashing outside the metal plume is obtained. The image processing method can effectively acquire the splash morphological characteristics outside the metal plume. However, the splashes existing in the interior of the metal plume are removed together with the metal plume by this method. While the splashes existing in the interior of the metal plume are often separated from the surface of the molten pool, the characteristics of the splashes can reflect the motion state of the molten pool more truly.
In addition, the existing technical proposal for processing high-speed images in the welding process only can extract the morphological characteristics of the spatter from the images, and aiming at the movement state characteristics of the spatter separated from a molten pool has been rarely reported. The method of manually tracking and measuring splash motion trajectories in high-speed photographic images frame by a manual measurement method of Cai Hua et al of Beijing university of industry has great limitation in practical application. Gao Xiangdong, et al, of the Guangzhou university of industry, is a method for characterizing the movement characteristics of splatter by the distance between the splatter and the laser action point identified by image processing, and cannot directly reflect the movement track, movement speed and movement direction of the splatter.
The splash generated in the laser welding process moves from the molten pool to the periphery in a radiation way, the existing research on the splash form and the movement characteristic is carried out in a two-dimensional plane parallel to the welding direction, and no technical proposal for identifying and tracking the distribution characteristic and the movement track in the splash three-dimensional space is reported.
The prior art has the following defects:
(1) Due to the interference of the radiation light of the metal vapor plume, the splash in the plume cannot be identified and extracted.
(2) The movement track splashed in the welding process cannot be automatically tracked, so that the movement characteristics splashed in the welding process cannot be conveniently obtained.
(3) There is no scheme for extracting the splash three-dimensional space distribution characteristics and tracking the motion trail in the welding process.
Therefore, those skilled in the art are working to develop a method for identifying and tracking the splash in the three-dimensional space in the laser welding process, overcome the interference of the metal vapor plume, automatically track the splash track, and extract the distribution characteristics of the splash in the three-dimensional space in the welding process and track the movement track.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the present invention aims to solve the technical problems of recognizing and tracking the splash of the laser welding process in the three-dimensional space.
In order to achieve the above purpose, the invention provides a method for identifying and tracking the splash of a laser welding process in a three-dimensional space, which is characterized by comprising the following steps:
step 1: acquiring a splash three-dimensional image;
step 2: extracting splash three-dimensional space features;
step 3: positioning and tracking the flying trace of the splash.
Further, step 1 acquires images of both splash XOZ and YOZ planes simultaneously.
Further, step 1 further includes a step of enhancing the acquired image:
step 11: setting a local processing area;
step 12: filtering the local processing area;
step 13: moving the local processing area by m pixel points;
step 14: repeating the steps 12 and 13 until the whole image area, and carrying out reinforced average on the images processed in each local processing area to obtain reinforced images;
step 15: and performing binarization processing and image segmentation on the enhanced image to obtain the shape and position characteristics of splash in the image.
Further, the parameters of the filter in step 12 are defined by the brightness maximum in the local processing regionT 1 Mean value T 2 The specific functions of the filter are determined as follows:
wherein I is 0 For locally processing the luminance values of the image in the region, I 1 For brightness values of the processed local processing area ΔS 1 Is a threshold value of the difference between the splash brightness and the plume brightness, S 2 Is a threshold value of the set plume brightness.
Further, step 2 is configured to extract the area size feature of the splashes in the XOZ plane and the three-dimensional spatial position feature thereof by one-to-one correlation of the splash position features obtained in the images of the XOZ and YOZ planes obtained at the same time.
Further, step 3 includes the steps of:
step 31: grouping and recombining splatters;
step 32: evaluating each set of splatters;
step 33: correlating the motion trail of the splash combination meeting the judgment criterion;
step 34: and checking the acquired splash movement track again.
Further, step 31 identifies and evaluates based on 3 sets of consecutively photographed images, and each set of images is taken of splatters, and three combinations are performed.
Further, step 32 is performed by evaluating each set of splash combinations in turn according to the following criteria, the criteria of which include: whether the sizes of the splatters in the combination are consistent, whether the movement directions of the splatters in the combination are consistent, and the movement distances of the splatters in the combination in the time of each frame interval are equal.
Further, when the dimensional characteristics and the spatial position of the splashes within the combination satisfy three judgment criteria, it is determined that the splashes are part of the movement trajectories of the same splashes at different times.
Further, the motion trajectory of the extracted splash is checked: the average size of the splash of the motion trajectories is consistent, the motion directions of the splash motion trajectories are consistent, the motion distance of the splash motion trajectories in each frame interval time is consistent, the distance between the first splash in the motion trajectories is in direct proportion to the time interval, and for the motion trajectory combinations with different serial numbers meeting the four judgment criteria, the motion trajectories are unified into the motion trajectories of the same splash at different moments again, and the motion characteristics of the splash motion trajectories are obtained through the splash motion trajectories after the re-inspection.
Unlike the prior art, the method can only identify and extract the splashing outside the metal plume in the laser welding process from a single side. The technology acquires splash images synchronously in the XOZ and YOZ planes, inhibits the radiation light of the metal vapor plume by the image enhancement technology, enhances the splash heat radiation light, and further extracts the splash form and the three-dimensional space position in the metal plume. Based on the extracted splash sizes and three-dimensional space position characteristics, the splash in the continuous three images is combined, evaluated, identified and checked again, so that the movement trajectories of different splashes in the welding process can be obtained, and the movement speed and movement direction of the splashes in the three-dimensional space are further obtained. The conception, specific structure, and technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, features, and effects of the present invention.
Drawings
FIG. 1 is a flow chart of the present invention for tracking the motion trajectories of the splatter that have been extracted from successive images;
FIG. 2 is a flow chart of the present invention for image enhancement of splatter in an image;
fig. 3 is a flow chart of the present invention for rechecking an identified motion profile.
Detailed Description
The following description of the preferred embodiments of the present invention refers to the accompanying drawings, which make the technical contents thereof more clear and easy to understand. The present invention may be embodied in many different forms of embodiments and the scope of the present invention is not limited to only the embodiments described herein.
In the drawings, like structural elements are referred to by like reference numerals and components having similar structure or function are referred to by like reference numerals. The dimensions and thickness of each component shown in the drawings are arbitrarily shown, and the present invention is not limited to the dimensions and thickness of each component. The thickness of the components is exaggerated in some places in the drawings for clarity of illustration.
In the laser welding process, molten metal is separated from a molten pool around the keyhole, and splashes are formed above the workpiece. The movement of the spatter in the space above the workpiece is three-dimensional, and therefore, it is necessary to capture the positions of the spatter simultaneously from two planes of XOZ and YOZ, respectively, and obtain spatter images of the spatter in the two planes, respectively.
In the laser welding process, because the energy input of the welding laser is high, metal vapor generated on the surface of the test plate escapes to the outside of the key hole, and atomized metal vapor plume is formed above the test plate. Since the metal plume has high temperature, spontaneous radiation can be generated, and recognition and feature extraction of splashing can be hindered. Therefore, it is necessary to enhance the acquired image based on image processing, remove the interference of plume, and obtain the spatial position feature of splash.
The method utilizes the characteristic that the radiation intensity of the plume in the image is lower than that of the splash, and the morphological distribution is in a plume shape to enhance the splash image in the acquired image. The image enhancement process is as shown in fig. 2:
1) A local processing area is set.
2) Filtering the local processing region, wherein the parameters of the filter are defined by the maximum brightness value T in the region 1 Mean value T 2 The specific functions of the filter are determined as follows:
wherein I is 0 For locally processing the luminance values of the image in the region, I 1 The brightness value of the processed local area is obtained; ΔS 1 Is a threshold value of the difference between the splashing brightness and the plume brightness;S 2 is a threshold value of the set plume brightness.
The principle is as follows:
a) When T is 1 -T 2 >ΔS 1 And T is 2 >S 2 In this case, it is described that the local processing region has both the splash and the plume, and it is necessary to reduce the luminance of the plume and to increase the luminance of the splash.
b) When T is 1 -T 2 <ΔS 1 And T is 2 >S 2 When the local processing area is provided with the plume, the local processing area is required to be reduced in the overall brightness;
c) When T is 2 <S 2 When the image in the local processing area does not have plume, the brightness of the image in the area does not need to be processed.
3) After brightness adjustment of the image in the local processing area is completed, the local processing area is moved to m pixel points, and brightness of the image in the new local processing area is adjusted.
4) And after the enhancement of the image in the whole image area is completed, carrying out enhanced average on the image processed in each local processing area to obtain an enhanced image.
5) And performing binarization processing and image segmentation on the enhanced image to obtain the shape and position characteristics of splash in the image.
6) The splash position features obtained from the images obtained at the same moment of the XOZ plane and the YOZ plane are associated one by one, and the area size feature A splashed in the XOZ plane is extracted i And three-dimensional spatial position features (S) x,i ,S y,i ,S z,i )。
The splashes detached from the bath have a high initial velocity. When the high-speed camera collects at a high frame rate, the motion trail of the three-dimensional space splashed above the test board can be regarded as uniform linear motion, and the area size, the motion direction and the motion distance between images of the same splash frame can be regarded as unchanged. Therefore, the flying track of the flying robot can be positioned and tracked according to the position and the shape of the splash in the images acquired at different moments. The specific tracking process is shown in fig. 1:
1) Grouping and recombining splatters;
splash movement trace tracking is based on a score (N) 1 ,N 1 +1,N 1 +2) 3 groups of consecutively taken images are identified and evaluated, the grouping scheme being: and selecting one splash from the splashes acquired by each group of images, performing three-three combination, and evaluating the combined splashes. The combined internal splashing is respectively marked as F N1 ，F N2 And F N3 The size of each splash is noted as A N1 ,A N2 ,A N3 Its spatial position is (S x,N1 ,S y,N1 ,S z,N1 )；(S x,N2 ,S y,N2 ,S z,N2 ) Sum (S) x,N3 ,S y,N3 ,S z,N3 )
2) Evaluating each set of splatters;
the following criteria were evaluated for each set of splash combinations in turn:
a) Whether the splash sizes in the combination are consistent, i.e. |A N1 -A N2 |＝|A N2 -A N3 And I is less than or equal to delta A. Δa is the error allowed for the identified splash size.
In the present embodiment, the dimension allowance error Δa is set to
b) Whether the movement direction of the splash in the combination is consistent
Namely: for alpha 12 ＝arccot[(S x,N1 -S x,N2 )/(S z,N1 -S z,N2 )],α 23 ＝arccot[(S x,N2 -S x,N3 )/(S z,N2 -S z,N3 )]And beta 12 ＝arccot[(S y,N1 -S y,N2 )/(S z,N1 -S z,N2 )]；β 23 ＝arccot[(S y,N2 -S y,N3 )/(S z,N2 -S z,N3 )]]. The requirements are satisfied: alpha 12 -α 23 Delta alpha and beta 12 -β 23 |≤Δβ
Δα and Δβ are the azimuthal tolerance of the projections of the identified splash motion in the XOZ plane and YOZ plane, respectively. In this embodiment, Δα and Δβ are both set to 5 °.
c) The distance of movement of the splatter within the combination within the time Δt of each frame interval is equal, i.e
L 12 ＝[(S x,N1 -S x,N2 ) 2 +(S y,N1 -S y,N2 ) 2 +(S z,N1 -S z,N2 ) 2 ] 1/2
L 23 ＝[(S x,N2 -S x,N3 ) 2 +(S y,N2 -S y,N3 ) 2 +(S z,N2 -S z,N3 ) 2 ] 1/2
|L 12 -L 23 |≤ΔL 0 。
ΔL 0 The allowable error of the distance of movement per frame interval Δt is the identified splatter. In the present embodiment, the movement distance Δl 0 The allowable error is set as:
3) Correlating the motion trail of the splash combination meeting the judgment criterion;
when splash (F) N1 ,F N2 ,F N3 ) When the dimensional characteristics and the spatial position of (2) satisfy the three criteria for judgment, the same splash can be considered as a part of uniform linear motion trajectories at different moments. At this time, the motion tracks of different splashes are distinguished by assigning serial numbers, and the serial number assignment criterion is as follows:
a) When the first splash F in the combination N1 Has a serial number M 1 At this time, the splash in the combination is considered to be identified as number M 1 Is a part of the splash trajectory of (1). Thus, the other two splashes F N2 And F N3 Marked with the same serial number M 1 。
b) When the first splash F in the combination 1 When no sequence number is assigned, the splatter within the combination can be considered to be the start of a new splatter trajectory. Thus, three splashes F N1 ,F N2 ,F N3 Marked as a new sequence number M 2 。
When pair (N) 1 ,N 1 +1,N 1 +2) after all combinations of recognized splashes in the 3 sets of consecutively photographed images are determined, one frame is moved backward, for (N) 1 +1,N 1 +2,N 1 +3) the extracted splatters in the three groups of continuously shot images are newly combined, judged and identified until the splatter movement track of the whole welding process is tracked.
4) The acquired splash movement track is checked again, and the flow is shown in fig. 3:
after completing the tracking of the splash movement track in the whole welding process, the splash movement track M is extracted i Checking when any two groups M i And M j When the following criterion is satisfied, it is considered that the same splash movement trajectory is interrupted by the lack of splash at the individual time points. The judgment criteria are as follows:
a) The average size of the splash of the motion trail is consistent. I.e.
Is the motion trail m i Average size of the contained splashes, S 0 The allowable error for the identified splash size.
In the present embodiment, the size allowance error is set to
b) The movement directions of the splash movement tracks are consistent. The angles of the motion tracks are consistent, namely:
and
wherein (1)>
And->
Respectively the motion trail m i Azimuth angles projected in the spatial planes XOZ and YOZ. Δα and Δβ are the projected azimuth angle allowable errors, respectively, and are set to 5 ° in the present embodiment. />
c) The movement distance of the splash movement track in each frame interval time is consistent, namely:
wherein, the liquid crystal display device comprises a liquid crystal display device,
is the motion trail m i Average distance between each splash, ΔL 0 The allowable error of the distance of movement per frame interval Δt is the identified splatter. In the present embodiment, the movement distance allowable error is set as: />
d) The distance between the first splatters in the motion profile is proportional to the time interval. I.e.
Wherein DeltaL mi,mj And Deltat mi,mj Respectively the motion trail m i And m j The distance between the first splatters and the time interval between the images, Δt is the interval time between each frame.
The combination of the motion trajectories with different serial numbers meeting the four judgment criteria can be considered to be caused by the lack of recognition of a certain splash in the middle, and the motion trajectories with the same splash at different moments can be re-unified into the motion trajectories with the same splash at different moments through the criteria.
And acquiring the movement characteristics of the splash movement track after the re-inspection. The speed can be calculated as:
wherein (1)>
And->
And the movement distance between adjacent frames and the projection of the movement distance on the x axis, the y axis and the z axis, which are respectively corresponding to the splash in the movement track.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention without requiring creative effort by one of ordinary skill in the art. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (6)
1. The method for recognizing and tracking the splashing of the three-dimensional space in the laser welding process is characterized by comprising the following steps:
step 1: acquiring a splash three-dimensional image;
step 2: extracting the splash three-dimensional space characteristics;
step 3: positioning and tracking the splash flight trajectory;
wherein, the step 3 comprises the following steps:
step 31: grouping and recombining the splatters: identifying and evaluating based on 3 groups of continuously shot images, wherein each group of images is used for acquiring splashes, and each group of images is selected from one splash and combined three by three;
step 32: each set of splatters was evaluated: evaluating each group of splash combinations in sequence according to a first judgment criterion, wherein the first judgment criterion comprises: whether the sizes of the splashes in the combination are consistent, whether the movement directions of the splashes in the combination are consistent, and the movement distances of the splashes in the combination in each frame of interval are equal;
step 33: correlating the motion trail of the splash combination meeting the first judgment criterion: when the size characteristics and the space position of the splashes in the combination meet the first judgment criterion, judging that the splashes are part of the movement tracks of the same splashes at different moments;
step 34: rechecking the acquired splash movement track: and (3) combining the motion trail with different serial numbers meeting the second judgment criterion, re-unifying the motion trail with the same splash motion trail at different moments, and acquiring the motion characteristics of the splash motion trail after re-inspection.
2. The method for three-dimensional space spatter identification and tracking during laser welding according to claim 1, wherein said step 1 acquires images of said spatter XOZ and YOZ planes simultaneously.
3. The method for three-dimensional space splash identification and tracking during laser welding according to claim 2, wherein said step 1 further comprises the step of enhancing said acquired image:
step 11: setting a local processing area;
step 12: filtering the local processing area;
step 13: moving the local processing area by m pixel points;
step 14: repeating the step 12 and the step 13 until the whole image area, and carrying out reinforced average on the images processed in each local processing area to obtain reinforced images;
step 15: and carrying out binarization processing and image segmentation on the enhanced image to obtain the splash shape and position characteristics in the image.
4. The method for three-dimensional space splash identification and tracking in laser welding process according to claim 3, wherein said step 12 filterThe parameter is defined by the maximum brightness value T in the local processing region 1 Mean value T 2 The specific functions of the filter are determined as follows:
wherein I is 0 For the luminance value of the image in the local processing region, I 1 For the brightness value of the local processing area after processing, deltaS 1 Is a threshold value of the difference between the splash brightness and the plume brightness, S 2 Is a threshold value of the set plume brightness.
5. The method for recognizing and tracking the spatter in the three-dimensional space during the laser welding according to claim 3, wherein the step 2 is configured to perform one-to-one correlation on the spatter location features obtained from the images of the XOZ and YOZ planes obtained at the same time, and extract the area size features of the spatter in the XOZ plane and the three-dimensional space location features thereof.
6. The method for identifying and tracking the spatter in a three-dimensional space during a laser welding process according to claim 5, wherein the second criterion is that the following conditions are satisfied at the same time: the average sizes of the splash of the motion trajectories are consistent, the motion directions of the splash motion trajectories are consistent, the motion distances of the splash motion trajectories in each frame interval time are consistent, and the distance between the first splashes in the motion trajectories is in direct proportion to the time interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010048245.7A CN111242979B (en) | 2020-01-16 | 2020-01-16 | Method for recognizing and tracking splashing of three-dimensional space in laser welding process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010048245.7A CN111242979B (en) | 2020-01-16 | 2020-01-16 | Method for recognizing and tracking splashing of three-dimensional space in laser welding process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111242979A CN111242979A (en) | 2020-06-05 |
| CN111242979B true CN111242979B (en) | 2023-05-12 |
Family
ID=70872706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010048245.7A Active CN111242979B (en) | 2020-01-16 | 2020-01-16 | Method for recognizing and tracking splashing of three-dimensional space in laser welding process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242979B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114905738B (en) * | 2022-02-18 | 2023-03-31 | 中国地质大学（武汉） | Method for in-situ measurement of splashing dynamics behavior in laser additive manufacturing |
| CN116493735B (en) * | 2023-06-29 | 2023-09-12 | 武汉纺织大学 | Real-time tracking method for motion splash in Wanwave-level ultra-high power laser welding process |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE69917728D1 (en) * | 1998-09-21 | 2004-07-08 | Lincoln Global Inc | Method for controlling a welding process and control |
| CN109990834A (en) * | 2019-03-27 | 2019-07-09 | 东南大学 | High-temperature flight particle temperature, speed, partial size in-situ measuring method |
-
2020
- 2020-01-16 CN CN202010048245.7A patent/CN111242979B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE69917728D1 (en) * | 1998-09-21 | 2004-07-08 | Lincoln Global Inc | Method for controlling a welding process and control |
| CN109990834A (en) * | 2019-03-27 | 2019-07-09 | 东南大学 | High-temperature flight particle temperature, speed, partial size in-situ measuring method |
Non-Patent Citations (2)
| Title |
|---|
| Jiazhou Wu.3D Multiphysical Modelling of Fluid Dynamics and Mass Transfer in Laser Welding of Dissimilar Materials.《RessearchGate》.2018,1-15. * |
| 王腾.基于等离子体特征信号的激光焊接过程动态监控技术研究进展.《河北科技大学学报》.2017,1-6. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111242979A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242979B (en) | Method for recognizing and tracking splashing of three-dimensional space in laser welding process | |
| CN106204614B (en) | A kind of workpiece appearance defects detection method based on machine vision | |
| CN111192307B (en) | Self-adaptive deviation rectifying method based on laser cutting of three-dimensional part | |
| CN104636760B (en) | A kind of localization method of weld seam | |
| CN108559995B (en) | A kind of method of laser cladding technological parameter optimization in plane | |
| CN109483018A (en) | The active vision bootstrap technique of weld seam in automatic welding of pipelines | |
| CN105033408A (en) | Double passive vision sensing detecting device in GMA material increase manufacturing and detecting method thereof | |
| Guo et al. | Weld deviation detection based on wide dynamic range vision sensor in MAG welding process | |
| CN111203639B (en) | Double-laser-beam bilateral synchronous welding filler wire molten drop transition monitoring system and method based on high-speed camera shooting | |
| CN108931535A (en) | A kind of laser gain material manufacture gas hole defect on-line monitoring method | |
| CN112991338B (en) | Defect detection method and device for laser cutting part | |
| CN113369697B (en) | Laser polishing online detection system and method | |
| CN109108518A (en) | A kind of online test method and device of Laser Welding hump defect | |
| DE102007032190A1 (en) | Method for treating the surface of a workpiece using heat comprises analyzing image signals in pixels and identifying an object based on shade gradients from which a geometric property can be determined | |
| CN116493735B (en) | Real-time tracking method for motion splash in Wanwave-level ultra-high power laser welding process | |
| CN105023018A (en) | Jet code detection method and system | |
| CN111203655B (en) | Three-dimensional space spattering recognition device in laser welding process | |
| CN113487570B (en) | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model | |
| CN112184820B (en) | Laser double-sided shot blasting spot positioning method and system and computer readable storage medium | |
| CN109470162B (en) | Intelligent detection system and method for micropore shape of oil nozzle based on machine vision | |
| CN209550915U (en) | A kind of on-line measuring device of the Laser Welding hump defect based on image procossing | |
| JP2010260095A (en) | Method and apparatus for evaluating laser welding quality | |
| CN108705689A (en) | Heavy caliber precision optics plane of crystal microdefect reparation automatic tool preset process | |
| CN210281077U (en) | Real-time identification device for narrow-gap laser welding deviation state | |
| Zheng et al. | Measurement of laser welding pool geometry using a closed convex active contour model |
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 |